miguel.horta/commandergenius
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

SDL: updated libiconv and libicu, removed prebuilt binaries, now they should be built on the fly

Browse Source
This commit is contained in:
Sergii Pylypenko
2017-06-21 17:48:55 +03:00
parent 2efd15f6b5
commit d89960517c
231 changed files with 16 additions and 104127 deletions
Download Patch File Download Diff File Expand all files Collapse all files
project/jni/Makefile.prebuilt
+10 -9
View File
@@ -1,13 +1,13 @@
# Makefile to build precompiled libraries, which cannot be built using standard NDK makefiles
# TODO: libboost, libffmpeg, libpython (used only in GemRB)
ARCHES32 := armeabi armeabi-v7a x86 mips
ARCHES32 := armeabi-v7a x86
ARCHES64 := arm64-v8a x86_64
ICONV := $(foreach ARCH, $(ARCHES32), iconv/lib/$(ARCH)/libiconv.so iconv/lib/$(ARCH)/libcharset.so)
ICONV := $(foreach ARCH, $(ARCHES32) $(ARCHES64), iconv/lib/$(ARCH)/libiconv.so iconv/lib/$(ARCH)/libcharset.so)
ICU_LIBS := data i18n io le lx test tu uc
ICU := $(foreach ARCH, $(ARCHES32), $(foreach NAME, $(ICU_LIBS), icuuc/lib/$(ARCH)/libicu$(NAME).a))
ICU_LIBS := icudata icui18n icuio icutest icutu icuuc iculx icu-le-hb harfbuzz
ICU := $(foreach ARCH, $(ARCHES32) $(ARCHES64), $(foreach NAME, $(ICU_LIBS), icuuc/lib/$(ARCH)/lib$(NAME).a))
OPENSSL := $(foreach ARCH, $(ARCHES32) $(ARCHES64), openssl/lib-$(ARCH)/libcrypto.so.sdl.1.so openssl/lib-$(ARCH)/libssl.so.sdl.1.so)
@@ -20,14 +20,15 @@ prebuilt-libraries: $(LIBS)
$(ICONV) $(ICU):
cd iconv/src && \
./build.sh && \
for ARCH in $(ARCHES32); do \
mkdir -p ../lib/$$ARCH ; \
for ARCH in $(ARCHES32) $(ARCHES64); do \
mkdir -p ../lib/$$ARCH ../include ; \
cp -f $$ARCH/libiconv.so $$ARCH/libcharset.so ../lib/$$ARCH/ ; \
cp -f $$ARCH/include/*.h ../include/ ; \
mkdir -p ../../icuuc/lib/$$ARCH ../../icuuc/include/layout ../../icuuc/include/unicode ; \
cp -f $$ARCH/libicu*.a ../../icuuc/lib/$$ARCH/ ; \
cp -f $$ARCH/include/layout/*.h ../../icuuc/include/layout/ ; \
mkdir -p ../../icuuc/lib/$$ARCH ../../icuuc/include/unicode ../../icuuc/include/layout ; \
cp -f $$ARCH/libicu*.a $$ARCH/libharfbuzz.a ../../icuuc/lib/$$ARCH/ ; \
cp -f $$ARCH/include/unicode/*.h ../../icuuc/include/unicode/ ; \
cp -f $$ARCH/include/layout/*.h ../../icuuc/include/layout/ ; \
cp -f $$ARCH/include/icu-le-hb/layout/*.h ../../icuuc/include/layout/ ; \
done
$(OPENSSL):
project/jni/icule → project/jni/harfbuzz
View File
project/jni/iconv/Android.mk
+2 -11
View File
@@ -2,20 +2,11 @@ LOCAL_PATH := $(call my-dir)
include $(CLEAR_VARS)
ifneq ($(TARGET_ARCH_ABI),armeabi-v7a-hard) # Pre-compiled lib disabled for armhf ABI
ifneq ($(TARGET_ARCH_ABI),arm64-v8a) # Not supported yet
ifneq ($(TARGET_ARCH_ABI),x86_64) # Not supported yet
ifneq ($(TARGET_ARCH_ABI),mips64) # Not supported yet
LOCAL_MODULE := $(notdir $(LOCAL_PATH))
LOCAL_C_INCLUDES := $(LOCAL_PATH)/include
LOCAL_C_INCLUDES := $(LOCAL_PATH)/$(NDK_TOOLCHAIN_VERSION)/include
LOCAL_SRC_FILES := lib/$(TARGET_ARCH_ABI)/lib$(LOCAL_MODULE).so
LOCAL_SRC_FILES := lib/$(TARGET_ARCH_ABI)/$(NDK_TOOLCHAIN_VERSION)/lib$(LOCAL_MODULE).so
include $(PREBUILT_SHARED_LIBRARY)
endif
endif
endif
endif
project/jni/iconv/include/iconv.h
-242
View File
@@ -1,242 +0,0 @@
/* Copyright (C) 1999-2003, 2005-2006, 2008-2011 Free Software Foundation, Inc.
This file is part of the GNU LIBICONV Library.
The GNU LIBICONV Library is free software; you can redistribute it
and/or modify it under the terms of the GNU Library General Public
License as published by the Free Software Foundation; either version 2
of the License, or (at your option) any later version.
The GNU LIBICONV Library is distributed in the hope that it will be
useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with the GNU LIBICONV Library; see the file COPYING.LIB.
If not, write to the Free Software Foundation, Inc., 51 Franklin Street,
Fifth Floor, Boston, MA 02110-1301, USA. */
/* When installed, this file is called "iconv.h". */
#ifndef _LIBICONV_H
#define _LIBICONV_H
#define _LIBICONV_VERSION 0x010E /* version number: (major<<8) + minor */
extern int _libiconv_version; /* Likewise */
/* We would like to #include any system header file which could define
iconv_t, 1. in order to eliminate the risk that the user gets compilation
errors because some other system header file includes /usr/include/iconv.h
which defines iconv_t or declares iconv after this file, 2. when compiling
for LIBICONV_PLUG, we need the proper iconv_t type in order to produce
binary compatible code.
But gcc's #include_next is not portable. Thus, once libiconv's iconv.h
has been installed in /usr/local/include, there is no way any more to
include the original /usr/include/iconv.h. We simply have to get away
without it.
Ad 1. The risk that a system header file does
#include "iconv.h" or #include_next "iconv.h"
is small. They all do #include <iconv.h>.
Ad 2. The iconv_t type is a pointer type in all cases I have seen. (It
has to be a scalar type because (iconv_t)(-1) is a possible return value
from iconv_open().) */
/* Define iconv_t ourselves. */
#undef iconv_t
#define iconv_t libiconv_t
typedef void* iconv_t;
/* Get size_t declaration.
Get wchar_t declaration if it exists. */
#include <stddef.h>
/* Get errno declaration and values. */
#include <errno.h>
/* Some systems, like SunOS 4, don't have EILSEQ. Some systems, like BSD/OS,
have EILSEQ in a different header. On these systems, define EILSEQ
ourselves. */
#ifndef EILSEQ
#define EILSEQ
#endif
#ifdef __cplusplus
extern "C" {
#endif
/* Allocates descriptor for code conversion from encoding ‘fromcode’ to
encoding ‘tocode’. */
#ifndef LIBICONV_PLUG
#define iconv_open libiconv_open
#endif
extern iconv_t iconv_open (const char* tocode, const char* fromcode);
/* Converts, using conversion descriptor ‘cd’, at most ‘*inbytesleft’ bytes
starting at ‘*inbuf’, writing at most ‘*outbytesleft’ bytes starting at
‘*outbuf’.
Decrements ‘*inbytesleft’ and increments ‘*inbuf’ by the same amount.
Decrements ‘*outbytesleft’ and increments ‘*outbuf’ by the same amount. */
#ifndef LIBICONV_PLUG
#define iconv libiconv
#endif
extern size_t iconv (iconv_t cd, char* * inbuf, size_t *inbytesleft, char* * outbuf, size_t *outbytesleft);
/* Frees resources allocated for conversion descriptor ‘cd’. */
#ifndef LIBICONV_PLUG
#define iconv_close libiconv_close
#endif
extern int iconv_close (iconv_t cd);
#ifdef __cplusplus
}
#endif
#ifndef LIBICONV_PLUG
/* Nonstandard extensions. */
#if 1
#if 0
/* Tru64 with Desktop Toolkit C has a bug: <stdio.h> must be included before
<wchar.h>.
BSD/OS 4.0.1 has a bug: <stddef.h>, <stdio.h> and <time.h> must be
included before <wchar.h>. */
#include <stddef.h>
#include <stdio.h>
#include <time.h>
#endif
#include <wchar.h>
#endif
#ifdef __cplusplus
extern "C" {
#endif
/* A type that holds all memory needed by a conversion descriptor.
A pointer to such an object can be used as an iconv_t. */
typedef struct {
void* dummy1[28];
#if 1
mbstate_t dummy2;
#endif
} iconv_allocation_t;
/* Allocates descriptor for code conversion from encoding ‘fromcode’ to
encoding ‘tocode’ into preallocated memory. Returns an error indicator
(0 or -1 with errno set). */
#define iconv_open_into libiconv_open_into
extern int iconv_open_into (const char* tocode, const char* fromcode,
iconv_allocation_t* resultp);
/* Control of attributes. */
#define iconvctl libiconvctl
extern int iconvctl (iconv_t cd, int request, void* argument);
/* Hook performed after every successful conversion of a Unicode character. */
typedef void (*iconv_unicode_char_hook) (unsigned int uc, void* data);
/* Hook performed after every successful conversion of a wide character. */
typedef void (*iconv_wide_char_hook) (wchar_t wc, void* data);
/* Set of hooks. */
struct iconv_hooks {
iconv_unicode_char_hook uc_hook;
iconv_wide_char_hook wc_hook;
void* data;
};
/* Fallback function. Invoked when a small number of bytes could not be
converted to a Unicode character. This function should process all
bytes from inbuf and may produce replacement Unicode characters by calling
the write_replacement callback repeatedly. */
typedef void (*iconv_unicode_mb_to_uc_fallback)
(const char* inbuf, size_t inbufsize,
void (*write_replacement) (const unsigned int *buf, size_t buflen,
void* callback_arg),
void* callback_arg,
void* data);
/* Fallback function. Invoked when a Unicode character could not be converted
to the target encoding. This function should process the character and
may produce replacement bytes (in the target encoding) by calling the
write_replacement callback repeatedly. */
typedef void (*iconv_unicode_uc_to_mb_fallback)
(unsigned int code,
void (*write_replacement) (const char *buf, size_t buflen,
void* callback_arg),
void* callback_arg,
void* data);
#if 1
/* Fallback function. Invoked when a number of bytes could not be converted to
a wide character. This function should process all bytes from inbuf and may
produce replacement wide characters by calling the write_replacement
callback repeatedly. */
typedef void (*iconv_wchar_mb_to_wc_fallback)
(const char* inbuf, size_t inbufsize,
void (*write_replacement) (const wchar_t *buf, size_t buflen,
void* callback_arg),
void* callback_arg,
void* data);
/* Fallback function. Invoked when a wide character could not be converted to
the target encoding. This function should process the character and may
produce replacement bytes (in the target encoding) by calling the
write_replacement callback repeatedly. */
typedef void (*iconv_wchar_wc_to_mb_fallback)
(wchar_t code,
void (*write_replacement) (const char *buf, size_t buflen,
void* callback_arg),
void* callback_arg,
void* data);
#else
/* If the wchar_t type does not exist, these two fallback functions are never
invoked. Their argument list therefore does not matter. */
typedef void (*iconv_wchar_mb_to_wc_fallback) ();
typedef void (*iconv_wchar_wc_to_mb_fallback) ();
#endif
/* Set of fallbacks. */
struct iconv_fallbacks {
iconv_unicode_mb_to_uc_fallback mb_to_uc_fallback;
iconv_unicode_uc_to_mb_fallback uc_to_mb_fallback;
iconv_wchar_mb_to_wc_fallback mb_to_wc_fallback;
iconv_wchar_wc_to_mb_fallback wc_to_mb_fallback;
void* data;
};
/* Requests for iconvctl. */
#define ICONV_TRIVIALP 0 /* int *argument */
#define ICONV_GET_TRANSLITERATE 1 /* int *argument */
#define ICONV_SET_TRANSLITERATE 2 /* const int *argument */
#define ICONV_GET_DISCARD_ILSEQ 3 /* int *argument */
#define ICONV_SET_DISCARD_ILSEQ 4 /* const int *argument */
#define ICONV_SET_HOOKS 5 /* const struct iconv_hooks *argument */
#define ICONV_SET_FALLBACKS 6 /* const struct iconv_fallbacks *argument */
/* Listing of locale independent encodings. */
#define iconvlist libiconvlist
extern void iconvlist (int (*do_one) (unsigned int namescount,
const char * const * names,
void* data),
void* data);
/* Canonicalize an encoding name.
The result is either a canonical encoding name, or name itself. */
extern const char * iconv_canonicalize (const char * name);
/* Support for relocatable packages. */
/* Sets the original and the current installation prefix of the package.
Relocation simply replaces a pathname starting with the original prefix
by the corresponding pathname with the current prefix instead. Both
prefixes should be directory names without trailing slash (i.e. use ""
instead of "/"). */
extern void libiconv_set_relocation_prefix (const char *orig_prefix,
const char *curr_prefix);
#ifdef __cplusplus
}
#endif
#endif
#endif /* _LIBICONV_H */
project/jni/iconv/include/libcharset.h
-46
View File
@@ -1,46 +0,0 @@
/* Copyright (C) 2003 Free Software Foundation, Inc.
This file is part of the GNU CHARSET Library.
The GNU CHARSET Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Library General Public License as
published by the Free Software Foundation; either version 2 of the
License, or (at your option) any later version.
The GNU CHARSET Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Library General Public License for more details.
You should have received a copy of the GNU Library General Public License
along with the GNU CHARSET Library; see the file COPYING.LIB. If not,
write to the Free Software Foundation, Inc., 51 Franklin Street,
Fifth Floor, Boston, MA 02110-1301, USA. */
#ifndef _LIBCHARSET_H
#define _LIBCHARSET_H
#include <localcharset.h>
#ifdef __cplusplus
extern "C" {
#endif
/* Support for relocatable packages. */
/* Sets the original and the current installation prefix of the package.
Relocation simply replaces a pathname starting with the original prefix
by the corresponding pathname with the current prefix instead. Both
prefixes should be directory names without trailing slash (i.e. use ""
instead of "/"). */
extern void libcharset_set_relocation_prefix (const char *orig_prefix,
const char *curr_prefix);
#ifdef __cplusplus
}
#endif
#endif /* _LIBCHARSET_H */
project/jni/iconv/include/localcharset.h
-42
View File
@@ -1,42 +0,0 @@
/* Determine a canonical name for the current locale's character encoding.
Copyright (C) 2000-2003 Free Software Foundation, Inc.
This file is part of the GNU CHARSET Library.
This program is free software; you can redistribute it and/or modify it
under the terms of the GNU Library General Public License as published
by the Free Software Foundation; either version 2, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Library General Public License for more details.
You should have received a copy of the GNU Library General Public
License along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301,
USA. */
#ifndef _LOCALCHARSET_H
#define _LOCALCHARSET_H
#ifdef __cplusplus
extern "C" {
#endif
/* Determine the current locale's character encoding, and canonicalize it
into one of the canonical names listed in config.charset.
The result must not be freed; it is statically allocated.
If the canonical name cannot be determined, the result is a non-canonical
name. */
extern const char * locale_charset (void);
#ifdef __cplusplus
}
#endif
#endif /* _LOCALCHARSET_H */
project/jni/iconv/lib/armeabi-v7a/libcharset.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/armeabi-v7a/libiconv.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/armeabi/libcharset.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/armeabi/libiconv.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/mips/libcharset.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/mips/libiconv.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/x86/libcharset.so
BIN
View File
Binary file not shown.
project/jni/iconv/lib/x86/libiconv.so
BIN
View File
Binary file not shown.
project/jni/iconv/src
+1 -1
Submodule project/jni/iconv/src updated: a6a6531070...48bca80cd2
project/jni/icu-le-hb
Symlink
+1
View File
@@ -0,0 +1 @@
icuuc
project/jni/icuuc/Android.mk
-10
View File
@@ -2,11 +2,6 @@ LOCAL_PATH := $(call my-dir)
include $(CLEAR_VARS)
ifneq ($(TARGET_ARCH_ABI),armeabi-v7a-hard) # Pre-compiled lib disabled for armhf ABI
ifneq ($(TARGET_ARCH_ABI),arm64-v8a) # Not supported yet
ifneq ($(TARGET_ARCH_ABI),x86_64) # Not supported yet
ifneq ($(TARGET_ARCH_ABI),mips64) # Not supported yet
LOCAL_MODULE := $(notdir $(LOCAL_PATH))
LOCAL_C_INCLUDES := $(LOCAL_PATH)/include
@@ -18,8 +13,3 @@ obj/local/$(TARGET_ARCH_ABI)/lib$(LOCAL_MODULE).a: $(LOCAL_PATH)/$(LOCAL_SRC_FIL
cp -f $< $@
include $(PREBUILT_STATIC_LIBRARY)
endif
endif
endif
endif
project/jni/icuuc/icudt52l.zip
BIN
View File
Binary file not shown.
project/jni/icuuc/include/layout/LEFontInstance.h
-550
View File
@@ -1,550 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2013 - All Rights Reserved
*
*/
#ifndef __LEFONTINSTANCE_H
#define __LEFONTINSTANCE_H
#include "LETypes.h"
/**
* \file
* \brief C++ API: Layout Engine Font Instance object
*/
U_NAMESPACE_BEGIN
/**
* Instances of this class are used by <code>LEFontInstance::mapCharsToGlyphs</code> and
* <code>LEFontInstance::mapCharToGlyph</code> to adjust character codes before the character
* to glyph mapping process. Examples of this are filtering out control characters
* and character mirroring - replacing a character which has both a left and a right
* hand form with the opposite form.
*
* @stable ICU 3.2
*/
class LECharMapper /* not : public UObject because this is an interface/mixin class */
{
public:
/**
* Destructor.
* @stable ICU 3.2
*/
virtual ~LECharMapper();
/**
* This method does the adjustments.
*
* @param ch - the input character
*
* @return the adjusted character
*
* @stable ICU 2.8
*/
virtual LEUnicode32 mapChar(LEUnicode32 ch) const = 0;
};
/**
* This is a forward reference to the class which holds the per-glyph
* storage.
*
* @stable ICU 3.0
*/
class LEGlyphStorage;
/**
* This is a virtual base class that serves as the interface between a LayoutEngine
* and the platform font environment. It allows a LayoutEngine to access font tables, do
* character to glyph mapping, and obtain metrics information without knowing any platform
* specific details. There are also a few utility methods for converting between points,
* pixels and funits. (font design units)
*
* An instance of an <code>LEFontInstance</code> represents a font at a particular point
* size. Each instance can represent either a single physical font, or a composite font.
* A composite font is a collection of physical fonts, each of which contains a subset of
* the characters contained in the composite font.
*
* Note: with the exception of <code>getSubFont</code>, the methods in this class only
* make sense for a physical font. If you have an <code>LEFontInstance</code> which
* represents a composite font you should only call the methods below which have
* an <code>LEGlyphID</code>, an <code>LEUnicode</code> or an <code>LEUnicode32</code>
* as one of the arguments because these can be used to select a particular subfont.
*
* Subclasses which implement composite fonts should supply an implementation of these
* methods with some default behavior such as returning constant values, or using the
* values from the first subfont.
*
* @stable ICU 3.0
*/
class U_LAYOUT_API LEFontInstance : public UObject
{
public:
/**
* This virtual destructor is here so that the subclass
* destructors can be invoked through the base class.
*
* @stable ICU 2.8
*/
virtual ~LEFontInstance();
/**
* Get a physical font which can render the given text. For composite fonts,
* if there is no single physical font which can render all of the text,
* return a physical font which can render an initial substring of the text,
* and set the <code>offset</code> parameter to the end of that substring.
*
* Internally, the LayoutEngine works with runs of text all in the same
* font and script, so it is best to call this method with text which is
* in a single script, passing the script code in as a hint. If you don't
* know the script of the text, you can use zero, which is the script code
* for characters used in more than one script.
*
* The default implementation of this method is intended for instances of
* <code>LEFontInstance</code> which represent a physical font. It returns
* <code>this</code> and indicates that the entire string can be rendered.
*
* This method will return a valid <code>LEFontInstance</code> unless you
* have passed illegal parameters, or an internal error has been encountered.
* For composite fonts, it may return the warning <code>LE_NO_SUBFONT_WARNING</code>
* to indicate that the returned font may not be able to render all of
* the text. Whenever a valid font is returned, the <code>offset</code> parameter
* will be advanced by at least one.
*
* Subclasses which implement composite fonts must override this method.
* Where it makes sense, they should use the script code as a hint to render
* characters from the COMMON script in the font which is used for the given
* script. For example, if the input text is a series of Arabic words separated
* by spaces, and the script code passed in is <code>arabScriptCode</code> you
* should return the font used for Arabic characters for all of the input text,
* including the spaces. If, on the other hand, the input text contains characters
* which cannot be rendered by the font used for Arabic characters, but which can
* be rendered by another font, you should return that font for those characters.
*
* @param chars - the array of Unicode characters.
* @param offset - a pointer to the starting offset in the text. On exit this
* will be set the the limit offset of the text which can be
* rendered using the returned font.
* @param limit - the limit offset for the input text.
* @param script - the script hint.
* @param success - set to an error code if the arguments are illegal, or no font
* can be returned for some reason. May also be set to
* <code>LE_NO_SUBFONT_WARNING</code> if the subfont which
* was returned cannot render all of the text.
*
* @return an <code>LEFontInstance</code> for the sub font which can render the characters, or
* <code>NULL</code> if there is an error.
*
* @see LEScripts.h
*
* @stable ICU 3.2
*/
virtual const LEFontInstance *getSubFont(const LEUnicode chars[], le_int32 *offset, le_int32 limit, le_int32 script, LEErrorCode &success) const;
//
// Font file access
//
/**
* This method reads a table from the font. Note that in general,
* it only makes sense to call this method on an <code>LEFontInstance</code>
* which represents a physical font - i.e. one which has been returned by
* <code>getSubFont()</code>. This is because each subfont in a composite font
* will have different tables, and there's no way to know which subfont to access.
*
* Subclasses which represent composite fonts should always return <code>NULL</code>.
*
* Note that implementing this function does not allow for range checking.
* Subclasses that desire the safety of range checking must implement the
* variation which has a length parameter.
*
* @param tableTag - the four byte table tag. (e.g. 'cmap')
*
* @return the address of the table in memory, or <code>NULL</code>
* if the table doesn't exist.
*
* @stable ICU 2.8
*/
virtual const void *getFontTable(LETag tableTag) const = 0;
/**
* This method reads a table from the font. Note that in general,
* it only makes sense to call this method on an <code>LEFontInstance</code>
* which represents a physical font - i.e. one which has been returned by
* <code>getSubFont()</code>. This is because each subfont in a composite font
* will have different tables, and there's no way to know which subfont to access.
*
* Subclasses which represent composite fonts should always return <code>NULL</code>.
*
* This version sets a length, for range checking.
* Note that range checking can only be accomplished if this function is
* implemented in subclasses.
*
* @param tableTag - the four byte table tag. (e.g. 'cmap')
* @param length - ignored on entry, on exit will be the length of the table if known, or -1 if unknown.
* @return the address of the table in memory, or <code>NULL</code>
* if the table doesn't exist.
* @draft ICU 52
*/
virtual const void* getFontTable(LETag tableTag, size_t &length) const { length=-1; return getFontTable(tableTag); } /* -1 = unknown length */
/**
* This method is used to determine if the font can
* render the given character. This can usually be done
* by looking the character up in the font's character
* to glyph mapping.
*
* The default implementation of this method will return
* <code>TRUE</code> if <code>mapCharToGlyph(ch)</code>
* returns a non-zero value.
*
* @param ch - the character to be tested
*
* @return <code>TRUE</code> if the font can render ch.
*
* @stable ICU 3.2
*/
virtual le_bool canDisplay(LEUnicode32 ch) const;
/**
* This method returns the number of design units in
* the font's EM square.
*
* @return the number of design units pre EM.
*
* @stable ICU 2.8
*/
virtual le_int32 getUnitsPerEM() const = 0;
/**
* This method maps an array of character codes to an array of glyph
* indices, using the font's character to glyph map.
*
* The default implementation iterates over all of the characters and calls
* <code>mapCharToGlyph(ch, mapper)</code> on each one. It also handles surrogate
* characters, storing the glyph ID for the high surrogate, and a deleted glyph (0xFFFF)
* for the low surrogate.
*
* Most sublcasses will not need to implement this method.
*
* @param chars - the character array
* @param offset - the index of the first character
* @param count - the number of characters
* @param reverse - if <code>TRUE</code>, store the glyph indices in reverse order.
* @param mapper - the character mapper.
* @param filterZeroWidth - <code>TRUE</code> if ZWJ / ZWNJ characters should map to a glyph w/ no contours.
* @param glyphStorage - the object which contains the output glyph array
*
* @see LECharMapper
*
* @stable ICU 3.6
*/
virtual void mapCharsToGlyphs(const LEUnicode chars[], le_int32 offset, le_int32 count, le_bool reverse, const LECharMapper *mapper, le_bool filterZeroWidth, LEGlyphStorage &glyphStorage) const;
/**
* This method maps a single character to a glyph index, using the
* font's character to glyph map. The default implementation of this
* method calls the mapper, and then calls <code>mapCharToGlyph(mappedCh)</code>.
*
* @param ch - the character
* @param mapper - the character mapper
* @param filterZeroWidth - <code>TRUE</code> if ZWJ / ZWNJ characters should map to a glyph w/ no contours.
*
* @return the glyph index
*
* @see LECharMapper
*
* @stable ICU 3.6
*/
virtual LEGlyphID mapCharToGlyph(LEUnicode32 ch, const LECharMapper *mapper, le_bool filterZeroWidth) const;
/**
* This method maps a single character to a glyph index, using the
* font's character to glyph map. The default implementation of this
* method calls the mapper, and then calls <code>mapCharToGlyph(mappedCh)</code>.
*
* @param ch - the character
* @param mapper - the character mapper
*
* @return the glyph index
*
* @see LECharMapper
*
* @stable ICU 3.2
*/
virtual LEGlyphID mapCharToGlyph(LEUnicode32 ch, const LECharMapper *mapper) const;
/**
* This method maps a single character to a glyph index, using the
* font's character to glyph map. There is no default implementation
* of this method because it requires information about the platform
* font implementation.
*
* @param ch - the character
*
* @return the glyph index
*
* @stable ICU 3.2
*/
virtual LEGlyphID mapCharToGlyph(LEUnicode32 ch) const = 0;
//
// Metrics
//
/**
* This method gets the X and Y advance of a particular glyph, in pixels.
*
* @param glyph - the glyph index
* @param advance - the X and Y pixel values will be stored here
*
* @stable ICU 3.2
*/
virtual void getGlyphAdvance(LEGlyphID glyph, LEPoint &advance) const = 0;
/**
* This method gets the hinted X and Y pixel coordinates of a particular
* point in the outline of the given glyph.
*
* @param glyph - the glyph index
* @param pointNumber - the number of the point
* @param point - the point's X and Y pixel values will be stored here
*
* @return <code>TRUE</code> if the point coordinates could be stored.
*
* @stable ICU 2.8
*/
virtual le_bool getGlyphPoint(LEGlyphID glyph, le_int32 pointNumber, LEPoint &point) const = 0;
/**
* This method returns the width of the font's EM square
* in pixels.
*
* @return the pixel width of the EM square
*
* @stable ICU 2.8
*/
virtual float getXPixelsPerEm() const = 0;
/**
* This method returns the height of the font's EM square
* in pixels.
*
* @return the pixel height of the EM square
*
* @stable ICU 2.8
*/
virtual float getYPixelsPerEm() const = 0;
/**
* This method converts font design units in the
* X direction to points.
*
* @param xUnits - design units in the X direction
*
* @return points in the X direction
*
* @stable ICU 3.2
*/
virtual float xUnitsToPoints(float xUnits) const;
/**
* This method converts font design units in the
* Y direction to points.
*
* @param yUnits - design units in the Y direction
*
* @return points in the Y direction
*
* @stable ICU 3.2
*/
virtual float yUnitsToPoints(float yUnits) const;
/**
* This method converts font design units to points.
*
* @param units - X and Y design units
* @param points - set to X and Y points
*
* @stable ICU 3.2
*/
virtual void unitsToPoints(LEPoint &units, LEPoint &points) const;
/**
* This method converts pixels in the
* X direction to font design units.
*
* @param xPixels - pixels in the X direction
*
* @return font design units in the X direction
*
* @stable ICU 3.2
*/
virtual float xPixelsToUnits(float xPixels) const;
/**
* This method converts pixels in the
* Y direction to font design units.
*
* @param yPixels - pixels in the Y direction
*
* @return font design units in the Y direction
*
* @stable ICU 3.2
*/
virtual float yPixelsToUnits(float yPixels) const;
/**
* This method converts pixels to font design units.
*
* @param pixels - X and Y pixel
* @param units - set to X and Y font design units
*
* @stable ICU 3.2
*/
virtual void pixelsToUnits(LEPoint &pixels, LEPoint &units) const;
/**
* Get the X scale factor from the font's transform. The default
* implementation of <code>transformFunits()</code> will call this method.
*
* @return the X scale factor.
*
*
* @see transformFunits
*
* @stable ICU 3.2
*/
virtual float getScaleFactorX() const = 0;
/**
* Get the Y scale factor from the font's transform. The default
* implementation of <code>transformFunits()</code> will call this method.
*
* @return the Yscale factor.
*
* @see transformFunits
*
* @stable ICU 3.2
*/
virtual float getScaleFactorY() const = 0;
/**
* This method transforms an X, Y point in font design units to a
* pixel coordinate, applying the font's transform. The default
* implementation of this method calls <code>getScaleFactorX()</code>
* and <code>getScaleFactorY()</code>.
*
* @param xFunits - the X coordinate in font design units
* @param yFunits - the Y coordinate in font design units
* @param pixels - the tranformed co-ordinate in pixels
*
* @see getScaleFactorX
* @see getScaleFactorY
*
* @stable ICU 3.2
*/
virtual void transformFunits(float xFunits, float yFunits, LEPoint &pixels) const;
/**
* This is a convenience method used to convert
* values in a 16.16 fixed point format to floating point.
*
* @param fixed - the fixed point value
*
* @return the floating point value
*
* @stable ICU 2.8
*/
static inline float fixedToFloat(le_int32 fixed);
/**
* This is a convenience method used to convert
* floating point values to 16.16 fixed point format.
*
* @param theFloat - the floating point value
*
* @return the fixed point value
*
* @stable ICU 2.8
*/
static inline le_int32 floatToFixed(float theFloat);
//
// These methods won't ever be called by the LayoutEngine,
// but are useful for clients of <code>LEFontInstance</code> who
// need to render text.
//
/**
* Get the font's ascent.
*
* @return the font's ascent, in points. This value
* will always be positive.
*
* @stable ICU 3.2
*/
virtual le_int32 getAscent() const = 0;
/**
* Get the font's descent.
*
* @return the font's descent, in points. This value
* will always be positive.
*
* @stable ICU 3.2
*/
virtual le_int32 getDescent() const = 0;
/**
* Get the font's leading.
*
* @return the font's leading, in points. This value
* will always be positive.
*
* @stable ICU 3.2
*/
virtual le_int32 getLeading() const = 0;
/**
* Get the line height required to display text in
* this font. The default implementation of this method
* returns the sum of the ascent, descent, and leading.
*
* @return the line height, in points. This vaule will
* always be positive.
*
* @stable ICU 3.2
*/
virtual le_int32 getLineHeight() const;
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static UClassID getStaticClassID();
};
inline float LEFontInstance::fixedToFloat(le_int32 fixed)
{
return (float) (fixed / 65536.0);
}
inline le_int32 LEFontInstance::floatToFixed(float theFloat)
{
return (le_int32) (theFloat * 65536.0);
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LEGlyphFilter.h
-45
View File
@@ -1,45 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2011 - All Rights Reserved
*
*/
#ifndef __LEGLYPHFILTER__H
#define __LEGLYPHFILTER__H
#include "LETypes.h"
U_NAMESPACE_BEGIN
#ifndef U_HIDE_INTERNAL_API
/**
* This is a helper class that is used to
* recognize a set of glyph indices.
*
* @internal
*/
class LEGlyphFilter /* not : public UObject because this is an interface/mixin class */ {
public:
/**
* Destructor.
* @internal
*/
virtual ~LEGlyphFilter();
/**
* This method is used to test a particular
* glyph index to see if it is in the set
* recognized by the filter.
*
* @param glyph - the glyph index to be tested
*
* @return TRUE if the glyph index is in the set.
*
* @internal
*/
virtual le_bool accept(LEGlyphID glyph) const = 0;
};
#endif /* U_HIDE_INTERNAL_API */
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LEGlyphStorage.h
-546
View File
@@ -1,546 +0,0 @@
/*
**********************************************************************
* Copyright (C) 1998-2010, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __LEGLYPHSTORAGE_H
#define __LEGLYPHSTORAGE_H
#include "LETypes.h"
#include "LEInsertionList.h"
/**
* \file
* \brief C++ API: This class encapsulates the per-glyph storage used by the ICU LayoutEngine.
*/
U_NAMESPACE_BEGIN
/**
* This class encapsulates the per-glyph storage used by the ICU LayoutEngine.
* For each glyph it holds the glyph ID, the index of the backing store character
* which produced the glyph, the X and Y position of the glyph and an auxillary data
* pointer.
*
* The storage is growable using the <code>LEInsertionList</code> class.
*
*
* @see LEInsertionList.h
*
* @stable ICU 3.6
*/
class U_LAYOUT_API LEGlyphStorage : public UObject, protected LEInsertionCallback
{
private:
/**
* The number of entries in the per-glyph arrays.
*
* @internal
*/
le_int32 fGlyphCount;
/**
* The glyph ID array.
*
* @internal
*/
LEGlyphID *fGlyphs;
/**
* The char indices array.
*
* @internal
*/
le_int32 *fCharIndices;
/**
* The glyph positions array.
*
* @internal
*/
float *fPositions;
/**
* The auxillary data array.
*
* @internal
*/
le_uint32 *fAuxData;
/**
* The insertion list, used to grow the above arrays.
*
* @internal
*/
LEInsertionList *fInsertionList;
/**
* The source index while growing the data arrays.
*
* @internal
*/
le_int32 fSrcIndex;
/**
* The destination index used while growing the data arrays.
*
* @internal
*/
le_int32 fDestIndex;
protected:
/**
* This implements <code>LEInsertionCallback</code>. The <code>LEInsertionList</code>
* will call this method once for each insertion.
*
* @param atPosition the position of the insertion
* @param count the number of glyphs being inserted
* @param newGlyphs the address of the new glyph IDs
*
* @return <code>true</code> if <code>LEInsertionList</code> should stop
* processing the insertion list after this insertion.
*
* @see LEInsertionList.h
*
* @stable ICU 3.0
*/
virtual le_bool applyInsertion(le_int32 atPosition, le_int32 count, LEGlyphID newGlyphs[]);
public:
/**
* Allocates an empty <code>LEGlyphStorage</code> object. You must call
* <code>allocateGlyphArray, allocatePositions and allocateAuxData</code>
* to allocate the data.
*
* @stable ICU 3.0
*/
LEGlyphStorage();
/**
* The destructor. This will deallocate all of the arrays.
*
* @stable ICU 3.0
*/
~LEGlyphStorage();
/**
* This method returns the number of glyphs in the glyph array.
*
* @return the number of glyphs in the glyph array
*
* @stable ICU 3.0
*/
inline le_int32 getGlyphCount() const;
/**
* This method copies the glyph array into a caller supplied array.
* The caller must ensure that the array is large enough to hold all
* the glyphs.
*
* @param glyphs - the destiniation glyph array
* @param success - set to an error code if the operation fails
*
* @stable ICU 3.0
*/
void getGlyphs(LEGlyphID glyphs[], LEErrorCode &success) const;
/**
* This method copies the glyph array into a caller supplied array,
* ORing in extra bits. (This functionality is needed by the JDK,
* which uses 32 bits pre glyph idex, with the high 16 bits encoding
* the composite font slot number)
*
* @param glyphs - the destination (32 bit) glyph array
* @param extraBits - this value will be ORed with each glyph index
* @param success - set to an error code if the operation fails
*
* @stable ICU 3.0
*/
void getGlyphs(le_uint32 glyphs[], le_uint32 extraBits, LEErrorCode &success) const;
/**
* This method copies the character index array into a caller supplied array.
* The caller must ensure that the array is large enough to hold a
* character index for each glyph.
*
* @param charIndices - the destiniation character index array
* @param success - set to an error code if the operation fails
*
* @stable ICU 3.0
*/
void getCharIndices(le_int32 charIndices[], LEErrorCode &success) const;
/**
* This method copies the character index array into a caller supplied array.
* The caller must ensure that the array is large enough to hold a
* character index for each glyph.
*
* @param charIndices - the destiniation character index array
* @param indexBase - an offset which will be added to each index
* @param success - set to an error code if the operation fails
*
* @stable ICU 3.0
*/
void getCharIndices(le_int32 charIndices[], le_int32 indexBase, LEErrorCode &success) const;
/**
* This method copies the position array into a caller supplied array.
* The caller must ensure that the array is large enough to hold an
* X and Y position for each glyph, plus an extra X and Y for the
* advance of the last glyph.
*
* @param positions - the destiniation position array
* @param success - set to an error code if the operation fails
*
* @stable ICU 3.0
*/
void getGlyphPositions(float positions[], LEErrorCode &success) const;
/**
* This method returns the X and Y position of the glyph at
* the given index.
*
* Input parameters:
* @param glyphIndex - the index of the glyph
*
* Output parameters:
* @param x - the glyph's X position
* @param y - the glyph's Y position
* @param success - set to an error code if the operation fails
*
* @stable ICU 3.0
*/
void getGlyphPosition(le_int32 glyphIndex, float &x, float &y, LEErrorCode &success) const;
/**
* This method allocates the glyph array, the char indices array and the insertion list. You
* must call this method before using the object. This method also initializes the char indices
* array.
*
* @param initialGlyphCount the initial size of the glyph and char indices arrays.
* @param rightToLeft <code>true</code> if the original input text is right to left.
* @param success set to an error code if the storage cannot be allocated of if the initial
* glyph count is not positive.
*
* @stable ICU 3.0
*/
void allocateGlyphArray(le_int32 initialGlyphCount, le_bool rightToLeft, LEErrorCode &success);
/**
* This method allocates the storage for the glyph positions. It allocates one extra X, Y
* position pair for the position just after the last glyph.
*
* @param success set to an error code if the positions array cannot be allocated.
*
* @return the number of X, Y position pairs allocated.
*
* @stable ICU 3.0
*/
le_int32 allocatePositions(LEErrorCode &success);
/**
* This method allocates the storage for the auxillary glyph data.
*
* @param success set to an error code if the aulillary data array cannot be allocated.
*
* @return the size of the auxillary data array.
*
* @stable ICU 3.6
*/
le_int32 allocateAuxData(LEErrorCode &success);
/**
* Copy the entire auxillary data array.
*
* @param auxData the auxillary data array will be copied to this address
* @param success set to an error code if the data cannot be copied
*
* @stable ICU 3.6
*/
void getAuxData(le_uint32 auxData[], LEErrorCode &success) const;
/**
* Get the glyph ID for a particular glyph.
*
* @param glyphIndex the index into the glyph array
* @param success set to an error code if the glyph ID cannot be retrieved.
*
* @return the glyph ID
*
* @stable ICU 3.0
*/
LEGlyphID getGlyphID(le_int32 glyphIndex, LEErrorCode &success) const;
/**
* Get the char index for a particular glyph.
*
* @param glyphIndex the index into the glyph array
* @param success set to an error code if the char index cannot be retrieved.
*
* @return the character index
*
* @stable ICU 3.0
*/
le_int32 getCharIndex(le_int32 glyphIndex, LEErrorCode &success) const;
/**
* Get the auxillary data for a particular glyph.
*
* @param glyphIndex the index into the glyph array
* @param success set to an error code if the auxillary data cannot be retrieved.
*
* @return the auxillary data
*
* @stable ICU 3.6
*/
le_uint32 getAuxData(le_int32 glyphIndex, LEErrorCode &success) const;
/**
* This operator allows direct access to the glyph array
* using the index operator.
*
* @param glyphIndex the index into the glyph array
*
* @return a reference to the given location in the glyph array
*
* @stable ICU 3.0
*/
inline LEGlyphID &operator[](le_int32 glyphIndex) const;
/**
* Call this method to replace a single glyph in the glyph array
* with multiple glyphs. This method uses the <code>LEInsertionList</code>
* to do the insertion. It returns the address of storage where the new
* glyph IDs can be stored. They will not actually be inserted into the
* glyph array until <code>applyInsertions</code> is called.
*
* @param atIndex the index of the glyph to be replaced
* @param insertCount the number of glyphs to replace it with
* @param success set to an error code if the auxillary data cannot be retrieved.
*
* @return the address at which to store the replacement glyphs.
*
* @see LEInsertionList.h
*
* @stable ICU 4.2
*/
LEGlyphID *insertGlyphs(le_int32 atIndex, le_int32 insertCount, LEErrorCode& success);
/**
* Call this method to replace a single glyph in the glyph array
* with multiple glyphs. This method uses the <code>LEInsertionList</code>
* to do the insertion. It returns the address of storage where the new
* glyph IDs can be stored. They will not actually be inserted into the
* glyph array until <code>applyInsertions</code> is called.
*
* Note: Don't use this version, use the other version of this function which has an error code.
*
* @param atIndex the index of the glyph to be replaced
* @param insertCount the number of glyphs to replace it with
*
* @return the address at which to store the replacement glyphs.
*
* @see LEInsertionList.h
*
* @stable ICU 3.0
*/
LEGlyphID *insertGlyphs(le_int32 atIndex, le_int32 insertCount);
/**
* This method is used to reposition glyphs during Indic v2 processing. It moves
* all of the relevant glyph information ( glyph, indices, positions, and auxData ),
* from the source position to the target position, and also allows for a marker bit
* to be set in the target glyph's auxData so that it won't be reprocessed later in the
* cycle.
*
* @param fromPosition - position of the glyph to be moved
* @param toPosition - target position of the glyph
* @param marker marker bit
*
* @stable ICU 4.2
*/
void moveGlyph(le_int32 fromPosition, le_int32 toPosition, le_uint32 marker);
/**
* This method causes all of the glyph insertions recorded by
* <code>insertGlyphs</code> to be applied to the glyph array. The
* new slots in the char indices and the auxillary data arrays
* will be filled in with the values for the glyph being replaced.
*
* @return the new size of the glyph array
*
* @see LEInsertionList.h
*
* @stable ICU 3.0
*/
le_int32 applyInsertions();
/**
* Set the glyph ID for a particular glyph.
*
* @param glyphIndex the index of the glyph
* @param glyphID the new glyph ID
* @param success will be set to an error code if the glyph ID cannot be set.
*
* @stable ICU 3.0
*/
void setGlyphID(le_int32 glyphIndex, LEGlyphID glyphID, LEErrorCode &success);
/**
* Set the char index for a particular glyph.
*
* @param glyphIndex the index of the glyph
* @param charIndex the new char index
* @param success will be set to an error code if the char index cannot be set.
*
* @stable ICU 3.0
*/
void setCharIndex(le_int32 glyphIndex, le_int32 charIndex, LEErrorCode &success);
/**
* Set the X, Y position for a particular glyph.
*
* @param glyphIndex the index of the glyph
* @param x the new X position
* @param y the new Y position
* @param success will be set to an error code if the position cannot be set.
*
* @stable ICU 3.0
*/
void setPosition(le_int32 glyphIndex, float x, float y, LEErrorCode &success);
/**
* Adjust the X, Y position for a particular glyph.
*
* @param glyphIndex the index of the glyph
* @param xAdjust the adjustment to the glyph's X position
* @param yAdjust the adjustment to the glyph's Y position
* @param success will be set to an error code if the glyph's position cannot be adjusted.
*
* @stable ICU 3.0
*/
void adjustPosition(le_int32 glyphIndex, float xAdjust, float yAdjust, LEErrorCode &success);
/**
* Set the auxillary data for a particular glyph.
*
* @param glyphIndex the index of the glyph
* @param auxData the new auxillary data
* @param success will be set to an error code if the auxillary data cannot be set.
*
* @stable ICU 3.6
*/
void setAuxData(le_int32 glyphIndex, le_uint32 auxData, LEErrorCode &success);
/**
* Delete the glyph array and replace it with the one
* in <code>from</code>. Set the glyph array pointer
* in <code>from</code> to <code>NULL</code>.
*
* @param from the <code>LEGlyphStorage</code> object from which
* to get the new glyph array.
*
* @stable ICU 3.0
*/
void adoptGlyphArray(LEGlyphStorage &from);
/**
* Delete the char indices array and replace it with the one
* in <code>from</code>. Set the char indices array pointer
* in <code>from</code> to <code>NULL</code>.
*
* @param from the <code>LEGlyphStorage</code> object from which
* to get the new char indices array.
*
* @stable ICU 3.0
*/
void adoptCharIndicesArray(LEGlyphStorage &from);
/**
* Delete the position array and replace it with the one
* in <code>from</code>. Set the position array pointer
* in <code>from</code> to <code>NULL</code>.
*
* @param from the <code>LEGlyphStorage</code> object from which
* to get the new position array.
*
* @stable ICU 3.0
*/
void adoptPositionArray(LEGlyphStorage &from);
/**
* Delete the auxillary data array and replace it with the one
* in <code>from</code>. Set the auxillary data array pointer
* in <code>from</code> to <code>NULL</code>.
*
* @param from the <code>LEGlyphStorage</code> object from which
* to get the new auxillary data array.
*
* @stable ICU 3.0
*/
void adoptAuxDataArray(LEGlyphStorage &from);
/**
* Change the glyph count of this object to be the same
* as the one in <code>from</code>.
*
* @param from the <code>LEGlyphStorage</code> object from which
* to get the new glyph count.
*
* @stable ICU 3.0
*/
void adoptGlyphCount(LEGlyphStorage &from);
/**
* Change the glyph count of this object to the given value.
*
* @param newGlyphCount the new glyph count.
*
* @stable ICU 3.0
*/
void adoptGlyphCount(le_int32 newGlyphCount);
/**
* This method frees the glyph, character index, position and
* auxillary data arrays so that the LayoutEngine can be reused
* to layout a different characer array. (This method is also called
* by the destructor)
*
* @stable ICU 3.0
*/
void reset();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.0
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.0
*/
static UClassID getStaticClassID();
};
inline le_int32 LEGlyphStorage::getGlyphCount() const
{
return fGlyphCount;
}
inline LEGlyphID &LEGlyphStorage::operator[](le_int32 glyphIndex) const
{
return fGlyphs[glyphIndex];
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LEInsertionList.h
-177
View File
@@ -1,177 +0,0 @@
/*
**********************************************************************
* Copyright (C) 1998-2011, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __LEINSERTIONLIST_H
#define __LEINSERTIONLIST_H
#include "LETypes.h"
U_NAMESPACE_BEGIN
struct InsertionRecord;
#ifndef U_HIDE_INTERNAL_API
/**
* This class encapsulates the callback used by <code>LEInsertionList</code>
* to apply an insertion from the insertion list.
*
* @internal
*/
class U_LAYOUT_API LEInsertionCallback
{
public:
/**
* This method will be called by <code>LEInsertionList::applyInsertions</code> for each
* entry on the insertion list.
*
* @param atPosition the position of the insertion
* @param count the number of glyphs to insert
* @param newGlyphs the address of the glyphs to insert
*
* @return <code>TRUE</code> if <code>LEInsertions::applyInsertions</code> should
* stop after applying this insertion.
*
* @internal
*/
virtual le_bool applyInsertion(le_int32 atPosition, le_int32 count, LEGlyphID newGlyphs[]) = 0;
/**
* The destructor
*/
virtual ~LEInsertionCallback();
};
/**
* This class is used to keep track of insertions to an array of
* <code>LEGlyphIDs</code>. The insertions are kept on a linked
* list of <code>InsertionRecords</code> so that the glyph array
* doesn't have to be grown for each insertion. The insertions are
* stored on the list from leftmost to rightmost to make it easier
* to do the insertions.
*
* The insertions are applied to the array by calling the
* <code>applyInsertions</code> method, which calls a client
* supplied <code>LEInsertionCallback</code> object to actually
* apply the individual insertions.
*
* @internal
*/
class LEInsertionList : public UObject
{
public:
/**
* Construct an empty insertion list.
*
* @param rightToLeft <code>TRUE</code> if the glyphs are stored
* in the array in right to left order.
*
* @internal
*/
LEInsertionList(le_bool rightToLeft);
/**
* The destructor.
*/
~LEInsertionList();
/**
* Add an entry to the insertion list.
*
* @param position the glyph at this position in the array will be
* replaced by the new glyphs.
* @param count the number of new glyphs
* @param success set to an error code if the auxillary data cannot be retrieved.
*
* @return the address of an array in which to store the new glyphs. This will
* <em>not</em> be in the glyph array.
*
* @internal
*/
LEGlyphID *insert(le_int32 position, le_int32 count, LEErrorCode &success);
/**
* Return the number of new glyphs that have been inserted.
*
* @return the number of new glyphs which have been inserted
*
* @internal
*/
le_int32 getGrowAmount();
/**
* Call the <code>LEInsertionCallback</code> once for each
* entry on the insertion list.
*
* @param callback the <code>LEInsertionCallback</code> to call for each insertion.
*
* @return <code>TRUE</code> if <code>callback</code> returned <code>TRUE</code> to
* terminate the insertion list processing.
*
* @internal
*/
le_bool applyInsertions(LEInsertionCallback *callback);
/**
* Empty the insertion list and free all associated
* storage.
*
* @internal
*/
void reset();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.8
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.8
*/
static UClassID getStaticClassID();
private:
/**
* The head of the insertion list.
*
* @internal
*/
InsertionRecord *head;
/**
* The tail of the insertion list.
*
* @internal
*/
InsertionRecord *tail;
/**
* The total number of new glyphs on the insertion list.
*
* @internal
*/
le_int32 growAmount;
/**
* Set to <code>TRUE</code> if the glyphs are in right
* to left order. Since we want the rightmost insertion
* to be first on the list, we need to append the
* insertions in this case. Otherwise they're prepended.
*
* @internal
*/
le_bool append;
};
#endif /* U_HIDE_INTERNAL_API */
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LELanguages.h
-111
View File
@@ -1,111 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2010. All Rights Reserved.
*
* WARNING: THIS FILE IS MACHINE GENERATED. DO NOT HAND EDIT IT UNLESS
* YOU REALLY KNOW WHAT YOU'RE DOING.
*
* Generated on: 10/26/2010 02:53:33 PM PDT
*/
#ifndef __LELANGUAGES_H
#define __LELANGUAGES_H
#include "LETypes.h"
/**
* \file
* \brief C++ API: List of language codes for LayoutEngine
*/
U_NAMESPACE_BEGIN
/**
* A provisional list of language codes. For now,
* this is just a list of languages which the LayoutEngine
* supports.
*
* @stable ICU 2.6
*/
enum LanguageCodes {
nullLanguageCode = 0,
araLanguageCode = 1,
asmLanguageCode = 2,
benLanguageCode = 3,
farLanguageCode = 4,
gujLanguageCode = 5,
hinLanguageCode = 6,
iwrLanguageCode = 7,
jiiLanguageCode = 8,
janLanguageCode = 9,
kanLanguageCode = 10,
kokLanguageCode = 11,
korLanguageCode = 12,
kshLanguageCode = 13,
malLanguageCode = 14,
marLanguageCode = 15,
mlrLanguageCode = 16,
mniLanguageCode = 17,
oriLanguageCode = 18,
sanLanguageCode = 19,
sndLanguageCode = 20,
snhLanguageCode = 21,
syrLanguageCode = 22,
tamLanguageCode = 23,
telLanguageCode = 24,
thaLanguageCode = 25,
urdLanguageCode = 26,
zhpLanguageCode = 27,
zhsLanguageCode = 28,
zhtLanguageCode = 29,
/** New language codes added 03/13/2008 @stable ICU 4.0 */
afkLanguageCode = 30,
belLanguageCode = 31,
bgrLanguageCode = 32,
catLanguageCode = 33,
cheLanguageCode = 34,
copLanguageCode = 35,
csyLanguageCode = 36,
danLanguageCode = 37,
deuLanguageCode = 38,
dznLanguageCode = 39,
ellLanguageCode = 40,
engLanguageCode = 41,
espLanguageCode = 42,
etiLanguageCode = 43,
euqLanguageCode = 44,
finLanguageCode = 45,
fraLanguageCode = 46,
gaeLanguageCode = 47,
hauLanguageCode = 48,
hrvLanguageCode = 49,
hunLanguageCode = 50,
hyeLanguageCode = 51,
indLanguageCode = 52,
itaLanguageCode = 53,
khmLanguageCode = 54,
mngLanguageCode = 55,
mtsLanguageCode = 56,
nepLanguageCode = 57,
nldLanguageCode = 58,
pasLanguageCode = 59,
plkLanguageCode = 60,
ptgLanguageCode = 61,
romLanguageCode = 62,
rusLanguageCode = 63,
skyLanguageCode = 64,
slvLanguageCode = 65,
sqiLanguageCode = 66,
srbLanguageCode = 67,
sveLanguageCode = 68,
tibLanguageCode = 69,
trkLanguageCode = 70,
welLanguageCode = 71,
languageCodeCount = 72
};
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LEScripts.h
-253
View File
@@ -1,253 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2013. All Rights Reserved.
*
* WARNING: THIS FILE IS MACHINE GENERATED. DO NOT HAND EDIT IT UNLESS
* YOU REALLY KNOW WHAT YOU'RE DOING.
*
* Generated on: 11/01/2011 04:08:09 PM PDT
*/
#ifndef __LESCRIPTS_H
#define __LESCRIPTS_H
#include "LETypes.h"
/**
* \file
* \brief C++ API: Constants for Unicode script values
*/
U_NAMESPACE_BEGIN
/**
* Constants for Unicode script values, generated using
* ICU4J's <code>UScript</code> class.
*
* @stable ICU 2.2
*/
enum ScriptCodes {
zyyyScriptCode = 0,
zinhScriptCode = 1,
qaaiScriptCode = zinhScriptCode, /* manually added alias, for API stability */
arabScriptCode = 2,
armnScriptCode = 3,
bengScriptCode = 4,
bopoScriptCode = 5,
cherScriptCode = 6,
coptScriptCode = 7,
cyrlScriptCode = 8,
dsrtScriptCode = 9,
devaScriptCode = 10,
ethiScriptCode = 11,
georScriptCode = 12,
gothScriptCode = 13,
grekScriptCode = 14,
gujrScriptCode = 15,
guruScriptCode = 16,
haniScriptCode = 17,
hangScriptCode = 18,
hebrScriptCode = 19,
hiraScriptCode = 20,
kndaScriptCode = 21,
kanaScriptCode = 22,
khmrScriptCode = 23,
laooScriptCode = 24,
latnScriptCode = 25,
mlymScriptCode = 26,
mongScriptCode = 27,
mymrScriptCode = 28,
ogamScriptCode = 29,
italScriptCode = 30,
oryaScriptCode = 31,
runrScriptCode = 32,
sinhScriptCode = 33,
syrcScriptCode = 34,
tamlScriptCode = 35,
teluScriptCode = 36,
thaaScriptCode = 37,
thaiScriptCode = 38,
tibtScriptCode = 39,
/**
* @stable ICU 2.6
*/
cansScriptCode = 40,
/**
* @stable ICU 2.2
*/
yiiiScriptCode = 41,
tglgScriptCode = 42,
hanoScriptCode = 43,
buhdScriptCode = 44,
tagbScriptCode = 45,
/**
* @stable ICU 2.6
*/
braiScriptCode = 46,
cprtScriptCode = 47,
limbScriptCode = 48,
linbScriptCode = 49,
osmaScriptCode = 50,
shawScriptCode = 51,
taleScriptCode = 52,
ugarScriptCode = 53,
/**
* @stable ICU 3.0
*/
hrktScriptCode = 54,
/**
* @stable ICU 3.4
*/
bugiScriptCode = 55,
glagScriptCode = 56,
kharScriptCode = 57,
syloScriptCode = 58,
taluScriptCode = 59,
tfngScriptCode = 60,
xpeoScriptCode = 61,
/**
* @stable ICU 3.6
*/
baliScriptCode = 62,
batkScriptCode = 63,
blisScriptCode = 64,
brahScriptCode = 65,
chamScriptCode = 66,
cirtScriptCode = 67,
cyrsScriptCode = 68,
egydScriptCode = 69,
egyhScriptCode = 70,
egypScriptCode = 71,
geokScriptCode = 72,
hansScriptCode = 73,
hantScriptCode = 74,
hmngScriptCode = 75,
hungScriptCode = 76,
indsScriptCode = 77,
javaScriptCode = 78,
kaliScriptCode = 79,
latfScriptCode = 80,
latgScriptCode = 81,
lepcScriptCode = 82,
linaScriptCode = 83,
mandScriptCode = 84,
mayaScriptCode = 85,
meroScriptCode = 86,
nkooScriptCode = 87,
orkhScriptCode = 88,
permScriptCode = 89,
phagScriptCode = 90,
phnxScriptCode = 91,
plrdScriptCode = 92,
roroScriptCode = 93,
saraScriptCode = 94,
syreScriptCode = 95,
syrjScriptCode = 96,
syrnScriptCode = 97,
tengScriptCode = 98,
vaiiScriptCode = 99,
vispScriptCode = 100,
xsuxScriptCode = 101,
zxxxScriptCode = 102,
zzzzScriptCode = 103,
/**
* @stable ICU 3.8
*/
cariScriptCode = 104,
jpanScriptCode = 105,
lanaScriptCode = 106,
lyciScriptCode = 107,
lydiScriptCode = 108,
olckScriptCode = 109,
rjngScriptCode = 110,
saurScriptCode = 111,
sgnwScriptCode = 112,
sundScriptCode = 113,
moonScriptCode = 114,
mteiScriptCode = 115,
/**
* @stable ICU 4.0
*/
armiScriptCode = 116,
avstScriptCode = 117,
cakmScriptCode = 118,
koreScriptCode = 119,
kthiScriptCode = 120,
maniScriptCode = 121,
phliScriptCode = 122,
phlpScriptCode = 123,
phlvScriptCode = 124,
prtiScriptCode = 125,
samrScriptCode = 126,
tavtScriptCode = 127,
zmthScriptCode = 128,
zsymScriptCode = 129,
/**
* @stable ICU 4.4
*/
bamuScriptCode = 130,
lisuScriptCode = 131,
nkgbScriptCode = 132,
sarbScriptCode = 133,
/**
* @stable ICU 4.6
*/
bassScriptCode = 134,
duplScriptCode = 135,
elbaScriptCode = 136,
granScriptCode = 137,
kpelScriptCode = 138,
lomaScriptCode = 139,
mendScriptCode = 140,
mercScriptCode = 141,
narbScriptCode = 142,
nbatScriptCode = 143,
palmScriptCode = 144,
sindScriptCode = 145,
waraScriptCode = 146,
/**
* @stable ICU 4.8
*/
afakScriptCode = 147,
jurcScriptCode = 148,
mrooScriptCode = 149,
nshuScriptCode = 150,
shrdScriptCode = 151,
soraScriptCode = 152,
takrScriptCode = 153,
tangScriptCode = 154,
woleScriptCode = 155,
/**
* @stable ICU 49
*/
hluwScriptCode = 156, /* bump to match current ICU */
khojScriptCode = 157,
tirhScriptCode = 158,
/**
* @stable ICU 52
*/
aghbScriptCode = 159,
mahjScriptCode = 160,
/**
* @stable ICU 2.2
*/
scriptCodeCount
};
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LESwaps.h
-100
View File
@@ -1,100 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2011 - All Rights Reserved
*
*/
#ifndef __LESWAPS_H
#define __LESWAPS_H
#include "LETypes.h"
/**
* \file
* \brief C++ API: Endian independent access to data for LayoutEngine
*/
U_NAMESPACE_BEGIN
/**
* A convenience macro which invokes the swapWord member function
* from a concise call.
*
* @stable ICU 2.8
*/
#define SWAPW(value) LESwaps::swapWord((le_uint16)(value))
/**
* A convenience macro which invokes the swapLong member function
* from a concise call.
*
* @stable ICU 2.8
*/
#define SWAPL(value) LESwaps::swapLong((le_uint32)(value))
/**
* This class is used to access data which stored in big endian order
* regardless of the conventions of the platform.
*
* All methods are static and inline in an attempt to induce the compiler
* to do most of the calculations at compile time.
*
* @stable ICU 2.8
*/
class U_LAYOUT_API LESwaps /* not : public UObject because all methods are static */ {
public:
/**
* Reads a big-endian 16-bit word and returns a native-endian value.
* No-op on a big-endian platform, byte-swaps on a little-endian platform.
*
* @param value - the word to be byte swapped
*
* @return the byte swapped word
*
* @stable ICU 2.8
*/
static le_uint16 swapWord(le_uint16 value)
{
#if (defined(U_IS_BIG_ENDIAN) && U_IS_BIG_ENDIAN) || \
(defined(BYTE_ORDER) && defined(BIG_ENDIAN) && (BYTE_ORDER == BIG_ENDIAN)) || \
defined(__BIG_ENDIAN__)
// Fastpath when we know that the platform is big-endian.
return value;
#else
// Reads a big-endian value on any platform.
const le_uint8 *p = reinterpret_cast<const le_uint8 *>(&value);
return (le_uint16)((p[0] << 8) | p[1]);
#endif
};
/**
* Reads a big-endian 32-bit word and returns a native-endian value.
* No-op on a big-endian platform, byte-swaps on a little-endian platform.
*
* @param value - the long to be byte swapped
*
* @return the byte swapped long
*
* @stable ICU 2.8
*/
static le_uint32 swapLong(le_uint32 value)
{
#if (defined(U_IS_BIG_ENDIAN) && U_IS_BIG_ENDIAN) || \
(defined(BYTE_ORDER) && defined(BIG_ENDIAN) && (BYTE_ORDER == BIG_ENDIAN)) || \
defined(__BIG_ENDIAN__)
// Fastpath when we know that the platform is big-endian.
return value;
#else
// Reads a big-endian value on any platform.
const le_uint8 *p = reinterpret_cast<const le_uint8 *>(&value);
return (le_uint32)((p[0] << 24) | (p[1] << 16) | (p[2] << 8) | p[3]);
#endif
};
private:
LESwaps() {} // private - forbid instantiation
};
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/LETableReference.h
-418
View File
@@ -1,418 +0,0 @@
/*
* -*- c++ -*-
*
* (C) Copyright IBM Corp. and others 2013 - All Rights Reserved
*
* Range checking
*
*/
#ifndef __LETABLEREFERENCE_H
#define __LETABLEREFERENCE_H
#include "LETypes.h"
#include "LEFontInstance.h"
#define kQuestionmarkTableTag 0x3F3F3F3FUL
#define kTildeTableTag 0x7e7e7e7eUL
#ifdef __cplusplus
// internal - interface for range checking
U_NAMESPACE_BEGIN
#if LE_ASSERT_BAD_FONT
class LETableReference; // fwd
/**
* defined in OpenTypeUtilities.cpp
* @internal
*/
extern void _debug_LETableReference(const char *f, int l, const char *msg, const LETableReference *what, const void *ptr, size_t len);
#define LE_DEBUG_TR(x) _debug_LETableReference(__FILE__, __LINE__, x, this, NULL, 0);
#define LE_DEBUG_TR3(x,y,z) _debug_LETableReference(__FILE__, __LINE__, x, this, (const void*)y, (size_t)z);
#if 0
#define LE_TRACE_TR(x) _debug_LETableReference(__FILE__, __LINE__, x, this, NULL, 0);
#else
#define LE_TRACE_TR(x)
#endif
#else
#define LE_DEBUG_TR(x)
#define LE_DEBUG_TR3(x,y,z)
#define LE_TRACE_TR(x)
#endif
/**
* @internal
*/
class LETableReference {
public:
/**
* @internal
* Construct from a specific tag
*/
LETableReference(const LEFontInstance* font, LETag tableTag, LEErrorCode &success) :
fFont(font), fTag(tableTag), fParent(NULL), fStart(NULL),fLength(LE_UINTPTR_MAX) {
loadTable(success);
LE_TRACE_TR("INFO: new table load")
}
LETableReference(const LETableReference &parent, LEErrorCode &success) : fFont(parent.fFont), fTag(parent.fTag), fParent(&parent), fStart(parent.fStart), fLength(parent.fLength) {
if(LE_FAILURE(success)) {
clear();
}
LE_TRACE_TR("INFO: new clone")
}
LETableReference(const le_uint8* data, size_t length = LE_UINTPTR_MAX) :
fFont(NULL), fTag(kQuestionmarkTableTag), fParent(NULL), fStart(data), fLength(length) {
LE_TRACE_TR("INFO: new raw")
}
LETableReference() :
fFont(NULL), fTag(kQuestionmarkTableTag), fParent(NULL), fStart(NULL), fLength(0) {
LE_TRACE_TR("INFO: new empty")
}
~LETableReference() {
fTag=kTildeTableTag;
LE_TRACE_TR("INFO: new dtor")
}
/**
* @internal
* @param length if LE_UINTPTR_MAX means "whole table"
* subset
*/
LETableReference(const LETableReference &parent, size_t offset, size_t length,
LEErrorCode &err) :
fFont(parent.fFont), fTag(parent.fTag), fParent(&parent),
fStart((parent.fStart)+offset), fLength(length) {
if(LE_SUCCESS(err)) {
if(isEmpty()) {
//err = LE_MISSING_FONT_TABLE_ERROR;
clear(); // it's just empty. Not an error.
} else if(offset >= fParent->fLength) {
LE_DEBUG_TR3("offset out of range: (%p) +%d", NULL, offset);
err = LE_INDEX_OUT_OF_BOUNDS_ERROR;
clear();
} else {
if(fLength == LE_UINTPTR_MAX &&
fParent->fLength != LE_UINTPTR_MAX) {
fLength = (fParent->fLength) - offset; // decrement length as base address is incremented
}
if(fLength != LE_UINTPTR_MAX) { // if we have bounds:
if(offset+fLength > fParent->fLength) {
LE_DEBUG_TR3("offset+fLength out of range: (%p) +%d", NULL, offset+fLength);
err = LE_INDEX_OUT_OF_BOUNDS_ERROR; // exceeded
clear();
}
}
}
} else {
clear();
}
LE_TRACE_TR("INFO: new subset")
}
const void* getAlias() const { return (const void*)fStart; }
const void* getAliasRAW() const { LE_DEBUG_TR("getAliasRAW()"); return (const void*)fStart; }
le_bool isEmpty() const { return fStart==NULL || fLength==0; }
le_bool isValid() const { return !isEmpty(); }
le_bool hasBounds() const { return fLength!=LE_UINTPTR_MAX; }
void clear() { fLength=0; fStart=NULL; }
size_t getLength() const { return fLength; }
const LEFontInstance* getFont() const { return fFont; }
LETag getTag() const { return fTag; }
const LETableReference* getParent() const { return fParent; }
void addOffset(size_t offset, LEErrorCode &success) {
if(hasBounds()) {
if(offset > fLength) {
LE_DEBUG_TR("addOffset off end");
success = LE_INDEX_OUT_OF_BOUNDS_ERROR;
return;
} else {
fLength -= offset;
}
}
fStart += offset;
}
size_t ptrToOffset(const void *atPtr, LEErrorCode &success) const {
if(atPtr==NULL) return 0;
if(LE_FAILURE(success)) return LE_UINTPTR_MAX;
if((atPtr < fStart) ||
(hasBounds() && (atPtr > fStart+fLength))) {
LE_DEBUG_TR3("ptrToOffset args out of range: %p", atPtr, 0);
success = LE_INDEX_OUT_OF_BOUNDS_ERROR;
return LE_UINTPTR_MAX;
}
return ((const le_uint8*)atPtr)-fStart;
}
/**
* Clamp down the length, for range checking.
*/
size_t contractLength(size_t newLength) {
if(fLength!=LE_UINTPTR_MAX&&newLength>0&&newLength<=fLength) {
fLength = newLength;
}
return fLength;
}
/**
* Throw an error if offset+length off end
*/
public:
size_t verifyLength(size_t offset, size_t length, LEErrorCode &success) {
if(isValid()&&
LE_SUCCESS(success) &&
fLength!=LE_UINTPTR_MAX && length!=LE_UINTPTR_MAX && offset!=LE_UINTPTR_MAX &&
(offset+length)>fLength) {
LE_DEBUG_TR3("verifyLength failed (%p) %d",NULL, offset+length);
success = LE_INDEX_OUT_OF_BOUNDS_ERROR;
#if LE_ASSERT_BAD_FONT
fprintf(stderr, "offset=%lu, len=%lu, would be at %p, (%lu) off end. End at %p\n", offset,length, fStart+offset+length, (offset+length-fLength), (offset+length-fLength)+fStart);
#endif
}
return fLength;
}
/**
* Change parent link to another
*/
LETableReference &reparent(const LETableReference &base) {
fParent = &base;
return *this;
}
/**
* remove parent link. Factory functions should do this.
*/
void orphan(void) {
fParent=NULL;
}
protected:
const LEFontInstance* fFont;
LETag fTag;
const LETableReference *fParent;
const le_uint8 *fStart; // keep as 8 bit internally, for pointer math
size_t fLength;
void loadTable(LEErrorCode &success) {
if(LE_SUCCESS(success)) {
fStart = (const le_uint8*)(fFont->getFontTable(fTag, fLength)); // note - a null table is not an error.
}
}
void setRaw(const void *data, size_t length = LE_UINTPTR_MAX) {
fFont = NULL;
fTag = kQuestionmarkTableTag;
fParent = NULL;
fStart = (const le_uint8*)data;
fLength = length;
}
};
template<class T>
class LETableVarSizer {
public:
inline static size_t getSize();
};
// base definition- could override for adjustments
template<class T> inline
size_t LETableVarSizer<T>::getSize() {
return sizeof(T);
}
/**
* \def LE_VAR_ARRAY
* @param x Type (T)
* @param y some member that is of length ANY_NUMBER
* Call this after defining a class, for example:
* LE_VAR_ARRAY(FeatureListTable,featureRecordArray)
* this is roughly equivalent to:
* template<> inline size_t LETableVarSizer<FeatureListTable>::getSize() { return sizeof(FeatureListTable) - (sizeof(le_uint16)*ANY_NUMBER); }
* it's a specialization that informs the LETableReference subclasses to NOT include the variable array in the size.
* dereferencing NULL is valid here because we never actually dereference it, just inside sizeof.
*/
#define LE_VAR_ARRAY(x,y) template<> inline size_t LETableVarSizer<x>::getSize() { return sizeof(x) - (sizeof(((const x*)0)->y)); }
/**
* \def LE_CORRECT_SIZE
* @param x type (T)
* @param y fixed size for T
*/
#define LE_CORRECT_SIZE(x,y) template<> inline size_t LETableVarSizer<x>::getSize() { return y; }
/**
* Open a new entry based on an existing table
*/
/**
* \def LE_UNBOUNDED_ARRAY
* define an array with no *known* bound. Will trim to available size.
* @internal
*/
#define LE_UNBOUNDED_ARRAY LE_UINT32_MAX
template<class T>
class LEReferenceToArrayOf : public LETableReference {
public:
LEReferenceToArrayOf(const LETableReference &parent, LEErrorCode &success, size_t offset, le_uint32 count)
: LETableReference(parent, offset, LE_UINTPTR_MAX, success), fCount(count) {
LE_TRACE_TR("INFO: new RTAO by offset")
if(LE_SUCCESS(success)) {
if(count == LE_UNBOUNDED_ARRAY) { // not a known length
count = getLength()/LETableVarSizer<T>::getSize(); // fit to max size
}
LETableReference::verifyLength(0, LETableVarSizer<T>::getSize()*count, success);
}
if(LE_FAILURE(success)) {
fCount=0;
clear();
}
}
LEReferenceToArrayOf(const LETableReference &parent, LEErrorCode &success, const T* array, le_uint32 count)
: LETableReference(parent, parent.ptrToOffset(array, success), LE_UINTPTR_MAX, success), fCount(count) {
LE_TRACE_TR("INFO: new RTAO")
if(LE_SUCCESS(success)) {
if(count == LE_UNBOUNDED_ARRAY) { // not a known length
count = getLength()/LETableVarSizer<T>::getSize(); // fit to max size
}
LETableReference::verifyLength(0, LETableVarSizer<T>::getSize()*count, success);
}
if(LE_FAILURE(success)) clear();
}
LEReferenceToArrayOf(const LETableReference &parent, LEErrorCode &success, const T* array, size_t offset, le_uint32 count)
: LETableReference(parent, parent.ptrToOffset(array, success)+offset, LE_UINTPTR_MAX, success), fCount(count) {
LE_TRACE_TR("INFO: new RTAO")
if(LE_SUCCESS(success)) {
if(count == LE_UNBOUNDED_ARRAY) { // not a known length
count = getLength()/LETableVarSizer<T>::getSize(); // fit to max size
}
LETableReference::verifyLength(0, LETableVarSizer<T>::getSize()*count, success);
}
if(LE_FAILURE(success)) clear();
}
LEReferenceToArrayOf() :LETableReference(), fCount(0) {}
le_uint32 getCount() const { return fCount; }
using LETableReference::getAlias;
const T *getAlias(le_uint32 i, LEErrorCode &success) const {
return ((const T*)(((const char*)getAlias())+getOffsetFor(i, success)));
}
const T *getAliasRAW() const { LE_DEBUG_TR("getAliasRAW<>"); return (const T*)fStart; }
const T& getObject(le_uint32 i, LEErrorCode &success) const {
return *getAlias(i,success);
}
const T& operator()(le_uint32 i, LEErrorCode &success) const {
return *getAlias(i,success);
}
size_t getOffsetFor(le_uint32 i, LEErrorCode &success) const {
if(LE_SUCCESS(success)&&i<getCount()) {
return LETableVarSizer<T>::getSize()*i;
} else {
success = LE_INDEX_OUT_OF_BOUNDS_ERROR;
}
return 0;
}
LEReferenceToArrayOf<T> &reparent(const LETableReference &base) {
fParent = &base;
return *this;
}
LEReferenceToArrayOf(const LETableReference& parent, LEErrorCode & success) : LETableReference(parent,0, LE_UINTPTR_MAX, success), fCount(0) {
LE_TRACE_TR("INFO: null RTAO")
}
private:
le_uint32 fCount;
};
template<class T>
class LEReferenceTo : public LETableReference {
public:
/**
* open a sub reference.
* @param parent parent reference
* @param success error status
* @param atPtr location of reference - if NULL, will be at offset zero (i.e. downcast of parent). Otherwise must be a pointer within parent's bounds.
*/
inline LEReferenceTo(const LETableReference &parent, LEErrorCode &success, const void* atPtr)
: LETableReference(parent, parent.ptrToOffset(atPtr, success), LE_UINTPTR_MAX, success) {
verifyLength(0, LETableVarSizer<T>::getSize(), success);
if(LE_FAILURE(success)) clear();
}
/**
* ptr plus offset
*/
inline LEReferenceTo(const LETableReference &parent, LEErrorCode &success, const void* atPtr, size_t offset)
: LETableReference(parent, parent.ptrToOffset(atPtr, success)+offset, LE_UINTPTR_MAX, success) {
verifyLength(0, LETableVarSizer<T>::getSize(), success);
if(LE_FAILURE(success)) clear();
}
inline LEReferenceTo(const LETableReference &parent, LEErrorCode &success, size_t offset)
: LETableReference(parent, offset, LE_UINTPTR_MAX, success) {
verifyLength(0, LETableVarSizer<T>::getSize(), success);
if(LE_FAILURE(success)) clear();
}
inline LEReferenceTo(const LETableReference &parent, LEErrorCode &success)
: LETableReference(parent, 0, LE_UINTPTR_MAX, success) {
verifyLength(0, LETableVarSizer<T>::getSize(), success);
if(LE_FAILURE(success)) clear();
}
inline LEReferenceTo(const LEFontInstance *font, LETag tableTag, LEErrorCode &success)
: LETableReference(font, tableTag, success) {
verifyLength(0, LETableVarSizer<T>::getSize(), success);
if(LE_FAILURE(success)) clear();
}
inline LEReferenceTo(const le_uint8 *data, size_t length = LE_UINTPTR_MAX) : LETableReference(data, length) {}
inline LEReferenceTo(const T *data, size_t length = LE_UINTPTR_MAX) : LETableReference((const le_uint8*)data, length) {}
inline LEReferenceTo() : LETableReference(NULL) {}
inline LEReferenceTo<T>& operator=(const T* other) {
setRaw(other);
return *this;
}
LEReferenceTo<T> &reparent(const LETableReference &base) {
fParent = &base;
return *this;
}
/**
* roll forward by one <T> size.
* same as addOffset(LETableVarSizer<T>::getSize(),success)
*/
void addObject(LEErrorCode &success) {
addOffset(LETableVarSizer<T>::getSize(), success);
}
void addObject(size_t count, LEErrorCode &success) {
addOffset(LETableVarSizer<T>::getSize()*count, success);
}
const T *operator->() const { return getAlias(); }
const T *getAlias() const { return (const T*)fStart; }
const T *getAliasRAW() const { LE_DEBUG_TR("getAliasRAW<>"); return (const T*)fStart; }
};
U_NAMESPACE_END
#endif
#endif
project/jni/icuuc/include/layout/LETypes.h
-728
View File
@@ -1,728 +0,0 @@
/*
*
* (C) Copyright IBM Corp. and others 1998-2013 - All Rights Reserved
*
*/
#ifndef __LETYPES_H
#define __LETYPES_H
#if !defined(LE_USE_CMEMORY) && (defined(U_LAYOUT_IMPLEMENTATION) || defined(U_LAYOUTEX_IMPLEMENTATION) || defined(U_STATIC_IMPLEMENTATION) || defined(U_COMBINED_IMPLEMENTATION))
#define LE_USE_CMEMORY
#endif
#include "unicode/utypes.h"
#ifdef __cplusplus
#include "unicode/uobject.h"
#endif
#ifdef LE_USE_CMEMORY
#include "cmemory.h"
#endif
/*!
* \file
* \brief C API: Basic definitions for the ICU LayoutEngine
*/
/**
* A type used for signed, 32-bit integers.
*
* @stable ICU 2.4
*/
typedef int32_t le_int32;
/**
* A type used for unsigned, 32-bit integers.
*
* @stable ICU 2.4
*/
typedef uint32_t le_uint32;
/**
* A type used for signed, 16-bit integers.
*
* @stable ICU 2.4
*/
typedef int16_t le_int16;
/**
* A type used for unsigned, 16-bit integers.
*
* @stable ICU 2.4
*/
typedef uint16_t le_uint16;
/**
* A type used for signed, 8-bit integers.
*
* @stable ICU 2.4
*/
typedef int8_t le_int8;
/**
* A type used for unsigned, 8-bit integers.
*
* @stable ICU 2.4
*/
typedef uint8_t le_uint8;
/**
* A type used for boolean values.
*
* @stable ICU 2.4
*/
typedef UBool le_bool;
#ifndef NULL
/**
* Used to represent empty pointers.
*
* @stable ICU 2.4
*/
#define NULL 0
#endif
/**
* Used for four character tags.
*
* @stable ICU 2.4
*/
typedef le_uint32 LETag;
/**
* Used for 16-bit glyph indices as they're represented
* in TrueType font tables.
*
* @stable ICU 3.2
*/
typedef le_uint16 TTGlyphID;
/**
* Used for glyph indices. The low-order 16 bits are
* the glyph ID within the font. The next 8 bits are
* the sub-font ID within a compound font. The high-
* order 8 bits are client defined. The LayoutEngine
* will never change or look at the client defined bits.
*
* @stable ICU 3.2
*/
typedef le_uint32 LEGlyphID;
/**
* Used to mask off the glyph ID part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_GLYPH_MASK 0x0000FFFF
/**
* Used to shift the glyph ID part of an LEGlyphID
* into the low-order bits.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_GLYPH_SHIFT 0
/**
* Used to mask off the sub-font ID part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_SUB_FONT_MASK 0x00FF0000
/**
* Used to shift the sub-font ID part of an LEGlyphID
* into the low-order bits.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_SUB_FONT_SHIFT 16
/**
* Used to mask off the client-defined part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_CLIENT_MASK 0xFF000000
/**
* Used to shift the sub-font ID part of an LEGlyphID
* into the low-order bits.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_CLIENT_SHIFT 24
/**
* A convenience macro to get the Glyph ID part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_GET_GLYPH(gid) ((gid & LE_GLYPH_MASK) >> LE_GLYPH_SHIFT)
/**
* A convenience macro to get the sub-font ID part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_GET_SUB_FONT(gid) ((gid & LE_SUB_FONT_MASK) >> LE_SUB_FONT_SHIFT)
/**
* A convenience macro to get the client-defined part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_GET_CLIENT(gid) ((gid & LE_CLIENT_MASK) >> LE_CLIENT_SHIFT)
/**
* A convenience macro to set the Glyph ID part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_SET_GLYPH(gid, glyph) ((gid & ~LE_GLYPH_MASK) | ((glyph << LE_GLYPH_SHIFT) & LE_GLYPH_MASK))
/**
* A convenience macro to set the sub-font ID part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_SET_SUB_FONT(gid, font) ((gid & ~LE_SUB_FONT_MASK) | ((font << LE_SUB_FONT_SHIFT) & LE_SUB_FONT_MASK))
/**
* A convenience macro to set the client-defined part of an LEGlyphID.
*
* @see LEGlyphID
* @stable ICU 3.2
*/
#define LE_SET_CLIENT(gid, client) ((gid & ~LE_CLIENT_MASK) | ((client << LE_CLIENT_SHIFT) & LE_CLIENT_MASK))
/**
* Used to represent 16-bit Unicode code points.
*
* @stable ICU 2.4
*/
typedef UChar LEUnicode16;
/**
* Used to represent 32-bit Unicode code points.
*
* @stable ICU 2.4
*/
typedef UChar32 LEUnicode32;
#ifndef U_HIDE_DEPRECATED_API
/**
* Used to represent 16-bit Unicode code points.
*
* @deprecated since ICU 2.4. Use LEUnicode16 instead
*/
typedef UChar LEUnicode;
#endif /* U_HIDE_DEPRECATED_API */
/**
* Used to hold a pair of (x, y) values which represent a point.
*
* @stable ICU 2.4
*/
struct LEPoint
{
/**
* The x coordinate of the point.
*
* @stable ICU 2.4
*/
float fX;
/**
* The y coordinate of the point.
*
* @stable ICU 2.4
*/
float fY;
};
#ifndef __cplusplus
/**
* Used to hold a pair of (x, y) values which represent a point.
*
* @stable ICU 2.4
*/
typedef struct LEPoint LEPoint;
#endif
#ifndef U_HIDE_INTERNAL_API
/**
* \def
* @internal
*/
#ifndef LE_ASSERT_BAD_FONT
#define LE_ASSERT_BAD_FONT 0
#endif
/**
* \def LE_DEBUG_BAD_FONT
* @internal
*/
#if LE_ASSERT_BAD_FONT
#include <stdio.h>
#define LE_DEBUG_BAD_FONT(x) fprintf(stderr,"%s:%d: BAD FONT: %s\n", __FILE__, __LINE__, (x));
#else
#define LE_DEBUG_BAD_FONT(x)
#endif
/**
* \def LE_UINTPTR_MAX
* Max value representable by a uintptr
*/
#ifndef UINT32_MAX
#define LE_UINT32_MAX 0xFFFFFFFFU
#else
#define LE_UINT32_MAX UINT32_MAX
#endif
#ifndef UINTPTR_MAX
#define LE_UINTPTR_MAX LE_UINT32_MAX
#else
#define LE_UINTPTR_MAX UINTPTR_MAX
#endif
/**
* Range check for overflow
*/
#define LE_RANGE_CHECK(type, count, ptrfn) (( (LE_UINTPTR_MAX / sizeof(type)) < (size_t)count ) ? NULL : (ptrfn))
/**
* A convenience macro to get the length of an array.
*
* @internal
*/
#define LE_ARRAY_SIZE(array) (sizeof array / sizeof array[0])
#ifdef LE_USE_CMEMORY
/**
* A convenience macro for copying an array.
*
* @internal
*/
#define LE_ARRAY_COPY(dst, src, count) uprv_memcpy((void *) (dst), (void *) (src), (count) * sizeof (src)[0])
/**
* Allocate an array of basic types. This is used to isolate the rest of
* the LayoutEngine code from cmemory.h.
*
* @internal
*/
#define LE_NEW_ARRAY(type, count) (type *) LE_RANGE_CHECK(type,count,uprv_malloc((count) * sizeof(type)))
/**
* Re-allocate an array of basic types. This is used to isolate the rest of
* the LayoutEngine code from cmemory.h.
*
* @internal
*/
#define LE_GROW_ARRAY(array, newSize) uprv_realloc((void *) (array), (newSize) * sizeof (array)[0])
/**
* Free an array of basic types. This is used to isolate the rest of
* the LayoutEngine code from cmemory.h.
*
* @internal
*/
#define LE_DELETE_ARRAY(array) uprv_free((void *) (array))
#else
/* Not using ICU memory - use C std lib versions */
#include <stdlib.h>
#include <string.h>
/**
* A convenience macro to get the length of an array.
*
* @internal
*/
#define LE_ARRAY_SIZE(array) (sizeof array / sizeof array[0])
/**
* A convenience macro for copying an array.
*
* @internal
*/
#define LE_ARRAY_COPY(dst, src, count) memcpy((void *) (dst), (void *) (src), (count) * sizeof (src)[0])
/**
* Allocate an array of basic types. This is used to isolate the rest of
* the LayoutEngine code from cmemory.h.
*
* @internal
*/
#define LE_NEW_ARRAY(type, count) LE_RANGE_CHECK(type,count,(type *) malloc((count) * sizeof(type)))
/**
* Re-allocate an array of basic types. This is used to isolate the rest of
* the LayoutEngine code from cmemory.h.
*
* @internal
*/
#define LE_GROW_ARRAY(array, newSize) realloc((void *) (array), (newSize) * sizeof (array)[0])
/**
* Free an array of basic types. This is used to isolate the rest of
* the LayoutEngine code from cmemory.h.
*
* @internal
*/
#define LE_DELETE_ARRAY(array) free((void *) (array))
#endif
#endif /* U_HIDE_INTERNAL_API */
/**
* A macro to construct the four-letter tags used to
* label TrueType tables, and for script, language and
* feature tags in OpenType tables.
*
* WARNING: THIS MACRO WILL ONLY WORK CORRECTLY IF
* THE ARGUMENT CHARACTERS ARE ASCII.
*
* @stable ICU 3.2
*/
#define LE_MAKE_TAG(a, b, c, d) \
(((le_uint32)(a) << 24) | \
((le_uint32)(b) << 16) | \
((le_uint32)(c) << 8) | \
(le_uint32)(d))
/**
* This enumeration defines constants for the standard
* TrueType, OpenType and AAT table tags.
*
* @stable ICU 3.2
*/
enum LETableTags {
LE_ACNT_TABLE_TAG = 0x61636E74UL, /**< 'acnt' */
LE_AVAR_TABLE_TAG = 0x61766172UL, /**< 'avar' */
LE_BASE_TABLE_TAG = 0x42415345UL, /**< 'BASE' */
LE_BDAT_TABLE_TAG = 0x62646174UL, /**< 'bdat' */
LE_BHED_TABLE_TAG = 0x62686564UL, /**< 'bhed' */
LE_BLOC_TABLE_TAG = 0x626C6F63UL, /**< 'bloc' */
LE_BSLN_TABLE_TAG = 0x62736C6EUL, /**< 'bsln' */
LE_CFF__TABLE_TAG = 0x43464620UL, /**< 'CFF ' */
LE_CMAP_TABLE_TAG = 0x636D6170UL, /**< 'cmap' */
LE_CVAR_TABLE_TAG = 0x63766172UL, /**< 'cvar' */
LE_CVT__TABLE_TAG = 0x63767420UL, /**< 'cvt ' */
LE_DSIG_TABLE_TAG = 0x44534947UL, /**< 'DSIG' */
LE_EBDT_TABLE_TAG = 0x45424454UL, /**< 'EBDT' */
LE_EBLC_TABLE_TAG = 0x45424C43UL, /**< 'EBLC' */
LE_EBSC_TABLE_TAG = 0x45425343UL, /**< 'EBSC' */
LE_FDSC_TABLE_TAG = 0x66647363UL, /**< 'fdsc' */
LE_FEAT_TABLE_TAG = 0x66656174UL, /**< 'feat' */
LE_FMTX_TABLE_TAG = 0x666D7478UL, /**< 'fmtx' */
LE_FPGM_TABLE_TAG = 0x6670676DUL, /**< 'fpgm' */
LE_FVAR_TABLE_TAG = 0x66766172UL, /**< 'fvar' */
LE_GASP_TABLE_TAG = 0x67617370UL, /**< 'gasp' */
LE_GDEF_TABLE_TAG = 0x47444546UL, /**< 'GDEF' */
LE_GLYF_TABLE_TAG = 0x676C7966UL, /**< 'glyf' */
LE_GPOS_TABLE_TAG = 0x47504F53UL, /**< 'GPOS' */
LE_GSUB_TABLE_TAG = 0x47535542UL, /**< 'GSUB' */
LE_GVAR_TABLE_TAG = 0x67766172UL, /**< 'gvar' */
LE_HDMX_TABLE_TAG = 0x68646D78UL, /**< 'hdmx' */
LE_HEAD_TABLE_TAG = 0x68656164UL, /**< 'head' */
LE_HHEA_TABLE_TAG = 0x68686561UL, /**< 'hhea' */
LE_HMTX_TABLE_TAG = 0x686D7478UL, /**< 'hmtx' */
LE_HSTY_TABLE_TAG = 0x68737479UL, /**< 'hsty' */
LE_JUST_TABLE_TAG = 0x6A757374UL, /**< 'just' */
LE_JSTF_TABLE_TAG = 0x4A535446UL, /**< 'JSTF' */
LE_KERN_TABLE_TAG = 0x6B65726EUL, /**< 'kern' */
LE_LCAR_TABLE_TAG = 0x6C636172UL, /**< 'lcar' */
LE_LOCA_TABLE_TAG = 0x6C6F6361UL, /**< 'loca' */
LE_LTSH_TABLE_TAG = 0x4C545348UL, /**< 'LTSH' */
LE_MAXP_TABLE_TAG = 0x6D617870UL, /**< 'maxp' */
LE_MORT_TABLE_TAG = 0x6D6F7274UL, /**< 'mort' */
LE_MORX_TABLE_TAG = 0x6D6F7278UL, /**< 'morx' */
LE_NAME_TABLE_TAG = 0x6E616D65UL, /**< 'name' */
LE_OPBD_TABLE_TAG = 0x6F706264UL, /**< 'opbd' */
LE_OS_2_TABLE_TAG = 0x4F532F32UL, /**< 'OS/2' */
LE_PCLT_TABLE_TAG = 0x50434C54UL, /**< 'PCLT' */
LE_POST_TABLE_TAG = 0x706F7374UL, /**< 'post' */
LE_PREP_TABLE_TAG = 0x70726570UL, /**< 'prep' */
LE_PROP_TABLE_TAG = 0x70726F70UL, /**< 'prop' */
LE_TRAK_TABLE_TAG = 0x7472616BUL, /**< 'trak' */
LE_VDMX_TABLE_TAG = 0x56444D58UL, /**< 'VDMX' */
LE_VHEA_TABLE_TAG = 0x76686561UL, /**< 'vhea' */
LE_VMTX_TABLE_TAG = 0x766D7478UL, /**< 'vmtx' */
LE_VORG_TABLE_TAG = 0x564F5247UL, /**< 'VORG' */
LE_ZAPF_TABLE_TAG = 0x5A617066UL /**< 'Zapf' */
};
/**
* This enumeration defines constants for all
* the common OpenType feature tags.
*
* @stable ICU 3.2
*/
enum LEFeatureTags {
LE_AALT_FEATURE_TAG = 0x61616C74UL, /**< 'aalt' */
LE_ABVF_FEATURE_TAG = 0x61627666UL, /**< 'abvf' */
LE_ABVM_FEATURE_TAG = 0x6162766DUL, /**< 'abvm' */
LE_ABVS_FEATURE_TAG = 0x61627673UL, /**< 'abvs' */
LE_AFRC_FEATURE_TAG = 0x61667263UL, /**< 'afrc' */
LE_AKHN_FEATURE_TAG = 0x616B686EUL, /**< 'akhn' */
LE_BLWF_FEATURE_TAG = 0x626C7766UL, /**< 'blwf' */
LE_BLWM_FEATURE_TAG = 0x626C776DUL, /**< 'blwm' */
LE_BLWS_FEATURE_TAG = 0x626C7773UL, /**< 'blws' */
LE_CALT_FEATURE_TAG = 0x63616C74UL, /**< 'calt' */
LE_CASE_FEATURE_TAG = 0x63617365UL, /**< 'case' */
LE_CCMP_FEATURE_TAG = 0x63636D70UL, /**< 'ccmp' */
LE_CJCT_FEATURE_TAG = 0x636A6374UL, /**< 'cjct' */
LE_CLIG_FEATURE_TAG = 0x636C6967UL, /**< 'clig' */
LE_CPSP_FEATURE_TAG = 0x63707370UL, /**< 'cpsp' */
LE_CSWH_FEATURE_TAG = 0x63737768UL, /**< 'cswh' */
LE_CURS_FEATURE_TAG = 0x63757273UL, /**< 'curs' */
LE_C2SC_FEATURE_TAG = 0x63327363UL, /**< 'c2sc' */
LE_C2PC_FEATURE_TAG = 0x63327063UL, /**< 'c2pc' */
LE_DIST_FEATURE_TAG = 0x64697374UL, /**< 'dist' */
LE_DLIG_FEATURE_TAG = 0x646C6967UL, /**< 'dlig' */
LE_DNOM_FEATURE_TAG = 0x646E6F6DUL, /**< 'dnom' */
LE_EXPT_FEATURE_TAG = 0x65787074UL, /**< 'expt' */
LE_FALT_FEATURE_TAG = 0x66616C74UL, /**< 'falt' */
LE_FIN2_FEATURE_TAG = 0x66696E32UL, /**< 'fin2' */
LE_FIN3_FEATURE_TAG = 0x66696E33UL, /**< 'fin3' */
LE_FINA_FEATURE_TAG = 0x66696E61UL, /**< 'fina' */
LE_FRAC_FEATURE_TAG = 0x66726163UL, /**< 'frac' */
LE_FWID_FEATURE_TAG = 0x66776964UL, /**< 'fwid' */
LE_HALF_FEATURE_TAG = 0x68616C66UL, /**< 'half' */
LE_HALN_FEATURE_TAG = 0x68616C6EUL, /**< 'haln' */
LE_HALT_FEATURE_TAG = 0x68616C74UL, /**< 'halt' */
LE_HIST_FEATURE_TAG = 0x68697374UL, /**< 'hist' */
LE_HKNA_FEATURE_TAG = 0x686B6E61UL, /**< 'hkna' */
LE_HLIG_FEATURE_TAG = 0x686C6967UL, /**< 'hlig' */
LE_HNGL_FEATURE_TAG = 0x686E676CUL, /**< 'hngl' */
LE_HWID_FEATURE_TAG = 0x68776964UL, /**< 'hwid' */
LE_INIT_FEATURE_TAG = 0x696E6974UL, /**< 'init' */
LE_ISOL_FEATURE_TAG = 0x69736F6CUL, /**< 'isol' */
LE_ITAL_FEATURE_TAG = 0x6974616CUL, /**< 'ital' */
LE_JALT_FEATURE_TAG = 0x6A616C74UL, /**< 'jalt' */
LE_JP78_FEATURE_TAG = 0x6A703738UL, /**< 'jp78' */
LE_JP83_FEATURE_TAG = 0x6A703833UL, /**< 'jp83' */
LE_JP90_FEATURE_TAG = 0x6A703930UL, /**< 'jp90' */
LE_KERN_FEATURE_TAG = 0x6B65726EUL, /**< 'kern' */
LE_LFBD_FEATURE_TAG = 0x6C666264UL, /**< 'lfbd' */
LE_LIGA_FEATURE_TAG = 0x6C696761UL, /**< 'liga' */
LE_LJMO_FEATURE_TAG = 0x6C6A6D6FUL, /**< 'ljmo' */
LE_LNUM_FEATURE_TAG = 0x6C6E756DUL, /**< 'lnum' */
LE_LOCL_FEATURE_TAG = 0x6C6F636CUL, /**< 'locl' */
LE_MARK_FEATURE_TAG = 0x6D61726BUL, /**< 'mark' */
LE_MED2_FEATURE_TAG = 0x6D656432UL, /**< 'med2' */
LE_MEDI_FEATURE_TAG = 0x6D656469UL, /**< 'medi' */
LE_MGRK_FEATURE_TAG = 0x6D67726BUL, /**< 'mgrk' */
LE_MKMK_FEATURE_TAG = 0x6D6B6D6BUL, /**< 'mkmk' */
LE_MSET_FEATURE_TAG = 0x6D736574UL, /**< 'mset' */
LE_NALT_FEATURE_TAG = 0x6E616C74UL, /**< 'nalt' */
LE_NLCK_FEATURE_TAG = 0x6E6C636BUL, /**< 'nlck' */
LE_NUKT_FEATURE_TAG = 0x6E756B74UL, /**< 'nukt' */
LE_NUMR_FEATURE_TAG = 0x6E756D72UL, /**< 'numr' */
LE_ONUM_FEATURE_TAG = 0x6F6E756DUL, /**< 'onum' */
LE_OPBD_FEATURE_TAG = 0x6F706264UL, /**< 'opbd' */
LE_ORDN_FEATURE_TAG = 0x6F72646EUL, /**< 'ordn' */
LE_ORNM_FEATURE_TAG = 0x6F726E6DUL, /**< 'ornm' */
LE_PALT_FEATURE_TAG = 0x70616C74UL, /**< 'palt' */
LE_PCAP_FEATURE_TAG = 0x70636170UL, /**< 'pcap' */
LE_PNUM_FEATURE_TAG = 0x706E756DUL, /**< 'pnum' */
LE_PREF_FEATURE_TAG = 0x70726566UL, /**< 'pref' */
LE_PRES_FEATURE_TAG = 0x70726573UL, /**< 'pres' */
LE_PSTF_FEATURE_TAG = 0x70737466UL, /**< 'pstf' */
LE_PSTS_FEATURE_TAG = 0x70737473UL, /**< 'psts' */
LE_PWID_FEATURE_TAG = 0x70776964UL, /**< 'pwid' */
LE_QWID_FEATURE_TAG = 0x71776964UL, /**< 'qwid' */
LE_RAND_FEATURE_TAG = 0x72616E64UL, /**< 'rand' */
LE_RLIG_FEATURE_TAG = 0x726C6967UL, /**< 'rlig' */
LE_RPHF_FEATURE_TAG = 0x72706866UL, /**< 'rphf' */
LE_RKRF_FEATURE_TAG = 0x726B7266UL, /**< 'rkrf' */
LE_RTBD_FEATURE_TAG = 0x72746264UL, /**< 'rtbd' */
LE_RTLA_FEATURE_TAG = 0x72746C61UL, /**< 'rtla' */
LE_RUBY_FEATURE_TAG = 0x72756279UL, /**< 'ruby' */
LE_SALT_FEATURE_TAG = 0x73616C74UL, /**< 'salt' */
LE_SINF_FEATURE_TAG = 0x73696E66UL, /**< 'sinf' */
LE_SIZE_FEATURE_TAG = 0x73697A65UL, /**< 'size' */
LE_SMCP_FEATURE_TAG = 0x736D6370UL, /**< 'smcp' */
LE_SMPL_FEATURE_TAG = 0x736D706CUL, /**< 'smpl' */
LE_SS01_FEATURE_TAG = 0x73733031UL, /**< 'ss01' */
LE_SS02_FEATURE_TAG = 0x73733032UL, /**< 'ss02' */
LE_SS03_FEATURE_TAG = 0x73733033UL, /**< 'ss03' */
LE_SS04_FEATURE_TAG = 0x73733034UL, /**< 'ss04' */
LE_SS05_FEATURE_TAG = 0x73733035UL, /**< 'ss05' */
LE_SS06_FEATURE_TAG = 0x73733036UL, /**< 'ss06' */
LE_SS07_FEATURE_TAG = 0x73733037UL, /**< 'ss07' */
LE_SS08_FEATURE_TAG = 0x73733038UL, /**< 'ss08' */
LE_SS09_FEATURE_TAG = 0x73733039UL, /**< 'ss09' */
LE_SS10_FEATURE_TAG = 0x73733130UL, /**< 'ss10' */
LE_SS11_FEATURE_TAG = 0x73733131UL, /**< 'ss11' */
LE_SS12_FEATURE_TAG = 0x73733132UL, /**< 'ss12' */
LE_SS13_FEATURE_TAG = 0x73733133UL, /**< 'ss13' */
LE_SS14_FEATURE_TAG = 0x73733134UL, /**< 'ss14' */
LE_SS15_FEATURE_TAG = 0x73733135UL, /**< 'ss15' */
LE_SS16_FEATURE_TAG = 0x73733136UL, /**< 'ss16' */
LE_SS17_FEATURE_TAG = 0x73733137UL, /**< 'ss17' */
LE_SS18_FEATURE_TAG = 0x73733138UL, /**< 'ss18' */
LE_SS19_FEATURE_TAG = 0x73733139UL, /**< 'ss19' */
LE_SS20_FEATURE_TAG = 0x73733230UL, /**< 'ss20' */
LE_SUBS_FEATURE_TAG = 0x73756273UL, /**< 'subs' */
LE_SUPS_FEATURE_TAG = 0x73757073UL, /**< 'sups' */
LE_SWSH_FEATURE_TAG = 0x73777368UL, /**< 'swsh' */
LE_TITL_FEATURE_TAG = 0x7469746CUL, /**< 'titl' */
LE_TJMO_FEATURE_TAG = 0x746A6D6FUL, /**< 'tjmo' */
LE_TNAM_FEATURE_TAG = 0x746E616DUL, /**< 'tnam' */
LE_TNUM_FEATURE_TAG = 0x746E756DUL, /**< 'tnum' */
LE_TRAD_FEATURE_TAG = 0x74726164UL, /**< 'trad' */
LE_TWID_FEATURE_TAG = 0x74776964UL, /**< 'twid' */
LE_UNIC_FEATURE_TAG = 0x756E6963UL, /**< 'unic' */
LE_VALT_FEATURE_TAG = 0x76616C74UL, /**< 'valt' */
LE_VATU_FEATURE_TAG = 0x76617475UL, /**< 'vatu' */
LE_VERT_FEATURE_TAG = 0x76657274UL, /**< 'vert' */
LE_VHAL_FEATURE_TAG = 0x7668616CUL, /**< 'vhal' */
LE_VJMO_FEATURE_TAG = 0x766A6D6FUL, /**< 'vjmo' */
LE_VKNA_FEATURE_TAG = 0x766B6E61UL, /**< 'vkna' */
LE_VKRN_FEATURE_TAG = 0x766B726EUL, /**< 'vkrn' */
LE_VPAL_FEATURE_TAG = 0x7670616CUL, /**< 'vpal' */
LE_VRT2_FEATURE_TAG = 0x76727432UL, /**< 'vrt2' */
LE_ZERO_FEATURE_TAG = 0x7A65726FUL /**< 'zero' */
};
/**
* @internal
*/
enum LEFeatureENUMs {
LE_Kerning_FEATURE_ENUM = 0, /**< Requests Kerning. Formerly LayoutEngine::kTypoFlagKern */
LE_Ligatures_FEATURE_ENUM = 1, /**< Requests Ligatures. Formerly LayoutEngine::kTypoFlagLiga */
LE_CLIG_FEATURE_ENUM, /**< Feature specific enum */
LE_DLIG_FEATURE_ENUM, /**< Feature specific enum */
LE_HLIG_FEATURE_ENUM, /**< Feature specific enum */
LE_LIGA_FEATURE_ENUM, /**< Feature specific enum */
LE_RLIG_FEATURE_ENUM, /**< Feature specific enum */
LE_SMCP_FEATURE_ENUM, /**< Feature specific enum */
LE_FRAC_FEATURE_ENUM, /**< Feature specific enum */
LE_AFRC_FEATURE_ENUM, /**< Feature specific enum */
LE_ZERO_FEATURE_ENUM, /**< Feature specific enum */
LE_SWSH_FEATURE_ENUM, /**< Feature specific enum */
LE_CSWH_FEATURE_ENUM, /**< Feature specific enum */
LE_SALT_FEATURE_ENUM, /**< Feature specific enum */
LE_NALT_FEATURE_ENUM, /**< Feature specific enum */
LE_RUBY_FEATURE_ENUM, /**< Feature specific enum */
LE_SS01_FEATURE_ENUM, /**< Feature specific enum */
LE_SS02_FEATURE_ENUM, /**< Feature specific enum */
LE_SS03_FEATURE_ENUM, /**< Feature specific enum */
LE_SS04_FEATURE_ENUM, /**< Feature specific enum */
LE_SS05_FEATURE_ENUM, /**< Feature specific enum */
LE_SS06_FEATURE_ENUM, /**< Feature specific enum */
LE_SS07_FEATURE_ENUM, /**< Feature specific enum */
LE_CHAR_FILTER_FEATURE_ENUM = 31, /**< Apply CharSubstitutionFilter */
LE_FEATURE_ENUM_MAX = LE_CHAR_FILTER_FEATURE_ENUM
};
/**
* Flags for typographic features.
* @internal
* @{
*/
#define LE_Kerning_FEATURE_FLAG (1 << LE_Kerning_FEATURE_ENUM)
#define LE_Ligatures_FEATURE_FLAG (1 << LE_Ligatures_FEATURE_ENUM)
#define LE_CLIG_FEATURE_FLAG (1 << LE_CLIG_FEATURE_ENUM)
#define LE_DLIG_FEATURE_FLAG (1 << LE_DLIG_FEATURE_ENUM)
#define LE_HLIG_FEATURE_FLAG (1 << LE_HLIG_FEATURE_ENUM)
#define LE_LIGA_FEATURE_FLAG (1 << LE_LIGA_FEATURE_ENUM)
#define LE_RLIG_FEATURE_FLAG (1 << LE_RLIG_FEATURE_ENUM)
#define LE_SMCP_FEATURE_FLAG (1 << LE_SMCP_FEATURE_ENUM)
#define LE_FRAC_FEATURE_FLAG (1 << LE_FRAC_FEATURE_ENUM)
#define LE_AFRC_FEATURE_FLAG (1 << LE_AFRC_FEATURE_ENUM)
#define LE_ZERO_FEATURE_FLAG (1 << LE_ZERO_FEATURE_ENUM)
#define LE_SWSH_FEATURE_FLAG (1 << LE_SWSH_FEATURE_ENUM)
#define LE_CSWH_FEATURE_FLAG (1 << LE_CSWH_FEATURE_ENUM)
#define LE_SALT_FEATURE_FLAG (1 << LE_SALT_FEATURE_ENUM)
#define LE_NALT_FEATURE_FLAG (1 << LE_NALT_FEATURE_ENUM)
#define LE_RUBY_FEATURE_FLAG (1 << LE_RUBY_FEATURE_ENUM)
#define LE_SS01_FEATURE_FLAG (1 << LE_SS01_FEATURE_ENUM)
#define LE_SS02_FEATURE_FLAG (1 << LE_SS02_FEATURE_ENUM)
#define LE_SS03_FEATURE_FLAG (1 << LE_SS03_FEATURE_ENUM)
#define LE_SS04_FEATURE_FLAG (1 << LE_SS04_FEATURE_ENUM)
#define LE_SS05_FEATURE_FLAG (1 << LE_SS05_FEATURE_ENUM)
#define LE_SS06_FEATURE_FLAG (1 << LE_SS06_FEATURE_ENUM)
#define LE_SS07_FEATURE_FLAG (1 << LE_SS07_FEATURE_ENUM)
#define LE_CHAR_FILTER_FEATURE_FLAG (1 << LE_CHAR_FILTER_FEATURE_ENUM)
/**
* @}
*/
#define LE_DEFAULT_FEATURE_FLAG (LE_Kerning_FEATURE_FLAG | LE_Ligatures_FEATURE_FLAG) /**< default features */
/**
* Error codes returned by the LayoutEngine.
*
* @stable ICU 2.4
*/
enum LEErrorCode {
/* informational */
LE_NO_SUBFONT_WARNING = U_USING_DEFAULT_WARNING, /**< The font does not contain subfonts. */
/* success */
LE_NO_ERROR = U_ZERO_ERROR, /**< No error, no warning. */
/* failures */
LE_ILLEGAL_ARGUMENT_ERROR = U_ILLEGAL_ARGUMENT_ERROR, /**< An illegal argument was detected. */
LE_MEMORY_ALLOCATION_ERROR = U_MEMORY_ALLOCATION_ERROR, /**< Memory allocation error. */
LE_INDEX_OUT_OF_BOUNDS_ERROR = U_INDEX_OUTOFBOUNDS_ERROR, /**< Trying to access an index that is out of bounds. */
LE_NO_LAYOUT_ERROR = U_UNSUPPORTED_ERROR, /**< You must call layoutChars() first. */
LE_INTERNAL_ERROR = U_INTERNAL_PROGRAM_ERROR, /**< An internal error was encountered. */
LE_FONT_FILE_NOT_FOUND_ERROR = U_FILE_ACCESS_ERROR, /**< The requested font file cannot be opened. */
LE_MISSING_FONT_TABLE_ERROR = U_MISSING_RESOURCE_ERROR /**< The requested font table does not exist. */
};
#ifndef __cplusplus
/**
* Error codes returned by the LayoutEngine.
*
* @stable ICU 2.4
*/
typedef enum LEErrorCode LEErrorCode;
#endif
/**
* A convenience macro to test for the success of a LayoutEngine call.
*
* @stable ICU 2.4
*/
#define LE_SUCCESS(code) (U_SUCCESS((UErrorCode)code))
/**
* A convenience macro to test for the failure of a LayoutEngine call.
*
* @stable ICU 2.4
*/
#define LE_FAILURE(code) (U_FAILURE((UErrorCode)code))
#endif
project/jni/icuuc/include/layout/LayoutEngine.h
-511
View File
@@ -1,511 +0,0 @@
/*
* (C) Copyright IBM Corp. and others 1998-2013 - All Rights Reserved
*/
#ifndef __LAYOUTENGINE_H
#define __LAYOUTENGINE_H
#include "LETypes.h"
/**
* \file
* \brief C++ API: Virtual base class for complex text layout.
*/
U_NAMESPACE_BEGIN
class LEFontInstance;
class LEGlyphFilter;
class LEGlyphStorage;
/**
* This is a virtual base class used to do complex text layout. The text must all
* be in a single font, script, and language. An instance of a LayoutEngine can be
* created by calling the layoutEngineFactory method. Fonts are identified by
* instances of the LEFontInstance class. Script and language codes are identified
* by integer codes, which are defined in ScriptAndLanuageTags.h.
*
* Note that this class is not public API. It is declared public so that it can be
* exported from the library that it is a part of.
*
* The input to the layout process is an array of characters in logical order,
* and a starting X, Y position for the text. The output is an array of glyph indices,
* an array of character indices for the glyphs, and an array of glyph positions.
* These arrays are protected members of LayoutEngine which can be retreived by a
* public method. The reset method can be called to free these arrays so that the
* LayoutEngine can be reused.
*
* The layout process is done in three steps. There is a protected virtual method
* for each step. These methods have a default implementation which only does
* character to glyph mapping and default positioning using the glyph's advance
* widths. Subclasses can override these methods for more advanced layout.
* There is a public method which invokes the steps in the correct order.
*
* The steps are:
*
* 1) Glyph processing - character to glyph mapping and any other glyph processing
* such as ligature substitution and contextual forms.
*
* 2) Glyph positioning - position the glyphs based on their advance widths.
*
* 3) Glyph position adjustments - adjustment of glyph positions for kerning,
* accent placement, etc.
*
* NOTE: in all methods below, output parameters are references to pointers so
* the method can allocate and free the storage as needed. All storage allocated
* in this way is owned by the object which created it, and will be freed when it
* is no longer needed, or when the object's destructor is invoked.
*
* @see LEFontInstance
* @see ScriptAndLanguageTags.h
*
* @stable ICU 2.8
*/
class U_LAYOUT_API LayoutEngine : public UObject {
public:
#ifndef U_HIDE_INTERNAL_API
/** @internal Flag to request kerning. Use LE_Kerning_FEATURE_FLAG instead. */
static const le_int32 kTypoFlagKern;
/** @internal Flag to request ligatures. Use LE_Ligatures_FEATURE_FLAG instead. */
static const le_int32 kTypoFlagLiga;
#endif /* U_HIDE_INTERNAL_API */
protected:
/**
* The object which holds the glyph storage
*
* @internal
*/
LEGlyphStorage *fGlyphStorage;
/**
* The font instance for the text font.
*
* @see LEFontInstance
*
* @internal
*/
const LEFontInstance *fFontInstance;
/**
* The script code for the text
*
* @see ScriptAndLanguageTags.h for script codes.
*
* @internal
*/
le_int32 fScriptCode;
/**
* The langauge code for the text
*
* @see ScriptAndLanguageTags.h for language codes.
*
* @internal
*/
le_int32 fLanguageCode;
/**
* The typographic control flags
*
* @internal
*/
le_int32 fTypoFlags;
/**
* <code>TRUE</code> if <code>mapCharsToGlyphs</code> should replace ZWJ / ZWNJ with a glyph
* with no contours.
*
* @internal
*/
le_bool fFilterZeroWidth;
#ifndef U_HIDE_INTERNAL_API
/**
* This constructs an instance for a given font, script and language. Subclass constructors
* must call this constructor.
*
* @param fontInstance - the font for the text
* @param scriptCode - the script for the text
* @param languageCode - the language for the text
* @param typoFlags - the typographic control flags for the text (a bitfield). Use kTypoFlagKern
* if kerning is desired, kTypoFlagLiga if ligature formation is desired. Others are reserved.
* @param success - set to an error code if the operation fails
*
* @see LEFontInstance
* @see ScriptAndLanguageTags.h
*
* @internal
*/
LayoutEngine(const LEFontInstance *fontInstance,
le_int32 scriptCode,
le_int32 languageCode,
le_int32 typoFlags,
LEErrorCode &success);
#endif /* U_HIDE_INTERNAL_API */
// Do not enclose the protected default constructor with #ifndef U_HIDE_INTERNAL_API
// or else the compiler will create a public default constructor.
/**
* This overrides the default no argument constructor to make it
* difficult for clients to call it. Clients are expected to call
* layoutEngineFactory.
*
* @internal
*/
LayoutEngine();
/**
* This method does any required pre-processing to the input characters. It
* may generate output characters that differ from the input charcters due to
* insertions, deletions, or reorderings. In such cases, it will also generate an
* output character index array reflecting these changes.
*
* Subclasses must override this method.
*
* Input parameters:
* @param chars - the input character context
* @param offset - the index of the first character to process
* @param count - the number of characters to process
* @param max - the number of characters in the input context
* @param rightToLeft - TRUE if the characters are in a right to left directional run
* @param outChars - the output character array, if different from the input
* @param glyphStorage - the object that holds the per-glyph storage. The character index array may be set.
* @param success - set to an error code if the operation fails
*
* @return the output character count (input character count if no change)
*
* @internal
*/
virtual le_int32 characterProcessing(const LEUnicode chars[], le_int32 offset, le_int32 count, le_int32 max, le_bool rightToLeft,
LEUnicode *&outChars, LEGlyphStorage &glyphStorage, LEErrorCode &success);
/**
* This method does the glyph processing. It converts an array of characters
* into an array of glyph indices and character indices. The characters to be
* processed are passed in a surrounding context. The context is specified as
* a starting address and a maximum character count. An offset and a count are
* used to specify the characters to be processed.
*
* The default implementation of this method only does character to glyph mapping.
* Subclasses needing more elaborate glyph processing must override this method.
*
* Input parameters:
* @param chars - the character context
* @param offset - the offset of the first character to process
* @param count - the number of characters to process
* @param max - the number of characters in the context.
* @param rightToLeft - TRUE if the text is in a right to left directional run
* @param glyphStorage - the object which holds the per-glyph storage. The glyph and char indices arrays
* will be set.
*
* Output parameters:
* @param success - set to an error code if the operation fails
*
* @return the number of glyphs in the glyph index array
*
* @internal
*/
virtual le_int32 computeGlyphs(const LEUnicode chars[], le_int32 offset, le_int32 count, le_int32 max, le_bool rightToLeft, LEGlyphStorage &glyphStorage, LEErrorCode &success);
/**
* This method does basic glyph positioning. The default implementation positions
* the glyphs based on their advance widths. This is sufficient for most uses. It
* is not expected that many subclasses will override this method.
*
* Input parameters:
* @param glyphStorage - the object which holds the per-glyph storage. The glyph position array will be set.
* @param x - the starting X position
* @param y - the starting Y position
* @param success - set to an error code if the operation fails
*
* @internal
*/
virtual void positionGlyphs(LEGlyphStorage &glyphStorage, float x, float y, LEErrorCode &success);
/**
* This method does positioning adjustments like accent positioning and
* kerning. The default implementation does nothing. Subclasses needing
* position adjustments must override this method.
*
* Note that this method has both characters and glyphs as input so that
* it can use the character codes to determine glyph types if that information
* isn't directly available. (e.g. Some Arabic OpenType fonts don't have a GDEF
* table)
*
* @param chars - the input character context
* @param offset - the offset of the first character to process
* @param count - the number of characters to process
* @param reverse - <code>TRUE</code> if the glyphs in the glyph array have been reordered
* @param glyphStorage - the object which holds the per-glyph storage. The glyph positions will be
* adjusted as needed.
* @param success - output parameter set to an error code if the operation fails
*
* @internal
*/
virtual void adjustGlyphPositions(const LEUnicode chars[], le_int32 offset, le_int32 count, le_bool reverse, LEGlyphStorage &glyphStorage, LEErrorCode &success);
/**
* This method gets a table from the font associated with
* the text. The default implementation gets the table from
* the font instance. Subclasses which need to get the tables
* some other way must override this method.
*
* @param tableTag - the four byte table tag.
* @param length - length to use
*
* @return the address of the table.
*
* @internal
*/
virtual const void *getFontTable(LETag tableTag, size_t &length) const;
/**
* @deprecated
*/
virtual const void *getFontTable(LETag tableTag) const { size_t ignored; return getFontTable(tableTag, ignored); }
/**
* This method does character to glyph mapping. The default implementation
* uses the font instance to do the mapping. It will allocate the glyph and
* character index arrays if they're not already allocated. If it allocates the
* character index array, it will fill it it.
*
* This method supports right to left
* text with the ability to store the glyphs in reverse order, and by supporting
* character mirroring, which will replace a character which has a left and right
* form, such as parens, with the opposite form before mapping it to a glyph index.
*
* Input parameters:
* @param chars - the input character context
* @param offset - the offset of the first character to be mapped
* @param count - the number of characters to be mapped
* @param reverse - if <code>TRUE</code>, the output will be in reverse order
* @param mirror - if <code>TRUE</code>, do character mirroring
* @param glyphStorage - the object which holds the per-glyph storage. The glyph and char
* indices arrays will be filled in.
* @param success - set to an error code if the operation fails
*
* @see LEFontInstance
*
* @internal
*/
virtual void mapCharsToGlyphs(const LEUnicode chars[], le_int32 offset, le_int32 count, le_bool reverse, le_bool mirror, LEGlyphStorage &glyphStorage, LEErrorCode &success);
#ifndef U_HIDE_INTERNAL_API
/**
* This is a convenience method that forces the advance width of mark
* glyphs to be zero, which is required for proper selection and highlighting.
*
* @param glyphStorage - the object containing the per-glyph storage. The positions array will be modified.
* @param markFilter - used to identify mark glyphs
* @param success - output parameter set to an error code if the operation fails
*
* @see LEGlyphFilter
*
* @internal
*/
static void adjustMarkGlyphs(LEGlyphStorage &glyphStorage, LEGlyphFilter *markFilter, LEErrorCode &success);
/**
* This is a convenience method that forces the advance width of mark
* glyphs to be zero, which is required for proper selection and highlighting.
* This method uses the input characters to identify marks. This is required in
* cases where the font does not contain enough information to identify them based
* on the glyph IDs.
*
* @param chars - the array of input characters
* @param charCount - the number of input characers
* @param glyphStorage - the object containing the per-glyph storage. The positions array will be modified.
* @param reverse - <code>TRUE</code> if the glyph array has been reordered
* @param markFilter - used to identify mark glyphs
* @param success - output parameter set to an error code if the operation fails
*
* @see LEGlyphFilter
*
* @internal
*/
static void adjustMarkGlyphs(const LEUnicode chars[], le_int32 charCount, le_bool reverse, LEGlyphStorage &glyphStorage, LEGlyphFilter *markFilter, LEErrorCode &success);
#endif /* U_HIDE_INTERNAL_API */
public:
/**
* The destructor. It will free any storage allocated for the
* glyph, character index and position arrays by calling the reset
* method. It is declared virtual so that it will be invoked by the
* subclass destructors.
*
* @stable ICU 2.8
*/
virtual ~LayoutEngine();
/**
* This method will invoke the layout steps in their correct order by calling
* the computeGlyphs, positionGlyphs and adjustGlyphPosition methods. It will
* compute the glyph, character index and position arrays.
*
* @param chars - the input character context
* @param offset - the offset of the first character to process
* @param count - the number of characters to process
* @param max - the number of characters in the input context
* @param rightToLeft - TRUE if the characers are in a right to left directional run
* @param x - the initial X position
* @param y - the initial Y position
* @param success - output parameter set to an error code if the operation fails
*
* @return the number of glyphs in the glyph array
*
* Note: The glyph, character index and position array can be accessed
* using the getter methods below.
*
* Note: If you call this method more than once, you must call the reset()
* method first to free the glyph, character index and position arrays
* allocated by the previous call.
*
* @stable ICU 2.8
*/
virtual le_int32 layoutChars(const LEUnicode chars[], le_int32 offset, le_int32 count, le_int32 max, le_bool rightToLeft, float x, float y, LEErrorCode &success);
/**
* This method returns the number of glyphs in the glyph array. Note
* that the number of glyphs will be greater than or equal to the number
* of characters used to create the LayoutEngine.
*
* @return the number of glyphs in the glyph array
*
* @stable ICU 2.8
*/
le_int32 getGlyphCount() const;
/**
* This method copies the glyph array into a caller supplied array.
* The caller must ensure that the array is large enough to hold all
* the glyphs.
*
* @param glyphs - the destiniation glyph array
* @param success - set to an error code if the operation fails
*
* @stable ICU 2.8
*/
void getGlyphs(LEGlyphID glyphs[], LEErrorCode &success) const;
/**
* This method copies the glyph array into a caller supplied array,
* ORing in extra bits. (This functionality is needed by the JDK,
* which uses 32 bits pre glyph idex, with the high 16 bits encoding
* the composite font slot number)
*
* @param glyphs - the destination (32 bit) glyph array
* @param extraBits - this value will be ORed with each glyph index
* @param success - set to an error code if the operation fails
*
* @stable ICU 2.8
*/
virtual void getGlyphs(le_uint32 glyphs[], le_uint32 extraBits, LEErrorCode &success) const;
/**
* This method copies the character index array into a caller supplied array.
* The caller must ensure that the array is large enough to hold a
* character index for each glyph.
*
* @param charIndices - the destiniation character index array
* @param success - set to an error code if the operation fails
*
* @stable ICU 2.8
*/
void getCharIndices(le_int32 charIndices[], LEErrorCode &success) const;
/**
* This method copies the character index array into a caller supplied array.
* The caller must ensure that the array is large enough to hold a
* character index for each glyph.
*
* @param charIndices - the destiniation character index array
* @param indexBase - an offset which will be added to each index
* @param success - set to an error code if the operation fails
*
* @stable ICU 2.8
*/
void getCharIndices(le_int32 charIndices[], le_int32 indexBase, LEErrorCode &success) const;
/**
* This method copies the position array into a caller supplied array.
* The caller must ensure that the array is large enough to hold an
* X and Y position for each glyph, plus an extra X and Y for the
* advance of the last glyph.
*
* @param positions - the destiniation position array
* @param success - set to an error code if the operation fails
*
* @stable ICU 2.8
*/
void getGlyphPositions(float positions[], LEErrorCode &success) const;
/**
* This method returns the X and Y position of the glyph at
* the given index.
*
* Input parameters:
* @param glyphIndex - the index of the glyph
*
* Output parameters:
* @param x - the glyph's X position
* @param y - the glyph's Y position
* @param success - set to an error code if the operation fails
*
* @stable ICU 2.8
*/
void getGlyphPosition(le_int32 glyphIndex, float &x, float &y, LEErrorCode &success) const;
/**
* This method frees the glyph, character index and position arrays
* so that the LayoutEngine can be reused to layout a different
* characer array. (This method is also called by the destructor)
*
* @stable ICU 2.8
*/
virtual void reset();
/**
* This method returns a LayoutEngine capable of laying out text
* in the given font, script and langauge. Note that the LayoutEngine
* returned may be a subclass of LayoutEngine.
*
* @param fontInstance - the font of the text
* @param scriptCode - the script of the text
* @param languageCode - the language of the text
* @param success - output parameter set to an error code if the operation fails
*
* @return a LayoutEngine which can layout text in the given font.
*
* @see LEFontInstance
*
* @stable ICU 2.8
*/
static LayoutEngine *layoutEngineFactory(const LEFontInstance *fontInstance, le_int32 scriptCode, le_int32 languageCode, LEErrorCode &success);
/**
* Override of existing call that provides flags to control typography.
* @stable ICU 3.4
*/
static LayoutEngine *layoutEngineFactory(const LEFontInstance *fontInstance, le_int32 scriptCode, le_int32 languageCode, le_int32 typo_flags, LEErrorCode &success);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.8
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.8
*/
static UClassID getStaticClassID();
};
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/ParagraphLayout.h
-740
View File
@@ -1,740 +0,0 @@
/*
**********************************************************************
* Copyright (C) 2002-2011, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __PARAGRAPHLAYOUT_H
#define __PARAGRAPHLAYOUT_H
/**
* \file
* \brief C++ API: Paragraph Layout
*/
/*
* ParagraphLayout doesn't make much sense without
* BreakIterator...
*/
#include "unicode/uscript.h"
#if ! UCONFIG_NO_BREAK_ITERATION
#include "layout/LETypes.h"
#include "layout/LEFontInstance.h"
#include "layout/LayoutEngine.h"
#include "unicode/ubidi.h"
#include "unicode/brkiter.h"
#include "layout/RunArrays.h"
U_NAMESPACE_BEGIN
/**
* ParagraphLayout.
*
* The <code>ParagraphLayout</code> object will analyze the text into runs of text in the
* same font, script and direction, and will create a <code>LayoutEngine</code> object for each run.
* The <code>LayoutEngine</code> will transform the characters into glyph codes in visual order.
*
* Clients can use this to break a paragraph into lines, and to display the glyphs in each line.
*
*/
class U_LAYOUTEX_API ParagraphLayout : public UObject
{
public:
class VisualRun;
/**
* This class represents a single line of text in a <code>ParagraphLayout</code>. They
* can only be created by calling <code>ParagraphLayout::nextLine()</code>. Each line
* consists of multiple visual runs, represented by <code>ParagraphLayout::VisualRun</code>
* objects.
*
* @see ParagraphLayout
* @see ParagraphLayout::VisualRun
*
* @stable ICU 3.2
*/
class U_LAYOUTEX_API Line : public UObject
{
public:
/**
* The constructor is private since these objects can only be
* created by <code>ParagraphLayout</code>. However, it is the
* clients responsibility to destroy the objects, so the destructor
* is public.
*
* @stable ICU 3.2
*/
~Line();
/**
* Count the number of visual runs in the line.
*
* @return the number of visual runs.
*
* @stable ICU 3.2
*/
inline le_int32 countRuns() const;
/**
* Get the ascent of the line. This is the maximum ascent
* of all the fonts on the line.
*
* @return the ascent of the line.
*
* @stable ICU 3.2
*/
le_int32 getAscent() const;
/**
* Get the descent of the line. This is the maximum descent
* of all the fonts on the line.
*
* @return the descent of the line.
*
* @stable ICU 3.2
*/
le_int32 getDescent() const;
/**
* Get the leading of the line. This is the maximum leading
* of all the fonts on the line.
*
* @return the leading of the line.
*
* @stable ICU 3.2
*/
le_int32 getLeading() const;
/**
* Get the width of the line. This is a convenience method
* which returns the last X position of the last visual run
* in the line.
*
* @return the width of the line.
*
* @stable ICU 2.8
*/
le_int32 getWidth() const;
/**
* Get a <code>ParagraphLayout::VisualRun</code> object for a given
* visual run in the line.
*
* @param runIndex is the index of the run, in visual order.
*
* @return the <code>ParagraphLayout::VisualRun</code> object representing the
* visual run. This object is owned by the <code>Line</code> object which
* created it, and will remain valid for as long as the <code>Line</code>
* object is valid.
*
* @see ParagraphLayout::VisualRun
*
* @stable ICU 3.2
*/
const VisualRun *getVisualRun(le_int32 runIndex) const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
private:
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
friend class ParagraphLayout;
le_int32 fAscent;
le_int32 fDescent;
le_int32 fLeading;
le_int32 fRunCount;
le_int32 fRunCapacity;
VisualRun **fRuns;
inline Line();
inline Line(const Line &other);
inline Line &operator=(const Line & /*other*/) { return *this; };
void computeMetrics();
void append(const LEFontInstance *font, UBiDiDirection direction, le_int32 glyphCount,
const LEGlyphID glyphs[], const float positions[], const le_int32 glyphToCharMap[]);
};
/**
* This object represents a single visual run in a line of text in
* a paragraph. A visual run is text which is in the same font,
* script, and direction. The text is represented by an array of
* <code>LEGlyphIDs</code>, an array of (x, y) glyph positions and
* a table which maps indices into the glyph array to indices into
* the original character array which was used to create the paragraph.
*
* These objects are only created by <code>ParagraphLayout::Line</code> objects,
* so their constructors and destructors are private.
*
* @see ParagraphLayout::Line
*
* @stable ICU 3.2
*/
class U_LAYOUTEX_API VisualRun : public UObject
{
public:
/**
* Get the <code>LEFontInstance</code> object which
* represents the font of the visual run. This will always
* be a non-composite font.
*
* @return the <code>LEFontInstance</code> object which represents the
* font of the visual run.
*
* @see LEFontInstance
*
* @stable ICU 3.2
*/
inline const LEFontInstance *getFont() const;
/**
* Get the direction of the visual run.
*
* @return the direction of the run. This will be UBIDI_LTR if the
* run is left-to-right and UBIDI_RTL if the line is right-to-left.
*
* @stable ICU 3.2
*/
inline UBiDiDirection getDirection() const;
/**
* Get the number of glyphs in the visual run.
*
* @return the number of glyphs.
*
* @stable ICU 3.2
*/
inline le_int32 getGlyphCount() const;
/**
* Get the glyphs in the visual run. Glyphs with the values <code>0xFFFE</code> and
* <code>0xFFFF</code> should be ignored.
*
* @return the address of the array of glyphs for this visual run. The storage
* is owned by the <code>VisualRun</code> object and must not be deleted.
* It will remain valid as long as the <code>VisualRun</code> object is valid.
*
* @stable ICU 3.2
*/
inline const LEGlyphID *getGlyphs() const;
/**
* Get the (x, y) positions of the glyphs in the visual run. To simplify storage
* management, the x and y positions are stored in a single array with the x positions
* at even offsets in the array and the corresponding y position in the following odd offset.
* There is an extra (x, y) pair at the end of the array which represents the advance of
* the final glyph in the run.
*
* @return the address of the array of glyph positions for this visual run. The storage
* is owned by the <code>VisualRun</code> object and must not be deleted.
* It will remain valid as long as the <code>VisualRun</code> object is valid.
*
* @stable ICU 3.2
*/
inline const float *getPositions() const;
/**
* Get the glyph-to-character map for this visual run. This maps the indices into
* the glyph array to indices into the character array used to create the paragraph.
*
* @return the address of the character-to-glyph map for this visual run. The storage
* is owned by the <code>VisualRun</code> object and must not be deleted.
* It will remain valid as long as the <code>VisualRun</code> object is valid.
*
* @stable ICU 3.2
*/
inline const le_int32 *getGlyphToCharMap() const;
/**
* A convenience method which returns the ascent value for the font
* associated with this run.
*
* @return the ascent value of this run's font.
*
* @stable ICU 3.2
*/
inline le_int32 getAscent() const;
/**
* A convenience method which returns the descent value for the font
* associated with this run.
*
* @return the descent value of this run's font.
*
* @stable ICU 3.2
*/
inline le_int32 getDescent() const;
/**
* A convenience method which returns the leading value for the font
* associated with this run.
*
* @return the leading value of this run's font.
*
* @stable ICU 3.2
*/
inline le_int32 getLeading() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
private:
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
const LEFontInstance *fFont;
const UBiDiDirection fDirection;
const le_int32 fGlyphCount;
const LEGlyphID *fGlyphs;
const float *fPositions;
const le_int32 *fGlyphToCharMap;
friend class Line;
inline VisualRun();
inline VisualRun(const VisualRun &other);
inline VisualRun &operator=(const VisualRun &/*other*/) { return *this; };
inline VisualRun(const LEFontInstance *font, UBiDiDirection direction, le_int32 glyphCount,
const LEGlyphID glyphs[], const float positions[], const le_int32 glyphToCharMap[]);
~VisualRun();
};
/**
* Construct a <code>ParagraphLayout</code> object for a styled paragraph. The paragraph is specified
* as runs of text all in the same font. An <code>LEFontInstance</code> object and a limit offset
* are specified for each font run. The limit offset is the offset of the character immediately
* after the font run.
*
* Clients can optionally specify directional runs and / or script runs. If these aren't specified
* they will be computed.
*
* If any errors are encountered during construction, <code>status</code> will be set, and the object
* will be set to be empty.
*
* @param chars is an array of the characters in the paragraph
*
* @param count is the number of characters in the paragraph.
*
* @param fontRuns a pointer to a <code>FontRuns</code> object representing the font runs.
*
* @param levelRuns is a pointer to a <code>ValueRuns</code> object representing the directional levels.
* If this pointer in <code>NULL</code> the levels will be determined by running the Unicde
* Bidi algorithm.
*
* @param scriptRuns is a pointer to a <code>ValueRuns</code> object representing script runs.
* If this pointer in <code>NULL</code> the script runs will be determined using the
* Unicode code points.
*
* @param localeRuns is a pointer to a <code>LocaleRuns</code> object representing locale runs.
* The <code>Locale</code> objects are used to determind the language of the text. If this
* pointer is <code>NULL</code> the default locale will be used for all of the text.
*
* @param paragraphLevel is the directionality of the paragraph, as in the UBiDi object.
*
* @param vertical is <code>TRUE</code> if the paragraph should be set vertically.
*
* @param status will be set to any error code encountered during construction.
*
* @see ubidi.h
* @see LEFontInstance.h
* @see LayoutEngine.h
* @see RunArrays.h
*
* @stable ICU 2.8
*/
ParagraphLayout(const LEUnicode chars[], le_int32 count,
const FontRuns *fontRuns,
const ValueRuns *levelRuns,
const ValueRuns *scriptRuns,
const LocaleRuns *localeRuns,
UBiDiLevel paragraphLevel, le_bool vertical,
LEErrorCode &status);
/**
* The destructor. Virtual so that it works correctly with
* sublcasses.
*
* @stable ICU 3.2
*/
~ParagraphLayout();
// Note: the following is #if 0'd out because there's no good
// way to implement it without either calling layoutEngineFactory()
// or duplicating the logic there...
#if 0
/**
* Examine the given styled paragraph and determine if it contains any text which
* requires complex processing. (i.e. that cannot be correctly rendered by
* just mapping the characters to glyphs and rendering them in order)
*
* @param chars is an array of the characters in the paragraph
*
* @param count is the number of characters in the paragraph.
*
* @param fontRuns is a pointer to a <code>FontRuns</code> object representing the font runs.
*
* @return <code>TRUE</code> if the paragraph contains complex text.
*
* @stable ICU 3.2
*/
static le_bool isComplex(const LEUnicode chars[], le_int32 count, const FontRuns *fontRuns);
#else
/**
* Examine the given text and determine if it contains characters in any
* script which requires complex processing to be rendered correctly.
*
* @param chars is an array of the characters in the paragraph
*
* @param count is the number of characters in the paragraph.
*
* @return <code>TRUE</code> if any of the text requires complex processing.
*
* @stable ICU 3.2
*/
static le_bool isComplex(const LEUnicode chars[], le_int32 count);
#endif
/**
* Return the resolved paragraph level. This is useful for those cases
* where the bidi analysis has determined the level based on the first
* strong character in the paragraph.
*
* @return the resolved paragraph level.
*
* @stable ICU 3.2
*/
inline UBiDiLevel getParagraphLevel();
/**
* Return the directionality of the text in the paragraph.
*
* @return <code>UBIDI_LTR</code> if the text is all left to right,
* <code>UBIDI_RTL</code> if the text is all right to left,
* or <code>UBIDI_MIXED</code> if the text has mixed direction.
*
* @stable ICU 3.2
*/
inline UBiDiDirection getTextDirection();
/**
* Return the max ascent value for all the fonts
* in the paragraph.
*
* @return the ascent value.
*
* @stable ICU 3.2
*/
virtual le_int32 getAscent() const;
/**
* Return the max descent value for all the fonts
* in the paragraph.
*
* @return the decent value.
*
* @stable ICU 3.2
*/
virtual le_int32 getDescent() const;
/**
* Return the max leading value for all the fonts
* in the paragraph.
*
* @return the leading value.
*
* @stable ICU 3.2
*/
virtual le_int32 getLeading() const;
/**
* Reset line breaking to start from the beginning of the paragraph.
*
*
* @stable ICU 3.2
*/
inline void reflow();
#ifndef U_HIDE_INTERNAL_API
/**
*
* Convenience method for determining if paragraph layout processing is complete ( i.e. there
* are no more lines left to process. )
*
* @return true if there are no more lines to be processed
*
* @internal
*/
inline le_bool isDone() const;
#endif /* U_HIDE_INTERNAL_API */
/**
* Return a <code>ParagraphLayout::Line</code> object which represents next line
* in the paragraph. The width of the line is specified each time so that it can
* be varied to support arbitrary paragraph shapes.
*
* @param width is the width of the line. If <code>width</code> is less than or equal
* to zero, a <code>ParagraphLayout::Line</code> object representing the
* rest of the paragraph will be returned.
*
* @return a <code>ParagraphLayout::Line</code> object which represents the line. The caller
* is responsible for deleting the object. Returns <code>NULL</code> if there are no
* more lines in the paragraph.
*
* @see ParagraphLayout::Line
*
* @stable ICU 3.2
*/
Line *nextLine(float width);
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
private:
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
struct StyleRunInfo
{
LayoutEngine *engine;
const LEFontInstance *font;
const Locale *locale;
LEGlyphID *glyphs;
float *positions;
UScriptCode script;
UBiDiLevel level;
le_int32 runBase;
le_int32 runLimit;
le_int32 glyphBase;
le_int32 glyphCount;
};
ParagraphLayout() {};
ParagraphLayout(const ParagraphLayout & /*other*/) : UObject( ){};
inline ParagraphLayout &operator=(const ParagraphLayout & /*other*/) { return *this; };
void computeLevels(UBiDiLevel paragraphLevel);
Line *computeVisualRuns();
void appendRun(Line *line, le_int32 run, le_int32 firstChar, le_int32 lastChar);
void computeScripts();
void computeLocales();
void computeSubFonts(const FontRuns *fontRuns, LEErrorCode &status);
void computeMetrics();
le_int32 getLanguageCode(const Locale *locale);
le_int32 getCharRun(le_int32 charIndex);
static le_bool isComplex(UScriptCode script);
le_int32 previousBreak(le_int32 charIndex);
const LEUnicode *fChars;
le_int32 fCharCount;
const FontRuns *fFontRuns;
const ValueRuns *fLevelRuns;
const ValueRuns *fScriptRuns;
const LocaleRuns *fLocaleRuns;
le_bool fVertical;
le_bool fClientLevels;
le_bool fClientScripts;
le_bool fClientLocales;
UBiDiLevel *fEmbeddingLevels;
le_int32 fAscent;
le_int32 fDescent;
le_int32 fLeading;
le_int32 *fGlyphToCharMap;
le_int32 *fCharToMinGlyphMap;
le_int32 *fCharToMaxGlyphMap;
float *fGlyphWidths;
le_int32 fGlyphCount;
UBiDi *fParaBidi;
UBiDi *fLineBidi;
le_int32 *fStyleRunLimits;
le_int32 *fStyleIndices;
StyleRunInfo *fStyleRunInfo;
le_int32 fStyleRunCount;
BreakIterator *fBreakIterator;
le_int32 fLineStart;
le_int32 fLineEnd;
le_int32 fFirstVisualRun;
le_int32 fLastVisualRun;
float fVisualRunLastX;
float fVisualRunLastY;
};
inline UBiDiLevel ParagraphLayout::getParagraphLevel()
{
return ubidi_getParaLevel(fParaBidi);
}
inline UBiDiDirection ParagraphLayout::getTextDirection()
{
return ubidi_getDirection(fParaBidi);
}
inline void ParagraphLayout::reflow()
{
fLineEnd = 0;
}
inline ParagraphLayout::Line::Line()
: UObject(), fAscent(0), fDescent(0), fLeading(0), fRunCount(0), fRunCapacity(0), fRuns(NULL)
{
// nothing else to do
}
inline ParagraphLayout::Line::Line(const Line & /*other*/)
: UObject(), fAscent(0), fDescent(0), fLeading(0), fRunCount(0), fRunCapacity(0), fRuns(NULL)
{
// nothing else to do
}
inline le_int32 ParagraphLayout::Line::countRuns() const
{
return fRunCount;
}
inline const LEFontInstance *ParagraphLayout::VisualRun::getFont() const
{
return fFont;
}
inline UBiDiDirection ParagraphLayout::VisualRun::getDirection() const
{
return fDirection;
}
inline le_int32 ParagraphLayout::VisualRun::getGlyphCount() const
{
return fGlyphCount;
}
inline const LEGlyphID *ParagraphLayout::VisualRun::getGlyphs() const
{
return fGlyphs;
}
inline const float *ParagraphLayout::VisualRun::getPositions() const
{
return fPositions;
}
inline const le_int32 *ParagraphLayout::VisualRun::getGlyphToCharMap() const
{
return fGlyphToCharMap;
}
inline le_int32 ParagraphLayout::VisualRun::getAscent() const
{
return fFont->getAscent();
}
inline le_int32 ParagraphLayout::VisualRun::getDescent() const
{
return fFont->getDescent();
}
inline le_int32 ParagraphLayout::VisualRun::getLeading() const
{
return fFont->getLeading();
}
inline ParagraphLayout::VisualRun::VisualRun()
: UObject(), fFont(NULL), fDirection(UBIDI_LTR), fGlyphCount(0), fGlyphs(NULL), fPositions(NULL), fGlyphToCharMap(NULL)
{
// nothing
}
inline ParagraphLayout::VisualRun::VisualRun(const VisualRun &/*other*/)
: UObject(), fFont(NULL), fDirection(UBIDI_LTR), fGlyphCount(0), fGlyphs(NULL), fPositions(NULL), fGlyphToCharMap(NULL)
{
// nothing
}
inline ParagraphLayout::VisualRun::VisualRun(const LEFontInstance *font, UBiDiDirection direction, le_int32 glyphCount,
const LEGlyphID glyphs[], const float positions[], const le_int32 glyphToCharMap[])
: fFont(font), fDirection(direction), fGlyphCount(glyphCount),
fGlyphs(glyphs), fPositions(positions), fGlyphToCharMap(glyphToCharMap)
{
// nothing else needs to be done!
}
U_NAMESPACE_END
#endif
#endif
project/jni/icuuc/include/layout/RunArrays.h
-676
View File
@@ -1,676 +0,0 @@
/*
**********************************************************************
* Copyright (C) 2003-2008, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __RUNARRAYS_H
#define __RUNARRAYS_H
#include "layout/LETypes.h"
#include "layout/LEFontInstance.h"
#include "unicode/utypes.h"
#include "unicode/locid.h"
/**
* \file
* \brief C++ API: base class for building classes which represent data that is associated with runs of text.
*/
U_NAMESPACE_BEGIN
/**
* The initial size of an array if it is unspecified.
*
* @stable ICU 3.2
*/
#define INITIAL_CAPACITY 16
/**
* When an array needs to grow, it will double in size until
* it becomes this large, then it will grow by this amount.
*
* @stable ICU 3.2
*/
#define CAPACITY_GROW_LIMIT 128
/**
* The <code>RunArray</code> class is a base class for building classes
* which represent data that is associated with runs of text. This class
* maintains an array of limit indices into the text, subclasses
* provide one or more arrays of data.
*
* @stable ICU 3.2
*/
class U_LAYOUTEX_API RunArray : public UObject
{
public:
/**
* Construct a <code>RunArray</code> object from a pre-existing
* array of limit indices.
*
* @param limits is an array of limit indices. This array must remain
* valid until the <code>RunArray</code> object is destroyed.
*
* @param count is the number of entries in the limit array.
*
* @stable ICU 3.2
*/
inline RunArray(const le_int32 *limits, le_int32 count);
/**
* Construct an empty <code>RunArray</code> object. Clients can add limit
* indices array using the <code>add</code> method.
*
* @param initialCapacity is the initial size of the limit indices array. If
* this value is zero, no array will be allocated.
*
* @see add
*
* @stable ICU 3.2
*/
RunArray(le_int32 initialCapacity);
/**
* The destructor; virtual so that subclass destructors are invoked as well.
*
* @stable ICU 3.2
*/
virtual ~RunArray();
/**
* Get the number of entries in the limit indices array.
*
* @return the number of entries in the limit indices array.
*
* @stable ICU 3.2
*/
inline le_int32 getCount() const;
/**
* Reset the limit indices array. This method sets the number of entries in the
* limit indices array to zero. It does not delete the array.
*
* Note: Subclass arrays will also be reset and not deleted.
*
* @stable ICU 3.6
*/
inline void reset();
/**
* Get the last limit index. This is the number of characters in
* the text.
*
* @return the last limit index.
*
* @stable ICU 3.2
*/
inline le_int32 getLimit() const;
/**
* Get the limit index for a particular run of text.
*
* @param run is the run. This is an index into the limit index array.
*
* @return the limit index for the run, or -1 if <code>run</code> is out of bounds.
*
* @stable ICU 3.2
*/
inline le_int32 getLimit(le_int32 run) const;
/**
* Add a limit index to the limit indices array and return the run index
* where it was stored. If the array does not exist, it will be created by
* calling the <code>init</code> method. If it is full, it will be grown by
* calling the <code>grow</code> method.
*
* If the <code>RunArray</code> object was created with a client-supplied
* limit indices array, this method will return a run index of -1.
*
* Subclasses should not override this method. Rather they should provide
* a new <code>add</code> method which takes a limit index along with whatever
* other data they implement. The new <code>add</code> method should
* first call this method to grow the data arrays, and use the return value
* to store the data in their own arrays.
*
* @param limit is the limit index to add to the array.
*
* @return the run index where the limit index was stored, or -1 if the limit index cannt be stored.
*
* @see init
* @see grow
*
* @stable ICU 3.2
*/
le_int32 add(le_int32 limit);
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
protected:
/**
* Create a data array with the given initial size. This method will be
* called by the <code>add</code> method if there is no limit indices
* array. Subclasses which override this method must also call it from
* the overriding method to create the limit indices array.
*
* @param capacity is the initial size of the data array.
*
* @see add
*
* @stable ICU 3.2
*/
virtual void init(le_int32 capacity);
/**
* Grow a data array to the given initial size. This method will be
* called by the <code>add</code> method if the limit indices
* array is full. Subclasses which override this method must also call it from
* the overriding method to grow the limit indices array.
*
* @param capacity is the initial size of the data array.
*
* @see add
*
* @stable ICU 3.2
*/
virtual void grow(le_int32 capacity);
/**
* Set by the constructors to indicate whether
* or not the client supplied the data arrays.
* If they were supplied by the client, the
* <code>add</code> method won't change the arrays
* and the destructor won't delete them.
*
* @stable ICU 3.2
*/
le_bool fClientArrays;
private:
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
le_int32 ensureCapacity();
inline RunArray();
inline RunArray(const RunArray & /*other*/);
inline RunArray &operator=(const RunArray & /*other*/) { return *this; };
const le_int32 *fLimits;
le_int32 fCount;
le_int32 fCapacity;
};
inline RunArray::RunArray()
: UObject(), fClientArrays(FALSE), fLimits(NULL), fCount(0), fCapacity(0)
{
// nothing else to do...
}
inline RunArray::RunArray(const RunArray & /*other*/)
: UObject(), fClientArrays(FALSE), fLimits(NULL), fCount(0), fCapacity(0)
{
// nothing else to do...
}
inline RunArray::RunArray(const le_int32 *limits, le_int32 count)
: UObject(), fClientArrays(TRUE), fLimits(limits), fCount(count), fCapacity(count)
{
// nothing else to do...
}
inline le_int32 RunArray::getCount() const
{
return fCount;
}
inline void RunArray::reset()
{
fCount = 0;
}
inline le_int32 RunArray::getLimit(le_int32 run) const
{
if (run < 0 || run >= fCount) {
return -1;
}
return fLimits[run];
}
inline le_int32 RunArray::getLimit() const
{
return getLimit(fCount - 1);
}
/**
* The <code>FontRuns</code> class associates pointers to <code>LEFontInstance</code>
* objects with runs of text.
*
* @stable ICU 3.2
*/
class U_LAYOUTEX_API FontRuns : public RunArray
{
public:
/**
* Construct a <code>FontRuns</code> object from pre-existing arrays of fonts
* and limit indices.
*
* @param fonts is the address of an array of pointers to <code>LEFontInstance</code> objects. This
* array, and the <code>LEFontInstance</code> objects to which it points must remain
* valid until the <code>FontRuns</code> object is destroyed.
*
* @param limits is the address of an array of limit indices. This array must remain valid until
* the <code>FontRuns</code> object is destroyed.
*
* @param count is the number of entries in the two arrays.
*
* @stable ICU 3.2
*/
inline FontRuns(const LEFontInstance **fonts, const le_int32 *limits, le_int32 count);
/**
* Construct an empty <code>FontRuns</code> object. Clients can add font and limit
* indices arrays using the <code>add</code> method.
*
* @param initialCapacity is the initial size of the font and limit indices arrays. If
* this value is zero, no arrays will be allocated.
*
* @see add
*
* @stable ICU 3.2
*/
FontRuns(le_int32 initialCapacity);
/**
* The destructor; virtual so that subclass destructors are invoked as well.
*
* @stable ICU 3.2
*/
virtual ~FontRuns();
/**
* Get the <code>LEFontInstance</code> object assoicated with the given run
* of text. Use <code>RunArray::getLimit(run)</code> to get the corresponding
* limit index.
*
* @param run is the index into the font and limit indices arrays.
*
* @return the <code>LEFontInstance</code> associated with the given text run.
*
* @see RunArray::getLimit
*
* @stable ICU 3.2
*/
const LEFontInstance *getFont(le_int32 run) const;
/**
* Add an <code>LEFontInstance</code> and limit index pair to the data arrays and return
* the run index where the data was stored. This method calls
* <code>RunArray::add(limit)</code> which will create or grow the arrays as needed.
*
* If the <code>FontRuns</code> object was created with a client-supplied
* font and limit indices arrays, this method will return a run index of -1.
*
* Subclasses should not override this method. Rather they should provide a new <code>add</code>
* method which takes a font and a limit index along with whatever other data they implement.
* The new <code>add</code> method should first call this method to grow the font and limit indices
* arrays, and use the returned run index to store data their own arrays.
*
* @param font is the address of the <code>LEFontInstance</code> to add. This object must
* remain valid until the <code>FontRuns</code> object is destroyed.
*
* @param limit is the limit index to add
*
* @return the run index where the font and limit index were stored, or -1 if the data cannot be stored.
*
* @stable ICU 3.2
*/
le_int32 add(const LEFontInstance *font, le_int32 limit);
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
protected:
virtual void init(le_int32 capacity);
virtual void grow(le_int32 capacity);
private:
inline FontRuns();
inline FontRuns(const FontRuns &other);
inline FontRuns &operator=(const FontRuns & /*other*/) { return *this; };
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
const LEFontInstance **fFonts;
};
inline FontRuns::FontRuns()
: RunArray(0), fFonts(NULL)
{
// nothing else to do...
}
inline FontRuns::FontRuns(const FontRuns & /*other*/)
: RunArray(0), fFonts(NULL)
{
// nothing else to do...
}
inline FontRuns::FontRuns(const LEFontInstance **fonts, const le_int32 *limits, le_int32 count)
: RunArray(limits, count), fFonts(fonts)
{
// nothing else to do...
}
/**
* The <code>LocaleRuns</code> class associates pointers to <code>Locale</code>
* objects with runs of text.
*
* @stable ICU 3.2
*/
class U_LAYOUTEX_API LocaleRuns : public RunArray
{
public:
/**
* Construct a <code>LocaleRuns</code> object from pre-existing arrays of locales
* and limit indices.
*
* @param locales is the address of an array of pointers to <code>Locale</code> objects. This array,
* and the <code>Locale</code> objects to which it points, must remain valid until
* the <code>LocaleRuns</code> object is destroyed.
*
* @param limits is the address of an array of limit indices. This array must remain valid until the
* <code>LocaleRuns</code> object is destroyed.
*
* @param count is the number of entries in the two arrays.
*
* @stable ICU 3.2
*/
inline LocaleRuns(const Locale **locales, const le_int32 *limits, le_int32 count);
/**
* Construct an empty <code>LocaleRuns</code> object. Clients can add locale and limit
* indices arrays using the <code>add</code> method.
*
* @param initialCapacity is the initial size of the locale and limit indices arrays. If
* this value is zero, no arrays will be allocated.
*
* @see add
*
* @stable ICU 3.2
*/
LocaleRuns(le_int32 initialCapacity);
/**
* The destructor; virtual so that subclass destructors are invoked as well.
*
* @stable ICU 3.2
*/
virtual ~LocaleRuns();
/**
* Get the <code>Locale</code> object assoicated with the given run
* of text. Use <code>RunArray::getLimit(run)</code> to get the corresponding
* limit index.
*
* @param run is the index into the font and limit indices arrays.
*
* @return the <code>Locale</code> associated with the given text run.
*
* @see RunArray::getLimit
*
* @stable ICU 3.2
*/
const Locale *getLocale(le_int32 run) const;
/**
* Add a <code>Locale</code> and limit index pair to the data arrays and return
* the run index where the data was stored. This method calls
* <code>RunArray::add(limit)</code> which will create or grow the arrays as needed.
*
* If the <code>LocaleRuns</code> object was created with a client-supplied
* locale and limit indices arrays, this method will return a run index of -1.
*
* Subclasses should not override this method. Rather they should provide a new <code>add</code>
* method which takes a locale and a limit index along with whatever other data they implement.
* The new <code>add</code> method should first call this method to grow the font and limit indices
* arrays, and use the returned run index to store data their own arrays.
*
* @param locale is the address of the <code>Locale</code> to add. This object must remain valid
* until the <code>LocaleRuns</code> object is destroyed.
*
* @param limit is the limit index to add
*
* @return the run index where the locale and limit index were stored, or -1 if the data cannot be stored.
*
* @stable ICU 3.2
*/
le_int32 add(const Locale *locale, le_int32 limit);
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
protected:
virtual void init(le_int32 capacity);
virtual void grow(le_int32 capacity);
/**
* @internal
*/
const Locale **fLocales;
private:
inline LocaleRuns();
inline LocaleRuns(const LocaleRuns &other);
inline LocaleRuns &operator=(const LocaleRuns & /*other*/) { return *this; };
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
};
inline LocaleRuns::LocaleRuns()
: RunArray(0), fLocales(NULL)
{
// nothing else to do...
}
inline LocaleRuns::LocaleRuns(const LocaleRuns & /*other*/)
: RunArray(0), fLocales(NULL)
{
// nothing else to do...
}
inline LocaleRuns::LocaleRuns(const Locale **locales, const le_int32 *limits, le_int32 count)
: RunArray(limits, count), fLocales(locales)
{
// nothing else to do...
}
/**
* The <code>ValueRuns</code> class associates integer values with runs of text.
*
* @stable ICU 3.2
*/
class U_LAYOUTEX_API ValueRuns : public RunArray
{
public:
/**
* Construct a <code>ValueRuns</code> object from pre-existing arrays of values
* and limit indices.
*
* @param values is the address of an array of integer. This array must remain valid until
* the <code>ValueRuns</code> object is destroyed.
*
* @param limits is the address of an array of limit indices. This array must remain valid until
* the <code>ValueRuns</code> object is destroyed.
*
* @param count is the number of entries in the two arrays.
*
* @stable ICU 3.2
*/
inline ValueRuns(const le_int32 *values, const le_int32 *limits, le_int32 count);
/**
* Construct an empty <code>ValueRuns</code> object. Clients can add value and limit
* indices arrays using the <code>add</code> method.
*
* @param initialCapacity is the initial size of the value and limit indices arrays. If
* this value is zero, no arrays will be allocated.
*
* @see add
*
* @stable ICU 3.2
*/
ValueRuns(le_int32 initialCapacity);
/**
* The destructor; virtual so that subclass destructors are invoked as well.
*
* @stable ICU 3.2
*/
virtual ~ValueRuns();
/**
* Get the integer value assoicated with the given run
* of text. Use <code>RunArray::getLimit(run)</code> to get the corresponding
* limit index.
*
* @param run is the index into the font and limit indices arrays.
*
* @return the integer value associated with the given text run.
*
* @see RunArray::getLimit
*
* @stable ICU 3.2
*/
le_int32 getValue(le_int32 run) const;
/**
* Add an integer value and limit index pair to the data arrays and return
* the run index where the data was stored. This method calls
* <code>RunArray::add(limit)</code> which will create or grow the arrays as needed.
*
* If the <code>ValueRuns</code> object was created with a client-supplied
* font and limit indices arrays, this method will return a run index of -1.
*
* Subclasses should not override this method. Rather they should provide a new <code>add</code>
* method which takes an integer value and a limit index along with whatever other data they implement.
* The new <code>add</code> method should first call this method to grow the font and limit indices
* arrays, and use the returned run index to store data their own arrays.
*
* @param value is the integer value to add
*
* @param limit is the limit index to add
*
* @return the run index where the value and limit index were stored, or -1 if the data cannot be stored.
*
* @stable ICU 3.2
*/
le_int32 add(le_int32 value, le_int32 limit);
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.2
*/
static inline UClassID getStaticClassID() { return (UClassID)&fgClassID; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.2
*/
virtual inline UClassID getDynamicClassID() const { return getStaticClassID(); }
protected:
virtual void init(le_int32 capacity);
virtual void grow(le_int32 capacity);
private:
inline ValueRuns();
inline ValueRuns(const ValueRuns &other);
inline ValueRuns &operator=(const ValueRuns & /*other*/) { return *this; };
/**
* The address of this static class variable serves as this class's ID
* for ICU "poor man's RTTI".
*/
static const char fgClassID;
const le_int32 *fValues;
};
inline ValueRuns::ValueRuns()
: RunArray(0), fValues(NULL)
{
// nothing else to do...
}
inline ValueRuns::ValueRuns(const ValueRuns & /*other*/)
: RunArray(0), fValues(NULL)
{
// nothing else to do...
}
inline ValueRuns::ValueRuns(const le_int32 *values, const le_int32 *limits, le_int32 count)
: RunArray(limits, count), fValues(values)
{
// nothing else to do...
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/layout/loengine.h
-225
View File
@@ -1,225 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2011 - All Rights Reserved
*
*/
#ifndef __LOENGINE_H
#define __LOENGINE_H
#include "LETypes.h"
#ifndef U_HIDE_INTERNAL_API
/**
* \file
* \brief C API for complex text layout.
* \internal
*
* This is a technology preview. The API may
* change significantly.
*
*/
/**
* The opaque type for a LayoutEngine.
*
* @internal
*/
typedef void le_engine;
/**
* The opaque type for a font instance.
*
* @internal
*/
typedef void le_font;
/**
* This function returns an le_engine capable of laying out text
* in the given font, script and langauge. Note that the LayoutEngine
* returned may be a subclass of LayoutEngine.
*
* @param font - the font of the text
* @param scriptCode - the script of the text
* @param languageCode - the language of the text
* @param typo_flags - flags that control layout features like kerning and ligatures.
* @param success - output parameter set to an error code if the operation fails
*
* @return an le_engine which can layout text in the given font.
*
* @internal
*/
U_INTERNAL le_engine * U_EXPORT2
le_create(const le_font *font,
le_int32 scriptCode,
le_int32 languageCode,
le_int32 typo_flags,
LEErrorCode *success);
/**
* This function closes the given LayoutEngine. After
* it returns, the le_engine is no longer valid.
*
* @param engine - the LayoutEngine to close.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_close(le_engine *engine);
/**
* This routine will compute the glyph, character index and position arrays.
*
* @param engine - the LayoutEngine
* @param chars - the input character context
* @param offset - the offset of the first character to process
* @param count - the number of characters to process
* @param max - the number of characters in the input context
* @param rightToLeft - TRUE if the characers are in a right to left directional run
* @param x - the initial X position
* @param y - the initial Y position
* @param success - output parameter set to an error code if the operation fails
*
* @return the number of glyphs in the glyph array
*
* Note: The glyph, character index and position array can be accessed
* using the getter routines below.
*
* Note: If you call this function more than once, you must call the reset()
* function first to free the glyph, character index and position arrays
* allocated by the previous call.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
le_layoutChars(le_engine *engine,
const LEUnicode chars[],
le_int32 offset,
le_int32 count,
le_int32 max,
le_bool rightToLeft,
float x,
float y,
LEErrorCode *success);
/**
* This function returns the number of glyphs in the glyph array. Note
* that the number of glyphs will be greater than or equal to the number
* of characters used to create the LayoutEngine.
*
* @param engine - the LayoutEngine
* @param success - output parameter set to an error code if the operation fails.
*
* @return the number of glyphs in the glyph array
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
le_getGlyphCount(le_engine *engine,
LEErrorCode *success);
/**
* This function copies the glyph array into a caller supplied array.
* The caller must ensure that the array is large enough to hold all
* the glyphs.
*
* @param engine - the LayoutEngine
* @param glyphs - the destiniation glyph array
* @param success - set to an error code if the operation fails
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_getGlyphs(le_engine *engine,
LEGlyphID glyphs[],
LEErrorCode *success);
/**
* This function copies the character index array into a caller supplied array.
* The caller must ensure that the array is large enough to hold a
* character index for each glyph.
*
* @param engine - the LayoutEngine
* @param charIndices - the destiniation character index array
* @param success - set to an error code if the operation fails
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_getCharIndices(le_engine *engine,
le_int32 charIndices[],
LEErrorCode *success);
/**
* This function copies the character index array into a caller supplied array.
* The caller must ensure that the array is large enough to hold a
* character index for each glyph.
*
* @param engine - the LayoutEngine
* @param charIndices - the destiniation character index array
* @param indexBase - an offset that will be added to each index.
* @param success - set to an error code if the operation fails
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_getCharIndicesWithBase(le_engine *engine,
le_int32 charIndices[],
le_int32 indexBase,
LEErrorCode *success);
/**
* This function copies the position array into a caller supplied array.
* The caller must ensure that the array is large enough to hold an
* X and Y position for each glyph, plus an extra X and Y for the
* advance of the last glyph.
*
* @param engine - the LayoutEngine
* @param positions - the destiniation position array
* @param success - set to an error code if the operation fails
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_getGlyphPositions(le_engine *engine,
float positions[],
LEErrorCode *success);
/**
* This function returns the X and Y position of the glyph at
* the given index.
*
* Input parameters:
* @param engine - the LayoutEngine
* @param glyphIndex - the index of the glyph
*
* Output parameters:
* @param x - the glyph's X position
* @param y - the glyph's Y position
* @param success - set to an error code if the operation fails
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_getGlyphPosition(le_engine *engine,
le_int32 glyphIndex,
float *x,
float *y,
LEErrorCode *success);
/**
* This function frees the glyph, character index and position arrays
* so that the LayoutEngine can be reused to layout a different
* characer array. (This function is also called by le_close)
*
* @param engine - the LayoutEngine
* @param success - set to an error code if the operation fails
*
* @internal
*/
U_INTERNAL void U_EXPORT2
le_reset(le_engine *engine,
LEErrorCode *success);
#endif /* U_HIDE_INTERNAL_API */
#endif
project/jni/icuuc/include/layout/playout.h
-466
View File
@@ -1,466 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2011 - All Rights Reserved
*
*/
#ifndef __PLAYOUT_H
#define __PLAYOUT_H
/*
* ParagraphLayout doesn't make much sense without
* BreakIterator...
*/
#include "unicode/ubidi.h"
#if ! UCONFIG_NO_BREAK_ITERATION
#ifndef U_HIDE_INTERNAL_API
#include "layout/LETypes.h"
#include "plruns.h"
/**
* \file
* \brief C API for paragraph layout.
*
* This is a technology preview. The API may
* change significantly.
*
*/
/**
* The opaque type for a paragraph layout.
*
* @internal
*/
typedef void pl_paragraph;
/**
* The opaque type for a line in a paragraph layout.
*
* @internal
*/
typedef void pl_line;
/**
* The opaque type for a visual run in a line.
*
* @internal
*/
typedef void pl_visualRun;
/**
* Construct a <code>ParagraphLayout</code> object for a styled paragraph. The paragraph is specified
* as runs of text all in the same font. An <code>LEFontInstance</code> object and a limit offset
* are specified for each font run. The limit offset is the offset of the character immediately
* after the font run.
*
* Clients can optionally specify directional runs and / or script runs. If these aren't specified
* they will be computed.
*
* If any errors are encountered during construction, <code>status</code> will be set, and the object
* will be set to be empty.
*
* @param chars is an array of the characters in the paragraph
*
* @param count is the number of characters in the paragraph.
*
* @param fontRuns a pointer to a <code>pl_fontRuns</code> object representing the font runs.
*
* @param levelRuns is a pointer to a <code>pl_valueRuns</code> object representing the directional levels.
* If this pointer in <code>NULL</code> the levels will be determined by running the Unicde
* Bidi algorithm.
*
* @param scriptRuns is a pointer to a <code>pl_valueRuns</code> object representing script runs.
* If this pointer in <code>NULL</code> the script runs will be determined using the
* Unicode code points.
*
* @param localeRuns is a pointer to a <code>pl_localeRuns</code> object representing locale runs.
* The <code>Locale</code> objects are used to determind the language of the text. If this
* pointer is <code>NULL</code> the default locale will be used for all of the text.
*
* @param paragraphLevel is the directionality of the paragraph, as in the UBiDi object.
*
* @param vertical is <code>TRUE</code> if the paragraph should be set vertically.
*
* @param status will be set to any error code encountered during construction.
*
* @return a pointer to the newly created <code>pl_paragraph</code> object. The object
* will remain valid until <code>pl_close</code> is called.
*
* @see ubidi.h
* @see longine.h
* @see plruns.h
*
* @internal
*/
U_INTERNAL pl_paragraph * U_EXPORT2
pl_create(const LEUnicode chars[],
le_int32 count,
const pl_fontRuns *fontRuns,
const pl_valueRuns *levelRuns,
const pl_valueRuns *scriptRuns,
const pl_localeRuns *localeRuns,
UBiDiLevel paragraphLevel,
le_bool vertical,
LEErrorCode *status);
/**
* Close the given paragraph layout object.
*
* @param paragraph the <code>pl_paragraph</code> object to be
* closed. Once this routine returns the object
* can no longer be referenced
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_close(pl_paragraph *paragraph);
/**
* Examine the given text and determine if it contains characters in any
* script which requires complex processing to be rendered correctly.
*
* @param chars is an array of the characters in the paragraph
*
* @param count is the number of characters in the paragraph.
*
* @return <code>TRUE</code> if any of the text requires complex processing.
*
* @internal
*/
U_INTERNAL le_bool U_EXPORT2
pl_isComplex(const LEUnicode chars[],
le_int32 count);
/**
* Return the resolved paragraph level. This is useful for those cases
* where the bidi analysis has determined the level based on the first
* strong character in the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* @return the resolved paragraph level.
*
* @internal
*/
U_INTERNAL UBiDiLevel U_EXPORT2
pl_getParagraphLevel(pl_paragraph *paragraph);
/**
* Return the directionality of the text in the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* @return <code>UBIDI_LTR</code> if the text is all left to right,
* <code>UBIDI_RTL</code> if the text is all right to left,
* or <code>UBIDI_MIXED</code> if the text has mixed direction.
*
* @internal
*/
U_INTERNAL UBiDiDirection U_EXPORT2
pl_getTextDirection(pl_paragraph *paragraph);
/**
* Get the max ascent value for all the fonts
* in the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* Return the max ascent value for all the fonts
* in the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* @return the ascent value.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getAscent(const pl_paragraph *paragraph);
/**
* Return the max descent value for all the fonts
* in the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* @return the decent value.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getDescent(const pl_paragraph *paragraph);
/**
* Return the max leading value for all the fonts
* in the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* @return the leading value.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLeading(const pl_paragraph *paragraph);
/**
* Reset line breaking to start from the beginning of the paragraph.
*
* @param paragraph the <code>pl_paragraph</code>
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_reflow(pl_paragraph *paragraph);
/**
* Return a <code>pl_line</code> object which represents next line
* in the paragraph. The width of the line is specified each time so that it can
* be varied to support arbitrary paragraph shapes.
*
* @param paragraph the <code>pl_paragraph</code>
* @param width is the width of the line. If <code>width</code> is less than or equal
* to zero, a <code>ParagraphLayout::Line</code> object representing the
* rest of the paragraph will be returned.
*
* @return a <code>ParagraphLayout::Line</code> object which represents the line. The caller
* is responsible for deleting the object. Returns <code>NULL</code> if there are no
* more lines in the paragraph.
*
* @see pl_line
*
* @internal
*/
U_INTERNAL pl_line * U_EXPORT2
pl_nextLine(pl_paragraph *paragraph, float width);
/**
* Close the given line object. Line objects are created
* by <code>pl_nextLine</code> but it is the client's responsibility
* to close them by calling this routine.
*
* @param line the <code>pl_line</code> object to close.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_closeLine(pl_line *line);
/**
* Count the number of visual runs in the line.
*
* @param line the <code>pl_line</code> object.
*
* @return the number of visual runs.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_countLineRuns(const pl_line *line);
/**
* Get the ascent of the line. This is the maximum ascent
* of all the fonts on the line.
*
* @param line the <code>pl_line</code> object.
*
* @return the ascent of the line.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLineAscent(const pl_line *line);
/**
* Get the descent of the line. This is the maximum descent
* of all the fonts on the line.
*
* @param line the <code>pl_line</code> object.
*
* @return the descent of the line.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLineDescent(const pl_line *line);
/**
* Get the leading of the line. This is the maximum leading
* of all the fonts on the line.
*
* @param line the <code>pl_line</code> object.
*
* @return the leading of the line.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLineLeading(const pl_line *line);
/**
* Get the width of the line. This is a convenience method
* which returns the last X position of the last visual run
* in the line.
*
* @param line the <code>pl_line</code> object.
*
* @return the width of the line.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLineWidth(const pl_line *line);
/**
* Get a <code>ParagraphLayout::VisualRun</code> object for a given
* visual run in the line.
*
* @param line the <code>pl_line</code> object.
* @param runIndex is the index of the run, in visual order.
*
* @return the <code>pl_visualRun</code> object representing the
* visual run. This object is owned by the <code>pl_line</code> object which
* created it, and will remain valid for as long as the <code>pl_line</code>
* object is valid.
*
* @see pl_visualRun
*
* @internal
*/
U_INTERNAL const pl_visualRun * U_EXPORT2
pl_getLineVisualRun(const pl_line *line, le_int32 runIndex);
/**
* Get the <code>le_font</code> object which
* represents the font of the visual run. This will always
* be a non-composite font.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the <code>le_font</code> object which represents the
* font of the visual run.
*
* @see le_font
*
* @internal
*/
U_INTERNAL const le_font * U_EXPORT2
pl_getVisualRunFont(const pl_visualRun *run);
/**
* Get the direction of the visual run.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the direction of the run. This will be <code>UBIDI_LTR</code> if the
* run is left-to-right and <code>UBIDI_RTL</code> if the line is right-to-left.
*
* @internal
*/
U_INTERNAL UBiDiDirection U_EXPORT2
pl_getVisualRunDirection(const pl_visualRun *run);
/**
* Get the number of glyphs in the visual run.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the number of glyphs.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getVisualRunGlyphCount(const pl_visualRun *run);
/**
* Get the glyphs in the visual run. Glyphs with the values <code>0xFFFE</code> and
* <code>0xFFFF</code> should be ignored.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the address of the array of glyphs for this visual run. The storage
* is owned by the <code>pl_visualRun</code> object and must not be deleted.
* It will remain valid as long as the <code>pl_visualRun</code> object is valid.
*
* @internal
*/
U_INTERNAL const LEGlyphID * U_EXPORT2
pl_getVisualRunGlyphs(const pl_visualRun *run);
/**
* Get the (x, y) positions of the glyphs in the visual run. To simplify storage
* management, the x and y positions are stored in a single array with the x positions
* at even offsets in the array and the corresponding y position in the following odd offset.
* There is an extra (x, y) pair at the end of the array which represents the advance of
* the final glyph in the run.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the address of the array of glyph positions for this visual run. The storage
* is owned by the <code>pl_visualRun</code> object and must not be deleted.
* It will remain valid as long as the <code>pl_visualRun</code> object is valid.
*
* @internal
*/
U_INTERNAL const float * U_EXPORT2
pl_getVisualRunPositions(const pl_visualRun *run);
/**
* Get the glyph-to-character map for this visual run. This maps the indices into
* the glyph array to indices into the character array used to create the paragraph.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the address of the character-to-glyph map for this visual run. The storage
* is owned by the <code>pl_visualRun</code> object and must not be deleted.
* It will remain valid as long as the <code>pl_visualRun</code> object is valid.
*
* @internal
*/
U_INTERNAL const le_int32 * U_EXPORT2
pl_getVisualRunGlyphToCharMap(const pl_visualRun *run);
/**
* A convenience method which returns the ascent value for the font
* associated with this run.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the ascent value of this run's font.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getVisualRunAscent(const pl_visualRun *run);
/**
* A convenience method which returns the descent value for the font
* associated with this run.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the descent value of this run's font.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getVisualRunDescent(const pl_visualRun *run);
/**
* A convenience method which returns the leading value for the font
* associated with this run.
*
* @param run the <code>pl_visualRun</code> object.
*
* @return the leading value of this run's font.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getVisualRunLeading(const pl_visualRun *run);
#endif /* U_HIDE_INTERNAL_API */
#endif
#endif
project/jni/icuuc/include/layout/plruns.h
-441
View File
@@ -1,441 +0,0 @@
/*
*
* (C) Copyright IBM Corp. 1998-2011 - All Rights Reserved
*
*/
#ifndef __PLRUNS_H
#define __PLRUNS_H
#include "unicode/utypes.h"
#ifndef U_HIDE_INTERNAL_API
#include "unicode/ubidi.h"
#include "layout/LETypes.h"
#include "layout/loengine.h"
/**
* Opaque datatype representing an array of font runs
*/
typedef void pl_fontRuns;
/**
* Opaque datatype representing an array of value runs
*/
typedef void pl_valueRuns;
/**
* Opaque datatype representing an array of locale runs
*/
typedef void pl_localeRuns;
/**
* \file
* \brief C API for run arrays.
*
* This is a technology preview. The API may
* change significantly.
*
*/
/**
* Construct a <code>pl_fontRuns</code> object from pre-existing arrays of fonts
* and limit indices.
*
* @param fonts is the address of an array of pointers to <code>le_font</code> objects. This
* array, and the <code>le_font</code> objects to which it points must remain
* valid until the <code>pl_fontRuns</code> object is closed.
*
* @param limits is the address of an array of limit indices. This array must remain valid until
* the <code>pl_fontRuns</code> object is closed.
*
* @param count is the number of entries in the two arrays.
*
* @internal
*/
U_INTERNAL pl_fontRuns * U_EXPORT2
pl_openFontRuns(const le_font **fonts,
const le_int32 *limits,
le_int32 count);
/**
* Construct an empty <code>pl_fontRuns</code> object. Clients can add font and limit
* indices arrays using the <code>pl_addFontRun</code> routine.
*
* @param initialCapacity is the initial size of the font and limit indices arrays. If
* this value is zero, no arrays will be allocated.
*
* @see pl_addFontRun
*
* @internal
*/
U_INTERNAL pl_fontRuns * U_EXPORT2
pl_openEmptyFontRuns(le_int32 initialCapacity);
/**
* Close the given <code>pl_fontRuns</code> object. Once this
* call returns, the object can no longer be referenced.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_closeFontRuns(pl_fontRuns *fontRuns);
/**
* Get the number of font runs.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
*
* @return the number of entries in the limit indices array.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getFontRunCount(const pl_fontRuns *fontRuns);
/**
* Reset the number of font runs to zero.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_resetFontRuns(pl_fontRuns *fontRuns);
/**
* Get the limit index for the last font run. This is the
* number of characters in the text.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
*
* @return the last limit index.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getFontRunLastLimit(const pl_fontRuns *fontRuns);
/**
* Get the limit index for a particular font run.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
* @param run is the run. This is an index into the limit index array.
*
* @return the limit index for the run, or -1 if <code>run</code> is out of bounds.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getFontRunLimit(const pl_fontRuns *fontRuns,
le_int32 run);
/**
* Get the <code>le_font</code> object assoicated with the given run
* of text. Use <code>pl_getFontRunLimit(run)</code> to get the corresponding
* limit index.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
* @param run is the index into the font and limit indices arrays.
*
* @return the <code>le_font</code> associated with the given text run.
*
* @internal
*/
U_INTERNAL const le_font * U_EXPORT2
pl_getFontRunFont(const pl_fontRuns *fontRuns,
le_int32 run);
/**
* Add a new font run to the given <code>pl_fontRuns</code> object.
*
* If the <code>pl_fontRuns</code> object was not created by calling
* <code>pl_openEmptyFontRuns</code>, this method will return a run index of -1.
*
* @param fontRuns is the <code>pl_fontRuns</code> object.
*
* @param font is the address of the <code>le_font</code> to add. This object must
* remain valid until the <code>pl_fontRuns</code> object is closed.
*
* @param limit is the limit index to add
*
* @return the run index where the font and limit index were stored, or -1 if
* the run cannot be added.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_addFontRun(pl_fontRuns *fontRuns,
const le_font *font,
le_int32 limit);
/**
* Construct a <code>pl_valueRuns</code> object from pre-existing arrays of values
* and limit indices.
*
* @param values is the address of an array of values. This array must remain valid until
the <code>pl_valueRuns</code> object is closed.
*
* @param limits is the address of an array of limit indices. This array must remain valid until
* the <code>pl_valueRuns</code> object is closed.
*
* @param count is the number of entries in the two arrays.
*
* @internal
*/
U_INTERNAL pl_valueRuns * U_EXPORT2
pl_openValueRuns(const le_int32 *values,
const le_int32 *limits,
le_int32 count);
/**
* Construct an empty <code>pl_valueRuns</code> object. Clients can add values and limits
* using the <code>pl_addValueRun</code> routine.
*
* @param initialCapacity is the initial size of the value and limit indices arrays. If
* this value is zero, no arrays will be allocated.
*
* @see pl_addValueRun
*
* @internal
*/
U_INTERNAL pl_valueRuns * U_EXPORT2
pl_openEmptyValueRuns(le_int32 initialCapacity);
/**
* Close the given <code>pl_valueRuns</code> object. Once this
* call returns, the object can no longer be referenced.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_closeValueRuns(pl_valueRuns *valueRuns);
/**
* Get the number of value runs.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
*
* @return the number of value runs.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getValueRunCount(const pl_valueRuns *valueRuns);
/**
* Reset the number of value runs to zero.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_resetValueRuns(pl_valueRuns *valueRuns);
/**
* Get the limit index for the last value run. This is the
* number of characters in the text.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
*
* @return the last limit index.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getValueRunLastLimit(const pl_valueRuns *valueRuns);
/**
* Get the limit index for a particular value run.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
* @param run is the run index.
*
* @return the limit index for the run, or -1 if <code>run</code> is out of bounds.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getValueRunLimit(const pl_valueRuns *valueRuns,
le_int32 run);
/**
* Get the value assoicated with the given run * of text. Use
* <code>pl_getValueRunLimit(run)</code> to get the corresponding
* limit index.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
* @param run is the run index.
*
* @return the value associated with the given text run.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getValueRunValue(const pl_valueRuns *valueRuns,
le_int32 run);
/**
* Add a new font run to the given <code>pl_valueRuns</code> object.
*
* If the <code>pl_valueRuns</code> object was not created by calling
* <code>pl_openEmptyFontRuns</code>, this method will return a run index of -1.
*
* @param valueRuns is the <code>pl_valueRuns</code> object.
*
* @param value is the value to add.
*
* @param limit is the limit index to add
*
* @return the run index where the font and limit index were stored, or -1 if
* the run cannot be added.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_addValueRun(pl_valueRuns *valueRuns,
le_int32 value,
le_int32 limit);
/**
* Construct a <code>pl_localeRuns</code> object from pre-existing arrays of fonts
* and limit indices.
*
* @param locales is the address of an array of pointers to locale name strings. This
* array must remain valid until the <code>pl_localeRuns</code> object is destroyed.
*
* @param limits is the address of an array of limit indices. This array must remain valid until
* the <code>pl_valueRuns</code> object is destroyed.
*
* @param count is the number of entries in the two arrays.
*
* @internal
*/
U_INTERNAL pl_localeRuns * U_EXPORT2
pl_openLocaleRuns(const char **locales,
const le_int32 *limits,
le_int32 count);
/**
* Construct an empty <code>pl_localeRuns</code> object. Clients can add font and limit
* indices arrays using the <code>pl_addFontRun</code> routine.
*
* @param initialCapacity is the initial size of the font and limit indices arrays. If
* this value is zero, no arrays will be allocated.
*
* @see pl_addLocaleRun
*
* @internal
*/
U_INTERNAL pl_localeRuns * U_EXPORT2
pl_openEmptyLocaleRuns(le_int32 initialCapacity);
/**
* Close the given <code>pl_localeRuns</code> object. Once this
* call returns, the object can no longer be referenced.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_closeLocaleRuns(pl_localeRuns *localeRuns);
/**
* Get the number of font runs.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
*
* @return the number of entries in the limit indices array.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLocaleRunCount(const pl_localeRuns *localeRuns);
/**
* Reset the number of locale runs to zero.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
*
* @internal
*/
U_INTERNAL void U_EXPORT2
pl_resetLocaleRuns(pl_localeRuns *localeRuns);
/**
* Get the limit index for the last font run. This is the
* number of characters in the text.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
*
* @return the last limit index.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLocaleRunLastLimit(const pl_localeRuns *localeRuns);
/**
* Get the limit index for a particular font run.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
* @param run is the run. This is an index into the limit index array.
*
* @return the limit index for the run, or -1 if <code>run</code> is out of bounds.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_getLocaleRunLimit(const pl_localeRuns *localeRuns,
le_int32 run);
/**
* Get the <code>le_font</code> object assoicated with the given run
* of text. Use <code>pl_getLocaleRunLimit(run)</code> to get the corresponding
* limit index.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
* @param run is the index into the font and limit indices arrays.
*
* @return the <code>le_font</code> associated with the given text run.
*
* @internal
*/
U_INTERNAL const char * U_EXPORT2
pl_getLocaleRunLocale(const pl_localeRuns *localeRuns,
le_int32 run);
/**
* Add a new run to the given <code>pl_localeRuns</code> object.
*
* If the <code>pl_localeRuns</code> object was not created by calling
* <code>pl_openEmptyLocaleRuns</code>, this method will return a run index of -1.
*
* @param localeRuns is the <code>pl_localeRuns</code> object.
*
* @param locale is the name of the locale to add. This name must
* remain valid until the <code>pl_localeRuns</code> object is closed.
*
* @param limit is the limit index to add
*
* @return the run index where the font and limit index were stored, or -1 if
* the run cannot be added.
*
* @internal
*/
U_INTERNAL le_int32 U_EXPORT2
pl_addLocaleRun(pl_localeRuns *localeRuns,
const char *locale,
le_int32 limit);
#endif /* U_HIDE_INTERNAL_API */
#endif
project/jni/icuuc/include/unicode/alphaindex.h
-761
View File
@@ -1,761 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2011-2013 International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
*/
#ifndef INDEXCHARS_H
#define INDEXCHARS_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/locid.h"
#if !UCONFIG_NO_COLLATION && !UCONFIG_NO_NORMALIZATION
/**
* \file
* \brief C++ API: Index Characters
*/
U_CDECL_BEGIN
/**
* Constants for Alphabetic Index Label Types.
* The form of these enum constants anticipates having a plain C API
* for Alphabetic Indexes that will also use them.
* @stable ICU 4.8
*/
typedef enum UAlphabeticIndexLabelType {
/**
* Normal Label, typically the starting letter of the names
* in the bucket with this label.
* @stable ICU 4.8
*/
U_ALPHAINDEX_NORMAL = 0,
/**
* Undeflow Label. The bucket with this label contains names
* in scripts that sort before any of the bucket labels in this index.
* @stable ICU 4.8
*/
U_ALPHAINDEX_UNDERFLOW = 1,
/**
* Inflow Label. The bucket with this label contains names
* in scripts that sort between two of the bucket labels in this index.
* Inflow labels are created when an index contains normal labels for
* multiple scripts, and skips other scripts that sort between some of the
* included scripts.
* @stable ICU 4.8
*/
U_ALPHAINDEX_INFLOW = 2,
/**
* Overflow Label. Te bucket with this label contains names in scripts
* that sort after all of the bucket labels in this index.
* @stable ICU 4.8
*/
U_ALPHAINDEX_OVERFLOW = 3
} UAlphabeticIndexLabelType;
struct UHashtable;
U_CDECL_END
U_NAMESPACE_BEGIN
// Forward Declarations
class BucketList;
class Collator;
class RuleBasedCollator;
class StringEnumeration;
class UnicodeSet;
class UVector;
/**
* AlphabeticIndex supports the creation of a UI index appropriate for a given language.
* It can support either direct use, or use with a client that doesn't support localized collation.
* The following is an example of what an index might look like in a UI:
*
* <pre>
* <b>... A B C D E F G H I J K L M N O P Q R S T U V W X Y Z ...</b>
*
* <b>A</b>
* Addison
* Albertson
* Azensky
* <b>B</b>
* Baker
* ...
* </pre>
*
* The class can generate a list of labels for use as a UI "index", that is, a list of
* clickable characters (or character sequences) that allow the user to see a segment
* (bucket) of a larger "target" list. That is, each label corresponds to a bucket in
* the target list, where everything in the bucket is greater than or equal to the character
* (according to the locale's collation). Strings can be added to the index;
* they will be in sorted order in the right bucket.
* <p>
* The class also supports having buckets for strings before the first (underflow),
* after the last (overflow), and between scripts (inflow). For example, if the index
* is constructed with labels for Russian and English, Greek characters would fall
* into an inflow bucket between the other two scripts.
* <p>
* The AlphabeticIndex class is not intended for public subclassing.
*
* <p><em>Note:</em> If you expect to have a lot of ASCII or Latin characters
* as well as characters from the user's language,
* then it is a good idea to call addLabels(Locale::getEnglish(), status).</p>
*
* <h2>Direct Use</h2>
* <p>The following shows an example of building an index directly.
* The "show..." methods below are just to illustrate usage.
*
* <pre>
* // Create a simple index. "Item" is assumed to be an application
* // defined type that the application's UI and other processing knows about,
* // and that has a name.
*
* UErrorCode status = U_ZERO_ERROR;
* AlphabeticIndex index = new AlphabeticIndex(desiredLocale, status);
* index->addLabels(additionalLocale, status);
* for (Item *item in some source of Items ) {
* index->addRecord(item->name(), item, status);
* }
* ...
* // Show index at top. We could skip or gray out empty buckets
*
* while (index->nextBucket(status)) {
* if (showAll || index->getBucketRecordCount() != 0) {
* showLabelAtTop(UI, index->getBucketLabel());
* }
* }
* ...
* // Show the buckets with their contents, skipping empty buckets
*
* index->resetBucketIterator(status);
* while (index->nextBucket(status)) {
* if (index->getBucketRecordCount() != 0) {
* showLabelInList(UI, index->getBucketLabel());
* while (index->nextRecord(status)) {
* showIndexedItem(UI, static_cast<Item *>(index->getRecordData()))
* </pre>
*
* The caller can build different UIs using this class.
* For example, an index character could be omitted or grayed-out
* if its bucket is empty. Small buckets could also be combined based on size, such as:
*
* <pre>
* <b>... A-F G-N O-Z ...</b>
* </pre>
*
* <h2>Client Support</h2>
* <p>Callers can also use the AlphabeticIndex::ImmutableIndex, or the AlphabeticIndex itself,
* to support sorting on a client that doesn't support AlphabeticIndex functionality.
*
* <p>The ImmutableIndex is both immutable and thread-safe.
* The corresponding AlphabeticIndex methods are not thread-safe because
* they "lazily" build the index buckets.
* <ul>
* <li>ImmutableIndex.getBucket(index) provides random access to all
* buckets and their labels and label types.
* <li>The AlphabeticIndex bucket iterator or ImmutableIndex.getBucket(0..getBucketCount-1)
* can be used to get a list of the labels,
* such as "...", "A", "B",..., and send that list to the client.
* <li>When the client has a new name, it sends that name to the server.
* The server needs to call the following methods,
* and communicate the bucketIndex and collationKey back to the client.
*
* <pre>
* int32_t bucketIndex = index.getBucketIndex(name, status);
* const UnicodeString &label = immutableIndex.getBucket(bucketIndex)->getLabel(); // optional
* int32_t skLength = collator.getSortKey(name, sk, skCapacity);
* </pre>
*
* <li>The client would put the name (and associated information) into its bucket for bucketIndex. The sort key sk is a
* sequence of bytes that can be compared with a binary compare, and produce the right localized result.</li>
* </ul>
*
* @stable ICU 4.8
*/
class U_I18N_API AlphabeticIndex: public UObject {
public:
#ifdef U_HIDE_DRAFT_API
class Bucket;
#else
/**
* An index "bucket" with a label string and type.
* It is referenced by getBucketIndex(),
* and returned by ImmutableIndex.getBucket().
*
* The Bucket class is not intended for public subclassing.
* @draft ICU 51
*/
class U_I18N_API Bucket : public UObject {
public:
/**
* Destructor.
* @draft ICU 51
*/
virtual ~Bucket();
/**
* Returns the label string.
*
* @return the label string for the bucket
* @draft ICU 51
*/
const UnicodeString &getLabel() const { return label_; }
/**
* Returns whether this bucket is a normal, underflow, overflow, or inflow bucket.
*
* @return the bucket label type
* @draft ICU 51
*/
UAlphabeticIndexLabelType getLabelType() const { return labelType_; }
private:
friend class AlphabeticIndex;
friend class BucketList;
UnicodeString label_;
UnicodeString lowerBoundary_;
UAlphabeticIndexLabelType labelType_;
Bucket *displayBucket_;
int32_t displayIndex_;
UVector *records_; // Records are owned by the inputList_ vector.
Bucket(const UnicodeString &label, // Parameter strings are copied.
const UnicodeString &lowerBoundary,
UAlphabeticIndexLabelType type);
};
/**
* Immutable, thread-safe version of AlphabeticIndex.
* This class provides thread-safe methods for bucketing,
* and random access to buckets and their properties,
* but does not offer adding records to the index.
*
* The ImmutableIndex class is not intended for public subclassing.
*
* @draft ICU 51
*/
class U_I18N_API ImmutableIndex : public UObject {
public:
/**
* Destructor.
* @draft ICU 51
*/
virtual ~ImmutableIndex();
/**
* Returns the number of index buckets and labels, including underflow/inflow/overflow.
*
* @return the number of index buckets
* @draft ICU 51
*/
int32_t getBucketCount() const;
/**
* Finds the index bucket for the given name and returns the number of that bucket.
* Use getBucket() to get the bucket's properties.
*
* @param name the string to be sorted into an index bucket
* @return the bucket number for the name
* @draft ICU 51
*/
int32_t getBucketIndex(const UnicodeString &name, UErrorCode &errorCode) const;
/**
* Returns the index-th bucket. Returns NULL if the index is out of range.
*
* @param index bucket number
* @return the index-th bucket
* @draft ICU 51
*/
const Bucket *getBucket(int32_t index) const;
private:
friend class AlphabeticIndex;
ImmutableIndex(BucketList *bucketList, Collator *collatorPrimaryOnly)
: buckets_(bucketList), collatorPrimaryOnly_(collatorPrimaryOnly) {}
BucketList *buckets_;
Collator *collatorPrimaryOnly_;
};
#endif /* U_HIDE_DRAFT_API */
/**
* Construct an AlphabeticIndex object for the specified locale. If the locale's
* data does not include index characters, a set of them will be
* synthesized based on the locale's exemplar characters. The locale
* determines the sorting order for both the index characters and the
* user item names appearing under each Index character.
*
* @param locale the desired locale.
* @param status Error code, will be set with the reason if the construction
* of the AlphabeticIndex object fails.
* @stable ICU 4.8
*/
AlphabeticIndex(const Locale &locale, UErrorCode &status);
#ifndef U_HIDE_DRAFT_API
/**
* Construct an AlphabeticIndex that uses a specific collator.
*
* The index will be created with no labels; the addLabels() function must be called
* after creation to add the desired labels to the index.
*
* The index adopts the collator, and is responsible for deleting it.
* The caller should make no further use of the collator after creating the index.
*
* @param collator The collator to use to order the contents of this index.
* @param status Error code, will be set with the reason if the
* operation fails.
* @draft ICU 51
*/
AlphabeticIndex(RuleBasedCollator *collator, UErrorCode &status);
#endif /* U_HIDE_DRAFT_API */
/**
* Add Labels to this Index. The labels are additions to those
* that are already in the index; they do not replace the existing
* ones.
* @param additions The additional characters to add to the index, such as A-Z.
* @param status Error code, will be set with the reason if the
* operation fails.
* @return this, for chaining
* @stable ICU 4.8
*/
virtual AlphabeticIndex &addLabels(const UnicodeSet &additions, UErrorCode &status);
/**
* Add the index characters from a Locale to the index. The labels
* are added to those that are already in the index; they do not replace the
* existing index characters. The collation order for this index is not
* changed; it remains that of the locale that was originally specified
* when creating this Index.
*
* @param locale The locale whose index characters are to be added.
* @param status Error code, will be set with the reason if the
* operation fails.
* @return this, for chaining
* @stable ICU 4.8
*/
virtual AlphabeticIndex &addLabels(const Locale &locale, UErrorCode &status);
/**
* Destructor
* @stable ICU 4.8
*/
virtual ~AlphabeticIndex();
#ifndef U_HIDE_DRAFT_API
/**
* Builds an immutable, thread-safe version of this instance, without data records.
*
* @return an immutable index instance
* @draft ICU 51
*/
ImmutableIndex *buildImmutableIndex(UErrorCode &errorCode);
#endif /* U_HIDE_DRAFT_API */
/**
* Get the Collator that establishes the ordering of the items in this index.
* Ownership of the collator remains with the AlphabeticIndex instance.
*
* The returned collator is a reference to the internal collator used by this
* index. It may be safely used to compare the names of items or to get
* sort keys for names. However if any settings need to be changed,
* or other non-const methods called, a cloned copy must be made first.
*
* @return The collator
* @stable ICU 4.8
*/
virtual const RuleBasedCollator &getCollator() const;
/**
* Get the default label used for abbreviated buckets <i>between</i> other index characters.
* For example, consider the labels when Latin and Greek are used:
* X Y Z ... &#x0391; &#x0392; &#x0393;.
*
* @return inflow label
* @stable ICU 4.8
*/
virtual const UnicodeString &getInflowLabel() const;
/**
* Set the default label used for abbreviated buckets <i>between</i> other index characters.
* An inflow label will be automatically inserted if two otherwise-adjacent label characters
* are from different scripts, e.g. Latin and Cyrillic, and a third script, e.g. Greek,
* sorts between the two. The default inflow character is an ellipsis (...)
*
* @param inflowLabel the new Inflow label.
* @param status Error code, will be set with the reason if the operation fails.
* @return this
* @stable ICU 4.8
*/
virtual AlphabeticIndex &setInflowLabel(const UnicodeString &inflowLabel, UErrorCode &status);
/**
* Get the special label used for items that sort after the last normal label,
* and that would not otherwise have an appropriate label.
*
* @return the overflow label
* @stable ICU 4.8
*/
virtual const UnicodeString &getOverflowLabel() const;
/**
* Set the label used for items that sort after the last normal label,
* and that would not otherwise have an appropriate label.
*
* @param overflowLabel the new overflow label.
* @param status Error code, will be set with the reason if the operation fails.
* @return this
* @stable ICU 4.8
*/
virtual AlphabeticIndex &setOverflowLabel(const UnicodeString &overflowLabel, UErrorCode &status);
/**
* Get the special label used for items that sort before the first normal label,
* and that would not otherwise have an appropriate label.
*
* @return underflow label
* @stable ICU 4.8
*/
virtual const UnicodeString &getUnderflowLabel() const;
/**
* Set the label used for items that sort before the first normal label,
* and that would not otherwise have an appropriate label.
*
* @param underflowLabel the new underflow label.
* @param status Error code, will be set with the reason if the operation fails.
* @return this
* @stable ICU 4.8
*/
virtual AlphabeticIndex &setUnderflowLabel(const UnicodeString &underflowLabel, UErrorCode &status);
/**
* Get the limit on the number of labels permitted in the index.
* The number does not include over, under and inflow labels.
*
* @return maxLabelCount maximum number of labels.
* @stable ICU 4.8
*/
virtual int32_t getMaxLabelCount() const;
/**
* Set a limit on the number of labels permitted in the index.
* The number does not include over, under and inflow labels.
* Currently, if the number is exceeded, then every
* nth item is removed to bring the count down.
* A more sophisticated mechanism may be available in the future.
*
* @param maxLabelCount the maximum number of labels.
* @param status error code
* @return This, for chaining
* @stable ICU 4.8
*/
virtual AlphabeticIndex &setMaxLabelCount(int32_t maxLabelCount, UErrorCode &status);
/**
* Add a record to the index. Each record will be associated with an index Bucket
* based on the record's name. The list of records for each bucket will be sorted
* based on the collation ordering of the names in the index's locale.
* Records with duplicate names are permitted; they will be kept in the order
* that they were added.
*
* @param name The display name for the Record. The Record will be placed in
* a bucket based on this name.
* @param data An optional pointer to user data associated with this
* item. When iterating the contents of a bucket, both the
* data pointer the name will be available for each Record.
* @param status Error code, will be set with the reason if the operation fails.
* @return This, for chaining.
* @stable ICU 4.8
*/
virtual AlphabeticIndex &addRecord(const UnicodeString &name, const void *data, UErrorCode &status);
/**
* Remove all Records from the Index. The set of Buckets, which define the headings under
* which records are classified, is not altered.
*
* @param status Error code, will be set with the reason if the operation fails.
* @return This, for chaining.
* @stable ICU 4.8
*/
virtual AlphabeticIndex &clearRecords(UErrorCode &status);
/** Get the number of labels in this index.
* Note: may trigger lazy index construction.
*
* @param status Error code, will be set with the reason if the operation fails.
* @return The number of labels in this index, including any under, over or
* in-flow labels.
* @stable ICU 4.8
*/
virtual int32_t getBucketCount(UErrorCode &status);
/** Get the total number of Records in this index, that is, the number
* of <name, data> pairs added.
*
* @param status Error code, will be set with the reason if the operation fails.
* @return The number of records in this index, that is, the total number
* of (name, data) items added with addRecord().
* @stable ICU 4.8
*/
virtual int32_t getRecordCount(UErrorCode &status);
/**
* Given the name of a record, return the zero-based index of the Bucket
* in which the item should appear. The name need not be in the index.
* A Record will not be added to the index by this function.
* Bucket numbers are zero-based, in Bucket iteration order.
*
* @param itemName The name whose bucket position in the index is to be determined.
* @param status Error code, will be set with the reason if the operation fails.
* @return The bucket number for this name.
* @stable ICU 4.8
*
*/
virtual int32_t getBucketIndex(const UnicodeString &itemName, UErrorCode &status);
/**
* Get the zero based index of the current Bucket from an iteration
* over the Buckets of this index. Return -1 if no iteration is in process.
* @return the index of the current Bucket
* @stable ICU 4.8
*/
virtual int32_t getBucketIndex() const;
/**
* Advance the iteration over the Buckets of this index. Return FALSE if
* there are no more Buckets.
*
* @param status Error code, will be set with the reason if the operation fails.
* U_ENUM_OUT_OF_SYNC_ERROR will be reported if the index is modified while
* an enumeration of its contents are in process.
*
* @return TRUE if success, FALSE if at end of iteration
* @stable ICU 4.8
*/
virtual UBool nextBucket(UErrorCode &status);
/**
* Return the name of the Label of the current bucket from an iteration over the buckets.
* If the iteration is before the first Bucket (nextBucket() has not been called),
* or after the last, return an empty string.
*
* @return the bucket label.
* @stable ICU 4.8
*/
virtual const UnicodeString &getBucketLabel() const;
/**
* Return the type of the label for the current Bucket (selected by the
* iteration over Buckets.)
*
* @return the label type.
* @stable ICU 4.8
*/
virtual UAlphabeticIndexLabelType getBucketLabelType() const;
/**
* Get the number of <name, data> Records in the current Bucket.
* If the current bucket iteration position is before the first label or after the
* last, return 0.
*
* @return the number of Records.
* @stable ICU 4.8
*/
virtual int32_t getBucketRecordCount() const;
/**
* Reset the Bucket iteration for this index. The next call to nextBucket()
* will restart the iteration at the first label.
*
* @param status Error code, will be set with the reason if the operation fails.
* @return this, for chaining.
* @stable ICU 4.8
*/
virtual AlphabeticIndex &resetBucketIterator(UErrorCode &status);
/**
* Advance to the next record in the current Bucket.
* When nextBucket() is called, Record iteration is reset to just before the
* first Record in the new Bucket.
*
* @param status Error code, will be set with the reason if the operation fails.
* U_ENUM_OUT_OF_SYNC_ERROR will be reported if the index is modified while
* an enumeration of its contents are in process.
* @return TRUE if successful, FALSE when the iteration advances past the last item.
* @stable ICU 4.8
*/
virtual UBool nextRecord(UErrorCode &status);
/**
* Get the name of the current Record.
* Return an empty string if the Record iteration position is before first
* or after the last.
*
* @return The name of the current index item.
* @stable ICU 4.8
*/
virtual const UnicodeString &getRecordName() const;
/**
* Return the data pointer of the Record currently being iterated over.
* Return NULL if the current iteration position before the first item in this Bucket,
* or after the last.
*
* @return The current Record's data pointer.
* @stable ICU 4.8
*/
virtual const void *getRecordData() const;
/**
* Reset the Record iterator position to before the first Record in the current Bucket.
*
* @return This, for chaining.
* @stable ICU 4.8
*/
virtual AlphabeticIndex &resetRecordIterator();
private:
/**
* No Copy constructor.
* @internal
*/
AlphabeticIndex(const AlphabeticIndex &other);
/**
* No assignment.
*/
AlphabeticIndex &operator =(const AlphabeticIndex & /*other*/) { return *this;};
/**
* No Equality operators.
* @internal
*/
virtual UBool operator==(const AlphabeticIndex& other) const;
/**
* Inequality operator.
* @internal
*/
virtual UBool operator!=(const AlphabeticIndex& other) const;
// Common initialization, for use from all constructors.
void init(const Locale *locale, UErrorCode &status);
/**
* This method is called to get the index exemplars. Normally these come from the locale directly,
* but if they aren't available, we have to synthesize them.
*/
void addIndexExemplars(const Locale &locale, UErrorCode &status);
/**
* Add Chinese index characters from the tailoring.
*/
UBool addChineseIndexCharacters(UErrorCode &errorCode);
UVector *firstStringsInScript(UErrorCode &status);
static UnicodeString separated(const UnicodeString &item);
/**
* Determine the best labels to use.
* This is based on the exemplars, but we also process to make sure that they are unique,
* and sort differently, and that the overall list is small enough.
*/
void initLabels(UVector &indexCharacters, UErrorCode &errorCode) const;
BucketList *createBucketList(UErrorCode &errorCode) const;
void initBuckets(UErrorCode &errorCode);
void clearBuckets();
void internalResetBucketIterator();
public:
// The Record is declared public only to allow access from
// implementation code written in plain C.
// It is not intended for public use.
#ifndef U_HIDE_INTERNAL_API
/**
* A (name, data) pair, to be sorted by name into one of the index buckets.
* The user data is not used by the index implementation.
* @internal
*/
struct Record: public UMemory {
const UnicodeString name_;
const void *data_;
Record(const UnicodeString &name, const void *data);
~Record();
};
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* Holds all user records before they are distributed into buckets.
* Type of contents is (Record *)
* @internal
*/
UVector *inputList_;
int32_t labelsIterIndex_; // Index of next item to return.
int32_t itemsIterIndex_;
Bucket *currentBucket_; // While an iteration of the index in underway,
// point to the bucket for the current label.
// NULL when no iteration underway.
int32_t maxLabelCount_; // Limit on # of labels permitted in the index.
UnicodeSet *initialLabels_; // Initial (unprocessed) set of Labels. Union
// of those explicitly set by the user plus
// those from locales. Raw values, before
// crunching into bucket labels.
UVector *firstCharsInScripts_; // The first character from each script,
// in collation order.
RuleBasedCollator *collator_;
RuleBasedCollator *collatorPrimaryOnly_;
// Lazy evaluated: null means that we have not built yet.
BucketList *buckets_;
UnicodeString inflowLabel_;
UnicodeString overflowLabel_;
UnicodeString underflowLabel_;
UnicodeString overflowComparisonString_;
UnicodeString emptyString_;
};
U_NAMESPACE_END
#endif /* UCONFIG_NO_COLLATION / UCONFIG_NO_NORMALIZATION */
#endif
project/jni/icuuc/include/unicode/appendable.h
-232
View File
@@ -1,232 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2011-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: appendable.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2010dec07
* created by: Markus W. Scherer
*/
#ifndef __APPENDABLE_H__
#define __APPENDABLE_H__
/**
* \file
* \brief C++ API: Appendable class: Sink for Unicode code points and 16-bit code units (UChars).
*/
#include "unicode/utypes.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
class UnicodeString;
/**
* Base class for objects to which Unicode characters and strings can be appended.
* Combines elements of Java Appendable and ICU4C ByteSink.
*
* This class can be used in APIs where it does not matter whether the actual destination is
* a UnicodeString, a UChar[] array, a UnicodeSet, or any other object
* that receives and processes characters and/or strings.
*
* Implementation classes must implement at least appendCodeUnit(UChar).
* The base class provides default implementations for the other methods.
*
* The methods do not take UErrorCode parameters.
* If an error occurs (e.g., out-of-memory),
* in addition to returning FALSE from failing operations,
* the implementation must prevent unexpected behavior (e.g., crashes)
* from further calls and should make the error condition available separately
* (e.g., store a UErrorCode, make/keep a UnicodeString bogus).
* @stable ICU 4.8
*/
class U_COMMON_API Appendable : public UObject {
public:
/**
* Destructor.
* @stable ICU 4.8
*/
~Appendable();
/**
* Appends a 16-bit code unit.
* @param c code unit
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool appendCodeUnit(UChar c) = 0;
/**
* Appends a code point.
* The default implementation calls appendCodeUnit(UChar) once or twice.
* @param c code point 0..0x10ffff
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool appendCodePoint(UChar32 c);
/**
* Appends a string.
* The default implementation calls appendCodeUnit(UChar) for each code unit.
* @param s string, must not be NULL if length!=0
* @param length string length, or -1 if NUL-terminated
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool appendString(const UChar *s, int32_t length);
/**
* Tells the object that the caller is going to append roughly
* appendCapacity UChars. A subclass might use this to pre-allocate
* a larger buffer if necessary.
* The default implementation does nothing. (It always returns TRUE.)
* @param appendCapacity estimated number of UChars that will be appended
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool reserveAppendCapacity(int32_t appendCapacity);
/**
* Returns a writable buffer for appending and writes the buffer's capacity to
* *resultCapacity. Guarantees *resultCapacity>=minCapacity.
* May return a pointer to the caller-owned scratch buffer which must have
* scratchCapacity>=minCapacity.
* The returned buffer is only valid until the next operation
* on this Appendable.
*
* After writing at most *resultCapacity UChars, call appendString() with the
* pointer returned from this function and the number of UChars written.
* Many appendString() implementations will avoid copying UChars if this function
* returned an internal buffer.
*
* Partial usage example:
* \code
* int32_t capacity;
* UChar* buffer = app.getAppendBuffer(..., &capacity);
* ... Write n UChars into buffer, with n <= capacity.
* app.appendString(buffer, n);
* \endcode
* In many implementations, that call to append will avoid copying UChars.
*
* If the Appendable allocates or reallocates an internal buffer, it should use
* the desiredCapacityHint if appropriate.
* If a caller cannot provide a reasonable guess at the desired capacity,
* it should pass desiredCapacityHint=0.
*
* If a non-scratch buffer is returned, the caller may only pass
* a prefix to it to appendString().
* That is, it is not correct to pass an interior pointer to appendString().
*
* The default implementation always returns the scratch buffer.
*
* @param minCapacity required minimum capacity of the returned buffer;
* must be non-negative
* @param desiredCapacityHint desired capacity of the returned buffer;
* must be non-negative
* @param scratch default caller-owned buffer
* @param scratchCapacity capacity of the scratch buffer
* @param resultCapacity pointer to an integer which will be set to the
* capacity of the returned buffer
* @return a buffer with *resultCapacity>=minCapacity
* @stable ICU 4.8
*/
virtual UChar *getAppendBuffer(int32_t minCapacity,
int32_t desiredCapacityHint,
UChar *scratch, int32_t scratchCapacity,
int32_t *resultCapacity);
};
/**
* An Appendable implementation which writes to a UnicodeString.
*
* This class is not intended for public subclassing.
* @stable ICU 4.8
*/
class U_COMMON_API UnicodeStringAppendable : public Appendable {
public:
/**
* Aliases the UnicodeString (keeps its reference) for writing.
* @param s The UnicodeString to which this Appendable will write.
* @stable ICU 4.8
*/
explicit UnicodeStringAppendable(UnicodeString &s) : str(s) {}
/**
* Destructor.
* @stable ICU 4.8
*/
~UnicodeStringAppendable();
/**
* Appends a 16-bit code unit to the string.
* @param c code unit
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool appendCodeUnit(UChar c);
/**
* Appends a code point to the string.
* @param c code point 0..0x10ffff
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool appendCodePoint(UChar32 c);
/**
* Appends a string to the UnicodeString.
* @param s string, must not be NULL if length!=0
* @param length string length, or -1 if NUL-terminated
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool appendString(const UChar *s, int32_t length);
/**
* Tells the UnicodeString that the caller is going to append roughly
* appendCapacity UChars.
* @param appendCapacity estimated number of UChars that will be appended
* @return TRUE if the operation succeeded
* @stable ICU 4.8
*/
virtual UBool reserveAppendCapacity(int32_t appendCapacity);
/**
* Returns a writable buffer for appending and writes the buffer's capacity to
* *resultCapacity. Guarantees *resultCapacity>=minCapacity.
* May return a pointer to the caller-owned scratch buffer which must have
* scratchCapacity>=minCapacity.
* The returned buffer is only valid until the next write operation
* on the UnicodeString.
*
* For details see Appendable::getAppendBuffer().
*
* @param minCapacity required minimum capacity of the returned buffer;
* must be non-negative
* @param desiredCapacityHint desired capacity of the returned buffer;
* must be non-negative
* @param scratch default caller-owned buffer
* @param scratchCapacity capacity of the scratch buffer
* @param resultCapacity pointer to an integer which will be set to the
* capacity of the returned buffer
* @return a buffer with *resultCapacity>=minCapacity
* @stable ICU 4.8
*/
virtual UChar *getAppendBuffer(int32_t minCapacity,
int32_t desiredCapacityHint,
UChar *scratch, int32_t scratchCapacity,
int32_t *resultCapacity);
private:
UnicodeString &str;
};
U_NAMESPACE_END
#endif // __APPENDABLE_H__
project/jni/icuuc/include/unicode/basictz.h
-214
View File
@@ -1,214 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2007-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*/
#ifndef BASICTZ_H
#define BASICTZ_H
/**
* \file
* \brief C++ API: ICU TimeZone base class
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/timezone.h"
#include "unicode/tzrule.h"
#include "unicode/tztrans.h"
U_NAMESPACE_BEGIN
// forward declarations
class UVector;
/**
* <code>BasicTimeZone</code> is an abstract class extending <code>TimeZone</code>.
* This class provides some additional methods to access time zone transitions and rules.
* All ICU <code>TimeZone</code> concrete subclasses extend this class.
* @stable ICU 3.8
*/
class U_I18N_API BasicTimeZone: public TimeZone {
public:
/**
* Destructor.
* @stable ICU 3.8
*/
virtual ~BasicTimeZone();
/**
* Gets the first time zone transition after the base time.
* @param base The base time.
* @param inclusive Whether the base time is inclusive or not.
* @param result Receives the first transition after the base time.
* @return TRUE if the transition is found.
* @stable ICU 3.8
*/
virtual UBool getNextTransition(UDate base, UBool inclusive, TimeZoneTransition& result) const = 0;
/**
* Gets the most recent time zone transition before the base time.
* @param base The base time.
* @param inclusive Whether the base time is inclusive or not.
* @param result Receives the most recent transition before the base time.
* @return TRUE if the transition is found.
* @stable ICU 3.8
*/
virtual UBool getPreviousTransition(UDate base, UBool inclusive, TimeZoneTransition& result) const = 0;
/**
* Checks if the time zone has equivalent transitions in the time range.
* This method returns true when all of transition times, from/to standard
* offsets and DST savings used by this time zone match the other in the
* time range.
* @param tz The <code>BasicTimeZone</code> object to be compared with.
* @param start The start time of the evaluated time range (inclusive)
* @param end The end time of the evaluated time range (inclusive)
* @param ignoreDstAmount
* When true, any transitions with only daylight saving amount
* changes will be ignored, except either of them is zero.
* For example, a transition from rawoffset 3:00/dstsavings 1:00
* to rawoffset 2:00/dstsavings 2:00 is excluded from the comparison,
* but a transtion from rawoffset 2:00/dstsavings 1:00 to
* rawoffset 3:00/dstsavings 0:00 is included.
* @param ec Output param to filled in with a success or an error.
* @return true if the other time zone has the equivalent transitions in the
* time range.
* @stable ICU 3.8
*/
virtual UBool hasEquivalentTransitions(const BasicTimeZone& tz, UDate start, UDate end,
UBool ignoreDstAmount, UErrorCode& ec) const;
/**
* Returns the number of <code>TimeZoneRule</code>s which represents time transitions,
* for this time zone, that is, all <code>TimeZoneRule</code>s for this time zone except
* <code>InitialTimeZoneRule</code>. The return value range is 0 or any positive value.
* @param status Receives error status code.
* @return The number of <code>TimeZoneRule</code>s representing time transitions.
* @stable ICU 3.8
*/
virtual int32_t countTransitionRules(UErrorCode& status) const = 0;
/**
* Gets the <code>InitialTimeZoneRule</code> and the set of <code>TimeZoneRule</code>
* which represent time transitions for this time zone. On successful return,
* the argument initial points to non-NULL <code>InitialTimeZoneRule</code> and
* the array trsrules is filled with 0 or multiple <code>TimeZoneRule</code>
* instances up to the size specified by trscount. The results are referencing the
* rule instance held by this time zone instance. Therefore, after this time zone
* is destructed, they are no longer available.
* @param initial Receives the initial timezone rule
* @param trsrules Receives the timezone transition rules
* @param trscount On input, specify the size of the array 'transitions' receiving
* the timezone transition rules. On output, actual number of
* rules filled in the array will be set.
* @param status Receives error status code.
* @stable ICU 3.8
*/
virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial,
const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status) const = 0;
/**
* Gets the set of time zone rules valid at the specified time. Some known external time zone
* implementations are not capable to handle historic time zone rule changes. Also some
* implementations can only handle certain type of rule definitions.
* If this time zone does not use any daylight saving time within about 1 year from the specified
* time, only the <code>InitialTimeZone</code> is returned. Otherwise, the rule for standard
* time and daylight saving time transitions are returned in addition to the
* <code>InitialTimeZoneRule</code>. The standard and daylight saving time transition rules are
* represented by <code>AnnualTimeZoneRule</code> with <code>DateTimeRule::DOW</code> for its date
* rule and <code>DateTimeRule::WALL_TIME</code> for its time rule. Because daylight saving time
* rule is changing time to time in many time zones and also mapping a transition time rule to
* different type is lossy transformation, the set of rules returned by this method may be valid
* for short period of time.
* The time zone rule objects returned by this method is owned by the caller, so the caller is
* responsible for deleting them after use.
* @param date The date used for extracting time zone rules.
* @param initial Receives the <code>InitialTimeZone</code>, always not NULL.
* @param std Receives the <code>AnnualTimeZoneRule</code> for standard time transitions.
* When this time time zone does not observe daylight saving times around the
* specified date, NULL is set.
* @param dst Receives the <code>AnnualTimeZoneRule</code> for daylight saving time
* transitions. When this time zone does not observer daylight saving times
* around the specified date, NULL is set.
* @param status Receives error status code.
* @stable ICU 3.8
*/
virtual void getSimpleRulesNear(UDate date, InitialTimeZoneRule*& initial,
AnnualTimeZoneRule*& std, AnnualTimeZoneRule*& dst, UErrorCode& status) const;
#ifndef U_HIDE_INTERNAL_API
/**
* The time type option bit flags used by getOffsetFromLocal
* @internal
*/
enum {
kStandard = 0x01,
kDaylight = 0x03,
kFormer = 0x04,
kLatter = 0x0C
};
#endif /* U_HIDE_INTERNAL_API */
/**
* Get time zone offsets from local wall time.
* @internal
*/
virtual void getOffsetFromLocal(UDate date, int32_t nonExistingTimeOpt, int32_t duplicatedTimeOpt,
int32_t& rawOffset, int32_t& dstOffset, UErrorCode& status) const;
protected:
#ifndef U_HIDE_INTERNAL_API
/**
* The time type option bit masks used by getOffsetFromLocal
* @internal
*/
enum {
kStdDstMask = kDaylight,
kFormerLatterMask = kLatter
};
#endif /* U_HIDE_INTERNAL_API */
/**
* Default constructor.
* @stable ICU 3.8
*/
BasicTimeZone();
/**
* Construct a timezone with a given ID.
* @param id a system time zone ID
* @stable ICU 3.8
*/
BasicTimeZone(const UnicodeString &id);
/**
* Copy constructor.
* @param source the object to be copied.
* @stable ICU 3.8
*/
BasicTimeZone(const BasicTimeZone& source);
/**
* Gets the set of TimeZoneRule instances applicable to the specified time and after.
* @param start The start date used for extracting time zone rules
* @param initial Receives the InitialTimeZone, always not NULL
* @param transitionRules Receives the transition rules, could be NULL
* @param status Receives error status code
*/
void getTimeZoneRulesAfter(UDate start, InitialTimeZoneRule*& initial, UVector*& transitionRules,
UErrorCode& status) const;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // BASICTZ_H
//eof
project/jni/icuuc/include/unicode/brkiter.h
-648
View File
@@ -1,648 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File brkiter.h
*
* Modification History:
*
* Date Name Description
* 02/18/97 aliu Added typedef for TextCount. Made DONE const.
* 05/07/97 aliu Fixed DLL declaration.
* 07/09/97 jfitz Renamed BreakIterator and interface synced with JDK
* 08/11/98 helena Sync-up JDK1.2.
* 01/13/2000 helena Added UErrorCode parameter to createXXXInstance methods.
********************************************************************************
*/
#ifndef BRKITER_H
#define BRKITER_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Break Iterator.
*/
#if UCONFIG_NO_BREAK_ITERATION
U_NAMESPACE_BEGIN
/*
* Allow the declaration of APIs with pointers to BreakIterator
* even when break iteration is removed from the build.
*/
class BreakIterator;
U_NAMESPACE_END
#else
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/chariter.h"
#include "unicode/locid.h"
#include "unicode/ubrk.h"
#include "unicode/strenum.h"
#include "unicode/utext.h"
#include "unicode/umisc.h"
U_NAMESPACE_BEGIN
/**
* The BreakIterator class implements methods for finding the location
* of boundaries in text. BreakIterator is an abstract base class.
* Instances of BreakIterator maintain a current position and scan over
* text returning the index of characters where boundaries occur.
* <p>
* Line boundary analysis determines where a text string can be broken
* when line-wrapping. The mechanism correctly handles punctuation and
* hyphenated words.
* <p>
* Sentence boundary analysis allows selection with correct
* interpretation of periods within numbers and abbreviations, and
* trailing punctuation marks such as quotation marks and parentheses.
* <p>
* Word boundary analysis is used by search and replace functions, as
* well as within text editing applications that allow the user to
* select words with a double click. Word selection provides correct
* interpretation of punctuation marks within and following
* words. Characters that are not part of a word, such as symbols or
* punctuation marks, have word-breaks on both sides.
* <p>
* Character boundary analysis allows users to interact with
* characters as they expect to, for example, when moving the cursor
* through a text string. Character boundary analysis provides correct
* navigation of through character strings, regardless of how the
* character is stored. For example, an accented character might be
* stored as a base character and a diacritical mark. What users
* consider to be a character can differ between languages.
* <p>
* The text boundary positions are found according to the rules
* described in Unicode Standard Annex #29, Text Boundaries, and
* Unicode Standard Annex #14, Line Breaking Properties. These
* are available at http://www.unicode.org/reports/tr14/ and
* http://www.unicode.org/reports/tr29/.
* <p>
* In addition to the C++ API defined in this header file, a
* plain C API with equivalent functionality is defined in the
* file ubrk.h
* <p>
* Code snippets illustrating the use of the Break Iterator APIs
* are available in the ICU User Guide,
* http://icu-project.org/userguide/boundaryAnalysis.html
* and in the sample program icu/source/samples/break/break.cpp
*
*/
class U_COMMON_API BreakIterator : public UObject {
public:
/**
* destructor
* @stable ICU 2.0
*/
virtual ~BreakIterator();
/**
* Return true if another object is semantically equal to this
* one. The other object should be an instance of the same subclass of
* BreakIterator. Objects of different subclasses are considered
* unequal.
* <P>
* Return true if this BreakIterator is at the same position in the
* same text, and is the same class and type (word, line, etc.) of
* BreakIterator, as the argument. Text is considered the same if
* it contains the same characters, it need not be the same
* object, and styles are not considered.
* @stable ICU 2.0
*/
virtual UBool operator==(const BreakIterator&) const = 0;
/**
* Returns the complement of the result of operator==
* @param rhs The BreakIterator to be compared for inequality
* @return the complement of the result of operator==
* @stable ICU 2.0
*/
UBool operator!=(const BreakIterator& rhs) const { return !operator==(rhs); }
/**
* Return a polymorphic copy of this object. This is an abstract
* method which subclasses implement.
* @stable ICU 2.0
*/
virtual BreakIterator* clone(void) const = 0;
/**
* Return a polymorphic class ID for this object. Different subclasses
* will return distinct unequal values.
* @stable ICU 2.0
*/
virtual UClassID getDynamicClassID(void) const = 0;
/**
* Return a CharacterIterator over the text being analyzed.
* @stable ICU 2.0
*/
virtual CharacterIterator& getText(void) const = 0;
/**
* Get a UText for the text being analyzed.
* The returned UText is a shallow clone of the UText used internally
* by the break iterator implementation. It can safely be used to
* access the text without impacting any break iterator operations,
* but the underlying text itself must not be altered.
*
* @param fillIn A UText to be filled in. If NULL, a new UText will be
* allocated to hold the result.
* @param status receives any error codes.
* @return The current UText for this break iterator. If an input
* UText was provided, it will always be returned.
* @stable ICU 3.4
*/
virtual UText *getUText(UText *fillIn, UErrorCode &status) const = 0;
/**
* Change the text over which this operates. The text boundary is
* reset to the start.
* @param text The UnicodeString used to change the text.
* @stable ICU 2.0
*/
virtual void setText(const UnicodeString &text) = 0;
/**
* Reset the break iterator to operate over the text represented by
* the UText. The iterator position is reset to the start.
*
* This function makes a shallow clone of the supplied UText. This means
* that the caller is free to immediately close or otherwise reuse the
* Utext that was passed as a parameter, but that the underlying text itself
* must not be altered while being referenced by the break iterator.
*
* All index positions returned by break iterator functions are
* native indices from the UText. For example, when breaking UTF-8
* encoded text, the break positions returned by next(), previous(), etc.
* will be UTF-8 string indices, not UTF-16 positions.
*
* @param text The UText used to change the text.
* @param status receives any error codes.
* @stable ICU 3.4
*/
virtual void setText(UText *text, UErrorCode &status) = 0;
/**
* Change the text over which this operates. The text boundary is
* reset to the start.
* Note that setText(UText *) provides similar functionality to this function,
* and is more efficient.
* @param it The CharacterIterator used to change the text.
* @stable ICU 2.0
*/
virtual void adoptText(CharacterIterator* it) = 0;
enum {
/**
* DONE is returned by previous() and next() after all valid
* boundaries have been returned.
* @stable ICU 2.0
*/
DONE = (int32_t)-1
};
/**
* Set the iterator position to the index of the first character in the text being scanned.
* @return The index of the first character in the text being scanned.
* @stable ICU 2.0
*/
virtual int32_t first(void) = 0;
/**
* Set the iterator position to the index immediately BEYOND the last character in the text being scanned.
* @return The index immediately BEYOND the last character in the text being scanned.
* @stable ICU 2.0
*/
virtual int32_t last(void) = 0;
/**
* Set the iterator position to the boundary preceding the current boundary.
* @return The character index of the previous text boundary or DONE if all
* boundaries have been returned.
* @stable ICU 2.0
*/
virtual int32_t previous(void) = 0;
/**
* Advance the iterator to the boundary following the current boundary.
* @return The character index of the next text boundary or DONE if all
* boundaries have been returned.
* @stable ICU 2.0
*/
virtual int32_t next(void) = 0;
/**
* Return character index of the current interator position within the text.
* @return The boundary most recently returned.
* @stable ICU 2.0
*/
virtual int32_t current(void) const = 0;
/**
* Advance the iterator to the first boundary following the specified offset.
* The value returned is always greater than the offset or
* the value BreakIterator.DONE
* @param offset the offset to begin scanning.
* @return The first boundary after the specified offset.
* @stable ICU 2.0
*/
virtual int32_t following(int32_t offset) = 0;
/**
* Set the iterator position to the first boundary preceding the specified offset.
* The value returned is always smaller than the offset or
* the value BreakIterator.DONE
* @param offset the offset to begin scanning.
* @return The first boundary before the specified offset.
* @stable ICU 2.0
*/
virtual int32_t preceding(int32_t offset) = 0;
/**
* Return true if the specfied position is a boundary position.
* As a side effect, the current position of the iterator is set
* to the first boundary position at or following the specified offset.
* @param offset the offset to check.
* @return True if "offset" is a boundary position.
* @stable ICU 2.0
*/
virtual UBool isBoundary(int32_t offset) = 0;
/**
* Set the iterator position to the nth boundary from the current boundary
* @param n the number of boundaries to move by. A value of 0
* does nothing. Negative values move to previous boundaries
* and positive values move to later boundaries.
* @return The new iterator position, or
* DONE if there are fewer than |n| boundaries in the specfied direction.
* @stable ICU 2.0
*/
virtual int32_t next(int32_t n) = 0;
/**
* For RuleBasedBreakIterators, return the status tag from the
* break rule that determined the most recently
* returned break position.
* <p>
* For break iterator types that do not support a rule status,
* a default value of 0 is returned.
* <p>
* @return the status from the break rule that determined the most recently
* returned break position.
* @see RuleBaseBreakIterator::getRuleStatus()
* @see UWordBreak
* @draft ICU 52
*/
virtual int32_t getRuleStatus() const;
/**
* For RuleBasedBreakIterators, get the status (tag) values from the break rule(s)
* that determined the most recently returned break position.
* <p>
* For break iterator types that do not support rule status,
* no values are returned.
* <p>
* The returned status value(s) are stored into an array provided by the caller.
* The values are stored in sorted (ascending) order.
* If the capacity of the output array is insufficient to hold the data,
* the output will be truncated to the available length, and a
* U_BUFFER_OVERFLOW_ERROR will be signaled.
* <p>
* @see RuleBaseBreakIterator::getRuleStatusVec
*
* @param fillInVec an array to be filled in with the status values.
* @param capacity the length of the supplied vector. A length of zero causes
* the function to return the number of status values, in the
* normal way, without attemtping to store any values.
* @param status receives error codes.
* @return The number of rule status values from rules that determined
* the most recent boundary returned by the break iterator.
* In the event of a U_BUFFER_OVERFLOW_ERROR, the return value
* is the total number of status values that were available,
* not the reduced number that were actually returned.
* @see getRuleStatus
* @draft ICU 52
*/
virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status);
/**
* Create BreakIterator for word-breaks using the given locale.
* Returns an instance of a BreakIterator implementing word breaks.
* WordBreak is useful for word selection (ex. double click)
* @param where the locale.
* @param status the error code
* @return A BreakIterator for word-breaks. The UErrorCode& status
* parameter is used to return status information to the user.
* To check whether the construction succeeded or not, you should check
* the value of U_SUCCESS(err). If you wish more detailed information, you
* can check for informational error results which still indicate success.
* U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
* used. U_USING_DEFAULT_WARNING indicates that the default locale data was
* used; neither the requested locale nor any of its fall back locales
* could be found.
* The caller owns the returned object and is responsible for deleting it.
* @stable ICU 2.0
*/
static BreakIterator* U_EXPORT2
createWordInstance(const Locale& where, UErrorCode& status);
/**
* Create BreakIterator for line-breaks using specified locale.
* Returns an instance of a BreakIterator implementing line breaks. Line
* breaks are logically possible line breaks, actual line breaks are
* usually determined based on display width.
* LineBreak is useful for word wrapping text.
* @param where the locale.
* @param status The error code.
* @return A BreakIterator for line-breaks. The UErrorCode& status
* parameter is used to return status information to the user.
* To check whether the construction succeeded or not, you should check
* the value of U_SUCCESS(err). If you wish more detailed information, you
* can check for informational error results which still indicate success.
* U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
* used. U_USING_DEFAULT_WARNING indicates that the default locale data was
* used; neither the requested locale nor any of its fall back locales
* could be found.
* The caller owns the returned object and is responsible for deleting it.
* @stable ICU 2.0
*/
static BreakIterator* U_EXPORT2
createLineInstance(const Locale& where, UErrorCode& status);
/**
* Create BreakIterator for character-breaks using specified locale
* Returns an instance of a BreakIterator implementing character breaks.
* Character breaks are boundaries of combining character sequences.
* @param where the locale.
* @param status The error code.
* @return A BreakIterator for character-breaks. The UErrorCode& status
* parameter is used to return status information to the user.
* To check whether the construction succeeded or not, you should check
* the value of U_SUCCESS(err). If you wish more detailed information, you
* can check for informational error results which still indicate success.
* U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
* used. U_USING_DEFAULT_WARNING indicates that the default locale data was
* used; neither the requested locale nor any of its fall back locales
* could be found.
* The caller owns the returned object and is responsible for deleting it.
* @stable ICU 2.0
*/
static BreakIterator* U_EXPORT2
createCharacterInstance(const Locale& where, UErrorCode& status);
/**
* Create BreakIterator for sentence-breaks using specified locale
* Returns an instance of a BreakIterator implementing sentence breaks.
* @param where the locale.
* @param status The error code.
* @return A BreakIterator for sentence-breaks. The UErrorCode& status
* parameter is used to return status information to the user.
* To check whether the construction succeeded or not, you should check
* the value of U_SUCCESS(err). If you wish more detailed information, you
* can check for informational error results which still indicate success.
* U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
* used. U_USING_DEFAULT_WARNING indicates that the default locale data was
* used; neither the requested locale nor any of its fall back locales
* could be found.
* The caller owns the returned object and is responsible for deleting it.
* @stable ICU 2.0
*/
static BreakIterator* U_EXPORT2
createSentenceInstance(const Locale& where, UErrorCode& status);
/**
* Create BreakIterator for title-casing breaks using the specified locale
* Returns an instance of a BreakIterator implementing title breaks.
* The iterator returned locates title boundaries as described for
* Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
* please use Word Boundary iterator.{@link #createWordInstance }
*
* @param where the locale.
* @param status The error code.
* @return A BreakIterator for title-breaks. The UErrorCode& status
* parameter is used to return status information to the user.
* To check whether the construction succeeded or not, you should check
* the value of U_SUCCESS(err). If you wish more detailed information, you
* can check for informational error results which still indicate success.
* U_USING_FALLBACK_WARNING indicates that a fall back locale was used. For
* example, 'de_CH' was requested, but nothing was found there, so 'de' was
* used. U_USING_DEFAULT_WARNING indicates that the default locale data was
* used; neither the requested locale nor any of its fall back locales
* could be found.
* The caller owns the returned object and is responsible for deleting it.
* @stable ICU 2.1
*/
static BreakIterator* U_EXPORT2
createTitleInstance(const Locale& where, UErrorCode& status);
/**
* Get the set of Locales for which TextBoundaries are installed.
* <p><b>Note:</b> this will not return locales added through the register
* call. To see the registered locales too, use the getAvailableLocales
* function that returns a StringEnumeration object </p>
* @param count the output parameter of number of elements in the locale list
* @return available locales
* @stable ICU 2.0
*/
static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count);
/**
* Get name of the object for the desired Locale, in the desired langauge.
* @param objectLocale must be from getAvailableLocales.
* @param displayLocale specifies the desired locale for output.
* @param name the fill-in parameter of the return value
* Uses best match.
* @return user-displayable name
* @stable ICU 2.0
*/
static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
const Locale& displayLocale,
UnicodeString& name);
/**
* Get name of the object for the desired Locale, in the langauge of the
* default locale.
* @param objectLocale must be from getMatchingLocales
* @param name the fill-in parameter of the return value
* @return user-displayable name
* @stable ICU 2.0
*/
static UnicodeString& U_EXPORT2 getDisplayName(const Locale& objectLocale,
UnicodeString& name);
/**
* Deprecated functionality. Use clone() instead.
*
* Thread safe client-buffer-based cloning operation
* Do NOT call delete on a safeclone, since 'new' is not used to create it.
* @param stackBuffer user allocated space for the new clone. If NULL new memory will be allocated.
* If buffer is not large enough, new memory will be allocated.
* @param BufferSize reference to size of allocated space.
* If BufferSize == 0, a sufficient size for use in cloning will
* be returned ('pre-flighting')
* If BufferSize is not enough for a stack-based safe clone,
* new memory will be allocated.
* @param status to indicate whether the operation went on smoothly or there were errors
* An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were
* necessary.
* @return pointer to the new clone
*
* @deprecated ICU 52. Use clone() instead.
*/
virtual BreakIterator * createBufferClone(void *stackBuffer,
int32_t &BufferSize,
UErrorCode &status) = 0;
#ifndef U_HIDE_DEPRECATED_API
/**
* Determine whether the BreakIterator was created in user memory by
* createBufferClone(), and thus should not be deleted. Such objects
* must be closed by an explicit call to the destructor (not delete).
* @deprecated ICU 52. Always delete the BreakIterator.
*/
inline UBool isBufferClone(void);
#endif /* U_HIDE_DEPRECATED_API */
#if !UCONFIG_NO_SERVICE
/**
* Register a new break iterator of the indicated kind, to use in the given locale.
* The break iterator will be adopted. Clones of the iterator will be returned
* if a request for a break iterator of the given kind matches or falls back to
* this locale.
* @param toAdopt the BreakIterator instance to be adopted
* @param locale the Locale for which this instance is to be registered
* @param kind the type of iterator for which this instance is to be registered
* @param status the in/out status code, no special meanings are assigned
* @return a registry key that can be used to unregister this instance
* @stable ICU 2.4
*/
static URegistryKey U_EXPORT2 registerInstance(BreakIterator* toAdopt,
const Locale& locale,
UBreakIteratorType kind,
UErrorCode& status);
/**
* Unregister a previously-registered BreakIterator using the key returned from the
* register call. Key becomes invalid after a successful call and should not be used again.
* The BreakIterator corresponding to the key will be deleted.
* @param key the registry key returned by a previous call to registerInstance
* @param status the in/out status code, no special meanings are assigned
* @return TRUE if the iterator for the key was successfully unregistered
* @stable ICU 2.4
*/
static UBool U_EXPORT2 unregister(URegistryKey key, UErrorCode& status);
/**
* Return a StringEnumeration over the locales available at the time of the call,
* including registered locales.
* @return a StringEnumeration over the locales available at the time of the call
* @stable ICU 2.4
*/
static StringEnumeration* U_EXPORT2 getAvailableLocales(void);
#endif
/**
* Returns the locale for this break iterator. Two flavors are available: valid and
* actual locale.
* @stable ICU 2.8
*/
Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
#ifndef U_HIDE_INTERNAL_API
/** Get the locale for this break iterator object. You can choose between valid and actual locale.
* @param type type of the locale we're looking for (valid or actual)
* @param status error code for the operation
* @return the locale
* @internal
*/
const char *getLocaleID(ULocDataLocaleType type, UErrorCode& status) const;
#endif /* U_HIDE_INTERNAL_API */
/**
* Set the subject text string upon which the break iterator is operating
* without changing any other aspect of the matching state.
* The new and previous text strings must have the same content.
*
* This function is intended for use in environments where ICU is operating on
* strings that may move around in memory. It provides a mechanism for notifying
* ICU that the string has been relocated, and providing a new UText to access the
* string in its new position.
*
* Note that the break iterator implementation never copies the underlying text
* of a string being processed, but always operates directly on the original text
* provided by the user. Refreshing simply drops the references to the old text
* and replaces them with references to the new.
*
* Caution: this function is normally used only by very specialized,
* system-level code. One example use case is with garbage collection that moves
* the text in memory.
*
* @param input The new (moved) text string.
* @param status Receives errors detected by this function.
* @return *this
*
* @stable ICU 49
*/
virtual BreakIterator &refreshInputText(UText *input, UErrorCode &status) = 0;
private:
static BreakIterator* buildInstance(const Locale& loc, const char *type, int32_t kind, UErrorCode& status);
static BreakIterator* createInstance(const Locale& loc, int32_t kind, UErrorCode& status);
static BreakIterator* makeInstance(const Locale& loc, int32_t kind, UErrorCode& status);
friend class ICUBreakIteratorFactory;
friend class ICUBreakIteratorService;
protected:
// Do not enclose protected default/copy constructors with #ifndef U_HIDE_INTERNAL_API
// or else the compiler will create a public ones.
/** @internal */
BreakIterator();
/** @internal */
BreakIterator (const BreakIterator &other) : UObject(other) {}
private:
/** @internal */
char actualLocale[ULOC_FULLNAME_CAPACITY];
char validLocale[ULOC_FULLNAME_CAPACITY];
/**
* The assignment operator has no real implementation.
* It's provided to make the compiler happy. Do not call.
*/
BreakIterator& operator=(const BreakIterator&);
};
#ifndef U_HIDE_DEPRECATED_API
inline UBool BreakIterator::isBufferClone()
{
return FALSE;
}
#endif /* U_HIDE_DEPRECATED_API */
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_BREAK_ITERATION */
#endif // _BRKITER
//eof
project/jni/icuuc/include/unicode/bytestream.h
-257
View File
@@ -1,257 +0,0 @@
// Copyright (C) 2009-2012, International Business Machines
// Corporation and others. All Rights Reserved.
//
// Copyright 2007 Google Inc. All Rights Reserved.
// Author: sanjay@google.com (Sanjay Ghemawat)
//
// Abstract interface that consumes a sequence of bytes (ByteSink).
//
// Used so that we can write a single piece of code that can operate
// on a variety of output string types.
//
// Various implementations of this interface are provided:
// ByteSink:
// CheckedArrayByteSink Write to a flat array, with bounds checking
// StringByteSink Write to an STL string
// This code is a contribution of Google code, and the style used here is
// a compromise between the original Google code and the ICU coding guidelines.
// For example, data types are ICU-ified (size_t,int->int32_t),
// and API comments doxygen-ified, but function names and behavior are
// as in the original, if possible.
// Assertion-style error handling, not available in ICU, was changed to
// parameter "pinning" similar to UnicodeString.
//
// In addition, this is only a partial port of the original Google code,
// limited to what was needed so far. The (nearly) complete original code
// is in the ICU svn repository at icuhtml/trunk/design/strings/contrib
// (see ICU ticket 6765, r25517).
#ifndef __BYTESTREAM_H__
#define __BYTESTREAM_H__
/**
* \file
* \brief C++ API: Interface for writing bytes, and implementation classes.
*/
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/std_string.h"
U_NAMESPACE_BEGIN
/**
* A ByteSink can be filled with bytes.
* @stable ICU 4.2
*/
class U_COMMON_API ByteSink : public UMemory {
public:
/**
* Default constructor.
* @stable ICU 4.2
*/
ByteSink() { }
/**
* Virtual destructor.
* @stable ICU 4.2
*/
virtual ~ByteSink();
/**
* Append "bytes[0,n-1]" to this.
* @param bytes the pointer to the bytes
* @param n the number of bytes; must be non-negative
* @stable ICU 4.2
*/
virtual void Append(const char* bytes, int32_t n) = 0;
/**
* Returns a writable buffer for appending and writes the buffer's capacity to
* *result_capacity. Guarantees *result_capacity>=min_capacity.
* May return a pointer to the caller-owned scratch buffer which must have
* scratch_capacity>=min_capacity.
* The returned buffer is only valid until the next operation
* on this ByteSink.
*
* After writing at most *result_capacity bytes, call Append() with the
* pointer returned from this function and the number of bytes written.
* Many Append() implementations will avoid copying bytes if this function
* returned an internal buffer.
*
* Partial usage example:
* int32_t capacity;
* char* buffer = sink->GetAppendBuffer(..., &capacity);
* ... Write n bytes into buffer, with n <= capacity.
* sink->Append(buffer, n);
* In many implementations, that call to Append will avoid copying bytes.
*
* If the ByteSink allocates or reallocates an internal buffer, it should use
* the desired_capacity_hint if appropriate.
* If a caller cannot provide a reasonable guess at the desired capacity,
* it should pass desired_capacity_hint=0.
*
* If a non-scratch buffer is returned, the caller may only pass
* a prefix to it to Append().
* That is, it is not correct to pass an interior pointer to Append().
*
* The default implementation always returns the scratch buffer.
*
* @param min_capacity required minimum capacity of the returned buffer;
* must be non-negative
* @param desired_capacity_hint desired capacity of the returned buffer;
* must be non-negative
* @param scratch default caller-owned buffer
* @param scratch_capacity capacity of the scratch buffer
* @param result_capacity pointer to an integer which will be set to the
* capacity of the returned buffer
* @return a buffer with *result_capacity>=min_capacity
* @stable ICU 4.2
*/
virtual char* GetAppendBuffer(int32_t min_capacity,
int32_t desired_capacity_hint,
char* scratch, int32_t scratch_capacity,
int32_t* result_capacity);
/**
* Flush internal buffers.
* Some byte sinks use internal buffers or provide buffering
* and require calling Flush() at the end of the stream.
* The ByteSink should be ready for further Append() calls after Flush().
* The default implementation of Flush() does nothing.
* @stable ICU 4.2
*/
virtual void Flush();
private:
ByteSink(const ByteSink &); // copy constructor not implemented
ByteSink &operator=(const ByteSink &); // assignment operator not implemented
};
// -------------------------------------------------------------
// Some standard implementations
/**
* Implementation of ByteSink that writes to a flat byte array,
* with bounds-checking:
* This sink will not write more than capacity bytes to outbuf.
* If more than capacity bytes are Append()ed, then excess bytes are ignored,
* and Overflowed() will return true.
* Overflow does not cause a runtime error.
* @stable ICU 4.2
*/
class U_COMMON_API CheckedArrayByteSink : public ByteSink {
public:
/**
* Constructs a ByteSink that will write to outbuf[0..capacity-1].
* @param outbuf buffer to write to
* @param capacity size of the buffer
* @stable ICU 4.2
*/
CheckedArrayByteSink(char* outbuf, int32_t capacity);
/**
* Destructor.
* @stable ICU 4.2
*/
virtual ~CheckedArrayByteSink();
/**
* Returns the sink to its original state, without modifying the buffer.
* Useful for reusing both the buffer and the sink for multiple streams.
* Resets the state to NumberOfBytesWritten()=NumberOfBytesAppended()=0
* and Overflowed()=FALSE.
* @return *this
* @stable ICU 4.6
*/
virtual CheckedArrayByteSink& Reset();
/**
* Append "bytes[0,n-1]" to this.
* @param bytes the pointer to the bytes
* @param n the number of bytes; must be non-negative
* @stable ICU 4.2
*/
virtual void Append(const char* bytes, int32_t n);
/**
* Returns a writable buffer for appending and writes the buffer's capacity to
* *result_capacity. For details see the base class documentation.
* @param min_capacity required minimum capacity of the returned buffer;
* must be non-negative
* @param desired_capacity_hint desired capacity of the returned buffer;
* must be non-negative
* @param scratch default caller-owned buffer
* @param scratch_capacity capacity of the scratch buffer
* @param result_capacity pointer to an integer which will be set to the
* capacity of the returned buffer
* @return a buffer with *result_capacity>=min_capacity
* @stable ICU 4.2
*/
virtual char* GetAppendBuffer(int32_t min_capacity,
int32_t desired_capacity_hint,
char* scratch, int32_t scratch_capacity,
int32_t* result_capacity);
/**
* Returns the number of bytes actually written to the sink.
* @return number of bytes written to the buffer
* @stable ICU 4.2
*/
int32_t NumberOfBytesWritten() const { return size_; }
/**
* Returns true if any bytes were discarded, i.e., if there was an
* attempt to write more than 'capacity' bytes.
* @return TRUE if more than 'capacity' bytes were Append()ed
* @stable ICU 4.2
*/
UBool Overflowed() const { return overflowed_; }
/**
* Returns the number of bytes appended to the sink.
* If Overflowed() then NumberOfBytesAppended()>NumberOfBytesWritten()
* else they return the same number.
* @return number of bytes written to the buffer
* @stable ICU 4.6
*/
int32_t NumberOfBytesAppended() const { return appended_; }
private:
char* outbuf_;
const int32_t capacity_;
int32_t size_;
int32_t appended_;
UBool overflowed_;
CheckedArrayByteSink(); ///< default constructor not implemented
CheckedArrayByteSink(const CheckedArrayByteSink &); ///< copy constructor not implemented
CheckedArrayByteSink &operator=(const CheckedArrayByteSink &); ///< assignment operator not implemented
};
#if U_HAVE_STD_STRING
/**
* Implementation of ByteSink that writes to a "string".
* The StringClass is usually instantiated with a std::string.
* @stable ICU 4.2
*/
template<typename StringClass>
class StringByteSink : public ByteSink {
public:
/**
* Constructs a ByteSink that will append bytes to the dest string.
* @param dest pointer to string object to append to
* @stable ICU 4.2
*/
StringByteSink(StringClass* dest) : dest_(dest) { }
/**
* Append "bytes[0,n-1]" to this.
* @param data the pointer to the bytes
* @param n the number of bytes; must be non-negative
* @stable ICU 4.2
*/
virtual void Append(const char* data, int32_t n) { dest_->append(data, n); }
private:
StringClass* dest_;
StringByteSink(); ///< default constructor not implemented
StringByteSink(const StringByteSink &); ///< copy constructor not implemented
StringByteSink &operator=(const StringByteSink &); ///< assignment operator not implemented
};
#endif
U_NAMESPACE_END
#endif // __BYTESTREAM_H__
project/jni/icuuc/include/unicode/bytestrie.h
-519
View File
@@ -1,519 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2010-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: bytestrie.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2010sep25
* created by: Markus W. Scherer
*/
#ifndef __BYTESTRIE_H__
#define __BYTESTRIE_H__
/**
* \file
* \brief C++ API: Trie for mapping byte sequences to integer values.
*/
#include "unicode/utypes.h"
#include "unicode/stringpiece.h"
#include "unicode/uobject.h"
#include "unicode/ustringtrie.h"
U_NAMESPACE_BEGIN
class ByteSink;
class BytesTrieBuilder;
class CharString;
class UVector32;
/**
* Light-weight, non-const reader class for a BytesTrie.
* Traverses a byte-serialized data structure with minimal state,
* for mapping byte sequences to non-negative integer values.
*
* This class owns the serialized trie data only if it was constructed by
* the builder's build() method.
* The public constructor and the copy constructor only alias the data (only copy the pointer).
* There is no assignment operator.
*
* This class is not intended for public subclassing.
* @stable ICU 4.8
*/
class U_COMMON_API BytesTrie : public UMemory {
public:
/**
* Constructs a BytesTrie reader instance.
*
* The trieBytes must contain a copy of a byte sequence from the BytesTrieBuilder,
* starting with the first byte of that sequence.
* The BytesTrie object will not read more bytes than
* the BytesTrieBuilder generated in the corresponding build() call.
*
* The array is not copied/cloned and must not be modified while
* the BytesTrie object is in use.
*
* @param trieBytes The byte array that contains the serialized trie.
* @stable ICU 4.8
*/
BytesTrie(const void *trieBytes)
: ownedArray_(NULL), bytes_(static_cast<const uint8_t *>(trieBytes)),
pos_(bytes_), remainingMatchLength_(-1) {}
/**
* Destructor.
* @stable ICU 4.8
*/
~BytesTrie();
/**
* Copy constructor, copies the other trie reader object and its state,
* but not the byte array which will be shared. (Shallow copy.)
* @param other Another BytesTrie object.
* @stable ICU 4.8
*/
BytesTrie(const BytesTrie &other)
: ownedArray_(NULL), bytes_(other.bytes_),
pos_(other.pos_), remainingMatchLength_(other.remainingMatchLength_) {}
/**
* Resets this trie to its initial state.
* @return *this
* @stable ICU 4.8
*/
BytesTrie &reset() {
pos_=bytes_;
remainingMatchLength_=-1;
return *this;
}
/**
* BytesTrie state object, for saving a trie's current state
* and resetting the trie back to this state later.
* @stable ICU 4.8
*/
class State : public UMemory {
public:
/**
* Constructs an empty State.
* @stable ICU 4.8
*/
State() { bytes=NULL; }
private:
friend class BytesTrie;
const uint8_t *bytes;
const uint8_t *pos;
int32_t remainingMatchLength;
};
/**
* Saves the state of this trie.
* @param state The State object to hold the trie's state.
* @return *this
* @see resetToState
* @stable ICU 4.8
*/
const BytesTrie &saveState(State &state) const {
state.bytes=bytes_;
state.pos=pos_;
state.remainingMatchLength=remainingMatchLength_;
return *this;
}
/**
* Resets this trie to the saved state.
* If the state object contains no state, or the state of a different trie,
* then this trie remains unchanged.
* @param state The State object which holds a saved trie state.
* @return *this
* @see saveState
* @see reset
* @stable ICU 4.8
*/
BytesTrie &resetToState(const State &state) {
if(bytes_==state.bytes && bytes_!=NULL) {
pos_=state.pos;
remainingMatchLength_=state.remainingMatchLength;
}
return *this;
}
/**
* Determines whether the byte sequence so far matches, whether it has a value,
* and whether another input byte can continue a matching byte sequence.
* @return The match/value Result.
* @stable ICU 4.8
*/
UStringTrieResult current() const;
/**
* Traverses the trie from the initial state for this input byte.
* Equivalent to reset().next(inByte).
* @param inByte Input byte value. Values -0x100..-1 are treated like 0..0xff.
* Values below -0x100 and above 0xff will never match.
* @return The match/value Result.
* @stable ICU 4.8
*/
inline UStringTrieResult first(int32_t inByte) {
remainingMatchLength_=-1;
if(inByte<0) {
inByte+=0x100;
}
return nextImpl(bytes_, inByte);
}
/**
* Traverses the trie from the current state for this input byte.
* @param inByte Input byte value. Values -0x100..-1 are treated like 0..0xff.
* Values below -0x100 and above 0xff will never match.
* @return The match/value Result.
* @stable ICU 4.8
*/
UStringTrieResult next(int32_t inByte);
/**
* Traverses the trie from the current state for this byte sequence.
* Equivalent to
* \code
* Result result=current();
* for(each c in s)
* if(!USTRINGTRIE_HAS_NEXT(result)) return USTRINGTRIE_NO_MATCH;
* result=next(c);
* return result;
* \endcode
* @param s A string or byte sequence. Can be NULL if length is 0.
* @param length The length of the byte sequence. Can be -1 if NUL-terminated.
* @return The match/value Result.
* @stable ICU 4.8
*/
UStringTrieResult next(const char *s, int32_t length);
/**
* Returns a matching byte sequence's value if called immediately after
* current()/first()/next() returned USTRINGTRIE_INTERMEDIATE_VALUE or USTRINGTRIE_FINAL_VALUE.
* getValue() can be called multiple times.
*
* Do not call getValue() after USTRINGTRIE_NO_MATCH or USTRINGTRIE_NO_VALUE!
* @return The value for the byte sequence so far.
* @stable ICU 4.8
*/
inline int32_t getValue() const {
const uint8_t *pos=pos_;
int32_t leadByte=*pos++;
// U_ASSERT(leadByte>=kMinValueLead);
return readValue(pos, leadByte>>1);
}
/**
* Determines whether all byte sequences reachable from the current state
* map to the same value.
* @param uniqueValue Receives the unique value, if this function returns TRUE.
* (output-only)
* @return TRUE if all byte sequences reachable from the current state
* map to the same value.
* @stable ICU 4.8
*/
inline UBool hasUniqueValue(int32_t &uniqueValue) const {
const uint8_t *pos=pos_;
// Skip the rest of a pending linear-match node.
return pos!=NULL && findUniqueValue(pos+remainingMatchLength_+1, FALSE, uniqueValue);
}
/**
* Finds each byte which continues the byte sequence from the current state.
* That is, each byte b for which it would be next(b)!=USTRINGTRIE_NO_MATCH now.
* @param out Each next byte is appended to this object.
* (Only uses the out.Append(s, length) method.)
* @return the number of bytes which continue the byte sequence from here
* @stable ICU 4.8
*/
int32_t getNextBytes(ByteSink &out) const;
/**
* Iterator for all of the (byte sequence, value) pairs in a BytesTrie.
* @stable ICU 4.8
*/
class U_COMMON_API Iterator : public UMemory {
public:
/**
* Iterates from the root of a byte-serialized BytesTrie.
* @param trieBytes The trie bytes.
* @param maxStringLength If 0, the iterator returns full strings/byte sequences.
* Otherwise, the iterator returns strings with this maximum length.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @stable ICU 4.8
*/
Iterator(const void *trieBytes, int32_t maxStringLength, UErrorCode &errorCode);
/**
* Iterates from the current state of the specified BytesTrie.
* @param trie The trie whose state will be copied for iteration.
* @param maxStringLength If 0, the iterator returns full strings/byte sequences.
* Otherwise, the iterator returns strings with this maximum length.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @stable ICU 4.8
*/
Iterator(const BytesTrie &trie, int32_t maxStringLength, UErrorCode &errorCode);
/**
* Destructor.
* @stable ICU 4.8
*/
~Iterator();
/**
* Resets this iterator to its initial state.
* @return *this
* @stable ICU 4.8
*/
Iterator &reset();
/**
* @return TRUE if there are more elements.
* @stable ICU 4.8
*/
UBool hasNext() const;
/**
* Finds the next (byte sequence, value) pair if there is one.
*
* If the byte sequence is truncated to the maximum length and does not
* have a real value, then the value is set to -1.
* In this case, this "not a real value" is indistinguishable from
* a real value of -1.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return TRUE if there is another element.
* @stable ICU 4.8
*/
UBool next(UErrorCode &errorCode);
/**
* @return The NUL-terminated byte sequence for the last successful next().
* @stable ICU 4.8
*/
const StringPiece &getString() const { return sp_; }
/**
* @return The value for the last successful next().
* @stable ICU 4.8
*/
int32_t getValue() const { return value_; }
private:
UBool truncateAndStop();
const uint8_t *branchNext(const uint8_t *pos, int32_t length, UErrorCode &errorCode);
const uint8_t *bytes_;
const uint8_t *pos_;
const uint8_t *initialPos_;
int32_t remainingMatchLength_;
int32_t initialRemainingMatchLength_;
CharString *str_;
StringPiece sp_;
int32_t maxLength_;
int32_t value_;
// The stack stores pairs of integers for backtracking to another
// outbound edge of a branch node.
// The first integer is an offset from bytes_.
// The second integer has the str_->length() from before the node in bits 15..0,
// and the remaining branch length in bits 24..16. (Bits 31..25 are unused.)
// (We could store the remaining branch length minus 1 in bits 23..16 and not use bits 31..24,
// but the code looks more confusing that way.)
UVector32 *stack_;
};
private:
friend class BytesTrieBuilder;
/**
* Constructs a BytesTrie reader instance.
* Unlike the public constructor which just aliases an array,
* this constructor adopts the builder's array.
* This constructor is only called by the builder.
*/
BytesTrie(void *adoptBytes, const void *trieBytes)
: ownedArray_(static_cast<uint8_t *>(adoptBytes)),
bytes_(static_cast<const uint8_t *>(trieBytes)),
pos_(bytes_), remainingMatchLength_(-1) {}
// No assignment operator.
BytesTrie &operator=(const BytesTrie &other);
inline void stop() {
pos_=NULL;
}
// Reads a compact 32-bit integer.
// pos is already after the leadByte, and the lead byte is already shifted right by 1.
static int32_t readValue(const uint8_t *pos, int32_t leadByte);
static inline const uint8_t *skipValue(const uint8_t *pos, int32_t leadByte) {
// U_ASSERT(leadByte>=kMinValueLead);
if(leadByte>=(kMinTwoByteValueLead<<1)) {
if(leadByte<(kMinThreeByteValueLead<<1)) {
++pos;
} else if(leadByte<(kFourByteValueLead<<1)) {
pos+=2;
} else {
pos+=3+((leadByte>>1)&1);
}
}
return pos;
}
static inline const uint8_t *skipValue(const uint8_t *pos) {
int32_t leadByte=*pos++;
return skipValue(pos, leadByte);
}
// Reads a jump delta and jumps.
static const uint8_t *jumpByDelta(const uint8_t *pos);
static inline const uint8_t *skipDelta(const uint8_t *pos) {
int32_t delta=*pos++;
if(delta>=kMinTwoByteDeltaLead) {
if(delta<kMinThreeByteDeltaLead) {
++pos;
} else if(delta<kFourByteDeltaLead) {
pos+=2;
} else {
pos+=3+(delta&1);
}
}
return pos;
}
static inline UStringTrieResult valueResult(int32_t node) {
return (UStringTrieResult)(USTRINGTRIE_INTERMEDIATE_VALUE-(node&kValueIsFinal));
}
// Handles a branch node for both next(byte) and next(string).
UStringTrieResult branchNext(const uint8_t *pos, int32_t length, int32_t inByte);
// Requires remainingLength_<0.
UStringTrieResult nextImpl(const uint8_t *pos, int32_t inByte);
// Helper functions for hasUniqueValue().
// Recursively finds a unique value (or whether there is not a unique one)
// from a branch.
static const uint8_t *findUniqueValueFromBranch(const uint8_t *pos, int32_t length,
UBool haveUniqueValue, int32_t &uniqueValue);
// Recursively finds a unique value (or whether there is not a unique one)
// starting from a position on a node lead byte.
static UBool findUniqueValue(const uint8_t *pos, UBool haveUniqueValue, int32_t &uniqueValue);
// Helper functions for getNextBytes().
// getNextBytes() when pos is on a branch node.
static void getNextBranchBytes(const uint8_t *pos, int32_t length, ByteSink &out);
static void append(ByteSink &out, int c);
// BytesTrie data structure
//
// The trie consists of a series of byte-serialized nodes for incremental
// string/byte sequence matching. The root node is at the beginning of the trie data.
//
// Types of nodes are distinguished by their node lead byte ranges.
// After each node, except a final-value node, another node follows to
// encode match values or continue matching further bytes.
//
// Node types:
// - Value node: Stores a 32-bit integer in a compact, variable-length format.
// The value is for the string/byte sequence so far.
// One node bit indicates whether the value is final or whether
// matching continues with the next node.
// - Linear-match node: Matches a number of bytes.
// - Branch node: Branches to other nodes according to the current input byte.
// The node byte is the length of the branch (number of bytes to select from)
// minus 1. It is followed by a sub-node:
// - If the length is at most kMaxBranchLinearSubNodeLength, then
// there are length-1 (key, value) pairs and then one more comparison byte.
// If one of the key bytes matches, then the value is either a final value for
// the string/byte sequence so far, or a "jump" delta to the next node.
// If the last byte matches, then matching continues with the next node.
// (Values have the same encoding as value nodes.)
// - If the length is greater than kMaxBranchLinearSubNodeLength, then
// there is one byte and one "jump" delta.
// If the input byte is less than the sub-node byte, then "jump" by delta to
// the next sub-node which will have a length of length/2.
// (The delta has its own compact encoding.)
// Otherwise, skip the "jump" delta to the next sub-node
// which will have a length of length-length/2.
// Node lead byte values.
// 00..0f: Branch node. If node!=0 then the length is node+1, otherwise
// the length is one more than the next byte.
// For a branch sub-node with at most this many entries, we drop down
// to a linear search.
static const int32_t kMaxBranchLinearSubNodeLength=5;
// 10..1f: Linear-match node, match 1..16 bytes and continue reading the next node.
static const int32_t kMinLinearMatch=0x10;
static const int32_t kMaxLinearMatchLength=0x10;
// 20..ff: Variable-length value node.
// If odd, the value is final. (Otherwise, intermediate value or jump delta.)
// Then shift-right by 1 bit.
// The remaining lead byte value indicates the number of following bytes (0..4)
// and contains the value's top bits.
static const int32_t kMinValueLead=kMinLinearMatch+kMaxLinearMatchLength; // 0x20
// It is a final value if bit 0 is set.
static const int32_t kValueIsFinal=1;
// Compact value: After testing bit 0, shift right by 1 and then use the following thresholds.
static const int32_t kMinOneByteValueLead=kMinValueLead/2; // 0x10
static const int32_t kMaxOneByteValue=0x40; // At least 6 bits in the first byte.
static const int32_t kMinTwoByteValueLead=kMinOneByteValueLead+kMaxOneByteValue+1; // 0x51
static const int32_t kMaxTwoByteValue=0x1aff;
static const int32_t kMinThreeByteValueLead=kMinTwoByteValueLead+(kMaxTwoByteValue>>8)+1; // 0x6c
static const int32_t kFourByteValueLead=0x7e;
// A little more than Unicode code points. (0x11ffff)
static const int32_t kMaxThreeByteValue=((kFourByteValueLead-kMinThreeByteValueLead)<<16)-1;
static const int32_t kFiveByteValueLead=0x7f;
// Compact delta integers.
static const int32_t kMaxOneByteDelta=0xbf;
static const int32_t kMinTwoByteDeltaLead=kMaxOneByteDelta+1; // 0xc0
static const int32_t kMinThreeByteDeltaLead=0xf0;
static const int32_t kFourByteDeltaLead=0xfe;
static const int32_t kFiveByteDeltaLead=0xff;
static const int32_t kMaxTwoByteDelta=((kMinThreeByteDeltaLead-kMinTwoByteDeltaLead)<<8)-1; // 0x2fff
static const int32_t kMaxThreeByteDelta=((kFourByteDeltaLead-kMinThreeByteDeltaLead)<<16)-1; // 0xdffff
uint8_t *ownedArray_;
// Fixed value referencing the BytesTrie bytes.
const uint8_t *bytes_;
// Iterator variables.
// Pointer to next trie byte to read. NULL if no more matches.
const uint8_t *pos_;
// Remaining length of a linear-match node, minus 1. Negative if not in such a node.
int32_t remainingMatchLength_;
};
U_NAMESPACE_END
#endif // __BYTESTRIE_H__
project/jni/icuuc/include/unicode/bytestriebuilder.h
-183
View File
@@ -1,183 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2010-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: bytestriebuilder.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2010sep25
* created by: Markus W. Scherer
*/
/**
* \file
* \brief C++ API: Builder for icu::BytesTrie
*/
#ifndef __BYTESTRIEBUILDER_H__
#define __BYTESTRIEBUILDER_H__
#include "unicode/utypes.h"
#include "unicode/bytestrie.h"
#include "unicode/stringpiece.h"
#include "unicode/stringtriebuilder.h"
U_NAMESPACE_BEGIN
class BytesTrieElement;
class CharString;
/**
* Builder class for BytesTrie.
*
* This class is not intended for public subclassing.
* @stable ICU 4.8
*/
class U_COMMON_API BytesTrieBuilder : public StringTrieBuilder {
public:
/**
* Constructs an empty builder.
* @param errorCode Standard ICU error code.
* @stable ICU 4.8
*/
BytesTrieBuilder(UErrorCode &errorCode);
/**
* Destructor.
* @stable ICU 4.8
*/
virtual ~BytesTrieBuilder();
/**
* Adds a (byte sequence, value) pair.
* The byte sequence must be unique.
* The bytes will be copied; the builder does not keep
* a reference to the input StringPiece or its data().
* @param s The input byte sequence.
* @param value The value associated with this byte sequence.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return *this
* @stable ICU 4.8
*/
BytesTrieBuilder &add(const StringPiece &s, int32_t value, UErrorCode &errorCode);
/**
* Builds a BytesTrie for the add()ed data.
* Once built, no further data can be add()ed until clear() is called.
*
* A BytesTrie cannot be empty. At least one (byte sequence, value) pair
* must have been add()ed.
*
* This method passes ownership of the builder's internal result array to the new trie object.
* Another call to any build() variant will re-serialize the trie.
* After clear() has been called, a new array will be used as well.
* @param buildOption Build option, see UStringTrieBuildOption.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return A new BytesTrie for the add()ed data.
* @stable ICU 4.8
*/
BytesTrie *build(UStringTrieBuildOption buildOption, UErrorCode &errorCode);
/**
* Builds a BytesTrie for the add()ed data and byte-serializes it.
* Once built, no further data can be add()ed until clear() is called.
*
* A BytesTrie cannot be empty. At least one (byte sequence, value) pair
* must have been add()ed.
*
* Multiple calls to buildStringPiece() return StringPieces referring to the
* builder's same byte array, without rebuilding.
* If buildStringPiece() is called after build(), the trie will be
* re-serialized into a new array.
* If build() is called after buildStringPiece(), the trie object will become
* the owner of the previously returned array.
* After clear() has been called, a new array will be used as well.
* @param buildOption Build option, see UStringTrieBuildOption.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return A StringPiece which refers to the byte-serialized BytesTrie for the add()ed data.
* @stable ICU 4.8
*/
StringPiece buildStringPiece(UStringTrieBuildOption buildOption, UErrorCode &errorCode);
/**
* Removes all (byte sequence, value) pairs.
* New data can then be add()ed and a new trie can be built.
* @return *this
* @stable ICU 4.8
*/
BytesTrieBuilder &clear();
private:
BytesTrieBuilder(const BytesTrieBuilder &other); // no copy constructor
BytesTrieBuilder &operator=(const BytesTrieBuilder &other); // no assignment operator
void buildBytes(UStringTrieBuildOption buildOption, UErrorCode &errorCode);
virtual int32_t getElementStringLength(int32_t i) const;
virtual UChar getElementUnit(int32_t i, int32_t byteIndex) const;
virtual int32_t getElementValue(int32_t i) const;
virtual int32_t getLimitOfLinearMatch(int32_t first, int32_t last, int32_t byteIndex) const;
virtual int32_t countElementUnits(int32_t start, int32_t limit, int32_t byteIndex) const;
virtual int32_t skipElementsBySomeUnits(int32_t i, int32_t byteIndex, int32_t count) const;
virtual int32_t indexOfElementWithNextUnit(int32_t i, int32_t byteIndex, UChar byte) const;
virtual UBool matchNodesCanHaveValues() const { return FALSE; }
virtual int32_t getMaxBranchLinearSubNodeLength() const { return BytesTrie::kMaxBranchLinearSubNodeLength; }
virtual int32_t getMinLinearMatch() const { return BytesTrie::kMinLinearMatch; }
virtual int32_t getMaxLinearMatchLength() const { return BytesTrie::kMaxLinearMatchLength; }
#ifndef U_HIDE_INTERNAL_API
/**
* @internal
*/
class BTLinearMatchNode : public LinearMatchNode {
public:
BTLinearMatchNode(const char *units, int32_t len, Node *nextNode);
virtual UBool operator==(const Node &other) const;
virtual void write(StringTrieBuilder &builder);
private:
const char *s;
};
#endif /* U_HIDE_INTERNAL_API */
virtual Node *createLinearMatchNode(int32_t i, int32_t byteIndex, int32_t length,
Node *nextNode) const;
UBool ensureCapacity(int32_t length);
virtual int32_t write(int32_t byte);
int32_t write(const char *b, int32_t length);
virtual int32_t writeElementUnits(int32_t i, int32_t byteIndex, int32_t length);
virtual int32_t writeValueAndFinal(int32_t i, UBool isFinal);
virtual int32_t writeValueAndType(UBool hasValue, int32_t value, int32_t node);
virtual int32_t writeDeltaTo(int32_t jumpTarget);
CharString *strings; // Pointer not object so we need not #include internal charstr.h.
BytesTrieElement *elements;
int32_t elementsCapacity;
int32_t elementsLength;
// Byte serialization of the trie.
// Grows from the back: bytesLength measures from the end of the buffer!
char *bytes;
int32_t bytesCapacity;
int32_t bytesLength;
};
U_NAMESPACE_END
#endif // __BYTESTRIEBUILDER_H__
project/jni/icuuc/include/unicode/calendar.h
-2486
View File
File diff suppressed because it is too large Load Diff
project/jni/icuuc/include/unicode/caniter.h
-208
View File
@@ -1,208 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1996-2011, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*/
#ifndef CANITER_H
#define CANITER_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/uobject.h"
#include "unicode/unistr.h"
/**
* \file
* \brief C++ API: Canonical Iterator
*/
/** Should permutation skip characters with combining class zero
* Should be either TRUE or FALSE. This is a compile time option
* @stable ICU 2.4
*/
#ifndef CANITER_SKIP_ZEROES
#define CANITER_SKIP_ZEROES TRUE
#endif
U_NAMESPACE_BEGIN
class Hashtable;
class Normalizer2;
class Normalizer2Impl;
/**
* This class allows one to iterate through all the strings that are canonically equivalent to a given
* string. For example, here are some sample results:
Results for: {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
1: \\u0041\\u030A\\u0064\\u0307\\u0327
= {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
2: \\u0041\\u030A\\u0064\\u0327\\u0307
= {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
3: \\u0041\\u030A\\u1E0B\\u0327
= {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
4: \\u0041\\u030A\\u1E11\\u0307
= {LATIN CAPITAL LETTER A}{COMBINING RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
5: \\u00C5\\u0064\\u0307\\u0327
= {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
6: \\u00C5\\u0064\\u0327\\u0307
= {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
7: \\u00C5\\u1E0B\\u0327
= {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
8: \\u00C5\\u1E11\\u0307
= {LATIN CAPITAL LETTER A WITH RING ABOVE}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
9: \\u212B\\u0064\\u0307\\u0327
= {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING DOT ABOVE}{COMBINING CEDILLA}
10: \\u212B\\u0064\\u0327\\u0307
= {ANGSTROM SIGN}{LATIN SMALL LETTER D}{COMBINING CEDILLA}{COMBINING DOT ABOVE}
11: \\u212B\\u1E0B\\u0327
= {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH DOT ABOVE}{COMBINING CEDILLA}
12: \\u212B\\u1E11\\u0307
= {ANGSTROM SIGN}{LATIN SMALL LETTER D WITH CEDILLA}{COMBINING DOT ABOVE}
*<br>Note: the code is intended for use with small strings, and is not suitable for larger ones,
* since it has not been optimized for that situation.
* Note, CanonicalIterator is not intended to be subclassed.
* @author M. Davis
* @author C++ port by V. Weinstein
* @stable ICU 2.4
*/
class U_COMMON_API CanonicalIterator : public UObject {
public:
/**
* Construct a CanonicalIterator object
* @param source string to get results for
* @param status Fill-in parameter which receives the status of this operation.
* @stable ICU 2.4
*/
CanonicalIterator(const UnicodeString &source, UErrorCode &status);
/** Destructor
* Cleans pieces
* @stable ICU 2.4
*/
virtual ~CanonicalIterator();
/**
* Gets the NFD form of the current source we are iterating over.
* @return gets the source: NOTE: it is the NFD form of source
* @stable ICU 2.4
*/
UnicodeString getSource();
/**
* Resets the iterator so that one can start again from the beginning.
* @stable ICU 2.4
*/
void reset();
/**
* Get the next canonically equivalent string.
* <br><b>Warning: The strings are not guaranteed to be in any particular order.</b>
* @return the next string that is canonically equivalent. A bogus string is returned when
* the iteration is done.
* @stable ICU 2.4
*/
UnicodeString next();
/**
* Set a new source for this iterator. Allows object reuse.
* @param newSource the source string to iterate against. This allows the same iterator to be used
* while changing the source string, saving object creation.
* @param status Fill-in parameter which receives the status of this operation.
* @stable ICU 2.4
*/
void setSource(const UnicodeString &newSource, UErrorCode &status);
#ifndef U_HIDE_INTERNAL_API
/**
* Dumb recursive implementation of permutation.
* TODO: optimize
* @param source the string to find permutations for
* @param skipZeros determine if skip zeros
* @param result the results in a set.
* @param status Fill-in parameter which receives the status of this operation.
* @internal
*/
static void U_EXPORT2 permute(UnicodeString &source, UBool skipZeros, Hashtable *result, UErrorCode &status);
#endif /* U_HIDE_INTERNAL_API */
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
private:
// ===================== PRIVATES ==============================
// private default constructor
CanonicalIterator();
/**
* Copy constructor. Private for now.
* @internal
*/
CanonicalIterator(const CanonicalIterator& other);
/**
* Assignment operator. Private for now.
* @internal
*/
CanonicalIterator& operator=(const CanonicalIterator& other);
// fields
UnicodeString source;
UBool done;
// 2 dimensional array holds the pieces of the string with
// their different canonically equivalent representations
UnicodeString **pieces;
int32_t pieces_length;
int32_t *pieces_lengths;
// current is used in iterating to combine pieces
int32_t *current;
int32_t current_length;
// transient fields
UnicodeString buffer;
const Normalizer2 &nfd;
const Normalizer2Impl &nfcImpl;
// we have a segment, in NFD. Find all the strings that are canonically equivalent to it.
UnicodeString *getEquivalents(const UnicodeString &segment, int32_t &result_len, UErrorCode &status); //private String[] getEquivalents(String segment)
//Set getEquivalents2(String segment);
Hashtable *getEquivalents2(Hashtable *fillinResult, const UChar *segment, int32_t segLen, UErrorCode &status);
//Hashtable *getEquivalents2(const UnicodeString &segment, int32_t segLen, UErrorCode &status);
/**
* See if the decomposition of cp2 is at segment starting at segmentPos
* (with canonical rearrangment!)
* If so, take the remainder, and return the equivalents
*/
//Set extract(int comp, String segment, int segmentPos, StringBuffer buffer);
Hashtable *extract(Hashtable *fillinResult, UChar32 comp, const UChar *segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
//Hashtable *extract(UChar32 comp, const UnicodeString &segment, int32_t segLen, int32_t segmentPos, UErrorCode &status);
void cleanPieces();
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_NORMALIZATION */
#endif
project/jni/icuuc/include/unicode/chariter.h
-722
View File
@@ -1,722 +0,0 @@
/*
********************************************************************
*
* Copyright (C) 1997-2011, International Business Machines
* Corporation and others. All Rights Reserved.
*
********************************************************************
*/
#ifndef CHARITER_H
#define CHARITER_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/unistr.h"
/**
* \file
* \brief C++ API: Character Iterator
*/
U_NAMESPACE_BEGIN
/**
* Abstract class that defines an API for forward-only iteration
* on text objects.
* This is a minimal interface for iteration without random access
* or backwards iteration. It is especially useful for wrapping
* streams with converters into an object for collation or
* normalization.
*
* <p>Characters can be accessed in two ways: as code units or as
* code points.
* Unicode code points are 21-bit integers and are the scalar values
* of Unicode characters. ICU uses the type UChar32 for them.
* Unicode code units are the storage units of a given
* Unicode/UCS Transformation Format (a character encoding scheme).
* With UTF-16, all code points can be represented with either one
* or two code units ("surrogates").
* String storage is typically based on code units, while properties
* of characters are typically determined using code point values.
* Some processes may be designed to work with sequences of code units,
* or it may be known that all characters that are important to an
* algorithm can be represented with single code units.
* Other processes will need to use the code point access functions.</p>
*
* <p>ForwardCharacterIterator provides nextPostInc() to access
* a code unit and advance an internal position into the text object,
* similar to a <code>return text[position++]</code>.<br>
* It provides next32PostInc() to access a code point and advance an internal
* position.</p>
*
* <p>next32PostInc() assumes that the current position is that of
* the beginning of a code point, i.e., of its first code unit.
* After next32PostInc(), this will be true again.
* In general, access to code units and code points in the same
* iteration loop should not be mixed. In UTF-16, if the current position
* is on a second code unit (Low Surrogate), then only that code unit
* is returned even by next32PostInc().</p>
*
* <p>For iteration with either function, there are two ways to
* check for the end of the iteration. When there are no more
* characters in the text object:
* <ul>
* <li>The hasNext() function returns FALSE.</li>
* <li>nextPostInc() and next32PostInc() return DONE
* when one attempts to read beyond the end of the text object.</li>
* </ul>
*
* Example:
* \code
* void function1(ForwardCharacterIterator &it) {
* UChar32 c;
* while(it.hasNext()) {
* c=it.next32PostInc();
* // use c
* }
* }
*
* void function1(ForwardCharacterIterator &it) {
* UChar c;
* while((c=it.nextPostInc())!=ForwardCharacterIterator::DONE) {
* // use c
* }
* }
* \endcode
* </p>
*
* @stable ICU 2.0
*/
class U_COMMON_API ForwardCharacterIterator : public UObject {
public:
/**
* Value returned by most of ForwardCharacterIterator's functions
* when the iterator has reached the limits of its iteration.
* @stable ICU 2.0
*/
enum { DONE = 0xffff };
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~ForwardCharacterIterator();
/**
* Returns true when both iterators refer to the same
* character in the same character-storage object.
* @param that The ForwardCharacterIterator to be compared for equality
* @return true when both iterators refer to the same
* character in the same character-storage object
* @stable ICU 2.0
*/
virtual UBool operator==(const ForwardCharacterIterator& that) const = 0;
/**
* Returns true when the iterators refer to different
* text-storage objects, or to different characters in the
* same text-storage object.
* @param that The ForwardCharacterIterator to be compared for inequality
* @return true when the iterators refer to different
* text-storage objects, or to different characters in the
* same text-storage object
* @stable ICU 2.0
*/
inline UBool operator!=(const ForwardCharacterIterator& that) const;
/**
* Generates a hash code for this iterator.
* @return the hash code.
* @stable ICU 2.0
*/
virtual int32_t hashCode(void) const = 0;
/**
* Returns a UClassID for this ForwardCharacterIterator ("poor man's
* RTTI").<P> Despite the fact that this function is public,
* DO NOT CONSIDER IT PART OF CHARACTERITERATOR'S API!
* @return a UClassID for this ForwardCharacterIterator
* @stable ICU 2.0
*/
virtual UClassID getDynamicClassID(void) const = 0;
/**
* Gets the current code unit for returning and advances to the next code unit
* in the iteration range
* (toward endIndex()). If there are
* no more code units to return, returns DONE.
* @return the current code unit.
* @stable ICU 2.0
*/
virtual UChar nextPostInc(void) = 0;
/**
* Gets the current code point for returning and advances to the next code point
* in the iteration range
* (toward endIndex()). If there are
* no more code points to return, returns DONE.
* @return the current code point.
* @stable ICU 2.0
*/
virtual UChar32 next32PostInc(void) = 0;
/**
* Returns FALSE if there are no more code units or code points
* at or after the current position in the iteration range.
* This is used with nextPostInc() or next32PostInc() in forward
* iteration.
* @returns FALSE if there are no more code units or code points
* at or after the current position in the iteration range.
* @stable ICU 2.0
*/
virtual UBool hasNext() = 0;
protected:
/** Default constructor to be overridden in the implementing class. @stable ICU 2.0*/
ForwardCharacterIterator();
/** Copy constructor to be overridden in the implementing class. @stable ICU 2.0*/
ForwardCharacterIterator(const ForwardCharacterIterator &other);
/**
* Assignment operator to be overridden in the implementing class.
* @stable ICU 2.0
*/
ForwardCharacterIterator &operator=(const ForwardCharacterIterator&) { return *this; }
};
/**
* Abstract class that defines an API for iteration
* on text objects.
* This is an interface for forward and backward iteration
* and random access into a text object.
*
* <p>The API provides backward compatibility to the Java and older ICU
* CharacterIterator classes but extends them significantly:
* <ol>
* <li>CharacterIterator is now a subclass of ForwardCharacterIterator.</li>
* <li>While the old API functions provided forward iteration with
* "pre-increment" semantics, the new one also provides functions
* with "post-increment" semantics. They are more efficient and should
* be the preferred iterator functions for new implementations.
* The backward iteration always had "pre-decrement" semantics, which
* are efficient.</li>
* <li>Just like ForwardCharacterIterator, it provides access to
* both code units and code points. Code point access versions are available
* for the old and the new iteration semantics.</li>
* <li>There are new functions for setting and moving the current position
* without returning a character, for efficiency.</li>
* </ol>
*
* See ForwardCharacterIterator for examples for using the new forward iteration
* functions. For backward iteration, there is also a hasPrevious() function
* that can be used analogously to hasNext().
* The old functions work as before and are shown below.</p>
*
* <p>Examples for some of the new functions:</p>
*
* Forward iteration with hasNext():
* \code
* void forward1(CharacterIterator &it) {
* UChar32 c;
* for(it.setToStart(); it.hasNext();) {
* c=it.next32PostInc();
* // use c
* }
* }
* \endcode
* Forward iteration more similar to loops with the old forward iteration,
* showing a way to convert simple for() loops:
* \code
* void forward2(CharacterIterator &it) {
* UChar c;
* for(c=it.firstPostInc(); c!=CharacterIterator::DONE; c=it.nextPostInc()) {
* // use c
* }
* }
* \endcode
* Backward iteration with setToEnd() and hasPrevious():
* \code
* void backward1(CharacterIterator &it) {
* UChar32 c;
* for(it.setToEnd(); it.hasPrevious();) {
* c=it.previous32();
* // use c
* }
* }
* \endcode
* Backward iteration with a more traditional for() loop:
* \code
* void backward2(CharacterIterator &it) {
* UChar c;
* for(c=it.last(); c!=CharacterIterator::DONE; c=it.previous()) {
* // use c
* }
* }
* \endcode
*
* Example for random access:
* \code
* void random(CharacterIterator &it) {
* // set to the third code point from the beginning
* it.move32(3, CharacterIterator::kStart);
* // get a code point from here without moving the position
* UChar32 c=it.current32();
* // get the position
* int32_t pos=it.getIndex();
* // get the previous code unit
* UChar u=it.previous();
* // move back one more code unit
* it.move(-1, CharacterIterator::kCurrent);
* // set the position back to where it was
* // and read the same code point c and move beyond it
* it.setIndex(pos);
* if(c!=it.next32PostInc()) {
* exit(1); // CharacterIterator inconsistent
* }
* }
* \endcode
*
* <p>Examples, especially for the old API:</p>
*
* Function processing characters, in this example simple output
* <pre>
* \code
* void processChar( UChar c )
* {
* cout << " " << c;
* }
* \endcode
* </pre>
* Traverse the text from start to finish
* <pre>
* \code
* void traverseForward(CharacterIterator& iter)
* {
* for(UChar c = iter.first(); c != CharacterIterator.DONE; c = iter.next()) {
* processChar(c);
* }
* }
* \endcode
* </pre>
* Traverse the text backwards, from end to start
* <pre>
* \code
* void traverseBackward(CharacterIterator& iter)
* {
* for(UChar c = iter.last(); c != CharacterIterator.DONE; c = iter.previous()) {
* processChar(c);
* }
* }
* \endcode
* </pre>
* Traverse both forward and backward from a given position in the text.
* Calls to notBoundary() in this example represents some additional stopping criteria.
* <pre>
* \code
* void traverseOut(CharacterIterator& iter, int32_t pos)
* {
* UChar c;
* for (c = iter.setIndex(pos);
* c != CharacterIterator.DONE && (Unicode::isLetter(c) || Unicode::isDigit(c));
* c = iter.next()) {}
* int32_t end = iter.getIndex();
* for (c = iter.setIndex(pos);
* c != CharacterIterator.DONE && (Unicode::isLetter(c) || Unicode::isDigit(c));
* c = iter.previous()) {}
* int32_t start = iter.getIndex() + 1;
*
* cout << "start: " << start << " end: " << end << endl;
* for (c = iter.setIndex(start); iter.getIndex() < end; c = iter.next() ) {
* processChar(c);
* }
* }
* \endcode
* </pre>
* Creating a StringCharacterIterator and calling the test functions
* <pre>
* \code
* void CharacterIterator_Example( void )
* {
* cout << endl << "===== CharacterIterator_Example: =====" << endl;
* UnicodeString text("Ein kleiner Satz.");
* StringCharacterIterator iterator(text);
* cout << "----- traverseForward: -----------" << endl;
* traverseForward( iterator );
* cout << endl << endl << "----- traverseBackward: ----------" << endl;
* traverseBackward( iterator );
* cout << endl << endl << "----- traverseOut: ---------------" << endl;
* traverseOut( iterator, 7 );
* cout << endl << endl << "-----" << endl;
* }
* \endcode
* </pre>
*
* @stable ICU 2.0
*/
class U_COMMON_API CharacterIterator : public ForwardCharacterIterator {
public:
/**
* Origin enumeration for the move() and move32() functions.
* @stable ICU 2.0
*/
enum EOrigin { kStart, kCurrent, kEnd };
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~CharacterIterator();
/**
* Returns a pointer to a new CharacterIterator of the same
* concrete class as this one, and referring to the same
* character in the same text-storage object as this one. The
* caller is responsible for deleting the new clone.
* @return a pointer to a new CharacterIterator
* @stable ICU 2.0
*/
virtual CharacterIterator* clone(void) const = 0;
/**
* Sets the iterator to refer to the first code unit in its
* iteration range, and returns that code unit.
* This can be used to begin an iteration with next().
* @return the first code unit in its iteration range.
* @stable ICU 2.0
*/
virtual UChar first(void) = 0;
/**
* Sets the iterator to refer to the first code unit in its
* iteration range, returns that code unit, and moves the position
* to the second code unit. This is an alternative to setToStart()
* for forward iteration with nextPostInc().
* @return the first code unit in its iteration range.
* @stable ICU 2.0
*/
virtual UChar firstPostInc(void);
/**
* Sets the iterator to refer to the first code point in its
* iteration range, and returns that code unit,
* This can be used to begin an iteration with next32().
* Note that an iteration with next32PostInc(), beginning with,
* e.g., setToStart() or firstPostInc(), is more efficient.
* @return the first code point in its iteration range.
* @stable ICU 2.0
*/
virtual UChar32 first32(void) = 0;
/**
* Sets the iterator to refer to the first code point in its
* iteration range, returns that code point, and moves the position
* to the second code point. This is an alternative to setToStart()
* for forward iteration with next32PostInc().
* @return the first code point in its iteration range.
* @stable ICU 2.0
*/
virtual UChar32 first32PostInc(void);
/**
* Sets the iterator to refer to the first code unit or code point in its
* iteration range. This can be used to begin a forward
* iteration with nextPostInc() or next32PostInc().
* @return the start position of the iteration range
* @stable ICU 2.0
*/
inline int32_t setToStart();
/**
* Sets the iterator to refer to the last code unit in its
* iteration range, and returns that code unit.
* This can be used to begin an iteration with previous().
* @return the last code unit.
* @stable ICU 2.0
*/
virtual UChar last(void) = 0;
/**
* Sets the iterator to refer to the last code point in its
* iteration range, and returns that code unit.
* This can be used to begin an iteration with previous32().
* @return the last code point.
* @stable ICU 2.0
*/
virtual UChar32 last32(void) = 0;
/**
* Sets the iterator to the end of its iteration range, just behind
* the last code unit or code point. This can be used to begin a backward
* iteration with previous() or previous32().
* @return the end position of the iteration range
* @stable ICU 2.0
*/
inline int32_t setToEnd();
/**
* Sets the iterator to refer to the "position"-th code unit
* in the text-storage object the iterator refers to, and
* returns that code unit.
* @param position the "position"-th code unit in the text-storage object
* @return the "position"-th code unit.
* @stable ICU 2.0
*/
virtual UChar setIndex(int32_t position) = 0;
/**
* Sets the iterator to refer to the beginning of the code point
* that contains the "position"-th code unit
* in the text-storage object the iterator refers to, and
* returns that code point.
* The current position is adjusted to the beginning of the code point
* (its first code unit).
* @param position the "position"-th code unit in the text-storage object
* @return the "position"-th code point.
* @stable ICU 2.0
*/
virtual UChar32 setIndex32(int32_t position) = 0;
/**
* Returns the code unit the iterator currently refers to.
* @return the current code unit.
* @stable ICU 2.0
*/
virtual UChar current(void) const = 0;
/**
* Returns the code point the iterator currently refers to.
* @return the current code point.
* @stable ICU 2.0
*/
virtual UChar32 current32(void) const = 0;
/**
* Advances to the next code unit in the iteration range
* (toward endIndex()), and returns that code unit. If there are
* no more code units to return, returns DONE.
* @return the next code unit.
* @stable ICU 2.0
*/
virtual UChar next(void) = 0;
/**
* Advances to the next code point in the iteration range
* (toward endIndex()), and returns that code point. If there are
* no more code points to return, returns DONE.
* Note that iteration with "pre-increment" semantics is less
* efficient than iteration with "post-increment" semantics
* that is provided by next32PostInc().
* @return the next code point.
* @stable ICU 2.0
*/
virtual UChar32 next32(void) = 0;
/**
* Advances to the previous code unit in the iteration range
* (toward startIndex()), and returns that code unit. If there are
* no more code units to return, returns DONE.
* @return the previous code unit.
* @stable ICU 2.0
*/
virtual UChar previous(void) = 0;
/**
* Advances to the previous code point in the iteration range
* (toward startIndex()), and returns that code point. If there are
* no more code points to return, returns DONE.
* @return the previous code point.
* @stable ICU 2.0
*/
virtual UChar32 previous32(void) = 0;
/**
* Returns FALSE if there are no more code units or code points
* before the current position in the iteration range.
* This is used with previous() or previous32() in backward
* iteration.
* @return FALSE if there are no more code units or code points
* before the current position in the iteration range, return TRUE otherwise.
* @stable ICU 2.0
*/
virtual UBool hasPrevious() = 0;
/**
* Returns the numeric index in the underlying text-storage
* object of the character returned by first(). Since it's
* possible to create an iterator that iterates across only
* part of a text-storage object, this number isn't
* necessarily 0.
* @returns the numeric index in the underlying text-storage
* object of the character returned by first().
* @stable ICU 2.0
*/
inline int32_t startIndex(void) const;
/**
* Returns the numeric index in the underlying text-storage
* object of the position immediately BEYOND the character
* returned by last().
* @return the numeric index in the underlying text-storage
* object of the position immediately BEYOND the character
* returned by last().
* @stable ICU 2.0
*/
inline int32_t endIndex(void) const;
/**
* Returns the numeric index in the underlying text-storage
* object of the character the iterator currently refers to
* (i.e., the character returned by current()).
* @return the numberic index in the text-storage object of
* the character the iterator currently refers to
* @stable ICU 2.0
*/
inline int32_t getIndex(void) const;
/**
* Returns the length of the entire text in the underlying
* text-storage object.
* @return the length of the entire text in the text-storage object
* @stable ICU 2.0
*/
inline int32_t getLength() const;
/**
* Moves the current position relative to the start or end of the
* iteration range, or relative to the current position itself.
* The movement is expressed in numbers of code units forward
* or backward by specifying a positive or negative delta.
* @param delta the position relative to origin. A positive delta means forward;
* a negative delta means backward.
* @param origin Origin enumeration {kStart, kCurrent, kEnd}
* @return the new position
* @stable ICU 2.0
*/
virtual int32_t move(int32_t delta, EOrigin origin) = 0;
/**
* Moves the current position relative to the start or end of the
* iteration range, or relative to the current position itself.
* The movement is expressed in numbers of code points forward
* or backward by specifying a positive or negative delta.
* @param delta the position relative to origin. A positive delta means forward;
* a negative delta means backward.
* @param origin Origin enumeration {kStart, kCurrent, kEnd}
* @return the new position
* @stable ICU 2.0
*/
virtual int32_t move32(int32_t delta, EOrigin origin) = 0;
/**
* Copies the text under iteration into the UnicodeString
* referred to by "result".
* @param result Receives a copy of the text under iteration.
* @stable ICU 2.0
*/
virtual void getText(UnicodeString& result) = 0;
protected:
/**
* Empty constructor.
* @stable ICU 2.0
*/
CharacterIterator();
/**
* Constructor, just setting the length field in this base class.
* @stable ICU 2.0
*/
CharacterIterator(int32_t length);
/**
* Constructor, just setting the length and position fields in this base class.
* @stable ICU 2.0
*/
CharacterIterator(int32_t length, int32_t position);
/**
* Constructor, just setting the length, start, end, and position fields in this base class.
* @stable ICU 2.0
*/
CharacterIterator(int32_t length, int32_t textBegin, int32_t textEnd, int32_t position);
/**
* Copy constructor.
*
* @param that The CharacterIterator to be copied
* @stable ICU 2.0
*/
CharacterIterator(const CharacterIterator &that);
/**
* Assignment operator. Sets this CharacterIterator to have the same behavior,
* as the one passed in.
* @param that The CharacterIterator passed in.
* @return the newly set CharacterIterator.
* @stable ICU 2.0
*/
CharacterIterator &operator=(const CharacterIterator &that);
/**
* Base class text length field.
* Necessary this for correct getText() and hashCode().
* @stable ICU 2.0
*/
int32_t textLength;
/**
* Base class field for the current position.
* @stable ICU 2.0
*/
int32_t pos;
/**
* Base class field for the start of the iteration range.
* @stable ICU 2.0
*/
int32_t begin;
/**
* Base class field for the end of the iteration range.
* @stable ICU 2.0
*/
int32_t end;
};
inline UBool
ForwardCharacterIterator::operator!=(const ForwardCharacterIterator& that) const {
return !operator==(that);
}
inline int32_t
CharacterIterator::setToStart() {
return move(0, kStart);
}
inline int32_t
CharacterIterator::setToEnd() {
return move(0, kEnd);
}
inline int32_t
CharacterIterator::startIndex(void) const {
return begin;
}
inline int32_t
CharacterIterator::endIndex(void) const {
return end;
}
inline int32_t
CharacterIterator::getIndex(void) const {
return pos;
}
inline int32_t
CharacterIterator::getLength(void) const {
return textLength;
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/choicfmt.h
-594
View File
@@ -1,594 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File CHOICFMT.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 03/20/97 helena Finished first cut of implementation and got rid
* of nextDouble/previousDouble and replaced with
* boolean array.
* 4/10/97 aliu Clean up. Modified to work on AIX.
* 8/6/97 nos Removed overloaded constructor, member var 'buffer'.
* 07/22/98 stephen Removed operator!= (implemented in Format)
********************************************************************************
*/
#ifndef CHOICFMT_H
#define CHOICFMT_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Choice Format.
*/
#if !UCONFIG_NO_FORMATTING
#ifndef U_HIDE_DEPRECATED_API
#include "unicode/fieldpos.h"
#include "unicode/format.h"
#include "unicode/messagepattern.h"
#include "unicode/numfmt.h"
#include "unicode/unistr.h"
U_NAMESPACE_BEGIN
class MessageFormat;
/**
* ChoiceFormat converts between ranges of numeric values and strings for those ranges.
* The strings must conform to the MessageFormat pattern syntax.
*
* <p><em><code>ChoiceFormat</code> is probably not what you need.
* Please use <code>MessageFormat</code>
* with <code>plural</code> arguments for proper plural selection,
* and <code>select</code> arguments for simple selection among a fixed set of choices!</em></p>
*
* <p>A <code>ChoiceFormat</code> splits
* the real number line \htmlonly<code>-&#x221E;</code> to
* <code>+&#x221E;</code>\endhtmlonly into two
* or more contiguous ranges. Each range is mapped to a
* string.</p>
*
* <p><code>ChoiceFormat</code> was originally intended
* for displaying grammatically correct
* plurals such as &quot;There is one file.&quot; vs. &quot;There are 2 files.&quot;
* <em>However,</em> plural rules for many languages
* are too complex for the capabilities of ChoiceFormat,
* and its requirement of specifying the precise rules for each message
* is unmanageable for translators.</p>
*
* <p>There are two methods of defining a <code>ChoiceFormat</code>; both
* are equivalent. The first is by using a string pattern. This is the
* preferred method in most cases. The second method is through direct
* specification of the arrays that logically make up the
* <code>ChoiceFormat</code>.</p>
*
* <p>Note: Typically, choice formatting is done (if done at all) via <code>MessageFormat</code>
* with a <code>choice</code> argument type,
* rather than using a stand-alone <code>ChoiceFormat</code>.</p>
*
* <h5>Patterns and Their Interpretation</h5>
*
* <p>The pattern string defines the range boundaries and the strings for each number range.
* Syntax:
* <pre>
* choiceStyle = number separator message ('|' number separator message)*
* number = normal_number | ['-'] \htmlonly&#x221E;\endhtmlonly (U+221E, infinity)
* normal_number = double value (unlocalized ASCII string)
* separator = less_than | less_than_or_equal
* less_than = '<'
* less_than_or_equal = '#' | \htmlonly&#x2264;\endhtmlonly (U+2264)
* message: see {@link MessageFormat}
* </pre>
* Pattern_White_Space between syntax elements is ignored, except
* around each range's sub-message.</p>
*
* <p>Each numeric sub-range extends from the current range's number
* to the next range's number.
* The number itself is included in its range if a <code>less_than_or_equal</code> sign is used,
* and excluded from its range (and instead included in the previous range)
* if a <code>less_than</code> sign is used.</p>
*
* <p>When a <code>ChoiceFormat</code> is constructed from
* arrays of numbers, closure flags and strings,
* they are interpreted just like
* the sequence of <code>(number separator string)</code> in an equivalent pattern string.
* <code>closure[i]==TRUE</code> corresponds to a <code>less_than</code> separator sign.
* The equivalent pattern string will be constructed automatically.</p>
*
* <p>During formatting, a number is mapped to the first range
* where the number is not greater than the range's upper limit.
* That range's message string is returned. A NaN maps to the very first range.</p>
*
* <p>During parsing, a range is selected for the longest match of
* any range's message. That range's number is returned, ignoring the separator/closure.
* Only a simple string match is performed, without parsing of arguments that
* might be specified in the message strings.</p>
*
* <p>Note that the first range's number is ignored in formatting
* but may be returned from parsing.</p>
*
* <h5>Examples</h5>
*
* <p>Here is an example of two arrays that map the number
* <code>1..7</code> to the English day of the week abbreviations
* <code>Sun..Sat</code>. No closures array is given; this is the same as
* specifying all closures to be <code>FALSE</code>.</p>
*
* <pre> {1,2,3,4,5,6,7},
* {&quot;Sun&quot;,&quot;Mon&quot;,&quot;Tue&quot;,&quot;Wed&quot;,&quot;Thur&quot;,&quot;Fri&quot;,&quot;Sat&quot;}</pre>
*
* <p>Here is an example that maps the ranges [-Inf, 1), [1, 1], and (1,
* +Inf] to three strings. That is, the number line is split into three
* ranges: x &lt; 1.0, x = 1.0, and x &gt; 1.0.
* (The round parentheses in the notation above indicate an exclusive boundary,
* like the turned bracket in European notation: [-Inf, 1) == [-Inf, 1[ )</p>
*
* <pre> {0, 1, 1},
* {FALSE, FALSE, TRUE},
* {&quot;no files&quot;, &quot;one file&quot;, &quot;many files&quot;}</pre>
*
* <p>Here is an example that shows formatting and parsing: </p>
*
* \code
* #include <unicode/choicfmt.h>
* #include <unicode/unistr.h>
* #include <iostream.h>
*
* int main(int argc, char *argv[]) {
* double limits[] = {1,2,3,4,5,6,7};
* UnicodeString monthNames[] = {
* "Sun","Mon","Tue","Wed","Thu","Fri","Sat"};
* ChoiceFormat fmt(limits, monthNames, 7);
* UnicodeString str;
* char buf[256];
* for (double x = 1.0; x <= 8.0; x += 1.0) {
* fmt.format(x, str);
* str.extract(0, str.length(), buf, 256, "");
* str.truncate(0);
* cout << x << " -> "
* << buf << endl;
* }
* cout << endl;
* return 0;
* }
* \endcode
*
* <p><em>User subclasses are not supported.</em> While clients may write
* subclasses, such code will not necessarily work and will not be
* guaranteed to work stably from release to release.
*
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
class U_I18N_API ChoiceFormat: public NumberFormat {
public:
/**
* Constructs a new ChoiceFormat from the pattern string.
*
* @param pattern Pattern used to construct object.
* @param status Output param to receive success code. If the
* pattern cannot be parsed, set to failure code.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
ChoiceFormat(const UnicodeString& pattern,
UErrorCode& status);
/**
* Constructs a new ChoiceFormat with the given limits and message strings.
* All closure flags default to <code>FALSE</code>,
* equivalent to <code>less_than_or_equal</code> separators.
*
* Copies the limits and formats instead of adopting them.
*
* @param limits Array of limit values.
* @param formats Array of formats.
* @param count Size of 'limits' and 'formats' arrays.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
ChoiceFormat(const double* limits,
const UnicodeString* formats,
int32_t count );
/**
* Constructs a new ChoiceFormat with the given limits, closure flags and message strings.
*
* Copies the limits and formats instead of adopting them.
*
* @param limits Array of limit values
* @param closures Array of booleans specifying whether each
* element of 'limits' is open or closed. If FALSE, then the
* corresponding limit number is a member of its range.
* If TRUE, then the limit number belongs to the previous range it.
* @param formats Array of formats
* @param count Size of 'limits', 'closures', and 'formats' arrays
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
ChoiceFormat(const double* limits,
const UBool* closures,
const UnicodeString* formats,
int32_t count);
/**
* Copy constructor.
*
* @param that ChoiceFormat object to be copied from
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
ChoiceFormat(const ChoiceFormat& that);
/**
* Assignment operator.
*
* @param that ChoiceFormat object to be copied
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
const ChoiceFormat& operator=(const ChoiceFormat& that);
/**
* Destructor.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual ~ChoiceFormat();
/**
* Clones this Format object. The caller owns the
* result and must delete it when done.
*
* @return a copy of this object
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual Format* clone(void) const;
/**
* Returns true if the given Format objects are semantically equal.
* Objects of different subclasses are considered unequal.
*
* @param other ChoiceFormat object to be compared
* @return true if other is the same as this.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UBool operator==(const Format& other) const;
/**
* Sets the pattern.
* @param pattern The pattern to be applied.
* @param status Output param set to success/failure code on
* exit. If the pattern is invalid, this will be
* set to a failure result.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual void applyPattern(const UnicodeString& pattern,
UErrorCode& status);
/**
* Sets the pattern.
* @param pattern The pattern to be applied.
* @param parseError Struct to receive information on position
* of error if an error is encountered
* @param status Output param set to success/failure code on
* exit. If the pattern is invalid, this will be
* set to a failure result.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual void applyPattern(const UnicodeString& pattern,
UParseError& parseError,
UErrorCode& status);
/**
* Gets the pattern.
*
* @param pattern Output param which will receive the pattern
* Previous contents are deleted.
* @return A reference to 'pattern'
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UnicodeString& toPattern(UnicodeString &pattern) const;
/**
* Sets the choices to be used in formatting.
* For details see the constructor with the same parameter list.
*
* @param limitsToCopy Contains the top value that you want
* parsed with that format,and should be in
* ascending sorted order. When formatting X,
* the choice will be the i, where limit[i]
* &lt;= X &lt; limit[i+1].
* @param formatsToCopy The format strings you want to use for each limit.
* @param count The size of the above arrays.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual void setChoices(const double* limitsToCopy,
const UnicodeString* formatsToCopy,
int32_t count );
/**
* Sets the choices to be used in formatting.
* For details see the constructor with the same parameter list.
*
* @param limits Array of limits
* @param closures Array of limit booleans
* @param formats Array of format string
* @param count The size of the above arrays
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual void setChoices(const double* limits,
const UBool* closures,
const UnicodeString* formats,
int32_t count);
/**
* Returns NULL and 0.
* Before ICU 4.8, this used to return the choice limits array.
*
* @param count Will be set to 0.
* @return NULL
* @deprecated ICU 4.8 Use the MessagePattern class to analyze a ChoiceFormat pattern.
*/
virtual const double* getLimits(int32_t& count) const;
/**
* Returns NULL and 0.
* Before ICU 4.8, this used to return the limit booleans array.
*
* @param count Will be set to 0.
* @return NULL
* @deprecated ICU 4.8 Use the MessagePattern class to analyze a ChoiceFormat pattern.
*/
virtual const UBool* getClosures(int32_t& count) const;
/**
* Returns NULL and 0.
* Before ICU 4.8, this used to return the array of choice strings.
*
* @param count Will be set to 0.
* @return NULL
* @deprecated ICU 4.8 Use the MessagePattern class to analyze a ChoiceFormat pattern.
*/
virtual const UnicodeString* getFormats(int32_t& count) const;
using NumberFormat::format;
/**
* Formats a double number using this object's choices.
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @return Reference to 'appendTo' parameter.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UnicodeString& format(double number,
UnicodeString& appendTo,
FieldPosition& pos) const;
/**
* Formats an int32_t number using this object's choices.
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @return Reference to 'appendTo' parameter.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UnicodeString& format(int32_t number,
UnicodeString& appendTo,
FieldPosition& pos) const;
/**
* Formats an int64_t number using this object's choices.
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @return Reference to 'appendTo' parameter.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UnicodeString& format(int64_t number,
UnicodeString& appendTo,
FieldPosition& pos) const;
/**
* Formats an array of objects using this object's choices.
*
* @param objs The array of objects to be formatted.
* @param cnt The size of objs.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param success Output param set to success/failure code on
* exit.
* @return Reference to 'appendTo' parameter.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UnicodeString& format(const Formattable* objs,
int32_t cnt,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& success) const;
using NumberFormat::parse;
/**
* Looks for the longest match of any message string on the input text and,
* if there is a match, sets the result object to the corresponding range's number.
*
* If no string matches, then the parsePosition is unchanged.
*
* @param text The text to be parsed.
* @param result Formattable to be set to the parse result.
* If parse fails, return contents are undefined.
* @param parsePosition The position to start parsing at on input.
* On output, moved to after the last successfully
* parse character. On parse failure, does not change.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual void parse(const UnicodeString& text,
Formattable& result,
ParsePosition& parsePosition) const;
/**
* Returns a unique class ID POLYMORPHICALLY. Part of ICU's "poor man's RTTI".
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
virtual UClassID getDynamicClassID(void) const;
/**
* Returns the class ID for this class. This is useful only for
* comparing to a return value from getDynamicClassID(). For example:
* <pre>
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . Derived::getStaticClassID()) ...
* </pre>
* @return The class ID for all objects of this class.
* @deprecated ICU 49 Use MessageFormat instead, with plural and select arguments.
*/
static UClassID U_EXPORT2 getStaticClassID(void);
private:
/**
* Converts a double value to a string.
* @param value the double number to be converted.
* @param string the result string.
* @return the converted string.
*/
static UnicodeString& dtos(double value, UnicodeString& string);
ChoiceFormat(); // default constructor not implemented
/**
* Construct a new ChoiceFormat with the limits and the corresponding formats
* based on the pattern.
*
* @param newPattern Pattern used to construct object.
* @param parseError Struct to receive information on position
* of error if an error is encountered.
* @param status Output param to receive success code. If the
* pattern cannot be parsed, set to failure code.
*/
ChoiceFormat(const UnicodeString& newPattern,
UParseError& parseError,
UErrorCode& status);
friend class MessageFormat;
virtual void setChoices(const double* limits,
const UBool* closures,
const UnicodeString* formats,
int32_t count,
UErrorCode &errorCode);
/**
* Finds the ChoiceFormat sub-message for the given number.
* @param pattern A MessagePattern.
* @param partIndex the index of the first ChoiceFormat argument style part.
* @param number a number to be mapped to one of the ChoiceFormat argument's intervals
* @return the sub-message start part index.
*/
static int32_t findSubMessage(const MessagePattern &pattern, int32_t partIndex, double number);
static double parseArgument(
const MessagePattern &pattern, int32_t partIndex,
const UnicodeString &source, ParsePosition &pos);
/**
* Matches the pattern string from the end of the partIndex to
* the beginning of the limitPartIndex,
* including all syntax except SKIP_SYNTAX,
* against the source string starting at sourceOffset.
* If they match, returns the length of the source string match.
* Otherwise returns -1.
*/
static int32_t matchStringUntilLimitPart(
const MessagePattern &pattern, int32_t partIndex, int32_t limitPartIndex,
const UnicodeString &source, int32_t sourceOffset);
/**
* Some of the ChoiceFormat constructors do not have a UErrorCode paramater.
* We need _some_ way to provide one for the MessagePattern constructor.
* Alternatively, the MessagePattern could be a pointer field, but that is
* not nice either.
*/
UErrorCode constructorErrorCode;
/**
* The MessagePattern which contains the parsed structure of the pattern string.
*
* Starting with ICU 4.8, the MessagePattern contains a sequence of
* numeric/selector/message parts corresponding to the parsed pattern.
* For details see the MessagePattern class API docs.
*/
MessagePattern msgPattern;
/**
* Docs & fields from before ICU 4.8, before MessagePattern was used.
* Commented out, and left only for explanation of semantics.
* --------
* Each ChoiceFormat divides the range -Inf..+Inf into fCount
* intervals. The intervals are:
*
* 0: fChoiceLimits[0]..fChoiceLimits[1]
* 1: fChoiceLimits[1]..fChoiceLimits[2]
* ...
* fCount-2: fChoiceLimits[fCount-2]..fChoiceLimits[fCount-1]
* fCount-1: fChoiceLimits[fCount-1]..+Inf
*
* Interval 0 is special; during formatting (mapping numbers to
* strings), it also contains all numbers less than
* fChoiceLimits[0], as well as NaN values.
*
* Interval i maps to and from string fChoiceFormats[i]. When
* parsing (mapping strings to numbers), then intervals map to
* their lower limit, that is, interval i maps to fChoiceLimit[i].
*
* The intervals may be closed, half open, or open. This affects
* formatting but does not affect parsing. Interval i is affected
* by fClosures[i] and fClosures[i+1]. If fClosures[i]
* is FALSE, then the value fChoiceLimits[i] is in interval i.
* That is, intervals i and i are:
*
* i-1: ... x < fChoiceLimits[i]
* i: fChoiceLimits[i] <= x ...
*
* If fClosures[i] is TRUE, then the value fChoiceLimits[i] is
* in interval i-1. That is, intervals i-1 and i are:
*
* i-1: ... x <= fChoiceLimits[i]
* i: fChoiceLimits[i] < x ...
*
* Because of the nature of interval 0, fClosures[0] has no
* effect.
*/
// double* fChoiceLimits;
// UBool* fClosures;
// UnicodeString* fChoiceFormats;
// int32_t fCount;
};
U_NAMESPACE_END
#endif // U_HIDE_DEPRECATED_API
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // CHOICFMT_H
//eof
project/jni/icuuc/include/unicode/coleitr.h
-384
View File
@@ -1,384 +0,0 @@
/*
******************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
******************************************************************************
*/
/**
* \file
* \brief C++ API: Collation Element Iterator.
*/
/**
* File coleitr.h
*
*
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
*
* 8/18/97 helena Added internal API documentation.
* 08/03/98 erm Synched with 1.2 version CollationElementIterator.java
* 12/10/99 aliu Ported Thai collation support from Java.
* 01/25/01 swquek Modified into a C++ wrapper calling C APIs (ucoliter.h)
* 02/19/01 swquek Removed CollationElementsIterator() since it is
* private constructor and no calls are made to it
*/
#ifndef COLEITR_H
#define COLEITR_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_COLLATION
#include "unicode/uobject.h"
#include "unicode/tblcoll.h"
#include "unicode/ucoleitr.h"
/**
* The UCollationElements struct.
* For usage in C programs.
* @stable ICU 2.0
*/
typedef struct UCollationElements UCollationElements;
U_NAMESPACE_BEGIN
/**
* The CollationElementIterator class is used as an iterator to walk through
* each character of an international string. Use the iterator to return the
* ordering priority of the positioned character. The ordering priority of a
* character, which we refer to as a key, defines how a character is collated in
* the given collation object.
* For example, consider the following in Spanish:
* <pre>
* "ca" -> the first key is key('c') and second key is key('a').
* "cha" -> the first key is key('ch') and second key is key('a').</pre>
* And in German,
* <pre> \htmlonly "&#x00E6;b"-> the first key is key('a'), the second key is key('e'), and
* the third key is key('b'). \endhtmlonly </pre>
* The key of a character, is an integer composed of primary order(short),
* secondary order(char), and tertiary order(char). Java strictly defines the
* size and signedness of its primitive data types. Therefore, the static
* functions primaryOrder(), secondaryOrder(), and tertiaryOrder() return
* int32_t to ensure the correctness of the key value.
* <p>Example of the iterator usage: (without error checking)
* <pre>
* \code
* void CollationElementIterator_Example()
* {
* UnicodeString str = "This is a test";
* UErrorCode success = U_ZERO_ERROR;
* RuleBasedCollator* rbc =
* (RuleBasedCollator*) RuleBasedCollator::createInstance(success);
* CollationElementIterator* c =
* rbc->createCollationElementIterator( str );
* int32_t order = c->next(success);
* c->reset();
* order = c->previous(success);
* delete c;
* delete rbc;
* }
* \endcode
* </pre>
* <p>
* The method next() returns the collation order of the next character based on
* the comparison level of the collator. The method previous() returns the
* collation order of the previous character based on the comparison level of
* the collator. The Collation Element Iterator moves only in one direction
* between calls to reset(), setOffset(), or setText(). That is, next()
* and previous() can not be inter-used. Whenever previous() is to be called after
* next() or vice versa, reset(), setOffset() or setText() has to be called first
* to reset the status, shifting pointers to either the end or the start of
* the string (reset() or setText()), or the specified position (setOffset()).
* Hence at the next call of next() or previous(), the first or last collation order,
* or collation order at the spefcifieid position will be returned. If a change of
* direction is done without one of these calls, the result is undefined.
* <p>
* The result of a forward iterate (next()) and reversed result of the backward
* iterate (previous()) on the same string are equivalent, if collation orders
* with the value UCOL_IGNORABLE are ignored.
* Character based on the comparison level of the collator. A collation order
* consists of primary order, secondary order and tertiary order. The data
* type of the collation order is <strong>t_int32</strong>.
*
* Note, CollationElementIterator should not be subclassed.
* @see Collator
* @see RuleBasedCollator
* @version 1.8 Jan 16 2001
*/
class U_I18N_API CollationElementIterator : public UObject {
public:
// CollationElementIterator public data member ------------------------------
enum {
/**
* NULLORDER indicates that an error has occured while processing
* @stable ICU 2.0
*/
NULLORDER = (int32_t)0xffffffff
};
// CollationElementIterator public constructor/destructor -------------------
/**
* Copy constructor.
*
* @param other the object to be copied from
* @stable ICU 2.0
*/
CollationElementIterator(const CollationElementIterator& other);
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~CollationElementIterator();
// CollationElementIterator public methods ----------------------------------
/**
* Returns true if "other" is the same as "this"
*
* @param other the object to be compared
* @return true if "other" is the same as "this"
* @stable ICU 2.0
*/
UBool operator==(const CollationElementIterator& other) const;
/**
* Returns true if "other" is not the same as "this".
*
* @param other the object to be compared
* @return true if "other" is not the same as "this"
* @stable ICU 2.0
*/
UBool operator!=(const CollationElementIterator& other) const;
/**
* Resets the cursor to the beginning of the string.
* @stable ICU 2.0
*/
void reset(void);
/**
* Gets the ordering priority of the next character in the string.
* @param status the error code status.
* @return the next character's ordering. otherwise returns NULLORDER if an
* error has occured or if the end of string has been reached
* @stable ICU 2.0
*/
int32_t next(UErrorCode& status);
/**
* Get the ordering priority of the previous collation element in the string.
* @param status the error code status.
* @return the previous element's ordering. otherwise returns NULLORDER if an
* error has occured or if the start of string has been reached
* @stable ICU 2.0
*/
int32_t previous(UErrorCode& status);
/**
* Gets the primary order of a collation order.
* @param order the collation order
* @return the primary order of a collation order.
* @stable ICU 2.0
*/
static inline int32_t primaryOrder(int32_t order);
/**
* Gets the secondary order of a collation order.
* @param order the collation order
* @return the secondary order of a collation order.
* @stable ICU 2.0
*/
static inline int32_t secondaryOrder(int32_t order);
/**
* Gets the tertiary order of a collation order.
* @param order the collation order
* @return the tertiary order of a collation order.
* @stable ICU 2.0
*/
static inline int32_t tertiaryOrder(int32_t order);
/**
* Return the maximum length of any expansion sequences that end with the
* specified comparison order.
* @param order a collation order returned by previous or next.
* @return maximum size of the expansion sequences ending with the collation
* element or 1 if collation element does not occur at the end of any
* expansion sequence
* @stable ICU 2.0
*/
int32_t getMaxExpansion(int32_t order) const;
/**
* Gets the comparison order in the desired strength. Ignore the other
* differences.
* @param order The order value
* @stable ICU 2.0
*/
int32_t strengthOrder(int32_t order) const;
/**
* Sets the source string.
* @param str the source string.
* @param status the error code status.
* @stable ICU 2.0
*/
void setText(const UnicodeString& str, UErrorCode& status);
/**
* Sets the source string.
* @param str the source character iterator.
* @param status the error code status.
* @stable ICU 2.0
*/
void setText(CharacterIterator& str, UErrorCode& status);
/**
* Checks if a comparison order is ignorable.
* @param order the collation order.
* @return TRUE if a character is ignorable, FALSE otherwise.
* @stable ICU 2.0
*/
static inline UBool isIgnorable(int32_t order);
/**
* Gets the offset of the currently processed character in the source string.
* @return the offset of the character.
* @stable ICU 2.0
*/
int32_t getOffset(void) const;
/**
* Sets the offset of the currently processed character in the source string.
* @param newOffset the new offset.
* @param status the error code status.
* @return the offset of the character.
* @stable ICU 2.0
*/
void setOffset(int32_t newOffset, UErrorCode& status);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
friend class RuleBasedCollator;
/**
* CollationElementIterator constructor. This takes the source string and the
* collation object. The cursor will walk thru the source string based on the
* predefined collation rules. If the source string is empty, NULLORDER will
* be returned on the calls to next().
* @param sourceText the source string.
* @param order the collation object.
* @param status the error code status.
*/
CollationElementIterator(const UnicodeString& sourceText,
const RuleBasedCollator* order, UErrorCode& status);
/**
* CollationElementIterator constructor. This takes the source string and the
* collation object. The cursor will walk thru the source string based on the
* predefined collation rules. If the source string is empty, NULLORDER will
* be returned on the calls to next().
* @param sourceText the source string.
* @param order the collation object.
* @param status the error code status.
*/
CollationElementIterator(const CharacterIterator& sourceText,
const RuleBasedCollator* order, UErrorCode& status);
/**
* Assignment operator
*
* @param other the object to be copied
*/
const CollationElementIterator&
operator=(const CollationElementIterator& other);
CollationElementIterator(); // default constructor not implemented
// CollationElementIterator private data members ----------------------------
/**
* Data wrapper for collation elements
*/
UCollationElements *m_data_;
/**
* Indicates if m_data_ belongs to this object.
*/
UBool isDataOwned_;
};
// CollationElementIterator inline method defination --------------------------
/**
* Get the primary order of a collation order.
* @param order the collation order
* @return the primary order of a collation order.
*/
inline int32_t CollationElementIterator::primaryOrder(int32_t order)
{
order &= RuleBasedCollator::PRIMARYORDERMASK;
return (order >> RuleBasedCollator::PRIMARYORDERSHIFT);
}
/**
* Get the secondary order of a collation order.
* @param order the collation order
* @return the secondary order of a collation order.
*/
inline int32_t CollationElementIterator::secondaryOrder(int32_t order)
{
order = order & RuleBasedCollator::SECONDARYORDERMASK;
return (order >> RuleBasedCollator::SECONDARYORDERSHIFT);
}
/**
* Get the tertiary order of a collation order.
* @param order the collation order
* @return the tertiary order of a collation order.
*/
inline int32_t CollationElementIterator::tertiaryOrder(int32_t order)
{
return (order &= RuleBasedCollator::TERTIARYORDERMASK);
}
inline int32_t CollationElementIterator::getMaxExpansion(int32_t order) const
{
return ucol_getMaxExpansion(m_data_, (uint32_t)order);
}
inline UBool CollationElementIterator::isIgnorable(int32_t order)
{
return (primaryOrder(order) == RuleBasedCollator::PRIMIGNORABLE);
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_COLLATION */
#endif
project/jni/icuuc/include/unicode/coll.h
-1213
View File
File diff suppressed because it is too large Load Diff
project/jni/icuuc/include/unicode/compactdecimalformat.h
-333
View File
@@ -1,333 +0,0 @@
/*
********************************************************************************
* Copyright (C) 2012-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File COMPACTDECIMALFORMAT.H
********************************************************************************
*/
#ifndef __COMPACT_DECIMAL_FORMAT_H__
#define __COMPACT_DECIMAL_FORMAT_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Formats decimal numbers in compact form.
*/
#if !UCONFIG_NO_FORMATTING
#ifndef U_HIDE_DRAFT_API
#include "unicode/decimfmt.h"
struct UHashtable;
U_NAMESPACE_BEGIN
class PluralRules;
/**
* The CompactDecimalFormat produces abbreviated numbers, suitable for display in
* environments will limited real estate. For example, 'Hits: 1.2B' instead of
* 'Hits: 1,200,000,000'. The format will be appropriate for the given language,
* such as "1,2 Mrd." for German.
* <p>
* For numbers under 1000 trillion (under 10^15, such as 123,456,789,012,345),
* the result will be short for supported languages. However, the result may
* sometimes exceed 7 characters, such as when there are combining marks or thin
* characters. In such cases, the visual width in fonts should still be short.
* <p>
* By default, there are 3 significant digits. After creation, if more than
* three significant digits are set (with setMaximumSignificantDigits), or if a
* fixed number of digits are set (with setMaximumIntegerDigits or
* setMaximumFractionDigits), then result may be wider.
* <p>
* At this time, parsing is not supported, and will produce a U_UNSUPPORTED_ERROR.
* Resetting the pattern prefixes or suffixes is not supported; the method calls
* are ignored.
* <p>
* @draft ICU 51
*/
class U_I18N_API CompactDecimalFormat : public DecimalFormat {
public:
/**
* Returns a compact decimal instance for specified locale.
* @param inLocale the given locale.
* @param style whether to use short or long style.
* @param status error code returned here.
* @draft ICU 51
*/
static CompactDecimalFormat* U_EXPORT2 createInstance(
const Locale& inLocale, UNumberCompactStyle style, UErrorCode& status);
/**
* Copy constructor.
*
* @param source the DecimalFormat object to be copied from.
* @draft ICU 51
*/
CompactDecimalFormat(const CompactDecimalFormat& source);
/**
* Destructor.
* @draft ICU 51
*/
virtual ~CompactDecimalFormat();
/**
* Assignment operator.
*
* @param rhs the DecimalFormat object to be copied.
* @draft ICU 51
*/
CompactDecimalFormat& operator=(const CompactDecimalFormat& rhs);
/**
* Clone this Format object polymorphically. The caller owns the
* result and should delete it when done.
*
* @return a polymorphic copy of this CompactDecimalFormat.
* @draft ICU 51
*/
virtual Format* clone() const;
/**
* Return TRUE if the given Format objects are semantically equal.
* Objects of different subclasses are considered unequal.
*
* @param other the object to be compared with.
* @return TRUE if the given Format objects are semantically equal.
* @draft ICU 51
*/
virtual UBool operator==(const Format& other) const;
using DecimalFormat::format;
/**
* Format a double or long number using base-10 representation.
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @return Reference to 'appendTo' parameter.
* @draft ICU 51
*/
virtual UnicodeString& format(double number,
UnicodeString& appendTo,
FieldPosition& pos) const;
/**
* Format a double or long number using base-10 representation.
* Currently sets status to U_UNSUPPORTED_ERROR.
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call.
* Can be NULL.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @internal
*/
virtual UnicodeString& format(double number,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Format an int64 number using base-10 representation.
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @return Reference to 'appendTo' parameter.
* @draft ICU 51
*/
virtual UnicodeString& format(int64_t number,
UnicodeString& appendTo,
FieldPosition& pos) const;
/**
* Format an int64 number using base-10 representation.
* Currently sets status to U_UNSUPPORTED_ERROR
*
* @param number The value to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call.
* Can be NULL.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @internal
*/
virtual UnicodeString& format(int64_t number,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Format a decimal number. Currently sets status to U_UNSUPPORTED_ERROR
* The syntax of the unformatted number is a "numeric string"
* as defined in the Decimal Arithmetic Specification, available at
* http://speleotrove.com/decimal
*
* @param number The unformatted number, as a string.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call.
* Can be NULL.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @internal
*/
virtual UnicodeString& format(const StringPiece &number,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Format a decimal number. Currently sets status to U_UNSUPPORTED_ERROR
* The number is a DigitList wrapper onto a floating point decimal number.
* The default implementation in NumberFormat converts the decimal number
* to a double and formats that.
*
* @param number The number, a DigitList format Decimal Floating Point.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @internal
*/
virtual UnicodeString& format(const DigitList &number,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Format a decimal number. Currently sets status to U_UNSUPPORTED_ERROR.
* The number is a DigitList wrapper onto a floating point decimal number.
* The default implementation in NumberFormat converts the decimal number
* to a double and formats that.
*
* @param number The number, a DigitList format Decimal Floating Point.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @internal
*/
virtual UnicodeString& format(const DigitList &number,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* CompactDecimalFormat does not support parsing. This implementation
* does nothing.
* @param text Unused.
* @param result Does not change.
* @param parsePosition Does not change.
* @see Formattable
* @draft ICU 51
*/
virtual void parse(const UnicodeString& text,
Formattable& result,
ParsePosition& parsePosition) const;
/**
* CompactDecimalFormat does not support parsing. This implementation
* sets status to U_UNSUPPORTED_ERROR
*
* @param text Unused.
* @param result Does not change.
* @param status Always set to U_UNSUPPORTED_ERROR.
* @draft ICU 51
*/
virtual void parse(const UnicodeString& text,
Formattable& result,
UErrorCode& status) const;
/* Cannot use #ifndef U_HIDE_INTERNAL_API for the following draft method since it is virtual */
/**
* Parses text from the given string as a currency amount. Unlike
* the parse() method, this method will attempt to parse a generic
* currency name, searching for a match of this object's locale's
* currency display names, or for a 3-letter ISO currency code.
* This method will fail if this format is not a currency format,
* that is, if it does not contain the currency pattern symbol
* (U+00A4) in its prefix or suffix. This implementation always returns
* NULL.
*
* @param text the string to parse
* @param pos input-output position; on input, the position within text
* to match; must have 0 <= pos.getIndex() < text.length();
* on output, the position after the last matched character.
* If the parse fails, the position in unchanged upon output.
* @return if parse succeeds, a pointer to a newly-created CurrencyAmount
* object (owned by the caller) containing information about
* the parsed currency; if parse fails, this is NULL.
* @internal
*/
virtual CurrencyAmount* parseCurrency(const UnicodeString& text,
ParsePosition& pos) const;
/**
* Return the class ID for this class. This is useful only for
* comparing to a return value from getDynamicClassID(). For example:
* <pre>
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . Derived::getStaticClassID()) ...
* </pre>
* @return The class ID for all objects of this class.
* @draft ICU 51
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override.
* This method is to implement a simple version of RTTI, since not all
* C++ compilers support genuine RTTI. Polymorphic operator==() and
* clone() methods call this method.
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @draft ICU 51
*/
virtual UClassID getDynamicClassID() const;
private:
const UHashtable* _unitsByVariant;
const double* _divisors;
PluralRules* _pluralRules;
// Default constructor not implemented.
CompactDecimalFormat(const DecimalFormat &, const UHashtable* unitsByVariant, const double* divisors, PluralRules* pluralRules);
UBool eqHelper(const CompactDecimalFormat& that) const;
};
U_NAMESPACE_END
#endif /* U_HIDE_DRAFT_API */
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // __COMPACT_DECIMAL_FORMAT_H__
//eof
project/jni/icuuc/include/unicode/curramt.h
-130
View File
@@ -1,130 +0,0 @@
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 26, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef __CURRENCYAMOUNT_H__
#define __CURRENCYAMOUNT_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/measure.h"
#include "unicode/currunit.h"
/**
* \file
* \brief C++ API: Currency Amount Object.
*/
U_NAMESPACE_BEGIN
/**
*
* A currency together with a numeric amount, such as 200 USD.
*
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API CurrencyAmount: public Measure {
public:
/**
* Construct an object with the given numeric amount and the given
* ISO currency code.
* @param amount a numeric object; amount.isNumeric() must be TRUE
* @param isoCode the 3-letter ISO 4217 currency code; must not be
* NULL and must have length 3
* @param ec input-output error code. If the amount or the isoCode
* is invalid, then this will be set to a failing value.
* @stable ICU 3.0
*/
CurrencyAmount(const Formattable& amount, const UChar* isoCode,
UErrorCode &ec);
/**
* Construct an object with the given numeric amount and the given
* ISO currency code.
* @param amount the amount of the given currency
* @param isoCode the 3-letter ISO 4217 currency code; must not be
* NULL and must have length 3
* @param ec input-output error code. If the isoCode is invalid,
* then this will be set to a failing value.
* @stable ICU 3.0
*/
CurrencyAmount(double amount, const UChar* isoCode,
UErrorCode &ec);
/**
* Copy constructor
* @stable ICU 3.0
*/
CurrencyAmount(const CurrencyAmount& other);
/**
* Assignment operator
* @stable ICU 3.0
*/
CurrencyAmount& operator=(const CurrencyAmount& other);
/**
* Return a polymorphic clone of this object. The result will
* have the same class as returned by getDynamicClassID().
* @stable ICU 3.0
*/
virtual UObject* clone() const;
/**
* Destructor
* @stable ICU 3.0
*/
virtual ~CurrencyAmount();
/**
* Returns a unique class ID for this object POLYMORPHICALLY.
* This method implements a simple form of RTTI used by ICU.
* @return The class ID for this object. All objects of a given
* class have the same class ID. Objects of other classes have
* different class IDs.
* @stable ICU 3.0
*/
virtual UClassID getDynamicClassID() const;
/**
* Returns the class ID for this class. This is used to compare to
* the return value of getDynamicClassID().
* @return The class ID for all objects of this class.
* @stable ICU 3.0
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* Return the currency unit object of this object.
* @stable ICU 3.0
*/
inline const CurrencyUnit& getCurrency() const;
/**
* Return the ISO currency code of this object.
* @stable ICU 3.0
*/
inline const UChar* getISOCurrency() const;
};
inline const CurrencyUnit& CurrencyAmount::getCurrency() const {
return (const CurrencyUnit&) getUnit();
}
inline const UChar* CurrencyAmount::getISOCurrency() const {
return getCurrency().getISOCurrency();
}
U_NAMESPACE_END
#endif // !UCONFIG_NO_FORMATTING
#endif // __CURRENCYAMOUNT_H__
project/jni/icuuc/include/unicode/currpinf.h
-258
View File
@@ -1,258 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2009-2011, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
#ifndef CURRPINF_H
#define CURRPINF_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Currency Plural Information used by Decimal Format
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/unistr.h"
U_NAMESPACE_BEGIN
class Locale;
class PluralRules;
class Hashtable;
/**
* This class represents the information needed by
* DecimalFormat to format currency plural,
* such as "3.00 US dollars" or "1.00 US dollar".
* DecimalFormat creates for itself an instance of
* CurrencyPluralInfo from its locale data.
* If you need to change any of these symbols, you can get the
* CurrencyPluralInfo object from your
* DecimalFormat and modify it.
*
* Following are the information needed for currency plural format and parse:
* locale information,
* plural rule of the locale,
* currency plural pattern of the locale.
*
* @stable ICU 4.2
*/
class U_I18N_API CurrencyPluralInfo : public UObject {
public:
/**
* Create a CurrencyPluralInfo object for the default locale.
* @param status output param set to success/failure code on exit
* @stable ICU 4.2
*/
CurrencyPluralInfo(UErrorCode& status);
/**
* Create a CurrencyPluralInfo object for the given locale.
* @param locale the locale
* @param status output param set to success/failure code on exit
* @stable ICU 4.2
*/
CurrencyPluralInfo(const Locale& locale, UErrorCode& status);
/**
* Copy constructor
*
* @stable ICU 4.2
*/
CurrencyPluralInfo(const CurrencyPluralInfo& info);
/**
* Assignment operator
*
* @stable ICU 4.2
*/
CurrencyPluralInfo& operator=(const CurrencyPluralInfo& info);
/**
* Destructor
*
* @stable ICU 4.2
*/
virtual ~CurrencyPluralInfo();
/**
* Equal operator.
*
* @stable ICU 4.2
*/
UBool operator==(const CurrencyPluralInfo& info) const;
/**
* Not equal operator
*
* @stable ICU 4.2
*/
UBool operator!=(const CurrencyPluralInfo& info) const;
/**
* Clone
*
* @stable ICU 4.2
*/
CurrencyPluralInfo* clone() const;
/**
* Gets plural rules of this locale, used for currency plural format
*
* @return plural rule
* @stable ICU 4.2
*/
const PluralRules* getPluralRules() const;
/**
* Given a plural count, gets currency plural pattern of this locale,
* used for currency plural format
*
* @param pluralCount currency plural count
* @param result output param to receive the pattern
* @return a currency plural pattern based on plural count
* @stable ICU 4.2
*/
UnicodeString& getCurrencyPluralPattern(const UnicodeString& pluralCount,
UnicodeString& result) const;
/**
* Get locale
*
* @return locale
* @stable ICU 4.2
*/
const Locale& getLocale() const;
/**
* Set plural rules.
* The plural rule is set when CurrencyPluralInfo
* instance is created.
* You can call this method to reset plural rules only if you want
* to modify the default plural rule of the locale.
*
* @param ruleDescription new plural rule description
* @param status output param set to success/failure code on exit
* @stable ICU 4.2
*/
void setPluralRules(const UnicodeString& ruleDescription,
UErrorCode& status);
/**
* Set currency plural pattern.
* The currency plural pattern is set when CurrencyPluralInfo
* instance is created.
* You can call this method to reset currency plural pattern only if
* you want to modify the default currency plural pattern of the locale.
*
* @param pluralCount the plural count for which the currency pattern will
* be overridden.
* @param pattern the new currency plural pattern
* @param status output param set to success/failure code on exit
* @stable ICU 4.2
*/
void setCurrencyPluralPattern(const UnicodeString& pluralCount,
const UnicodeString& pattern,
UErrorCode& status);
/**
* Set locale
*
* @param loc the new locale to set
* @param status output param set to success/failure code on exit
* @stable ICU 4.2
*/
void setLocale(const Locale& loc, UErrorCode& status);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 4.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 4.2
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
friend class DecimalFormat;
void initialize(const Locale& loc, UErrorCode& status);
void setupCurrencyPluralPattern(const Locale& loc, UErrorCode& status);
/*
* delete hash table
*
* @param hTable hash table to be deleted
*/
void deleteHash(Hashtable* hTable);
/*
* initialize hash table
*
* @param status output param set to success/failure code on exit
* @return hash table initialized
*/
Hashtable* initHash(UErrorCode& status);
/**
* copy hash table
*
* @param source the source to copy from
* @param target the target to copy to
* @param status error code
*/
void copyHash(const Hashtable* source, Hashtable* target, UErrorCode& status);
//-------------------- private data member ---------------------
// map from plural count to currency plural pattern, for example
// a plural pattern defined in "CurrencyUnitPatterns" is
// "one{{0} {1}}", in which "one" is a plural count
// and "{0} {1}" is a currency plural pattern".
// The currency plural pattern saved in this mapping is the pattern
// defined in "CurrencyUnitPattern" by replacing
// {0} with the number format pattern,
// and {1} with 3 currency sign.
Hashtable* fPluralCountToCurrencyUnitPattern;
/*
* The plural rule is used to format currency plural name,
* for example: "3.00 US Dollars".
* If there are 3 currency signs in the currency patttern,
* the 3 currency signs will be replaced by currency plural name.
*/
PluralRules* fPluralRules;
// locale
Locale* fLocale;
};
inline UBool
CurrencyPluralInfo::operator!=(const CurrencyPluralInfo& info) const { return !operator==(info); }
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _CURRPINFO
//eof
project/jni/icuuc/include/unicode/currunit.h
-117
View File
@@ -1,117 +0,0 @@
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 26, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef __CURRENCYUNIT_H__
#define __CURRENCYUNIT_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/measunit.h"
/**
* \file
* \brief C++ API: Currency Unit Information.
*/
U_NAMESPACE_BEGIN
/**
* A unit of currency, such as USD (U.S. dollars) or JPY (Japanese
* yen). This class is a thin wrapper over a UChar string that
* subclasses MeasureUnit, for use with Measure and MeasureFormat.
*
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API CurrencyUnit: public MeasureUnit {
public:
/**
* Construct an object with the given ISO currency code.
* @param isoCode the 3-letter ISO 4217 currency code; must not be
* NULL and must have length 3
* @param ec input-output error code. If the isoCode is invalid,
* then this will be set to a failing value.
* @stable ICU 3.0
*/
CurrencyUnit(const UChar* isoCode, UErrorCode &ec);
/**
* Copy constructor
* @stable ICU 3.0
*/
CurrencyUnit(const CurrencyUnit& other);
/**
* Assignment operator
* @stable ICU 3.0
*/
CurrencyUnit& operator=(const CurrencyUnit& other);
/**
* Return a polymorphic clone of this object. The result will
* have the same class as returned by getDynamicClassID().
* @stable ICU 3.0
*/
virtual UObject* clone() const;
/**
* Destructor
* @stable ICU 3.0
*/
virtual ~CurrencyUnit();
/**
* Equality operator. Return true if this object is equal
* to the given object.
* @stable ICU 3.0
*/
UBool operator==(const UObject& other) const;
/**
* Returns a unique class ID for this object POLYMORPHICALLY.
* This method implements a simple form of RTTI used by ICU.
* @return The class ID for this object. All objects of a given
* class have the same class ID. Objects of other classes have
* different class IDs.
* @stable ICU 3.0
*/
virtual UClassID getDynamicClassID() const;
/**
* Returns the class ID for this class. This is used to compare to
* the return value of getDynamicClassID().
* @return The class ID for all objects of this class.
* @stable ICU 3.0
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* Return the ISO currency code of this object.
* @stable ICU 3.0
*/
inline const UChar* getISOCurrency() const;
private:
/**
* The ISO 4217 code of this object.
*/
UChar isoCode[4];
};
inline const UChar* CurrencyUnit::getISOCurrency() const {
return isoCode;
}
U_NAMESPACE_END
#endif // !UCONFIG_NO_FORMATTING
#endif // __CURRENCYUNIT_H__
project/jni/icuuc/include/unicode/datefmt.h
-820
View File
@@ -1,820 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File DATEFMT.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 04/01/97 aliu Added support for centuries.
* 07/23/98 stephen JDK 1.2 sync
* 11/15/99 weiv Added support for week of year/day of week formatting
********************************************************************************
*/
#ifndef DATEFMT_H
#define DATEFMT_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/udat.h"
#include "unicode/calendar.h"
#include "unicode/numfmt.h"
#include "unicode/format.h"
#include "unicode/locid.h"
#include "unicode/enumset.h"
/**
* \file
* \brief C++ API: Abstract class for converting dates.
*/
U_NAMESPACE_BEGIN
class TimeZone;
class DateTimePatternGenerator;
// explicit template instantiation. see digitlst.h
#if defined (_MSC_VER)
template class U_I18N_API EnumSet<UDateFormatBooleanAttribute,
0,
UDAT_BOOLEAN_ATTRIBUTE_COUNT>;
#endif
/**
* DateFormat is an abstract class for a family of classes that convert dates and
* times from their internal representations to textual form and back again in a
* language-independent manner. Converting from the internal representation (milliseconds
* since midnight, January 1, 1970) to text is known as "formatting," and converting
* from text to millis is known as "parsing." We currently define only one concrete
* subclass of DateFormat: SimpleDateFormat, which can handle pretty much all normal
* date formatting and parsing actions.
* <P>
* DateFormat helps you to format and parse dates for any locale. Your code can
* be completely independent of the locale conventions for months, days of the
* week, or even the calendar format: lunar vs. solar.
* <P>
* To format a date for the current Locale, use one of the static factory
* methods:
* <pre>
* \code
* DateFormat* dfmt = DateFormat::createDateInstance();
* UDate myDate = Calendar::getNow();
* UnicodeString myString;
* myString = dfmt->format( myDate, myString );
* \endcode
* </pre>
* If you are formatting multiple numbers, it is more efficient to get the
* format and use it multiple times so that the system doesn't have to fetch the
* information about the local language and country conventions multiple times.
* <pre>
* \code
* DateFormat* df = DateFormat::createDateInstance();
* UnicodeString myString;
* UDate myDateArr[] = { 0.0, 100000000.0, 2000000000.0 }; // test values
* for (int32_t i = 0; i < 3; ++i) {
* myString.remove();
* cout << df->format( myDateArr[i], myString ) << endl;
* }
* \endcode
* </pre>
* To get specific fields of a date, you can use UFieldPosition to
* get specific fields.
* <pre>
* \code
* DateFormat* dfmt = DateFormat::createDateInstance();
* FieldPosition pos(DateFormat::YEAR_FIELD);
* UnicodeString myString;
* myString = dfmt->format( myDate, myString );
* cout << myString << endl;
* cout << pos.getBeginIndex() << "," << pos. getEndIndex() << endl;
* \endcode
* </pre>
* To format a date for a different Locale, specify it in the call to
* createDateInstance().
* <pre>
* \code
* DateFormat* df =
* DateFormat::createDateInstance( DateFormat::SHORT, Locale::getFrance());
* \endcode
* </pre>
* You can use a DateFormat to parse also.
* <pre>
* \code
* UErrorCode status = U_ZERO_ERROR;
* UDate myDate = df->parse(myString, status);
* \endcode
* </pre>
* Use createDateInstance() to produce the normal date format for that country.
* There are other static factory methods available. Use createTimeInstance()
* to produce the normal time format for that country. Use createDateTimeInstance()
* to produce a DateFormat that formats both date and time. You can pass in
* different options to these factory methods to control the length of the
* result; from SHORT to MEDIUM to LONG to FULL. The exact result depends on the
* locale, but generally:
* <ul type=round>
* <li> SHORT is completely numeric, such as 12/13/52 or 3:30pm
* <li> MEDIUM is longer, such as Jan 12, 1952
* <li> LONG is longer, such as January 12, 1952 or 3:30:32pm
* <li> FULL is pretty completely specified, such as
* Tuesday, April 12, 1952 AD or 3:30:42pm PST.
* </ul>
* You can also set the time zone on the format if you wish. If you want even
* more control over the format or parsing, (or want to give your users more
* control), you can try casting the DateFormat you get from the factory methods
* to a SimpleDateFormat. This will work for the majority of countries; just
* remember to chck getDynamicClassID() before carrying out the cast.
* <P>
* You can also use forms of the parse and format methods with ParsePosition and
* FieldPosition to allow you to
* <ul type=round>
* <li> Progressively parse through pieces of a string.
* <li> Align any particular field, or find out where it is for selection
* on the screen.
* </ul>
*
* <p><em>User subclasses are not supported.</em> While clients may write
* subclasses, such code will not necessarily work and will not be
* guaranteed to work stably from release to release.
*/
class U_I18N_API DateFormat : public Format {
public:
/**
* Constants for various style patterns. These reflect the order of items in
* the DateTimePatterns resource. There are 4 time patterns, 4 date patterns,
* the default date-time pattern, and 4 date-time patterns. Each block of 4 values
* in the resource occurs in the order full, long, medium, short.
* @stable ICU 2.4
*/
enum EStyle
{
kNone = -1,
kFull = 0,
kLong = 1,
kMedium = 2,
kShort = 3,
kDateOffset = kShort + 1,
// kFull + kDateOffset = 4
// kLong + kDateOffset = 5
// kMedium + kDateOffset = 6
// kShort + kDateOffset = 7
kDateTime = 8,
// Default DateTime
kDateTimeOffset = kDateTime + 1,
// kFull + kDateTimeOffset = 9
// kLong + kDateTimeOffset = 10
// kMedium + kDateTimeOffset = 11
// kShort + kDateTimeOffset = 12
// relative dates
kRelative = (1 << 7),
kFullRelative = (kFull | kRelative),
kLongRelative = kLong | kRelative,
kMediumRelative = kMedium | kRelative,
kShortRelative = kShort | kRelative,
kDefault = kMedium,
/**
* These constants are provided for backwards compatibility only.
* Please use the C++ style constants defined above.
*/
FULL = kFull,
LONG = kLong,
MEDIUM = kMedium,
SHORT = kShort,
DEFAULT = kDefault,
DATE_OFFSET = kDateOffset,
NONE = kNone,
DATE_TIME = kDateTime
};
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~DateFormat();
/**
* Equality operator. Returns true if the two formats have the same behavior.
* @stable ICU 2.0
*/
virtual UBool operator==(const Format&) const;
using Format::format;
/**
* Format an object to produce a string. This method handles Formattable
* objects with a UDate type. If a the Formattable object type is not a Date,
* then it returns a failing UErrorCode.
*
* @param obj The object to format. Must be a Date.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 2.0
*/
virtual UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Format an object to produce a string. This method handles Formattable
* objects with a UDate type. If a the Formattable object type is not a Date,
* then it returns a failing UErrorCode.
*
* @param obj The object to format. Must be a Date.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call. Field values
* are defined in UDateFormatField. Can be NULL.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.4
*/
virtual UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Formats a date into a date/time string. This is an abstract method which
* concrete subclasses must implement.
* <P>
* On input, the FieldPosition parameter may have its "field" member filled with
* an enum value specifying a field. On output, the FieldPosition will be filled
* in with the text offsets for that field.
* <P> For example, given a time text
* "1996.07.10 AD at 15:08:56 PDT", if the given fieldPosition.field is
* UDAT_YEAR_FIELD, the offsets fieldPosition.beginIndex and
* statfieldPositionus.getEndIndex will be set to 0 and 4, respectively.
* <P> Notice
* that if the same time field appears more than once in a pattern, the status will
* be set for the first occurence of that time field. For instance,
* formatting a UDate to the time string "1 PM PDT (Pacific Daylight Time)"
* using the pattern "h a z (zzzz)" and the alignment field
* DateFormat::TIMEZONE_FIELD, the offsets fieldPosition.beginIndex and
* fieldPosition.getEndIndex will be set to 5 and 8, respectively, for the first
* occurence of the timezone pattern character 'z'.
*
* @param cal Calendar set to the date and time to be formatted
* into a date/time string. When the calendar type is
* different from the internal calendar held by this
* DateFormat instance, the date and the time zone will
* be inherited from the input calendar, but other calendar
* field values will be calculated by the internal calendar.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param fieldPosition On input: an alignment field, if desired (see examples above)
* On output: the offsets of the alignment field (see examples above)
* @return Reference to 'appendTo' parameter.
* @stable ICU 2.1
*/
virtual UnicodeString& format( Calendar& cal,
UnicodeString& appendTo,
FieldPosition& fieldPosition) const = 0;
/**
* Formats a date into a date/time string. Subclasses should implement this method.
*
* @param cal Calendar set to the date and time to be formatted
* into a date/time string. When the calendar type is
* different from the internal calendar held by this
* DateFormat instance, the date and the time zone will
* be inherited from the input calendar, but other calendar
* field values will be calculated by the internal calendar.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call. Field values
* are defined in UDateFormatField. Can be NULL.
* @param status error status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.4
*/
virtual UnicodeString& format(Calendar& cal,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Formats a UDate into a date/time string.
* <P>
* On input, the FieldPosition parameter may have its "field" member filled with
* an enum value specifying a field. On output, the FieldPosition will be filled
* in with the text offsets for that field.
* <P> For example, given a time text
* "1996.07.10 AD at 15:08:56 PDT", if the given fieldPosition.field is
* UDAT_YEAR_FIELD, the offsets fieldPosition.beginIndex and
* statfieldPositionus.getEndIndex will be set to 0 and 4, respectively.
* <P> Notice
* that if the same time field appears more than once in a pattern, the status will
* be set for the first occurence of that time field. For instance,
* formatting a UDate to the time string "1 PM PDT (Pacific Daylight Time)"
* using the pattern "h a z (zzzz)" and the alignment field
* DateFormat::TIMEZONE_FIELD, the offsets fieldPosition.beginIndex and
* fieldPosition.getEndIndex will be set to 5 and 8, respectively, for the first
* occurence of the timezone pattern character 'z'.
*
* @param date UDate to be formatted into a date/time string.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param fieldPosition On input: an alignment field, if desired (see examples above)
* On output: the offsets of the alignment field (see examples above)
* @return Reference to 'appendTo' parameter.
* @stable ICU 2.0
*/
UnicodeString& format( UDate date,
UnicodeString& appendTo,
FieldPosition& fieldPosition) const;
/**
* Formats a UDate into a date/time string.
*
* @param date UDate to be formatted into a date/time string.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call. Field values
* are defined in UDateFormatField. Can be NULL.
* @param status error status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.4
*/
UnicodeString& format(UDate date,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Formats a UDate into a date/time string. If there is a problem, you won't
* know, using this method. Use the overloaded format() method which takes a
* FieldPosition& to detect formatting problems.
*
* @param date The UDate value to be formatted into a string.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @return Reference to 'appendTo' parameter.
* @stable ICU 2.0
*/
UnicodeString& format(UDate date, UnicodeString& appendTo) const;
/**
* Parse a date/time string. For example, a time text "07/10/96 4:5 PM, PDT"
* will be parsed into a UDate that is equivalent to Date(837039928046).
* Parsing begins at the beginning of the string and proceeds as far as
* possible. Assuming no parse errors were encountered, this function
* doesn't return any information about how much of the string was consumed
* by the parsing. If you need that information, use the version of
* parse() that takes a ParsePosition.
* <P>
* By default, parsing is lenient: If the input is not in the form used by
* this object's format method but can still be parsed as a date, then the
* parse succeeds. Clients may insist on strict adherence to the format by
* calling setLenient(false).
* @see DateFormat::setLenient(boolean)
* <P>
* Note that the normal date formats associated with some calendars - such
* as the Chinese lunar calendar - do not specify enough fields to enable
* dates to be parsed unambiguously. In the case of the Chinese lunar
* calendar, while the year within the current 60-year cycle is specified,
* the number of such cycles since the start date of the calendar (in the
* ERA field of the Calendar object) is not normally part of the format,
* and parsing may assume the wrong era. For cases such as this it is
* recommended that clients parse using the method
* parse(const UnicodeString&, Calendar& cal, ParsePosition&)
* with the Calendar passed in set to the current date, or to a date
* within the era/cycle that should be assumed if absent in the format.
*
* @param text The date/time string to be parsed into a UDate value.
* @param status Output param to be set to success/failure code. If
* 'text' cannot be parsed, it will be set to a failure
* code.
* @return The parsed UDate value, if successful.
* @stable ICU 2.0
*/
virtual UDate parse( const UnicodeString& text,
UErrorCode& status) const;
/**
* Parse a date/time string beginning at the given parse position. For
* example, a time text "07/10/96 4:5 PM, PDT" will be parsed into a Date
* that is equivalent to Date(837039928046).
* <P>
* By default, parsing is lenient: If the input is not in the form used by
* this object's format method but can still be parsed as a date, then the
* parse succeeds. Clients may insist on strict adherence to the format by
* calling setLenient(false).
* @see DateFormat::setLenient(boolean)
*
* @param text The date/time string to be parsed.
* @param cal A Calendar set on input to the date and time to be used for
* missing values in the date/time string being parsed, and set
* on output to the parsed date/time. When the calendar type is
* different from the internal calendar held by this DateFormat
* instance, the internal calendar will be cloned to a work
* calendar set to the same milliseconds and time zone as the
* cal parameter, field values will be parsed based on the work
* calendar, then the result (milliseconds and time zone) will
* be set in this calendar.
* @param pos On input, the position at which to start parsing; on
* output, the position at which parsing terminated, or the
* start position if the parse failed.
* @stable ICU 2.1
*/
virtual void parse( const UnicodeString& text,
Calendar& cal,
ParsePosition& pos) const = 0;
/**
* Parse a date/time string beginning at the given parse position. For
* example, a time text "07/10/96 4:5 PM, PDT" will be parsed into a Date
* that is equivalent to Date(837039928046).
* <P>
* By default, parsing is lenient: If the input is not in the form used by
* this object's format method but can still be parsed as a date, then the
* parse succeeds. Clients may insist on strict adherence to the format by
* calling setLenient(false).
* @see DateFormat::setLenient(boolean)
* <P>
* Note that the normal date formats associated with some calendars - such
* as the Chinese lunar calendar - do not specify enough fields to enable
* dates to be parsed unambiguously. In the case of the Chinese lunar
* calendar, while the year within the current 60-year cycle is specified,
* the number of such cycles since the start date of the calendar (in the
* ERA field of the Calendar object) is not normally part of the format,
* and parsing may assume the wrong era. For cases such as this it is
* recommended that clients parse using the method
* parse(const UnicodeString&, Calendar& cal, ParsePosition&)
* with the Calendar passed in set to the current date, or to a date
* within the era/cycle that should be assumed if absent in the format.
*
* @param text The date/time string to be parsed into a UDate value.
* @param pos On input, the position at which to start parsing; on
* output, the position at which parsing terminated, or the
* start position if the parse failed.
* @return A valid UDate if the input could be parsed.
* @stable ICU 2.0
*/
UDate parse( const UnicodeString& text,
ParsePosition& pos) const;
/**
* Parse a string to produce an object. This methods handles parsing of
* date/time strings into Formattable objects with UDate types.
* <P>
* Before calling, set parse_pos.index to the offset you want to start
* parsing at in the source. After calling, parse_pos.index is the end of
* the text you parsed. If error occurs, index is unchanged.
* <P>
* When parsing, leading whitespace is discarded (with a successful parse),
* while trailing whitespace is left as is.
* <P>
* See Format::parseObject() for more.
*
* @param source The string to be parsed into an object.
* @param result Formattable to be set to the parse result.
* If parse fails, return contents are undefined.
* @param parse_pos The position to start parsing at. Upon return
* this param is set to the position after the
* last character successfully parsed. If the
* source is not parsed successfully, this param
* will remain unchanged.
* @stable ICU 2.0
*/
virtual void parseObject(const UnicodeString& source,
Formattable& result,
ParsePosition& parse_pos) const;
/**
* Create a default date/time formatter that uses the SHORT style for both
* the date and the time.
*
* @return A date/time formatter which the caller owns.
* @stable ICU 2.0
*/
static DateFormat* U_EXPORT2 createInstance(void);
/**
* Creates a time formatter with the given formatting style for the given
* locale.
*
* @param style The given formatting style. For example,
* SHORT for "h:mm a" in the US locale. Relative
* time styles are not currently supported.
* @param aLocale The given locale.
* @return A time formatter which the caller owns.
* @stable ICU 2.0
*/
static DateFormat* U_EXPORT2 createTimeInstance(EStyle style = kDefault,
const Locale& aLocale = Locale::getDefault());
/**
* Creates a date formatter with the given formatting style for the given
* const locale.
*
* @param style The given formatting style. For example, SHORT for "M/d/yy" in the
* US locale. As currently implemented, relative date formatting only
* affects a limited range of calendar days before or after the
* current date, based on the CLDR &lt;field type="day"&gt;/&lt;relative&gt; data:
* For example, in English, "Yesterday", "Today", and "Tomorrow".
* Outside of this range, dates are formatted using the corresponding
* non-relative style.
* @param aLocale The given locale.
* @return A date formatter which the caller owns.
* @stable ICU 2.0
*/
static DateFormat* U_EXPORT2 createDateInstance(EStyle style = kDefault,
const Locale& aLocale = Locale::getDefault());
/**
* Creates a date/time formatter with the given formatting styles for the
* given locale.
*
* @param dateStyle The given formatting style for the date portion of the result.
* For example, SHORT for "M/d/yy" in the US locale. As currently
* implemented, relative date formatting only affects a limited range
* of calendar days before or after the current date, based on the
* CLDR &lt;field type="day"&gt;/&lt;relative&gt; data: For example, in English,
* "Yesterday", "Today", and "Tomorrow". Outside of this range, dates
* are formatted using the corresponding non-relative style.
* @param timeStyle The given formatting style for the time portion of the result.
* For example, SHORT for "h:mm a" in the US locale. Relative
* time styles are not currently supported.
* @param aLocale The given locale.
* @return A date/time formatter which the caller owns.
* @stable ICU 2.0
*/
static DateFormat* U_EXPORT2 createDateTimeInstance(EStyle dateStyle = kDefault,
EStyle timeStyle = kDefault,
const Locale& aLocale = Locale::getDefault());
/**
* Gets the set of locales for which DateFormats are installed.
* @param count Filled in with the number of locales in the list that is returned.
* @return the set of locales for which DateFormats are installed. The caller
* does NOT own this list and must not delete it.
* @stable ICU 2.0
*/
static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count);
/**
* Returns true if the encapsulated Calendar object is set for lenient parsing.
* @stable ICU 2.0
*/
virtual UBool isLenient(void) const;
/**
* Specify whether or not date/time parsing is to be lenient. With lenient
* parsing, the parser may use heuristics to interpret inputs that do not
* precisely match this object's format. With strict parsing, inputs must
* match this object's format.
*
* Note: This method is specific to the encapsulated Calendar object. DateFormat
* leniency aspects are controlled by setBooleanAttribute.
*
* @param lenient True specifies date/time interpretation to be lenient.
* @see Calendar::setLenient
* @stable ICU 2.0
*/
virtual void setLenient(UBool lenient);
/**
* Gets the calendar associated with this date/time formatter.
* @return the calendar associated with this date/time formatter.
* @stable ICU 2.0
*/
virtual const Calendar* getCalendar(void) const;
/**
* Set the calendar to be used by this date format. Initially, the default
* calendar for the specified or default locale is used. The caller should
* not delete the Calendar object after it is adopted by this call.
* Adopting a new calendar will change to the default symbols.
*
* @param calendarToAdopt Calendar object to be adopted.
* @stable ICU 2.0
*/
virtual void adoptCalendar(Calendar* calendarToAdopt);
/**
* Set the calendar to be used by this date format. Initially, the default
* calendar for the specified or default locale is used.
*
* @param newCalendar Calendar object to be set.
* @stable ICU 2.0
*/
virtual void setCalendar(const Calendar& newCalendar);
/**
* Gets the number formatter which this date/time formatter uses to format
* and parse the numeric portions of the pattern.
* @return the number formatter which this date/time formatter uses.
* @stable ICU 2.0
*/
virtual const NumberFormat* getNumberFormat(void) const;
/**
* Allows you to set the number formatter. The caller should
* not delete the NumberFormat object after it is adopted by this call.
* @param formatToAdopt NumberFormat object to be adopted.
* @stable ICU 2.0
*/
virtual void adoptNumberFormat(NumberFormat* formatToAdopt);
/**
* Allows you to set the number formatter.
* @param newNumberFormat NumberFormat object to be set.
* @stable ICU 2.0
*/
virtual void setNumberFormat(const NumberFormat& newNumberFormat);
/**
* Returns a reference to the TimeZone used by this DateFormat's calendar.
* @return the time zone associated with the calendar of DateFormat.
* @stable ICU 2.0
*/
virtual const TimeZone& getTimeZone(void) const;
/**
* Sets the time zone for the calendar of this DateFormat object. The caller
* no longer owns the TimeZone object and should not delete it after this call.
* @param zoneToAdopt the TimeZone to be adopted.
* @stable ICU 2.0
*/
virtual void adoptTimeZone(TimeZone* zoneToAdopt);
/**
* Sets the time zone for the calendar of this DateFormat object.
* @param zone the new time zone.
* @stable ICU 2.0
*/
virtual void setTimeZone(const TimeZone& zone);
/**
* Set an boolean attribute on this DateFormat.
* May return U_UNSUPPORTED_ERROR if this instance does not support
* the specified attribute.
* @param attr the attribute to set
* @param newvalue new value
* @param status the error type
* @return *this - for chaining (example: format.setAttribute(...).setAttribute(...) )
* @internal ICU technology preview
*/
virtual DateFormat& U_EXPORT2 setBooleanAttribute(UDateFormatBooleanAttribute attr,
UBool newvalue,
UErrorCode &status);
/**
* Get an boolean from this DateFormat
* May return U_UNSUPPORTED_ERROR if this instance does not support
* the specified attribute.
* @param attr the attribute to set
* @param status the error type
* @return the attribute value. Undefined if there is an error.
* @internal ICU technology preview
*/
virtual UBool U_EXPORT2 getBooleanAttribute(UDateFormatBooleanAttribute attr, UErrorCode &status) const;
protected:
/**
* Default constructor. Creates a DateFormat with no Calendar or NumberFormat
* associated with it. This constructor depends on the subclasses to fill in
* the calendar and numberFormat fields.
* @stable ICU 2.0
*/
DateFormat();
/**
* Copy constructor.
* @stable ICU 2.0
*/
DateFormat(const DateFormat&);
/**
* Default assignment operator.
* @stable ICU 2.0
*/
DateFormat& operator=(const DateFormat&);
/**
* The calendar that DateFormat uses to produce the time field values needed
* to implement date/time formatting. Subclasses should generally initialize
* this to the default calendar for the locale associated with this DateFormat.
* @stable ICU 2.4
*/
Calendar* fCalendar;
/**
* The number formatter that DateFormat uses to format numbers in dates and
* times. Subclasses should generally initialize this to the default number
* format for the locale associated with this DateFormat.
* @stable ICU 2.4
*/
NumberFormat* fNumberFormat;
private:
/**
* Gets the date/time formatter with the given formatting styles for the
* given locale.
* @param dateStyle the given date formatting style.
* @param timeStyle the given time formatting style.
* @param inLocale the given locale.
* @return a date/time formatter, or 0 on failure.
*/
static DateFormat* U_EXPORT2 create(EStyle timeStyle, EStyle dateStyle, const Locale& inLocale);
/**
* enum set of active boolean attributes for this instance
*/
EnumSet<UDateFormatBooleanAttribute, 0, UDAT_BOOLEAN_ATTRIBUTE_COUNT> fBoolFlags;
public:
#ifndef U_HIDE_OBSOLETE_API
/**
* Field selector for FieldPosition for DateFormat fields.
* @obsolete ICU 3.4 use UDateFormatField instead, since this API will be
* removed in that release
*/
enum EField
{
// Obsolete; use UDateFormatField instead
kEraField = UDAT_ERA_FIELD,
kYearField = UDAT_YEAR_FIELD,
kMonthField = UDAT_MONTH_FIELD,
kDateField = UDAT_DATE_FIELD,
kHourOfDay1Field = UDAT_HOUR_OF_DAY1_FIELD,
kHourOfDay0Field = UDAT_HOUR_OF_DAY0_FIELD,
kMinuteField = UDAT_MINUTE_FIELD,
kSecondField = UDAT_SECOND_FIELD,
kMillisecondField = UDAT_FRACTIONAL_SECOND_FIELD,
kDayOfWeekField = UDAT_DAY_OF_WEEK_FIELD,
kDayOfYearField = UDAT_DAY_OF_YEAR_FIELD,
kDayOfWeekInMonthField = UDAT_DAY_OF_WEEK_IN_MONTH_FIELD,
kWeekOfYearField = UDAT_WEEK_OF_YEAR_FIELD,
kWeekOfMonthField = UDAT_WEEK_OF_MONTH_FIELD,
kAmPmField = UDAT_AM_PM_FIELD,
kHour1Field = UDAT_HOUR1_FIELD,
kHour0Field = UDAT_HOUR0_FIELD,
kTimezoneField = UDAT_TIMEZONE_FIELD,
kYearWOYField = UDAT_YEAR_WOY_FIELD,
kDOWLocalField = UDAT_DOW_LOCAL_FIELD,
kExtendedYearField = UDAT_EXTENDED_YEAR_FIELD,
kJulianDayField = UDAT_JULIAN_DAY_FIELD,
kMillisecondsInDayField = UDAT_MILLISECONDS_IN_DAY_FIELD,
// Obsolete; use UDateFormatField instead
ERA_FIELD = UDAT_ERA_FIELD,
YEAR_FIELD = UDAT_YEAR_FIELD,
MONTH_FIELD = UDAT_MONTH_FIELD,
DATE_FIELD = UDAT_DATE_FIELD,
HOUR_OF_DAY1_FIELD = UDAT_HOUR_OF_DAY1_FIELD,
HOUR_OF_DAY0_FIELD = UDAT_HOUR_OF_DAY0_FIELD,
MINUTE_FIELD = UDAT_MINUTE_FIELD,
SECOND_FIELD = UDAT_SECOND_FIELD,
MILLISECOND_FIELD = UDAT_FRACTIONAL_SECOND_FIELD,
DAY_OF_WEEK_FIELD = UDAT_DAY_OF_WEEK_FIELD,
DAY_OF_YEAR_FIELD = UDAT_DAY_OF_YEAR_FIELD,
DAY_OF_WEEK_IN_MONTH_FIELD = UDAT_DAY_OF_WEEK_IN_MONTH_FIELD,
WEEK_OF_YEAR_FIELD = UDAT_WEEK_OF_YEAR_FIELD,
WEEK_OF_MONTH_FIELD = UDAT_WEEK_OF_MONTH_FIELD,
AM_PM_FIELD = UDAT_AM_PM_FIELD,
HOUR1_FIELD = UDAT_HOUR1_FIELD,
HOUR0_FIELD = UDAT_HOUR0_FIELD,
TIMEZONE_FIELD = UDAT_TIMEZONE_FIELD
};
#endif /* U_HIDE_OBSOLETE_API */
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _DATEFMT
//eof
project/jni/icuuc/include/unicode/dbbi.h
-40
View File
@@ -1,40 +0,0 @@
/*
**********************************************************************
* Copyright (C) 1999-2006,2013 IBM Corp. All rights reserved.
**********************************************************************
* Date Name Description
* 12/1/99 rgillam Complete port from Java.
* 01/13/2000 helena Added UErrorCode to ctors.
**********************************************************************
*/
#ifndef DBBI_H
#define DBBI_H
#include "unicode/rbbi.h"
#if !UCONFIG_NO_BREAK_ITERATION
/**
* \file
* \brief C++ API: Dictionary Based Break Iterator
*/
U_NAMESPACE_BEGIN
#ifndef U_HIDE_DEPRECATED_API
/**
* An obsolete subclass of RuleBasedBreakIterator. Handling of dictionary-
* based break iteration has been folded into the base class. This class
* is deprecated as of ICU 3.6.
* @deprecated ICU 3.6
*/
typedef RuleBasedBreakIterator DictionaryBasedBreakIterator;
#endif /* U_HIDE_DEPRECATED_API */
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_BREAK_ITERATION */
#endif
project/jni/icuuc/include/unicode/dcfmtsym.h
-479
View File
@@ -1,479 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File DCFMTSYM.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 03/18/97 clhuang Updated per C++ implementation.
* 03/27/97 helena Updated to pass the simple test after code review.
* 08/26/97 aliu Added currency/intl currency symbol support.
* 07/22/98 stephen Changed to match C++ style
* currencySymbol -> fCurrencySymbol
* Constants changed from CAPS to kCaps
* 06/24/99 helena Integrated Alan's NF enhancements and Java2 bug fixes
* 09/22/00 grhoten Marked deprecation tags with a pointer to replacement
* functions.
********************************************************************************
*/
#ifndef DCFMTSYM_H
#define DCFMTSYM_H
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/uobject.h"
#include "unicode/locid.h"
#include "unicode/unum.h"
/**
* \file
* \brief C++ API: Symbols for formatting numbers.
*/
U_NAMESPACE_BEGIN
/**
* This class represents the set of symbols needed by DecimalFormat
* to format numbers. DecimalFormat creates for itself an instance of
* DecimalFormatSymbols from its locale data. If you need to change any
* of these symbols, you can get the DecimalFormatSymbols object from
* your DecimalFormat and modify it.
* <P>
* Here are the special characters used in the parts of the
* subpattern, with notes on their usage.
* <pre>
* \code
* Symbol Meaning
* 0 a digit
* # a digit, zero shows as absent
* . placeholder for decimal separator
* , placeholder for grouping separator.
* ; separates formats.
* - default negative prefix.
* % divide by 100 and show as percentage
* X any other characters can be used in the prefix or suffix
* ' used to quote special characters in a prefix or suffix.
* \endcode
* </pre>
* [Notes]
* <P>
* If there is no explicit negative subpattern, - is prefixed to the
* positive form. That is, "0.00" alone is equivalent to "0.00;-0.00".
* <P>
* The grouping separator is commonly used for thousands, but in some
* countries for ten-thousands. The interval is a constant number of
* digits between the grouping characters, such as 100,000,000 or 1,0000,0000.
* If you supply a pattern with multiple grouping characters, the interval
* between the last one and the end of the integer is the one that is
* used. So "#,##,###,####" == "######,####" == "##,####,####".
* <P>
* This class only handles localized digits where the 10 digits are
* contiguous in Unicode, from 0 to 9. Other digits sets (such as
* superscripts) would need a different subclass.
*/
class U_I18N_API DecimalFormatSymbols : public UObject {
public:
/**
* Constants for specifying a number format symbol.
* @stable ICU 2.0
*/
enum ENumberFormatSymbol {
/** The decimal separator */
kDecimalSeparatorSymbol,
/** The grouping separator */
kGroupingSeparatorSymbol,
/** The pattern separator */
kPatternSeparatorSymbol,
/** The percent sign */
kPercentSymbol,
/** Zero*/
kZeroDigitSymbol,
/** Character representing a digit in the pattern */
kDigitSymbol,
/** The minus sign */
kMinusSignSymbol,
/** The plus sign */
kPlusSignSymbol,
/** The currency symbol */
kCurrencySymbol,
/** The international currency symbol */
kIntlCurrencySymbol,
/** The monetary separator */
kMonetarySeparatorSymbol,
/** The exponential symbol */
kExponentialSymbol,
/** Per mill symbol - replaces kPermillSymbol */
kPerMillSymbol,
/** Escape padding character */
kPadEscapeSymbol,
/** Infinity symbol */
kInfinitySymbol,
/** Nan symbol */
kNaNSymbol,
/** Significant digit symbol
* @stable ICU 3.0 */
kSignificantDigitSymbol,
/** The monetary grouping separator
* @stable ICU 3.6
*/
kMonetaryGroupingSeparatorSymbol,
/** One
* @stable ICU 4.6
*/
kOneDigitSymbol,
/** Two
* @stable ICU 4.6
*/
kTwoDigitSymbol,
/** Three
* @stable ICU 4.6
*/
kThreeDigitSymbol,
/** Four
* @stable ICU 4.6
*/
kFourDigitSymbol,
/** Five
* @stable ICU 4.6
*/
kFiveDigitSymbol,
/** Six
* @stable ICU 4.6
*/
kSixDigitSymbol,
/** Seven
* @stable ICU 4.6
*/
kSevenDigitSymbol,
/** Eight
* @stable ICU 4.6
*/
kEightDigitSymbol,
/** Nine
* @stable ICU 4.6
*/
kNineDigitSymbol,
/** count symbol constants */
kFormatSymbolCount
};
/**
* Create a DecimalFormatSymbols object for the given locale.
*
* @param locale The locale to get symbols for.
* @param status Input/output parameter, set to success or
* failure code upon return.
* @stable ICU 2.0
*/
DecimalFormatSymbols(const Locale& locale, UErrorCode& status);
/**
* Create a DecimalFormatSymbols object for the default locale.
* This constructor will not fail. If the resource file data is
* not available, it will use hard-coded last-resort data and
* set status to U_USING_FALLBACK_ERROR.
*
* @param status Input/output parameter, set to success or
* failure code upon return.
* @stable ICU 2.0
*/
DecimalFormatSymbols(UErrorCode& status);
#ifndef U_HIDE_DRAFT_API
/**
* Creates a DecimalFormatSymbols object with last-resort data.
* Intended for callers who cache the symbols data and
* set all symbols on the resulting object.
*
* The last-resort symbols are similar to those for the root data,
* except that the grouping separators are empty,
* the NaN symbol is U+FFFD rather than "NaN",
* and the CurrencySpacing patterns are empty.
*
* @param status Input/output parameter, set to success or
* failure code upon return.
* @return last-resort symbols
* @draft ICU 52
*/
static DecimalFormatSymbols* createWithLastResortData(UErrorCode& status);
#endif /* U_HIDE_DRAFT_API */
/**
* Copy constructor.
* @stable ICU 2.0
*/
DecimalFormatSymbols(const DecimalFormatSymbols&);
/**
* Assignment operator.
* @stable ICU 2.0
*/
DecimalFormatSymbols& operator=(const DecimalFormatSymbols&);
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~DecimalFormatSymbols();
/**
* Return true if another object is semantically equal to this one.
*
* @param other the object to be compared with.
* @return true if another object is semantically equal to this one.
* @stable ICU 2.0
*/
UBool operator==(const DecimalFormatSymbols& other) const;
/**
* Return true if another object is semantically unequal to this one.
*
* @param other the object to be compared with.
* @return true if another object is semantically unequal to this one.
* @stable ICU 2.0
*/
UBool operator!=(const DecimalFormatSymbols& other) const { return !operator==(other); }
/**
* Get one of the format symbols by its enum constant.
* Each symbol is stored as a string so that graphemes
* (characters with modifier letters) can be used.
*
* @param symbol Constant to indicate a number format symbol.
* @return the format symbols by the param 'symbol'
* @stable ICU 2.0
*/
inline UnicodeString getSymbol(ENumberFormatSymbol symbol) const;
/**
* Set one of the format symbols by its enum constant.
* Each symbol is stored as a string so that graphemes
* (characters with modifier letters) can be used.
*
* @param symbol Constant to indicate a number format symbol.
* @param value value of the format symbol
* @param propogateDigits If false, setting the zero digit will not automatically set 1-9.
* The default behavior is to automatically set 1-9 if zero is being set and the value
* it is being set to corresponds to a known Unicode zero digit.
* @stable ICU 2.0
*/
void setSymbol(ENumberFormatSymbol symbol, const UnicodeString &value, const UBool propogateDigits);
/**
* Returns the locale for which this object was constructed.
* @stable ICU 2.6
*/
inline Locale getLocale() const;
/**
* Returns the locale for this object. Two flavors are available:
* valid and actual locale.
* @stable ICU 2.8
*/
Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
/**
* Get pattern string for 'CurrencySpacing' that can be applied to
* currency format.
* This API gets the CurrencySpacing data from ResourceBundle. The pattern can
* be empty if there is no data from current locale and its parent locales.
*
* @param type : UNUM_CURRENCY_MATCH, UNUM_CURRENCY_SURROUNDING_MATCH or UNUM_CURRENCY_INSERT.
* @param beforeCurrency : true if the pattern is for before currency symbol.
* false if the pattern is for after currency symbol.
* @param status: Input/output parameter, set to success or
* failure code upon return.
* @return pattern string for currencyMatch, surroundingMatch or spaceInsert.
* Return empty string if there is no data for this locale and its parent
* locales.
* @stable ICU 4.8
*/
const UnicodeString& getPatternForCurrencySpacing(UCurrencySpacing type,
UBool beforeCurrency,
UErrorCode& status) const;
/**
* Set pattern string for 'CurrencySpacing' that can be applied to
* currency format.
*
* @param type : UNUM_CURRENCY_MATCH, UNUM_CURRENCY_SURROUNDING_MATCH or UNUM_CURRENCY_INSERT.
* @param beforeCurrency : true if the pattern is for before currency symbol.
* false if the pattern is for after currency symbol.
* @param pattern : pattern string to override current setting.
* @stable ICU 4.8
*/
void setPatternForCurrencySpacing(UCurrencySpacing type,
UBool beforeCurrency,
const UnicodeString& pattern);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
DecimalFormatSymbols();
/**
* Initializes the symbols from the LocaleElements resource bundle.
* Note: The organization of LocaleElements badly needs to be
* cleaned up.
*
* @param locale The locale to get symbols for.
* @param success Input/output parameter, set to success or
* failure code upon return.
* @param useLastResortData determine if use last resort data
*/
void initialize(const Locale& locale, UErrorCode& success, UBool useLastResortData = FALSE);
/**
* Initialize the symbols with default values.
*/
void initialize();
void setCurrencyForSymbols();
public:
#ifndef U_HIDE_INTERNAL_API
/**
* _Internal_ function - more efficient version of getSymbol,
* returning a const reference to one of the symbol strings.
* The returned reference becomes invalid when the symbol is changed
* or when the DecimalFormatSymbols are destroyed.
* ### TODO markus 2002oct11: Consider proposing getConstSymbol() to be really public.
*
* @param symbol Constant to indicate a number format symbol.
* @return the format symbol by the param 'symbol'
* @internal
*/
inline const UnicodeString &getConstSymbol(ENumberFormatSymbol symbol) const;
/**
* Returns that pattern stored in currecy info. Internal API for use by NumberFormat API.
* @internal
*/
inline const UChar* getCurrencyPattern(void) const;
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* Private symbol strings.
* They are either loaded from a resource bundle or otherwise owned.
* setSymbol() clones the symbol string.
* Readonly aliases can only come from a resource bundle, so that we can always
* use fastCopyFrom() with them.
*
* If DecimalFormatSymbols becomes subclassable and the status of fSymbols changes
* from private to protected,
* or when fSymbols can be set any other way that allows them to be readonly aliases
* to non-resource bundle strings,
* then regular UnicodeString copies must be used instead of fastCopyFrom().
*
* @internal
*/
UnicodeString fSymbols[kFormatSymbolCount];
/**
* Non-symbol variable for getConstSymbol(). Always empty.
* @internal
*/
UnicodeString fNoSymbol;
Locale locale;
char actualLocale[ULOC_FULLNAME_CAPACITY];
char validLocale[ULOC_FULLNAME_CAPACITY];
const UChar* currPattern;
UnicodeString currencySpcBeforeSym[UNUM_CURRENCY_SPACING_COUNT];
UnicodeString currencySpcAfterSym[UNUM_CURRENCY_SPACING_COUNT];
};
// -------------------------------------
inline UnicodeString
DecimalFormatSymbols::getSymbol(ENumberFormatSymbol symbol) const {
const UnicodeString *strPtr;
if(symbol < kFormatSymbolCount) {
strPtr = &fSymbols[symbol];
} else {
strPtr = &fNoSymbol;
}
return *strPtr;
}
#ifndef U_HIDE_INTERNAL_API
inline const UnicodeString &
DecimalFormatSymbols::getConstSymbol(ENumberFormatSymbol symbol) const {
const UnicodeString *strPtr;
if(symbol < kFormatSymbolCount) {
strPtr = &fSymbols[symbol];
} else {
strPtr = &fNoSymbol;
}
return *strPtr;
}
#endif /* U_HIDE_INTERNAL_API */
// -------------------------------------
inline void
DecimalFormatSymbols::setSymbol(ENumberFormatSymbol symbol, const UnicodeString &value, const UBool propogateDigits = TRUE) {
if(symbol<kFormatSymbolCount) {
fSymbols[symbol]=value;
}
// If the zero digit is being set to a known zero digit according to Unicode,
// then we automatically set the corresponding 1-9 digits
if ( propogateDigits && symbol == kZeroDigitSymbol && value.countChar32() == 1 ) {
UChar32 sym = value.char32At(0);
if ( u_charDigitValue(sym) == 0 ) {
for ( int8_t i = 1 ; i<= 9 ; i++ ) {
sym++;
fSymbols[(int)kOneDigitSymbol+i-1] = UnicodeString(sym);
}
}
}
}
// -------------------------------------
inline Locale
DecimalFormatSymbols::getLocale() const {
return locale;
}
#ifndef U_HIDE_INTERNAL_API
inline const UChar*
DecimalFormatSymbols::getCurrencyPattern() const {
return currPattern;
}
#endif /* U_HIDE_INTERNAL_API */
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _DCFMTSYM
//eof
project/jni/icuuc/include/unicode/decimfmt.h
-2407
View File
File diff suppressed because it is too large Load Diff
project/jni/icuuc/include/unicode/docmain.h
-215
View File
@@ -1,215 +0,0 @@
/********************************************************************
* COPYRIGHT:
* Copyright (c) 1997-2012, International Business Machines Corporation and
* others. All Rights Reserved.
*
* FILE NAME: DOCMAIN.h
*
* Date Name Description
* 12/11/2000 Ram Creation.
*/
/**
* \file
* \brief (Non API- contains Doxygen definitions)
*
* This file contains documentation for Doxygen and doesnot have
* any significance with respect to C or C++ API
*/
/*! \mainpage
*
* \section API API Reference Usage
*
* <h3>C++ Programmers:</h3>
* <p>Use <a href="hierarchy.html">Class Hierarchy</a> or <a href="classes.html"> Alphabetical List </a>
* or <a href="annotated.html"> Compound List</a>
* to find the class you are interested in. For example, to find BreakIterator,
* you can go to the <a href="classes.html"> Alphabetical List</a>, then click on
* "BreakIterator". Once you are at the class, you will find an inheritance
* chart, a list of the public members, a detailed description of the class,
* then detailed member descriptions.</p>
*
* <h3>C Programmers:</h3>
* <p>Use <a href="#Module">Module List</a> or <a href="globals.html">File Members</a>
* to find a list of all the functions and constants.
* For example, to find BreakIterator functions you would click on
* <a href="files.html"> File List</a>,
* then find "ubrk.h" and click on it. You will find descriptions of Defines,
* Typedefs, Enumerations, and Functions, with detailed descriptions below.
* If you want to find a specific function, such as ubrk_next(), then click
* first on <a href="globals.html"> File Members</a>, then use your browser
* Find dialog to search for "ubrk_next()".</p>
*
*
* <h3>API References for Previous Releases</h3>
* <p>The API References for each release of ICU are also available as
* a zip file from the ICU
* <a href="http://site.icu-project.org/download">download page</a>.</p>
*
* <hr>
*
* <h2>Architecture (User's Guide)</h2>
* <ul>
* <li><a href="http://userguide.icu-project.org/">Introduction</a></li>
* <li><a href="http://userguide.icu-project.org/i18n">Internationalization</a></li>
* <li><a href="http://userguide.icu-project.org/design">Locale Model, Multithreading, Error Handling, etc.</a></li>
* <li><a href="http://userguide.icu-project.org/conversion">Conversion</a></li>
* </ul>
*
* <hr>
*\htmlonly <h2><a NAME="Module">Module List</a></h2> \endhtmlonly
* <table border="1" cols="3" align="center">
* <tr>
* <td><strong>Module Name</strong></td>
* <td><strong>C</strong></td>
* <td><strong>C++</strong></td>
* </tr>
* <tr>
* <td>Basic Types and Constants</td>
* <td>utypes.h</td>
* <td>utypes.h</td>
* </tr>
* <tr>
* <td>Strings and Character Iteration</td>
* <td>ustring.h, utf8.h, utf16.h, UText, UCharIterator</td>
* <td>icu::UnicodeString, icu::CharacterIterator, icu::Appendable, icu::StringPiece,icu::ByteSink</td>
* </tr>
* <tr>
* <td>Unicode Character<br/>Properties and Names</td>
* <td>uchar.h, uscript.h</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>Sets of Unicode Code Points and Strings</td>
* <td>uset.h</td>
* <td>icu::UnicodeSet</td>
* </tr>
* <tr>
* <td>Maps from Strings to Integer Values</td>
* <td>(no C API)</td>
* <td>icu::BytesTrie, icu::UCharsTrie</td>
* </tr>
* <tr>
* <td>Codepage Conversion</td>
* <td>ucnv.h, ucnvsel.hb</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>Unicode Text Compression</td>
* <td>ucnv.h<br/>(encoding name "SCSU" or "BOCU-1")</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>Locales </td>
* <td>uloc.h</a></td>
* <td>icu::Locale</td>
* </tr>
* <tr>
* <td>Resource Bundles</td>
* <td>ures.h</td>
* <td>icu::ResourceBundle</td>
* </tr>
* <tr>
* <td>Normalization</td>
* <td>unorm2.h</td>
* <td>icu::Normalizer2</td>
* </tr>
* <tr>
* <td>Calendars</td>
* <td>ucal.h</td>
* <td>icu::Calendar</td>
* </tr>
* <tr>
* <td>Date and Time Formatting</td>
* <td>udat.h</td>
* <td>icu::DateFormat</td>
* </tr>
* <tr>
* <td>Message Formatting</td>
* <td>umsg.h</td>
* <td>icu::MessageFormat</td>
* </tr>
* <tr>
* <td>Number Formatting</td>
* <td>unum.h</td>
* <td>icu::NumberFormat</td>
* </tr>
* <tr>
* <td>Number Spellout<br/>(Rule Based Number Formatting)</td>
* <td>unum.h<br/>(use UNUM_SPELLOUT)</td>
* <td>icu::RuleBasedNumberFormat</td>
* </tr>
* <tr>
* <td>Text Transformation<br/>(Transliteration)</td>
* <td>utrans.h</td>
* <td>icu::Transliterator</td>
* </tr>
* <tr>
* <td>Bidirectional Algorithm</td>
* <td>ubidi.h</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>Arabic Shaping</td>
* <td>ushape.h</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>Collation</td>
* <td>ucol.h</td>
* <td>icu::Collator</td>
* </tr>
* <tr>
* <td>String Searching</td>
* <td>usearch.h</td>
* <td>icu::StringSearch</td>
* </tr>
* <tr>
* <td>Index Characters/<br/>Bucketing for Sorted Lists</td>
* <td>(no C API)</td>
* <td>icu::AlphabeticIndex</td>
* </tr>
* <tr>
* <td>Text Boundary Analysis<br/>(Break Iteration)</td>
* <td>ubrk.h</td>
* <td>icu::BreakIterator</td>
* </tr>
* <tr>
* <td>Regular Expressions</td>
* <td>uregex.h</td>
* <td>icu::RegexPattern, icu::RegexMatcher</td>
* </tr>
* <tr>
* <td>StringPrep</td>
* <td>usprep.h</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>International Domain Names in Applications:<br/>
* UTS #46 in C/C++, IDNA2003 only via C API</td>
* <td>uidna.h</td>
* <td>idna.h</td>
* </tr>
* <tr>
* <td>Identifier Spoofing & Confusability</td>
* <td>uspoof.h</td>
* <td>C API</td>
* <tr>
* <td>Universal Time Scale</td>
* <td>utmscale.h</td>
* <td>C API</td>
* </tr>
* <tr>
* <td>Layout Engine/Complex Text Layout</td>
* <td>loengine.h</td>
* <td>icu::LayoutEngine,icu::ParagraphLayout</td>
* </tr>
* <tr>
* <td>ICU I/O</td>
* <td>ustdio.h</td>
* <td>ustream.h</td>
* </tr>
* </table>
* <i>This main page is generated from docmain.h</i>
*/
project/jni/icuuc/include/unicode/dtfmtsym.h
-847
View File
@@ -1,847 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File DTFMTSYM.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 07/21/98 stephen Added getZoneIndex()
* Changed to match C++ conventions
********************************************************************************
*/
#ifndef DTFMTSYM_H
#define DTFMTSYM_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/calendar.h"
#include "unicode/uobject.h"
#include "unicode/locid.h"
#include "unicode/udat.h"
#include "unicode/ures.h"
/**
* \file
* \brief C++ API: Symbols for formatting dates.
*/
U_NAMESPACE_BEGIN
/* forward declaration */
class SimpleDateFormat;
class Hashtable;
/**
* DateFormatSymbols is a public class for encapsulating localizable date-time
* formatting data -- including timezone data. DateFormatSymbols is used by
* DateFormat and SimpleDateFormat.
* <P>
* Rather than first creating a DateFormatSymbols to get a date-time formatter
* by using a SimpleDateFormat constructor, clients are encouraged to create a
* date-time formatter using the getTimeInstance(), getDateInstance(), or
* getDateTimeInstance() method in DateFormat. Each of these methods can return a
* date/time formatter initialized with a default format pattern along with the
* date-time formatting data for a given or default locale. After a formatter is
* created, clients may modify the format pattern using the setPattern function
* as so desired. For more information on using these formatter factory
* functions, see DateFormat.
* <P>
* If clients decide to create a date-time formatter with a particular format
* pattern and locale, they can do so with new SimpleDateFormat(aPattern,
* new DateFormatSymbols(aLocale)). This will load the appropriate date-time
* formatting data from the locale.
* <P>
* DateFormatSymbols objects are clonable. When clients obtain a
* DateFormatSymbols object, they can feel free to modify the date-time
* formatting data as necessary. For instance, clients can
* replace the localized date-time format pattern characters with the ones that
* they feel easy to remember. Or they can change the representative cities
* originally picked by default to using their favorite ones.
* <P>
* DateFormatSymbols are not expected to be subclassed. Data for a calendar is
* loaded out of resource bundles. The 'type' parameter indicates the type of
* calendar, for example, "gregorian" or "japanese". If the type is not gregorian
* (or NULL, or an empty string) then the type is appended to the resource name,
* for example, 'Eras_japanese' instead of 'Eras'. If the resource 'Eras_japanese' did
* not exist (even in root), then this class will fall back to just 'Eras', that is,
* Gregorian data. Therefore, the calendar implementor MUST ensure that the root
* locale at least contains any resources that are to be particularized for the
* calendar type.
*/
class U_I18N_API DateFormatSymbols : public UObject {
public:
/**
* Construct a DateFormatSymbols object by loading format data from
* resources for the default locale, in the default calendar (Gregorian).
* <P>
* NOTE: This constructor will never fail; if it cannot get resource
* data for the default locale, it will return a last-resort object
* based on hard-coded strings.
*
* @param status Status code. Failure
* results if the resources for the default cannot be
* found or cannot be loaded
* @stable ICU 2.0
*/
DateFormatSymbols(UErrorCode& status);
/**
* Construct a DateFormatSymbols object by loading format data from
* resources for the given locale, in the default calendar (Gregorian).
*
* @param locale Locale to load format data from.
* @param status Status code. Failure
* results if the resources for the locale cannot be
* found or cannot be loaded
* @stable ICU 2.0
*/
DateFormatSymbols(const Locale& locale,
UErrorCode& status);
#ifndef U_HIDE_INTERNAL_API
/**
* Construct a DateFormatSymbols object by loading format data from
* resources for the default locale, in the default calendar (Gregorian).
* <P>
* NOTE: This constructor will never fail; if it cannot get resource
* data for the default locale, it will return a last-resort object
* based on hard-coded strings.
*
* @param type Type of calendar (as returned by Calendar::getType).
* Will be used to access the correct set of strings.
* (NULL or empty string defaults to "gregorian".)
* @param status Status code. Failure
* results if the resources for the default cannot be
* found or cannot be loaded
* @internal
*/
DateFormatSymbols(const char *type, UErrorCode& status);
/**
* Construct a DateFormatSymbols object by loading format data from
* resources for the given locale, in the default calendar (Gregorian).
*
* @param locale Locale to load format data from.
* @param type Type of calendar (as returned by Calendar::getType).
* Will be used to access the correct set of strings.
* (NULL or empty string defaults to "gregorian".)
* @param status Status code. Failure
* results if the resources for the locale cannot be
* found or cannot be loaded
* @internal
*/
DateFormatSymbols(const Locale& locale,
const char *type,
UErrorCode& status);
#endif /* U_HIDE_INTERNAL_API */
/**
* Copy constructor.
* @stable ICU 2.0
*/
DateFormatSymbols(const DateFormatSymbols&);
/**
* Assignment operator.
* @stable ICU 2.0
*/
DateFormatSymbols& operator=(const DateFormatSymbols&);
/**
* Destructor. This is nonvirtual because this class is not designed to be
* subclassed.
* @stable ICU 2.0
*/
virtual ~DateFormatSymbols();
/**
* Return true if another object is semantically equal to this one.
*
* @param other the DateFormatSymbols object to be compared with.
* @return true if other is semantically equal to this.
* @stable ICU 2.0
*/
UBool operator==(const DateFormatSymbols& other) const;
/**
* Return true if another object is semantically unequal to this one.
*
* @param other the DateFormatSymbols object to be compared with.
* @return true if other is semantically unequal to this.
* @stable ICU 2.0
*/
UBool operator!=(const DateFormatSymbols& other) const { return !operator==(other); }
/**
* Gets abbreviated era strings. For example: "AD" and "BC".
*
* @param count Filled in with length of the array.
* @return the era strings.
* @stable ICU 2.0
*/
const UnicodeString* getEras(int32_t& count) const;
/**
* Sets abbreviated era strings. For example: "AD" and "BC".
* @param eras Array of era strings (DateFormatSymbols retains ownership.)
* @param count Filled in with length of the array.
* @stable ICU 2.0
*/
void setEras(const UnicodeString* eras, int32_t count);
/**
* Gets era name strings. For example: "Anno Domini" and "Before Christ".
*
* @param count Filled in with length of the array.
* @return the era name strings.
* @stable ICU 3.4
*/
const UnicodeString* getEraNames(int32_t& count) const;
/**
* Sets era name strings. For example: "Anno Domini" and "Before Christ".
* @param eraNames Array of era name strings (DateFormatSymbols retains ownership.)
* @param count Filled in with length of the array.
* @stable ICU 3.6
*/
void setEraNames(const UnicodeString* eraNames, int32_t count);
/**
* Gets narrow era strings. For example: "A" and "B".
*
* @param count Filled in with length of the array.
* @return the narrow era strings.
* @stable ICU 4.2
*/
const UnicodeString* getNarrowEras(int32_t& count) const;
/**
* Sets narrow era strings. For example: "A" and "B".
* @param narrowEras Array of narrow era strings (DateFormatSymbols retains ownership.)
* @param count Filled in with length of the array.
* @stable ICU 4.2
*/
void setNarrowEras(const UnicodeString* narrowEras, int32_t count);
/**
* Gets month strings. For example: "January", "February", etc.
* @param count Filled in with length of the array.
* @return the month strings. (DateFormatSymbols retains ownership.)
* @stable ICU 2.0
*/
const UnicodeString* getMonths(int32_t& count) const;
/**
* Sets month strings. For example: "January", "February", etc.
*
* @param months the new month strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @stable ICU 2.0
*/
void setMonths(const UnicodeString* months, int32_t count);
/**
* Gets short month strings. For example: "Jan", "Feb", etc.
*
* @param count Filled in with length of the array.
* @return the short month strings. (DateFormatSymbols retains ownership.)
* @stable ICU 2.0
*/
const UnicodeString* getShortMonths(int32_t& count) const;
/**
* Sets short month strings. For example: "Jan", "Feb", etc.
* @param count Filled in with length of the array.
* @param shortMonths the new short month strings. (not adopted; caller retains ownership)
* @stable ICU 2.0
*/
void setShortMonths(const UnicodeString* shortMonths, int32_t count);
/**
* Selector for date formatting context
* @stable ICU 3.6
*/
enum DtContextType {
FORMAT,
STANDALONE,
DT_CONTEXT_COUNT
};
/**
* Selector for date formatting width
* @stable ICU 3.6
*/
enum DtWidthType {
ABBREVIATED,
WIDE,
NARROW,
#ifndef U_HIDE_DRAFT_API
/**
* Short width is currently only supported for weekday names.
* @draft ICU 51
*/
SHORT,
#endif /* U_HIDE_DRAFT_API */
/**
*/
DT_WIDTH_COUNT = 4
};
/**
* Gets month strings by width and context. For example: "January", "February", etc.
* @param count Filled in with length of the array.
* @param context The formatting context, either FORMAT or STANDALONE
* @param width The width of returned strings, either WIDE, ABBREVIATED, or NARROW.
* @return the month strings. (DateFormatSymbols retains ownership.)
* @stable ICU 3.4
*/
const UnicodeString* getMonths(int32_t& count, DtContextType context, DtWidthType width) const;
/**
* Sets month strings by width and context. For example: "January", "February", etc.
*
* @param months The new month strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @param context The formatting context, either FORMAT or STANDALONE
* @param width The width of returned strings, either WIDE, ABBREVIATED, or NARROW.
* @stable ICU 3.6
*/
void setMonths(const UnicodeString* months, int32_t count, DtContextType context, DtWidthType width);
/**
* Gets wide weekday strings. For example: "Sunday", "Monday", etc.
* @param count Filled in with length of the array.
* @return the weekday strings. (DateFormatSymbols retains ownership.)
* @stable ICU 2.0
*/
const UnicodeString* getWeekdays(int32_t& count) const;
/**
* Sets wide weekday strings. For example: "Sunday", "Monday", etc.
* @param weekdays the new weekday strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @stable ICU 2.0
*/
void setWeekdays(const UnicodeString* weekdays, int32_t count);
/**
* Gets abbreviated weekday strings. For example: "Sun", "Mon", etc. (Note: The method name is
* misleading; it does not get the CLDR-style "short" weekday strings, e.g. "Su", "Mo", etc.)
* @param count Filled in with length of the array.
* @return the abbreviated weekday strings. (DateFormatSymbols retains ownership.)
* @stable ICU 2.0
*/
const UnicodeString* getShortWeekdays(int32_t& count) const;
/**
* Sets abbreviated weekday strings. For example: "Sun", "Mon", etc. (Note: The method name is
* misleading; it does not set the CLDR-style "short" weekday strings, e.g. "Su", "Mo", etc.)
* @param abbrevWeekdays the new abbreviated weekday strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @stable ICU 2.0
*/
void setShortWeekdays(const UnicodeString* abbrevWeekdays, int32_t count);
/**
* Gets weekday strings by width and context. For example: "Sunday", "Monday", etc.
* @param count Filled in with length of the array.
* @param context The formatting context, either FORMAT or STANDALONE
* @param width The width of returned strings, either WIDE, ABBREVIATED, SHORT, or NARROW
* @return the month strings. (DateFormatSymbols retains ownership.)
* @stable ICU 3.4
*/
const UnicodeString* getWeekdays(int32_t& count, DtContextType context, DtWidthType width) const;
/**
* Sets weekday strings by width and context. For example: "Sunday", "Monday", etc.
* @param weekdays The new weekday strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @param context The formatting context, either FORMAT or STANDALONE
* @param width The width of returned strings, either WIDE, ABBREVIATED, SHORT, or NARROW
* @stable ICU 3.6
*/
void setWeekdays(const UnicodeString* weekdays, int32_t count, DtContextType context, DtWidthType width);
/**
* Gets quarter strings by width and context. For example: "1st Quarter", "2nd Quarter", etc.
* @param count Filled in with length of the array.
* @param context The formatting context, either FORMAT or STANDALONE
* @param width The width of returned strings, either WIDE or ABBREVIATED. There
* are no NARROW quarters.
* @return the quarter strings. (DateFormatSymbols retains ownership.)
* @stable ICU 3.6
*/
const UnicodeString* getQuarters(int32_t& count, DtContextType context, DtWidthType width) const;
/**
* Sets quarter strings by width and context. For example: "1st Quarter", "2nd Quarter", etc.
*
* @param quarters The new quarter strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @param context The formatting context, either FORMAT or STANDALONE
* @param width The width of returned strings, either WIDE or ABBREVIATED. There
* are no NARROW quarters.
* @stable ICU 3.6
*/
void setQuarters(const UnicodeString* quarters, int32_t count, DtContextType context, DtWidthType width);
/**
* Gets AM/PM strings. For example: "AM" and "PM".
* @param count Filled in with length of the array.
* @return the weekday strings. (DateFormatSymbols retains ownership.)
* @stable ICU 2.0
*/
const UnicodeString* getAmPmStrings(int32_t& count) const;
/**
* Sets ampm strings. For example: "AM" and "PM".
* @param ampms the new ampm strings. (not adopted; caller retains ownership)
* @param count Filled in with length of the array.
* @stable ICU 2.0
*/
void setAmPmStrings(const UnicodeString* ampms, int32_t count);
#ifndef U_HIDE_INTERNAL_API
/**
* Somewhat temporary constants for leap month pattern types, adequate for supporting
* just leap month patterns as needed for Chinese lunar calendar.
* Eventually we will add full support for different month pattern types (needed for
* other calendars such as Hindu) at which point this approach will be replaced by a
* more complete approach.
* @internal
*/
enum EMonthPatternType
{
kLeapMonthPatternFormatWide,
kLeapMonthPatternFormatAbbrev,
kLeapMonthPatternFormatNarrow,
kLeapMonthPatternStandaloneWide,
kLeapMonthPatternStandaloneAbbrev,
kLeapMonthPatternStandaloneNarrow,
kLeapMonthPatternNumeric,
kMonthPatternsCount
};
/**
* Somewhat temporary function for getting complete set of leap month patterns for all
* contexts & widths, indexed by EMonthPatternType values. Returns NULL if calendar
* does not have leap month patterns. Note, there is currently no setter for this.
* Eventually we will add full support for different month pattern types (needed for
* other calendars such as Hindu) at which point this approach will be replaced by a
* more complete approach.
* @param count Filled in with length of the array (may be 0).
* @return The leap month patterns (DateFormatSymbols retains ownership).
* May be NULL if there are no leap month patterns for this calendar.
* @internal
*/
const UnicodeString* getLeapMonthPatterns(int32_t& count) const;
#endif /* U_HIDE_INTERNAL_API */
#ifndef U_HIDE_DEPRECATED_API
/**
* Gets timezone strings. These strings are stored in a 2-dimensional array.
* @param rowCount Output param to receive number of rows.
* @param columnCount Output param to receive number of columns.
* @return The timezone strings as a 2-d array. (DateFormatSymbols retains ownership.)
* @deprecated ICU 3.6
*/
const UnicodeString** getZoneStrings(int32_t& rowCount, int32_t& columnCount) const;
#endif /* U_HIDE_DEPRECATED_API */
/**
* Sets timezone strings. These strings are stored in a 2-dimensional array.
* <p><b>Note:</b> SimpleDateFormat no longer use the zone strings stored in
* a DateFormatSymbols. Therefore, the time zone strings set by this mthod
* have no effects in an instance of SimpleDateFormat for formatting time
* zones.
* @param strings The timezone strings as a 2-d array to be copied. (not adopted; caller retains ownership)
* @param rowCount The number of rows (count of first index).
* @param columnCount The number of columns (count of second index).
* @stable ICU 2.0
*/
void setZoneStrings(const UnicodeString* const* strings, int32_t rowCount, int32_t columnCount);
/**
* Get the non-localized date-time pattern characters.
* @return the non-localized date-time pattern characters
* @stable ICU 2.0
*/
static const UChar * U_EXPORT2 getPatternUChars(void);
/**
* Gets localized date-time pattern characters. For example: 'u', 't', etc.
* <p>
* Note: ICU no longer provides localized date-time pattern characters for a locale
* starting ICU 3.8. This method returns the non-localized date-time pattern
* characters unless user defined localized data is set by setLocalPatternChars.
* @param result Output param which will receive the localized date-time pattern characters.
* @return A reference to 'result'.
* @stable ICU 2.0
*/
UnicodeString& getLocalPatternChars(UnicodeString& result) const;
/**
* Sets localized date-time pattern characters. For example: 'u', 't', etc.
* @param newLocalPatternChars the new localized date-time
* pattern characters.
* @stable ICU 2.0
*/
void setLocalPatternChars(const UnicodeString& newLocalPatternChars);
/**
* Returns the locale for this object. Two flavors are available:
* valid and actual locale.
* @stable ICU 2.8
*/
Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
/**
* Constants for capitalization context usage types.
* @internal
*/
enum ECapitalizationContextUsageType
{
kCapContextUsageOther,
kCapContextUsageMonthFormat, /* except narrow */
kCapContextUsageMonthStandalone, /* except narrow */
kCapContextUsageMonthNarrow,
kCapContextUsageDayFormat, /* except narrow */
kCapContextUsageDayStandalone, /* except narrow */
kCapContextUsageDayNarrow,
kCapContextUsageEraWide,
kCapContextUsageEraAbbrev,
kCapContextUsageEraNarrow,
kCapContextUsageZoneLong,
kCapContextUsageZoneShort,
kCapContextUsageMetazoneLong,
kCapContextUsageMetazoneShort,
kCapContextUsageTypeCount
};
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
friend class SimpleDateFormat;
friend class DateFormatSymbolsSingleSetter; // see udat.cpp
/**
* Abbreviated era strings. For example: "AD" and "BC".
*/
UnicodeString* fEras;
int32_t fErasCount;
/**
* Era name strings. For example: "Anno Domini" and "Before Christ".
*/
UnicodeString* fEraNames;
int32_t fEraNamesCount;
/**
* Narrow era strings. For example: "A" and "B".
*/
UnicodeString* fNarrowEras;
int32_t fNarrowErasCount;
/**
* Month strings. For example: "January", "February", etc.
*/
UnicodeString* fMonths;
int32_t fMonthsCount;
/**
* Short month strings. For example: "Jan", "Feb", etc.
*/
UnicodeString* fShortMonths;
int32_t fShortMonthsCount;
/**
* Narrow month strings. For example: "J", "F", etc.
*/
UnicodeString* fNarrowMonths;
int32_t fNarrowMonthsCount;
/**
* Standalone Month strings. For example: "January", "February", etc.
*/
UnicodeString* fStandaloneMonths;
int32_t fStandaloneMonthsCount;
/**
* Standalone Short month strings. For example: "Jan", "Feb", etc.
*/
UnicodeString* fStandaloneShortMonths;
int32_t fStandaloneShortMonthsCount;
/**
* Standalone Narrow month strings. For example: "J", "F", etc.
*/
UnicodeString* fStandaloneNarrowMonths;
int32_t fStandaloneNarrowMonthsCount;
/**
* CLDR-style format wide weekday strings. For example: "Sunday", "Monday", etc.
*/
UnicodeString* fWeekdays;
int32_t fWeekdaysCount;
/**
* CLDR-style format abbreviated (not short) weekday strings. For example: "Sun", "Mon", etc.
*/
UnicodeString* fShortWeekdays;
int32_t fShortWeekdaysCount;
/**
* CLDR-style format short weekday strings. For example: "Su", "Mo", etc.
*/
UnicodeString* fShorterWeekdays;
int32_t fShorterWeekdaysCount;
/**
* CLDR-style format narrow weekday strings. For example: "S", "M", etc.
*/
UnicodeString* fNarrowWeekdays;
int32_t fNarrowWeekdaysCount;
/**
* CLDR-style standalone wide weekday strings. For example: "Sunday", "Monday", etc.
*/
UnicodeString* fStandaloneWeekdays;
int32_t fStandaloneWeekdaysCount;
/**
* CLDR-style standalone abbreviated (not short) weekday strings. For example: "Sun", "Mon", etc.
*/
UnicodeString* fStandaloneShortWeekdays;
int32_t fStandaloneShortWeekdaysCount;
/**
* CLDR-style standalone short weekday strings. For example: "Su", "Mo", etc.
*/
UnicodeString* fStandaloneShorterWeekdays;
int32_t fStandaloneShorterWeekdaysCount;
/**
* Standalone Narrow weekday strings. For example: "Sun", "Mon", etc.
*/
UnicodeString* fStandaloneNarrowWeekdays;
int32_t fStandaloneNarrowWeekdaysCount;
/**
* Ampm strings. For example: "AM" and "PM".
*/
UnicodeString* fAmPms;
int32_t fAmPmsCount;
/**
* Quarter strings. For example: "1st quarter", "2nd quarter", etc.
*/
UnicodeString *fQuarters;
int32_t fQuartersCount;
/**
* Short quarters. For example: "Q1", "Q2", etc.
*/
UnicodeString *fShortQuarters;
int32_t fShortQuartersCount;
/**
* Standalone quarter strings. For example: "1st quarter", "2nd quarter", etc.
*/
UnicodeString *fStandaloneQuarters;
int32_t fStandaloneQuartersCount;
/**
* Standalone short quarter strings. For example: "Q1", "Q2", etc.
*/
UnicodeString *fStandaloneShortQuarters;
int32_t fStandaloneShortQuartersCount;
/**
* All leap month patterns, for example "{0}bis".
*/
UnicodeString *fLeapMonthPatterns;
int32_t fLeapMonthPatternsCount;
/**
* (Format) Short cyclic year names, for example: "jia-zi", "yi-chou", ... "gui-hai"
*/
UnicodeString* fShortYearNames;
int32_t fShortYearNamesCount;
/**
* Localized names of time zones in this locale. This is a
* two-dimensional array of strings of size n by m,
* where m is at least 5 and up to 7. Each of the n rows is an
* entry containing the localized names for a single TimeZone.
*
* Each such row contains (with i ranging from 0..n-1):
*
* zoneStrings[i][0] - time zone ID
* example: America/Los_Angeles
* zoneStrings[i][1] - long name of zone in standard time
* example: Pacific Standard Time
* zoneStrings[i][2] - short name of zone in standard time
* example: PST
* zoneStrings[i][3] - long name of zone in daylight savings time
* example: Pacific Daylight Time
* zoneStrings[i][4] - short name of zone in daylight savings time
* example: PDT
* zoneStrings[i][5] - location name of zone
* example: United States (Los Angeles)
* zoneStrings[i][6] - long generic name of zone
* example: Pacific Time
* zoneStrings[i][7] - short generic of zone
* example: PT
*
* The zone ID is not localized; it corresponds to the ID
* value associated with a system time zone object. All other entries
* are localized names. If a zone does not implement daylight savings
* time, the daylight savings time names are ignored.
*
* Note:CLDR 1.5 introduced metazone and its historical mappings.
* This simple two-dimensional array is no longer sufficient to represent
* localized names and its historic changes. Since ICU 3.8.1, localized
* zone names extracted from ICU locale data is stored in a ZoneStringFormat
* instance. But we still need to support the old way of customizing
* localized zone names, so we keep this field for the purpose.
*/
UnicodeString **fZoneStrings; // Zone string array set by setZoneStrings
UnicodeString **fLocaleZoneStrings; // Zone string array created by the locale
int32_t fZoneStringsRowCount;
int32_t fZoneStringsColCount;
Locale fZSFLocale; // Locale used for getting ZoneStringFormat
/**
* Localized date-time pattern characters. For example: use 'u' as 'y'.
*/
UnicodeString fLocalPatternChars;
/**
* Capitalization transforms. For each usage type, the first array element indicates
* whether to titlecase for uiListOrMenu context, the second indicates whether to
* titlecase for stand-alone context.
*/
UBool fCapitalization[kCapContextUsageTypeCount][2];
private:
/** valid/actual locale information
* these are always ICU locales, so the length should not be a problem
*/
char validLocale[ULOC_FULLNAME_CAPACITY];
char actualLocale[ULOC_FULLNAME_CAPACITY];
DateFormatSymbols(); // default constructor not implemented
/**
* Called by the constructors to actually load data from the resources
*
* @param locale The locale to get symbols for.
* @param type Calendar Type (as from Calendar::getType())
* @param status Input/output parameter, set to success or
* failure code upon return.
* @param useLastResortData determine if use last resort data
*/
void initializeData(const Locale& locale, const char *type, UErrorCode& status, UBool useLastResortData = FALSE);
/**
* Copy or alias an array in another object, as appropriate.
*
* @param dstArray the copy destination array.
* @param dstCount fill in with the lenth of 'dstArray'.
* @param srcArray the source array to be copied.
* @param srcCount the length of items to be copied from the 'srcArray'.
*/
static void assignArray(UnicodeString*& dstArray,
int32_t& dstCount,
const UnicodeString* srcArray,
int32_t srcCount);
/**
* Return true if the given arrays' contents are equal, or if the arrays are
* identical (pointers are equal).
*
* @param array1 one array to be compared with.
* @param array2 another array to be compared with.
* @param count the length of items to be copied.
* @return true if the given arrays' contents are equal, or if the arrays are
* identical (pointers are equal).
*/
static UBool arrayCompare(const UnicodeString* array1,
const UnicodeString* array2,
int32_t count);
/**
* Create a copy, in fZoneStrings, of the given zone strings array. The
* member variables fZoneStringsRowCount and fZoneStringsColCount should be
* set already by the caller.
*/
void createZoneStrings(const UnicodeString *const * otherStrings);
/**
* Delete all the storage owned by this object.
*/
void dispose(void);
/**
* Copy all of the other's data to this.
* @param other the object to be copied.
*/
void copyData(const DateFormatSymbols& other);
/**
* Create zone strings array by locale if not yet available
*/
void initZoneStringsArray(void);
/**
* Delete just the zone strings.
*/
void disposeZoneStrings(void);
/**
* Returns the date format field index of the pattern character c,
* or UDAT_FIELD_COUNT if c is not a pattern character.
*/
static UDateFormatField U_EXPORT2 getPatternCharIndex(UChar c);
/**
* Returns TRUE if f (with its pattern character repeated count times) is a numeric field.
*/
static UBool U_EXPORT2 isNumericField(UDateFormatField f, int32_t count);
/**
* Returns TRUE if c (repeated count times) is the pattern character for a numeric field.
*/
static UBool U_EXPORT2 isNumericPatternChar(UChar c, int32_t count);
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _DTFMTSYM
//eof
project/jni/icuuc/include/unicode/dtintrv.h
-158
View File
@@ -1,158 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2008-2009, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
* File DTINTRV.H
*
*******************************************************************************
*/
#ifndef __DTINTRV_H__
#define __DTINTRV_H__
#include "unicode/utypes.h"
#include "unicode/uobject.h"
/**
* \file
* \brief C++ API: Date Interval data type
*/
U_NAMESPACE_BEGIN
/**
* This class represents a date interval.
* It is a pair of UDate representing from UDate 1 to UDate 2.
* @stable ICU 4.0
**/
class U_COMMON_API DateInterval : public UObject {
public:
/**
* Construct a DateInterval given a from date and a to date.
* @param fromDate The from date in date interval.
* @param toDate The to date in date interval.
* @stable ICU 4.0
*/
DateInterval(UDate fromDate, UDate toDate);
/**
* destructor
* @stable ICU 4.0
*/
virtual ~DateInterval();
/**
* Get the from date.
* @return the from date in dateInterval.
* @stable ICU 4.0
*/
UDate getFromDate() const;
/**
* Get the to date.
* @return the to date in dateInterval.
* @stable ICU 4.0
*/
UDate getToDate() const;
/**
* Return the class ID for this class. This is useful only for comparing to
* a return value from getDynamicClassID(). For example:
* <pre>
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . erived::getStaticClassID()) ...
* </pre>
* @return The class ID for all objects of this class.
* @stable ICU 4.0
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This
* method is to implement a simple version of RTTI, since not all C++
* compilers support genuine RTTI. Polymorphic operator==() and clone()
* methods call this method.
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @stable ICU 4.0
*/
virtual UClassID getDynamicClassID(void) const;
/**
* Copy constructor.
* @stable ICU 4.0
*/
DateInterval(const DateInterval& other);
/**
* Default assignment operator
* @stable ICU 4.0
*/
DateInterval& operator=(const DateInterval&);
/**
* Equality operator.
* @return TRUE if the two DateIntervals are the same
* @stable ICU 4.0
*/
virtual UBool operator==(const DateInterval& other) const;
/**
* Non-equality operator
* @return TRUE if the two DateIntervals are not the same
* @stable ICU 4.0
*/
UBool operator!=(const DateInterval& other) const;
/**
* clone this object.
* The caller owns the result and should delete it when done.
* @return a cloned DateInterval
* @stable ICU 4.0
*/
virtual DateInterval* clone() const;
private:
/**
* Default constructor, not implemented.
*/
DateInterval();
UDate fromDate;
UDate toDate;
} ;// end class DateInterval
inline UDate
DateInterval::getFromDate() const {
return fromDate;
}
inline UDate
DateInterval::getToDate() const {
return toDate;
}
inline UBool
DateInterval::operator!=(const DateInterval& other) const {
return ( !operator==(other) );
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/dtitvfmt.h
-985
View File
@@ -1,985 +0,0 @@
/********************************************************************************
* Copyright (C) 2008-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
* File DTITVFMT.H
*
*******************************************************************************
*/
#ifndef __DTITVFMT_H__
#define __DTITVFMT_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Format and parse date interval in a language-independent manner.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/ucal.h"
#include "unicode/smpdtfmt.h"
#include "unicode/dtintrv.h"
#include "unicode/dtitvinf.h"
#include "unicode/dtptngen.h"
U_NAMESPACE_BEGIN
/**
* DateIntervalFormat is a class for formatting and parsing date
* intervals in a language-independent manner.
* Only formatting is supported, parsing is not supported.
*
* <P>
* Date interval means from one date to another date,
* for example, from "Jan 11, 2008" to "Jan 18, 2008".
* We introduced class DateInterval to represent it.
* DateInterval is a pair of UDate, which is
* the standard milliseconds since 24:00 GMT, Jan 1, 1970.
*
* <P>
* DateIntervalFormat formats a DateInterval into
* text as compactly as possible.
* For example, the date interval format from "Jan 11, 2008" to "Jan 18,. 2008"
* is "Jan 11-18, 2008" for English.
* And it parses text into DateInterval,
* although initially, parsing is not supported.
*
* <P>
* There is no structural information in date time patterns.
* For any punctuations and string literals inside a date time pattern,
* we do not know whether it is just a separator, or a prefix, or a suffix.
* Without such information, so, it is difficult to generate a sub-pattern
* (or super-pattern) by algorithm.
* So, formatting a DateInterval is pattern-driven. It is very
* similar to formatting in SimpleDateFormat.
* We introduce class DateIntervalInfo to save date interval
* patterns, similar to date time pattern in SimpleDateFormat.
*
* <P>
* Logically, the interval patterns are mappings
* from (skeleton, the_largest_different_calendar_field)
* to (date_interval_pattern).
*
* <P>
* A skeleton
* <ol>
* <li>
* only keeps the field pattern letter and ignores all other parts
* in a pattern, such as space, punctuations, and string literals.
* </li>
* <li>
* hides the order of fields.
* </li>
* <li>
* might hide a field's pattern letter length.
* </li>
* </ol>
*
* For those non-digit calendar fields, the pattern letter length is
* important, such as MMM, MMMM, and MMMMM; EEE and EEEE,
* and the field's pattern letter length is honored.
*
* For the digit calendar fields, such as M or MM, d or dd, yy or yyyy,
* the field pattern length is ignored and the best match, which is defined
* in date time patterns, will be returned without honor the field pattern
* letter length in skeleton.
*
* <P>
* The calendar fields we support for interval formatting are:
* year, month, date, day-of-week, am-pm, hour, hour-of-day, and minute.
* Those calendar fields can be defined in the following order:
* year > month > date > hour (in day) > minute
*
* The largest different calendar fields between 2 calendars is the
* first different calendar field in above order.
*
* For example: the largest different calendar fields between "Jan 10, 2007"
* and "Feb 20, 2008" is year.
*
* <P>
* For other calendar fields, the compact interval formatting is not
* supported. And the interval format will be fall back to fall-back
* patterns, which is mostly "{date0} - {date1}".
*
* <P>
* There is a set of pre-defined static skeleton strings.
* There are pre-defined interval patterns for those pre-defined skeletons
* in locales' resource files.
* For example, for a skeleton UDAT_YEAR_ABBR_MONTH_DAY, which is &quot;yMMMd&quot;,
* in en_US, if the largest different calendar field between date1 and date2
* is &quot;year&quot;, the date interval pattern is &quot;MMM d, yyyy - MMM d, yyyy&quot;,
* such as &quot;Jan 10, 2007 - Jan 10, 2008&quot;.
* If the largest different calendar field between date1 and date2 is &quot;month&quot;,
* the date interval pattern is &quot;MMM d - MMM d, yyyy&quot;,
* such as &quot;Jan 10 - Feb 10, 2007&quot;.
* If the largest different calendar field between date1 and date2 is &quot;day&quot;,
* the date interval pattern is &quot;MMM d-d, yyyy&quot;, such as &quot;Jan 10-20, 2007&quot;.
*
* For date skeleton, the interval patterns when year, or month, or date is
* different are defined in resource files.
* For time skeleton, the interval patterns when am/pm, or hour, or minute is
* different are defined in resource files.
*
* <P>
* If a skeleton is not found in a locale's DateIntervalInfo, which means
* the interval patterns for the skeleton is not defined in resource file,
* the interval pattern will falls back to the interval "fallback" pattern
* defined in resource file.
* If the interval "fallback" pattern is not defined, the default fall-back
* is "{date0} - {data1}".
*
* <P>
* For the combination of date and time,
* The rule to generate interval patterns are:
* <ol>
* <li>
* when the year, month, or day differs, falls back to fall-back
* interval pattern, which mostly is the concatenate the two original
* expressions with a separator between,
* For example, interval pattern from "Jan 10, 2007 10:10 am"
* to "Jan 11, 2007 10:10am" is
* "Jan 10, 2007 10:10 am - Jan 11, 2007 10:10am"
* </li>
* <li>
* otherwise, present the date followed by the range expression
* for the time.
* For example, interval pattern from "Jan 10, 2007 10:10 am"
* to "Jan 10, 2007 11:10am" is "Jan 10, 2007 10:10 am - 11:10am"
* </li>
* </ol>
*
*
* <P>
* If two dates are the same, the interval pattern is the single date pattern.
* For example, interval pattern from "Jan 10, 2007" to "Jan 10, 2007" is
* "Jan 10, 2007".
*
* Or if the presenting fields between 2 dates have the exact same values,
* the interval pattern is the single date pattern.
* For example, if user only requests year and month,
* the interval pattern from "Jan 10, 2007" to "Jan 20, 2007" is "Jan 2007".
*
* <P>
* DateIntervalFormat needs the following information for correct
* formatting: time zone, calendar type, pattern, date format symbols,
* and date interval patterns.
* It can be instantiated in 2 ways:
* <ol>
* <li>
* create an instance using default or given locale plus given skeleton.
* Users are encouraged to created date interval formatter this way and
* to use the pre-defined skeleton macros, such as
* UDAT_YEAR_NUM_MONTH, which consists the calendar fields and
* the format style.
* </li>
* <li>
* create an instance using default or given locale plus given skeleton
* plus a given DateIntervalInfo.
* This factory method is for powerful users who want to provide their own
* interval patterns.
* Locale provides the timezone, calendar, and format symbols information.
* Local plus skeleton provides full pattern information.
* DateIntervalInfo provides the date interval patterns.
* </li>
* </ol>
*
* <P>
* For the calendar field pattern letter, such as G, y, M, d, a, h, H, m, s etc.
* DateIntervalFormat uses the same syntax as that of
* DateTime format.
*
* <P>
* Code Sample: general usage
* <pre>
* \code
* // the date interval object which the DateIntervalFormat formats on
* // and parses into
* DateInterval* dtInterval = new DateInterval(1000*3600*24, 1000*3600*24*2);
* UErrorCode status = U_ZERO_ERROR;
* DateIntervalFormat* dtIntervalFmt = DateIntervalFormat::createInstance(
* UDAT_YEAR_MONTH_DAY,
* Locale("en", "GB", ""), status);
* UnicodeUnicodeString dateIntervalString;
* FieldPosition pos = 0;
* // formatting
* dtIntervalFmt->format(dtInterval, dateIntervalUnicodeString, pos, status);
* delete dtIntervalFmt;
* \endcode
* </pre>
*/
class U_I18N_API DateIntervalFormat : public Format {
public:
/**
* Construct a DateIntervalFormat from skeleton and the default locale.
*
* This is a convenient override of
* createInstance(const UnicodeString& skeleton, const Locale& locale,
* UErrorCode&)
* with the value of locale as default locale.
*
* @param skeleton the skeleton on which interval format based.
* @param status output param set to success/failure code on exit
* @return a date time interval formatter which the caller owns.
* @stable ICU 4.0
*/
static DateIntervalFormat* U_EXPORT2 createInstance(
const UnicodeString& skeleton,
UErrorCode& status);
/**
* Construct a DateIntervalFormat from skeleton and a given locale.
* <P>
* In this factory method,
* the date interval pattern information is load from resource files.
* Users are encouraged to created date interval formatter this way and
* to use the pre-defined skeleton macros.
*
* <P>
* There are pre-defined skeletons (defined in udate.h) having predefined
* interval patterns in resource files.
* Users are encouraged to use those macros.
* For example:
* DateIntervalFormat::createInstance(UDAT_MONTH_DAY, status)
*
* The given Locale provides the interval patterns.
* For example, for en_GB, if skeleton is UDAT_YEAR_ABBR_MONTH_WEEKDAY_DAY,
* which is "yMMMEEEd",
* the interval patterns defined in resource file to above skeleton are:
* "EEE, d MMM, yyyy - EEE, d MMM, yyyy" for year differs,
* "EEE, d MMM - EEE, d MMM, yyyy" for month differs,
* "EEE, d - EEE, d MMM, yyyy" for day differs,
* @param skeleton the skeleton on which the interval format is based.
* @param locale the given locale
* @param status output param set to success/failure code on exit
* @return a date time interval formatter which the caller owns.
* @stable ICU 4.0
* <p>
* <h4>Sample code</h4>
* \snippet samples/dtitvfmtsample/dtitvfmtsample.cpp dtitvfmtPreDefined1
* \snippet samples/dtitvfmtsample/dtitvfmtsample.cpp dtitvfmtPreDefined
* <p>
*/
static DateIntervalFormat* U_EXPORT2 createInstance(
const UnicodeString& skeleton,
const Locale& locale,
UErrorCode& status);
/**
* Construct a DateIntervalFormat from skeleton
* DateIntervalInfo, and default locale.
*
* This is a convenient override of
* createInstance(const UnicodeString& skeleton, const Locale& locale,
* const DateIntervalInfo& dtitvinf, UErrorCode&)
* with the locale value as default locale.
*
* @param skeleton the skeleton on which interval format based.
* @param dtitvinf the DateIntervalInfo object.
* @param status output param set to success/failure code on exit
* @return a date time interval formatter which the caller owns.
* @stable ICU 4.0
*/
static DateIntervalFormat* U_EXPORT2 createInstance(
const UnicodeString& skeleton,
const DateIntervalInfo& dtitvinf,
UErrorCode& status);
/**
* Construct a DateIntervalFormat from skeleton
* a DateIntervalInfo, and the given locale.
*
* <P>
* In this factory method, user provides its own date interval pattern
* information, instead of using those pre-defined data in resource file.
* This factory method is for powerful users who want to provide their own
* interval patterns.
* <P>
* There are pre-defined skeletons (defined in udate.h) having predefined
* interval patterns in resource files.
* Users are encouraged to use those macros.
* For example:
* DateIntervalFormat::createInstance(UDAT_MONTH_DAY, status)
*
* The DateIntervalInfo provides the interval patterns.
* and the DateIntervalInfo ownership remains to the caller.
*
* User are encouraged to set default interval pattern in DateIntervalInfo
* as well, if they want to set other interval patterns ( instead of
* reading the interval patterns from resource files).
* When the corresponding interval pattern for a largest calendar different
* field is not found ( if user not set it ), interval format fallback to
* the default interval pattern.
* If user does not provide default interval pattern, it fallback to
* "{date0} - {date1}"
*
* @param skeleton the skeleton on which interval format based.
* @param locale the given locale
* @param dtitvinf the DateIntervalInfo object.
* @param status output param set to success/failure code on exit
* @return a date time interval formatter which the caller owns.
* @stable ICU 4.0
* <p>
* <h4>Sample code</h4>
* \snippet samples/dtitvfmtsample/dtitvfmtsample.cpp dtitvfmtPreDefined1
* \snippet samples/dtitvfmtsample/dtitvfmtsample.cpp dtitvfmtCustomized
* <p>
*/
static DateIntervalFormat* U_EXPORT2 createInstance(
const UnicodeString& skeleton,
const Locale& locale,
const DateIntervalInfo& dtitvinf,
UErrorCode& status);
/**
* Destructor.
* @stable ICU 4.0
*/
virtual ~DateIntervalFormat();
/**
* Clone this Format object polymorphically. The caller owns the result and
* should delete it when done.
* @return A copy of the object.
* @stable ICU 4.0
*/
virtual Format* clone(void) const;
/**
* Return true if the given Format objects are semantically equal. Objects
* of different subclasses are considered unequal.
* @param other the object to be compared with.
* @return true if the given Format objects are semantically equal.
* @stable ICU 4.0
*/
virtual UBool operator==(const Format& other) const;
/**
* Return true if the given Format objects are not semantically equal.
* Objects of different subclasses are considered unequal.
* @param other the object to be compared with.
* @return true if the given Format objects are not semantically equal.
* @stable ICU 4.0
*/
UBool operator!=(const Format& other) const;
using Format::format;
/**
* Format an object to produce a string. This method handles Formattable
* objects with a DateInterval type.
* If a the Formattable object type is not a DateInterval,
* then it returns a failing UErrorCode.
*
* @param obj The object to format.
* Must be a DateInterval.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param fieldPosition On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.0
*/
virtual UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
FieldPosition& fieldPosition,
UErrorCode& status) const ;
/**
* Format a DateInterval to produce a string.
*
* @param dtInterval DateInterval to be formatted.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param fieldPosition On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.0
*/
UnicodeString& format(const DateInterval* dtInterval,
UnicodeString& appendTo,
FieldPosition& fieldPosition,
UErrorCode& status) const ;
/**
* Format 2 Calendars to produce a string.
*
* Note: "fromCalendar" and "toCalendar" are not const,
* since calendar is not const in SimpleDateFormat::format(Calendar&),
*
* @param fromCalendar calendar set to the from date in date interval
* to be formatted into date interval string
* @param toCalendar calendar set to the to date in date interval
* to be formatted into date interval string
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param fieldPosition On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* Caller needs to make sure it is SUCCESS
* at the function entrance
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.0
*/
UnicodeString& format(Calendar& fromCalendar,
Calendar& toCalendar,
UnicodeString& appendTo,
FieldPosition& fieldPosition,
UErrorCode& status) const ;
/**
* Date interval parsing is not supported. Please do not use.
* <P>
* This method should handle parsing of
* date time interval strings into Formattable objects with
* DateInterval type, which is a pair of UDate.
* <P>
* Before calling, set parse_pos.index to the offset you want to start
* parsing at in the source. After calling, parse_pos.index is the end of
* the text you parsed. If error occurs, index is unchanged.
* <P>
* When parsing, leading whitespace is discarded (with a successful parse),
* while trailing whitespace is left as is.
* <P>
* See Format::parseObject() for more.
*
* @param source The string to be parsed into an object.
* @param result Formattable to be set to the parse result.
* If parse fails, return contents are undefined.
* @param parse_pos The position to start parsing at. Since no parsing
* is supported, upon return this param is unchanged.
* @return A newly created Formattable* object, or NULL
* on failure. The caller owns this and should
* delete it when done.
* @internal ICU 4.0
*/
virtual void parseObject(const UnicodeString& source,
Formattable& result,
ParsePosition& parse_pos) const;
/**
* Gets the date time interval patterns.
* @return the date time interval patterns associated with
* this date interval formatter.
* @stable ICU 4.0
*/
const DateIntervalInfo* getDateIntervalInfo(void) const;
/**
* Set the date time interval patterns.
* @param newIntervalPatterns the given interval patterns to copy.
* @param status output param set to success/failure code on exit
* @stable ICU 4.0
*/
void setDateIntervalInfo(const DateIntervalInfo& newIntervalPatterns,
UErrorCode& status);
/**
* Gets the date formatter
* @return the date formatter associated with this date interval formatter.
* @stable ICU 4.0
*/
const DateFormat* getDateFormat(void) const;
/**
* Returns a reference to the TimeZone used by this DateIntervalFormat's calendar.
* @return the time zone associated with the calendar of DateIntervalFormat.
* @stable ICU 4.8
*/
virtual const TimeZone& getTimeZone(void) const;
/**
* Sets the time zone for the calendar used by this DateIntervalFormat object. The
* caller no longer owns the TimeZone object and should not delete it after this call.
* @param zoneToAdopt the TimeZone to be adopted.
* @stable ICU 4.8
*/
virtual void adoptTimeZone(TimeZone* zoneToAdopt);
/**
* Sets the time zone for the calendar used by this DateIntervalFormat object.
* @param zone the new time zone.
* @stable ICU 4.8
*/
virtual void setTimeZone(const TimeZone& zone);
/**
* Return the class ID for this class. This is useful only for comparing to
* a return value from getDynamicClassID(). For example:
* <pre>
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . erived::getStaticClassID()) ...
* </pre>
* @return The class ID for all objects of this class.
* @stable ICU 4.0
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This
* method is to implement a simple version of RTTI, since not all C++
* compilers support genuine RTTI. Polymorphic operator==() and clone()
* methods call this method.
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @stable ICU 4.0
*/
virtual UClassID getDynamicClassID(void) const;
protected:
/**
* Copy constructor.
* @stable ICU 4.0
*/
DateIntervalFormat(const DateIntervalFormat&);
/**
* Assignment operator.
* @stable ICU 4.0
*/
DateIntervalFormat& operator=(const DateIntervalFormat&);
private:
/*
* This is for ICU internal use only. Please do not use.
* Save the interval pattern information.
* Interval pattern consists of 2 single date patterns and the separator.
* For example, interval pattern "MMM d - MMM d, yyyy" consists
* a single date pattern "MMM d", another single date pattern "MMM d, yyyy",
* and a separator "-".
* The pattern is divided into 2 parts. For above example,
* the first part is "MMM d - ", and the second part is "MMM d, yyyy".
* Also, the first date appears in an interval pattern could be
* the earlier date or the later date.
* And such information is saved in the interval pattern as well.
*/
struct PatternInfo {
UnicodeString firstPart;
UnicodeString secondPart;
/**
* Whether the first date in interval pattern is later date or not.
* Fallback format set the default ordering.
* And for a particular interval pattern, the order can be
* overriden by prefixing the interval pattern with "latestFirst:" or
* "earliestFirst:"
* For example, given 2 date, Jan 10, 2007 to Feb 10, 2007.
* if the fallback format is "{0} - {1}",
* and the pattern is "d MMM - d MMM yyyy", the interval format is
* "10 Jan - 10 Feb, 2007".
* If the pattern is "latestFirst:d MMM - d MMM yyyy",
* the interval format is "10 Feb - 10 Jan, 2007"
*/
UBool laterDateFirst;
};
/**
* default constructor
* @internal ICU 4.0
*/
DateIntervalFormat();
/**
* Construct a DateIntervalFormat from DateFormat,
* a DateIntervalInfo, and skeleton.
* DateFormat provides the timezone, calendar,
* full pattern, and date format symbols information.
* It should be a SimpleDateFormat object which
* has a pattern in it.
* the DateIntervalInfo provides the interval patterns.
*
* Note: the DateIntervalFormat takes ownership of both
* DateFormat and DateIntervalInfo objects.
* Caller should not delete them.
*
* @param locale the locale of this date interval formatter.
* @param dtItvInfo the DateIntervalInfo object to be adopted.
* @param skeleton the skeleton of the date formatter
* @param status output param set to success/failure code on exit
*/
DateIntervalFormat(const Locale& locale, DateIntervalInfo* dtItvInfo,
const UnicodeString* skeleton, UErrorCode& status);
/**
* Construct a DateIntervalFormat from DateFormat
* and a DateIntervalInfo.
*
* It is a wrapper of the constructor.
*
* @param locale the locale of this date interval formatter.
* @param dtitvinf the DateIntervalInfo object to be adopted.
* @param skeleton the skeleton of this formatter.
* @param status Output param set to success/failure code.
* @return a date time interval formatter which the caller owns.
*/
static DateIntervalFormat* U_EXPORT2 create(const Locale& locale,
DateIntervalInfo* dtitvinf,
const UnicodeString* skeleton,
UErrorCode& status);
/**
* Create a simple date/time formatter from skeleton, given locale,
* and date time pattern generator.
*
* @param skeleton the skeleton on which date format based.
* @param locale the given locale.
* @param dtpng the date time pattern generator.
* @param status Output param to be set to success/failure code.
* If it is failure, the returned date formatter will
* be NULL.
* @return a simple date formatter which the caller owns.
*/
static SimpleDateFormat* U_EXPORT2 createSDFPatternInstance(
const UnicodeString& skeleton,
const Locale& locale,
DateTimePatternGenerator* dtpng,
UErrorCode& status);
/**
* Below are for generating interval patterns local to the formatter
*/
/**
* Format 2 Calendars using fall-back interval pattern
*
* The full pattern used in this fall-back format is the
* full pattern of the date formatter.
*
* @param fromCalendar calendar set to the from date in date interval
* to be formatted into date interval string
* @param toCalendar calendar set to the to date in date interval
* to be formatted into date interval string
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status output param set to success/failure code on exit
* @return Reference to 'appendTo' parameter.
*/
UnicodeString& fallbackFormat(Calendar& fromCalendar,
Calendar& toCalendar,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Initialize interval patterns locale to this formatter
*
* This code is a bit complicated since
* 1. the interval patterns saved in resource bundle files are interval
* patterns based on date or time only.
* It does not have interval patterns based on both date and time.
* Interval patterns on both date and time are algorithm generated.
*
* For example, it has interval patterns on skeleton "dMy" and "hm",
* but it does not have interval patterns on skeleton "dMyhm".
*
* The rule to generate interval patterns for both date and time skeleton are
* 1) when the year, month, or day differs, concatenate the two original
* expressions with a separator between,
* For example, interval pattern from "Jan 10, 2007 10:10 am"
* to "Jan 11, 2007 10:10am" is
* "Jan 10, 2007 10:10 am - Jan 11, 2007 10:10am"
*
* 2) otherwise, present the date followed by the range expression
* for the time.
* For example, interval pattern from "Jan 10, 2007 10:10 am"
* to "Jan 10, 2007 11:10am" is
* "Jan 10, 2007 10:10 am - 11:10am"
*
* 2. even a pattern does not request a certain calendar field,
* the interval pattern needs to include such field if such fields are
* different between 2 dates.
* For example, a pattern/skeleton is "hm", but the interval pattern
* includes year, month, and date when year, month, and date differs.
*
*
* @param status output param set to success/failure code on exit
*/
void initializePattern(UErrorCode& status);
/**
* Set fall back interval pattern given a calendar field,
* a skeleton, and a date time pattern generator.
* @param field the largest different calendar field
* @param skeleton a skeleton
* @param status output param set to success/failure code on exit
*/
void setFallbackPattern(UCalendarDateFields field,
const UnicodeString& skeleton,
UErrorCode& status);
/**
* get separated date and time skeleton from a combined skeleton.
*
* The difference between date skeleton and normalizedDateSkeleton are:
* 1. both 'y' and 'd' are appeared only once in normalizeDateSkeleton
* 2. 'E' and 'EE' are normalized into 'EEE'
* 3. 'MM' is normalized into 'M'
*
** the difference between time skeleton and normalizedTimeSkeleton are:
* 1. both 'H' and 'h' are normalized as 'h' in normalized time skeleton,
* 2. 'a' is omitted in normalized time skeleton.
* 3. there is only one appearance for 'h', 'm','v', 'z' in normalized time
* skeleton
*
*
* @param skeleton given combined skeleton.
* @param date Output parameter for date only skeleton.
* @param normalizedDate Output parameter for normalized date only
*
* @param time Output parameter for time only skeleton.
* @param normalizedTime Output parameter for normalized time only
* skeleton.
*
*/
static void U_EXPORT2 getDateTimeSkeleton(const UnicodeString& skeleton,
UnicodeString& date,
UnicodeString& normalizedDate,
UnicodeString& time,
UnicodeString& normalizedTime);
/**
* Generate date or time interval pattern from resource,
* and set them into the interval pattern locale to this formatter.
*
* It needs to handle the following:
* 1. need to adjust field width.
* For example, the interval patterns saved in DateIntervalInfo
* includes "dMMMy", but not "dMMMMy".
* Need to get interval patterns for dMMMMy from dMMMy.
* Another example, the interval patterns saved in DateIntervalInfo
* includes "hmv", but not "hmz".
* Need to get interval patterns for "hmz' from 'hmv'
*
* 2. there might be no pattern for 'y' differ for skeleton "Md",
* in order to get interval patterns for 'y' differ,
* need to look for it from skeleton 'yMd'
*
* @param dateSkeleton normalized date skeleton
* @param timeSkeleton normalized time skeleton
* @return whether the resource is found for the skeleton.
* TRUE if interval pattern found for the skeleton,
* FALSE otherwise.
*/
UBool setSeparateDateTimePtn(const UnicodeString& dateSkeleton,
const UnicodeString& timeSkeleton);
/**
* Generate interval pattern from existing resource
*
* It not only save the interval patterns,
* but also return the extended skeleton and its best match skeleton.
*
* @param field largest different calendar field
* @param skeleton skeleton
* @param bestSkeleton the best match skeleton which has interval pattern
* defined in resource
* @param differenceInfo the difference between skeleton and best skeleton
* 0 means the best matched skeleton is the same as input skeleton
* 1 means the fields are the same, but field width are different
* 2 means the only difference between fields are v/z,
* -1 means there are other fields difference
*
* @param extendedSkeleton extended skeleton
* @param extendedBestSkeleton extended best match skeleton
* @return whether the interval pattern is found
* through extending skeleton or not.
* TRUE if interval pattern is found by
* extending skeleton, FALSE otherwise.
*/
UBool setIntervalPattern(UCalendarDateFields field,
const UnicodeString* skeleton,
const UnicodeString* bestSkeleton,
int8_t differenceInfo,
UnicodeString* extendedSkeleton = NULL,
UnicodeString* extendedBestSkeleton = NULL);
/**
* Adjust field width in best match interval pattern to match
* the field width in input skeleton.
*
* TODO (xji) make a general solution
* The adjusting rule can be:
* 1. always adjust
* 2. never adjust
* 3. default adjust, which means adjust according to the following rules
* 3.1 always adjust string, such as MMM and MMMM
* 3.2 never adjust between string and numeric, such as MM and MMM
* 3.3 always adjust year
* 3.4 do not adjust 'd', 'h', or 'm' if h presents
* 3.5 do not adjust 'M' if it is numeric(?)
*
* Since date interval format is well-formed format,
* date and time skeletons are normalized previously,
* till this stage, the adjust here is only "adjust strings, such as MMM
* and MMMM, EEE and EEEE.
*
* @param inputSkeleton the input skeleton
* @param bestMatchSkeleton the best match skeleton
* @param bestMatchIntervalPattern the best match interval pattern
* @param differenceInfo the difference between 2 skeletons
* 1 means only field width differs
* 2 means v/z exchange
* @param adjustedIntervalPattern adjusted interval pattern
*/
static void U_EXPORT2 adjustFieldWidth(
const UnicodeString& inputSkeleton,
const UnicodeString& bestMatchSkeleton,
const UnicodeString& bestMatchIntervalPattern,
int8_t differenceInfo,
UnicodeString& adjustedIntervalPattern);
/**
* Concat a single date pattern with a time interval pattern,
* set it into the intervalPatterns, while field is time field.
* This is used to handle time interval patterns on skeleton with
* both time and date. Present the date followed by
* the range expression for the time.
* @param format date and time format
* @param formatLen format string length
* @param datePattern date pattern
* @param field time calendar field: AM_PM, HOUR, MINUTE
* @param status output param set to success/failure code on exit
*/
void concatSingleDate2TimeInterval(const UChar* format,
int32_t formatLen,
const UnicodeString& datePattern,
UCalendarDateFields field,
UErrorCode& status);
/**
* check whether a calendar field present in a skeleton.
* @param field calendar field need to check
* @param skeleton given skeleton on which to check the calendar field
* @return true if field present in a skeleton.
*/
static UBool U_EXPORT2 fieldExistsInSkeleton(UCalendarDateFields field,
const UnicodeString& skeleton);
/**
* Split interval patterns into 2 part.
* @param intervalPattern interval pattern
* @return the index in interval pattern which split the pattern into 2 part
*/
static int32_t U_EXPORT2 splitPatternInto2Part(const UnicodeString& intervalPattern);
/**
* Break interval patterns as 2 part and save them into pattern info.
* @param field calendar field
* @param intervalPattern interval pattern
*/
void setIntervalPattern(UCalendarDateFields field,
const UnicodeString& intervalPattern);
/**
* Break interval patterns as 2 part and save them into pattern info.
* @param field calendar field
* @param intervalPattern interval pattern
* @param laterDateFirst whether later date appear first in interval pattern
*/
void setIntervalPattern(UCalendarDateFields field,
const UnicodeString& intervalPattern,
UBool laterDateFirst);
/**
* Set pattern information.
*
* @param field calendar field
* @param firstPart the first part in interval pattern
* @param secondPart the second part in interval pattern
* @param laterDateFirst whether the first date in intervalPattern
* is earlier date or later date
*/
void setPatternInfo(UCalendarDateFields field,
const UnicodeString* firstPart,
const UnicodeString* secondPart,
UBool laterDateFirst);
// from calendar field to pattern letter
static const UChar fgCalendarFieldToPatternLetter[];
/**
* The interval patterns for this locale.
*/
DateIntervalInfo* fInfo;
/**
* The DateFormat object used to format single pattern
*/
SimpleDateFormat* fDateFormat;
/**
* The 2 calendars with the from and to date.
* could re-use the calendar in fDateFormat,
* but keeping 2 calendars make it clear and clean.
*/
Calendar* fFromCalendar;
Calendar* fToCalendar;
/**
* Date time pattern generator
*/
DateTimePatternGenerator* fDtpng;
/**
* Following are interval information relavent (locale) to this formatter.
*/
UnicodeString fSkeleton;
PatternInfo fIntervalPatterns[DateIntervalInfo::kIPI_MAX_INDEX];
};
inline UBool
DateIntervalFormat::operator!=(const Format& other) const {
return !operator==(other);
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _DTITVFMT_H__
//eof
project/jni/icuuc/include/unicode/dtitvinf.h
-514
View File
@@ -1,514 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2008-2011,2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
* File DTITVINF.H
*
*******************************************************************************
*/
#ifndef __DTITVINF_H__
#define __DTITVINF_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Date/Time interval patterns for formatting date/time interval
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/udat.h"
#include "unicode/locid.h"
#include "unicode/ucal.h"
#include "unicode/dtptngen.h"
U_NAMESPACE_BEGIN
/**
* DateIntervalInfo is a public class for encapsulating localizable
* date time interval patterns. It is used by DateIntervalFormat.
*
* <P>
* For most users, ordinary use of DateIntervalFormat does not need to create
* DateIntervalInfo object directly.
* DateIntervalFormat will take care of it when creating a date interval
* formatter when user pass in skeleton and locale.
*
* <P>
* For power users, who want to create their own date interval patterns,
* or want to re-set date interval patterns, they could do so by
* directly creating DateIntervalInfo and manupulating it.
*
* <P>
* Logically, the interval patterns are mappings
* from (skeleton, the_largest_different_calendar_field)
* to (date_interval_pattern).
*
* <P>
* A skeleton
* <ol>
* <li>
* only keeps the field pattern letter and ignores all other parts
* in a pattern, such as space, punctuations, and string literals.
* <li>
* hides the order of fields.
* <li>
* might hide a field's pattern letter length.
*
* For those non-digit calendar fields, the pattern letter length is
* important, such as MMM, MMMM, and MMMMM; EEE and EEEE,
* and the field's pattern letter length is honored.
*
* For the digit calendar fields, such as M or MM, d or dd, yy or yyyy,
* the field pattern length is ignored and the best match, which is defined
* in date time patterns, will be returned without honor the field pattern
* letter length in skeleton.
* </ol>
*
* <P>
* The calendar fields we support for interval formatting are:
* year, month, date, day-of-week, am-pm, hour, hour-of-day, and minute.
* Those calendar fields can be defined in the following order:
* year > month > date > am-pm > hour > minute
*
* The largest different calendar fields between 2 calendars is the
* first different calendar field in above order.
*
* For example: the largest different calendar fields between &quot;Jan 10, 2007&quot;
* and &quot;Feb 20, 2008&quot; is year.
*
* <P>
* There is a set of pre-defined static skeleton strings.
* There are pre-defined interval patterns for those pre-defined skeletons
* in locales' resource files.
* For example, for a skeleton UDAT_YEAR_ABBR_MONTH_DAY, which is &quot;yMMMd&quot;,
* in en_US, if the largest different calendar field between date1 and date2
* is &quot;year&quot;, the date interval pattern is &quot;MMM d, yyyy - MMM d, yyyy&quot;,
* such as &quot;Jan 10, 2007 - Jan 10, 2008&quot;.
* If the largest different calendar field between date1 and date2 is &quot;month&quot;,
* the date interval pattern is &quot;MMM d - MMM d, yyyy&quot;,
* such as &quot;Jan 10 - Feb 10, 2007&quot;.
* If the largest different calendar field between date1 and date2 is &quot;day&quot;,
* the date interval pattern is &quot;MMM d-d, yyyy&quot;, such as &quot;Jan 10-20, 2007&quot;.
*
* For date skeleton, the interval patterns when year, or month, or date is
* different are defined in resource files.
* For time skeleton, the interval patterns when am/pm, or hour, or minute is
* different are defined in resource files.
*
*
* <P>
* There are 2 dates in interval pattern. For most locales, the first date
* in an interval pattern is the earlier date. There might be a locale in which
* the first date in an interval pattern is the later date.
* We use fallback format for the default order for the locale.
* For example, if the fallback format is &quot;{0} - {1}&quot;, it means
* the first date in the interval pattern for this locale is earlier date.
* If the fallback format is &quot;{1} - {0}&quot;, it means the first date is the
* later date.
* For a particular interval pattern, the default order can be overriden
* by prefixing &quot;latestFirst:&quot; or &quot;earliestFirst:&quot; to the interval pattern.
* For example, if the fallback format is &quot;{0}-{1}&quot;,
* but for skeleton &quot;yMMMd&quot;, the interval pattern when day is different is
* &quot;latestFirst:d-d MMM yy&quot;, it means by default, the first date in interval
* pattern is the earlier date. But for skeleton &quot;yMMMd&quot;, when day is different,
* the first date in &quot;d-d MMM yy&quot; is the later date.
*
* <P>
* The recommended way to create a DateIntervalFormat object is to pass in
* the locale.
* By using a Locale parameter, the DateIntervalFormat object is
* initialized with the pre-defined interval patterns for a given or
* default locale.
* <P>
* Users can also create DateIntervalFormat object
* by supplying their own interval patterns.
* It provides flexibility for power users.
*
* <P>
* After a DateIntervalInfo object is created, clients may modify
* the interval patterns using setIntervalPattern function as so desired.
* Currently, users can only set interval patterns when the following
* calendar fields are different: ERA, YEAR, MONTH, DATE, DAY_OF_MONTH,
* DAY_OF_WEEK, AM_PM, HOUR, HOUR_OF_DAY, and MINUTE.
* Interval patterns when other calendar fields are different is not supported.
* <P>
* DateIntervalInfo objects are cloneable.
* When clients obtain a DateIntervalInfo object,
* they can feel free to modify it as necessary.
* <P>
* DateIntervalInfo are not expected to be subclassed.
* Data for a calendar is loaded out of resource bundles.
* Through ICU 4.4, date interval patterns are only supported in the Gregorian
* calendar; non-Gregorian calendars are supported from ICU 4.4.1.
* @stable ICU 4.0
**/
class U_I18N_API DateIntervalInfo : public UObject {
public:
#ifndef U_HIDE_INTERNAL_API
/**
* Default constructor.
* It does not initialize any interval patterns except
* that it initialize default fall-back pattern as "{0} - {1}",
* which can be reset by setFallbackIntervalPattern().
* It should be followed by setFallbackIntervalPattern() and
* setIntervalPattern(),
* and is recommended to be used only for power users who
* wants to create their own interval patterns and use them to create
* date interval formatter.
* @param status output param set to success/failure code on exit
* @internal ICU 4.0
*/
DateIntervalInfo(UErrorCode& status);
#endif /* U_HIDE_INTERNAL_API */
/**
* Construct DateIntervalInfo for the given locale,
* @param locale the interval patterns are loaded from the appropriate calendar
* data (specified calendar or default calendar) in this locale.
* @param status output param set to success/failure code on exit
* @stable ICU 4.0
*/
DateIntervalInfo(const Locale& locale, UErrorCode& status);
/**
* Copy constructor.
* @stable ICU 4.0
*/
DateIntervalInfo(const DateIntervalInfo&);
/**
* Assignment operator
* @stable ICU 4.0
*/
DateIntervalInfo& operator=(const DateIntervalInfo&);
/**
* Clone this object polymorphically.
* The caller owns the result and should delete it when done.
* @return a copy of the object
* @stable ICU 4.0
*/
virtual DateIntervalInfo* clone(void) const;
/**
* Destructor.
* It is virtual to be safe, but it is not designed to be subclassed.
* @stable ICU 4.0
*/
virtual ~DateIntervalInfo();
/**
* Return true if another object is semantically equal to this one.
*
* @param other the DateIntervalInfo object to be compared with.
* @return true if other is semantically equal to this.
* @stable ICU 4.0
*/
virtual UBool operator==(const DateIntervalInfo& other) const;
/**
* Return true if another object is semantically unequal to this one.
*
* @param other the DateIntervalInfo object to be compared with.
* @return true if other is semantically unequal to this.
* @stable ICU 4.0
*/
UBool operator!=(const DateIntervalInfo& other) const;
/**
* Provides a way for client to build interval patterns.
* User could construct DateIntervalInfo by providing a list of skeletons
* and their patterns.
* <P>
* For example:
* <pre>
* UErrorCode status = U_ZERO_ERROR;
* DateIntervalInfo dIntervalInfo = new DateIntervalInfo();
* dIntervalInfo->setFallbackIntervalPattern("{0} ~ {1}");
* dIntervalInfo->setIntervalPattern("yMd", UCAL_YEAR, "'from' yyyy-M-d 'to' yyyy-M-d", status);
* dIntervalInfo->setIntervalPattern("yMMMd", UCAL_MONTH, "'from' yyyy MMM d 'to' MMM d", status);
* dIntervalInfo->setIntervalPattern("yMMMd", UCAL_DAY, "yyyy MMM d-d", status, status);
* </pre>
*
* Restriction:
* Currently, users can only set interval patterns when the following
* calendar fields are different: ERA, YEAR, MONTH, DATE, DAY_OF_MONTH,
* DAY_OF_WEEK, AM_PM, HOUR, HOUR_OF_DAY, and MINUTE.
* Interval patterns when other calendar fields are different are
* not supported.
*
* @param skeleton the skeleton on which interval pattern based
* @param lrgDiffCalUnit the largest different calendar unit.
* @param intervalPattern the interval pattern on the largest different
* calendar unit.
* For example, if lrgDiffCalUnit is
* "year", the interval pattern for en_US when year
* is different could be "'from' yyyy 'to' yyyy".
* @param status output param set to success/failure code on exit
* @stable ICU 4.0
*/
void setIntervalPattern(const UnicodeString& skeleton,
UCalendarDateFields lrgDiffCalUnit,
const UnicodeString& intervalPattern,
UErrorCode& status);
/**
* Get the interval pattern given skeleton and
* the largest different calendar field.
* @param skeleton the skeleton
* @param field the largest different calendar field
* @param result output param to receive the pattern
* @param status output param set to success/failure code on exit
* @return a reference to 'result'
* @stable ICU 4.0
*/
UnicodeString& getIntervalPattern(const UnicodeString& skeleton,
UCalendarDateFields field,
UnicodeString& result,
UErrorCode& status) const;
/**
* Get the fallback interval pattern.
* @param result output param to receive the pattern
* @return a reference to 'result'
* @stable ICU 4.0
*/
UnicodeString& getFallbackIntervalPattern(UnicodeString& result) const;
/**
* Re-set the fallback interval pattern.
*
* In construction, default fallback pattern is set as "{0} - {1}".
* And constructor taking locale as parameter will set the
* fallback pattern as what defined in the locale resource file.
*
* This method provides a way for user to replace the fallback pattern.
*
* @param fallbackPattern fall-back interval pattern.
* @param status output param set to success/failure code on exit
* @stable ICU 4.0
*/
void setFallbackIntervalPattern(const UnicodeString& fallbackPattern,
UErrorCode& status);
/** Get default order -- whether the first date in pattern is later date
or not.
* return default date ordering in interval pattern. TRUE if the first date
* in pattern is later date, FALSE otherwise.
* @stable ICU 4.0
*/
UBool getDefaultOrder() const;
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 4.0
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 4.0
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
/**
* DateIntervalFormat will need access to
* getBestSkeleton(), parseSkeleton(), enum IntervalPatternIndex,
* and calendarFieldToPatternIndex().
*
* Instead of making above public,
* make DateIntervalFormat a friend of DateIntervalInfo.
*/
friend class DateIntervalFormat;
/**
* Following is for saving the interval patterns.
* We only support interval patterns on
* ERA, YEAR, MONTH, DAY, AM_PM, HOUR, and MINUTE
*/
enum IntervalPatternIndex
{
kIPI_ERA,
kIPI_YEAR,
kIPI_MONTH,
kIPI_DATE,
kIPI_AM_PM,
kIPI_HOUR,
kIPI_MINUTE,
kIPI_MAX_INDEX
};
public:
#ifndef U_HIDE_INTERNAL_API
/**
* Max index for stored interval patterns
* @internal ICU 4.4
*/
enum {
kMaxIntervalPatternIndex = kIPI_MAX_INDEX
};
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* Initialize the DateIntervalInfo from locale
* @param locale the given locale.
* @param status output param set to success/failure code on exit
*/
void initializeData(const Locale& locale, UErrorCode& status);
/* Set Interval pattern.
*
* It sets interval pattern into the hash map.
*
* @param skeleton skeleton on which the interval pattern based
* @param lrgDiffCalUnit the largest different calendar unit.
* @param intervalPattern the interval pattern on the largest different
* calendar unit.
* @param status output param set to success/failure code on exit
*/
void setIntervalPatternInternally(const UnicodeString& skeleton,
UCalendarDateFields lrgDiffCalUnit,
const UnicodeString& intervalPattern,
UErrorCode& status);
/**given an input skeleton, get the best match skeleton
* which has pre-defined interval pattern in resource file.
* Also return the difference between the input skeleton
* and the best match skeleton.
*
* TODO (xji): set field weight or
* isolate the funtionality in DateTimePatternGenerator
* @param skeleton input skeleton
* @param bestMatchDistanceInfo the difference between input skeleton
* and best match skeleton.
* 0, if there is exact match for input skeleton
* 1, if there is only field width difference between
* the best match and the input skeleton
* 2, the only field difference is 'v' and 'z'
* -1, if there is calendar field difference between
* the best match and the input skeleton
* @return best match skeleton
*/
const UnicodeString* getBestSkeleton(const UnicodeString& skeleton,
int8_t& bestMatchDistanceInfo) const;
/**
* Parse skeleton, save each field's width.
* It is used for looking for best match skeleton,
* and adjust pattern field width.
* @param skeleton skeleton to be parsed
* @param skeletonFieldWidth parsed skeleton field width
*/
static void U_EXPORT2 parseSkeleton(const UnicodeString& skeleton,
int32_t* skeletonFieldWidth);
/**
* Check whether one field width is numeric while the other is string.
*
* TODO (xji): make it general
*
* @param fieldWidth one field width
* @param anotherFieldWidth another field width
* @param patternLetter pattern letter char
* @return true if one field width is numeric and the other is string,
* false otherwise.
*/
static UBool U_EXPORT2 stringNumeric(int32_t fieldWidth,
int32_t anotherFieldWidth,
char patternLetter);
/**
* Convert calendar field to the interval pattern index in
* hash table.
*
* Since we only support the following calendar fields:
* ERA, YEAR, MONTH, DATE, DAY_OF_MONTH, DAY_OF_WEEK,
* AM_PM, HOUR, HOUR_OF_DAY, and MINUTE,
* We reserve only 4 interval patterns for a skeleton.
*
* @param field calendar field
* @param status output param set to success/failure code on exit
* @return interval pattern index in hash table
*/
static IntervalPatternIndex U_EXPORT2 calendarFieldToIntervalIndex(
UCalendarDateFields field,
UErrorCode& status);
/**
* delete hash table (of type fIntervalPatterns).
*
* @param hTable hash table to be deleted
*/
void deleteHash(Hashtable* hTable);
/**
* initialize hash table (of type fIntervalPatterns).
*
* @param status output param set to success/failure code on exit
* @return hash table initialized
*/
Hashtable* initHash(UErrorCode& status);
/**
* copy hash table (of type fIntervalPatterns).
*
* @param source the source to copy from
* @param target the target to copy to
* @param status output param set to success/failure code on exit
*/
void copyHash(const Hashtable* source, Hashtable* target, UErrorCode& status);
// data members
// fallback interval pattern
UnicodeString fFallbackIntervalPattern;
// default order
UBool fFirstDateInPtnIsLaterDate;
// HashMap<UnicodeString, UnicodeString[kIPI_MAX_INDEX]>
// HashMap( skeleton, pattern[largest_different_field] )
Hashtable* fIntervalPatterns;
};// end class DateIntervalInfo
inline UBool
DateIntervalInfo::operator!=(const DateIntervalInfo& other) const {
return !operator==(other);
}
U_NAMESPACE_END
#endif
#endif
project/jni/icuuc/include/unicode/dtptngen.h
-498
View File
@@ -1,498 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2007-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
* File DTPTNGEN.H
*
*******************************************************************************
*/
#ifndef __DTPTNGEN_H__
#define __DTPTNGEN_H__
#include "unicode/datefmt.h"
#include "unicode/locid.h"
#include "unicode/udat.h"
#include "unicode/udatpg.h"
U_NAMESPACE_BEGIN
/**
* \file
* \brief C++ API: Date/Time Pattern Generator
*/
class Hashtable;
class FormatParser;
class DateTimeMatcher;
class DistanceInfo;
class PatternMap;
class PtnSkeleton;
/**
* This class provides flexible generation of date format patterns, like "yy-MM-dd".
* The user can build up the generator by adding successive patterns. Once that
* is done, a query can be made using a "skeleton", which is a pattern which just
* includes the desired fields and lengths. The generator will return the "best fit"
* pattern corresponding to that skeleton.
* <p>The main method people will use is getBestPattern(String skeleton),
* since normally this class is pre-built with data from a particular locale.
* However, generators can be built directly from other data as well.
* <p><i>Issue: may be useful to also have a function that returns the list of
* fields in a pattern, in order, since we have that internally.
* That would be useful for getting the UI order of field elements.</i>
* @stable ICU 3.8
**/
class U_I18N_API DateTimePatternGenerator : public UObject {
public:
/**
* Construct a flexible generator according to default locale.
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @stable ICU 3.8
*/
static DateTimePatternGenerator* U_EXPORT2 createInstance(UErrorCode& status);
/**
* Construct a flexible generator according to data for a given locale.
* @param uLocale
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @stable ICU 3.8
*/
static DateTimePatternGenerator* U_EXPORT2 createInstance(const Locale& uLocale, UErrorCode& status);
/**
* Create an empty generator, to be constructed with addPattern(...) etc.
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @stable ICU 3.8
*/
static DateTimePatternGenerator* U_EXPORT2 createEmptyInstance(UErrorCode& status);
/**
* Destructor.
* @stable ICU 3.8
*/
virtual ~DateTimePatternGenerator();
/**
* Clone DateTimePatternGenerator object. Clients are responsible for
* deleting the DateTimePatternGenerator object cloned.
* @stable ICU 3.8
*/
DateTimePatternGenerator* clone() const;
/**
* Return true if another object is semantically equal to this one.
*
* @param other the DateTimePatternGenerator object to be compared with.
* @return true if other is semantically equal to this.
* @stable ICU 3.8
*/
UBool operator==(const DateTimePatternGenerator& other) const;
/**
* Return true if another object is semantically unequal to this one.
*
* @param other the DateTimePatternGenerator object to be compared with.
* @return true if other is semantically unequal to this.
* @stable ICU 3.8
*/
UBool operator!=(const DateTimePatternGenerator& other) const;
/**
* Utility to return a unique skeleton from a given pattern. For example,
* both "MMM-dd" and "dd/MMM" produce the skeleton "MMMdd".
*
* @param pattern Input pattern, such as "dd/MMM"
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return skeleton such as "MMMdd"
* @stable ICU 3.8
*/
UnicodeString getSkeleton(const UnicodeString& pattern, UErrorCode& status);
/**
* Utility to return a unique base skeleton from a given pattern. This is
* the same as the skeleton, except that differences in length are minimized
* so as to only preserve the difference between string and numeric form. So
* for example, both "MMM-dd" and "d/MMM" produce the skeleton "MMMd"
* (notice the single d).
*
* @param pattern Input pattern, such as "dd/MMM"
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return base skeleton, such as "Md"
* @stable ICU 3.8
*/
UnicodeString getBaseSkeleton(const UnicodeString& pattern, UErrorCode& status);
/**
* Adds a pattern to the generator. If the pattern has the same skeleton as
* an existing pattern, and the override parameter is set, then the previous
* value is overriden. Otherwise, the previous value is retained. In either
* case, the conflicting status is set and previous vale is stored in
* conflicting pattern.
* <p>
* Note that single-field patterns (like "MMM") are automatically added, and
* don't need to be added explicitly!
*
* @param pattern Input pattern, such as "dd/MMM"
* @param override When existing values are to be overridden use true,
* otherwise use false.
* @param conflictingPattern Previous pattern with the same skeleton.
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return conflicting status. The value could be UDATPG_NO_CONFLICT,
* UDATPG_BASE_CONFLICT or UDATPG_CONFLICT.
* @stable ICU 3.8
* <p>
* <h4>Sample code</h4>
* \snippet samples/dtptngsample/dtptngsample.cpp getBestPatternExample1
* \snippet samples/dtptngsample/dtptngsample.cpp addPatternExample
* <p>
*/
UDateTimePatternConflict addPattern(const UnicodeString& pattern,
UBool override,
UnicodeString& conflictingPattern,
UErrorCode& status);
/**
* An AppendItem format is a pattern used to append a field if there is no
* good match. For example, suppose that the input skeleton is "GyyyyMMMd",
* and there is no matching pattern internally, but there is a pattern
* matching "yyyyMMMd", say "d-MM-yyyy". Then that pattern is used, plus the
* G. The way these two are conjoined is by using the AppendItemFormat for G
* (era). So if that value is, say "{0}, {1}" then the final resulting
* pattern is "d-MM-yyyy, G".
* <p>
* There are actually three available variables: {0} is the pattern so far,
* {1} is the element we are adding, and {2} is the name of the element.
* <p>
* This reflects the way that the CLDR data is organized.
*
* @param field such as UDATPG_ERA_FIELD.
* @param value pattern, such as "{0}, {1}"
* @stable ICU 3.8
*/
void setAppendItemFormat(UDateTimePatternField field, const UnicodeString& value);
/**
* Getter corresponding to setAppendItemFormat. Values below 0 or at or
* above UDATPG_FIELD_COUNT are illegal arguments.
*
* @param field such as UDATPG_ERA_FIELD.
* @return append pattern for field
* @stable ICU 3.8
*/
const UnicodeString& getAppendItemFormat(UDateTimePatternField field) const;
/**
* Sets the names of field, eg "era" in English for ERA. These are only
* used if the corresponding AppendItemFormat is used, and if it contains a
* {2} variable.
* <p>
* This reflects the way that the CLDR data is organized.
*
* @param field such as UDATPG_ERA_FIELD.
* @param value name of the field
* @stable ICU 3.8
*/
void setAppendItemName(UDateTimePatternField field, const UnicodeString& value);
/**
* Getter corresponding to setAppendItemNames. Values below 0 or at or above
* UDATPG_FIELD_COUNT are illegal arguments.
*
* @param field such as UDATPG_ERA_FIELD.
* @return name for field
* @stable ICU 3.8
*/
const UnicodeString& getAppendItemName(UDateTimePatternField field) const;
/**
* The date time format is a message format pattern used to compose date and
* time patterns. The default value is "{0} {1}", where {0} will be replaced
* by the date pattern and {1} will be replaced by the time pattern.
* <p>
* This is used when the input skeleton contains both date and time fields,
* but there is not a close match among the added patterns. For example,
* suppose that this object was created by adding "dd-MMM" and "hh:mm", and
* its datetimeFormat is the default "{0} {1}". Then if the input skeleton
* is "MMMdhmm", there is not an exact match, so the input skeleton is
* broken up into two components "MMMd" and "hmm". There are close matches
* for those two skeletons, so the result is put together with this pattern,
* resulting in "d-MMM h:mm".
*
* @param dateTimeFormat
* message format pattern, here {0} will be replaced by the date
* pattern and {1} will be replaced by the time pattern.
* @stable ICU 3.8
*/
void setDateTimeFormat(const UnicodeString& dateTimeFormat);
/**
* Getter corresponding to setDateTimeFormat.
* @return DateTimeFormat.
* @stable ICU 3.8
*/
const UnicodeString& getDateTimeFormat() const;
/**
* Return the best pattern matching the input skeleton. It is guaranteed to
* have all of the fields in the skeleton.
*
* @param skeleton
* The skeleton is a pattern containing only the variable fields.
* For example, "MMMdd" and "mmhh" are skeletons.
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return bestPattern
* The best pattern found from the given skeleton.
* @stable ICU 3.8
* <p>
* <h4>Sample code</h4>
* \snippet samples/dtptngsample/dtptngsample.cpp getBestPatternExample1
* \snippet samples/dtptngsample/dtptngsample.cpp getBestPatternExample
* <p>
*/
UnicodeString getBestPattern(const UnicodeString& skeleton, UErrorCode& status);
/**
* Return the best pattern matching the input skeleton. It is guaranteed to
* have all of the fields in the skeleton.
*
* @param skeleton
* The skeleton is a pattern containing only the variable fields.
* For example, "MMMdd" and "mmhh" are skeletons.
* @param options
* Options for forcing the length of specified fields in the
* returned pattern to match those in the skeleton (when this
* would not happen otherwise). For default behavior, use
* UDATPG_MATCH_NO_OPTIONS.
* @param status
* Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return bestPattern
* The best pattern found from the given skeleton.
* @stable ICU 4.4
*/
UnicodeString getBestPattern(const UnicodeString& skeleton,
UDateTimePatternMatchOptions options,
UErrorCode& status);
/**
* Adjusts the field types (width and subtype) of a pattern to match what is
* in a skeleton. That is, if you supply a pattern like "d-M H:m", and a
* skeleton of "MMMMddhhmm", then the input pattern is adjusted to be
* "dd-MMMM hh:mm". This is used internally to get the best match for the
* input skeleton, but can also be used externally.
*
* @param pattern Input pattern
* @param skeleton
* The skeleton is a pattern containing only the variable fields.
* For example, "MMMdd" and "mmhh" are skeletons.
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return pattern adjusted to match the skeleton fields widths and subtypes.
* @stable ICU 3.8
* <p>
* <h4>Sample code</h4>
* \snippet samples/dtptngsample/dtptngsample.cpp getBestPatternExample1
* \snippet samples/dtptngsample/dtptngsample.cpp replaceFieldTypesExample
* <p>
*/
UnicodeString replaceFieldTypes(const UnicodeString& pattern,
const UnicodeString& skeleton,
UErrorCode& status);
/**
* Adjusts the field types (width and subtype) of a pattern to match what is
* in a skeleton. That is, if you supply a pattern like "d-M H:m", and a
* skeleton of "MMMMddhhmm", then the input pattern is adjusted to be
* "dd-MMMM hh:mm". This is used internally to get the best match for the
* input skeleton, but can also be used externally.
*
* @param pattern Input pattern
* @param skeleton
* The skeleton is a pattern containing only the variable fields.
* For example, "MMMdd" and "mmhh" are skeletons.
* @param options
* Options controlling whether the length of specified fields in the
* pattern are adjusted to match those in the skeleton (when this
* would not happen otherwise). For default behavior, use
* UDATPG_MATCH_NO_OPTIONS.
* @param status
* Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return pattern adjusted to match the skeleton fields widths and subtypes.
* @stable ICU 4.4
*/
UnicodeString replaceFieldTypes(const UnicodeString& pattern,
const UnicodeString& skeleton,
UDateTimePatternMatchOptions options,
UErrorCode& status);
/**
* Return a list of all the skeletons (in canonical form) from this class.
*
* Call getPatternForSkeleton() to get the corresponding pattern.
*
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return StringEnumeration with the skeletons.
* The caller must delete the object.
* @stable ICU 3.8
*/
StringEnumeration* getSkeletons(UErrorCode& status) const;
/**
* Get the pattern corresponding to a given skeleton.
* @param skeleton
* @return pattern corresponding to a given skeleton.
* @stable ICU 3.8
*/
const UnicodeString& getPatternForSkeleton(const UnicodeString& skeleton) const;
/**
* Return a list of all the base skeletons (in canonical form) from this class.
*
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return a StringEnumeration with the base skeletons.
* The caller must delete the object.
* @stable ICU 3.8
*/
StringEnumeration* getBaseSkeletons(UErrorCode& status) const;
#ifndef U_HIDE_INTERNAL_API
/**
* Return a list of redundant patterns are those which if removed, make no
* difference in the resulting getBestPattern values. This method returns a
* list of them, to help check the consistency of the patterns used to build
* this generator.
*
* @param status Output param set to success/failure code on exit,
* which must not indicate a failure before the function call.
* @return a StringEnumeration with the redundant pattern.
* The caller must delete the object.
* @internal ICU 3.8
*/
StringEnumeration* getRedundants(UErrorCode& status);
#endif /* U_HIDE_INTERNAL_API */
/**
* The decimal value is used in formatting fractions of seconds. If the
* skeleton contains fractional seconds, then this is used with the
* fractional seconds. For example, suppose that the input pattern is
* "hhmmssSSSS", and the best matching pattern internally is "H:mm:ss", and
* the decimal string is ",". Then the resulting pattern is modified to be
* "H:mm:ss,SSSS"
*
* @param decimal
* @stable ICU 3.8
*/
void setDecimal(const UnicodeString& decimal);
/**
* Getter corresponding to setDecimal.
* @return UnicodeString corresponding to the decimal point
* @stable ICU 3.8
*/
const UnicodeString& getDecimal() const;
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 3.8
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 3.8
*/
static UClassID U_EXPORT2 getStaticClassID(void);
private:
/**
* Constructor.
* @stable ICU 3.8
*/
DateTimePatternGenerator(UErrorCode & status);
/**
* Constructor.
* @stable ICU 3.8
*/
DateTimePatternGenerator(const Locale& locale, UErrorCode & status);
/**
* Copy constructor.
* @param other DateTimePatternGenerator to copy
* @stable ICU 3.8
*/
DateTimePatternGenerator(const DateTimePatternGenerator& other);
/**
* Default assignment operator.
* @param other DateTimePatternGenerator to copy
* @stable ICU 3.8
*/
DateTimePatternGenerator& operator=(const DateTimePatternGenerator& other);
Locale pLocale; // pattern locale
FormatParser *fp;
DateTimeMatcher* dtMatcher;
DistanceInfo *distanceInfo;
PatternMap *patternMap;
UnicodeString appendItemFormats[UDATPG_FIELD_COUNT];
UnicodeString appendItemNames[UDATPG_FIELD_COUNT];
UnicodeString dateTimeFormat;
UnicodeString decimal;
DateTimeMatcher *skipMatcher;
Hashtable *fAvailableFormatKeyHash;
UnicodeString hackPattern;
UnicodeString emptyString;
UChar fDefaultHourFormatChar;
/* internal flags masks for adjustFieldTypes etc. */
enum {
kDTPGNoFlags = 0,
kDTPGFixFractionalSeconds = 1,
kDTPGSkeletonUsesCapJ = 2
};
void initData(const Locale &locale, UErrorCode &status);
void addCanonicalItems();
void addICUPatterns(const Locale& locale, UErrorCode& status);
void hackTimes(const UnicodeString& hackPattern, UErrorCode& status);
void addCLDRData(const Locale& locale, UErrorCode& status);
UDateTimePatternConflict addPatternWithSkeleton(const UnicodeString& pattern, const UnicodeString * skeletonToUse, UBool override, UnicodeString& conflictingPattern, UErrorCode& status);
void initHashtable(UErrorCode& status);
void setDateTimeFromCalendar(const Locale& locale, UErrorCode& status);
void setDecimalSymbols(const Locale& locale, UErrorCode& status);
UDateTimePatternField getAppendFormatNumber(const char* field) const;
UDateTimePatternField getAppendNameNumber(const char* field) const;
void getAppendName(UDateTimePatternField field, UnicodeString& value);
int32_t getCanonicalIndex(const UnicodeString& field);
const UnicodeString* getBestRaw(DateTimeMatcher& source, int32_t includeMask, DistanceInfo* missingFields, const PtnSkeleton** specifiedSkeletonPtr = 0);
UnicodeString adjustFieldTypes(const UnicodeString& pattern, const PtnSkeleton* specifiedSkeleton, int32_t flags, UDateTimePatternMatchOptions options = UDATPG_MATCH_NO_OPTIONS);
UnicodeString getBestAppending(int32_t missingFields, int32_t flags, UDateTimePatternMatchOptions options = UDATPG_MATCH_NO_OPTIONS);
int32_t getTopBitNumber(int32_t foundMask);
void setAvailableFormat(const UnicodeString &key, UErrorCode& status);
UBool isAvailableFormatSet(const UnicodeString &key) const;
void copyHashtable(Hashtable *other, UErrorCode &status);
UBool isCanonicalItem(const UnicodeString& item) const;
} ;// end class DateTimePatternGenerator
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/dtrule.h
-250
View File
@@ -1,250 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2007-2008, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
#ifndef DTRULE_H
#define DTRULE_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Rule for specifying date and time in an year
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* <code>DateTimeRule</code> is a class representing a time in a year by
* a rule specified by month, day of month, day of week and
* time in the day.
*
* @stable ICU 3.8
*/
class U_I18N_API DateTimeRule : public UObject {
public:
/**
* Date rule type constants.
* @stable ICU 3.8
*/
enum DateRuleType {
DOM = 0, /**< The exact day of month,
for example, March 11. */
DOW, /**< The Nth occurence of the day of week,
for example, 2nd Sunday in March. */
DOW_GEQ_DOM, /**< The first occurence of the day of week on or after the day of monnth,
for example, first Sunday on or after March 8. */
DOW_LEQ_DOM /**< The last occurence of the day of week on or before the day of month,
for example, first Sunday on or before March 14. */
};
/**
* Time rule type constants.
* @stable ICU 3.8
*/
enum TimeRuleType {
WALL_TIME = 0, /**< The local wall clock time */
STANDARD_TIME, /**< The local standard time */
UTC_TIME /**< The UTC time */
};
/**
* Constructs a <code>DateTimeRule</code> by the day of month and
* the time rule. The date rule type for an instance created by
* this constructor is <code>DOM</code>.
*
* @param month The rule month, for example, <code>Calendar::JANUARY</code>
* @param dayOfMonth The day of month, 1-based.
* @param millisInDay The milliseconds in the rule date.
* @param timeType The time type, <code>WALL_TIME</code> or <code>STANDARD_TIME</code>
* or <code>UTC_TIME</code>.
* @stable ICU 3.8
*/
DateTimeRule(int32_t month, int32_t dayOfMonth,
int32_t millisInDay, TimeRuleType timeType);
/**
* Constructs a <code>DateTimeRule</code> by the day of week and its oridinal
* number and the time rule. The date rule type for an instance created
* by this constructor is <code>DOW</code>.
*
* @param month The rule month, for example, <code>Calendar::JANUARY</code>.
* @param weekInMonth The ordinal number of the day of week. Negative number
* may be used for specifying a rule date counted from the
* end of the rule month.
* @param dayOfWeek The day of week, for example, <code>Calendar::SUNDAY</code>.
* @param millisInDay The milliseconds in the rule date.
* @param timeType The time type, <code>WALL_TIME</code> or <code>STANDARD_TIME</code>
* or <code>UTC_TIME</code>.
* @stable ICU 3.8
*/
DateTimeRule(int32_t month, int32_t weekInMonth, int32_t dayOfWeek,
int32_t millisInDay, TimeRuleType timeType);
/**
* Constructs a <code>DateTimeRule</code> by the first/last day of week
* on or after/before the day of month and the time rule. The date rule
* type for an instance created by this constructor is either
* <code>DOM_GEQ_DOM</code> or <code>DOM_LEQ_DOM</code>.
*
* @param month The rule month, for example, <code>Calendar::JANUARY</code>
* @param dayOfMonth The day of month, 1-based.
* @param dayOfWeek The day of week, for example, <code>Calendar::SUNDAY</code>.
* @param after true if the rule date is on or after the day of month.
* @param millisInDay The milliseconds in the rule date.
* @param timeType The time type, <code>WALL_TIME</code> or <code>STANDARD_TIME</code>
* or <code>UTC_TIME</code>.
* @stable ICU 3.8
*/
DateTimeRule(int32_t month, int32_t dayOfMonth, int32_t dayOfWeek, UBool after,
int32_t millisInDay, TimeRuleType timeType);
/**
* Copy constructor.
* @param source The DateTimeRule object to be copied.
* @stable ICU 3.8
*/
DateTimeRule(const DateTimeRule& source);
/**
* Destructor.
* @stable ICU 3.8
*/
~DateTimeRule();
/**
* Clone this DateTimeRule object polymorphically. The caller owns the result and
* should delete it when done.
* @return A copy of the object.
* @stable ICU 3.8
*/
DateTimeRule* clone(void) const;
/**
* Assignment operator.
* @param right The object to be copied.
* @stable ICU 3.8
*/
DateTimeRule& operator=(const DateTimeRule& right);
/**
* Return true if the given DateTimeRule objects are semantically equal. Objects
* of different subclasses are considered unequal.
* @param that The object to be compared with.
* @return true if the given DateTimeRule objects are semantically equal.
* @stable ICU 3.8
*/
UBool operator==(const DateTimeRule& that) const;
/**
* Return true if the given DateTimeRule objects are semantically unequal. Objects
* of different subclasses are considered unequal.
* @param that The object to be compared with.
* @return true if the given DateTimeRule objects are semantically unequal.
* @stable ICU 3.8
*/
UBool operator!=(const DateTimeRule& that) const;
/**
* Gets the date rule type, such as <code>DOM</code>
* @return The date rule type.
* @stable ICU 3.8
*/
DateRuleType getDateRuleType(void) const;
/**
* Gets the time rule type
* @return The time rule type, either <code>WALL_TIME</code> or <code>STANDARD_TIME</code>
* or <code>UTC_TIME</code>.
* @stable ICU 3.8
*/
TimeRuleType getTimeRuleType(void) const;
/**
* Gets the rule month.
* @return The rule month.
* @stable ICU 3.8
*/
int32_t getRuleMonth(void) const;
/**
* Gets the rule day of month. When the date rule type
* is <code>DOW</code>, the value is always 0.
* @return The rule day of month
* @stable ICU 3.8
*/
int32_t getRuleDayOfMonth(void) const;
/**
* Gets the rule day of week. When the date rule type
* is <code>DOM</code>, the value is always 0.
* @return The rule day of week.
* @stable ICU 3.8
*/
int32_t getRuleDayOfWeek(void) const;
/**
* Gets the ordinal number of the occurence of the day of week
* in the month. When the date rule type is not <code>DOW</code>,
* the value is always 0.
* @return The rule day of week ordinal number in the month.
* @stable ICU 3.8
*/
int32_t getRuleWeekInMonth(void) const;
/**
* Gets the rule time in the rule day.
* @return The time in the rule day in milliseconds.
* @stable ICU 3.8
*/
int32_t getRuleMillisInDay(void) const;
private:
int32_t fMonth;
int32_t fDayOfMonth;
int32_t fDayOfWeek;
int32_t fWeekInMonth;
int32_t fMillisInDay;
DateRuleType fDateRuleType;
TimeRuleType fTimeRuleType;
public:
/**
* Return the class ID for this class. This is useful only for comparing to
* a return value from getDynamicClassID(). For example:
* <pre>
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . erived::getStaticClassID()) ...
* </pre>
* @return The class ID for all objects of this class.
* @stable ICU 3.8
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This
* method is to implement a simple version of RTTI, since not all C++
* compilers support genuine RTTI. Polymorphic operator==() and clone()
* methods call this method.
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @stable ICU 3.8
*/
virtual UClassID getDynamicClassID(void) const;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // DTRULE_H
//eof
project/jni/icuuc/include/unicode/enumset.h
-61
View File
@@ -1,61 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 2012, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*/
/**
* \file
* \brief C++: internal template EnumSet<>
*/
#ifndef ENUMSET_H
#define ENUMSET_H
#include "unicode/utypes.h"
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* enum bitset for boolean fields. Similar to Java EnumSet<>.
* Needs to range check.
* @internal
*/
template<typename T, uint32_t minValue, uint32_t limitValue>
class EnumSet {
public:
inline EnumSet() : fBools(0) {}
inline EnumSet(const EnumSet<T,minValue,limitValue>& other) : fBools(other.fBools) {}
inline ~EnumSet() {}
inline void clear() { fBools=0; }
inline void add(T toAdd) { set(toAdd, 1); }
inline void remove(T toRemove) { set(toRemove, 0); }
inline int32_t contains(T toCheck) const { return get(toCheck); }
inline void set(T toSet, int32_t v) { fBools=(fBools&(~flag(toSet)))|(v?(flag(toSet)):0); }
inline int32_t get(T toCheck) const { return (fBools & flag(toCheck))?1:0; }
inline UBool isValidEnum(T toCheck) const { return (toCheck>=minValue&&toCheck<limitValue); }
inline UBool isValidValue(int32_t v) const { return (v==0||v==1); }
inline const EnumSet<T,minValue,limitValue>& operator=(const EnumSet<T,minValue,limitValue>& other) {
fBools = other.fBools;
return *this;
}
inline uint32_t getAll() const {
return fBools;
}
private:
inline uint32_t flag(T toCheck) const { return (1<<(toCheck-minValue)); }
private:
uint32_t fBools;
};
U_NAMESPACE_END
#endif /* U_SHOW_CPLUSPLUS_API */
#endif /* ENUMSET_H */
project/jni/icuuc/include/unicode/errorcode.h
-137
View File
@@ -1,137 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2009-2011, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: errorcode.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2009mar10
* created by: Markus W. Scherer
*/
#ifndef __ERRORCODE_H__
#define __ERRORCODE_H__
/**
* \file
* \brief C++ API: ErrorCode class intended to make it easier to use
* ICU C and C++ APIs from C++ user code.
*/
#include "unicode/utypes.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* Wrapper class for UErrorCode, with conversion operators for direct use
* in ICU C and C++ APIs.
* Intended to be used as a base class, where a subclass overrides
* the handleFailure() function so that it throws an exception,
* does an assert(), logs an error, etc.
* This is not an abstract base class. This class can be used and instantiated
* by itself, although it will be more useful when subclassed.
*
* Features:
* - The constructor initializes the internal UErrorCode to U_ZERO_ERROR,
* removing one common source of errors.
* - Same use in C APIs taking a UErrorCode * (pointer)
* and C++ taking UErrorCode & (reference) via conversion operators.
* - Possible automatic checking for success when it goes out of scope.
*
* Note: For automatic checking for success in the destructor, a subclass
* must implement such logic in its own destructor because the base class
* destructor cannot call a subclass function (like handleFailure()).
* The ErrorCode base class destructor does nothing.
*
* Note also: While it is possible for a destructor to throw an exception,
* it is generally unsafe to do so. This means that in a subclass the destructor
* and the handleFailure() function may need to take different actions.
*
* Sample code:
* \code
* class IcuErrorCode: public icu::ErrorCode {
* public:
* virtual ~IcuErrorCode() { // should be defined in .cpp as "key function"
* // Safe because our handleFailure() does not throw exceptions.
* if(isFailure()) { handleFailure(); }
* }
* protected:
* virtual void handleFailure() const {
* log_failure(u_errorName(errorCode));
* exit(errorCode);
* }
* };
* IcuErrorCode error_code;
* UConverter *cnv = ucnv_open("Shift-JIS", error_code);
* length = ucnv_fromUChars(dest, capacity, src, length, error_code);
* ucnv_close(cnv);
* // IcuErrorCode destructor checks for success.
* \endcode
*
* @stable ICU 4.2
*/
class U_COMMON_API ErrorCode: public UMemory {
public:
/**
* Default constructor. Initializes its UErrorCode to U_ZERO_ERROR.
* @stable ICU 4.2
*/
ErrorCode() : errorCode(U_ZERO_ERROR) {}
/** Destructor, does nothing. See class documentation for details. @stable ICU 4.2 */
virtual ~ErrorCode();
/** Conversion operator, returns a reference. @stable ICU 4.2 */
operator UErrorCode & () { return errorCode; }
/** Conversion operator, returns a pointer. @stable ICU 4.2 */
operator UErrorCode * () { return &errorCode; }
/** Tests for U_SUCCESS(). @stable ICU 4.2 */
UBool isSuccess() const { return U_SUCCESS(errorCode); }
/** Tests for U_FAILURE(). @stable ICU 4.2 */
UBool isFailure() const { return U_FAILURE(errorCode); }
/** Returns the UErrorCode value. @stable ICU 4.2 */
UErrorCode get() const { return errorCode; }
/** Sets the UErrorCode value. @stable ICU 4.2 */
void set(UErrorCode value) { errorCode=value; }
/** Returns the UErrorCode value and resets it to U_ZERO_ERROR. @stable ICU 4.2 */
UErrorCode reset();
/**
* Asserts isSuccess().
* In other words, this method checks for a failure code,
* and the base class handles it like this:
* \code
* if(isFailure()) { handleFailure(); }
* \endcode
* @stable ICU 4.4
*/
void assertSuccess() const;
/**
* Return a string for the UErrorCode value.
* The string will be the same as the name of the error code constant
* in the UErrorCode enum.
* @stable ICU 4.4
*/
const char* errorName() const;
protected:
/**
* Internal UErrorCode, accessible to subclasses.
* @stable ICU 4.2
*/
UErrorCode errorCode;
/**
* Called by assertSuccess() if isFailure() is true.
* A subclass should override this function to deal with a failure code:
* Throw an exception, log an error, terminate the program, or similar.
* @stable ICU 4.2
*/
virtual void handleFailure() const {}
};
U_NAMESPACE_END
#endif // __ERRORCODE_H__
project/jni/icuuc/include/unicode/fieldpos.h
-291
View File
@@ -1,291 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2006, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File FIELDPOS.H
*
* Modification History:
*
* Date Name Description
* 02/25/97 aliu Converted from java.
* 03/17/97 clhuang Updated per Format implementation.
* 07/17/98 stephen Added default/copy ctors, and operators =, ==, !=
********************************************************************************
*/
// *****************************************************************************
// This file was generated from the java source file FieldPosition.java
// *****************************************************************************
#ifndef FIELDPOS_H
#define FIELDPOS_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: FieldPosition identifies the fields in a formatted output.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* <code>FieldPosition</code> is a simple class used by <code>Format</code>
* and its subclasses to identify fields in formatted output. Fields are
* identified by constants, whose names typically end with <code>_FIELD</code>,
* defined in the various subclasses of <code>Format</code>. See
* <code>ERA_FIELD</code> and its friends in <code>DateFormat</code> for
* an example.
*
* <p>
* <code>FieldPosition</code> keeps track of the position of the
* field within the formatted output with two indices: the index
* of the first character of the field and the index of the last
* character of the field.
*
* <p>
* One version of the <code>format</code> method in the various
* <code>Format</code> classes requires a <code>FieldPosition</code>
* object as an argument. You use this <code>format</code> method
* to perform partial formatting or to get information about the
* formatted output (such as the position of a field).
*
* The FieldPosition class is not suitable for subclassing.
*
* <p>
* Below is an example of using <code>FieldPosition</code> to aid
* alignment of an array of formatted floating-point numbers on
* their decimal points:
* <pre>
* \code
* double doubleNum[] = {123456789.0, -12345678.9, 1234567.89, -123456.789,
* 12345.6789, -1234.56789, 123.456789, -12.3456789, 1.23456789};
* int dNumSize = (int)(sizeof(doubleNum)/sizeof(double));
*
* UErrorCode status = U_ZERO_ERROR;
* DecimalFormat* fmt = (DecimalFormat*) NumberFormat::createInstance(status);
* fmt->setDecimalSeparatorAlwaysShown(true);
*
* const int tempLen = 20;
* char temp[tempLen];
*
* for (int i=0; i<dNumSize; i++) {
* FieldPosition pos(NumberFormat::INTEGER_FIELD);
* UnicodeString buf;
* char fmtText[tempLen];
* ToCharString(fmt->format(doubleNum[i], buf, pos), fmtText);
* for (int j=0; j<tempLen; j++) temp[j] = ' '; // clear with spaces
* temp[__min(tempLen, tempLen-pos.getEndIndex())] = '\0';
* cout << temp << fmtText << endl;
* }
* delete fmt;
* \endcode
* </pre>
* <p>
* The code will generate the following output:
* <pre>
* \code
* 123,456,789.000
* -12,345,678.900
* 1,234,567.880
* -123,456.789
* 12,345.678
* -1,234.567
* 123.456
* -12.345
* 1.234
* \endcode
* </pre>
*/
class U_I18N_API FieldPosition : public UObject {
public:
/**
* DONT_CARE may be specified as the field to indicate that the
* caller doesn't need to specify a field. Do not subclass.
*/
enum { DONT_CARE = -1 };
/**
* Creates a FieldPosition object with a non-specified field.
* @stable ICU 2.0
*/
FieldPosition()
: UObject(), fField(DONT_CARE), fBeginIndex(0), fEndIndex(0) {}
/**
* Creates a FieldPosition object for the given field. Fields are
* identified by constants, whose names typically end with _FIELD,
* in the various subclasses of Format.
*
* @see NumberFormat#INTEGER_FIELD
* @see NumberFormat#FRACTION_FIELD
* @see DateFormat#YEAR_FIELD
* @see DateFormat#MONTH_FIELD
* @stable ICU 2.0
*/
FieldPosition(int32_t field)
: UObject(), fField(field), fBeginIndex(0), fEndIndex(0) {}
/**
* Copy constructor
* @param copy the object to be copied from.
* @stable ICU 2.0
*/
FieldPosition(const FieldPosition& copy)
: UObject(copy), fField(copy.fField), fBeginIndex(copy.fBeginIndex), fEndIndex(copy.fEndIndex) {}
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~FieldPosition();
/**
* Assignment operator
* @param copy the object to be copied from.
* @stable ICU 2.0
*/
FieldPosition& operator=(const FieldPosition& copy);
/**
* Equality operator.
* @param that the object to be compared with.
* @return TRUE if the two field positions are equal, FALSE otherwise.
* @stable ICU 2.0
*/
UBool operator==(const FieldPosition& that) const;
/**
* Equality operator.
* @param that the object to be compared with.
* @return TRUE if the two field positions are not equal, FALSE otherwise.
* @stable ICU 2.0
*/
UBool operator!=(const FieldPosition& that) const;
/**
* Clone this object.
* Clones can be used concurrently in multiple threads.
* If an error occurs, then NULL is returned.
* The caller must delete the clone.
*
* @return a clone of this object
*
* @see getDynamicClassID
* @stable ICU 2.8
*/
FieldPosition *clone() const;
/**
* Retrieve the field identifier.
* @return the field identifier.
* @stable ICU 2.0
*/
int32_t getField(void) const { return fField; }
/**
* Retrieve the index of the first character in the requested field.
* @return the index of the first character in the requested field.
* @stable ICU 2.0
*/
int32_t getBeginIndex(void) const { return fBeginIndex; }
/**
* Retrieve the index of the character following the last character in the
* requested field.
* @return the index of the character following the last character in the
* requested field.
* @stable ICU 2.0
*/
int32_t getEndIndex(void) const { return fEndIndex; }
/**
* Set the field.
* @param f the new value of the field.
* @stable ICU 2.0
*/
void setField(int32_t f) { fField = f; }
/**
* Set the begin index. For use by subclasses of Format.
* @param bi the new value of the begin index
* @stable ICU 2.0
*/
void setBeginIndex(int32_t bi) { fBeginIndex = bi; }
/**
* Set the end index. For use by subclasses of Format.
* @param ei the new value of the end index
* @stable ICU 2.0
*/
void setEndIndex(int32_t ei) { fEndIndex = ei; }
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
/**
* Input: Desired field to determine start and end offsets for.
* The meaning depends on the subclass of Format.
*/
int32_t fField;
/**
* Output: Start offset of field in text.
* If the field does not occur in the text, 0 is returned.
*/
int32_t fBeginIndex;
/**
* Output: End offset of field in text.
* If the field does not occur in the text, 0 is returned.
*/
int32_t fEndIndex;
};
inline FieldPosition&
FieldPosition::operator=(const FieldPosition& copy)
{
fField = copy.fField;
fEndIndex = copy.fEndIndex;
fBeginIndex = copy.fBeginIndex;
return *this;
}
inline UBool
FieldPosition::operator==(const FieldPosition& copy) const
{
return (fField == copy.fField &&
fEndIndex == copy.fEndIndex &&
fBeginIndex == copy.fBeginIndex);
}
inline UBool
FieldPosition::operator!=(const FieldPosition& copy) const
{
return !operator==(copy);
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _FIELDPOS
//eof
project/jni/icuuc/include/unicode/fmtable.h
-764
View File
@@ -1,764 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File FMTABLE.H
*
* Modification History:
*
* Date Name Description
* 02/29/97 aliu Creation.
********************************************************************************
*/
#ifndef FMTABLE_H
#define FMTABLE_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Formattable is a thin wrapper for primitive types used for formatting and parsing
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/unistr.h"
#include "unicode/stringpiece.h"
#include "unicode/uformattable.h"
U_NAMESPACE_BEGIN
class CharString;
class DigitList;
/**
* \def UNUM_INTERNAL_STACKARRAY_SIZE
* @internal
*/
#if U_PLATFORM == U_PF_OS400
#define UNUM_INTERNAL_STACKARRAY_SIZE 144
#else
#define UNUM_INTERNAL_STACKARRAY_SIZE 128
#endif
/**
* Formattable objects can be passed to the Format class or
* its subclasses for formatting. Formattable is a thin wrapper
* class which interconverts between the primitive numeric types
* (double, long, etc.) as well as UDate and UnicodeString.
*
* <p>Internally, a Formattable object is a union of primitive types.
* As such, it can only store one flavor of data at a time. To
* determine what flavor of data it contains, use the getType method.
*
* <p>As of ICU 3.0, Formattable may also wrap a UObject pointer,
* which it owns. This allows an instance of any ICU class to be
* encapsulated in a Formattable. For legacy reasons and for
* efficiency, primitive numeric types are still stored directly
* within a Formattable.
*
* <p>The Formattable class is not suitable for subclassing.
*
* <p>See UFormattable for a C wrapper.
*/
class U_I18N_API Formattable : public UObject {
public:
/**
* This enum is only used to let callers distinguish between
* the Formattable(UDate) constructor and the Formattable(double)
* constructor; the compiler cannot distinguish the signatures,
* since UDate is currently typedefed to be either double or long.
* If UDate is changed later to be a bonafide class
* or struct, then we no longer need this enum.
* @stable ICU 2.4
*/
enum ISDATE { kIsDate };
/**
* Default constructor
* @stable ICU 2.4
*/
Formattable(); // Type kLong, value 0
/**
* Creates a Formattable object with a UDate instance.
* @param d the UDate instance.
* @param flag the flag to indicate this is a date. Always set it to kIsDate
* @stable ICU 2.0
*/
Formattable(UDate d, ISDATE flag);
/**
* Creates a Formattable object with a double number.
* @param d the double number.
* @stable ICU 2.0
*/
Formattable(double d);
/**
* Creates a Formattable object with a long number.
* @param l the long number.
* @stable ICU 2.0
*/
Formattable(int32_t l);
/**
* Creates a Formattable object with an int64_t number
* @param ll the int64_t number.
* @stable ICU 2.8
*/
Formattable(int64_t ll);
#if !UCONFIG_NO_CONVERSION
/**
* Creates a Formattable object with a char string pointer.
* Assumes that the char string is null terminated.
* @param strToCopy the char string.
* @stable ICU 2.0
*/
Formattable(const char* strToCopy);
#endif
/**
* Creates a Formattable object of an appropriate numeric type from a
* a decimal number in string form. The Formattable will retain the
* full precision of the input in decimal format, even when it exceeds
* what can be represented by a double or int64_t.
*
* @param number the unformatted (not localized) string representation
* of the Decimal number.
* @param status the error code. Possible errors include U_INVALID_FORMAT_ERROR
* if the format of the string does not conform to that of a
* decimal number.
* @stable ICU 4.4
*/
Formattable(const StringPiece &number, UErrorCode &status);
/**
* Creates a Formattable object with a UnicodeString object to copy from.
* @param strToCopy the UnicodeString string.
* @stable ICU 2.0
*/
Formattable(const UnicodeString& strToCopy);
/**
* Creates a Formattable object with a UnicodeString object to adopt from.
* @param strToAdopt the UnicodeString string.
* @stable ICU 2.0
*/
Formattable(UnicodeString* strToAdopt);
/**
* Creates a Formattable object with an array of Formattable objects.
* @param arrayToCopy the Formattable object array.
* @param count the array count.
* @stable ICU 2.0
*/
Formattable(const Formattable* arrayToCopy, int32_t count);
/**
* Creates a Formattable object that adopts the given UObject.
* @param objectToAdopt the UObject to set this object to
* @stable ICU 3.0
*/
Formattable(UObject* objectToAdopt);
/**
* Copy constructor.
* @stable ICU 2.0
*/
Formattable(const Formattable&);
/**
* Assignment operator.
* @param rhs The Formattable object to copy into this object.
* @stable ICU 2.0
*/
Formattable& operator=(const Formattable &rhs);
/**
* Equality comparison.
* @param other the object to be compared with.
* @return TRUE if other are equal to this, FALSE otherwise.
* @stable ICU 2.0
*/
UBool operator==(const Formattable &other) const;
/**
* Equality operator.
* @param other the object to be compared with.
* @return TRUE if other are unequal to this, FALSE otherwise.
* @stable ICU 2.0
*/
UBool operator!=(const Formattable& other) const
{ return !operator==(other); }
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~Formattable();
/**
* Clone this object.
* Clones can be used concurrently in multiple threads.
* If an error occurs, then NULL is returned.
* The caller must delete the clone.
*
* @return a clone of this object
*
* @see getDynamicClassID
* @stable ICU 2.8
*/
Formattable *clone() const;
/**
* Selector for flavor of data type contained within a
* Formattable object. Formattable is a union of several
* different types, and at any time contains exactly one type.
* @stable ICU 2.4
*/
enum Type {
/**
* Selector indicating a UDate value. Use getDate to retrieve
* the value.
* @stable ICU 2.4
*/
kDate,
/**
* Selector indicating a double value. Use getDouble to
* retrieve the value.
* @stable ICU 2.4
*/
kDouble,
/**
* Selector indicating a 32-bit integer value. Use getLong to
* retrieve the value.
* @stable ICU 2.4
*/
kLong,
/**
* Selector indicating a UnicodeString value. Use getString
* to retrieve the value.
* @stable ICU 2.4
*/
kString,
/**
* Selector indicating an array of Formattables. Use getArray
* to retrieve the value.
* @stable ICU 2.4
*/
kArray,
/**
* Selector indicating a 64-bit integer value. Use getInt64
* to retrieve the value.
* @stable ICU 2.8
*/
kInt64,
/**
* Selector indicating a UObject value. Use getObject to
* retrieve the value.
* @stable ICU 3.0
*/
kObject
};
/**
* Gets the data type of this Formattable object.
* @return the data type of this Formattable object.
* @stable ICU 2.0
*/
Type getType(void) const;
/**
* Returns TRUE if the data type of this Formattable object
* is kDouble, kLong, or kInt64
* @return TRUE if this is a pure numeric object
* @stable ICU 3.0
*/
UBool isNumeric() const;
/**
* Gets the double value of this object. If this object is not of type
* kDouble then the result is undefined.
* @return the double value of this object.
* @stable ICU 2.0
*/
double getDouble(void) const { return fValue.fDouble; }
/**
* Gets the double value of this object. If this object is of type
* long, int64 or Decimal Number then a conversion is peformed, with
* possible loss of precision. If the type is kObject and the
* object is a Measure, then the result of
* getNumber().getDouble(status) is returned. If this object is
* neither a numeric type nor a Measure, then 0 is returned and
* the status is set to U_INVALID_FORMAT_ERROR.
* @param status the error code
* @return the double value of this object.
* @stable ICU 3.0
*/
double getDouble(UErrorCode& status) const;
/**
* Gets the long value of this object. If this object is not of type
* kLong then the result is undefined.
* @return the long value of this object.
* @stable ICU 2.0
*/
int32_t getLong(void) const { return (int32_t)fValue.fInt64; }
/**
* Gets the long value of this object. If the magnitude is too
* large to fit in a long, then the maximum or minimum long value,
* as appropriate, is returned and the status is set to
* U_INVALID_FORMAT_ERROR. If this object is of type kInt64 and
* it fits within a long, then no precision is lost. If it is of
* type kDouble, then a conversion is peformed, with
* truncation of any fractional part. If the type is kObject and
* the object is a Measure, then the result of
* getNumber().getLong(status) is returned. If this object is
* neither a numeric type nor a Measure, then 0 is returned and
* the status is set to U_INVALID_FORMAT_ERROR.
* @param status the error code
* @return the long value of this object.
* @stable ICU 3.0
*/
int32_t getLong(UErrorCode& status) const;
/**
* Gets the int64 value of this object. If this object is not of type
* kInt64 then the result is undefined.
* @return the int64 value of this object.
* @stable ICU 2.8
*/
int64_t getInt64(void) const { return fValue.fInt64; }
/**
* Gets the int64 value of this object. If this object is of a numeric
* type and the magnitude is too large to fit in an int64, then
* the maximum or minimum int64 value, as appropriate, is returned
* and the status is set to U_INVALID_FORMAT_ERROR. If the
* magnitude fits in an int64, then a casting conversion is
* peformed, with truncation of any fractional part. If the type
* is kObject and the object is a Measure, then the result of
* getNumber().getDouble(status) is returned. If this object is
* neither a numeric type nor a Measure, then 0 is returned and
* the status is set to U_INVALID_FORMAT_ERROR.
* @param status the error code
* @return the int64 value of this object.
* @stable ICU 3.0
*/
int64_t getInt64(UErrorCode& status) const;
/**
* Gets the Date value of this object. If this object is not of type
* kDate then the result is undefined.
* @return the Date value of this object.
* @stable ICU 2.0
*/
UDate getDate() const { return fValue.fDate; }
/**
* Gets the Date value of this object. If the type is not a date,
* status is set to U_INVALID_FORMAT_ERROR and the return value is
* undefined.
* @param status the error code.
* @return the Date value of this object.
* @stable ICU 3.0
*/
UDate getDate(UErrorCode& status) const;
/**
* Gets the string value of this object. If this object is not of type
* kString then the result is undefined.
* @param result Output param to receive the Date value of this object.
* @return A reference to 'result'.
* @stable ICU 2.0
*/
UnicodeString& getString(UnicodeString& result) const
{ result=*fValue.fString; return result; }
/**
* Gets the string value of this object. If the type is not a
* string, status is set to U_INVALID_FORMAT_ERROR and a bogus
* string is returned.
* @param result Output param to receive the Date value of this object.
* @param status the error code.
* @return A reference to 'result'.
* @stable ICU 3.0
*/
UnicodeString& getString(UnicodeString& result, UErrorCode& status) const;
/**
* Gets a const reference to the string value of this object. If
* this object is not of type kString then the result is
* undefined.
* @return a const reference to the string value of this object.
* @stable ICU 2.0
*/
inline const UnicodeString& getString(void) const;
/**
* Gets a const reference to the string value of this object. If
* the type is not a string, status is set to
* U_INVALID_FORMAT_ERROR and the result is a bogus string.
* @param status the error code.
* @return a const reference to the string value of this object.
* @stable ICU 3.0
*/
const UnicodeString& getString(UErrorCode& status) const;
/**
* Gets a reference to the string value of this object. If this
* object is not of type kString then the result is undefined.
* @return a reference to the string value of this object.
* @stable ICU 2.0
*/
inline UnicodeString& getString(void);
/**
* Gets a reference to the string value of this object. If the
* type is not a string, status is set to U_INVALID_FORMAT_ERROR
* and the result is a bogus string.
* @param status the error code.
* @return a reference to the string value of this object.
* @stable ICU 3.0
*/
UnicodeString& getString(UErrorCode& status);
/**
* Gets the array value and count of this object. If this object
* is not of type kArray then the result is undefined.
* @param count fill-in with the count of this object.
* @return the array value of this object.
* @stable ICU 2.0
*/
const Formattable* getArray(int32_t& count) const
{ count=fValue.fArrayAndCount.fCount; return fValue.fArrayAndCount.fArray; }
/**
* Gets the array value and count of this object. If the type is
* not an array, status is set to U_INVALID_FORMAT_ERROR, count is
* set to 0, and the result is NULL.
* @param count fill-in with the count of this object.
* @param status the error code.
* @return the array value of this object.
* @stable ICU 3.0
*/
const Formattable* getArray(int32_t& count, UErrorCode& status) const;
/**
* Accesses the specified element in the array value of this
* Formattable object. If this object is not of type kArray then
* the result is undefined.
* @param index the specified index.
* @return the accessed element in the array.
* @stable ICU 2.0
*/
Formattable& operator[](int32_t index) { return fValue.fArrayAndCount.fArray[index]; }
/**
* Returns a pointer to the UObject contained within this
* formattable, or NULL if this object does not contain a UObject.
* @return a UObject pointer, or NULL
* @stable ICU 3.0
*/
const UObject* getObject() const;
/**
* Returns a numeric string representation of the number contained within this
* formattable, or NULL if this object does not contain numeric type.
* For values obtained by parsing, the returned decimal number retains
* the full precision and range of the original input, unconstrained by
* the limits of a double floating point or a 64 bit int.
*
* This function is not thread safe, and therfore is not declared const,
* even though it is logically const.
*
* Possible errors include U_MEMORY_ALLOCATION_ERROR, and
* U_INVALID_STATE if the formattable object has not been set to
* a numeric type.
*
* @param status the error code.
* @return the unformatted string representation of a number.
* @stable ICU 4.4
*/
StringPiece getDecimalNumber(UErrorCode &status);
/**
* Sets the double value of this object and changes the type to
* kDouble.
* @param d the new double value to be set.
* @stable ICU 2.0
*/
void setDouble(double d);
/**
* Sets the long value of this object and changes the type to
* kLong.
* @param l the new long value to be set.
* @stable ICU 2.0
*/
void setLong(int32_t l);
/**
* Sets the int64 value of this object and changes the type to
* kInt64.
* @param ll the new int64 value to be set.
* @stable ICU 2.8
*/
void setInt64(int64_t ll);
/**
* Sets the Date value of this object and changes the type to
* kDate.
* @param d the new Date value to be set.
* @stable ICU 2.0
*/
void setDate(UDate d);
/**
* Sets the string value of this object and changes the type to
* kString.
* @param stringToCopy the new string value to be set.
* @stable ICU 2.0
*/
void setString(const UnicodeString& stringToCopy);
/**
* Sets the array value and count of this object and changes the
* type to kArray.
* @param array the array value.
* @param count the number of array elements to be copied.
* @stable ICU 2.0
*/
void setArray(const Formattable* array, int32_t count);
/**
* Sets and adopts the string value and count of this object and
* changes the type to kArray.
* @param stringToAdopt the new string value to be adopted.
* @stable ICU 2.0
*/
void adoptString(UnicodeString* stringToAdopt);
/**
* Sets and adopts the array value and count of this object and
* changes the type to kArray.
* @stable ICU 2.0
*/
void adoptArray(Formattable* array, int32_t count);
/**
* Sets and adopts the UObject value of this object and changes
* the type to kObject. After this call, the caller must not
* delete the given object.
* @param objectToAdopt the UObject value to be adopted
* @stable ICU 3.0
*/
void adoptObject(UObject* objectToAdopt);
/**
* Sets the the numeric value from a decimal number string, and changes
* the type to to a numeric type appropriate for the number.
* The syntax of the number is a "numeric string"
* as defined in the Decimal Arithmetic Specification, available at
* http://speleotrove.com/decimal
* The full precision and range of the input number will be retained,
* even when it exceeds what can be represented by a double or an int64.
*
* @param numberString a string representation of the unformatted decimal number.
* @param status the error code. Set to U_INVALID_FORMAT_ERROR if the
* incoming string is not a valid decimal number.
* @stable ICU 4.4
*/
void setDecimalNumber(const StringPiece &numberString,
UErrorCode &status);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
#ifndef U_HIDE_DRAFT_API
/**
* Convert the UFormattable to a Formattable. Internally, this is a reinterpret_cast.
* @param fmt a valid UFormattable
* @return the UFormattable as a Formattable object pointer. This is an alias to the original
* UFormattable, and so is only valid while the original argument remains in scope.
* @draft ICU 52
*/
static inline Formattable *fromUFormattable(UFormattable *fmt);
/**
* Convert the const UFormattable to a const Formattable. Internally, this is a reinterpret_cast.
* @param fmt a valid UFormattable
* @return the UFormattable as a Formattable object pointer. This is an alias to the original
* UFormattable, and so is only valid while the original argument remains in scope.
* @draft ICU 52
*/
static inline const Formattable *fromUFormattable(const UFormattable *fmt);
/**
* Convert this object pointer to a UFormattable.
* @return this object as a UFormattable pointer. This is an alias to this object,
* and so is only valid while this object remains in scope.
* @draft ICU 52
*/
inline UFormattable *toUFormattable();
/**
* Convert this object pointer to a UFormattable.
* @return this object as a UFormattable pointer. This is an alias to this object,
* and so is only valid while this object remains in scope.
* @draft ICU 52
*/
inline const UFormattable *toUFormattable() const;
#endif /* U_HIDE_DRAFT_API */
#ifndef U_HIDE_DEPRECATED_API
/**
* Deprecated variant of getLong(UErrorCode&).
* @param status the error code
* @return the long value of this object.
* @deprecated ICU 3.0 use getLong(UErrorCode&) instead
*/
inline int32_t getLong(UErrorCode* status) const;
#endif /* U_HIDE_DEPRECATED_API */
#ifndef U_HIDE_INTERNAL_API
/**
* Internal function, do not use.
* TODO: figure out how to make this be non-public.
* NumberFormat::format(Formattable, ...
* needs to get at the DigitList, if it exists, for
* big decimal formatting.
* @internal
*/
DigitList *getDigitList() const { return fDecimalNum;}
/**
* @internal
*/
DigitList *getInternalDigitList();
/**
* Adopt, and set value from, a DigitList
* Internal Function, do not use.
* @param dl the Digit List to be adopted
* @internal
*/
void adoptDigitList(DigitList *dl);
/**
* Internal function to return the CharString pointer.
* @param status error code
* @return pointer to the CharString - may become invalid if the object is modified
* @internal
*/
CharString *internalGetCharString(UErrorCode &status);
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* Cleans up the memory for unwanted values. For example, the adopted
* string or array objects.
*/
void dispose(void);
/**
* Common initialization, for use by constructors.
*/
void init();
UnicodeString* getBogus() const;
union {
UObject* fObject;
UnicodeString* fString;
double fDouble;
int64_t fInt64;
UDate fDate;
struct {
Formattable* fArray;
int32_t fCount;
} fArrayAndCount;
} fValue;
CharString *fDecimalStr;
DigitList *fDecimalNum;
char fStackData[UNUM_INTERNAL_STACKARRAY_SIZE]; // must be big enough for DigitList
Type fType;
UnicodeString fBogus; // Bogus string when it's needed.
};
inline UDate Formattable::getDate(UErrorCode& status) const {
if (fType != kDate) {
if (U_SUCCESS(status)) {
status = U_INVALID_FORMAT_ERROR;
}
return 0;
}
return fValue.fDate;
}
inline const UnicodeString& Formattable::getString(void) const {
return *fValue.fString;
}
inline UnicodeString& Formattable::getString(void) {
return *fValue.fString;
}
#ifndef U_HIDE_DEPRECATED_API
inline int32_t Formattable::getLong(UErrorCode* status) const {
return getLong(*status);
}
#endif /* U_HIDE_DEPRECATED_API */
#ifndef U_HIDE_DRAFT_API
inline UFormattable* Formattable::toUFormattable() {
return reinterpret_cast<UFormattable*>(this);
}
inline const UFormattable* Formattable::toUFormattable() const {
return reinterpret_cast<const UFormattable*>(this);
}
inline Formattable* Formattable::fromUFormattable(UFormattable *fmt) {
return reinterpret_cast<Formattable *>(fmt);
}
inline const Formattable* Formattable::fromUFormattable(const UFormattable *fmt) {
return reinterpret_cast<const Formattable *>(fmt);
}
#endif /* U_HIDE_DRAFT_API */
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif //_FMTABLE
//eof
project/jni/icuuc/include/unicode/format.h
-305
View File
@@ -1,305 +0,0 @@
/*
********************************************************************************
* Copyright (C) 1997-2011, International Business Machines Corporation and others.
* All Rights Reserved.
********************************************************************************
*
* File FORMAT.H
*
* Modification History:
*
* Date Name Description
* 02/19/97 aliu Converted from java.
* 03/17/97 clhuang Updated per C++ implementation.
* 03/27/97 helena Updated to pass the simple test after code review.
********************************************************************************
*/
// *****************************************************************************
// This file was generated from the java source file Format.java
// *****************************************************************************
#ifndef FORMAT_H
#define FORMAT_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Base class for all formats.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/unistr.h"
#include "unicode/fmtable.h"
#include "unicode/fieldpos.h"
#include "unicode/fpositer.h"
#include "unicode/parsepos.h"
#include "unicode/parseerr.h"
#include "unicode/locid.h"
U_NAMESPACE_BEGIN
/**
* Base class for all formats. This is an abstract base class which
* specifies the protocol for classes which convert other objects or
* values, such as numeric values and dates, and their string
* representations. In some cases these representations may be
* localized or contain localized characters or strings. For example,
* a numeric formatter such as DecimalFormat may convert a numeric
* value such as 12345 to the string "$12,345". It may also parse
* the string back into a numeric value. A date and time formatter
* like SimpleDateFormat may represent a specific date, encoded
* numerically, as a string such as "Wednesday, February 26, 1997 AD".
* <P>
* Many of the concrete subclasses of Format employ the notion of
* a pattern. A pattern is a string representation of the rules which
* govern the interconversion between values and strings. For example,
* a DecimalFormat object may be associated with the pattern
* "$#,##0.00;($#,##0.00)", which is a common US English format for
* currency values, yielding strings such as "$1,234.45" for 1234.45,
* and "($987.65)" for 987.6543. The specific syntax of a pattern
* is defined by each subclass.
* <P>
* Even though many subclasses use patterns, the notion of a pattern
* is not inherent to Format classes in general, and is not part of
* the explicit base class protocol.
* <P>
* Two complex formatting classes bear mentioning. These are
* MessageFormat and ChoiceFormat. ChoiceFormat is a subclass of
* NumberFormat which allows the user to format different number ranges
* as strings. For instance, 0 may be represented as "no files", 1 as
* "one file", and any number greater than 1 as "many files".
* MessageFormat is a formatter which utilizes other Format objects to
* format a string containing with multiple values. For instance,
* A MessageFormat object might produce the string "There are no files
* on the disk MyDisk on February 27, 1997." given the arguments 0,
* "MyDisk", and the date value of 2/27/97. See the ChoiceFormat
* and MessageFormat headers for further information.
* <P>
* If formatting is unsuccessful, a failing UErrorCode is returned when
* the Format cannot format the type of object, otherwise if there is
* something illformed about the the Unicode replacement character
* 0xFFFD is returned.
* <P>
* If there is no match when parsing, a parse failure UErrorCode is
* retured for methods which take no ParsePosition. For the method
* that takes a ParsePosition, the index parameter is left unchanged.
* <P>
* <em>User subclasses are not supported.</em> While clients may write
* subclasses, such code will not necessarily work and will not be
* guaranteed to work stably from release to release.
*/
class U_I18N_API Format : public UObject {
public:
/** Destructor
* @stable ICU 2.4
*/
virtual ~Format();
/**
* Return true if the given Format objects are semantically equal.
* Objects of different subclasses are considered unequal.
* @param other the object to be compared with.
* @return Return true if the given Format objects are semantically equal.
* Objects of different subclasses are considered unequal.
* @stable ICU 2.0
*/
virtual UBool operator==(const Format& other) const = 0;
/**
* Return true if the given Format objects are not semantically
* equal.
* @param other the object to be compared with.
* @return Return true if the given Format objects are not semantically.
* @stable ICU 2.0
*/
UBool operator!=(const Format& other) const { return !operator==(other); }
/**
* Clone this object polymorphically. The caller is responsible
* for deleting the result when done.
* @return A copy of the object
* @stable ICU 2.0
*/
virtual Format* clone() const = 0;
/**
* Formats an object to produce a string.
*
* @param obj The object to format.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param status Output parameter filled in with success or failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 2.0
*/
UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
UErrorCode& status) const;
/**
* Format an object to produce a string. This is a pure virtual method which
* subclasses must implement. This method allows polymorphic formatting
* of Formattable objects. If a subclass of Format receives a Formattable
* object type it doesn't handle (e.g., if a numeric Formattable is passed
* to a DateFormat object) then it returns a failing UErrorCode.
*
* @param obj The object to format.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 2.0
*/
virtual UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const = 0;
/**
* Format an object to produce a string. Subclasses should override this
* method. This method allows polymorphic formatting of Formattable objects.
* If a subclass of Format receives a Formattable object type it doesn't
* handle (e.g., if a numeric Formattable is passed to a DateFormat object)
* then it returns a failing UErrorCode.
*
* @param obj The object to format.
* @param appendTo Output parameter to receive result.
* Result is appended to existing contents.
* @param posIter On return, can be used to iterate over positions
* of fields generated by this format call.
* @param status Output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.4
*/
virtual UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
FieldPositionIterator* posIter,
UErrorCode& status) const;
/**
* Parse a string to produce an object. This is a pure virtual
* method which subclasses must implement. This method allows
* polymorphic parsing of strings into Formattable objects.
* <P>
* Before calling, set parse_pos.index to the offset you want to
* start parsing at in the source. After calling, parse_pos.index
* is the end of the text you parsed. If error occurs, index is
* unchanged.
* <P>
* When parsing, leading whitespace is discarded (with successful
* parse), while trailing whitespace is left as is.
* <P>
* Example:
* <P>
* Parsing "_12_xy" (where _ represents a space) for a number,
* with index == 0 will result in the number 12, with
* parse_pos.index updated to 3 (just before the second space).
* Parsing a second time will result in a failing UErrorCode since
* "xy" is not a number, and leave index at 3.
* <P>
* Subclasses will typically supply specific parse methods that
* return different types of values. Since methods can't overload
* on return types, these will typically be named "parse", while
* this polymorphic method will always be called parseObject. Any
* parse method that does not take a parse_pos should set status
* to an error value when no text in the required format is at the
* start position.
*
* @param source The string to be parsed into an object.
* @param result Formattable to be set to the parse result.
* If parse fails, return contents are undefined.
* @param parse_pos The position to start parsing at. Upon return
* this param is set to the position after the
* last character successfully parsed. If the
* source is not parsed successfully, this param
* will remain unchanged.
* @stable ICU 2.0
*/
virtual void parseObject(const UnicodeString& source,
Formattable& result,
ParsePosition& parse_pos) const = 0;
/**
* Parses a string to produce an object. This is a convenience method
* which calls the pure virtual parseObject() method, and returns a
* failure UErrorCode if the ParsePosition indicates failure.
*
* @param source The string to be parsed into an object.
* @param result Formattable to be set to the parse result.
* If parse fails, return contents are undefined.
* @param status Output param to be filled with success/failure
* result code.
* @stable ICU 2.0
*/
void parseObject(const UnicodeString& source,
Formattable& result,
UErrorCode& status) const;
/** Get the locale for this format object. You can choose between valid and actual locale.
* @param type type of the locale we're looking for (valid or actual)
* @param status error code for the operation
* @return the locale
* @stable ICU 2.8
*/
Locale getLocale(ULocDataLocaleType type, UErrorCode& status) const;
#ifndef U_HIDE_INTERNAL_API
/** Get the locale for this format object. You can choose between valid and actual locale.
* @param type type of the locale we're looking for (valid or actual)
* @param status error code for the operation
* @return the locale
* @internal
*/
const char* getLocaleID(ULocDataLocaleType type, UErrorCode &status) const;
#endif /* U_HIDE_INTERNAL_API */
protected:
/** @stable ICU 2.8 */
void setLocaleIDs(const char* valid, const char* actual);
protected:
/**
* Default constructor for subclass use only. Does nothing.
* @stable ICU 2.0
*/
Format();
/**
* @stable ICU 2.0
*/
Format(const Format&); // Does nothing; for subclasses only
/**
* @stable ICU 2.0
*/
Format& operator=(const Format&); // Does nothing; for subclasses
/**
* Simple function for initializing a UParseError from a UnicodeString.
*
* @param pattern The pattern to copy into the parseError
* @param pos The position in pattern where the error occured
* @param parseError The UParseError object to fill in
* @stable ICU 2.4
*/
static void syntaxError(const UnicodeString& pattern,
int32_t pos,
UParseError& parseError);
private:
char actualLocale[ULOC_FULLNAME_CAPACITY];
char validLocale[ULOC_FULLNAME_CAPACITY];
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _FORMAT
//eof
project/jni/icuuc/include/unicode/fpositer.h
-117
View File
@@ -1,117 +0,0 @@
/*
********************************************************************************
* Copyright (C) 2010-2012, International Business Machines
* Corporation and others. All Rights Reserved.
********************************************************************************
*
* File attiter.h
*
* Modification History:
*
* Date Name Description
* 12/15/2009 dougfelt Created
********************************************************************************
*/
#ifndef FPOSITER_H
#define FPOSITER_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
/**
* \file
* \brief C++ API: FieldPosition Iterator.
*/
#if UCONFIG_NO_FORMATTING
U_NAMESPACE_BEGIN
/*
* Allow the declaration of APIs with pointers to FieldPositionIterator
* even when formatting is removed from the build.
*/
class FieldPositionIterator;
U_NAMESPACE_END
#else
#include "unicode/fieldpos.h"
#include "unicode/umisc.h"
U_NAMESPACE_BEGIN
class UVector32;
/**
* FieldPositionIterator returns the field ids and their start/limit positions generated
* by a call to Format::format. See Format, NumberFormat, DecimalFormat.
* @stable ICU 4.4
*/
class U_I18N_API FieldPositionIterator : public UObject {
public:
/**
* Destructor.
* @stable ICU 4.4
*/
~FieldPositionIterator();
/**
* Constructs a new, empty iterator.
* @stable ICU 4.4
*/
FieldPositionIterator(void);
/**
* Copy constructor. If the copy failed for some reason, the new iterator will
* be empty.
* @stable ICU 4.4
*/
FieldPositionIterator(const FieldPositionIterator&);
/**
* Return true if another object is semantically equal to this
* one.
* <p>
* Return true if this FieldPositionIterator is at the same position in an
* equal array of run values.
* @stable ICU 4.4
*/
UBool operator==(const FieldPositionIterator&) const;
/**
* Returns the complement of the result of operator==
* @param rhs The FieldPositionIterator to be compared for inequality
* @return the complement of the result of operator==
* @stable ICU 4.4
*/
UBool operator!=(const FieldPositionIterator& rhs) const { return !operator==(rhs); }
/**
* If the current position is valid, updates the FieldPosition values, advances the iterator,
* and returns TRUE, otherwise returns FALSE.
* @stable ICU 4.4
*/
UBool next(FieldPosition& fp);
private:
friend class FieldPositionIteratorHandler;
/**
* Sets the data used by the iterator, and resets the position.
* Returns U_ILLEGAL_ARGUMENT_ERROR in status if the data is not valid
* (length is not a multiple of 3, or start >= limit for any run).
*/
void setData(UVector32 *adopt, UErrorCode& status);
UVector32 *data;
int32_t pos;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // FPOSITER_H
project/jni/icuuc/include/unicode/gender.h
-111
View File
@@ -1,111 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2008-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
*
* File GENDER.H
*
* Modification History:*
* Date Name Description
*
********************************************************************************
*/
#ifndef _GENDER
#define _GENDER
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/locid.h"
#include "unicode/ugender.h"
#include "unicode/uobject.h"
class GenderInfoTest;
U_NAMESPACE_BEGIN
// Forward Declaration
void GenderInfo_initCache(UErrorCode &status);
/**
* GenderInfo computes the gender of a list as a whole given the gender of
* each element.
* @stable ICU 50
*/
class U_I18N_API GenderInfo : public UObject {
public:
/**
* Provides access to the predefined GenderInfo object for a given
* locale.
*
* @param locale The locale for which a <code>GenderInfo</code> object is
* returned.
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return The predefined <code>GenderInfo</code> object pointer for
* this locale. The returned object is immutable, so it is
* declared as const. Caller does not own the returned
* pointer, so it must not attempt to free it.
* @stable ICU 50
*/
static const GenderInfo* U_EXPORT2 getInstance(const Locale& locale, UErrorCode& status);
/**
* Determines the gender of a list as a whole given the gender of each
* of the elements.
*
* @param genders the gender of each element in the list.
* @param length the length of gender array.
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return the gender of the whole list.
* @stable ICU 50
*/
UGender getListGender(const UGender* genders, int32_t length, UErrorCode& status) const;
/**
* Destructor.
*
* @stable ICU 50
*/
virtual ~GenderInfo();
private:
int32_t _style;
/**
* Copy constructor. One object per locale invariant. Clients
* must never copy GenderInfo objects.
*/
GenderInfo(const GenderInfo& other);
/**
* Assignment operator. Not applicable to immutable objects.
*/
GenderInfo& operator=(const GenderInfo&);
GenderInfo();
static const GenderInfo* getNeutralInstance();
static const GenderInfo* getMixedNeutralInstance();
static const GenderInfo* getMaleTaintsInstance();
static const GenderInfo* loadInstance(const Locale& locale, UErrorCode& status);
friend class ::GenderInfoTest;
friend void GenderInfo_initCache(UErrorCode &status);
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _GENDER
//eof
project/jni/icuuc/include/unicode/gregocal.h
-777
View File
@@ -1,777 +0,0 @@
/*
* Copyright (C) 1997-2013, International Business Machines Corporation and others.
* All Rights Reserved.
********************************************************************************
*
* File GREGOCAL.H
*
* Modification History:
*
* Date Name Description
* 04/22/97 aliu Overhauled header.
* 07/28/98 stephen Sync with JDK 1.2
* 09/04/98 stephen Re-sync with JDK 8/31 putback
* 09/14/98 stephen Changed type of kOneDay, kOneWeek to double.
* Fixed bug in roll()
* 10/15/99 aliu Fixed j31, incorrect WEEK_OF_YEAR computation.
* Added documentation of WEEK_OF_YEAR computation.
* 10/15/99 aliu Fixed j32, cannot set date to Feb 29 2000 AD.
* {JDK bug 4210209 4209272}
* 11/07/2003 srl Update, clean up documentation.
********************************************************************************
*/
#ifndef GREGOCAL_H
#define GREGOCAL_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/calendar.h"
/**
* \file
* \brief C++ API: Concrete class which provides the standard calendar.
*/
U_NAMESPACE_BEGIN
/**
* Concrete class which provides the standard calendar used by most of the world.
* <P>
* The standard (Gregorian) calendar has 2 eras, BC and AD.
* <P>
* This implementation handles a single discontinuity, which corresponds by default to
* the date the Gregorian calendar was originally instituted (October 15, 1582). Not all
* countries adopted the Gregorian calendar then, so this cutover date may be changed by
* the caller.
* <P>
* Prior to the institution of the Gregorian Calendar, New Year's Day was March 25. To
* avoid confusion, this Calendar always uses January 1. A manual adjustment may be made
* if desired for dates that are prior to the Gregorian changeover and which fall
* between January 1 and March 24.
*
* <p>Values calculated for the <code>WEEK_OF_YEAR</code> field range from 1 to
* 53. Week 1 for a year is the first week that contains at least
* <code>getMinimalDaysInFirstWeek()</code> days from that year. It thus
* depends on the values of <code>getMinimalDaysInFirstWeek()</code>,
* <code>getFirstDayOfWeek()</code>, and the day of the week of January 1.
* Weeks between week 1 of one year and week 1 of the following year are
* numbered sequentially from 2 to 52 or 53 (as needed).
*
* <p>For example, January 1, 1998 was a Thursday. If
* <code>getFirstDayOfWeek()</code> is <code>MONDAY</code> and
* <code>getMinimalDaysInFirstWeek()</code> is 4 (these are the values
* reflecting ISO 8601 and many national standards), then week 1 of 1998 starts
* on December 29, 1997, and ends on January 4, 1998. If, however,
* <code>getFirstDayOfWeek()</code> is <code>SUNDAY</code>, then week 1 of 1998
* starts on January 4, 1998, and ends on January 10, 1998; the first three days
* of 1998 then are part of week 53 of 1997.
*
* <p>Example for using GregorianCalendar:
* <pre>
* \code
* // get the supported ids for GMT-08:00 (Pacific Standard Time)
* UErrorCode success = U_ZERO_ERROR;
* const StringEnumeration *ids = TimeZone::createEnumeration(-8 * 60 * 60 * 1000);
* // if no ids were returned, something is wrong. get out.
* if (ids == 0 || ids->count(success) == 0) {
* return;
* }
*
* // begin output
* cout << "Current Time" << endl;
*
* // create a Pacific Standard Time time zone
* SimpleTimeZone* pdt = new SimpleTimeZone(-8 * 60 * 60 * 1000, ids->unext(NULL, success)));
*
* // set up rules for daylight savings time
* pdt->setStartRule(UCAL_MARCH, 1, UCAL_SUNDAY, 2 * 60 * 60 * 1000);
* pdt->setEndRule(UCAL_NOVEMBER, 2, UCAL_SUNDAY, 2 * 60 * 60 * 1000);
*
* // create a GregorianCalendar with the Pacific Daylight time zone
* // and the current date and time
* Calendar* calendar = new GregorianCalendar( pdt, success );
*
* // print out a bunch of interesting things
* cout << "ERA: " << calendar->get( UCAL_ERA, success ) << endl;
* cout << "YEAR: " << calendar->get( UCAL_YEAR, success ) << endl;
* cout << "MONTH: " << calendar->get( UCAL_MONTH, success ) << endl;
* cout << "WEEK_OF_YEAR: " << calendar->get( UCAL_WEEK_OF_YEAR, success ) << endl;
* cout << "WEEK_OF_MONTH: " << calendar->get( UCAL_WEEK_OF_MONTH, success ) << endl;
* cout << "DATE: " << calendar->get( UCAL_DATE, success ) << endl;
* cout << "DAY_OF_MONTH: " << calendar->get( UCAL_DAY_OF_MONTH, success ) << endl;
* cout << "DAY_OF_YEAR: " << calendar->get( UCAL_DAY_OF_YEAR, success ) << endl;
* cout << "DAY_OF_WEEK: " << calendar->get( UCAL_DAY_OF_WEEK, success ) << endl;
* cout << "DAY_OF_WEEK_IN_MONTH: " << calendar->get( UCAL_DAY_OF_WEEK_IN_MONTH, success ) << endl;
* cout << "AM_PM: " << calendar->get( UCAL_AM_PM, success ) << endl;
* cout << "HOUR: " << calendar->get( UCAL_HOUR, success ) << endl;
* cout << "HOUR_OF_DAY: " << calendar->get( UCAL_HOUR_OF_DAY, success ) << endl;
* cout << "MINUTE: " << calendar->get( UCAL_MINUTE, success ) << endl;
* cout << "SECOND: " << calendar->get( UCAL_SECOND, success ) << endl;
* cout << "MILLISECOND: " << calendar->get( UCAL_MILLISECOND, success ) << endl;
* cout << "ZONE_OFFSET: " << (calendar->get( UCAL_ZONE_OFFSET, success )/(60*60*1000)) << endl;
* cout << "DST_OFFSET: " << (calendar->get( UCAL_DST_OFFSET, success )/(60*60*1000)) << endl;
*
* cout << "Current Time, with hour reset to 3" << endl;
* calendar->clear(UCAL_HOUR_OF_DAY); // so doesn't override
* calendar->set(UCAL_HOUR, 3);
* cout << "ERA: " << calendar->get( UCAL_ERA, success ) << endl;
* cout << "YEAR: " << calendar->get( UCAL_YEAR, success ) << endl;
* cout << "MONTH: " << calendar->get( UCAL_MONTH, success ) << endl;
* cout << "WEEK_OF_YEAR: " << calendar->get( UCAL_WEEK_OF_YEAR, success ) << endl;
* cout << "WEEK_OF_MONTH: " << calendar->get( UCAL_WEEK_OF_MONTH, success ) << endl;
* cout << "DATE: " << calendar->get( UCAL_DATE, success ) << endl;
* cout << "DAY_OF_MONTH: " << calendar->get( UCAL_DAY_OF_MONTH, success ) << endl;
* cout << "DAY_OF_YEAR: " << calendar->get( UCAL_DAY_OF_YEAR, success ) << endl;
* cout << "DAY_OF_WEEK: " << calendar->get( UCAL_DAY_OF_WEEK, success ) << endl;
* cout << "DAY_OF_WEEK_IN_MONTH: " << calendar->get( UCAL_DAY_OF_WEEK_IN_MONTH, success ) << endl;
* cout << "AM_PM: " << calendar->get( UCAL_AM_PM, success ) << endl;
* cout << "HOUR: " << calendar->get( UCAL_HOUR, success ) << endl;
* cout << "HOUR_OF_DAY: " << calendar->get( UCAL_HOUR_OF_DAY, success ) << endl;
* cout << "MINUTE: " << calendar->get( UCAL_MINUTE, success ) << endl;
* cout << "SECOND: " << calendar->get( UCAL_SECOND, success ) << endl;
* cout << "MILLISECOND: " << calendar->get( UCAL_MILLISECOND, success ) << endl;
* cout << "ZONE_OFFSET: " << (calendar->get( UCAL_ZONE_OFFSET, success )/(60*60*1000)) << endl; // in hours
* cout << "DST_OFFSET: " << (calendar->get( UCAL_DST_OFFSET, success )/(60*60*1000)) << endl; // in hours
*
* if (U_FAILURE(success)) {
* cout << "An error occured. success=" << u_errorName(success) << endl;
* }
*
* delete ids;
* delete calendar; // also deletes pdt
* \endcode
* </pre>
* @stable ICU 2.0
*/
class U_I18N_API GregorianCalendar: public Calendar {
public:
/**
* Useful constants for GregorianCalendar and TimeZone.
* @stable ICU 2.0
*/
enum EEras {
BC,
AD
};
/**
* Constructs a default GregorianCalendar using the current time in the default time
* zone with the default locale.
*
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(UErrorCode& success);
/**
* Constructs a GregorianCalendar based on the current time in the given time zone
* with the default locale. Clients are no longer responsible for deleting the given
* time zone object after it's adopted.
*
* @param zoneToAdopt The given timezone.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(TimeZone* zoneToAdopt, UErrorCode& success);
/**
* Constructs a GregorianCalendar based on the current time in the given time zone
* with the default locale.
*
* @param zone The given timezone.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(const TimeZone& zone, UErrorCode& success);
/**
* Constructs a GregorianCalendar based on the current time in the default time zone
* with the given locale.
*
* @param aLocale The given locale.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(const Locale& aLocale, UErrorCode& success);
/**
* Constructs a GregorianCalendar based on the current time in the given time zone
* with the given locale. Clients are no longer responsible for deleting the given
* time zone object after it's adopted.
*
* @param zoneToAdopt The given timezone.
* @param aLocale The given locale.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(TimeZone* zoneToAdopt, const Locale& aLocale, UErrorCode& success);
/**
* Constructs a GregorianCalendar based on the current time in the given time zone
* with the given locale.
*
* @param zone The given timezone.
* @param aLocale The given locale.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(const TimeZone& zone, const Locale& aLocale, UErrorCode& success);
/**
* Constructs a GregorianCalendar with the given AD date set in the default time
* zone with the default locale.
*
* @param year The value used to set the YEAR time field in the calendar.
* @param month The value used to set the MONTH time field in the calendar. Month
* value is 0-based. e.g., 0 for January.
* @param date The value used to set the DATE time field in the calendar.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(int32_t year, int32_t month, int32_t date, UErrorCode& success);
/**
* Constructs a GregorianCalendar with the given AD date and time set for the
* default time zone with the default locale.
*
* @param year The value used to set the YEAR time field in the calendar.
* @param month The value used to set the MONTH time field in the calendar. Month
* value is 0-based. e.g., 0 for January.
* @param date The value used to set the DATE time field in the calendar.
* @param hour The value used to set the HOUR_OF_DAY time field in the calendar.
* @param minute The value used to set the MINUTE time field in the calendar.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(int32_t year, int32_t month, int32_t date, int32_t hour, int32_t minute, UErrorCode& success);
/**
* Constructs a GregorianCalendar with the given AD date and time set for the
* default time zone with the default locale.
*
* @param year The value used to set the YEAR time field in the calendar.
* @param month The value used to set the MONTH time field in the calendar. Month
* value is 0-based. e.g., 0 for January.
* @param date The value used to set the DATE time field in the calendar.
* @param hour The value used to set the HOUR_OF_DAY time field in the calendar.
* @param minute The value used to set the MINUTE time field in the calendar.
* @param second The value used to set the SECOND time field in the calendar.
* @param success Indicates the status of GregorianCalendar object construction.
* Returns U_ZERO_ERROR if constructed successfully.
* @stable ICU 2.0
*/
GregorianCalendar(int32_t year, int32_t month, int32_t date, int32_t hour, int32_t minute, int32_t second, UErrorCode& success);
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~GregorianCalendar();
/**
* Copy constructor
* @param source the object to be copied.
* @stable ICU 2.0
*/
GregorianCalendar(const GregorianCalendar& source);
/**
* Default assignment operator
* @param right the object to be copied.
* @stable ICU 2.0
*/
GregorianCalendar& operator=(const GregorianCalendar& right);
/**
* Create and return a polymorphic copy of this calendar.
* @return return a polymorphic copy of this calendar.
* @stable ICU 2.0
*/
virtual Calendar* clone(void) const;
/**
* Sets the GregorianCalendar change date. This is the point when the switch from
* Julian dates to Gregorian dates occurred. Default is 00:00:00 local time, October
* 15, 1582. Previous to this time and date will be Julian dates.
*
* @param date The given Gregorian cutover date.
* @param success Output param set to success/failure code on exit.
* @stable ICU 2.0
*/
void setGregorianChange(UDate date, UErrorCode& success);
/**
* Gets the Gregorian Calendar change date. This is the point when the switch from
* Julian dates to Gregorian dates occurred. Default is 00:00:00 local time, October
* 15, 1582. Previous to this time and date will be Julian dates.
*
* @return The Gregorian cutover time for this calendar.
* @stable ICU 2.0
*/
UDate getGregorianChange(void) const;
/**
* Return true if the given year is a leap year. Determination of whether a year is
* a leap year is actually very complicated. We do something crude and mostly
* correct here, but for a real determination you need a lot of contextual
* information. For example, in Sweden, the change from Julian to Gregorian happened
* in a complex way resulting in missed leap years and double leap years between
* 1700 and 1753. Another example is that after the start of the Julian calendar in
* 45 B.C., the leap years did not regularize until 8 A.D. This method ignores these
* quirks, and pays attention only to the Julian onset date and the Gregorian
* cutover (which can be changed).
*
* @param year The given year.
* @return True if the given year is a leap year; false otherwise.
* @stable ICU 2.0
*/
UBool isLeapYear(int32_t year) const;
/**
* Returns TRUE if the given Calendar object is equivalent to this
* one. Calendar override.
*
* @param other the Calendar to be compared with this Calendar
* @stable ICU 2.4
*/
virtual UBool isEquivalentTo(const Calendar& other) const;
/**
* (Overrides Calendar) Rolls up or down by the given amount in the specified field.
* For more information, see the documentation for Calendar::roll().
*
* @param field The time field.
* @param amount Indicates amount to roll.
* @param status Output param set to success/failure code on exit. If any value
* previously set in the time field is invalid, this will be set to
* an error status.
* @deprecated ICU 2.6. Use roll(UCalendarDateFields field, int32_t amount, UErrorCode& status) instead.
*/
virtual void roll(EDateFields field, int32_t amount, UErrorCode& status);
/**
* (Overrides Calendar) Rolls up or down by the given amount in the specified field.
* For more information, see the documentation for Calendar::roll().
*
* @param field The time field.
* @param amount Indicates amount to roll.
* @param status Output param set to success/failure code on exit. If any value
* previously set in the time field is invalid, this will be set to
* an error status.
* @stable ICU 2.6.
*/
virtual void roll(UCalendarDateFields field, int32_t amount, UErrorCode& status);
#ifndef U_HIDE_DEPRECATED_API
/**
* Return the minimum value that this field could have, given the current date.
* For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum().
* @param field the time field.
* @return the minimum value that this field could have, given the current date.
* @deprecated ICU 2.6. Use getActualMinimum(UCalendarDateFields field) instead.
*/
int32_t getActualMinimum(EDateFields field) const;
/**
* Return the minimum value that this field could have, given the current date.
* For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum().
* @param field the time field.
* @param status
* @return the minimum value that this field could have, given the current date.
* @deprecated ICU 2.6. Use getActualMinimum(UCalendarDateFields field) instead. (Added to ICU 3.0 for signature consistency)
*/
int32_t getActualMinimum(EDateFields field, UErrorCode& status) const;
#endif /* U_HIDE_DEPRECATED_API */
/**
* Return the minimum value that this field could have, given the current date.
* For the Gregorian calendar, this is the same as getMinimum() and getGreatestMinimum().
* @param field the time field.
* @param status error result.
* @return the minimum value that this field could have, given the current date.
* @stable ICU 3.0
*/
int32_t getActualMinimum(UCalendarDateFields field, UErrorCode &status) const;
#ifndef U_HIDE_DEPRECATED_API
/**
* Return the maximum value that this field could have, given the current date.
* For example, with the date "Feb 3, 1997" and the DAY_OF_MONTH field, the actual
* maximum would be 28; for "Feb 3, 1996" it s 29. Similarly for a Hebrew calendar,
* for some years the actual maximum for MONTH is 12, and for others 13.
* @param field the time field.
* @return the maximum value that this field could have, given the current date.
* @deprecated ICU 2.6. Use getActualMaximum(UCalendarDateFields field) instead.
*/
int32_t getActualMaximum(EDateFields field) const;
#endif /* U_HIDE_DEPRECATED_API */
/**
* Return the maximum value that this field could have, given the current date.
* For example, with the date "Feb 3, 1997" and the DAY_OF_MONTH field, the actual
* maximum would be 28; for "Feb 3, 1996" it s 29. Similarly for a Hebrew calendar,
* for some years the actual maximum for MONTH is 12, and for others 13.
* @param field the time field.
* @param status returns any errors that may result from this function call.
* @return the maximum value that this field could have, given the current date.
* @stable ICU 2.6
*/
virtual int32_t getActualMaximum(UCalendarDateFields field, UErrorCode& status) const;
/**
* (Overrides Calendar) Return true if the current date for this Calendar is in
* Daylight Savings Time. Recognizes DST_OFFSET, if it is set.
*
* @param status Fill-in parameter which receives the status of this operation.
* @return True if the current date for this Calendar is in Daylight Savings Time,
* false, otherwise.
* @stable ICU 2.0
*/
virtual UBool inDaylightTime(UErrorCode& status) const;
public:
/**
* Override Calendar Returns a unique class ID POLYMORPHICALLY. Pure virtual
* override. This method is to implement a simple version of RTTI, since not all C++
* compilers support genuine RTTI. Polymorphic operator==() and clone() methods call
* this method.
*
* @return The class ID for this object. All objects of a given class have the
* same class ID. Objects of other classes have different class IDs.
* @stable ICU 2.0
*/
virtual UClassID getDynamicClassID(void) const;
/**
* Return the class ID for this class. This is useful only for comparing to a return
* value from getDynamicClassID(). For example:
*
* Base* polymorphic_pointer = createPolymorphicObject();
* if (polymorphic_pointer->getDynamicClassID() ==
* Derived::getStaticClassID()) ...
*
* @return The class ID for all objects of this class.
* @stable ICU 2.0
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Returns the calendar type name string for this Calendar object.
* The returned string is the legacy ICU calendar attribute value,
* for example, "gregorian" or "japanese".
*
* For more details see the Calendar::getType() documentation.
*
* @return legacy calendar type name string
* @stable ICU 49
*/
virtual const char * getType() const;
private:
GregorianCalendar(); // default constructor not implemented
protected:
/**
* Return the ERA. We need a special method for this because the
* default ERA is AD, but a zero (unset) ERA is BC.
* @return the ERA.
* @internal
*/
virtual int32_t internalGetEra() const;
/**
* Return the Julian day number of day before the first day of the
* given month in the given extended year. Subclasses should override
* this method to implement their calendar system.
* @param eyear the extended year
* @param month the zero-based month, or 0 if useMonth is false
* @param useMonth if false, compute the day before the first day of
* the given year, otherwise, compute the day before the first day of
* the given month
* @return the Julian day number of the day before the first
* day of the given month and year
* @internal
*/
virtual int32_t handleComputeMonthStart(int32_t eyear, int32_t month,
UBool useMonth) const;
/**
* Subclasses may override this. This method calls
* handleGetMonthLength() to obtain the calendar-specific month
* length.
* @param bestField which field to use to calculate the date
* @return julian day specified by calendar fields.
* @internal
*/
virtual int32_t handleComputeJulianDay(UCalendarDateFields bestField) ;
/**
* Return the number of days in the given month of the given extended
* year of this calendar system. Subclasses should override this
* method if they can provide a more correct or more efficient
* implementation than the default implementation in Calendar.
* @internal
*/
virtual int32_t handleGetMonthLength(int32_t extendedYear, int32_t month) const;
/**
* Return the number of days in the given extended year of this
* calendar system. Subclasses should override this method if they can
* provide a more correct or more efficient implementation than the
* default implementation in Calendar.
* @stable ICU 2.0
*/
virtual int32_t handleGetYearLength(int32_t eyear) const;
/**
* return the length of the given month.
* @param month the given month.
* @return the length of the given month.
* @internal
*/
virtual int32_t monthLength(int32_t month) const;
/**
* return the length of the month according to the given year.
* @param month the given month.
* @param year the given year.
* @return the length of the month
* @internal
*/
virtual int32_t monthLength(int32_t month, int32_t year) const;
#ifndef U_HIDE_INTERNAL_API
/**
* return the length of the given year.
* @param year the given year.
* @return the length of the given year.
* @internal
*/
int32_t yearLength(int32_t year) const;
/**
* return the length of the year field.
* @return the length of the year field
* @internal
*/
int32_t yearLength(void) const;
/**
* After adjustments such as add(MONTH), add(YEAR), we don't want the
* month to jump around. E.g., we don't want Jan 31 + 1 month to go to Mar
* 3, we want it to go to Feb 28. Adjustments which might run into this
* problem call this method to retain the proper month.
* @internal
*/
void pinDayOfMonth(void);
#endif /* U_HIDE_INTERNAL_API */
/**
* Return the day number with respect to the epoch. January 1, 1970 (Gregorian)
* is day zero.
* @param status Fill-in parameter which receives the status of this operation.
* @return the day number with respect to the epoch.
* @internal
*/
virtual UDate getEpochDay(UErrorCode& status);
/**
* Subclass API for defining limits of different types.
* Subclasses must implement this method to return limits for the
* following fields:
*
* <pre>UCAL_ERA
* UCAL_YEAR
* UCAL_MONTH
* UCAL_WEEK_OF_YEAR
* UCAL_WEEK_OF_MONTH
* UCAL_DATE (DAY_OF_MONTH on Java)
* UCAL_DAY_OF_YEAR
* UCAL_DAY_OF_WEEK_IN_MONTH
* UCAL_YEAR_WOY
* UCAL_EXTENDED_YEAR</pre>
*
* @param field one of the above field numbers
* @param limitType one of <code>MINIMUM</code>, <code>GREATEST_MINIMUM</code>,
* <code>LEAST_MAXIMUM</code>, or <code>MAXIMUM</code>
* @internal
*/
virtual int32_t handleGetLimit(UCalendarDateFields field, ELimitType limitType) const;
/**
* Return the extended year defined by the current fields. This will
* use the UCAL_EXTENDED_YEAR field or the UCAL_YEAR and supra-year fields (such
* as UCAL_ERA) specific to the calendar system, depending on which set of
* fields is newer.
* @return the extended year
* @internal
*/
virtual int32_t handleGetExtendedYear();
/**
* Subclasses may override this to convert from week fields
* (YEAR_WOY and WEEK_OF_YEAR) to an extended year in the case
* where YEAR, EXTENDED_YEAR are not set.
* The Gregorian implementation assumes a yearWoy in gregorian format, according to the current era.
* @return the extended year, UCAL_EXTENDED_YEAR
* @internal
*/
virtual int32_t handleGetExtendedYearFromWeekFields(int32_t yearWoy, int32_t woy);
/**
* Subclasses may override this method to compute several fields
* specific to each calendar system. These are:
*
* <ul><li>ERA
* <li>YEAR
* <li>MONTH
* <li>DAY_OF_MONTH
* <li>DAY_OF_YEAR
* <li>EXTENDED_YEAR</ul>
*
* <p>The GregorianCalendar implementation implements
* a calendar with the specified Julian/Gregorian cutover date.
* @internal
*/
virtual void handleComputeFields(int32_t julianDay, UErrorCode &status);
private:
/**
* Compute the julian day number of the given year.
* @param isGregorian if true, using Gregorian calendar, otherwise using Julian calendar
* @param year the given year.
* @param isLeap true if the year is a leap year.
* @return
*/
static double computeJulianDayOfYear(UBool isGregorian, int32_t year,
UBool& isLeap);
/**
* Validates the values of the set time fields. True if they're all valid.
* @return True if the set time fields are all valid.
*/
UBool validateFields(void) const;
/**
* Validates the value of the given time field. True if it's valid.
*/
UBool boundsCheck(int32_t value, UCalendarDateFields field) const;
/**
* Return the pseudo-time-stamp for two fields, given their
* individual pseudo-time-stamps. If either of the fields
* is unset, then the aggregate is unset. Otherwise, the
* aggregate is the later of the two stamps.
* @param stamp_a One given field.
* @param stamp_b Another given field.
* @return the pseudo-time-stamp for two fields
*/
int32_t aggregateStamp(int32_t stamp_a, int32_t stamp_b);
/**
* The point at which the Gregorian calendar rules are used, measured in
* milliseconds from the standard epoch. Default is October 15, 1582
* (Gregorian) 00:00:00 UTC, that is, October 4, 1582 (Julian) is followed
* by October 15, 1582 (Gregorian). This corresponds to Julian day number
* 2299161. This is measured from the standard epoch, not in Julian Days.
*/
UDate fGregorianCutover;
/**
* Julian day number of the Gregorian cutover
*/
int32_t fCutoverJulianDay;
/**
* Midnight, local time (using this Calendar's TimeZone) at or before the
* gregorianCutover. This is a pure date value with no time of day or
* timezone component.
*/
UDate fNormalizedGregorianCutover;// = gregorianCutover;
/**
* The year of the gregorianCutover, with 0 representing
* 1 BC, -1 representing 2 BC, etc.
*/
int32_t fGregorianCutoverYear;// = 1582;
/**
* The year of the gregorianCutover, with 0 representing
* 1 BC, -1 representing 2 BC, etc.
*/
int32_t fGregorianCutoverJulianDay;// = 2299161;
/**
* Converts time as milliseconds to Julian date. The Julian date used here is not a
* true Julian date, since it is measured from midnight, not noon.
*
* @param millis The given milliseconds.
* @return The Julian date number.
*/
static double millisToJulianDay(UDate millis);
/**
* Converts Julian date to time as milliseconds. The Julian date used here is not a
* true Julian date, since it is measured from midnight, not noon.
*
* @param julian The given Julian date number.
* @return Time as milliseconds.
*/
static UDate julianDayToMillis(double julian);
/**
* Used by handleComputeJulianDay() and handleComputeMonthStart().
* Temporary field indicating whether the calendar is currently Gregorian as opposed to Julian.
*/
UBool fIsGregorian;
/**
* Used by handleComputeJulianDay() and handleComputeMonthStart().
* Temporary field indicating that the sense of the gregorian cutover should be inverted
* to handle certain calculations on and around the cutover date.
*/
UBool fInvertGregorian;
public: // internal implementation
/**
* @return TRUE if this calendar has the notion of a default century
* @internal
*/
virtual UBool haveDefaultCentury() const;
/**
* @return the start of the default century
* @internal
*/
virtual UDate defaultCenturyStart() const;
/**
* @return the beginning year of the default century
* @internal
*/
virtual int32_t defaultCenturyStartYear() const;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _GREGOCAL
//eof
project/jni/icuuc/include/unicode/icudataver.h
-41
View File
@@ -1,41 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 2009-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*/
/**
* \file
* \brief C API: access to ICU Data Version number
*/
#ifndef __ICU_DATA_VER_H__
#define __ICU_DATA_VER_H__
#include "unicode/utypes.h"
/**
* @stable ICU 49
*/
#define U_ICU_VERSION_BUNDLE "icuver"
/**
* @stable ICU 49
*/
#define U_ICU_DATA_KEY "DataVersion"
/**
* Retrieves the data version from icuver and stores it in dataVersionFillin.
*
* @param dataVersionFillin icuver data version information to be filled in if not-null
* @param status stores the error code from the calls to resource bundle
*
* @stable ICU 49
*/
U_STABLE void U_EXPORT2 u_getDataVersion(UVersionInfo dataVersionFillin, UErrorCode *status);
#endif
project/jni/icuuc/include/unicode/icuplug.h
-371
View File
@@ -1,371 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 2009-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* FILE NAME : icuplug.h
*
* Date Name Description
* 10/29/2009 sl New.
******************************************************************************
*/
/**
* \file
* \brief C API: ICU Plugin API
*
* <h2>C API: ICU Plugin API</h2>
*
* <p>C API allowing run-time loadable modules that extend or modify ICU functionality.</p>
*
* <h3>Loading and Configuration</h3>
*
* <p>At ICU startup time, the environment variable "ICU_PLUGINS" will be
* queried for a directory name. If it is not set, the preprocessor symbol
* "DEFAULT_ICU_PLUGINS" will be checked for a default value.</p>
*
* <p>Within the above-named directory, the file "icuplugins##.txt" will be
* opened, if present, where ## is the major+minor number of the currently
* running ICU (such as, 44 for ICU 4.4, thus icuplugins44.txt)</p>
*
* <p>The configuration file has this format:</p>
*
* <ul>
* <li>Hash (#) begins a comment line</li>
*
* <li>Non-comment lines have two or three components:
* LIBRARYNAME ENTRYPOINT [ CONFIGURATION .. ]</li>
*
* <li>Tabs or spaces separate the three items.</li>
*
* <li>LIBRARYNAME is the name of a shared library, either a short name if
* it is on the loader path, or a full pathname.</li>
*
* <li>ENTRYPOINT is the short (undecorated) symbol name of the plugin's
* entrypoint, as above.</li>
*
* <li>CONFIGURATION is the entire rest of the line . It's passed as-is to
* the plugin.</li>
* </ul>
*
* <p>An example configuration file is, in its entirety:</p>
*
* \code
* # this is icuplugins44.txt
* testplug.dll myPlugin hello=world
* \endcode
* <p>Plugins are categorized as "high" or "low" level. Low level are those
* which must be run BEFORE high level plugins, and before any operations
* which cause ICU to be 'initialized'. If a plugin is low level but
* causes ICU to allocate memory or become initialized, that plugin is said
* to cause a 'level change'. </p>
*
* <p>At load time, ICU first queries all plugins to determine their level,
* then loads all 'low' plugins first, and then loads all 'high' plugins.
* Plugins are otherwise loaded in the order listed in the configuration file.</p>
*
* <h3>Implementing a Plugin</h3>
* \code
* U_CAPI UPlugTokenReturn U_EXPORT2
* myPlugin (UPlugData *plug, UPlugReason reason, UErrorCode *status) {
* if(reason==UPLUG_REASON_QUERY) {
* uplug_setPlugName(plug, "Simple Plugin");
* uplug_setPlugLevel(plug, UPLUG_LEVEL_HIGH);
* } else if(reason==UPLUG_REASON_LOAD) {
* ... Set up some ICU things here....
* } else if(reason==UPLUG_REASON_UNLOAD) {
* ... unload, clean up ...
* }
* return UPLUG_TOKEN;
* }
* \endcode
*
* <p>The UPlugData* is an opaque pointer to the plugin-specific data, and is
* used in all other API calls.</p>
*
* <p>The API contract is:</p>
* <ol><li>The plugin MUST always return UPLUG_TOKEN as a return value- to
* indicate that it is a valid plugin.</li>
*
* <li>When the 'reason' parameter is set to UPLUG_REASON_QUERY, the
* plugin MUST call uplug_setPlugLevel() to indicate whether it is a high
* level or low level plugin.</li>
*
* <li>When the 'reason' parameter is UPLUG_REASON_QUERY, the plugin
* SHOULD call uplug_setPlugName to indicate a human readable plugin name.</li></ol>
*
*
* \internal ICU 4.4 Technology Preview
*/
#ifndef ICUPLUG_H
#define ICUPLUG_H
#include "unicode/utypes.h"
/* === Basic types === */
#ifndef U_HIDE_INTERNAL_API
/**
* @{
* Opaque structure passed to/from a plugin.
* use the APIs to access it.
* @internal ICU 4.4 Technology Preview
*/
struct UPlugData;
typedef struct UPlugData UPlugData;
/** @} */
/**
* Random Token to identify a valid ICU plugin. Plugins must return this
* from the entrypoint.
* @internal ICU 4.4 Technology Preview
*/
#define UPLUG_TOKEN 0x54762486
/**
* Max width of names, symbols, and configuration strings
* @internal ICU 4.4 Technology Preview
*/
#define UPLUG_NAME_MAX 100
/**
* Return value from a plugin entrypoint.
* Must always be set to UPLUG_TOKEN
* @see UPLUG_TOKEN
* @internal ICU 4.4 Technology Preview
*/
typedef uint32_t UPlugTokenReturn;
/**
* Reason code for the entrypoint's call
* @internal ICU 4.4 Technology Preview
*/
typedef enum {
UPLUG_REASON_QUERY = 0, /**< The plugin is being queried for info. **/
UPLUG_REASON_LOAD = 1, /**< The plugin is being loaded. **/
UPLUG_REASON_UNLOAD = 2, /**< The plugin is being unloaded. **/
UPLUG_REASON_COUNT /**< count of known reasons **/
} UPlugReason;
/**
* Level of plugin loading
* INITIAL: UNKNOWN
* QUERY: INVALID -> { LOW | HIGH }
* ERR -> INVALID
* @internal ICU 4.4 Technology Preview
*/
typedef enum {
UPLUG_LEVEL_INVALID = 0, /**< The plugin is invalid, hasn't called uplug_setLevel, or can't load. **/
UPLUG_LEVEL_UNKNOWN = 1, /**< The plugin is waiting to be installed. **/
UPLUG_LEVEL_LOW = 2, /**< The plugin must be called before u_init completes **/
UPLUG_LEVEL_HIGH = 3, /**< The plugin can run at any time. **/
UPLUG_LEVEL_COUNT /**< count of known reasons **/
} UPlugLevel;
/**
* Entrypoint for an ICU plugin.
* @param plug the UPlugData handle.
* @param status the plugin's extended status code.
* @return A valid plugin must return UPLUG_TOKEN
* @internal ICU 4.4 Technology Preview
*/
typedef UPlugTokenReturn (U_EXPORT2 UPlugEntrypoint) (
UPlugData *plug,
UPlugReason reason,
UErrorCode *status);
/* === Needed for Implementing === */
/**
* Request that this plugin not be unloaded at cleanup time.
* This is appropriate for plugins which cannot be cleaned up.
* @see u_cleanup()
* @param plug plugin
* @param dontUnload set true if this plugin can't be unloaded
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void U_EXPORT2
uplug_setPlugNoUnload(UPlugData *plug, UBool dontUnload);
/**
* Set the level of this plugin.
* @param plug plugin data handle
* @param level the level of this plugin
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void U_EXPORT2
uplug_setPlugLevel(UPlugData *plug, UPlugLevel level);
/**
* Get the level of this plugin.
* @param plug plugin data handle
* @return the level of this plugin
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL UPlugLevel U_EXPORT2
uplug_getPlugLevel(UPlugData *plug);
/**
* Get the lowest level of plug which can currently load.
* For example, if UPLUG_LEVEL_LOW is returned, then low level plugins may load
* if UPLUG_LEVEL_HIGH is returned, then only high level plugins may load.
* @return the lowest level of plug which can currently load
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL UPlugLevel U_EXPORT2
uplug_getCurrentLevel(void);
/**
* Get plug load status
* @return The error code of this plugin's load attempt.
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL UErrorCode U_EXPORT2
uplug_getPlugLoadStatus(UPlugData *plug);
/**
* Set the human-readable name of this plugin.
* @param plug plugin data handle
* @param name the name of this plugin. The first UPLUG_NAME_MAX characters willi be copied into a new buffer.
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void U_EXPORT2
uplug_setPlugName(UPlugData *plug, const char *name);
/**
* Get the human-readable name of this plugin.
* @param plug plugin data handle
* @return the name of this plugin
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL const char * U_EXPORT2
uplug_getPlugName(UPlugData *plug);
/**
* Return the symbol name for this plugin, if known.
* @param plug plugin data handle
* @return the symbol name, or NULL
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL const char * U_EXPORT2
uplug_getSymbolName(UPlugData *plug);
/**
* Return the library name for this plugin, if known.
* @param plug plugin data handle
* @param status error code
* @return the library name, or NULL
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL const char * U_EXPORT2
uplug_getLibraryName(UPlugData *plug, UErrorCode *status);
/**
* Return the library used for this plugin, if known.
* Plugins could use this to load data out of their
* @param plug plugin data handle
* @return the library, or NULL
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void * U_EXPORT2
uplug_getLibrary(UPlugData *plug);
/**
* Return the plugin-specific context data.
* @param plug plugin data handle
* @return the context, or NULL if not set
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void * U_EXPORT2
uplug_getContext(UPlugData *plug);
/**
* Set the plugin-specific context data.
* @param plug plugin data handle
* @param context new context to set
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void U_EXPORT2
uplug_setContext(UPlugData *plug, void *context);
/**
* Get the configuration string, if available.
* The string is in the platform default codepage.
* @param plug plugin data handle
* @return configuration string, or else null.
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL const char * U_EXPORT2
uplug_getConfiguration(UPlugData *plug);
/**
* Return all currently installed plugins, from newest to oldest
* Usage Example:
* \code
* UPlugData *plug = NULL;
* while(plug=uplug_nextPlug(plug)) {
* ... do something with 'plug' ...
* }
* \endcode
* Not thread safe- do not call while plugs are added or removed.
* @param prior pass in 'NULL' to get the first (most recent) plug,
* otherwise pass the value returned on a prior call to uplug_nextPlug
* @return the next oldest plugin, or NULL if no more.
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL UPlugData* U_EXPORT2
uplug_nextPlug(UPlugData *prior);
/**
* Inject a plugin as if it were loaded from a library.
* This is useful for testing plugins.
* Note that it will have a 'NULL' library pointer associated
* with it, and therefore no llibrary will be closed at cleanup time.
* Low level plugins may not be able to load, as ordering can't be enforced.
* @param entrypoint entrypoint to install
* @param config user specified configuration string, if available, or NULL.
* @param status error result
* @return the new UPlugData associated with this plugin, or NULL if error.
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL UPlugData* U_EXPORT2
uplug_loadPlugFromEntrypoint(UPlugEntrypoint *entrypoint, const char *config, UErrorCode *status);
/**
* Inject a plugin from a library, as if the information came from a config file.
* Low level plugins may not be able to load, and ordering can't be enforced.
* @param libName DLL name to load
* @param sym symbol of plugin (UPlugEntrypoint function)
* @param config configuration string, or NULL
* @param status error result
* @return the new UPlugData associated with this plugin, or NULL if error.
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL UPlugData* U_EXPORT2
uplug_loadPlugFromLibrary(const char *libName, const char *sym, const char *config, UErrorCode *status);
/**
* Remove a plugin.
* Will request the plugin to be unloaded, and close the library if needed
* @param plug plugin handle to close
* @param status error result
* @internal ICU 4.4 Technology Preview
*/
U_INTERNAL void U_EXPORT2
uplug_removePlug(UPlugData *plug, UErrorCode *status);
#endif /* U_HIDE_INTERNAL_API */
#endif
project/jni/icuuc/include/unicode/idna.h
-323
View File
@@ -1,323 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2010-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: idna.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2010mar05
* created by: Markus W. Scherer
*/
#ifndef __IDNA_H__
#define __IDNA_H__
/**
* \file
* \brief C++ API: Internationalizing Domain Names in Applications (IDNA)
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_IDNA
#include "unicode/bytestream.h"
#include "unicode/stringpiece.h"
#include "unicode/uidna.h"
#include "unicode/unistr.h"
U_NAMESPACE_BEGIN
class IDNAInfo;
/**
* Abstract base class for IDNA processing.
* See http://www.unicode.org/reports/tr46/
* and http://www.ietf.org/rfc/rfc3490.txt
*
* The IDNA class is not intended for public subclassing.
*
* This C++ API currently only implements UTS #46.
* The uidna.h C API implements both UTS #46 (functions using UIDNA service object)
* and IDNA2003 (functions that do not use a service object).
* @stable ICU 4.6
*/
class U_COMMON_API IDNA : public UObject {
public:
/**
* Destructor.
* @stable ICU 4.6
*/
~IDNA();
/**
* Returns an IDNA instance which implements UTS #46.
* Returns an unmodifiable instance, owned by the caller.
* Cache it for multiple operations, and delete it when done.
* The instance is thread-safe, that is, it can be used concurrently.
*
* UTS #46 defines Unicode IDNA Compatibility Processing,
* updated to the latest version of Unicode and compatible with both
* IDNA2003 and IDNA2008.
*
* The worker functions use transitional processing, including deviation mappings,
* unless UIDNA_NONTRANSITIONAL_TO_ASCII or UIDNA_NONTRANSITIONAL_TO_UNICODE
* is used in which case the deviation characters are passed through without change.
*
* Disallowed characters are mapped to U+FFFD.
*
* For available options see the uidna.h header.
* Operations with the UTS #46 instance do not support the
* UIDNA_ALLOW_UNASSIGNED option.
*
* By default, the UTS #46 implementation allows all ASCII characters (as valid or mapped).
* When the UIDNA_USE_STD3_RULES option is used, ASCII characters other than
* letters, digits, hyphen (LDH) and dot/full stop are disallowed and mapped to U+FFFD.
*
* @param options Bit set to modify the processing and error checking.
* See option bit set values in uidna.h.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the UTS #46 IDNA instance, if successful
* @stable ICU 4.6
*/
static IDNA *
createUTS46Instance(uint32_t options, UErrorCode &errorCode);
/**
* Converts a single domain name label into its ASCII form for DNS lookup.
* If any processing step fails, then info.hasErrors() will be TRUE and
* the result might not be an ASCII string.
* The label might be modified according to the types of errors.
* Labels with severe errors will be left in (or turned into) their Unicode form.
*
* The UErrorCode indicates an error only in exceptional cases,
* such as a U_MEMORY_ALLOCATION_ERROR.
*
* @param label Input domain name label
* @param dest Destination string object
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual UnicodeString &
labelToASCII(const UnicodeString &label, UnicodeString &dest,
IDNAInfo &info, UErrorCode &errorCode) const = 0;
/**
* Converts a single domain name label into its Unicode form for human-readable display.
* If any processing step fails, then info.hasErrors() will be TRUE.
* The label might be modified according to the types of errors.
*
* The UErrorCode indicates an error only in exceptional cases,
* such as a U_MEMORY_ALLOCATION_ERROR.
*
* @param label Input domain name label
* @param dest Destination string object
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual UnicodeString &
labelToUnicode(const UnicodeString &label, UnicodeString &dest,
IDNAInfo &info, UErrorCode &errorCode) const = 0;
/**
* Converts a whole domain name into its ASCII form for DNS lookup.
* If any processing step fails, then info.hasErrors() will be TRUE and
* the result might not be an ASCII string.
* The domain name might be modified according to the types of errors.
* Labels with severe errors will be left in (or turned into) their Unicode form.
*
* The UErrorCode indicates an error only in exceptional cases,
* such as a U_MEMORY_ALLOCATION_ERROR.
*
* @param name Input domain name
* @param dest Destination string object
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual UnicodeString &
nameToASCII(const UnicodeString &name, UnicodeString &dest,
IDNAInfo &info, UErrorCode &errorCode) const = 0;
/**
* Converts a whole domain name into its Unicode form for human-readable display.
* If any processing step fails, then info.hasErrors() will be TRUE.
* The domain name might be modified according to the types of errors.
*
* The UErrorCode indicates an error only in exceptional cases,
* such as a U_MEMORY_ALLOCATION_ERROR.
*
* @param name Input domain name
* @param dest Destination string object
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual UnicodeString &
nameToUnicode(const UnicodeString &name, UnicodeString &dest,
IDNAInfo &info, UErrorCode &errorCode) const = 0;
// UTF-8 versions of the processing methods ---------------------------- ***
/**
* Converts a single domain name label into its ASCII form for DNS lookup.
* UTF-8 version of labelToASCII(), same behavior.
*
* @param label Input domain name label
* @param dest Destination byte sink; Flush()ed if successful
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual void
labelToASCII_UTF8(const StringPiece &label, ByteSink &dest,
IDNAInfo &info, UErrorCode &errorCode) const;
/**
* Converts a single domain name label into its Unicode form for human-readable display.
* UTF-8 version of labelToUnicode(), same behavior.
*
* @param label Input domain name label
* @param dest Destination byte sink; Flush()ed if successful
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual void
labelToUnicodeUTF8(const StringPiece &label, ByteSink &dest,
IDNAInfo &info, UErrorCode &errorCode) const;
/**
* Converts a whole domain name into its ASCII form for DNS lookup.
* UTF-8 version of nameToASCII(), same behavior.
*
* @param name Input domain name
* @param dest Destination byte sink; Flush()ed if successful
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual void
nameToASCII_UTF8(const StringPiece &name, ByteSink &dest,
IDNAInfo &info, UErrorCode &errorCode) const;
/**
* Converts a whole domain name into its Unicode form for human-readable display.
* UTF-8 version of nameToUnicode(), same behavior.
*
* @param name Input domain name
* @param dest Destination byte sink; Flush()ed if successful
* @param info Output container of IDNA processing details.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.6
*/
virtual void
nameToUnicodeUTF8(const StringPiece &name, ByteSink &dest,
IDNAInfo &info, UErrorCode &errorCode) const;
};
class UTS46;
/**
* Output container for IDNA processing errors.
* The IDNAInfo class is not suitable for subclassing.
* @stable ICU 4.6
*/
class U_COMMON_API IDNAInfo : public UMemory {
public:
/**
* Constructor for stack allocation.
* @stable ICU 4.6
*/
IDNAInfo() : errors(0), labelErrors(0), isTransDiff(FALSE), isBiDi(FALSE), isOkBiDi(TRUE) {}
/**
* Were there IDNA processing errors?
* @return TRUE if there were processing errors
* @stable ICU 4.6
*/
UBool hasErrors() const { return errors!=0; }
/**
* Returns a bit set indicating IDNA processing errors.
* See UIDNA_ERROR_... constants in uidna.h.
* @return bit set of processing errors
* @stable ICU 4.6
*/
uint32_t getErrors() const { return errors; }
/**
* Returns TRUE if transitional and nontransitional processing produce different results.
* This is the case when the input label or domain name contains
* one or more deviation characters outside a Punycode label (see UTS #46).
* <ul>
* <li>With nontransitional processing, such characters are
* copied to the destination string.
* <li>With transitional processing, such characters are
* mapped (sharp s/sigma) or removed (joiner/nonjoiner).
* </ul>
* @return TRUE if transitional and nontransitional processing produce different results
* @stable ICU 4.6
*/
UBool isTransitionalDifferent() const { return isTransDiff; }
private:
friend class UTS46;
IDNAInfo(const IDNAInfo &other); // no copying
IDNAInfo &operator=(const IDNAInfo &other); // no copying
void reset() {
errors=labelErrors=0;
isTransDiff=FALSE;
isBiDi=FALSE;
isOkBiDi=TRUE;
}
uint32_t errors, labelErrors;
UBool isTransDiff;
UBool isBiDi;
UBool isOkBiDi;
};
U_NAMESPACE_END
#endif // UCONFIG_NO_IDNA
#endif // __IDNA_H__
project/jni/icuuc/include/unicode/listformatter.h
-155
View File
@@ -1,155 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2012-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: listformatter.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 20120426
* created by: Umesh P. Nair
*/
#ifndef __LISTFORMATTER_H__
#define __LISTFORMATTER_H__
#include "unicode/utypes.h"
#ifndef U_HIDE_DRAFT_API
#include "unicode/unistr.h"
#include "unicode/locid.h"
U_NAMESPACE_BEGIN
/** @internal */
class Hashtable;
#ifndef U_HIDE_INTERNAL_API
/** @internal */
struct ListFormatData : public UMemory {
UnicodeString twoPattern;
UnicodeString startPattern;
UnicodeString middlePattern;
UnicodeString endPattern;
ListFormatData(const UnicodeString& two, const UnicodeString& start, const UnicodeString& middle, const UnicodeString& end) :
twoPattern(two), startPattern(start), middlePattern(middle), endPattern(end) {}
};
#endif /* U_HIDE_INTERNAL_API */
/**
* \file
* \brief C++ API: API for formatting a list.
*/
/**
* An immutable class for formatting a list, using data from CLDR (or supplied
* separately).
*
* Example: Input data ["Alice", "Bob", "Charlie", "Delta"] will be formatted
* as "Alice, Bob, Charlie and Delta" in English.
*
* The ListFormatter class is not intended for public subclassing.
* @draft ICU 50
*/
class U_COMMON_API ListFormatter : public UObject{
public:
/**
* Copy constructor.
* @draft ICU 52
*/
ListFormatter(const ListFormatter&);
/**
* Assignment operator.
* @draft ICU 52
*/
ListFormatter& operator=(const ListFormatter& other);
/**
* Creates a ListFormatter appropriate for the default locale.
*
* @param errorCode ICU error code, set if no data available for default locale.
* @return Pointer to a ListFormatter object for the default locale,
* created from internal data derived from CLDR data.
* @draft ICU 50
*/
static ListFormatter* createInstance(UErrorCode& errorCode);
/**
* Creates a ListFormatter appropriate for a locale.
*
* @param locale The locale.
* @param errorCode ICU error code, set if no data available for the given locale.
* @return A ListFormatter object created from internal data derived from
* CLDR data.
* @draft ICU 50
*/
static ListFormatter* createInstance(const Locale& locale, UErrorCode& errorCode);
#ifndef U_HIDE_INTERNAL_API
/**
* Creates a ListFormatter appropriate for a locale and style.
*
* @param locale The locale.
* @param style the style, either "standard", "duration", or "duration-short"
* @param errorCode ICU error code, set if no data available for the given locale.
* @return A ListFormatter object created from internal data derived from
* CLDR data.
* @internal
*/
static ListFormatter* createInstance(const Locale& locale, const char* style, UErrorCode& errorCode);
#endif /* U_HIDE_INTERNAL_API */
/**
* Destructor.
*
* @draft ICU 50
*/
virtual ~ListFormatter();
/**
* Formats a list of strings.
*
* @param items An array of strings to be combined and formatted.
* @param n_items Length of the array items.
* @param appendTo The string to which the result should be appended to.
* @param errorCode ICU error code, set if there is an error.
* @return Formatted string combining the elements of items, appended to appendTo.
* @draft ICU 50
*/
UnicodeString& format(const UnicodeString items[], int32_t n_items,
UnicodeString& appendTo, UErrorCode& errorCode) const;
#ifndef U_HIDE_INTERNAL_API
/**
* @internal constructor made public for testing.
*/
ListFormatter(const ListFormatData* listFormatterData);
#endif /* U_HIDE_INTERNAL_API */
private:
static void initializeHash(UErrorCode& errorCode);
static const ListFormatData* getListFormatData(const Locale& locale, const char *style, UErrorCode& errorCode);
ListFormatter();
void addNewString(const UnicodeString& pattern, UnicodeString& originalString,
const UnicodeString& newString, UErrorCode& errorCode) const;
const ListFormatData* data;
};
U_NAMESPACE_END
#endif /* U_HIDE_DRAFT_API */
#endif
project/jni/icuuc/include/unicode/localpointer.h
-304
View File
@@ -1,304 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2009-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: localpointer.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2009nov13
* created by: Markus W. Scherer
*/
#ifndef __LOCALPOINTER_H__
#define __LOCALPOINTER_H__
/**
* \file
* \brief C++ API: "Smart pointers" for use with and in ICU4C C++ code.
*
* These classes are inspired by
* - std::auto_ptr
* - boost::scoped_ptr & boost::scoped_array
* - Taligent Safe Pointers (TOnlyPointerTo)
*
* but none of those provide for all of the goals for ICU smart pointers:
* - Smart pointer owns the object and releases it when it goes out of scope.
* - No transfer of ownership via copy/assignment to reduce misuse. Simpler & more robust.
* - ICU-compatible: No exceptions.
* - Need to be able to orphan/release the pointer and its ownership.
* - Need variants for normal C++ object pointers, C++ arrays, and ICU C service objects.
*
* For details see http://site.icu-project.org/design/cpp/scoped_ptr
*/
#include "unicode/utypes.h"
#if U_SHOW_CPLUSPLUS_API
U_NAMESPACE_BEGIN
/**
* "Smart pointer" base class; do not use directly: use LocalPointer etc.
*
* Base class for smart pointer classes that do not throw exceptions.
*
* Do not use this base class directly, since it does not delete its pointer.
* A subclass must implement methods that delete the pointer:
* Destructor and adoptInstead().
*
* There is no operator T *() provided because the programmer must decide
* whether to use getAlias() (without transfer of ownership) or orpan()
* (with transfer of ownership and NULLing of the pointer).
*
* @see LocalPointer
* @see LocalArray
* @see U_DEFINE_LOCAL_OPEN_POINTER
* @stable ICU 4.4
*/
template<typename T>
class LocalPointerBase {
public:
/**
* Constructor takes ownership.
* @param p simple pointer to an object that is adopted
* @stable ICU 4.4
*/
explicit LocalPointerBase(T *p=NULL) : ptr(p) {}
/**
* Destructor deletes the object it owns.
* Subclass must override: Base class does nothing.
* @stable ICU 4.4
*/
~LocalPointerBase() { /* delete ptr; */ }
/**
* NULL check.
* @return TRUE if ==NULL
* @stable ICU 4.4
*/
UBool isNull() const { return ptr==NULL; }
/**
* NULL check.
* @return TRUE if !=NULL
* @stable ICU 4.4
*/
UBool isValid() const { return ptr!=NULL; }
/**
* Comparison with a simple pointer, so that existing code
* with ==NULL need not be changed.
* @param other simple pointer for comparison
* @return true if this pointer value equals other
* @stable ICU 4.4
*/
bool operator==(const T *other) const { return ptr==other; }
/**
* Comparison with a simple pointer, so that existing code
* with !=NULL need not be changed.
* @param other simple pointer for comparison
* @return true if this pointer value differs from other
* @stable ICU 4.4
*/
bool operator!=(const T *other) const { return ptr!=other; }
/**
* Access without ownership change.
* @return the pointer value
* @stable ICU 4.4
*/
T *getAlias() const { return ptr; }
/**
* Access without ownership change.
* @return the pointer value as a reference
* @stable ICU 4.4
*/
T &operator*() const { return *ptr; }
/**
* Access without ownership change.
* @return the pointer value
* @stable ICU 4.4
*/
T *operator->() const { return ptr; }
/**
* Gives up ownership; the internal pointer becomes NULL.
* @return the pointer value;
* caller becomes responsible for deleting the object
* @stable ICU 4.4
*/
T *orphan() {
T *p=ptr;
ptr=NULL;
return p;
}
/**
* Deletes the object it owns,
* and adopts (takes ownership of) the one passed in.
* Subclass must override: Base class does not delete the object.
* @param p simple pointer to an object that is adopted
* @stable ICU 4.4
*/
void adoptInstead(T *p) {
// delete ptr;
ptr=p;
}
protected:
/**
* Actual pointer.
* @internal
*/
T *ptr;
private:
// No comparison operators with other LocalPointerBases.
bool operator==(const LocalPointerBase &other);
bool operator!=(const LocalPointerBase &other);
// No ownership transfer: No copy constructor, no assignment operator.
LocalPointerBase(const LocalPointerBase &other);
void operator=(const LocalPointerBase &other);
// No heap allocation. Use only on the stack.
static void * U_EXPORT2 operator new(size_t size);
static void * U_EXPORT2 operator new[](size_t size);
#if U_HAVE_PLACEMENT_NEW
static void * U_EXPORT2 operator new(size_t, void *ptr);
#endif
};
/**
* "Smart pointer" class, deletes objects via the standard C++ delete operator.
* For most methods see the LocalPointerBase base class.
*
* Usage example:
* \code
* LocalPointer<UnicodeString> s(new UnicodeString((UChar32)0x50005));
* int32_t length=s->length(); // 2
* UChar lead=s->charAt(0); // 0xd900
* if(some condition) { return; } // no need to explicitly delete the pointer
* s.adoptInstead(new UnicodeString((UChar)0xfffc));
* length=s->length(); // 1
* // no need to explicitly delete the pointer
* \endcode
*
* @see LocalPointerBase
* @stable ICU 4.4
*/
template<typename T>
class LocalPointer : public LocalPointerBase<T> {
public:
/**
* Constructor takes ownership.
* @param p simple pointer to an object that is adopted
* @stable ICU 4.4
*/
explicit LocalPointer(T *p=NULL) : LocalPointerBase<T>(p) {}
/**
* Destructor deletes the object it owns.
* @stable ICU 4.4
*/
~LocalPointer() {
delete LocalPointerBase<T>::ptr;
}
/**
* Deletes the object it owns,
* and adopts (takes ownership of) the one passed in.
* @param p simple pointer to an object that is adopted
* @stable ICU 4.4
*/
void adoptInstead(T *p) {
delete LocalPointerBase<T>::ptr;
LocalPointerBase<T>::ptr=p;
}
};
/**
* "Smart pointer" class, deletes objects via the C++ array delete[] operator.
* For most methods see the LocalPointerBase base class.
* Adds operator[] for array item access.
*
* Usage example:
* \code
* LocalArray<UnicodeString> a(new UnicodeString[2]);
* a[0].append((UChar)0x61);
* if(some condition) { return; } // no need to explicitly delete the array
* a.adoptInstead(new UnicodeString[4]);
* a[3].append((UChar)0x62).append((UChar)0x63).reverse();
* // no need to explicitly delete the array
* \endcode
*
* @see LocalPointerBase
* @stable ICU 4.4
*/
template<typename T>
class LocalArray : public LocalPointerBase<T> {
public:
/**
* Constructor takes ownership.
* @param p simple pointer to an array of T objects that is adopted
* @stable ICU 4.4
*/
explicit LocalArray(T *p=NULL) : LocalPointerBase<T>(p) {}
/**
* Destructor deletes the array it owns.
* @stable ICU 4.4
*/
~LocalArray() {
delete[] LocalPointerBase<T>::ptr;
}
/**
* Deletes the array it owns,
* and adopts (takes ownership of) the one passed in.
* @param p simple pointer to an array of T objects that is adopted
* @stable ICU 4.4
*/
void adoptInstead(T *p) {
delete[] LocalPointerBase<T>::ptr;
LocalPointerBase<T>::ptr=p;
}
/**
* Array item access (writable).
* No index bounds check.
* @param i array index
* @return reference to the array item
* @stable ICU 4.4
*/
T &operator[](ptrdiff_t i) const { return LocalPointerBase<T>::ptr[i]; }
};
/**
* \def U_DEFINE_LOCAL_OPEN_POINTER
* "Smart pointer" definition macro, deletes objects via the closeFunction.
* Defines a subclass of LocalPointerBase which works just
* like LocalPointer<Type> except that this subclass will use the closeFunction
* rather than the C++ delete operator.
*
* Requirement: The closeFunction must tolerate a NULL pointer.
* (We could add a NULL check here but it is normally redundant.)
*
* Usage example:
* \code
* LocalUCaseMapPointer csm(ucasemap_open(localeID, options, &errorCode));
* utf8OutLength=ucasemap_utf8ToLower(csm.getAlias(),
* utf8Out, (int32_t)sizeof(utf8Out),
* utf8In, utf8InLength, &errorCode);
* if(U_FAILURE(errorCode)) { return; } // no need to explicitly delete the UCaseMap
* \endcode
*
* @see LocalPointerBase
* @see LocalPointer
* @stable ICU 4.4
*/
#define U_DEFINE_LOCAL_OPEN_POINTER(LocalPointerClassName, Type, closeFunction) \
class LocalPointerClassName : public LocalPointerBase<Type> { \
public: \
explicit LocalPointerClassName(Type *p=NULL) : LocalPointerBase<Type>(p) {} \
~LocalPointerClassName() { closeFunction(ptr); } \
void adoptInstead(Type *p) { \
closeFunction(ptr); \
ptr=p; \
} \
}
U_NAMESPACE_END
#endif /* U_SHOW_CPLUSPLUS_API */
#endif /* __LOCALPOINTER_H__ */
project/jni/icuuc/include/unicode/locdspnm.h
-206
View File
@@ -1,206 +0,0 @@
/*
******************************************************************************
* Copyright (C) 2010-2012, International Business Machines Corporation and
* others. All Rights Reserved.
******************************************************************************
*/
#ifndef LOCDSPNM_H
#define LOCDSPNM_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Provides display names of Locale and its components.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/locid.h"
#include "unicode/uscript.h"
#include "unicode/uldnames.h"
#include "unicode/udisplaycontext.h"
U_NAMESPACE_BEGIN
/**
* Returns display names of Locales and components of Locales. For
* more information on language, script, region, variant, key, and
* values, see Locale.
* @stable ICU 4.4
*/
class U_I18N_API LocaleDisplayNames : public UObject {
public:
/**
* Destructor.
* @stable ICU 4.4
*/
virtual ~LocaleDisplayNames();
/**
* Convenience overload of
* {@link #createInstance(const Locale& locale, UDialectHandling dialectHandling)}
* that specifies STANDARD dialect handling.
* @param locale the display locale
* @return a LocaleDisplayNames instance
* @stable ICU 4.4
*/
static LocaleDisplayNames* U_EXPORT2 createInstance(const Locale& locale);
/**
* Returns an instance of LocaleDisplayNames that returns names
* formatted for the provided locale, using the provided
* dialectHandling.
*
* @param locale the display locale
* @param dialectHandling how to select names for locales
* @return a LocaleDisplayNames instance
* @stable ICU 4.4
*/
static LocaleDisplayNames* U_EXPORT2 createInstance(const Locale& locale,
UDialectHandling dialectHandling);
#ifndef U_HIDE_DRAFT_API
/**
* Returns an instance of LocaleDisplayNames that returns names formatted
* for the provided locale, using the provided UDisplayContext settings.
*
* @param locale the display locale
* @param contexts List of one or more context settings (e.g. for dialect
* handling, capitalization, etc.
* @param length Number of items in the contexts list
* @return a LocaleDisplayNames instance
* @draft ICU 51
*/
static LocaleDisplayNames* U_EXPORT2 createInstance(const Locale& locale,
UDisplayContext *contexts, int32_t length);
#endif /* U_HIDE_DRAFT_API */
// getters for state
/**
* Returns the locale used to determine the display names. This is
* not necessarily the same locale passed to {@link #createInstance}.
* @return the display locale
* @stable ICU 4.4
*/
virtual const Locale& getLocale() const = 0;
/**
* Returns the dialect handling used in the display names.
* @return the dialect handling enum
* @stable ICU 4.4
*/
virtual UDialectHandling getDialectHandling() const = 0;
/**
* Returns the UDisplayContext value for the specified UDisplayContextType.
* @param type the UDisplayContextType whose value to return
* @return the UDisplayContext for the specified type.
* @draft ICU 51
*/
virtual UDisplayContext getContext(UDisplayContextType type) const = 0;
// names for entire locales
/**
* Returns the display name of the provided locale.
* @param locale the locale whose display name to return
* @param result receives the locale's display name
* @return the display name of the provided locale
* @stable ICU 4.4
*/
virtual UnicodeString& localeDisplayName(const Locale& locale,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided locale id.
* @param localeId the id of the locale whose display name to return
* @param result receives the locale's display name
* @return the display name of the provided locale
* @stable ICU 4.4
*/
virtual UnicodeString& localeDisplayName(const char* localeId,
UnicodeString& result) const = 0;
// names for components of a locale id
/**
* Returns the display name of the provided language code.
* @param lang the language code
* @param result receives the language code's display name
* @return the display name of the provided language code
* @stable ICU 4.4
*/
virtual UnicodeString& languageDisplayName(const char* lang,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided script code.
* @param script the script code
* @param result receives the script code's display name
* @return the display name of the provided script code
* @stable ICU 4.4
*/
virtual UnicodeString& scriptDisplayName(const char* script,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided script code.
* @param scriptCode the script code number
* @param result receives the script code's display name
* @return the display name of the provided script code
* @stable ICU 4.4
*/
virtual UnicodeString& scriptDisplayName(UScriptCode scriptCode,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided region code.
* @param region the region code
* @param result receives the region code's display name
* @return the display name of the provided region code
* @stable ICU 4.4
*/
virtual UnicodeString& regionDisplayName(const char* region,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided variant.
* @param variant the variant string
* @param result receives the variant's display name
* @return the display name of the provided variant
* @stable ICU 4.4
*/
virtual UnicodeString& variantDisplayName(const char* variant,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided locale key.
* @param key the locale key name
* @param result receives the locale key's display name
* @return the display name of the provided locale key
* @stable ICU 4.4
*/
virtual UnicodeString& keyDisplayName(const char* key,
UnicodeString& result) const = 0;
/**
* Returns the display name of the provided value (used with the provided key).
* @param key the locale key name
* @param value the locale key's value
* @param result receives the value's display name
* @return the display name of the provided value
* @stable ICU 4.4
*/
virtual UnicodeString& keyValueDisplayName(const char* key, const char* value,
UnicodeString& result) const = 0;
};
inline LocaleDisplayNames* LocaleDisplayNames::createInstance(const Locale& locale) {
return LocaleDisplayNames::createInstance(locale, ULDN_STANDARD_NAMES);
}
U_NAMESPACE_END
#endif
#endif
project/jni/icuuc/include/unicode/locid.h
-798
View File
@@ -1,798 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 1996-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* File locid.h
*
* Created by: Helena Shih
*
* Modification History:
*
* Date Name Description
* 02/11/97 aliu Changed gLocPath to fgLocPath and added methods to
* get and set it.
* 04/02/97 aliu Made operator!= inline; fixed return value of getName().
* 04/15/97 aliu Cleanup for AIX/Win32.
* 04/24/97 aliu Numerous changes per code review.
* 08/18/98 stephen Added tokenizeString(),changed getDisplayName()
* 09/08/98 stephen Moved definition of kEmptyString for Mac Port
* 11/09/99 weiv Added const char * getName() const;
* 04/12/00 srl removing unicodestring api's and cached hash code
* 08/10/01 grhoten Change the static Locales to accessor functions
******************************************************************************
*/
#ifndef LOCID_H
#define LOCID_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/putil.h"
#include "unicode/uloc.h"
#include "unicode/strenum.h"
/**
* \file
* \brief C++ API: Locale ID object.
*/
U_NAMESPACE_BEGIN
// Forward Declarations
void U_CALLCONV locale_available_init(); /**< @internal */
/**
* A <code>Locale</code> object represents a specific geographical, political,
* or cultural region. An operation that requires a <code>Locale</code> to perform
* its task is called <em>locale-sensitive</em> and uses the <code>Locale</code>
* to tailor information for the user. For example, displaying a number
* is a locale-sensitive operation--the number should be formatted
* according to the customs/conventions of the user's native country,
* region, or culture.
*
* The Locale class is not suitable for subclassing.
*
* <P>
* You can create a <code>Locale</code> object using the constructor in
* this class:
* \htmlonly<blockquote>\endhtmlonly
* <pre>
* Locale( const char* language,
* const char* country,
* const char* variant);
* </pre>
* \htmlonly</blockquote>\endhtmlonly
* The first argument to the constructors is a valid <STRONG>ISO
* Language Code.</STRONG> These codes are the lower-case two-letter
* codes as defined by ISO-639.
* You can find a full list of these codes at:
* <BR><a href ="http://www.loc.gov/standards/iso639-2/">
* http://www.loc.gov/standards/iso639-2/</a>
*
* <P>
* The second argument to the constructors is a valid <STRONG>ISO Country
* Code.</STRONG> These codes are the upper-case two-letter codes
* as defined by ISO-3166.
* You can find a full list of these codes at a number of sites, such as:
* <BR><a href="http://www.iso.org/iso/en/prods-services/iso3166ma/index.html">
* http://www.iso.org/iso/en/prods-services/iso3166ma/index.html</a>
*
* <P>
* The third constructor requires a third argument--the <STRONG>Variant.</STRONG>
* The Variant codes are vendor and browser-specific.
* For example, use REVISED for a langauge's revised script orthography, and POSIX for POSIX.
* Where there are two variants, separate them with an underscore, and
* put the most important one first. For
* example, a Traditional Spanish collation might be referenced, with
* "ES", "ES", "Traditional_POSIX".
*
* <P>
* Because a <code>Locale</code> object is just an identifier for a region,
* no validity check is performed when you construct a <code>Locale</code>.
* If you want to see whether particular resources are available for the
* <code>Locale</code> you construct, you must query those resources. For
* example, ask the <code>NumberFormat</code> for the locales it supports
* using its <code>getAvailableLocales</code> method.
* <BR><STRONG>Note:</STRONG> When you ask for a resource for a particular
* locale, you get back the best available match, not necessarily
* precisely what you asked for. For more information, look at
* <code>ResourceBundle</code>.
*
* <P>
* The <code>Locale</code> class provides a number of convenient constants
* that you can use to create <code>Locale</code> objects for commonly used
* locales. For example, the following refers to a <code>Locale</code> object
* for the United States:
* \htmlonly<blockquote>\endhtmlonly
* <pre>
* Locale::getUS()
* </pre>
* \htmlonly</blockquote>\endhtmlonly
*
* <P>
* Once you've created a <code>Locale</code> you can query it for information about
* itself. Use <code>getCountry</code> to get the ISO Country Code and
* <code>getLanguage</code> to get the ISO Language Code. You can
* use <code>getDisplayCountry</code> to get the
* name of the country suitable for displaying to the user. Similarly,
* you can use <code>getDisplayLanguage</code> to get the name of
* the language suitable for displaying to the user. Interestingly,
* the <code>getDisplayXXX</code> methods are themselves locale-sensitive
* and have two versions: one that uses the default locale and one
* that takes a locale as an argument and displays the name or country in
* a language appropriate to that locale.
*
* <P>
* ICU provides a number of classes that perform locale-sensitive
* operations. For example, the <code>NumberFormat</code> class formats
* numbers, currency, or percentages in a locale-sensitive manner. Classes
* such as <code>NumberFormat</code> have a number of convenience methods
* for creating a default object of that type. For example, the
* <code>NumberFormat</code> class provides these three convenience methods
* for creating a default <code>NumberFormat</code> object:
* \htmlonly<blockquote>\endhtmlonly
* <pre>
* UErrorCode success = U_ZERO_ERROR;
* Locale myLocale;
* NumberFormat *nf;
*
* nf = NumberFormat::createInstance( success ); delete nf;
* nf = NumberFormat::createCurrencyInstance( success ); delete nf;
* nf = NumberFormat::createPercentInstance( success ); delete nf;
* </pre>
* \htmlonly</blockquote>\endhtmlonly
* Each of these methods has two variants; one with an explicit locale
* and one without; the latter using the default locale.
* \htmlonly<blockquote>\endhtmlonly
* <pre>
* nf = NumberFormat::createInstance( myLocale, success ); delete nf;
* nf = NumberFormat::createCurrencyInstance( myLocale, success ); delete nf;
* nf = NumberFormat::createPercentInstance( myLocale, success ); delete nf;
* </pre>
* \htmlonly</blockquote>\endhtmlonly
* A <code>Locale</code> is the mechanism for identifying the kind of object
* (<code>NumberFormat</code>) that you would like to get. The locale is
* <STRONG>just</STRONG> a mechanism for identifying objects,
* <STRONG>not</STRONG> a container for the objects themselves.
*
* <P>
* Each class that performs locale-sensitive operations allows you
* to get all the available objects of that type. You can sift
* through these objects by language, country, or variant,
* and use the display names to present a menu to the user.
* For example, you can create a menu of all the collation objects
* suitable for a given language. Such classes implement these
* three class methods:
* \htmlonly<blockquote>\endhtmlonly
* <pre>
* static Locale* getAvailableLocales(int32_t& numLocales)
* static UnicodeString& getDisplayName(const Locale& objectLocale,
* const Locale& displayLocale,
* UnicodeString& displayName)
* static UnicodeString& getDisplayName(const Locale& objectLocale,
* UnicodeString& displayName)
* </pre>
* \htmlonly</blockquote>\endhtmlonly
*
* @stable ICU 2.0
* @see ResourceBundle
*/
class U_COMMON_API Locale : public UObject {
public:
/** Useful constant for the Root locale. @stable ICU 4.4 */
static const Locale &U_EXPORT2 getRoot(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getEnglish(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getFrench(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getGerman(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getItalian(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getJapanese(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getKorean(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getChinese(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getSimplifiedChinese(void);
/** Useful constant for this language. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getTraditionalChinese(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getFrance(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getGermany(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getItaly(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getJapan(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getKorea(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getChina(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getPRC(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getTaiwan(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getUK(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getUS(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getCanada(void);
/** Useful constant for this country/region. @stable ICU 2.0 */
static const Locale &U_EXPORT2 getCanadaFrench(void);
/**
* Construct a default locale object, a Locale for the default locale ID.
*
* @see getDefault
* @see uloc_getDefault
* @stable ICU 2.0
*/
Locale();
/**
* Construct a locale from language, country, variant.
* If an error occurs, then the constructed object will be "bogus"
* (isBogus() will return TRUE).
*
* @param language Lowercase two-letter or three-letter ISO-639 code.
* This parameter can instead be an ICU style C locale (e.g. "en_US"),
* but the other parameters must not be used.
* This parameter can be NULL; if so,
* the locale is initialized to match the current default locale.
* (This is the same as using the default constructor.)
* Please note: The Java Locale class does NOT accept the form
* 'new Locale("en_US")' but only 'new Locale("en","US")'
*
* @param country Uppercase two-letter ISO-3166 code. (optional)
* @param variant Uppercase vendor and browser specific code. See class
* description. (optional)
* @param keywordsAndValues A string consisting of keyword/values pairs, such as
* "collation=phonebook;currency=euro"
*
* @see getDefault
* @see uloc_getDefault
* @stable ICU 2.0
*/
Locale( const char * language,
const char * country = 0,
const char * variant = 0,
const char * keywordsAndValues = 0);
/**
* Initializes a Locale object from another Locale object.
*
* @param other The Locale object being copied in.
* @stable ICU 2.0
*/
Locale(const Locale& other);
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~Locale() ;
/**
* Replaces the entire contents of *this with the specified value.
*
* @param other The Locale object being copied in.
* @return *this
* @stable ICU 2.0
*/
Locale& operator=(const Locale& other);
/**
* Checks if two locale keys are the same.
*
* @param other The locale key object to be compared with this.
* @return True if the two locale keys are the same, false otherwise.
* @stable ICU 2.0
*/
UBool operator==(const Locale& other) const;
/**
* Checks if two locale keys are not the same.
*
* @param other The locale key object to be compared with this.
* @return True if the two locale keys are not the same, false
* otherwise.
* @stable ICU 2.0
*/
UBool operator!=(const Locale& other) const;
/**
* Clone this object.
* Clones can be used concurrently in multiple threads.
* If an error occurs, then NULL is returned.
* The caller must delete the clone.
*
* @return a clone of this object
*
* @see getDynamicClassID
* @stable ICU 2.8
*/
Locale *clone() const;
#ifndef U_HIDE_SYSTEM_API
/**
* Common methods of getting the current default Locale. Used for the
* presentation: menus, dialogs, etc. Generally set once when your applet or
* application is initialized, then never reset. (If you do reset the
* default locale, you probably want to reload your GUI, so that the change
* is reflected in your interface.)
*
* More advanced programs will allow users to use different locales for
* different fields, e.g. in a spreadsheet.
*
* Note that the initial setting will match the host system.
* @return a reference to the Locale object for the default locale ID
* @system
* @stable ICU 2.0
*/
static const Locale& U_EXPORT2 getDefault(void);
/**
* Sets the default. Normally set once at the beginning of a process,
* then never reset.
* setDefault() only changes ICU's default locale ID, <strong>not</strong>
* the default locale ID of the runtime environment.
*
* @param newLocale Locale to set to. If NULL, set to the value obtained
* from the runtime environement.
* @param success The error code.
* @system
* @stable ICU 2.0
*/
static void U_EXPORT2 setDefault(const Locale& newLocale,
UErrorCode& success);
#endif /* U_HIDE_SYSTEM_API */
/**
* Creates a locale which has had minimal canonicalization
* as per uloc_getName().
* @param name The name to create from. If name is null,
* the default Locale is used.
* @return new locale object
* @stable ICU 2.0
* @see uloc_getName
*/
static Locale U_EXPORT2 createFromName(const char *name);
/**
* Creates a locale from the given string after canonicalizing
* the string by calling uloc_canonicalize().
* @param name the locale ID to create from. Must not be NULL.
* @return a new locale object corresponding to the given name
* @stable ICU 3.0
* @see uloc_canonicalize
*/
static Locale U_EXPORT2 createCanonical(const char* name);
/**
* Returns the locale's ISO-639 language code.
* @return An alias to the code
* @stable ICU 2.0
*/
inline const char * getLanguage( ) const;
/**
* Returns the locale's ISO-15924 abbreviation script code.
* @return An alias to the code
* @see uscript_getShortName
* @see uscript_getCode
* @stable ICU 2.8
*/
inline const char * getScript( ) const;
/**
* Returns the locale's ISO-3166 country code.
* @return An alias to the code
* @stable ICU 2.0
*/
inline const char * getCountry( ) const;
/**
* Returns the locale's variant code.
* @return An alias to the code
* @stable ICU 2.0
*/
inline const char * getVariant( ) const;
/**
* Returns the programmatic name of the entire locale, with the language,
* country and variant separated by underbars. If a field is missing, up
* to two leading underbars will occur. Example: "en", "de_DE", "en_US_WIN",
* "de__POSIX", "fr__MAC", "__MAC", "_MT", "_FR_EURO"
* @return A pointer to "name".
* @stable ICU 2.0
*/
inline const char * getName() const;
/**
* Returns the programmatic name of the entire locale as getName() would return,
* but without keywords.
* @return A pointer to "name".
* @see getName
* @stable ICU 2.8
*/
const char * getBaseName() const;
/**
* Gets the list of keywords for the specified locale.
*
* @param status the status code
* @return pointer to StringEnumeration class, or NULL if there are no keywords.
* Client must dispose of it by calling delete.
* @stable ICU 2.8
*/
StringEnumeration * createKeywords(UErrorCode &status) const;
/**
* Gets the value for a keyword.
*
* @param keywordName name of the keyword for which we want the value. Case insensitive.
* @param buffer The buffer to receive the keyword value.
* @param bufferCapacity The capacity of receiving buffer
* @param status Returns any error information while performing this operation.
* @return the length of the keyword value
*
* @stable ICU 2.8
*/
int32_t getKeywordValue(const char* keywordName, char *buffer, int32_t bufferCapacity, UErrorCode &status) const;
/**
* Sets or removes the value for a keyword.
*
* For removing all keywords, use getBaseName(),
* and construct a new Locale if it differs from getName().
*
* @param keywordName name of the keyword to be set. Case insensitive.
* @param keywordValue value of the keyword to be set. If 0-length or
* NULL, will result in the keyword being removed. No error is given if
* that keyword does not exist.
* @param status Returns any error information while performing this operation.
*
* @stable ICU 49
*/
void setKeywordValue(const char* keywordName, const char* keywordValue, UErrorCode &status);
/**
* returns the locale's three-letter language code, as specified
* in ISO draft standard ISO-639-2.
* @return An alias to the code, or an empty string
* @stable ICU 2.0
*/
const char * getISO3Language() const;
/**
* Fills in "name" with the locale's three-letter ISO-3166 country code.
* @return An alias to the code, or an empty string
* @stable ICU 2.0
*/
const char * getISO3Country() const;
/**
* Returns the Windows LCID value corresponding to this locale.
* This value is stored in the resource data for the locale as a one-to-four-digit
* hexadecimal number. If the resource is missing, in the wrong format, or
* there is no Windows LCID value that corresponds to this locale, returns 0.
* @stable ICU 2.0
*/
uint32_t getLCID(void) const;
/**
* Fills in "dispLang" with the name of this locale's language in a format suitable for
* user display in the default locale. For example, if the locale's language code is
* "fr" and the default locale's language code is "en", this function would set
* dispLang to "French".
* @param dispLang Receives the language's display name.
* @return A reference to "dispLang".
* @stable ICU 2.0
*/
UnicodeString& getDisplayLanguage(UnicodeString& dispLang) const;
/**
* Fills in "dispLang" with the name of this locale's language in a format suitable for
* user display in the locale specified by "displayLocale". For example, if the locale's
* language code is "en" and displayLocale's language code is "fr", this function would set
* dispLang to "Anglais".
* @param displayLocale Specifies the locale to be used to display the name. In other words,
* if the locale's language code is "en", passing Locale::getFrench() for
* displayLocale would result in "Anglais", while passing Locale::getGerman()
* for displayLocale would result in "Englisch".
* @param dispLang Receives the language's display name.
* @return A reference to "dispLang".
* @stable ICU 2.0
*/
UnicodeString& getDisplayLanguage( const Locale& displayLocale,
UnicodeString& dispLang) const;
/**
* Fills in "dispScript" with the name of this locale's script in a format suitable
* for user display in the default locale. For example, if the locale's script code
* is "LATN" and the default locale's language code is "en", this function would set
* dispScript to "Latin".
* @param dispScript Receives the scripts's display name.
* @return A reference to "dispScript".
* @stable ICU 2.8
*/
UnicodeString& getDisplayScript( UnicodeString& dispScript) const;
/**
* Fills in "dispScript" with the name of this locale's country in a format suitable
* for user display in the locale specified by "displayLocale". For example, if the locale's
* script code is "LATN" and displayLocale's language code is "en", this function would set
* dispScript to "Latin".
* @param displayLocale Specifies the locale to be used to display the name. In other
* words, if the locale's script code is "LATN", passing
* Locale::getFrench() for displayLocale would result in "", while
* passing Locale::getGerman() for displayLocale would result in
* "".
* @param dispScript Receives the scripts's display name.
* @return A reference to "dispScript".
* @stable ICU 2.8
*/
UnicodeString& getDisplayScript( const Locale& displayLocale,
UnicodeString& dispScript) const;
/**
* Fills in "dispCountry" with the name of this locale's country in a format suitable
* for user display in the default locale. For example, if the locale's country code
* is "FR" and the default locale's language code is "en", this function would set
* dispCountry to "France".
* @param dispCountry Receives the country's display name.
* @return A reference to "dispCountry".
* @stable ICU 2.0
*/
UnicodeString& getDisplayCountry( UnicodeString& dispCountry) const;
/**
* Fills in "dispCountry" with the name of this locale's country in a format suitable
* for user display in the locale specified by "displayLocale". For example, if the locale's
* country code is "US" and displayLocale's language code is "fr", this function would set
* dispCountry to "&Eacute;tats-Unis".
* @param displayLocale Specifies the locale to be used to display the name. In other
* words, if the locale's country code is "US", passing
* Locale::getFrench() for displayLocale would result in "&Eacute;tats-Unis", while
* passing Locale::getGerman() for displayLocale would result in
* "Vereinigte Staaten".
* @param dispCountry Receives the country's display name.
* @return A reference to "dispCountry".
* @stable ICU 2.0
*/
UnicodeString& getDisplayCountry( const Locale& displayLocale,
UnicodeString& dispCountry) const;
/**
* Fills in "dispVar" with the name of this locale's variant code in a format suitable
* for user display in the default locale.
* @param dispVar Receives the variant's name.
* @return A reference to "dispVar".
* @stable ICU 2.0
*/
UnicodeString& getDisplayVariant( UnicodeString& dispVar) const;
/**
* Fills in "dispVar" with the name of this locale's variant code in a format
* suitable for user display in the locale specified by "displayLocale".
* @param displayLocale Specifies the locale to be used to display the name.
* @param dispVar Receives the variant's display name.
* @return A reference to "dispVar".
* @stable ICU 2.0
*/
UnicodeString& getDisplayVariant( const Locale& displayLocale,
UnicodeString& dispVar) const;
/**
* Fills in "name" with the name of this locale in a format suitable for user display
* in the default locale. This function uses getDisplayLanguage(), getDisplayCountry(),
* and getDisplayVariant() to do its work, and outputs the display name in the format
* "language (country[,variant])". For example, if the default locale is en_US, then
* fr_FR's display name would be "French (France)", and es_MX_Traditional's display name
* would be "Spanish (Mexico,Traditional)".
* @param name Receives the locale's display name.
* @return A reference to "name".
* @stable ICU 2.0
*/
UnicodeString& getDisplayName( UnicodeString& name) const;
/**
* Fills in "name" with the name of this locale in a format suitable for user display
* in the locale specfied by "displayLocale". This function uses getDisplayLanguage(),
* getDisplayCountry(), and getDisplayVariant() to do its work, and outputs the display
* name in the format "language (country[,variant])". For example, if displayLocale is
* fr_FR, then en_US's display name would be "Anglais (&Eacute;tats-Unis)", and no_NO_NY's
* display name would be "norv&eacute;gien (Norv&egrave;ge,NY)".
* @param displayLocale Specifies the locale to be used to display the name.
* @param name Receives the locale's display name.
* @return A reference to "name".
* @stable ICU 2.0
*/
UnicodeString& getDisplayName( const Locale& displayLocale,
UnicodeString& name) const;
/**
* Generates a hash code for the locale.
* @stable ICU 2.0
*/
int32_t hashCode(void) const;
/**
* Sets the locale to bogus
* A bogus locale represents a non-existing locale associated
* with services that can be instantiated from non-locale data
* in addition to locale (for example, collation can be
* instantiated from a locale and from a rule set).
* @stable ICU 2.1
*/
void setToBogus();
/**
* Gets the bogus state. Locale object can be bogus if it doesn't exist
* @return FALSE if it is a real locale, TRUE if it is a bogus locale
* @stable ICU 2.1
*/
UBool isBogus(void) const;
/**
* Returns a list of all installed locales.
* @param count Receives the number of locales in the list.
* @return A pointer to an array of Locale objects. This array is the list
* of all locales with installed resource files. The called does NOT
* get ownership of this list, and must NOT delete it.
* @stable ICU 2.0
*/
static const Locale* U_EXPORT2 getAvailableLocales(int32_t& count);
/**
* Gets a list of all available 2-letter country codes defined in ISO 3166. This is a
* pointer to an array of pointers to arrays of char. All of these pointers are
* owned by ICU-- do not delete them, and do not write through them. The array is
* terminated with a null pointer.
* @return a list of all available country codes
* @stable ICU 2.0
*/
static const char* const* U_EXPORT2 getISOCountries();
/**
* Gets a list of all available language codes defined in ISO 639. This is a pointer
* to an array of pointers to arrays of char. All of these pointers are owned
* by ICU-- do not delete them, and do not write through them. The array is
* terminated with a null pointer.
* @return a list of all available language codes
* @stable ICU 2.0
*/
static const char* const* U_EXPORT2 getISOLanguages();
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
protected: /* only protected for testing purposes. DO NOT USE. */
#ifndef U_HIDE_INTERNAL_API
/**
* Set this from a single POSIX style locale string.
* @internal
*/
void setFromPOSIXID(const char *posixID);
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* Initialize the locale object with a new name.
* Was deprecated - used in implementation - moved internal
*
* @param cLocaleID The new locale name.
* @param canonicalize whether to call uloc_canonicalize on cLocaleID
*/
Locale& init(const char* cLocaleID, UBool canonicalize);
/*
* Internal constructor to allow construction of a locale object with
* NO side effects. (Default constructor tries to get
* the default locale.)
*/
enum ELocaleType {
eBOGUS
};
Locale(ELocaleType);
/**
* Initialize the locale cache for commonly used locales
*/
static Locale *getLocaleCache(void);
char language[ULOC_LANG_CAPACITY];
char script[ULOC_SCRIPT_CAPACITY];
char country[ULOC_COUNTRY_CAPACITY];
int32_t variantBegin;
char* fullName;
char fullNameBuffer[ULOC_FULLNAME_CAPACITY];
// name without keywords
char* baseName;
char baseNameBuffer[ULOC_FULLNAME_CAPACITY];
UBool fIsBogus;
static const Locale &getLocale(int locid);
/**
* A friend to allow the default locale to be set by either the C or C++ API.
* @internal
*/
friend Locale *locale_set_default_internal(const char *, UErrorCode& status);
/**
* @internal
*/
friend void locale_available_init();
};
inline UBool
Locale::operator!=(const Locale& other) const
{
return !operator==(other);
}
inline const char *
Locale::getCountry() const
{
return country;
}
inline const char *
Locale::getLanguage() const
{
return language;
}
inline const char *
Locale::getScript() const
{
return script;
}
inline const char *
Locale::getVariant() const
{
getBaseName(); // lazy init
return &baseName[variantBegin];
}
inline const char *
Locale::getName() const
{
return fullName;
}
inline UBool
Locale::isBogus(void) const {
return fIsBogus;
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/measfmt.h
-81
View File
@@ -1,81 +0,0 @@
/*
**********************************************************************
* Copyright (c) 2004-2011, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 20, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef MEASUREFORMAT_H
#define MEASUREFORMAT_H
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/format.h"
/**
* \file
* \brief C++ API: Formatter for measure objects.
*/
U_NAMESPACE_BEGIN
/**
*
* A formatter for measure objects. This is an abstract base class.
*
* <p>To format or parse a measure object, first create a formatter
* object using a MeasureFormat factory method. Then use that
* object's format and parse methods.
*
* <p>This is an abstract class.
*
* @see Format
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API MeasureFormat : public Format {
public:
/**
* Destructor.
* @stable ICU 3.0
*/
virtual ~MeasureFormat();
/**
* Return a formatter for CurrencyAmount objects in the given
* locale.
* @param locale desired locale
* @param ec input-output error code
* @return a formatter object, or NULL upon error
* @stable ICU 3.0
*/
static MeasureFormat* U_EXPORT2 createCurrencyFormat(const Locale& locale,
UErrorCode& ec);
/**
* Return a formatter for CurrencyAmount objects in the default
* locale.
* @param ec input-output error code
* @return a formatter object, or NULL upon error
* @stable ICU 3.0
*/
static MeasureFormat* U_EXPORT2 createCurrencyFormat(UErrorCode& ec);
protected:
/**
* Default constructor.
* @stable ICU 3.0
*/
MeasureFormat();
};
U_NAMESPACE_END
#endif // #if !UCONFIG_NO_FORMATTING
#endif // #ifndef MEASUREFORMAT_H
project/jni/icuuc/include/unicode/measunit.h
-71
View File
@@ -1,71 +0,0 @@
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 26, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef __MEASUREUNIT_H__
#define __MEASUREUNIT_H__
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/fmtable.h"
/**
* \file
* \brief C++ API: A unit for measuring a quantity.
*/
U_NAMESPACE_BEGIN
/**
* A unit such as length, mass, volume, currency, etc. A unit is
* coupled with a numeric amount to produce a Measure.
*
* <p>This is an abstract class.
*
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API MeasureUnit: public UObject {
public:
/**
* Return a polymorphic clone of this object. The result will
* have the same class as returned by getDynamicClassID().
* @stable ICU 3.0
*/
virtual UObject* clone() const = 0;
/**
* Destructor
* @stable ICU 3.0
*/
virtual ~MeasureUnit();
/**
* Equality operator. Return true if this object is equal
* to the given object.
* @stable ICU 3.0
*/
virtual UBool operator==(const UObject& other) const = 0;
protected:
/**
* Default constructor.
* @stable ICU 3.0
*/
MeasureUnit();
};
U_NAMESPACE_END
// NOTE: There is no measunit.cpp. For implementation, see measure.cpp. [alan]
#endif // !UCONFIG_NO_FORMATTING
#endif // __MEASUREUNIT_H__
project/jni/icuuc/include/unicode/measure.h
-137
View File
@@ -1,137 +0,0 @@
/*
**********************************************************************
* Copyright (c) 2004-2006, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Author: Alan Liu
* Created: April 26, 2004
* Since: ICU 3.0
**********************************************************************
*/
#ifndef __MEASURE_H__
#define __MEASURE_H__
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: MeasureUnit object.
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/fmtable.h"
U_NAMESPACE_BEGIN
class MeasureUnit;
/**
* An amount of a specified unit, consisting of a number and a Unit.
* For example, a length measure consists of a number and a length
* unit, such as feet or meters. This is an abstract class.
* Subclasses specify a concrete Unit type.
*
* <p>Measure objects are parsed and formatted by subclasses of
* MeasureFormat.
*
* <p>Measure objects are immutable.
*
* <p>This is an abstract class.
*
* @author Alan Liu
* @stable ICU 3.0
*/
class U_I18N_API Measure: public UObject {
public:
/**
* Construct an object with the given numeric amount and the given
* unit. After this call, the caller must not delete the given
* unit object.
* @param number a numeric object; amount.isNumeric() must be TRUE
* @param adoptedUnit the unit object, which must not be NULL
* @param ec input-output error code. If the amount or the unit
* is invalid, then this will be set to a failing value.
* @stable ICU 3.0
*/
Measure(const Formattable& number, MeasureUnit* adoptedUnit,
UErrorCode& ec);
/**
* Copy constructor
* @stable ICU 3.0
*/
Measure(const Measure& other);
/**
* Assignment operator
* @stable ICU 3.0
*/
Measure& operator=(const Measure& other);
/**
* Return a polymorphic clone of this object. The result will
* have the same class as returned by getDynamicClassID().
* @stable ICU 3.0
*/
virtual UObject* clone() const = 0;
/**
* Destructor
* @stable ICU 3.0
*/
virtual ~Measure();
/**
* Equality operator. Return true if this object is equal
* to the given object.
* @stable ICU 3.0
*/
UBool operator==(const UObject& other) const;
/**
* Return a reference to the numeric value of this object. The
* numeric value may be of any numeric type supported by
* Formattable.
* @stable ICU 3.0
*/
inline const Formattable& getNumber() const;
/**
* Return a reference to the unit of this object.
* @stable ICU 3.0
*/
inline const MeasureUnit& getUnit() const;
protected:
/**
* Default constructor.
* @stable ICU 3.0
*/
Measure();
private:
/**
* The numeric value of this object, e.g. 2.54 or 100.
*/
Formattable number;
/**
* The unit of this object, e.g., "millimeter" or "JPY". This is
* owned by this object.
*/
MeasureUnit* unit;
};
inline const Formattable& Measure::getNumber() const {
return number;
}
inline const MeasureUnit& Measure::getUnit() const {
return *unit;
}
U_NAMESPACE_END
#endif // !UCONFIG_NO_FORMATTING
#endif // __MEASURE_H__
project/jni/icuuc/include/unicode/messagepattern.h
-943
View File
@@ -1,943 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2011-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*******************************************************************************
* file name: messagepattern.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2011mar14
* created by: Markus W. Scherer
*/
#ifndef __MESSAGEPATTERN_H__
#define __MESSAGEPATTERN_H__
/**
* \file
* \brief C++ API: MessagePattern class: Parses and represents ICU MessageFormat patterns.
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_FORMATTING
#include "unicode/parseerr.h"
#include "unicode/unistr.h"
/**
* Mode for when an apostrophe starts quoted literal text for MessageFormat output.
* The default is DOUBLE_OPTIONAL unless overridden via uconfig.h
* (UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE).
* <p>
* A pair of adjacent apostrophes always results in a single apostrophe in the output,
* even when the pair is between two single, text-quoting apostrophes.
* <p>
* The following table shows examples of desired MessageFormat.format() output
* with the pattern strings that yield that output.
* <p>
* <table>
* <tr>
* <th>Desired output</th>
* <th>DOUBLE_OPTIONAL</th>
* <th>DOUBLE_REQUIRED</th>
* </tr>
* <tr>
* <td>I see {many}</td>
* <td>I see '{many}'</td>
* <td>(same)</td>
* </tr>
* <tr>
* <td>I said {'Wow!'}</td>
* <td>I said '{''Wow!''}'</td>
* <td>(same)</td>
* </tr>
* <tr>
* <td>I don't know</td>
* <td>I don't know OR<br> I don''t know</td>
* <td>I don''t know</td>
* </tr>
* </table>
* @stable ICU 4.8
* @see UCONFIG_MSGPAT_DEFAULT_APOSTROPHE_MODE
*/
enum UMessagePatternApostropheMode {
/**
* A literal apostrophe is represented by
* either a single or a double apostrophe pattern character.
* Within a MessageFormat pattern, a single apostrophe only starts quoted literal text
* if it immediately precedes a curly brace {},
* or a pipe symbol | if inside a choice format,
* or a pound symbol # if inside a plural format.
* <p>
* This is the default behavior starting with ICU 4.8.
* @stable ICU 4.8
*/
UMSGPAT_APOS_DOUBLE_OPTIONAL,
/**
* A literal apostrophe must be represented by
* a double apostrophe pattern character.
* A single apostrophe always starts quoted literal text.
* <p>
* This is the behavior of ICU 4.6 and earlier, and of the JDK.
* @stable ICU 4.8
*/
UMSGPAT_APOS_DOUBLE_REQUIRED
};
/**
* @stable ICU 4.8
*/
typedef enum UMessagePatternApostropheMode UMessagePatternApostropheMode;
/**
* MessagePattern::Part type constants.
* @stable ICU 4.8
*/
enum UMessagePatternPartType {
/**
* Start of a message pattern (main or nested).
* The length is 0 for the top-level message
* and for a choice argument sub-message, otherwise 1 for the '{'.
* The value indicates the nesting level, starting with 0 for the main message.
* <p>
* There is always a later MSG_LIMIT part.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_MSG_START,
/**
* End of a message pattern (main or nested).
* The length is 0 for the top-level message and
* the last sub-message of a choice argument,
* otherwise 1 for the '}' or (in a choice argument style) the '|'.
* The value indicates the nesting level, starting with 0 for the main message.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_MSG_LIMIT,
/**
* Indicates a substring of the pattern string which is to be skipped when formatting.
* For example, an apostrophe that begins or ends quoted text
* would be indicated with such a part.
* The value is undefined and currently always 0.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_SKIP_SYNTAX,
/**
* Indicates that a syntax character needs to be inserted for auto-quoting.
* The length is 0.
* The value is the character code of the insertion character. (U+0027=APOSTROPHE)
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_INSERT_CHAR,
/**
* Indicates a syntactic (non-escaped) # symbol in a plural variant.
* When formatting, replace this part's substring with the
* (value-offset) for the plural argument value.
* The value is undefined and currently always 0.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_REPLACE_NUMBER,
/**
* Start of an argument.
* The length is 1 for the '{'.
* The value is the ordinal value of the ArgType. Use getArgType().
* <p>
* This part is followed by either an ARG_NUMBER or ARG_NAME,
* followed by optional argument sub-parts (see UMessagePatternArgType constants)
* and finally an ARG_LIMIT part.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_START,
/**
* End of an argument.
* The length is 1 for the '}'.
* The value is the ordinal value of the ArgType. Use getArgType().
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_LIMIT,
/**
* The argument number, provided by the value.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_NUMBER,
/**
* The argument name.
* The value is undefined and currently always 0.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_NAME,
/**
* The argument type.
* The value is undefined and currently always 0.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_TYPE,
/**
* The argument style text.
* The value is undefined and currently always 0.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_STYLE,
/**
* A selector substring in a "complex" argument style.
* The value is undefined and currently always 0.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_SELECTOR,
/**
* An integer value, for example the offset or an explicit selector value
* in a PluralFormat style.
* The part value is the integer value.
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_INT,
/**
* A numeric value, for example the offset or an explicit selector value
* in a PluralFormat style.
* The part value is an index into an internal array of numeric values;
* use getNumericValue().
* @stable ICU 4.8
*/
UMSGPAT_PART_TYPE_ARG_DOUBLE
};
/**
* @stable ICU 4.8
*/
typedef enum UMessagePatternPartType UMessagePatternPartType;
/**
* Argument type constants.
* Returned by Part.getArgType() for ARG_START and ARG_LIMIT parts.
*
* Messages nested inside an argument are each delimited by MSG_START and MSG_LIMIT,
* with a nesting level one greater than the surrounding message.
* @stable ICU 4.8
*/
enum UMessagePatternArgType {
/**
* The argument has no specified type.
* @stable ICU 4.8
*/
UMSGPAT_ARG_TYPE_NONE,
/**
* The argument has a "simple" type which is provided by the ARG_TYPE part.
* An ARG_STYLE part might follow that.
* @stable ICU 4.8
*/
UMSGPAT_ARG_TYPE_SIMPLE,
/**
* The argument is a ChoiceFormat with one or more
* ((ARG_INT | ARG_DOUBLE), ARG_SELECTOR, message) tuples.
* @stable ICU 4.8
*/
UMSGPAT_ARG_TYPE_CHOICE,
/**
* The argument is a cardinal-number PluralFormat with an optional ARG_INT or ARG_DOUBLE offset
* (e.g., offset:1)
* and one or more (ARG_SELECTOR [explicit-value] message) tuples.
* If the selector has an explicit value (e.g., =2), then
* that value is provided by the ARG_INT or ARG_DOUBLE part preceding the message.
* Otherwise the message immediately follows the ARG_SELECTOR.
* @stable ICU 4.8
*/
UMSGPAT_ARG_TYPE_PLURAL,
/**
* The argument is a SelectFormat with one or more (ARG_SELECTOR, message) pairs.
* @stable ICU 4.8
*/
UMSGPAT_ARG_TYPE_SELECT,
/**
* The argument is an ordinal-number PluralFormat
* with the same style parts sequence and semantics as UMSGPAT_ARG_TYPE_PLURAL.
* @stable ICU 50
*/
UMSGPAT_ARG_TYPE_SELECTORDINAL
};
/**
* @stable ICU 4.8
*/
typedef enum UMessagePatternArgType UMessagePatternArgType;
/**
* \def UMSGPAT_ARG_TYPE_HAS_PLURAL_STYLE
* Returns TRUE if the argument type has a plural style part sequence and semantics,
* for example UMSGPAT_ARG_TYPE_PLURAL and UMSGPAT_ARG_TYPE_SELECTORDINAL.
* @stable ICU 50
*/
#define UMSGPAT_ARG_TYPE_HAS_PLURAL_STYLE(argType) \
((argType)==UMSGPAT_ARG_TYPE_PLURAL || (argType)==UMSGPAT_ARG_TYPE_SELECTORDINAL)
enum {
/**
* Return value from MessagePattern.validateArgumentName() for when
* the string is a valid "pattern identifier" but not a number.
* @stable ICU 4.8
*/
UMSGPAT_ARG_NAME_NOT_NUMBER=-1,
/**
* Return value from MessagePattern.validateArgumentName() for when
* the string is invalid.
* It might not be a valid "pattern identifier",
* or it have only ASCII digits but there is a leading zero or the number is too large.
* @stable ICU 4.8
*/
UMSGPAT_ARG_NAME_NOT_VALID=-2
};
/**
* Special value that is returned by getNumericValue(Part) when no
* numeric value is defined for a part.
* @see MessagePattern.getNumericValue()
* @stable ICU 4.8
*/
#define UMSGPAT_NO_NUMERIC_VALUE ((double)(-123456789))
U_NAMESPACE_BEGIN
class MessagePatternDoubleList;
class MessagePatternPartsList;
/**
* Parses and represents ICU MessageFormat patterns.
* Also handles patterns for ChoiceFormat, PluralFormat and SelectFormat.
* Used in the implementations of those classes as well as in tools
* for message validation, translation and format conversion.
* <p>
* The parser handles all syntax relevant for identifying message arguments.
* This includes "complex" arguments whose style strings contain
* nested MessageFormat pattern substrings.
* For "simple" arguments (with no nested MessageFormat pattern substrings),
* the argument style is not parsed any further.
* <p>
* The parser handles named and numbered message arguments and allows both in one message.
* <p>
* Once a pattern has been parsed successfully, iterate through the parsed data
* with countParts(), getPart() and related methods.
* <p>
* The data logically represents a parse tree, but is stored and accessed
* as a list of "parts" for fast and simple parsing and to minimize object allocations.
* Arguments and nested messages are best handled via recursion.
* For every _START "part", MessagePattern.getLimitPartIndex() efficiently returns
* the index of the corresponding _LIMIT "part".
* <p>
* List of "parts":
* <pre>
* message = MSG_START (SKIP_SYNTAX | INSERT_CHAR | REPLACE_NUMBER | argument)* MSG_LIMIT
* argument = noneArg | simpleArg | complexArg
* complexArg = choiceArg | pluralArg | selectArg
*
* noneArg = ARG_START.NONE (ARG_NAME | ARG_NUMBER) ARG_LIMIT.NONE
* simpleArg = ARG_START.SIMPLE (ARG_NAME | ARG_NUMBER) ARG_TYPE [ARG_STYLE] ARG_LIMIT.SIMPLE
* choiceArg = ARG_START.CHOICE (ARG_NAME | ARG_NUMBER) choiceStyle ARG_LIMIT.CHOICE
* pluralArg = ARG_START.PLURAL (ARG_NAME | ARG_NUMBER) pluralStyle ARG_LIMIT.PLURAL
* selectArg = ARG_START.SELECT (ARG_NAME | ARG_NUMBER) selectStyle ARG_LIMIT.SELECT
*
* choiceStyle = ((ARG_INT | ARG_DOUBLE) ARG_SELECTOR message)+
* pluralStyle = [ARG_INT | ARG_DOUBLE] (ARG_SELECTOR [ARG_INT | ARG_DOUBLE] message)+
* selectStyle = (ARG_SELECTOR message)+
* </pre>
* <ul>
* <li>Literal output text is not represented directly by "parts" but accessed
* between parts of a message, from one part's getLimit() to the next part's getIndex().
* <li><code>ARG_START.CHOICE</code> stands for an ARG_START Part with ArgType CHOICE.
* <li>In the choiceStyle, the ARG_SELECTOR has the '<', the '#' or
* the less-than-or-equal-to sign (U+2264).
* <li>In the pluralStyle, the first, optional numeric Part has the "offset:" value.
* The optional numeric Part between each (ARG_SELECTOR, message) pair
* is the value of an explicit-number selector like "=2",
* otherwise the selector is a non-numeric identifier.
* <li>The REPLACE_NUMBER Part can occur only in an immediate sub-message of the pluralStyle.
* </ul>
* <p>
* This class is not intended for public subclassing.
*
* @stable ICU 4.8
*/
class U_COMMON_API MessagePattern : public UObject {
public:
/**
* Constructs an empty MessagePattern with default UMessagePatternApostropheMode.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @stable ICU 4.8
*/
MessagePattern(UErrorCode &errorCode);
/**
* Constructs an empty MessagePattern.
* @param mode Explicit UMessagePatternApostropheMode.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @stable ICU 4.8
*/
MessagePattern(UMessagePatternApostropheMode mode, UErrorCode &errorCode);
/**
* Constructs a MessagePattern with default UMessagePatternApostropheMode and
* parses the MessageFormat pattern string.
* @param pattern a MessageFormat pattern string
* @param parseError Struct to receive information on the position
* of an error within the pattern.
* Can be NULL.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* TODO: turn @throws into UErrorCode specifics?
* @throws IllegalArgumentException for syntax errors in the pattern string
* @throws IndexOutOfBoundsException if certain limits are exceeded
* (e.g., argument number too high, argument name too long, etc.)
* @throws NumberFormatException if a number could not be parsed
* @stable ICU 4.8
*/
MessagePattern(const UnicodeString &pattern, UParseError *parseError, UErrorCode &errorCode);
/**
* Copy constructor.
* @param other Object to copy.
* @stable ICU 4.8
*/
MessagePattern(const MessagePattern &other);
/**
* Assignment operator.
* @param other Object to copy.
* @return *this=other
* @stable ICU 4.8
*/
MessagePattern &operator=(const MessagePattern &other);
/**
* Destructor.
* @stable ICU 4.8
*/
virtual ~MessagePattern();
/**
* Parses a MessageFormat pattern string.
* @param pattern a MessageFormat pattern string
* @param parseError Struct to receive information on the position
* of an error within the pattern.
* Can be NULL.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return *this
* @throws IllegalArgumentException for syntax errors in the pattern string
* @throws IndexOutOfBoundsException if certain limits are exceeded
* (e.g., argument number too high, argument name too long, etc.)
* @throws NumberFormatException if a number could not be parsed
* @stable ICU 4.8
*/
MessagePattern &parse(const UnicodeString &pattern,
UParseError *parseError, UErrorCode &errorCode);
/**
* Parses a ChoiceFormat pattern string.
* @param pattern a ChoiceFormat pattern string
* @param parseError Struct to receive information on the position
* of an error within the pattern.
* Can be NULL.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return *this
* @throws IllegalArgumentException for syntax errors in the pattern string
* @throws IndexOutOfBoundsException if certain limits are exceeded
* (e.g., argument number too high, argument name too long, etc.)
* @throws NumberFormatException if a number could not be parsed
* @stable ICU 4.8
*/
MessagePattern &parseChoiceStyle(const UnicodeString &pattern,
UParseError *parseError, UErrorCode &errorCode);
/**
* Parses a PluralFormat pattern string.
* @param pattern a PluralFormat pattern string
* @param parseError Struct to receive information on the position
* of an error within the pattern.
* Can be NULL.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return *this
* @throws IllegalArgumentException for syntax errors in the pattern string
* @throws IndexOutOfBoundsException if certain limits are exceeded
* (e.g., argument number too high, argument name too long, etc.)
* @throws NumberFormatException if a number could not be parsed
* @stable ICU 4.8
*/
MessagePattern &parsePluralStyle(const UnicodeString &pattern,
UParseError *parseError, UErrorCode &errorCode);
/**
* Parses a SelectFormat pattern string.
* @param pattern a SelectFormat pattern string
* @param parseError Struct to receive information on the position
* of an error within the pattern.
* Can be NULL.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return *this
* @throws IllegalArgumentException for syntax errors in the pattern string
* @throws IndexOutOfBoundsException if certain limits are exceeded
* (e.g., argument number too high, argument name too long, etc.)
* @throws NumberFormatException if a number could not be parsed
* @stable ICU 4.8
*/
MessagePattern &parseSelectStyle(const UnicodeString &pattern,
UParseError *parseError, UErrorCode &errorCode);
/**
* Clears this MessagePattern.
* countParts() will return 0.
* @stable ICU 4.8
*/
void clear();
/**
* Clears this MessagePattern and sets the UMessagePatternApostropheMode.
* countParts() will return 0.
* @param mode The new UMessagePatternApostropheMode.
* @stable ICU 4.8
*/
void clearPatternAndSetApostropheMode(UMessagePatternApostropheMode mode) {
clear();
aposMode=mode;
}
/**
* @param other another object to compare with.
* @return TRUE if this object is equivalent to the other one.
* @stable ICU 4.8
*/
UBool operator==(const MessagePattern &other) const;
/**
* @param other another object to compare with.
* @return FALSE if this object is equivalent to the other one.
* @stable ICU 4.8
*/
inline UBool operator!=(const MessagePattern &other) const {
return !operator==(other);
}
/**
* @return A hash code for this object.
* @stable ICU 4.8
*/
int32_t hashCode() const;
/**
* @return this instance's UMessagePatternApostropheMode.
* @stable ICU 4.8
*/
UMessagePatternApostropheMode getApostropheMode() const {
return aposMode;
}
// Java has package-private jdkAposMode() here.
// In C++, this is declared in the MessageImpl class.
/**
* @return the parsed pattern string (null if none was parsed).
* @stable ICU 4.8
*/
const UnicodeString &getPatternString() const {
return msg;
}
/**
* Does the parsed pattern have named arguments like {first_name}?
* @return TRUE if the parsed pattern has at least one named argument.
* @stable ICU 4.8
*/
UBool hasNamedArguments() const {
return hasArgNames;
}
/**
* Does the parsed pattern have numbered arguments like {2}?
* @return TRUE if the parsed pattern has at least one numbered argument.
* @stable ICU 4.8
*/
UBool hasNumberedArguments() const {
return hasArgNumbers;
}
/**
* Validates and parses an argument name or argument number string.
* An argument name must be a "pattern identifier", that is, it must contain
* no Unicode Pattern_Syntax or Pattern_White_Space characters.
* If it only contains ASCII digits, then it must be a small integer with no leading zero.
* @param name Input string.
* @return &gt;=0 if the name is a valid number,
* ARG_NAME_NOT_NUMBER (-1) if it is a "pattern identifier" but not all ASCII digits,
* ARG_NAME_NOT_VALID (-2) if it is neither.
* @stable ICU 4.8
*/
static int32_t validateArgumentName(const UnicodeString &name);
/**
* Returns a version of the parsed pattern string where each ASCII apostrophe
* is doubled (escaped) if it is not already, and if it is not interpreted as quoting syntax.
* <p>
* For example, this turns "I don't '{know}' {gender,select,female{h''er}other{h'im}}."
* into "I don''t '{know}' {gender,select,female{h''er}other{h''im}}."
* @return the deep-auto-quoted version of the parsed pattern string.
* @see MessageFormat.autoQuoteApostrophe()
* @stable ICU 4.8
*/
UnicodeString autoQuoteApostropheDeep() const;
class Part;
/**
* Returns the number of "parts" created by parsing the pattern string.
* Returns 0 if no pattern has been parsed or clear() was called.
* @return the number of pattern parts.
* @stable ICU 4.8
*/
int32_t countParts() const {
return partsLength;
}
/**
* Gets the i-th pattern "part".
* @param i The index of the Part data. (0..countParts()-1)
* @return the i-th pattern "part".
* @stable ICU 4.8
*/
const Part &getPart(int32_t i) const {
return parts[i];
}
/**
* Returns the UMessagePatternPartType of the i-th pattern "part".
* Convenience method for getPart(i).getType().
* @param i The index of the Part data. (0..countParts()-1)
* @return The UMessagePatternPartType of the i-th Part.
* @stable ICU 4.8
*/
UMessagePatternPartType getPartType(int32_t i) const {
return getPart(i).type;
}
/**
* Returns the pattern index of the specified pattern "part".
* Convenience method for getPart(partIndex).getIndex().
* @param partIndex The index of the Part data. (0..countParts()-1)
* @return The pattern index of this Part.
* @stable ICU 4.8
*/
int32_t getPatternIndex(int32_t partIndex) const {
return getPart(partIndex).index;
}
/**
* Returns the substring of the pattern string indicated by the Part.
* Convenience method for getPatternString().substring(part.getIndex(), part.getLimit()).
* @param part a part of this MessagePattern.
* @return the substring associated with part.
* @stable ICU 4.8
*/
UnicodeString getSubstring(const Part &part) const {
return msg.tempSubString(part.index, part.length);
}
/**
* Compares the part's substring with the input string s.
* @param part a part of this MessagePattern.
* @param s a string.
* @return TRUE if getSubstring(part).equals(s).
* @stable ICU 4.8
*/
UBool partSubstringMatches(const Part &part, const UnicodeString &s) const {
return 0==msg.compare(part.index, part.length, s);
}
/**
* Returns the numeric value associated with an ARG_INT or ARG_DOUBLE.
* @param part a part of this MessagePattern.
* @return the part's numeric value, or UMSGPAT_NO_NUMERIC_VALUE if this is not a numeric part.
* @stable ICU 4.8
*/
double getNumericValue(const Part &part) const;
/**
* Returns the "offset:" value of a PluralFormat argument, or 0 if none is specified.
* @param pluralStart the index of the first PluralFormat argument style part. (0..countParts()-1)
* @return the "offset:" value.
* @stable ICU 4.8
*/
double getPluralOffset(int32_t pluralStart) const;
/**
* Returns the index of the ARG|MSG_LIMIT part corresponding to the ARG|MSG_START at start.
* @param start The index of some Part data (0..countParts()-1);
* this Part should be of Type ARG_START or MSG_START.
* @return The first i>start where getPart(i).getType()==ARG|MSG_LIMIT at the same nesting level,
* or start itself if getPartType(msgStart)!=ARG|MSG_START.
* @stable ICU 4.8
*/
int32_t getLimitPartIndex(int32_t start) const {
int32_t limit=getPart(start).limitPartIndex;
if(limit<start) {
return start;
}
return limit;
}
/**
* A message pattern "part", representing a pattern parsing event.
* There is a part for the start and end of a message or argument,
* for quoting and escaping of and with ASCII apostrophes,
* and for syntax elements of "complex" arguments.
* @stable ICU 4.8
*/
class Part : public UMemory {
public:
/**
* Default constructor, do not use.
* @internal
*/
Part() {}
/**
* Returns the type of this part.
* @return the part type.
* @stable ICU 4.8
*/
UMessagePatternPartType getType() const {
return type;
}
/**
* Returns the pattern string index associated with this Part.
* @return this part's pattern string index.
* @stable ICU 4.8
*/
int32_t getIndex() const {
return index;
}
/**
* Returns the length of the pattern substring associated with this Part.
* This is 0 for some parts.
* @return this part's pattern substring length.
* @stable ICU 4.8
*/
int32_t getLength() const {
return length;
}
/**
* Returns the pattern string limit (exclusive-end) index associated with this Part.
* Convenience method for getIndex()+getLength().
* @return this part's pattern string limit index, same as getIndex()+getLength().
* @stable ICU 4.8
*/
int32_t getLimit() const {
return index+length;
}
/**
* Returns a value associated with this part.
* See the documentation of each part type for details.
* @return the part value.
* @stable ICU 4.8
*/
int32_t getValue() const {
return value;
}
/**
* Returns the argument type if this part is of type ARG_START or ARG_LIMIT,
* otherwise UMSGPAT_ARG_TYPE_NONE.
* @return the argument type for this part.
* @stable ICU 4.8
*/
UMessagePatternArgType getArgType() const {
UMessagePatternPartType type=getType();
if(type==UMSGPAT_PART_TYPE_ARG_START || type==UMSGPAT_PART_TYPE_ARG_LIMIT) {
return (UMessagePatternArgType)value;
} else {
return UMSGPAT_ARG_TYPE_NONE;
}
}
/**
* Indicates whether the Part type has a numeric value.
* If so, then that numeric value can be retrieved via MessagePattern.getNumericValue().
* @param type The Part type to be tested.
* @return TRUE if the Part type has a numeric value.
* @stable ICU 4.8
*/
static UBool hasNumericValue(UMessagePatternPartType type) {
return type==UMSGPAT_PART_TYPE_ARG_INT || type==UMSGPAT_PART_TYPE_ARG_DOUBLE;
}
/**
* @param other another object to compare with.
* @return TRUE if this object is equivalent to the other one.
* @stable ICU 4.8
*/
UBool operator==(const Part &other) const;
/**
* @param other another object to compare with.
* @return FALSE if this object is equivalent to the other one.
* @stable ICU 4.8
*/
inline UBool operator!=(const Part &other) const {
return !operator==(other);
}
/**
* @return A hash code for this object.
* @stable ICU 4.8
*/
int32_t hashCode() const {
return ((type*37+index)*37+length)*37+value;
}
private:
friend class MessagePattern;
static const int32_t MAX_LENGTH=0xffff;
static const int32_t MAX_VALUE=0x7fff;
// Some fields are not final because they are modified during pattern parsing.
// After pattern parsing, the parts are effectively immutable.
UMessagePatternPartType type;
int32_t index;
uint16_t length;
int16_t value;
int32_t limitPartIndex;
};
private:
void preParse(const UnicodeString &pattern, UParseError *parseError, UErrorCode &errorCode);
void postParse();
int32_t parseMessage(int32_t index, int32_t msgStartLength,
int32_t nestingLevel, UMessagePatternArgType parentType,
UParseError *parseError, UErrorCode &errorCode);
int32_t parseArg(int32_t index, int32_t argStartLength, int32_t nestingLevel,
UParseError *parseError, UErrorCode &errorCode);
int32_t parseSimpleStyle(int32_t index, UParseError *parseError, UErrorCode &errorCode);
int32_t parseChoiceStyle(int32_t index, int32_t nestingLevel,
UParseError *parseError, UErrorCode &errorCode);
int32_t parsePluralOrSelectStyle(UMessagePatternArgType argType, int32_t index, int32_t nestingLevel,
UParseError *parseError, UErrorCode &errorCode);
/**
* Validates and parses an argument name or argument number string.
* This internal method assumes that the input substring is a "pattern identifier".
* @return &gt;=0 if the name is a valid number,
* ARG_NAME_NOT_NUMBER (-1) if it is a "pattern identifier" but not all ASCII digits,
* ARG_NAME_NOT_VALID (-2) if it is neither.
* @see #validateArgumentName(String)
*/
static int32_t parseArgNumber(const UnicodeString &s, int32_t start, int32_t limit);
int32_t parseArgNumber(int32_t start, int32_t limit) {
return parseArgNumber(msg, start, limit);
}
/**
* Parses a number from the specified message substring.
* @param start start index into the message string
* @param limit limit index into the message string, must be start<limit
* @param allowInfinity TRUE if U+221E is allowed (for ChoiceFormat)
* @param parseError
* @param errorCode
*/
void parseDouble(int32_t start, int32_t limit, UBool allowInfinity,
UParseError *parseError, UErrorCode &errorCode);
// Java has package-private appendReducedApostrophes() here.
// In C++, this is declared in the MessageImpl class.
int32_t skipWhiteSpace(int32_t index);
int32_t skipIdentifier(int32_t index);
/**
* Skips a sequence of characters that could occur in a double value.
* Does not fully parse or validate the value.
*/
int32_t skipDouble(int32_t index);
static UBool isArgTypeChar(UChar32 c);
UBool isChoice(int32_t index);
UBool isPlural(int32_t index);
UBool isSelect(int32_t index);
UBool isOrdinal(int32_t index);
/**
* @return TRUE if we are inside a MessageFormat (sub-)pattern,
* as opposed to inside a top-level choice/plural/select pattern.
*/
UBool inMessageFormatPattern(int32_t nestingLevel);
/**
* @return TRUE if we are in a MessageFormat sub-pattern
* of a top-level ChoiceFormat pattern.
*/
UBool inTopLevelChoiceMessage(int32_t nestingLevel, UMessagePatternArgType parentType);
void addPart(UMessagePatternPartType type, int32_t index, int32_t length,
int32_t value, UErrorCode &errorCode);
void addLimitPart(int32_t start,
UMessagePatternPartType type, int32_t index, int32_t length,
int32_t value, UErrorCode &errorCode);
void addArgDoublePart(double numericValue, int32_t start, int32_t length, UErrorCode &errorCode);
void setParseError(UParseError *parseError, int32_t index);
UBool init(UErrorCode &errorCode);
UBool copyStorage(const MessagePattern &other, UErrorCode &errorCode);
UMessagePatternApostropheMode aposMode;
UnicodeString msg;
// ArrayList<Part> parts=new ArrayList<Part>();
MessagePatternPartsList *partsList;
Part *parts;
int32_t partsLength;
// ArrayList<Double> numericValues;
MessagePatternDoubleList *numericValuesList;
double *numericValues;
int32_t numericValuesLength;
UBool hasArgNames;
UBool hasArgNumbers;
UBool needsAutoQuoting;
};
U_NAMESPACE_END
#endif // !UCONFIG_NO_FORMATTING
#endif // __MESSAGEPATTERN_H__
project/jni/icuuc/include/unicode/msgfmt.h
-1093
View File
File diff suppressed because it is too large Load Diff
project/jni/icuuc/include/unicode/normalizer2.h
-658
View File
@@ -1,658 +0,0 @@
/*
*******************************************************************************
*
* Copyright (C) 2009-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: normalizer2.h
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2009nov22
* created by: Markus W. Scherer
*/
#ifndef __NORMALIZER2_H__
#define __NORMALIZER2_H__
/**
* \file
* \brief C++ API: New API for Unicode Normalization.
*/
#include "unicode/utypes.h"
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/uniset.h"
#include "unicode/unistr.h"
#include "unicode/unorm2.h"
U_NAMESPACE_BEGIN
/**
* Unicode normalization functionality for standard Unicode normalization or
* for using custom mapping tables.
* All instances of this class are unmodifiable/immutable.
* Instances returned by getInstance() are singletons that must not be deleted by the caller.
* The Normalizer2 class is not intended for public subclassing.
*
* The primary functions are to produce a normalized string and to detect whether
* a string is already normalized.
* The most commonly used normalization forms are those defined in
* http://www.unicode.org/unicode/reports/tr15/
* However, this API supports additional normalization forms for specialized purposes.
* For example, NFKC_Casefold is provided via getInstance("nfkc_cf", COMPOSE)
* and can be used in implementations of UTS #46.
*
* Not only are the standard compose and decompose modes supplied,
* but additional modes are provided as documented in the Mode enum.
*
* Some of the functions in this class identify normalization boundaries.
* At a normalization boundary, the portions of the string
* before it and starting from it do not interact and can be handled independently.
*
* The spanQuickCheckYes() stops at a normalization boundary.
* When the goal is a normalized string, then the text before the boundary
* can be copied, and the remainder can be processed with normalizeSecondAndAppend().
*
* The hasBoundaryBefore(), hasBoundaryAfter() and isInert() functions test whether
* a character is guaranteed to be at a normalization boundary,
* regardless of context.
* This is used for moving from one normalization boundary to the next
* or preceding boundary, and for performing iterative normalization.
*
* Iterative normalization is useful when only a small portion of a
* longer string needs to be processed.
* For example, in ICU, iterative normalization is used by the NormalizationTransliterator
* (to avoid replacing already-normalized text) and ucol_nextSortKeyPart()
* (to process only the substring for which sort key bytes are computed).
*
* The set of normalization boundaries returned by these functions may not be
* complete: There may be more boundaries that could be returned.
* Different functions may return different boundaries.
* @stable ICU 4.4
*/
class U_COMMON_API Normalizer2 : public UObject {
public:
/**
* Destructor.
* @stable ICU 4.4
*/
~Normalizer2();
/**
* Returns a Normalizer2 instance for Unicode NFC normalization.
* Same as getInstance(NULL, "nfc", UNORM2_COMPOSE, errorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
static const Normalizer2 *
getNFCInstance(UErrorCode &errorCode);
/**
* Returns a Normalizer2 instance for Unicode NFD normalization.
* Same as getInstance(NULL, "nfc", UNORM2_DECOMPOSE, errorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
static const Normalizer2 *
getNFDInstance(UErrorCode &errorCode);
/**
* Returns a Normalizer2 instance for Unicode NFKC normalization.
* Same as getInstance(NULL, "nfkc", UNORM2_COMPOSE, errorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
static const Normalizer2 *
getNFKCInstance(UErrorCode &errorCode);
/**
* Returns a Normalizer2 instance for Unicode NFKD normalization.
* Same as getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, errorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
static const Normalizer2 *
getNFKDInstance(UErrorCode &errorCode);
/**
* Returns a Normalizer2 instance for Unicode NFKC_Casefold normalization.
* Same as getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, errorCode).
* Returns an unmodifiable singleton instance. Do not delete it.
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 49
*/
static const Normalizer2 *
getNFKCCasefoldInstance(UErrorCode &errorCode);
/**
* Returns a Normalizer2 instance which uses the specified data file
* (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle)
* and which composes or decomposes text according to the specified mode.
* Returns an unmodifiable singleton instance. Do not delete it.
*
* Use packageName=NULL for data files that are part of ICU's own data.
* Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD.
* Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD.
* Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold.
*
* @param packageName NULL for ICU built-in data, otherwise application data package name
* @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file
* @param mode normalization mode (compose or decompose etc.)
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return the requested Normalizer2, if successful
* @stable ICU 4.4
*/
static const Normalizer2 *
getInstance(const char *packageName,
const char *name,
UNormalization2Mode mode,
UErrorCode &errorCode);
/**
* Returns the normalized form of the source string.
* @param src source string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return normalized src
* @stable ICU 4.4
*/
UnicodeString
normalize(const UnicodeString &src, UErrorCode &errorCode) const {
UnicodeString result;
normalize(src, result, errorCode);
return result;
}
/**
* Writes the normalized form of the source string to the destination string
* (replacing its contents) and returns the destination string.
* The source and destination strings must be different objects.
* @param src source string
* @param dest destination string; its contents is replaced with normalized src
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.4
*/
virtual UnicodeString &
normalize(const UnicodeString &src,
UnicodeString &dest,
UErrorCode &errorCode) const = 0;
/**
* Appends the normalized form of the second string to the first string
* (merging them at the boundary) and returns the first string.
* The result is normalized if the first string was normalized.
* The first and second strings must be different objects.
* @param first string, should be normalized
* @param second string, will be normalized
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
virtual UnicodeString &
normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const = 0;
/**
* Appends the second string to the first string
* (merging them at the boundary) and returns the first string.
* The result is normalized if both the strings were normalized.
* The first and second strings must be different objects.
* @param first string, should be normalized
* @param second string, should be normalized
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
virtual UnicodeString &
append(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const = 0;
/**
* Gets the decomposition mapping of c.
* Roughly equivalent to normalizing the String form of c
* on a UNORM2_DECOMPOSE Normalizer2 instance, but much faster, and except that this function
* returns FALSE and does not write a string
* if c does not have a decomposition mapping in this instance's data.
* This function is independent of the mode of the Normalizer2.
* @param c code point
* @param decomposition String object which will be set to c's
* decomposition mapping, if there is one.
* @return TRUE if c has a decomposition, otherwise FALSE
* @stable ICU 4.6
*/
virtual UBool
getDecomposition(UChar32 c, UnicodeString &decomposition) const = 0;
/**
* Gets the raw decomposition mapping of c.
*
* This is similar to the getDecomposition() method but returns the
* raw decomposition mapping as specified in UnicodeData.txt or
* (for custom data) in the mapping files processed by the gennorm2 tool.
* By contrast, getDecomposition() returns the processed,
* recursively-decomposed version of this mapping.
*
* When used on a standard NFKC Normalizer2 instance,
* getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property.
*
* When used on a standard NFC Normalizer2 instance,
* it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can);
* in this case, the result contains either one or two code points (=1..4 UChars).
*
* This function is independent of the mode of the Normalizer2.
* The default implementation returns FALSE.
* @param c code point
* @param decomposition String object which will be set to c's
* raw decomposition mapping, if there is one.
* @return TRUE if c has a decomposition, otherwise FALSE
* @stable ICU 49
*/
virtual UBool
getRawDecomposition(UChar32 c, UnicodeString &decomposition) const;
/**
* Performs pairwise composition of a & b and returns the composite if there is one.
*
* Returns a composite code point c only if c has a two-way mapping to a+b.
* In standard Unicode normalization, this means that
* c has a canonical decomposition to a+b
* and c does not have the Full_Composition_Exclusion property.
*
* This function is independent of the mode of the Normalizer2.
* The default implementation returns a negative value.
* @param a A (normalization starter) code point.
* @param b Another code point.
* @return The non-negative composite code point if there is one; otherwise a negative value.
* @stable ICU 49
*/
virtual UChar32
composePair(UChar32 a, UChar32 b) const;
/**
* Gets the combining class of c.
* The default implementation returns 0
* but all standard implementations return the Unicode Canonical_Combining_Class value.
* @param c code point
* @return c's combining class
* @stable ICU 49
*/
virtual uint8_t
getCombiningClass(UChar32 c) const;
/**
* Tests if the string is normalized.
* Internally, in cases where the quickCheck() method would return "maybe"
* (which is only possible for the two COMPOSE modes) this method
* resolves to "yes" or "no" to provide a definitive result,
* at the cost of doing more work in those cases.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return TRUE if s is normalized
* @stable ICU 4.4
*/
virtual UBool
isNormalized(const UnicodeString &s, UErrorCode &errorCode) const = 0;
/**
* Tests if the string is normalized.
* For the two COMPOSE modes, the result could be "maybe" in cases that
* would take a little more work to resolve definitively.
* Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster
* combination of quick check + normalization, to avoid
* re-checking the "yes" prefix.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return UNormalizationCheckResult
* @stable ICU 4.4
*/
virtual UNormalizationCheckResult
quickCheck(const UnicodeString &s, UErrorCode &errorCode) const = 0;
/**
* Returns the end of the normalized substring of the input string.
* In other words, with <code>end=spanQuickCheckYes(s, ec);</code>
* the substring <code>UnicodeString(s, 0, end)</code>
* will pass the quick check with a "yes" result.
*
* The returned end index is usually one or more characters before the
* "no" or "maybe" character: The end index is at a normalization boundary.
* (See the class documentation for more about normalization boundaries.)
*
* When the goal is a normalized string and most input strings are expected
* to be normalized already, then call this method,
* and if it returns a prefix shorter than the input string,
* copy that prefix and use normalizeSecondAndAppend() for the remainder.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return "yes" span end index
* @stable ICU 4.4
*/
virtual int32_t
spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const = 0;
/**
* Tests if the character always has a normalization boundary before it,
* regardless of context.
* If true, then the character does not normalization-interact with
* preceding characters.
* In other words, a string containing this character can be normalized
* by processing portions before this character and starting from this
* character independently.
* This is used for iterative normalization. See the class documentation for details.
* @param c character to test
* @return TRUE if c has a normalization boundary before it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryBefore(UChar32 c) const = 0;
/**
* Tests if the character always has a normalization boundary after it,
* regardless of context.
* If true, then the character does not normalization-interact with
* following characters.
* In other words, a string containing this character can be normalized
* by processing portions up to this character and after this
* character independently.
* This is used for iterative normalization. See the class documentation for details.
* Note that this operation may be significantly slower than hasBoundaryBefore().
* @param c character to test
* @return TRUE if c has a normalization boundary after it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryAfter(UChar32 c) const = 0;
/**
* Tests if the character is normalization-inert.
* If true, then the character does not change, nor normalization-interact with
* preceding or following characters.
* In other words, a string containing this character can be normalized
* by processing portions before this character and after this
* character independently.
* This is used for iterative normalization. See the class documentation for details.
* Note that this operation may be significantly slower than hasBoundaryBefore().
* @param c character to test
* @return TRUE if c is normalization-inert
* @stable ICU 4.4
*/
virtual UBool isInert(UChar32 c) const = 0;
};
/**
* Normalization filtered by a UnicodeSet.
* Normalizes portions of the text contained in the filter set and leaves
* portions not contained in the filter set unchanged.
* Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE).
* Not-in-the-filter text is treated as "is normalized" and "quick check yes".
* This class implements all of (and only) the Normalizer2 API.
* An instance of this class is unmodifiable/immutable but is constructed and
* must be destructed by the owner.
* @stable ICU 4.4
*/
class U_COMMON_API FilteredNormalizer2 : public Normalizer2 {
public:
/**
* Constructs a filtered normalizer wrapping any Normalizer2 instance
* and a filter set.
* Both are aliased and must not be modified or deleted while this object
* is used.
* The filter set should be frozen; otherwise the performance will suffer greatly.
* @param n2 wrapped Normalizer2 instance
* @param filterSet UnicodeSet which determines the characters to be normalized
* @stable ICU 4.4
*/
FilteredNormalizer2(const Normalizer2 &n2, const UnicodeSet &filterSet) :
norm2(n2), set(filterSet) {}
/**
* Destructor.
* @stable ICU 4.4
*/
~FilteredNormalizer2();
/**
* Writes the normalized form of the source string to the destination string
* (replacing its contents) and returns the destination string.
* The source and destination strings must be different objects.
* @param src source string
* @param dest destination string; its contents is replaced with normalized src
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return dest
* @stable ICU 4.4
*/
virtual UnicodeString &
normalize(const UnicodeString &src,
UnicodeString &dest,
UErrorCode &errorCode) const;
/**
* Appends the normalized form of the second string to the first string
* (merging them at the boundary) and returns the first string.
* The result is normalized if the first string was normalized.
* The first and second strings must be different objects.
* @param first string, should be normalized
* @param second string, will be normalized
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
virtual UnicodeString &
normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const;
/**
* Appends the second string to the first string
* (merging them at the boundary) and returns the first string.
* The result is normalized if both the strings were normalized.
* The first and second strings must be different objects.
* @param first string, should be normalized
* @param second string, should be normalized
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return first
* @stable ICU 4.4
*/
virtual UnicodeString &
append(UnicodeString &first,
const UnicodeString &second,
UErrorCode &errorCode) const;
/**
* Gets the decomposition mapping of c.
* For details see the base class documentation.
*
* This function is independent of the mode of the Normalizer2.
* @param c code point
* @param decomposition String object which will be set to c's
* decomposition mapping, if there is one.
* @return TRUE if c has a decomposition, otherwise FALSE
* @stable ICU 4.6
*/
virtual UBool
getDecomposition(UChar32 c, UnicodeString &decomposition) const;
/**
* Gets the raw decomposition mapping of c.
* For details see the base class documentation.
*
* This function is independent of the mode of the Normalizer2.
* @param c code point
* @param decomposition String object which will be set to c's
* raw decomposition mapping, if there is one.
* @return TRUE if c has a decomposition, otherwise FALSE
* @stable ICU 49
*/
virtual UBool
getRawDecomposition(UChar32 c, UnicodeString &decomposition) const;
/**
* Performs pairwise composition of a & b and returns the composite if there is one.
* For details see the base class documentation.
*
* This function is independent of the mode of the Normalizer2.
* @param a A (normalization starter) code point.
* @param b Another code point.
* @return The non-negative composite code point if there is one; otherwise a negative value.
* @stable ICU 49
*/
virtual UChar32
composePair(UChar32 a, UChar32 b) const;
/**
* Gets the combining class of c.
* The default implementation returns 0
* but all standard implementations return the Unicode Canonical_Combining_Class value.
* @param c code point
* @return c's combining class
* @stable ICU 49
*/
virtual uint8_t
getCombiningClass(UChar32 c) const;
/**
* Tests if the string is normalized.
* For details see the Normalizer2 base class documentation.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return TRUE if s is normalized
* @stable ICU 4.4
*/
virtual UBool
isNormalized(const UnicodeString &s, UErrorCode &errorCode) const;
/**
* Tests if the string is normalized.
* For details see the Normalizer2 base class documentation.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return UNormalizationCheckResult
* @stable ICU 4.4
*/
virtual UNormalizationCheckResult
quickCheck(const UnicodeString &s, UErrorCode &errorCode) const;
/**
* Returns the end of the normalized substring of the input string.
* For details see the Normalizer2 base class documentation.
* @param s input string
* @param errorCode Standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return "yes" span end index
* @stable ICU 4.4
*/
virtual int32_t
spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const;
/**
* Tests if the character always has a normalization boundary before it,
* regardless of context.
* For details see the Normalizer2 base class documentation.
* @param c character to test
* @return TRUE if c has a normalization boundary before it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryBefore(UChar32 c) const;
/**
* Tests if the character always has a normalization boundary after it,
* regardless of context.
* For details see the Normalizer2 base class documentation.
* @param c character to test
* @return TRUE if c has a normalization boundary after it
* @stable ICU 4.4
*/
virtual UBool hasBoundaryAfter(UChar32 c) const;
/**
* Tests if the character is normalization-inert.
* For details see the Normalizer2 base class documentation.
* @param c character to test
* @return TRUE if c is normalization-inert
* @stable ICU 4.4
*/
virtual UBool isInert(UChar32 c) const;
private:
UnicodeString &
normalize(const UnicodeString &src,
UnicodeString &dest,
USetSpanCondition spanCondition,
UErrorCode &errorCode) const;
UnicodeString &
normalizeSecondAndAppend(UnicodeString &first,
const UnicodeString &second,
UBool doNormalize,
UErrorCode &errorCode) const;
const Normalizer2 &norm2;
const UnicodeSet &set;
};
U_NAMESPACE_END
#endif // !UCONFIG_NO_NORMALIZATION
#endif // __NORMALIZER2_H__
project/jni/icuuc/include/unicode/normlzr.h
-797
View File
@@ -1,797 +0,0 @@
/*
********************************************************************
* COPYRIGHT:
* Copyright (c) 1996-2011, International Business Machines Corporation and
* others. All Rights Reserved.
********************************************************************
*/
#ifndef NORMLZR_H
#define NORMLZR_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Unicode Normalization
*/
#if !UCONFIG_NO_NORMALIZATION
#include "unicode/chariter.h"
#include "unicode/normalizer2.h"
#include "unicode/unistr.h"
#include "unicode/unorm.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* The Normalizer class supports the standard normalization forms described in
* <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode">
* Unicode Standard Annex #15: Unicode Normalization Forms</a>.
*
* Note: This API has been replaced by the Normalizer2 class and is only available
* for backward compatibility. This class simply delegates to the Normalizer2 class.
* There is one exception: The new API does not provide a replacement for Normalizer::compare().
*
* The Normalizer class consists of two parts:
* - static functions that normalize strings or test if strings are normalized
* - a Normalizer object is an iterator that takes any kind of text and
* provides iteration over its normalized form
*
* The Normalizer class is not suitable for subclassing.
*
* For basic information about normalization forms and details about the C API
* please see the documentation in unorm.h.
*
* The iterator API with the Normalizer constructors and the non-static functions
* use a CharacterIterator as input. It is possible to pass a string which
* is then internally wrapped in a CharacterIterator.
* The input text is not normalized all at once, but incrementally where needed
* (providing efficient random access).
* This allows to pass in a large text but spend only a small amount of time
* normalizing a small part of that text.
* However, if the entire text is normalized, then the iterator will be
* slower than normalizing the entire text at once and iterating over the result.
* A possible use of the Normalizer iterator is also to report an index into the
* original text that is close to where the normalized characters come from.
*
* <em>Important:</em> The iterator API was cleaned up significantly for ICU 2.0.
* The earlier implementation reported the getIndex() inconsistently,
* and previous() could not be used after setIndex(), next(), first(), and current().
*
* Normalizer allows to start normalizing from anywhere in the input text by
* calling setIndexOnly(), first(), or last().
* Without calling any of these, the iterator will start at the beginning of the text.
*
* At any time, next() returns the next normalized code point (UChar32),
* with post-increment semantics (like CharacterIterator::next32PostInc()).
* previous() returns the previous normalized code point (UChar32),
* with pre-decrement semantics (like CharacterIterator::previous32()).
*
* current() returns the current code point
* (respectively the one at the newly set index) without moving
* the getIndex(). Note that if the text at the current position
* needs to be normalized, then these functions will do that.
* (This is why current() is not const.)
* It is more efficient to call setIndexOnly() instead, which does not
* normalize.
*
* getIndex() always refers to the position in the input text where the normalized
* code points are returned from. It does not always change with each returned
* code point.
* The code point that is returned from any of the functions
* corresponds to text at or after getIndex(), according to the
* function's iteration semantics (post-increment or pre-decrement).
*
* next() returns a code point from at or after the getIndex()
* from before the next() call. After the next() call, the getIndex()
* might have moved to where the next code point will be returned from
* (from a next() or current() call).
* This is semantically equivalent to array access with array[index++]
* (post-increment semantics).
*
* previous() returns a code point from at or after the getIndex()
* from after the previous() call.
* This is semantically equivalent to array access with array[--index]
* (pre-decrement semantics).
*
* Internally, the Normalizer iterator normalizes a small piece of text
* starting at the getIndex() and ending at a following "safe" index.
* The normalized results is stored in an internal string buffer, and
* the code points are iterated from there.
* With multiple iteration calls, this is repeated until the next piece
* of text needs to be normalized, and the getIndex() needs to be moved.
*
* The following "safe" index, the internal buffer, and the secondary
* iteration index into that buffer are not exposed on the API.
* This also means that it is currently not practical to return to
* a particular, arbitrary position in the text because one would need to
* know, and be able to set, in addition to the getIndex(), at least also the
* current index into the internal buffer.
* It is currently only possible to observe when getIndex() changes
* (with careful consideration of the iteration semantics),
* at which time the internal index will be 0.
* For example, if getIndex() is different after next() than before it,
* then the internal index is 0 and one can return to this getIndex()
* later with setIndexOnly().
*
* Note: While the setIndex() and getIndex() refer to indices in the
* underlying Unicode input text, the next() and previous() methods
* iterate through characters in the normalized output.
* This means that there is not necessarily a one-to-one correspondence
* between characters returned by next() and previous() and the indices
* passed to and returned from setIndex() and getIndex().
* It is for this reason that Normalizer does not implement the CharacterIterator interface.
*
* @author Laura Werner, Mark Davis, Markus Scherer
* @stable ICU 2.0
*/
class U_COMMON_API Normalizer : public UObject {
public:
/**
* If DONE is returned from an iteration function that returns a code point,
* then there are no more normalization results available.
* @stable ICU 2.0
*/
enum {
DONE=0xffff
};
// Constructors
/**
* Creates a new <code>Normalizer</code> object for iterating over the
* normalized form of a given string.
* <p>
* @param str The string to be normalized. The normalization
* will start at the beginning of the string.
*
* @param mode The normalization mode.
* @stable ICU 2.0
*/
Normalizer(const UnicodeString& str, UNormalizationMode mode);
/**
* Creates a new <code>Normalizer</code> object for iterating over the
* normalized form of a given string.
* <p>
* @param str The string to be normalized. The normalization
* will start at the beginning of the string.
*
* @param length Length of the string, or -1 if NUL-terminated.
* @param mode The normalization mode.
* @stable ICU 2.0
*/
Normalizer(const UChar* str, int32_t length, UNormalizationMode mode);
/**
* Creates a new <code>Normalizer</code> object for iterating over the
* normalized form of the given text.
* <p>
* @param iter The input text to be normalized. The normalization
* will start at the beginning of the string.
*
* @param mode The normalization mode.
* @stable ICU 2.0
*/
Normalizer(const CharacterIterator& iter, UNormalizationMode mode);
/**
* Copy constructor.
* @param copy The object to be copied.
* @stable ICU 2.0
*/
Normalizer(const Normalizer& copy);
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~Normalizer();
//-------------------------------------------------------------------------
// Static utility methods
//-------------------------------------------------------------------------
/**
* Normalizes a <code>UnicodeString</code> according to the specified normalization mode.
* This is a wrapper for unorm_normalize(), using UnicodeString's.
*
* The <code>options</code> parameter specifies which optional
* <code>Normalizer</code> features are to be enabled for this operation.
*
* @param source the input string to be normalized.
* @param mode the normalization mode
* @param options the optional features to be enabled (0 for no options)
* @param result The normalized string (on output).
* @param status The error code.
* @stable ICU 2.0
*/
static void U_EXPORT2 normalize(const UnicodeString& source,
UNormalizationMode mode, int32_t options,
UnicodeString& result,
UErrorCode &status);
/**
* Compose a <code>UnicodeString</code>.
* This is equivalent to normalize() with mode UNORM_NFC or UNORM_NFKC.
* This is a wrapper for unorm_normalize(), using UnicodeString's.
*
* The <code>options</code> parameter specifies which optional
* <code>Normalizer</code> features are to be enabled for this operation.
*
* @param source the string to be composed.
* @param compat Perform compatibility decomposition before composition.
* If this argument is <code>FALSE</code>, only canonical
* decomposition will be performed.
* @param options the optional features to be enabled (0 for no options)
* @param result The composed string (on output).
* @param status The error code.
* @stable ICU 2.0
*/
static void U_EXPORT2 compose(const UnicodeString& source,
UBool compat, int32_t options,
UnicodeString& result,
UErrorCode &status);
/**
* Static method to decompose a <code>UnicodeString</code>.
* This is equivalent to normalize() with mode UNORM_NFD or UNORM_NFKD.
* This is a wrapper for unorm_normalize(), using UnicodeString's.
*
* The <code>options</code> parameter specifies which optional
* <code>Normalizer</code> features are to be enabled for this operation.
*
* @param source the string to be decomposed.
* @param compat Perform compatibility decomposition.
* If this argument is <code>FALSE</code>, only canonical
* decomposition will be performed.
* @param options the optional features to be enabled (0 for no options)
* @param result The decomposed string (on output).
* @param status The error code.
* @stable ICU 2.0
*/
static void U_EXPORT2 decompose(const UnicodeString& source,
UBool compat, int32_t options,
UnicodeString& result,
UErrorCode &status);
/**
* Performing quick check on a string, to quickly determine if the string is
* in a particular normalization format.
* This is a wrapper for unorm_quickCheck(), using a UnicodeString.
*
* Three types of result can be returned UNORM_YES, UNORM_NO or
* UNORM_MAYBE. Result UNORM_YES indicates that the argument
* string is in the desired normalized format, UNORM_NO determines that
* argument string is not in the desired normalized format. A
* UNORM_MAYBE result indicates that a more thorough check is required,
* the user may have to put the string in its normalized form and compare the
* results.
* @param source string for determining if it is in a normalized format
* @param mode normalization format
* @param status A reference to a UErrorCode to receive any errors
* @return UNORM_YES, UNORM_NO or UNORM_MAYBE
*
* @see isNormalized
* @stable ICU 2.0
*/
static inline UNormalizationCheckResult
quickCheck(const UnicodeString &source, UNormalizationMode mode, UErrorCode &status);
/**
* Performing quick check on a string; same as the other version of quickCheck
* but takes an extra options parameter like most normalization functions.
*
* @param source string for determining if it is in a normalized format
* @param mode normalization format
* @param options the optional features to be enabled (0 for no options)
* @param status A reference to a UErrorCode to receive any errors
* @return UNORM_YES, UNORM_NO or UNORM_MAYBE
*
* @see isNormalized
* @stable ICU 2.6
*/
static UNormalizationCheckResult
quickCheck(const UnicodeString &source, UNormalizationMode mode, int32_t options, UErrorCode &status);
/**
* Test if a string is in a given normalization form.
* This is semantically equivalent to source.equals(normalize(source, mode)) .
*
* Unlike unorm_quickCheck(), this function returns a definitive result,
* never a "maybe".
* For NFD, NFKD, and FCD, both functions work exactly the same.
* For NFC and NFKC where quickCheck may return "maybe", this function will
* perform further tests to arrive at a TRUE/FALSE result.
*
* @param src String that is to be tested if it is in a normalization format.
* @param mode Which normalization form to test for.
* @param errorCode ICU error code in/out parameter.
* Must fulfill U_SUCCESS before the function call.
* @return Boolean value indicating whether the source string is in the
* "mode" normalization form.
*
* @see quickCheck
* @stable ICU 2.2
*/
static inline UBool
isNormalized(const UnicodeString &src, UNormalizationMode mode, UErrorCode &errorCode);
/**
* Test if a string is in a given normalization form; same as the other version of isNormalized
* but takes an extra options parameter like most normalization functions.
*
* @param src String that is to be tested if it is in a normalization format.
* @param mode Which normalization form to test for.
* @param options the optional features to be enabled (0 for no options)
* @param errorCode ICU error code in/out parameter.
* Must fulfill U_SUCCESS before the function call.
* @return Boolean value indicating whether the source string is in the
* "mode" normalization form.
*
* @see quickCheck
* @stable ICU 2.6
*/
static UBool
isNormalized(const UnicodeString &src, UNormalizationMode mode, int32_t options, UErrorCode &errorCode);
/**
* Concatenate normalized strings, making sure that the result is normalized as well.
*
* If both the left and the right strings are in
* the normalization form according to "mode/options",
* then the result will be
*
* \code
* dest=normalize(left+right, mode, options)
* \endcode
*
* For details see unorm_concatenate in unorm.h.
*
* @param left Left source string.
* @param right Right source string.
* @param result The output string.
* @param mode The normalization mode.
* @param options A bit set of normalization options.
* @param errorCode ICU error code in/out parameter.
* Must fulfill U_SUCCESS before the function call.
* @return result
*
* @see unorm_concatenate
* @see normalize
* @see unorm_next
* @see unorm_previous
*
* @stable ICU 2.1
*/
static UnicodeString &
U_EXPORT2 concatenate(const UnicodeString &left, const UnicodeString &right,
UnicodeString &result,
UNormalizationMode mode, int32_t options,
UErrorCode &errorCode);
/**
* Compare two strings for canonical equivalence.
* Further options include case-insensitive comparison and
* code point order (as opposed to code unit order).
*
* Canonical equivalence between two strings is defined as their normalized
* forms (NFD or NFC) being identical.
* This function compares strings incrementally instead of normalizing
* (and optionally case-folding) both strings entirely,
* improving performance significantly.
*
* Bulk normalization is only necessary if the strings do not fulfill the FCD
* conditions. Only in this case, and only if the strings are relatively long,
* is memory allocated temporarily.
* For FCD strings and short non-FCD strings there is no memory allocation.
*
* Semantically, this is equivalent to
* strcmp[CodePointOrder](NFD(foldCase(s1)), NFD(foldCase(s2)))
* where code point order and foldCase are all optional.
*
* UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match
* the case folding must be performed first, then the normalization.
*
* @param s1 First source string.
* @param s2 Second source string.
*
* @param options A bit set of options:
* - U_FOLD_CASE_DEFAULT or 0 is used for default options:
* Case-sensitive comparison in code unit order, and the input strings
* are quick-checked for FCD.
*
* - UNORM_INPUT_IS_FCD
* Set if the caller knows that both s1 and s2 fulfill the FCD conditions.
* If not set, the function will quickCheck for FCD
* and normalize if necessary.
*
* - U_COMPARE_CODE_POINT_ORDER
* Set to choose code point order instead of code unit order
* (see u_strCompare for details).
*
* - U_COMPARE_IGNORE_CASE
* Set to compare strings case-insensitively using case folding,
* instead of case-sensitively.
* If set, then the following case folding options are used.
*
* - Options as used with case-insensitive comparisons, currently:
*
* - U_FOLD_CASE_EXCLUDE_SPECIAL_I
* (see u_strCaseCompare for details)
*
* - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT
*
* @param errorCode ICU error code in/out parameter.
* Must fulfill U_SUCCESS before the function call.
* @return <0 or 0 or >0 as usual for string comparisons
*
* @see unorm_compare
* @see normalize
* @see UNORM_FCD
* @see u_strCompare
* @see u_strCaseCompare
*
* @stable ICU 2.2
*/
static inline int32_t
compare(const UnicodeString &s1, const UnicodeString &s2,
uint32_t options,
UErrorCode &errorCode);
//-------------------------------------------------------------------------
// Iteration API
//-------------------------------------------------------------------------
/**
* Return the current character in the normalized text.
* current() may need to normalize some text at getIndex().
* The getIndex() is not changed.
*
* @return the current normalized code point
* @stable ICU 2.0
*/
UChar32 current(void);
/**
* Return the first character in the normalized text.
* This is equivalent to setIndexOnly(startIndex()) followed by next().
* (Post-increment semantics.)
*
* @return the first normalized code point
* @stable ICU 2.0
*/
UChar32 first(void);
/**
* Return the last character in the normalized text.
* This is equivalent to setIndexOnly(endIndex()) followed by previous().
* (Pre-decrement semantics.)
*
* @return the last normalized code point
* @stable ICU 2.0
*/
UChar32 last(void);
/**
* Return the next character in the normalized text.
* (Post-increment semantics.)
* If the end of the text has already been reached, DONE is returned.
* The DONE value could be confused with a U+FFFF non-character code point
* in the text. If this is possible, you can test getIndex()<endIndex()
* before calling next(), or (getIndex()<endIndex() || last()!=DONE)
* after calling next(). (Calling last() will change the iterator state!)
*
* The C API unorm_next() is more efficient and does not have this ambiguity.
*
* @return the next normalized code point
* @stable ICU 2.0
*/
UChar32 next(void);
/**
* Return the previous character in the normalized text and decrement.
* (Pre-decrement semantics.)
* If the beginning of the text has already been reached, DONE is returned.
* The DONE value could be confused with a U+FFFF non-character code point
* in the text. If this is possible, you can test
* (getIndex()>startIndex() || first()!=DONE). (Calling first() will change
* the iterator state!)
*
* The C API unorm_previous() is more efficient and does not have this ambiguity.
*
* @return the previous normalized code point
* @stable ICU 2.0
*/
UChar32 previous(void);
/**
* Set the iteration position in the input text that is being normalized,
* without any immediate normalization.
* After setIndexOnly(), getIndex() will return the same index that is
* specified here.
*
* @param index the desired index in the input text.
* @stable ICU 2.0
*/
void setIndexOnly(int32_t index);
/**
* Reset the index to the beginning of the text.
* This is equivalent to setIndexOnly(startIndex)).
* @stable ICU 2.0
*/
void reset(void);
/**
* Retrieve the current iteration position in the input text that is
* being normalized.
*
* A following call to next() will return a normalized code point from
* the input text at or after this index.
*
* After a call to previous(), getIndex() will point at or before the
* position in the input text where the normalized code point
* was returned from with previous().
*
* @return the current index in the input text
* @stable ICU 2.0
*/
int32_t getIndex(void) const;
/**
* Retrieve the index of the start of the input text. This is the begin index
* of the <code>CharacterIterator</code> or the start (i.e. index 0) of the string
* over which this <code>Normalizer</code> is iterating.
*
* @return the smallest index in the input text where the Normalizer operates
* @stable ICU 2.0
*/
int32_t startIndex(void) const;
/**
* Retrieve the index of the end of the input text. This is the end index
* of the <code>CharacterIterator</code> or the length of the string
* over which this <code>Normalizer</code> is iterating.
* This end index is exclusive, i.e., the Normalizer operates only on characters
* before this index.
*
* @return the first index in the input text where the Normalizer does not operate
* @stable ICU 2.0
*/
int32_t endIndex(void) const;
/**
* Returns TRUE when both iterators refer to the same character in the same
* input text.
*
* @param that a Normalizer object to compare this one to
* @return comparison result
* @stable ICU 2.0
*/
UBool operator==(const Normalizer& that) const;
/**
* Returns FALSE when both iterators refer to the same character in the same
* input text.
*
* @param that a Normalizer object to compare this one to
* @return comparison result
* @stable ICU 2.0
*/
inline UBool operator!=(const Normalizer& that) const;
/**
* Returns a pointer to a new Normalizer that is a clone of this one.
* The caller is responsible for deleting the new clone.
* @return a pointer to a new Normalizer
* @stable ICU 2.0
*/
Normalizer* clone(void) const;
/**
* Generates a hash code for this iterator.
*
* @return the hash code
* @stable ICU 2.0
*/
int32_t hashCode(void) const;
//-------------------------------------------------------------------------
// Property access methods
//-------------------------------------------------------------------------
/**
* Set the normalization mode for this object.
* <p>
* <b>Note:</b>If the normalization mode is changed while iterating
* over a string, calls to {@link #next() } and {@link #previous() } may
* return previously buffers characters in the old normalization mode
* until the iteration is able to re-sync at the next base character.
* It is safest to call {@link #setIndexOnly }, {@link #reset() },
* {@link #setText }, {@link #first() },
* {@link #last() }, etc. after calling <code>setMode</code>.
* <p>
* @param newMode the new mode for this <code>Normalizer</code>.
* @see #getUMode
* @stable ICU 2.0
*/
void setMode(UNormalizationMode newMode);
/**
* Return the normalization mode for this object.
*
* This is an unusual name because there used to be a getMode() that
* returned a different type.
*
* @return the mode for this <code>Normalizer</code>
* @see #setMode
* @stable ICU 2.0
*/
UNormalizationMode getUMode(void) const;
/**
* Set options that affect this <code>Normalizer</code>'s operation.
* Options do not change the basic composition or decomposition operation
* that is being performed, but they control whether
* certain optional portions of the operation are done.
* Currently the only available option is obsolete.
*
* It is possible to specify multiple options that are all turned on or off.
*
* @param option the option(s) whose value is/are to be set.
* @param value the new setting for the option. Use <code>TRUE</code> to
* turn the option(s) on and <code>FALSE</code> to turn it/them off.
*
* @see #getOption
* @stable ICU 2.0
*/
void setOption(int32_t option,
UBool value);
/**
* Determine whether an option is turned on or off.
* If multiple options are specified, then the result is TRUE if any
* of them are set.
* <p>
* @param option the option(s) that are to be checked
* @return TRUE if any of the option(s) are set
* @see #setOption
* @stable ICU 2.0
*/
UBool getOption(int32_t option) const;
/**
* Set the input text over which this <code>Normalizer</code> will iterate.
* The iteration position is set to the beginning.
*
* @param newText a string that replaces the current input text
* @param status a UErrorCode
* @stable ICU 2.0
*/
void setText(const UnicodeString& newText,
UErrorCode &status);
/**
* Set the input text over which this <code>Normalizer</code> will iterate.
* The iteration position is set to the beginning.
*
* @param newText a CharacterIterator object that replaces the current input text
* @param status a UErrorCode
* @stable ICU 2.0
*/
void setText(const CharacterIterator& newText,
UErrorCode &status);
/**
* Set the input text over which this <code>Normalizer</code> will iterate.
* The iteration position is set to the beginning.
*
* @param newText a string that replaces the current input text
* @param length the length of the string, or -1 if NUL-terminated
* @param status a UErrorCode
* @stable ICU 2.0
*/
void setText(const UChar* newText,
int32_t length,
UErrorCode &status);
/**
* Copies the input text into the UnicodeString argument.
*
* @param result Receives a copy of the text under iteration.
* @stable ICU 2.0
*/
void getText(UnicodeString& result);
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
* @returns a UClassID for this class.
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
* @return a UClassID for the actual class.
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
private:
//-------------------------------------------------------------------------
// Private functions
//-------------------------------------------------------------------------
Normalizer(); // default constructor not implemented
Normalizer &operator=(const Normalizer &that); // assignment operator not implemented
// Private utility methods for iteration
// For documentation, see the source code
UBool nextNormalize();
UBool previousNormalize();
void init();
void clearBuffer(void);
//-------------------------------------------------------------------------
// Private data
//-------------------------------------------------------------------------
FilteredNormalizer2*fFilteredNorm2; // owned if not NULL
const Normalizer2 *fNorm2; // not owned; may be equal to fFilteredNorm2
UNormalizationMode fUMode;
int32_t fOptions;
// The input text and our position in it
CharacterIterator *text;
// The normalization buffer is the result of normalization
// of the source in [currentIndex..nextIndex[ .
int32_t currentIndex, nextIndex;
// A buffer for holding intermediate results
UnicodeString buffer;
int32_t bufferPos;
};
//-------------------------------------------------------------------------
// Inline implementations
//-------------------------------------------------------------------------
inline UBool
Normalizer::operator!= (const Normalizer& other) const
{ return ! operator==(other); }
inline UNormalizationCheckResult
Normalizer::quickCheck(const UnicodeString& source,
UNormalizationMode mode,
UErrorCode &status) {
return quickCheck(source, mode, 0, status);
}
inline UBool
Normalizer::isNormalized(const UnicodeString& source,
UNormalizationMode mode,
UErrorCode &status) {
return isNormalized(source, mode, 0, status);
}
inline int32_t
Normalizer::compare(const UnicodeString &s1, const UnicodeString &s2,
uint32_t options,
UErrorCode &errorCode) {
// all argument checking is done in unorm_compare
return unorm_compare(s1.getBuffer(), s1.length(),
s2.getBuffer(), s2.length(),
options,
&errorCode);
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_NORMALIZATION */
#endif // NORMLZR_H
project/jni/icuuc/include/unicode/numfmt.h
-1127
View File
File diff suppressed because it is too large Load Diff
project/jni/icuuc/include/unicode/numsys.h
-205
View File
@@ -1,205 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2010-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
*
* File NUMSYS.H
*
* Modification History:*
* Date Name Description
*
********************************************************************************
*/
#ifndef NUMSYS
#define NUMSYS
#include "unicode/utypes.h"
/**
* \def NUMSYS_NAME_CAPACITY
* Size of a numbering system name.
* @internal
*/
#define NUMSYS_NAME_CAPACITY 8
/**
* \file
* \brief C++ API: NumberingSystem object
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/format.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* Defines numbering systems. A numbering system describes the scheme by which
* numbers are to be presented to the end user. In its simplest form, a numbering
* system describes the set of digit characters that are to be used to display
* numbers, such as Western digits, Thai digits, Arabic-Indic digits, etc., in a
* positional numbering system with a specified radix (typically 10).
* More complicated numbering systems are algorithmic in nature, and require use
* of an RBNF formatter ( rule based number formatter ), in order to calculate
* the characters to be displayed for a given number. Examples of algorithmic
* numbering systems include Roman numerals, Chinese numerals, and Hebrew numerals.
* Formatting rules for many commonly used numbering systems are included in
* the ICU package, based on the numbering system rules defined in CLDR.
* Alternate numbering systems can be specified to a locale by using the
* numbers locale keyword.
*/
class U_I18N_API NumberingSystem : public UObject {
public:
/**
* Default Constructor.
*
* @stable ICU 4.2
*/
NumberingSystem();
/**
* Copy constructor.
* @stable ICU 4.2
*/
NumberingSystem(const NumberingSystem& other);
/**
* Destructor.
* @stable ICU 4.2
*/
virtual ~NumberingSystem();
/**
* Create the default numbering system associated with the specified locale.
* @param inLocale The given locale.
* @param status ICU status
* @stable ICU 4.2
*/
static NumberingSystem* U_EXPORT2 createInstance(const Locale & inLocale, UErrorCode& status);
/**
* Create the default numbering system associated with the default locale.
* @stable ICU 4.2
*/
static NumberingSystem* U_EXPORT2 createInstance(UErrorCode& status);
/**
* Create a numbering system using the specified radix, type, and description.
* @param radix The radix (base) for this numbering system.
* @param isAlgorithmic TRUE if the numbering system is algorithmic rather than numeric.
* @param description The string representing the set of digits used in a numeric system, or the name of the RBNF
* ruleset to be used in an algorithmic system.
* @param status ICU status
* @stable ICU 4.2
*/
static NumberingSystem* U_EXPORT2 createInstance(int32_t radix, UBool isAlgorithmic, const UnicodeString& description, UErrorCode& status );
/**
* Return a StringEnumeration over all the names of numbering systems known to ICU.
* @stable ICU 4.2
*/
static StringEnumeration * U_EXPORT2 getAvailableNames(UErrorCode& status);
/**
* Create a numbering system from one of the predefined numbering systems specified
* by CLDR and known to ICU, such as "latn", "arabext", or "hanidec"; the full list
* is returned by unumsys_openAvailableNames. Note that some of the names listed at
* http://unicode.org/repos/cldr/tags/latest/common/bcp47/number.xml - e.g.
* default, native, traditional, finance - do not identify specific numbering systems,
* but rather key values that may only be used as part of a locale, which in turn
* defines how they are mapped to a specific numbering system such as "latn" or "hant".
* @param name The name of the numbering system.
* @param status ICU status
* @stable ICU 4.2
*/
static NumberingSystem* U_EXPORT2 createInstanceByName(const char* name, UErrorCode& status);
/**
* Returns the radix of this numbering system. Simple positional numbering systems
* typically have radix 10, but might have a radix of e.g. 16 for hexadecimal. The
* radix is less well-defined for non-positional algorithmic systems.
* @stable ICU 4.2
*/
int32_t getRadix() const;
/**
* Returns the name of this numbering system if it was created using one of the predefined names
* known to ICU. Otherwise, returns NULL.
* @stable ICU 4.6
*/
const char * getName() const;
/**
* Returns the description string of this numbering system. For simple
* positional systems this is the ordered string of digits (with length matching
* the radix), e.g. "\u3007\u4E00\u4E8C\u4E09\u56DB\u4E94\u516D\u4E03\u516B\u4E5D"
* for "hanidec"; it would be "0123456789ABCDEF" for hexadecimal. For
* algorithmic systems this is the name of the RBNF ruleset used for formatting,
* e.g. "zh/SpelloutRules/%spellout-cardinal" for "hans" or "%greek-upper" for
* "grek".
* @stable ICU 4.2
*/
virtual UnicodeString getDescription() const;
/**
* Returns TRUE if the given numbering system is algorithmic
*
* @return TRUE if the numbering system is algorithmic.
* Otherwise, return FALSE.
* @stable ICU 4.2
*/
UBool isAlgorithmic() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 4.2
*
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 4.2
*/
virtual UClassID getDynamicClassID() const;
private:
UnicodeString desc;
int32_t radix;
UBool algorithmic;
char name[NUMSYS_NAME_CAPACITY+1];
void setRadix(int32_t radix);
void setAlgorithmic(UBool algorithmic);
void setDesc(UnicodeString desc);
void setName(const char* name);
static UBool isValidDigitString(const UnicodeString &str);
UBool hasContiguousDecimalDigits() const;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _NUMSYS
//eof
project/jni/icuuc/include/unicode/parseerr.h
-92
View File
@@ -1,92 +0,0 @@
/*
**********************************************************************
* Copyright (C) 1999-2005, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* Date Name Description
* 03/14/00 aliu Creation.
* 06/27/00 aliu Change from C++ class to C struct
**********************************************************************
*/
#ifndef PARSEERR_H
#define PARSEERR_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Parse Error Information
*/
/**
* The capacity of the context strings in UParseError.
* @stable ICU 2.0
*/
enum { U_PARSE_CONTEXT_LEN = 16 };
/**
* A UParseError struct is used to returned detailed information about
* parsing errors. It is used by ICU parsing engines that parse long
* rules, patterns, or programs, where the text being parsed is long
* enough that more information than a UErrorCode is needed to
* localize the error.
*
* <p>The line, offset, and context fields are optional; parsing
* engines may choose not to use to use them.
*
* <p>The preContext and postContext strings include some part of the
* context surrounding the error. If the source text is "let for=7"
* and "for" is the error (e.g., because it is a reserved word), then
* some examples of what a parser might produce are the following:
*
* <pre>
* preContext postContext
* "" "" The parser does not support context
* "let " "=7" Pre- and post-context only
* "let " "for=7" Pre- and post-context and error text
* "" "for" Error text only
* </pre>
*
* <p>Examples of engines which use UParseError (or may use it in the
* future) are Transliterator, RuleBasedBreakIterator, and
* RegexPattern.
*
* @stable ICU 2.0
*/
typedef struct UParseError {
/**
* The line on which the error occured. If the parser uses this
* field, it sets it to the line number of the source text line on
* which the error appears, which will be be a value >= 1. If the
* parse does not support line numbers, the value will be <= 0.
* @stable ICU 2.0
*/
int32_t line;
/**
* The character offset to the error. If the line field is >= 1,
* then this is the offset from the start of the line. Otherwise,
* this is the offset from the start of the text. If the parser
* does not support this field, it will have a value < 0.
* @stable ICU 2.0
*/
int32_t offset;
/**
* Textual context before the error. Null-terminated. The empty
* string if not supported by parser.
* @stable ICU 2.0
*/
UChar preContext[U_PARSE_CONTEXT_LEN];
/**
* The error itself and/or textual context after the error.
* Null-terminated. The empty string if not supported by parser.
* @stable ICU 2.0
*/
UChar postContext[U_PARSE_CONTEXT_LEN];
} UParseError;
#endif
project/jni/icuuc/include/unicode/parsepos.h
-230
View File
@@ -1,230 +0,0 @@
/*
* Copyright (C) 1997-2005, International Business Machines Corporation and others. All Rights Reserved.
*******************************************************************************
*
* File PARSEPOS.H
*
* Modification History:
*
* Date Name Description
* 07/09/97 helena Converted from java.
* 07/17/98 stephen Added errorIndex support.
* 05/11/99 stephen Cleaned up.
*******************************************************************************
*/
#ifndef PARSEPOS_H
#define PARSEPOS_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
U_NAMESPACE_BEGIN
/**
* \file
* \brief C++ API: Canonical Iterator
*/
/**
* <code>ParsePosition</code> is a simple class used by <code>Format</code>
* and its subclasses to keep track of the current position during parsing.
* The <code>parseObject</code> method in the various <code>Format</code>
* classes requires a <code>ParsePosition</code> object as an argument.
*
* <p>
* By design, as you parse through a string with different formats,
* you can use the same <code>ParsePosition</code>, since the index parameter
* records the current position.
*
* The ParsePosition class is not suitable for subclassing.
*
* @version 1.3 10/30/97
* @author Mark Davis, Helena Shih
* @see java.text.Format
*/
class U_COMMON_API ParsePosition : public UObject {
public:
/**
* Default constructor, the index starts with 0 as default.
* @stable ICU 2.0
*/
ParsePosition()
: UObject(),
index(0),
errorIndex(-1)
{}
/**
* Create a new ParsePosition with the given initial index.
* @param newIndex the new text offset.
* @stable ICU 2.0
*/
ParsePosition(int32_t newIndex)
: UObject(),
index(newIndex),
errorIndex(-1)
{}
/**
* Copy constructor
* @param copy the object to be copied from.
* @stable ICU 2.0
*/
ParsePosition(const ParsePosition& copy)
: UObject(copy),
index(copy.index),
errorIndex(copy.errorIndex)
{}
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~ParsePosition();
/**
* Assignment operator
* @stable ICU 2.0
*/
ParsePosition& operator=(const ParsePosition& copy);
/**
* Equality operator.
* @return TRUE if the two parse positions are equal, FALSE otherwise.
* @stable ICU 2.0
*/
UBool operator==(const ParsePosition& that) const;
/**
* Equality operator.
* @return TRUE if the two parse positions are not equal, FALSE otherwise.
* @stable ICU 2.0
*/
UBool operator!=(const ParsePosition& that) const;
/**
* Clone this object.
* Clones can be used concurrently in multiple threads.
* If an error occurs, then NULL is returned.
* The caller must delete the clone.
*
* @return a clone of this object
*
* @see getDynamicClassID
* @stable ICU 2.8
*/
ParsePosition *clone() const;
/**
* Retrieve the current parse position. On input to a parse method, this
* is the index of the character at which parsing will begin; on output, it
* is the index of the character following the last character parsed.
* @return the current index.
* @stable ICU 2.0
*/
int32_t getIndex(void) const;
/**
* Set the current parse position.
* @param index the new index.
* @stable ICU 2.0
*/
void setIndex(int32_t index);
/**
* Set the index at which a parse error occurred. Formatters
* should set this before returning an error code from their
* parseObject method. The default value is -1 if this is not
* set.
* @stable ICU 2.0
*/
void setErrorIndex(int32_t ei);
/**
* Retrieve the index at which an error occurred, or -1 if the
* error index has not been set.
* @stable ICU 2.0
*/
int32_t getErrorIndex(void) const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
private:
/**
* Input: the place you start parsing.
* <br>Output: position where the parse stopped.
* This is designed to be used serially,
* with each call setting index up for the next one.
*/
int32_t index;
/**
* The index at which a parse error occurred.
*/
int32_t errorIndex;
};
inline ParsePosition&
ParsePosition::operator=(const ParsePosition& copy)
{
index = copy.index;
errorIndex = copy.errorIndex;
return *this;
}
inline UBool
ParsePosition::operator==(const ParsePosition& copy) const
{
if(index != copy.index || errorIndex != copy.errorIndex)
return FALSE;
else
return TRUE;
}
inline UBool
ParsePosition::operator!=(const ParsePosition& copy) const
{
return !operator==(copy);
}
inline int32_t
ParsePosition::getIndex() const
{
return index;
}
inline void
ParsePosition::setIndex(int32_t offset)
{
this->index = offset;
}
inline int32_t
ParsePosition::getErrorIndex() const
{
return errorIndex;
}
inline void
ParsePosition::setErrorIndex(int32_t ei)
{
this->errorIndex = ei;
}
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/platform.h
-755
View File
@@ -1,755 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 1997-2013, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* FILE NAME : platform.h
*
* Date Name Description
* 05/13/98 nos Creation (content moved here from ptypes.h).
* 03/02/99 stephen Added AS400 support.
* 03/30/99 stephen Added Linux support.
* 04/13/99 stephen Reworked for autoconf.
******************************************************************************
*/
#ifndef _PLATFORM_H
#define _PLATFORM_H
#include "unicode/uconfig.h"
#include "unicode/uvernum.h"
/**
* \file
* \brief Basic types for the platform.
*
* This file used to be generated by autoconf/configure.
* Starting with ICU 49, platform.h is a normal source file,
* to simplify cross-compiling and working with non-autoconf/make build systems.
*
* When a value in this file does not work on a platform, then please
* try to derive it from the U_PLATFORM value
* (for which we might need a new value constant in rare cases)
* and/or from other macros that are predefined by the compiler
* or defined in standard (POSIX or platform or compiler) headers.
*
* As a temporary workaround, you can add an explicit <code>#define</code> for some macros
* before it is first tested, or add an equivalent -D macro definition
* to the compiler's command line.
*
* Note: Some compilers provide ways to show the predefined macros.
* For example, with gcc you can compile an empty .c file and have the compiler
* print the predefined macros with
* \code
* gcc -E -dM -x c /dev/null | sort
* \endcode
* (You can provide an actual empty .c file rather than /dev/null.
* <code>-x c++</code> is for C++.)
*/
/**
* Define some things so that they can be documented.
* @internal
*/
#ifdef U_IN_DOXYGEN
/*
* Problem: "platform.h:335: warning: documentation for unknown define U_HAVE_STD_STRING found." means that U_HAVE_STD_STRING is not documented.
* Solution: #define any defines for non @internal API here, so that they are visible in the docs. If you just set PREDEFINED in Doxyfile.in, they won't be documented.
*/
/* None for now. */
#endif
/**
* \def U_PLATFORM
* The U_PLATFORM macro defines the platform we're on.
*
* We used to define one different, value-less macro per platform.
* That made it hard to know the set of relevant platforms and macros,
* and hard to deal with variants of platforms.
*
* Starting with ICU 49, we define platforms as numeric macros,
* with ranges of values for related platforms and their variants.
* The U_PLATFORM macro is set to one of these values.
*
* Historical note from the Solaris Wikipedia article:
* AT&T and Sun collaborated on a project to merge the most popular Unix variants
* on the market at that time: BSD, System V, and Xenix.
* This became Unix System V Release 4 (SVR4).
*
* @internal
*/
/** Unknown platform. @internal */
#define U_PF_UNKNOWN 0
/** Windows @internal */
#define U_PF_WINDOWS 1000
/** MinGW. Windows, calls to Win32 API, but using GNU gcc and binutils. @internal */
#define U_PF_MINGW 1800
/**
* Cygwin. Windows, calls to cygwin1.dll for Posix functions,
* using MSVC or GNU gcc and binutils.
* @internal
*/
#define U_PF_CYGWIN 1900
/* Reserve 2000 for U_PF_UNIX? */
/** HP-UX is based on UNIX System V. @internal */
#define U_PF_HPUX 2100
/** Solaris is a Unix operating system based on SVR4. @internal */
#define U_PF_SOLARIS 2600
/** BSD is a UNIX operating system derivative. @internal */
#define U_PF_BSD 3000
/** AIX is based on UNIX System V Releases and 4.3 BSD. @internal */
#define U_PF_AIX 3100
/** IRIX is based on UNIX System V with BSD extensions. @internal */
#define U_PF_IRIX 3200
/**
* Darwin is a POSIX-compliant operating system, composed of code developed by Apple,
* as well as code derived from NeXTSTEP, BSD, and other projects,
* built around the Mach kernel.
* Darwin forms the core set of components upon which Mac OS X, Apple TV, and iOS are based.
* (Original description modified from WikiPedia.)
* @internal
*/
#define U_PF_DARWIN 3500
/** iPhone OS (iOS) is a derivative of Mac OS X. @internal */
#define U_PF_IPHONE 3550
/** QNX is a commercial Unix-like real-time operating system related to BSD. @internal */
#define U_PF_QNX 3700
/** Linux is a Unix-like operating system. @internal */
#define U_PF_LINUX 4000
/** Android is based on Linux. @internal */
#define U_PF_ANDROID 4050
/** "Classic" Mac OS (1984-2001) @internal */
#define U_PF_CLASSIC_MACOS 8000
/** z/OS is the successor to OS/390 which was the successor to MVS. @internal */
#define U_PF_OS390 9000
/** "IBM i" is the current name of what used to be i5/OS and earlier OS/400. @internal */
#define U_PF_OS400 9400
#ifdef U_PLATFORM
/* Use the predefined value. */
#elif defined(__MINGW32__)
# define U_PLATFORM U_PF_MINGW
#elif defined(__CYGWIN__)
# define U_PLATFORM U_PF_CYGWIN
#elif defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)
# define U_PLATFORM U_PF_WINDOWS
#elif defined(__ANDROID__)
# define U_PLATFORM U_PF_ANDROID
/* Android wchar_t support depends on the API level. */
# include <android/api-level.h>
#elif defined(linux) || defined(__linux__) || defined(__linux)
# define U_PLATFORM U_PF_LINUX
#elif defined(__APPLE__) && defined(__MACH__)
# include <TargetConditionals.h>
# if defined(TARGET_OS_IPHONE) && TARGET_OS_IPHONE /* variant of TARGET_OS_MAC */
# define U_PLATFORM U_PF_IPHONE
# else
# define U_PLATFORM U_PF_DARWIN
# endif
#elif defined(BSD) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__MirBSD__)
# define U_PLATFORM U_PF_BSD
#elif defined(sun) || defined(__sun)
/* Check defined(__SVR4) || defined(__svr4__) to distinguish Solaris from SunOS? */
# define U_PLATFORM U_PF_SOLARIS
# if defined(__GNUC__)
/* Solaris/GCC needs this header file to get the proper endianness. Normally, this
* header file is included with stddef.h but on Solairs/GCC, the GCC version of stddef.h
* is included which does not include this header file.
*/
# include <sys/isa_defs.h>
# endif
#elif defined(_AIX) || defined(__TOS_AIX__)
# define U_PLATFORM U_PF_AIX
#elif defined(_hpux) || defined(hpux) || defined(__hpux)
# define U_PLATFORM U_PF_HPUX
#elif defined(sgi) || defined(__sgi)
# define U_PLATFORM U_PF_IRIX
#elif defined(macintosh)
# define U_PLATFORM U_PF_CLASSIC_MACOS
#elif defined(__QNX__) || defined(__QNXNTO__)
# define U_PLATFORM U_PF_QNX
#elif defined(__TOS_MVS__)
# define U_PLATFORM U_PF_OS390
#elif defined(__OS400__) || defined(__TOS_OS400__)
# define U_PLATFORM U_PF_OS400
#else
# define U_PLATFORM U_PF_UNKNOWN
#endif
/**
* \def CYGWINMSVC
* Defined if this is Windows with Cygwin, but using MSVC rather than gcc.
* Otherwise undefined.
* @internal
*/
/* Commented out because this is already set in mh-cygwin-msvc
#if U_PLATFORM == U_PF_CYGWIN && defined(_MSC_VER)
# define CYGWINMSVC
#endif
*/
/**
* \def U_PLATFORM_USES_ONLY_WIN32_API
* Defines whether the platform uses only the Win32 API.
* Set to 1 for Windows/MSVC and MinGW but not Cygwin.
* @internal
*/
#ifdef U_PLATFORM_USES_ONLY_WIN32_API
/* Use the predefined value. */
#elif (U_PF_WINDOWS <= U_PLATFORM && U_PLATFORM <= U_PF_MINGW) || defined(CYGWINMSVC)
# define U_PLATFORM_USES_ONLY_WIN32_API 1
#else
/* Cygwin implements POSIX. */
# define U_PLATFORM_USES_ONLY_WIN32_API 0
#endif
/**
* \def U_PLATFORM_HAS_WIN32_API
* Defines whether the Win32 API is available on the platform.
* Set to 1 for Windows/MSVC, MinGW and Cygwin.
* @internal
*/
#ifdef U_PLATFORM_HAS_WIN32_API
/* Use the predefined value. */
#elif U_PF_WINDOWS <= U_PLATFORM && U_PLATFORM <= U_PF_CYGWIN
# define U_PLATFORM_HAS_WIN32_API 1
#else
# define U_PLATFORM_HAS_WIN32_API 0
#endif
/**
* \def U_PLATFORM_IMPLEMENTS_POSIX
* Defines whether the platform implements (most of) the POSIX API.
* Set to 1 for Cygwin and most other platforms.
* @internal
*/
#ifdef U_PLATFORM_IMPLEMENTS_POSIX
/* Use the predefined value. */
#elif U_PLATFORM_USES_ONLY_WIN32_API || U_PLATFORM == U_PF_CLASSIC_MACOS
# define U_PLATFORM_IMPLEMENTS_POSIX 0
#else
# define U_PLATFORM_IMPLEMENTS_POSIX 1
#endif
/**
* \def U_PLATFORM_IS_LINUX_BASED
* Defines whether the platform is Linux or one of its derivatives.
* @internal
*/
#ifdef U_PLATFORM_IS_LINUX_BASED
/* Use the predefined value. */
#elif U_PF_LINUX <= U_PLATFORM && U_PLATFORM <= U_PF_ANDROID
# define U_PLATFORM_IS_LINUX_BASED 1
#else
# define U_PLATFORM_IS_LINUX_BASED 0
#endif
/**
* \def U_PLATFORM_IS_DARWIN_BASED
* Defines whether the platform is Darwin or one of its derivatives.
* @internal
*/
#ifdef U_PLATFORM_IS_DARWIN_BASED
/* Use the predefined value. */
#elif U_PF_DARWIN <= U_PLATFORM && U_PLATFORM <= U_PF_IPHONE
# define U_PLATFORM_IS_DARWIN_BASED 1
#else
# define U_PLATFORM_IS_DARWIN_BASED 0
#endif
/**
* \def U_HAVE_STDINT_H
* Defines whether stdint.h is available. It is a C99 standard header.
* We used to include inttypes.h which includes stdint.h but we usually do not need
* the additional definitions from inttypes.h.
* @internal
*/
#ifdef U_HAVE_STDINT_H
/* Use the predefined value. */
#elif U_PLATFORM_USES_ONLY_WIN32_API
# if defined(__BORLANDC__) || U_PLATFORM == U_PF_MINGW || (defined(_MSC_VER) && _MSC_VER>=1600)
/* Windows Visual Studio 9 and below do not have stdint.h & inttypes.h, but VS 2010 adds them. */
# define U_HAVE_STDINT_H 1
# else
# define U_HAVE_STDINT_H 0
# endif
#elif U_PLATFORM == U_PF_SOLARIS
/* Solaris has inttypes.h but not stdint.h. */
# define U_HAVE_STDINT_H 0
#elif U_PLATFORM == U_PF_AIX && !defined(_AIX51) && defined(_POWER)
/* PPC AIX <= 4.3 has inttypes.h but not stdint.h. */
# define U_HAVE_STDINT_H 0
#else
# define U_HAVE_STDINT_H 1
#endif
/**
* \def U_HAVE_INTTYPES_H
* Defines whether inttypes.h is available. It is a C99 standard header.
* We include inttypes.h where it is available but stdint.h is not.
* @internal
*/
#ifdef U_HAVE_INTTYPES_H
/* Use the predefined value. */
#elif U_PLATFORM == U_PF_SOLARIS
/* Solaris has inttypes.h but not stdint.h. */
# define U_HAVE_INTTYPES_H 1
#elif U_PLATFORM == U_PF_AIX && !defined(_AIX51) && defined(_POWER)
/* PPC AIX <= 4.3 has inttypes.h but not stdint.h. */
# define U_HAVE_INTTYPES_H 1
#else
/* Most platforms have both inttypes.h and stdint.h, or neither. */
# define U_HAVE_INTTYPES_H U_HAVE_STDINT_H
#endif
/**
* \def U_IOSTREAM_SOURCE
* Defines what support for C++ streams is available.
*
* If U_IOSTREAM_SOURCE is set to 199711, then &lt;iostream&gt; is available
* (the ISO/IEC C++ FDIS was published in November 1997), and then
* one should qualify streams using the std namespace in ICU header
* files.
* Starting with ICU 49, this is the only supported version.
*
* If U_IOSTREAM_SOURCE is set to 198506, then &lt;iostream.h&gt; is
* available instead (in June 1985 Stroustrup published
* "An Extensible I/O Facility for C++" at the summer USENIX conference).
* Starting with ICU 49, this version is not supported any more.
*
* If U_IOSTREAM_SOURCE is 0 (or any value less than 199711),
* then C++ streams are not available and
* support for them will be silently suppressed in ICU.
*
* @internal
*/
#ifndef U_IOSTREAM_SOURCE
#define U_IOSTREAM_SOURCE 199711
#endif
/**
* \def U_HAVE_STD_STRING
* Defines whether the standard C++ (STL) &lt;string&gt; header is available.
* @internal
*/
#ifdef U_HAVE_STD_STRING
/* Use the predefined value. */
#else
# define U_HAVE_STD_STRING 1
#endif
/*===========================================================================*/
/** @{ Compiler and environment features */
/*===========================================================================*/
/**
* \def U_GCC_MAJOR_MINOR
* Indicates whether the compiler is gcc (test for != 0),
* and if so, contains its major (times 100) and minor version numbers.
* If the compiler is not gcc, then U_GCC_MAJOR_MINOR == 0.
*
* For example, for testing for whether we have gcc, and whether it's 4.6 or higher,
* use "#if U_GCC_MAJOR_MINOR >= 406".
* @internal
*/
#ifdef __GNUC__
# define U_GCC_MAJOR_MINOR (__GNUC__ * 100 + __GNUC_MINOR__)
#else
# define U_GCC_MAJOR_MINOR 0
#endif
/**
* \def U_IS_BIG_ENDIAN
* Determines the endianness of the platform.
* @internal
*/
#ifdef U_IS_BIG_ENDIAN
/* Use the predefined value. */
#elif defined(BYTE_ORDER) && defined(BIG_ENDIAN)
# define U_IS_BIG_ENDIAN (BYTE_ORDER == BIG_ENDIAN)
#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__)
/* gcc */
# define U_IS_BIG_ENDIAN (__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__)
#elif defined(__BIG_ENDIAN__) || defined(_BIG_ENDIAN)
# define U_IS_BIG_ENDIAN 1
#elif defined(__LITTLE_ENDIAN__) || defined(_LITTLE_ENDIAN)
# define U_IS_BIG_ENDIAN 0
#elif U_PLATFORM == U_PF_OS390 || U_PLATFORM == U_PF_OS400 || defined(__s390__) || defined(__s390x__)
/* These platforms do not appear to predefine any endianness macros. */
# define U_IS_BIG_ENDIAN 1
#elif defined(_PA_RISC1_0) || defined(_PA_RISC1_1) || defined(_PA_RISC2_0)
/* HPPA do not appear to predefine any endianness macros. */
# define U_IS_BIG_ENDIAN 1
#elif defined(sparc) || defined(__sparc) || defined(__sparc__)
/* Some sparc based systems (e.g. Linux) do not predefine any endianness macros. */
# define U_IS_BIG_ENDIAN 1
#else
# define U_IS_BIG_ENDIAN 0
#endif
/**
* \def U_HAVE_PLACEMENT_NEW
* Determines whether to override placement new and delete for STL.
* @stable ICU 2.6
*/
#ifdef U_HAVE_PLACEMENT_NEW
/* Use the predefined value. */
#elif defined(__BORLANDC__)
# define U_HAVE_PLACEMENT_NEW 0
#else
# define U_HAVE_PLACEMENT_NEW 1
#endif
/**
* \def U_HAVE_DEBUG_LOCATION_NEW
* Define this to define the MFC debug version of the operator new.
*
* @stable ICU 3.4
*/
#ifdef U_HAVE_DEBUG_LOCATION_NEW
/* Use the predefined value. */
#elif defined(_MSC_VER)
# define U_HAVE_DEBUG_LOCATION_NEW 1
#else
# define U_HAVE_DEBUG_LOCATION_NEW 0
#endif
/* Compatibility with non clang compilers */
#ifndef __has_attribute
# define __has_attribute(x) 0
#endif
/**
* \def U_MALLOC_ATTR
* Attribute to mark functions as malloc-like
* @internal
*/
#if defined(__GNUC__) && __GNUC__>=3
# define U_MALLOC_ATTR __attribute__ ((__malloc__))
#else
# define U_MALLOC_ATTR
#endif
/**
* \def U_ALLOC_SIZE_ATTR
* Attribute to specify the size of the allocated buffer for malloc-like functions
* @internal
*/
#if (defined(__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))) || __has_attribute(alloc_size)
# define U_ALLOC_SIZE_ATTR(X) __attribute__ ((alloc_size(X)))
# define U_ALLOC_SIZE_ATTR2(X,Y) __attribute__ ((alloc_size(X,Y)))
#else
# define U_ALLOC_SIZE_ATTR(X)
# define U_ALLOC_SIZE_ATTR2(X,Y)
#endif
/** @} */
/*===========================================================================*/
/** @{ Character data types */
/*===========================================================================*/
/**
* U_CHARSET_FAMILY is equal to this value when the platform is an ASCII based platform.
* @stable ICU 2.0
*/
#define U_ASCII_FAMILY 0
/**
* U_CHARSET_FAMILY is equal to this value when the platform is an EBCDIC based platform.
* @stable ICU 2.0
*/
#define U_EBCDIC_FAMILY 1
/**
* \def U_CHARSET_FAMILY
*
* <p>These definitions allow to specify the encoding of text
* in the char data type as defined by the platform and the compiler.
* It is enough to determine the code point values of "invariant characters",
* which are the ones shared by all encodings that are in use
* on a given platform.</p>
*
* <p>Those "invariant characters" should be all the uppercase and lowercase
* latin letters, the digits, the space, and "basic punctuation".
* Also, '\\n', '\\r', '\\t' should be available.</p>
*
* <p>The list of "invariant characters" is:<br>
* \code
* A-Z a-z 0-9 SPACE " % &amp; ' ( ) * + , - . / : ; < = > ? _
* \endcode
* <br>
* (52 letters + 10 numbers + 20 punc/sym/space = 82 total)</p>
*
* <p>This matches the IBM Syntactic Character Set (CS 640).</p>
*
* <p>In other words, all the graphic characters in 7-bit ASCII should
* be safely accessible except the following:</p>
*
* \code
* '\' <backslash>
* '[' <left bracket>
* ']' <right bracket>
* '{' <left brace>
* '}' <right brace>
* '^' <circumflex>
* '~' <tilde>
* '!' <exclamation mark>
* '#' <number sign>
* '|' <vertical line>
* '$' <dollar sign>
* '@' <commercial at>
* '`' <grave accent>
* \endcode
* @stable ICU 2.0
*/
#ifdef U_CHARSET_FAMILY
/* Use the predefined value. */
#elif U_PLATFORM == U_PF_OS390 && (!defined(__CHARSET_LIB) || !__CHARSET_LIB)
# define U_CHARSET_FAMILY U_EBCDIC_FAMILY
#elif U_PLATFORM == U_PF_OS400 && !defined(__UTF32__)
# define U_CHARSET_FAMILY U_EBCDIC_FAMILY
#else
# define U_CHARSET_FAMILY U_ASCII_FAMILY
#endif
/**
* \def U_CHARSET_IS_UTF8
*
* Hardcode the default charset to UTF-8.
*
* If this is set to 1, then
* - ICU will assume that all non-invariant char*, StringPiece, std::string etc.
* contain UTF-8 text, regardless of what the system API uses
* - some ICU code will use fast functions like u_strFromUTF8()
* rather than the more general and more heavy-weight conversion API (ucnv.h)
* - ucnv_getDefaultName() always returns "UTF-8"
* - ucnv_setDefaultName() is disabled and will not change the default charset
* - static builds of ICU are smaller
* - more functionality is available with the UCONFIG_NO_CONVERSION build-time
* configuration option (see unicode/uconfig.h)
* - the UCONFIG_NO_CONVERSION build option in uconfig.h is more usable
*
* @stable ICU 4.2
* @see UCONFIG_NO_CONVERSION
*/
#ifdef U_CHARSET_IS_UTF8
/* Use the predefined value. */
#elif U_PLATFORM == U_PF_ANDROID || U_PLATFORM_IS_DARWIN_BASED
# define U_CHARSET_IS_UTF8 1
#else
# define U_CHARSET_IS_UTF8 0
#endif
/** @} */
/*===========================================================================*/
/** @{ Information about wchar support */
/*===========================================================================*/
/**
* \def U_HAVE_WCHAR_H
* Indicates whether <wchar.h> is available (1) or not (0). Set to 1 by default.
*
* @stable ICU 2.0
*/
#ifdef U_HAVE_WCHAR_H
/* Use the predefined value. */
#elif U_PLATFORM == U_PF_ANDROID && __ANDROID_API__ < 9
/*
* Android before Gingerbread (Android 2.3, API level 9) did not support wchar_t.
* The type and header existed, but the library functions did not work as expected.
* The size of wchar_t was 1 but L"xyz" string literals had 32-bit units anyway.
*/
# define U_HAVE_WCHAR_H 0
#else
# define U_HAVE_WCHAR_H 1
#endif
/**
* \def U_SIZEOF_WCHAR_T
* U_SIZEOF_WCHAR_T==sizeof(wchar_t)
*
* @stable ICU 2.0
*/
#ifdef U_SIZEOF_WCHAR_T
/* Use the predefined value. */
#elif (U_PLATFORM == U_PF_ANDROID && __ANDROID_API__ < 9) || U_PLATFORM == U_PF_CLASSIC_MACOS
/*
* Classic Mac OS and Mac OS X before 10.3 (Panther) did not support wchar_t or wstring.
* Newer Mac OS X has size 4.
*/
# define U_SIZEOF_WCHAR_T 1
#elif U_PLATFORM_HAS_WIN32_API || U_PLATFORM == U_PF_CYGWIN
# define U_SIZEOF_WCHAR_T 2
#elif U_PLATFORM == U_PF_AIX
/*
* AIX 6.1 information, section "Wide character data representation":
* "... the wchar_t datatype is 32-bit in the 64-bit environment and
* 16-bit in the 32-bit environment."
* and
* "All locales use Unicode for their wide character code values (process code),
* except the IBM-eucTW codeset."
*/
# ifdef __64BIT__
# define U_SIZEOF_WCHAR_T 4
# else
# define U_SIZEOF_WCHAR_T 2
# endif
#elif U_PLATFORM == U_PF_OS390
/*
* z/OS V1R11 information center, section "LP64 | ILP32":
* "In 31-bit mode, the size of long and pointers is 4 bytes and the size of wchar_t is 2 bytes.
* Under LP64, the size of long and pointer is 8 bytes and the size of wchar_t is 4 bytes."
*/
# ifdef _LP64
# define U_SIZEOF_WCHAR_T 4
# else
# define U_SIZEOF_WCHAR_T 2
# endif
#elif U_PLATFORM == U_PF_OS400
# if defined(__UTF32__)
/*
* LOCALETYPE(*LOCALEUTF) is specified.
* Wide-character strings are in UTF-32,
* narrow-character strings are in UTF-8.
*/
# define U_SIZEOF_WCHAR_T 4
# elif defined(__UCS2__)
/*
* LOCALETYPE(*LOCALEUCS2) is specified.
* Wide-character strings are in UCS-2,
* narrow-character strings are in EBCDIC.
*/
# define U_SIZEOF_WCHAR_T 2
#else
/*
* LOCALETYPE(*CLD) or LOCALETYPE(*LOCALE) is specified.
* Wide-character strings are in 16-bit EBCDIC,
* narrow-character strings are in EBCDIC.
*/
# define U_SIZEOF_WCHAR_T 2
# endif
#else
# define U_SIZEOF_WCHAR_T 4
#endif
#ifndef U_HAVE_WCSCPY
#define U_HAVE_WCSCPY U_HAVE_WCHAR_H
#endif
/** @} */
/**
* \def U_HAVE_CHAR16_T
* Defines whether the char16_t type is available for UTF-16
* and u"abc" UTF-16 string literals are supported.
* This is a new standard type and standard string literal syntax in C++0x
* but has been available in some compilers before.
* @internal
*/
#ifdef U_HAVE_CHAR16_T
/* Use the predefined value. */
#else
/*
* Notes:
* Visual Studio 10 (_MSC_VER>=1600) defines char16_t but
* does not support u"abc" string literals.
* gcc 4.4 defines the __CHAR16_TYPE__ macro to a usable type but
* does not support u"abc" string literals.
* C++11 and C11 require support for UTF-16 literals
*/
# if (defined(__cplusplus) && __cplusplus >= 201103L) || (defined(__STDC_VERSION__) && __STDC_VERSION__ >= 201112L)
# define U_HAVE_CHAR16_T 1
# else
# define U_HAVE_CHAR16_T 0
# endif
#endif
/**
* @{
* \def U_DECLARE_UTF16
* Do not use this macro because it is not defined on all platforms.
* Use the UNICODE_STRING or U_STRING_DECL macros instead.
* @internal
*/
#ifdef U_DECLARE_UTF16
/* Use the predefined value. */
#elif U_HAVE_CHAR16_T \
|| (defined(__xlC__) && defined(__IBM_UTF_LITERAL) && U_SIZEOF_WCHAR_T != 2) \
|| (defined(__HP_aCC) && __HP_aCC >= 035000) \
|| (defined(__HP_cc) && __HP_cc >= 111106)
# define U_DECLARE_UTF16(string) u ## string
#elif U_SIZEOF_WCHAR_T == 2 \
&& (U_CHARSET_FAMILY == 0 || (U_PF_OS390 <= U_PLATFORM && U_PLATFORM <= U_PF_OS400 && defined(__UCS2__)))
# define U_DECLARE_UTF16(string) L ## string
#else
/* Leave U_DECLARE_UTF16 undefined. See unistr.h. */
#endif
/** @} */
/*===========================================================================*/
/** @{ Symbol import-export control */
/*===========================================================================*/
#ifdef U_EXPORT
/* Use the predefined value. */
#elif defined(U_STATIC_IMPLEMENTATION)
# define U_EXPORT
#elif defined(__GNUC__)
# define U_EXPORT __attribute__((visibility("default")))
#elif (defined(__SUNPRO_CC) && __SUNPRO_CC >= 0x550) \
|| (defined(__SUNPRO_C) && __SUNPRO_C >= 0x550)
# define U_EXPORT __global
/*#elif defined(__HP_aCC) || defined(__HP_cc)
# define U_EXPORT __declspec(dllexport)*/
#elif defined(_MSC_VER)
# define U_EXPORT __declspec(dllexport)
#else
# define U_EXPORT
#endif
/* U_CALLCONV is releated to U_EXPORT2 */
#ifdef U_EXPORT2
/* Use the predefined value. */
#elif defined(_MSC_VER)
# define U_EXPORT2 __cdecl
#else
# define U_EXPORT2
#endif
#ifdef U_IMPORT
/* Use the predefined value. */
#elif defined(_MSC_VER)
/* Windows needs to export/import data. */
# define U_IMPORT __declspec(dllimport)
#else
# define U_IMPORT
#endif
/**
* \def U_CALLCONV
* Similar to U_CDECL_BEGIN/U_CDECL_END, this qualifier is necessary
* in callback function typedefs to make sure that the calling convention
* is compatible.
*
* This is only used for non-ICU-API functions.
* When a function is a public ICU API,
* you must use the U_CAPI and U_EXPORT2 qualifiers.
* @stable ICU 2.0
*/
#if U_PLATFORM == U_PF_OS390 && defined(__cplusplus)
# define U_CALLCONV __cdecl
#else
# define U_CALLCONV U_EXPORT2
#endif
/* @} */
#endif
project/jni/icuuc/include/unicode/plurfmt.h
-610
View File
@@ -1,610 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2007-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
* File PLURFMT.H
********************************************************************************
*/
#ifndef PLURFMT
#define PLURFMT
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: PluralFormat object
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/messagepattern.h"
#include "unicode/numfmt.h"
#include "unicode/plurrule.h"
U_NAMESPACE_BEGIN
class Hashtable;
/**
* <p>
* <code>PluralFormat</code> supports the creation of internationalized
* messages with plural inflection. It is based on <i>plural
* selection</i>, i.e. the caller specifies messages for each
* plural case that can appear in the user's language and the
* <code>PluralFormat</code> selects the appropriate message based on
* the number.
* </p>
* <h4>The Problem of Plural Forms in Internationalized Messages</h4>
* <p>
* Different languages have different ways to inflect
* plurals. Creating internationalized messages that include plural
* forms is only feasible when the framework is able to handle plural
* forms of <i>all</i> languages correctly. <code>ChoiceFormat</code>
* doesn't handle this well, because it attaches a number interval to
* each message and selects the message whose interval contains a
* given number. This can only handle a finite number of
* intervals. But in some languages, like Polish, one plural case
* applies to infinitely many intervals (e.g., the plural case applies to
* numbers ending with 2, 3, or 4 except those ending with 12, 13, or
* 14). Thus <code>ChoiceFormat</code> is not adequate.
* </p><p>
* <code>PluralFormat</code> deals with this by breaking the problem
* into two parts:
* <ul>
* <li>It uses <code>PluralRules</code> that can define more complex
* conditions for a plural case than just a single interval. These plural
* rules define both what plural cases exist in a language, and to
* which numbers these cases apply.
* <li>It provides predefined plural rules for many languages. Thus, the programmer
* need not worry about the plural cases of a language and
* does not have to define the plural cases; they can simply
* use the predefined keywords. The whole plural formatting of messages can
* be done using localized patterns from resource bundles. For predefined plural
* rules, see the CLDR <i>Language Plural Rules</i> page at
* http://unicode.org/repos/cldr-tmp/trunk/diff/supplemental/language_plural_rules.html
* </ul>
* </p>
* <h4>Usage of <code>PluralFormat</code></h4>
* <p>Note: Typically, plural formatting is done via <code>MessageFormat</code>
* with a <code>plural</code> argument type,
* rather than using a stand-alone <code>PluralFormat</code>.
* </p><p>
* This discussion assumes that you use <code>PluralFormat</code> with
* a predefined set of plural rules. You can create one using one of
* the constructors that takes a <code>locale</code> object. To
* specify the message pattern, you can either pass it to the
* constructor or set it explicitly using the
* <code>applyPattern()</code> method. The <code>format()</code>
* method takes a number object and selects the message of the
* matching plural case. This message will be returned.
* </p>
* <h5>Patterns and Their Interpretation</h5>
* <p>
* The pattern text defines the message output for each plural case of the
* specified locale. Syntax:
* <pre>
* pluralStyle = [offsetValue] (selector '{' message '}')+
* offsetValue = "offset:" number
* selector = explicitValue | keyword
* explicitValue = '=' number // adjacent, no white space in between
* keyword = [^[[:Pattern_Syntax:][:Pattern_White_Space:]]]+
* message: see {@link MessageFormat}
* </pre>
* Pattern_White_Space between syntax elements is ignored, except
* between the {curly braces} and their sub-message,
* and between the '=' and the number of an explicitValue.
*
* </p><p>
* There are 6 predefined casekeyword in CLDR/ICU - 'zero', 'one', 'two', 'few', 'many' and
* 'other'. You always have to define a message text for the default plural case
* <code>other</code> which is contained in every rule set.
* If you do not specify a message text for a particular plural case, the
* message text of the plural case <code>other</code> gets assigned to this
* plural case.
* </p><p>
* When formatting, the input number is first matched against the explicitValue clauses.
* If there is no exact-number match, then a keyword is selected by calling
* the <code>PluralRules</code> with the input number <em>minus the offset</em>.
* (The offset defaults to 0 if it is omitted from the pattern string.)
* If there is no clause with that keyword, then the "other" clauses is returned.
* </p><p>
* An unquoted pound sign (<code>#</code>) in the selected sub-message
* itself (i.e., outside of arguments nested in the sub-message)
* is replaced by the input number minus the offset.
* The number-minus-offset value is formatted using a
* <code>NumberFormat</code> for the <code>PluralFormat</code>'s locale. If you
* need special number formatting, you have to use a <code>MessageFormat</code>
* and explicitly specify a <code>NumberFormat</code> argument.
* <strong>Note:</strong> That argument is formatting without subtracting the offset!
* If you need a custom format and have a non-zero offset, then you need to pass the
* number-minus-offset value as a separate parameter.
* </p>
* For a usage example, see the {@link MessageFormat} class documentation.
*
* <h4>Defining Custom Plural Rules</h4>
* <p>If you need to use <code>PluralFormat</code> with custom rules, you can
* create a <code>PluralRules</code> object and pass it to
* <code>PluralFormat</code>'s constructor. If you also specify a locale in this
* constructor, this locale will be used to format the number in the message
* texts.
* </p><p>
* For more information about <code>PluralRules</code>, see
* {@link PluralRules}.
* </p>
*
* ported from Java
* @stable ICU 4.0
*/
class U_I18N_API PluralFormat : public Format {
public:
/**
* Creates a new cardinal-number <code>PluralFormat</code> for the default locale.
* This locale will be used to get the set of plural rules and for standard
* number formatting.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(UErrorCode& status);
/**
* Creates a new cardinal-number <code>PluralFormat</code> for a given locale.
* @param locale the <code>PluralFormat</code> will be configured with
* rules for this locale. This locale will also be used for
* standard number formatting.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(const Locale& locale, UErrorCode& status);
/**
* Creates a new <code>PluralFormat</code> for a given set of rules.
* The standard number formatting will be done using the default locale.
* @param rules defines the behavior of the <code>PluralFormat</code>
* object.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(const PluralRules& rules, UErrorCode& status);
/**
* Creates a new <code>PluralFormat</code> for a given set of rules.
* The standard number formatting will be done using the given locale.
* @param locale the default number formatting will be done using this
* locale.
* @param rules defines the behavior of the <code>PluralFormat</code>
* object.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
* <p>
* <h4>Sample code</h4>
* \snippet samples/plurfmtsample/plurfmtsample.cpp PluralFormatExample1
* \snippet samples/plurfmtsample/plurfmtsample.cpp PluralFormatExample
* <p>
*/
PluralFormat(const Locale& locale, const PluralRules& rules, UErrorCode& status);
/**
* Creates a new <code>PluralFormat</code> for the plural type.
* The standard number formatting will be done using the given locale.
* @param locale the default number formatting will be done using this
* locale.
* @param type The plural type (e.g., cardinal or ordinal).
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 50
*/
PluralFormat(const Locale& locale, UPluralType type, UErrorCode& status);
/**
* Creates a new cardinal-number <code>PluralFormat</code> for a given pattern string.
* The default locale will be used to get the set of plural rules and for
* standard number formatting.
* @param pattern the pattern for this <code>PluralFormat</code>.
* errors are returned to status if the pattern is invalid.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(const UnicodeString& pattern, UErrorCode& status);
/**
* Creates a new cardinal-number <code>PluralFormat</code> for a given pattern string and
* locale.
* The locale will be used to get the set of plural rules and for
* standard number formatting.
* @param locale the <code>PluralFormat</code> will be configured with
* rules for this locale. This locale will also be used for
* standard number formatting.
* @param pattern the pattern for this <code>PluralFormat</code>.
* errors are returned to status if the pattern is invalid.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(const Locale& locale, const UnicodeString& pattern, UErrorCode& status);
/**
* Creates a new <code>PluralFormat</code> for a given set of rules, a
* pattern and a locale.
* @param rules defines the behavior of the <code>PluralFormat</code>
* object.
* @param pattern the pattern for this <code>PluralFormat</code>.
* errors are returned to status if the pattern is invalid.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(const PluralRules& rules,
const UnicodeString& pattern,
UErrorCode& status);
/**
* Creates a new <code>PluralFormat</code> for a given set of rules, a
* pattern and a locale.
* @param locale the <code>PluralFormat</code> will be configured with
* rules for this locale. This locale will also be used for
* standard number formatting.
* @param rules defines the behavior of the <code>PluralFormat</code>
* object.
* @param pattern the pattern for this <code>PluralFormat</code>.
* errors are returned to status if the pattern is invalid.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
PluralFormat(const Locale& locale,
const PluralRules& rules,
const UnicodeString& pattern,
UErrorCode& status);
/**
* Creates a new <code>PluralFormat</code> for a plural type, a
* pattern and a locale.
* @param locale the <code>PluralFormat</code> will be configured with
* rules for this locale. This locale will also be used for
* standard number formatting.
* @param type The plural type (e.g., cardinal or ordinal).
* @param pattern the pattern for this <code>PluralFormat</code>.
* errors are returned to status if the pattern is invalid.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 50
*/
PluralFormat(const Locale& locale,
UPluralType type,
const UnicodeString& pattern,
UErrorCode& status);
/**
* copy constructor.
* @stable ICU 4.0
*/
PluralFormat(const PluralFormat& other);
/**
* Destructor.
* @stable ICU 4.0
*/
virtual ~PluralFormat();
/**
* Sets the pattern used by this plural format.
* The method parses the pattern and creates a map of format strings
* for the plural rules.
* Patterns and their interpretation are specified in the class description.
*
* @param pattern the pattern for this plural format
* errors are returned to status if the pattern is invalid.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
void applyPattern(const UnicodeString& pattern, UErrorCode& status);
using Format::format;
/**
* Formats a plural message for a given number.
*
* @param number a number for which the plural message should be formatted
* for. If no pattern has been applied to this
* <code>PluralFormat</code> object yet, the formatted number
* will be returned.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return the string containing the formatted plural message.
* @stable ICU 4.0
*/
UnicodeString format(int32_t number, UErrorCode& status) const;
/**
* Formats a plural message for a given number.
*
* @param number a number for which the plural message should be formatted
* for. If no pattern has been applied to this
* PluralFormat object yet, the formatted number
* will be returned.
* @param status output param set to success or failure code on exit, which
* must not indicate a failure before the function call.
* @return the string containing the formatted plural message.
* @stable ICU 4.0
*/
UnicodeString format(double number, UErrorCode& status) const;
/**
* Formats a plural message for a given number.
*
* @param number a number for which the plural message should be formatted
* for. If no pattern has been applied to this
* <code>PluralFormat</code> object yet, the formatted number
* will be returned.
* @param appendTo output parameter to receive result.
* result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return the string containing the formatted plural message.
* @stable ICU 4.0
*/
UnicodeString& format(int32_t number,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Formats a plural message for a given number.
*
* @param number a number for which the plural message should be formatted
* for. If no pattern has been applied to this
* PluralFormat object yet, the formatted number
* will be returned.
* @param appendTo output parameter to receive result.
* result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return the string containing the formatted plural message.
* @stable ICU 4.0
*/
UnicodeString& format(double number,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const;
#ifndef U_HIDE_DEPRECATED_API
/**
* Sets the locale used by this <code>PluraFormat</code> object.
* Note: Calling this method resets this <code>PluraFormat</code> object,
* i.e., a pattern that was applied previously will be removed,
* and the NumberFormat is set to the default number format for
* the locale. The resulting format behaves the same as one
* constructed from {@link #PluralFormat(const Locale& locale, UPluralType type, UErrorCode& status)}
* with UPLURAL_TYPE_CARDINAL.
* @param locale the <code>locale</code> to use to configure the formatter.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @deprecated ICU 50 This method clears the pattern and might create
* a different kind of PluralRules instance;
* use one of the constructors to create a new instance instead.
*/
void setLocale(const Locale& locale, UErrorCode& status);
#endif /* U_HIDE_DEPRECATED_API */
/**
* Sets the number format used by this formatter. You only need to
* call this if you want a different number format than the default
* formatter for the locale.
* @param format the number format to use.
* @param status output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @stable ICU 4.0
*/
void setNumberFormat(const NumberFormat* format, UErrorCode& status);
/**
* Assignment operator
*
* @param other the PluralFormat object to copy from.
* @stable ICU 4.0
*/
PluralFormat& operator=(const PluralFormat& other);
/**
* Return true if another object is semantically equal to this one.
*
* @param other the PluralFormat object to be compared with.
* @return true if other is semantically equal to this.
* @stable ICU 4.0
*/
virtual UBool operator==(const Format& other) const;
/**
* Return true if another object is semantically unequal to this one.
*
* @param other the PluralFormat object to be compared with.
* @return true if other is semantically unequal to this.
* @stable ICU 4.0
*/
virtual UBool operator!=(const Format& other) const;
/**
* Clones this Format object polymorphically. The caller owns the
* result and should delete it when done.
* @stable ICU 4.0
*/
virtual Format* clone(void) const;
/**
* Formats a plural message for a number taken from a Formattable object.
*
* @param obj The object containing a number for which the
* plural message should be formatted.
* The object must be of a numeric type.
* @param appendTo output parameter to receive result.
* Result is appended to existing contents.
* @param pos On input: an alignment field, if desired.
* On output: the offsets of the alignment field.
* @param status output param filled with success/failure status.
* @return Reference to 'appendTo' parameter.
* @stable ICU 4.0
*/
UnicodeString& format(const Formattable& obj,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Returns the pattern from applyPattern() or constructor().
*
* @param appendTo output parameter to receive result.
* Result is appended to existing contents.
* @return the UnicodeString with inserted pattern.
* @stable ICU 4.0
*/
UnicodeString& toPattern(UnicodeString& appendTo);
/**
* This method is not yet supported by <code>PluralFormat</code>.
* <P>
* Before calling, set parse_pos.index to the offset you want to start
* parsing at in the source. After calling, parse_pos.index is the end of
* the text you parsed. If error occurs, index is unchanged.
* <P>
* When parsing, leading whitespace is discarded (with a successful parse),
* while trailing whitespace is left as is.
* <P>
* See Format::parseObject() for more.
*
* @param source The string to be parsed into an object.
* @param result Formattable to be set to the parse result.
* If parse fails, return contents are undefined.
* @param parse_pos The position to start parsing at. Upon return
* this param is set to the position after the
* last character successfully parsed. If the
* source is not parsed successfully, this param
* will remain unchanged.
* @stable ICU 4.0
*/
virtual void parseObject(const UnicodeString& source,
Formattable& result,
ParsePosition& parse_pos) const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 4.0
*
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 4.0
*/
virtual UClassID getDynamicClassID() const;
#if (defined(__xlC__) && (__xlC__ < 0x0C00)) || (U_PLATFORM == U_PF_OS390) || (U_PLATFORM ==U_PF_OS400)
// Work around a compiler bug on xlC 11.1 on AIX 7.1 that would
// prevent PluralSelectorAdapter from implementing private PluralSelector.
// xlC error message:
// 1540-0300 (S) The "private" member "class icu_49::PluralFormat::PluralSelector" cannot be accessed.
public:
#else
private:
#endif
/**
* @internal
*/
class U_I18N_API PluralSelector : public UMemory {
public:
virtual ~PluralSelector();
/**
* Given a number, returns the appropriate PluralFormat keyword.
*
* @param context worker object for the selector.
* @param number The number to be plural-formatted.
* @param ec Error code.
* @return The selected PluralFormat keyword.
* @internal
*/
virtual UnicodeString select(void *context, double number, UErrorCode& ec) const = 0;
};
/**
* @internal
*/
class U_I18N_API PluralSelectorAdapter : public PluralSelector {
public:
PluralSelectorAdapter() : pluralRules(NULL) {
}
virtual ~PluralSelectorAdapter();
virtual UnicodeString select(void *context, double number, UErrorCode& /*ec*/) const; /**< @internal */
void reset();
PluralRules* pluralRules;
};
#if defined(__xlC__)
// End of xlC bug workaround, keep remaining definitions private.
private:
#endif
Locale locale;
MessagePattern msgPattern;
NumberFormat* numberFormat;
double offset;
PluralSelectorAdapter pluralRulesWrapper;
PluralFormat(); // default constructor not implemented
void init(const PluralRules* rules, UPluralType type, UErrorCode& status);
/**
* Copies dynamically allocated values (pointer fields).
* Others are copied using their copy constructors and assignment operators.
*/
void copyObjects(const PluralFormat& other);
UnicodeString& format(const Formattable& numberObject, double number,
UnicodeString& appendTo,
FieldPosition& pos,
UErrorCode& status) const; /**< @internal */
/**
* Finds the PluralFormat sub-message for the given number, or the "other" sub-message.
* @param pattern A MessagePattern.
* @param partIndex the index of the first PluralFormat argument style part.
* @param selector the PluralSelector for mapping the number (minus offset) to a keyword.
* @param context worker object for the selector.
* @param number a number to be matched to one of the PluralFormat argument's explicit values,
* or mapped via the PluralSelector.
* @param ec ICU error code.
* @return the sub-message start part index.
*/
static int32_t findSubMessage(
const MessagePattern& pattern, int32_t partIndex,
const PluralSelector& selector, void *context, double number, UErrorCode& ec); /**< @internal */
friend class MessageFormat;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _PLURFMT
//eof
project/jni/icuuc/include/unicode/plurrule.h
-481
View File
@@ -1,481 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2008-2013, International Business Machines Corporation and
* others. All Rights Reserved.
*******************************************************************************
*
*
* File PLURRULE.H
*
* Modification History:*
* Date Name Description
*
********************************************************************************
*/
#ifndef PLURRULE
#define PLURRULE
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: PluralRules object
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/format.h"
#include "unicode/upluralrules.h"
/**
* Value returned by PluralRules::getUniqueKeywordValue() when there is no
* unique value to return.
* @stable ICU 4.8
*/
#define UPLRULES_NO_UNIQUE_VALUE ((double)-0.00123456777)
U_NAMESPACE_BEGIN
class Hashtable;
class FixedDecimal;
class RuleChain;
class PluralRuleParser;
class PluralKeywordEnumeration;
class AndConstraint;
/**
* Defines rules for mapping non-negative numeric values onto a small set of
* keywords. Rules are constructed from a text description, consisting
* of a series of keywords and conditions. The {@link #select} method
* examines each condition in order and returns the keyword for the
* first condition that matches the number. If none match,
* default rule(other) is returned.
*
* For more information, details, and tips for writing rules, see the
* LDML spec, C.11 Language Plural Rules:
* http://www.unicode.org/draft/reports/tr35/tr35.html#Language_Plural_Rules
*
* Examples:<pre>
* "one: n is 1; few: n in 2..4"</pre>
* This defines two rules, for 'one' and 'few'. The condition for
* 'one' is "n is 1" which means that the number must be equal to
* 1 for this condition to pass. The condition for 'few' is
* "n in 2..4" which means that the number must be between 2 and
* 4 inclusive for this condition to pass. All other numbers
* are assigned the keyword "other" by the default rule.
* </p><pre>
* "zero: n is 0; one: n is 1; zero: n mod 100 in 1..19"</pre>
* This illustrates that the same keyword can be defined multiple times.
* Each rule is examined in order, and the first keyword whose condition
* passes is the one returned. Also notes that a modulus is applied
* to n in the last rule. Thus its condition holds for 119, 219, 319...
* </p><pre>
* "one: n is 1; few: n mod 10 in 2..4 and n mod 100 not in 12..14"</pre>
* This illustrates conjunction and negation. The condition for 'few'
* has two parts, both of which must be met: "n mod 10 in 2..4" and
* "n mod 100 not in 12..14". The first part applies a modulus to n
* before the test as in the previous example. The second part applies
* a different modulus and also uses negation, thus it matches all
* numbers _not_ in 12, 13, 14, 112, 113, 114, 212, 213, 214...
* </p>
* <p>
* Syntax:<pre>
* \code
* rules = rule (';' rule)*
* rule = keyword ':' condition
* keyword = <identifier>
* condition = and_condition ('or' and_condition)*
* and_condition = relation ('and' relation)*
* relation = is_relation | in_relation | within_relation | 'n' <EOL>
* is_relation = expr 'is' ('not')? value
* in_relation = expr ('not')? 'in' range_list
* within_relation = expr ('not')? 'within' range
* expr = ('n' | 'i' | 'f' | 'v' | 'j') ('mod' value)?
* range_list = (range | value) (',' range_list)*
* value = digit+ ('.' digit+)?
* digit = 0|1|2|3|4|5|6|7|8|9
* range = value'..'value
* \endcode
* </pre></p>
* <p>
* <p>
* The i, f, and v values are defined as follows:
* </p>
* <ul>
* <li>i to be the integer digits.</li>
* <li>f to be the visible fractional digits, as an integer.</li>
* <li>v to be the number of visible fraction digits.</li>
* <li>j is defined to only match integers. That is j is 3 fails if v != 0 (eg for 3.1 or 3.0).</li>
* </ul>
* <p>
* Examples are in the following table:
* </p>
* <table border='1' style="border-collapse:collapse">
* <tbody>
* <tr>
* <th>n</th>
* <th>i</th>
* <th>f</th>
* <th>v</th>
* </tr>
* <tr>
* <td>1.0</td>
* <td>1</td>
* <td align="right">0</td>
* <td>1</td>
* </tr>
* <tr>
* <td>1.00</td>
* <td>1</td>
* <td align="right">0</td>
* <td>2</td>
* </tr>
* <tr>
* <td>1.3</td>
* <td>1</td>
* <td align="right">3</td>
* <td>1</td>
* </tr>
* <tr>
* <td>1.03</td>
* <td>1</td>
* <td align="right">3</td>
* <td>2</td>
* </tr>
* <tr>
* <td>1.23</td>
* <td>1</td>
* <td align="right">23</td>
* <td>2</td>
* </tr>
* </tbody>
* </table>
* <p>
* The difference between 'in' and 'within' is that 'in' only includes integers in the specified range, while 'within'
* includes all values. Using 'within' with a range_list consisting entirely of values is the same as using 'in' (it's
* not an error).
* </p>
* An "identifier" is a sequence of characters that do not have the
* Unicode Pattern_Syntax or Pattern_White_Space properties.
* <p>
* The difference between 'in' and 'within' is that 'in' only includes
* integers in the specified range, while 'within' includes all values.
* Using 'within' with a range_list consisting entirely of values is the
* same as using 'in' (it's not an error).
*</p>
* <p>
* Keywords
* could be defined by users or from ICU locale data. There are 6
* predefined values in ICU - 'zero', 'one', 'two', 'few', 'many' and
* 'other'. Callers need to check the value of keyword returned by
* {@link #select} method.
* </p>
*
* Examples:<pre>
* UnicodeString keyword = pl->select(number);
* if (keyword== UnicodeString("one") {
* ...
* }
* else if ( ... )
* </pre>
* <strong>Note:</strong><br>
* <p>
* ICU defines plural rules for many locales based on CLDR <i>Language Plural Rules</i>.
* For these predefined rules, see CLDR page at
* http://unicode.org/repos/cldr-tmp/trunk/diff/supplemental/language_plural_rules.html
* </p>
*/
class U_I18N_API PluralRules : public UObject {
public:
/**
* Constructor.
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
*
* @stable ICU 4.0
*/
PluralRules(UErrorCode& status);
/**
* Copy constructor.
* @stable ICU 4.0
*/
PluralRules(const PluralRules& other);
/**
* Destructor.
* @stable ICU 4.0
*/
virtual ~PluralRules();
/**
* Clone
* @stable ICU 4.0
*/
PluralRules* clone() const;
/**
* Assignment operator.
* @stable ICU 4.0
*/
PluralRules& operator=(const PluralRules&);
/**
* Creates a PluralRules from a description if it is parsable, otherwise
* returns NULL.
*
* @param description rule description
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return new PluralRules pointer. NULL if there is an error.
* @stable ICU 4.0
*/
static PluralRules* U_EXPORT2 createRules(const UnicodeString& description,
UErrorCode& status);
/**
* The default rules that accept any number.
*
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return new PluralRules pointer. NULL if there is an error.
* @stable ICU 4.0
*/
static PluralRules* U_EXPORT2 createDefaultRules(UErrorCode& status);
/**
* Provides access to the predefined cardinal-number <code>PluralRules</code> for a given
* locale.
* Same as forLocale(locale, UPLURAL_TYPE_CARDINAL, status).
*
* @param locale The locale for which a <code>PluralRules</code> object is
* returned.
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return The predefined <code>PluralRules</code> object pointer for
* this locale. If there's no predefined rules for this locale,
* the rules for the closest parent in the locale hierarchy
* that has one will be returned. The final fallback always
* returns the default 'other' rules.
* @stable ICU 4.0
*/
static PluralRules* U_EXPORT2 forLocale(const Locale& locale, UErrorCode& status);
/**
* Provides access to the predefined <code>PluralRules</code> for a given
* locale and the plural type.
*
* @param locale The locale for which a <code>PluralRules</code> object is
* returned.
* @param type The plural type (e.g., cardinal or ordinal).
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return The predefined <code>PluralRules</code> object pointer for
* this locale. If there's no predefined rules for this locale,
* the rules for the closest parent in the locale hierarchy
* that has one will be returned. The final fallback always
* returns the default 'other' rules.
* @stable ICU 50
*/
static PluralRules* U_EXPORT2 forLocale(const Locale& locale, UPluralType type, UErrorCode& status);
#ifndef U_HIDE_INTERNAL_API
/**
* Return a StringEnumeration over the locales for which there is plurals data.
* @return a StringEnumeration over the locales available.
* @internal
*/
static StringEnumeration* U_EXPORT2 getAvailableLocales(UErrorCode &status);
/**
* Returns whether or not there are overrides.
* @param locale the locale to check.
* @return
* @internal
*/
static UBool hasOverride(const Locale &locale);
#endif /* U_HIDE_INTERNAL_API */
/**
* Given a number, returns the keyword of the first rule that applies to
* the number. This function can be used with isKeyword* functions to
* determine the keyword for default plural rules.
*
* @param number The number for which the rule has to be determined.
* @return The keyword of the selected rule.
* @stable ICU 4.0
*/
UnicodeString select(int32_t number) const;
/**
* Given a number, returns the keyword of the first rule that applies to
* the number. This function can be used with isKeyword* functions to
* determine the keyword for default plural rules.
*
* @param number The number for which the rule has to be determined.
* @return The keyword of the selected rule.
* @stable ICU 4.0
*/
UnicodeString select(double number) const;
#ifndef U_HIDE_INTERNAL_API
/**
* @internal
*/
UnicodeString select(const FixedDecimal &number) const;
#endif /* U_HIDE_INTERNAL_API */
/**
* Returns a list of all rule keywords used in this <code>PluralRules</code>
* object. The rule 'other' is always present by default.
*
* @param status Output param set to success/failure code on exit, which
* must not indicate a failure before the function call.
* @return StringEnumeration with the keywords.
* The caller must delete the object.
* @stable ICU 4.0
*/
StringEnumeration* getKeywords(UErrorCode& status) const;
/**
* Returns a unique value for this keyword if it exists, else the constant
* UPLRULES_NO_UNIQUE_VALUE.
*
* @param keyword The keyword.
* @return The unique value that generates the keyword, or
* UPLRULES_NO_UNIQUE_VALUE if the keyword is undefined or there is no
* unique value that generates this keyword.
* @stable ICU 4.8
*/
double getUniqueKeywordValue(const UnicodeString& keyword);
/**
* Returns all the values for which select() would return the keyword. If
* the keyword is unknown, returns no values, but this is not an error. If
* the number of values is unlimited, returns no values and -1 as the
* count.
*
* The number of returned values is typically small.
*
* @param keyword The keyword.
* @param dest Array into which to put the returned values. May
* be NULL if destCapacity is 0.
* @param destCapacity The capacity of the array, must be at least 0.
* @param status The error code.
* @return The count of values available, or -1. This count
* can be larger than destCapacity, but no more than
* destCapacity values will be written.
* @stable ICU 4.8
*/
int32_t getAllKeywordValues(const UnicodeString &keyword,
double *dest, int32_t destCapacity,
UErrorCode& status);
/**
* Returns sample values for which select() would return the keyword. If
* the keyword is unknown, returns no values, but this is not an error.
*
* The number of returned values is typically small.
*
* @param keyword The keyword.
* @param dest Array into which to put the returned values. May
* be NULL if destCapacity is 0.
* @param destCapacity The capacity of the array, must be at least 0.
* @param status The error code.
* @return The count of values written.
* If more than destCapacity samples are available, then
* only destCapacity are written, and destCapacity is returned as the count,
* rather than setting a U_BUFFER_OVERFLOW_ERROR.
* (The actual number of keyword values could be unlimited.)
* @stable ICU 4.8
*/
int32_t getSamples(const UnicodeString &keyword,
double *dest, int32_t destCapacity,
UErrorCode& status);
/**
* Returns TRUE if the given keyword is defined in this
* <code>PluralRules</code> object.
*
* @param keyword the input keyword.
* @return TRUE if the input keyword is defined.
* Otherwise, return FALSE.
* @stable ICU 4.0
*/
UBool isKeyword(const UnicodeString& keyword) const;
/**
* Returns keyword for default plural form.
*
* @return keyword for default plural form.
* @stable ICU 4.0
*/
UnicodeString getKeywordOther() const;
#ifndef U_HIDE_INTERNAL_API
/**
*
* @internal
*/
UnicodeString getRules() const;
#endif /* U_HIDE_INTERNAL_API */
/**
* Compares the equality of two PluralRules objects.
*
* @param other The other PluralRules object to be compared with.
* @return True if the given PluralRules is the same as this
* PluralRules; false otherwise.
* @stable ICU 4.0
*/
virtual UBool operator==(const PluralRules& other) const;
/**
* Compares the inequality of two PluralRules objects.
*
* @param other The PluralRules object to be compared with.
* @return True if the given PluralRules is not the same as this
* PluralRules; false otherwise.
* @stable ICU 4.0
*/
UBool operator!=(const PluralRules& other) const {return !operator==(other);}
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 4.0
*
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 4.0
*/
virtual UClassID getDynamicClassID() const;
private:
RuleChain *mRules;
PluralRules(); // default constructor not implemented
void parseDescription(const UnicodeString& ruleData, UErrorCode &status);
int32_t getNumberValue(const UnicodeString& token) const;
UnicodeString getRuleFromResource(const Locale& locale, UPluralType type, UErrorCode& status);
RuleChain *rulesForKeyword(const UnicodeString &keyword) const;
friend class PluralRuleParser;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // _PLURRULE
//eof
project/jni/icuuc/include/unicode/ptypes.h
-126
View File
@@ -1,126 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 1997-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* FILE NAME : ptypes.h
*
* Date Name Description
* 05/13/98 nos Creation (content moved here from ptypes.h).
* 03/02/99 stephen Added AS400 support.
* 03/30/99 stephen Added Linux support.
* 04/13/99 stephen Reworked for autoconf.
* 09/18/08 srl Moved basic types back to ptypes.h from platform.h
******************************************************************************
*/
/**
* \file
* \brief C API: Definitions of integer types of various widths
*/
#ifndef _PTYPES_H
#define _PTYPES_H
/**
* \def __STDC_LIMIT_MACROS
* According to the Linux stdint.h, the ISO C99 standard specifies that in C++ implementations
* macros like INT32_MIN and UINTPTR_MAX should only be defined if explicitly requested.
* We need to define __STDC_LIMIT_MACROS before including stdint.h in C++ code
* that uses such limit macros.
* @internal
*/
#ifndef __STDC_LIMIT_MACROS
#define __STDC_LIMIT_MACROS
#endif
/* NULL, size_t, wchar_t */
#include <stddef.h>
/*
* If all compilers provided all of the C99 headers and types,
* we would just unconditionally #include <stdint.h> here
* and not need any of the stuff after including platform.h.
*/
/* Find out if we have stdint.h etc. */
#include "unicode/platform.h"
/*===========================================================================*/
/* Generic data types */
/*===========================================================================*/
/* If your platform does not have the <stdint.h> header, you may
need to edit the typedefs in the #else section below.
Use #if...#else...#endif with predefined compiler macros if possible. */
#if U_HAVE_STDINT_H
/*
* We mostly need <stdint.h> (which defines the standard integer types) but not <inttypes.h>.
* <inttypes.h> includes <stdint.h> and adds the printf/scanf helpers PRId32, SCNx16 etc.
* which we almost never use, plus stuff like imaxabs() which we never use.
*/
#include <stdint.h>
#if U_PLATFORM == U_PF_OS390
/* The features header is needed to get (u)int64_t sometimes. */
#include <features.h>
/* z/OS has <stdint.h>, but some versions are missing uint8_t (APAR PK62248). */
#if !defined(__uint8_t)
#define __uint8_t 1
typedef unsigned char uint8_t;
#endif
#endif /* U_PLATFORM == U_PF_OS390 */
#elif U_HAVE_INTTYPES_H
# include <inttypes.h>
#else /* neither U_HAVE_STDINT_H nor U_HAVE_INTTYPES_H */
#if ! U_HAVE_INT8_T
typedef signed char int8_t;
#endif
#if ! U_HAVE_UINT8_T
typedef unsigned char uint8_t;
#endif
#if ! U_HAVE_INT16_T
typedef signed short int16_t;
#endif
#if ! U_HAVE_UINT16_T
typedef unsigned short uint16_t;
#endif
#if ! U_HAVE_INT32_T
typedef signed int int32_t;
#endif
#if ! U_HAVE_UINT32_T
typedef unsigned int uint32_t;
#endif
#if ! U_HAVE_INT64_T
#ifdef _MSC_VER
typedef signed __int64 int64_t;
#else
typedef signed long long int64_t;
#endif
#endif
#if ! U_HAVE_UINT64_T
#ifdef _MSC_VER
typedef unsigned __int64 uint64_t;
#else
typedef unsigned long long uint64_t;
#endif
#endif
#endif /* U_HAVE_STDINT_H / U_HAVE_INTTYPES_H */
#endif /* _PTYPES_H */
project/jni/icuuc/include/unicode/putil.h
-164
View File
@@ -1,164 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 1997-2011, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* FILE NAME : putil.h
*
* Date Name Description
* 05/14/98 nos Creation (content moved here from utypes.h).
* 06/17/99 erm Added IEEE_754
* 07/22/98 stephen Added IEEEremainder, max, min, trunc
* 08/13/98 stephen Added isNegativeInfinity, isPositiveInfinity
* 08/24/98 stephen Added longBitsFromDouble
* 03/02/99 stephen Removed openFile(). Added AS400 support.
* 04/15/99 stephen Converted to C
* 11/15/99 helena Integrated S/390 changes for IEEE support.
* 01/11/00 helena Added u_getVersion.
******************************************************************************
*/
#ifndef PUTIL_H
#define PUTIL_H
#include "unicode/utypes.h"
/**
* \file
* \brief C API: Platform Utilities
*/
/*==========================================================================*/
/* Platform utilities */
/*==========================================================================*/
/**
* Platform utilities isolates the platform dependencies of the
* libarary. For each platform which this code is ported to, these
* functions may have to be re-implemented.
*/
/**
* Return the ICU data directory.
* The data directory is where common format ICU data files (.dat files)
* are loaded from. Note that normal use of the built-in ICU
* facilities does not require loading of an external data file;
* unless you are adding custom data to ICU, the data directory
* does not need to be set.
*
* The data directory is determined as follows:
* If u_setDataDirectory() has been called, that is it, otherwise
* if the ICU_DATA environment variable is set, use that, otherwise
* If a data directory was specifed at ICU build time
* <code>
* \code
* #define ICU_DATA_DIR "path"
* \endcode
* </code> use that,
* otherwise no data directory is available.
*
* @return the data directory, or an empty string ("") if no data directory has
* been specified.
*
* @stable ICU 2.0
*/
U_STABLE const char* U_EXPORT2 u_getDataDirectory(void);
/**
* Set the ICU data directory.
* The data directory is where common format ICU data files (.dat files)
* are loaded from. Note that normal use of the built-in ICU
* facilities does not require loading of an external data file;
* unless you are adding custom data to ICU, the data directory
* does not need to be set.
*
* This function should be called at most once in a process, before the
* first ICU operation (e.g., u_init()) that will require the loading of an
* ICU data file.
* This function is not thread-safe. Use it before calling ICU APIs from
* multiple threads.
*
* @param directory The directory to be set.
*
* @see u_init
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2 u_setDataDirectory(const char *directory);
/**
* @{
* Filesystem file and path separator characters.
* Example: '/' and ':' on Unix, '\\' and ';' on Windows.
* @stable ICU 2.0
*/
#if U_PLATFORM == U_PF_CLASSIC_MACOS
# define U_FILE_SEP_CHAR ':'
# define U_FILE_ALT_SEP_CHAR ':'
# define U_PATH_SEP_CHAR ';'
# define U_FILE_SEP_STRING ":"
# define U_FILE_ALT_SEP_STRING ":"
# define U_PATH_SEP_STRING ";"
#elif U_PLATFORM_USES_ONLY_WIN32_API
# define U_FILE_SEP_CHAR '\\'
# define U_FILE_ALT_SEP_CHAR '/'
# define U_PATH_SEP_CHAR ';'
# define U_FILE_SEP_STRING "\\"
# define U_FILE_ALT_SEP_STRING "/"
# define U_PATH_SEP_STRING ";"
#else
# define U_FILE_SEP_CHAR '/'
# define U_FILE_ALT_SEP_CHAR '/'
# define U_PATH_SEP_CHAR ':'
# define U_FILE_SEP_STRING "/"
# define U_FILE_ALT_SEP_STRING "/"
# define U_PATH_SEP_STRING ":"
#endif
/** @} */
/**
* Convert char characters to UChar characters.
* This utility function is useful only for "invariant characters"
* that are encoded in the platform default encoding.
* They are a small, constant subset of the encoding and include
* just the latin letters, digits, and some punctuation.
* For details, see U_CHARSET_FAMILY.
*
* @param cs Input string, points to <code>length</code>
* character bytes from a subset of the platform encoding.
* @param us Output string, points to memory for <code>length</code>
* Unicode characters.
* @param length The number of characters to convert; this may
* include the terminating <code>NUL</code>.
*
* @see U_CHARSET_FAMILY
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
u_charsToUChars(const char *cs, UChar *us, int32_t length);
/**
* Convert UChar characters to char characters.
* This utility function is useful only for "invariant characters"
* that can be encoded in the platform default encoding.
* They are a small, constant subset of the encoding and include
* just the latin letters, digits, and some punctuation.
* For details, see U_CHARSET_FAMILY.
*
* @param us Input string, points to <code>length</code>
* Unicode characters that can be encoded with the
* codepage-invariant subset of the platform encoding.
* @param cs Output string, points to memory for <code>length</code>
* character bytes.
* @param length The number of characters to convert; this may
* include the terminating <code>NUL</code>.
*
* @see U_CHARSET_FAMILY
* @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
u_UCharsToChars(const UChar *us, char *cs, int32_t length);
#endif
project/jni/icuuc/include/unicode/rbbi.h
-782
View File
@@ -1,782 +0,0 @@
/*
***************************************************************************
* Copyright (C) 1999-2013 International Business Machines Corporation *
* and others. All rights reserved. *
***************************************************************************
**********************************************************************
* Date Name Description
* 10/22/99 alan Creation.
* 11/11/99 rgillam Complete port from Java.
**********************************************************************
*/
#ifndef RBBI_H
#define RBBI_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Rule Based Break Iterator
*/
#if !UCONFIG_NO_BREAK_ITERATION
#include "unicode/brkiter.h"
#include "unicode/udata.h"
#include "unicode/parseerr.h"
#include "unicode/schriter.h"
#include "unicode/uchriter.h"
struct UTrie;
U_NAMESPACE_BEGIN
/** @internal */
struct RBBIDataHeader;
class RuleBasedBreakIteratorTables;
class BreakIterator;
class RBBIDataWrapper;
class UStack;
class LanguageBreakEngine;
class UnhandledEngine;
struct RBBIStateTable;
/**
*
* A subclass of BreakIterator whose behavior is specified using a list of rules.
* <p>Instances of this class are most commonly created by the factory methods of
* BreakIterator::createWordInstance(), BreakIterator::createLineInstance(), etc.,
* and then used via the abstract API in class BreakIterator</p>
*
* <p>See the ICU User Guide for information on Break Iterator Rules.</p>
*
* <p>This class is not intended to be subclassed. (Class DictionaryBasedBreakIterator
* is a subclass, but that relationship is effectively internal to the ICU
* implementation. The subclassing interface to RulesBasedBreakIterator is
* not part of the ICU API, and may not remain stable.</p>
*
*/
class U_COMMON_API RuleBasedBreakIterator : public BreakIterator {
protected:
/**
* The UText through which this BreakIterator accesses the text
* @internal
*/
UText *fText;
/**
* A character iterator that refers to the same text as the UText, above.
* Only included for compatibility with old API, which was based on CharacterIterators.
* Value may be adopted from outside, or one of fSCharIter or fDCharIter, below.
*/
CharacterIterator *fCharIter;
/**
* When the input text is provided by a UnicodeString, this will point to
* a characterIterator that wraps that data. Needed only for the
* implementation of getText(), a backwards compatibility issue.
*/
StringCharacterIterator *fSCharIter;
/**
* When the input text is provided by a UText, this
* dummy CharacterIterator over an empty string will
* be returned from getText()
*/
UCharCharacterIterator *fDCharIter;
/**
* The rule data for this BreakIterator instance
* @internal
*/
RBBIDataWrapper *fData;
/** Index of the Rule {tag} values for the most recent match.
* @internal
*/
int32_t fLastRuleStatusIndex;
/**
* Rule tag value valid flag.
* Some iterator operations don't intrinsically set the correct tag value.
* This flag lets us lazily compute the value if we are ever asked for it.
* @internal
*/
UBool fLastStatusIndexValid;
/**
* Counter for the number of characters encountered with the "dictionary"
* flag set.
* @internal
*/
uint32_t fDictionaryCharCount;
/**
* When a range of characters is divided up using the dictionary, the break
* positions that are discovered are stored here, preventing us from having
* to use either the dictionary or the state table again until the iterator
* leaves this range of text. Has the most impact for line breaking.
* @internal
*/
int32_t* fCachedBreakPositions;
/**
* The number of elements in fCachedBreakPositions
* @internal
*/
int32_t fNumCachedBreakPositions;
/**
* if fCachedBreakPositions is not null, this indicates which item in the
* cache the current iteration position refers to
* @internal
*/
int32_t fPositionInCache;
/**
*
* If present, UStack of LanguageBreakEngine objects that might handle
* dictionary characters. Searched from top to bottom to find an object to
* handle a given character.
* @internal
*/
UStack *fLanguageBreakEngines;
/**
*
* If present, the special LanguageBreakEngine used for handling
* characters that are in the dictionary set, but not handled by any
* LangugageBreakEngine.
* @internal
*/
UnhandledEngine *fUnhandledBreakEngine;
/**
*
* The type of the break iterator, or -1 if it has not been set.
* @internal
*/
int32_t fBreakType;
protected:
//=======================================================================
// constructors
//=======================================================================
#ifndef U_HIDE_INTERNAL_API
/**
* Constant to be used in the constructor
* RuleBasedBreakIterator(RBBIDataHeader*, EDontAdopt, UErrorCode &);
* which does not adopt the memory indicated by the RBBIDataHeader*
* parameter.
*
* @internal
*/
enum EDontAdopt {
kDontAdopt
};
/**
* Constructor from a flattened set of RBBI data in malloced memory.
* RulesBasedBreakIterators built from a custom set of rules
* are created via this constructor; the rules are compiled
* into memory, then the break iterator is constructed here.
*
* The break iterator adopts the memory, and will
* free it when done.
* @internal
*/
RuleBasedBreakIterator(RBBIDataHeader* data, UErrorCode &status);
/**
* Constructor from a flattened set of RBBI data in memory which need not
* be malloced (e.g. it may be a memory-mapped file, etc.).
*
* This version does not adopt the memory, and does not
* free it when done.
* @internal
*/
RuleBasedBreakIterator(const RBBIDataHeader* data, enum EDontAdopt dontAdopt, UErrorCode &status);
#endif /* U_HIDE_INTERNAL_API */
friend class RBBIRuleBuilder;
/** @internal */
friend class BreakIterator;
public:
/** Default constructor. Creates an empty shell of an iterator, with no
* rules or text to iterate over. Object can subsequently be assigned to.
* @stable ICU 2.2
*/
RuleBasedBreakIterator();
/**
* Copy constructor. Will produce a break iterator with the same behavior,
* and which iterates over the same text, as the one passed in.
* @param that The RuleBasedBreakIterator passed to be copied
* @stable ICU 2.0
*/
RuleBasedBreakIterator(const RuleBasedBreakIterator& that);
/**
* Construct a RuleBasedBreakIterator from a set of rules supplied as a string.
* @param rules The break rules to be used.
* @param parseError In the event of a syntax error in the rules, provides the location
* within the rules of the problem.
* @param status Information on any errors encountered.
* @stable ICU 2.2
*/
RuleBasedBreakIterator( const UnicodeString &rules,
UParseError &parseError,
UErrorCode &status);
/**
* Contruct a RuleBasedBreakIterator from a set of precompiled binary rules.
* Binary rules are obtained from RulesBasedBreakIterator::getBinaryRules().
* Construction of a break iterator in this way is substantially faster than
* constuction from source rules.
*
* Ownership of the storage containing the compiled rules remains with the
* caller of this function. The compiled rules must not be modified or
* deleted during the life of the break iterator.
*
* The compiled rules are not compatible across different major versions of ICU.
* The compiled rules are comaptible only between machines with the same
* byte ordering (little or big endian) and the same base character set family
* (ASCII or EBCDIC).
*
* @see #getBinaryRules
* @param compiledRules A pointer to the compiled break rules to be used.
* @param ruleLength The length of the compiled break rules, in bytes. This
* corresponds to the length value produced by getBinaryRules().
* @param status Information on any errors encountered, including invalid
* binary rules.
* @stable ICU 4.8
*/
RuleBasedBreakIterator(const uint8_t *compiledRules,
uint32_t ruleLength,
UErrorCode &status);
/**
* This constructor uses the udata interface to create a BreakIterator
* whose internal tables live in a memory-mapped file. "image" is an
* ICU UDataMemory handle for the pre-compiled break iterator tables.
* @param image handle to the memory image for the break iterator data.
* Ownership of the UDataMemory handle passes to the Break Iterator,
* which will be responsible for closing it when it is no longer needed.
* @param status Information on any errors encountered.
* @see udata_open
* @see #getBinaryRules
* @stable ICU 2.8
*/
RuleBasedBreakIterator(UDataMemory* image, UErrorCode &status);
/**
* Destructor
* @stable ICU 2.0
*/
virtual ~RuleBasedBreakIterator();
/**
* Assignment operator. Sets this iterator to have the same behavior,
* and iterate over the same text, as the one passed in.
* @param that The RuleBasedBreakItertor passed in
* @return the newly created RuleBasedBreakIterator
* @stable ICU 2.0
*/
RuleBasedBreakIterator& operator=(const RuleBasedBreakIterator& that);
/**
* Equality operator. Returns TRUE if both BreakIterators are of the
* same class, have the same behavior, and iterate over the same text.
* @param that The BreakIterator to be compared for equality
* @return TRUE if both BreakIterators are of the
* same class, have the same behavior, and iterate over the same text.
* @stable ICU 2.0
*/
virtual UBool operator==(const BreakIterator& that) const;
/**
* Not-equal operator. If operator== returns TRUE, this returns FALSE,
* and vice versa.
* @param that The BreakIterator to be compared for inequality
* @return TRUE if both BreakIterators are not same.
* @stable ICU 2.0
*/
UBool operator!=(const BreakIterator& that) const;
/**
* Returns a newly-constructed RuleBasedBreakIterator with the same
* behavior, and iterating over the same text, as this one.
* Differs from the copy constructor in that it is polymorphic, and
* will correctly clone (copy) a derived class.
* clone() is thread safe. Multiple threads may simultaeneously
* clone the same source break iterator.
* @return a newly-constructed RuleBasedBreakIterator
* @stable ICU 2.0
*/
virtual BreakIterator* clone() const;
/**
* Compute a hash code for this BreakIterator
* @return A hash code
* @stable ICU 2.0
*/
virtual int32_t hashCode(void) const;
/**
* Returns the description used to create this iterator
* @return the description used to create this iterator
* @stable ICU 2.0
*/
virtual const UnicodeString& getRules(void) const;
//=======================================================================
// BreakIterator overrides
//=======================================================================
/**
* <p>
* Return a CharacterIterator over the text being analyzed.
* The returned character iterator is owned by the break iterator, and must
* not be deleted by the caller. Repeated calls to this function may
* return the same CharacterIterator.
* </p>
* <p>
* The returned character iterator must not be used concurrently with
* the break iterator. If concurrent operation is needed, clone the
* returned character iterator first and operate on the clone.
* </p>
* <p>
* When the break iterator is operating on text supplied via a UText,
* this function will fail. Lacking any way to signal failures, it
* returns an CharacterIterator containing no text.
* The function getUText() provides similar functionality,
* is reliable, and is more efficient.
* </p>
*
* TODO: deprecate this function?
*
* @return An iterator over the text being analyzed.
* @stable ICU 2.0
*/
virtual CharacterIterator& getText(void) const;
/**
* Get a UText for the text being analyzed.
* The returned UText is a shallow clone of the UText used internally
* by the break iterator implementation. It can safely be used to
* access the text without impacting any break iterator operations,
* but the underlying text itself must not be altered.
*
* @param fillIn A UText to be filled in. If NULL, a new UText will be
* allocated to hold the result.
* @param status receives any error codes.
* @return The current UText for this break iterator. If an input
* UText was provided, it will always be returned.
* @stable ICU 3.4
*/
virtual UText *getUText(UText *fillIn, UErrorCode &status) const;
/**
* Set the iterator to analyze a new piece of text. This function resets
* the current iteration position to the beginning of the text.
* @param newText An iterator over the text to analyze. The BreakIterator
* takes ownership of the character iterator. The caller MUST NOT delete it!
* @stable ICU 2.0
*/
virtual void adoptText(CharacterIterator* newText);
/**
* Set the iterator to analyze a new piece of text. This function resets
* the current iteration position to the beginning of the text.
* @param newText The text to analyze.
* @stable ICU 2.0
*/
virtual void setText(const UnicodeString& newText);
/**
* Reset the break iterator to operate over the text represented by
* the UText. The iterator position is reset to the start.
*
* This function makes a shallow clone of the supplied UText. This means
* that the caller is free to immediately close or otherwise reuse the
* Utext that was passed as a parameter, but that the underlying text itself
* must not be altered while being referenced by the break iterator.
*
* @param text The UText used to change the text.
* @param status Receives any error codes.
* @stable ICU 3.4
*/
virtual void setText(UText *text, UErrorCode &status);
/**
* Sets the current iteration position to the beginning of the text.
* @return The offset of the beginning of the text.
* @stable ICU 2.0
*/
virtual int32_t first(void);
/**
* Sets the current iteration position to the end of the text.
* @return The text's past-the-end offset.
* @stable ICU 2.0
*/
virtual int32_t last(void);
/**
* Advances the iterator either forward or backward the specified number of steps.
* Negative values move backward, and positive values move forward. This is
* equivalent to repeatedly calling next() or previous().
* @param n The number of steps to move. The sign indicates the direction
* (negative is backwards, and positive is forwards).
* @return The character offset of the boundary position n boundaries away from
* the current one.
* @stable ICU 2.0
*/
virtual int32_t next(int32_t n);
/**
* Advances the iterator to the next boundary position.
* @return The position of the first boundary after this one.
* @stable ICU 2.0
*/
virtual int32_t next(void);
/**
* Moves the iterator backwards, to the last boundary preceding this one.
* @return The position of the last boundary position preceding this one.
* @stable ICU 2.0
*/
virtual int32_t previous(void);
/**
* Sets the iterator to refer to the first boundary position following
* the specified position.
* @param offset The position from which to begin searching for a break position.
* @return The position of the first break after the current position.
* @stable ICU 2.0
*/
virtual int32_t following(int32_t offset);
/**
* Sets the iterator to refer to the last boundary position before the
* specified position.
* @param offset The position to begin searching for a break from.
* @return The position of the last boundary before the starting position.
* @stable ICU 2.0
*/
virtual int32_t preceding(int32_t offset);
/**
* Returns true if the specfied position is a boundary position. As a side
* effect, leaves the iterator pointing to the first boundary position at
* or after "offset".
* @param offset the offset to check.
* @return True if "offset" is a boundary position.
* @stable ICU 2.0
*/
virtual UBool isBoundary(int32_t offset);
/**
* Returns the current iteration position.
* @return The current iteration position.
* @stable ICU 2.0
*/
virtual int32_t current(void) const;
/**
* Return the status tag from the break rule that determined the most recently
* returned break position. For break rules that do not specify a
* status, a default value of 0 is returned. If more than one break rule
* would cause a boundary to be located at some position in the text,
* the numerically largest of the applicable status values is returned.
* <p>
* Of the standard types of ICU break iterators, only word break and
* line break provide status values. The values are defined in
* the header file ubrk.h. For Word breaks, the status allows distinguishing between words
* that contain alphabetic letters, "words" that appear to be numbers,
* punctuation and spaces, words containing ideographic characters, and
* more. For Line Break, the status distinguishes between hard (mandatory) breaks
* and soft (potential) break positions.
* <p>
* <code>getRuleStatus()</code> can be called after obtaining a boundary
* position from <code>next()</code>, <code>previous()</code>, or
* any other break iterator functions that returns a boundary position.
* <p>
* When creating custom break rules, one is free to define whatever
* status values may be convenient for the application.
* <p>
* Note: this function is not thread safe. It should not have been
* declared const, and the const remains only for compatibility
* reasons. (The function is logically const, but not bit-wise const).
* <p>
* @return the status from the break rule that determined the most recently
* returned break position.
*
* @see UWordBreak
* @stable ICU 2.2
*/
virtual int32_t getRuleStatus() const;
/**
* Get the status (tag) values from the break rule(s) that determined the most
* recently returned break position.
* <p>
* The returned status value(s) are stored into an array provided by the caller.
* The values are stored in sorted (ascending) order.
* If the capacity of the output array is insufficient to hold the data,
* the output will be truncated to the available length, and a
* U_BUFFER_OVERFLOW_ERROR will be signaled.
*
* @param fillInVec an array to be filled in with the status values.
* @param capacity the length of the supplied vector. A length of zero causes
* the function to return the number of status values, in the
* normal way, without attemtping to store any values.
* @param status receives error codes.
* @return The number of rule status values from rules that determined
* the most recent boundary returned by the break iterator.
* In the event of a U_BUFFER_OVERFLOW_ERROR, the return value
* is the total number of status values that were available,
* not the reduced number that were actually returned.
* @see getRuleStatus
* @stable ICU 3.0
*/
virtual int32_t getRuleStatusVec(int32_t *fillInVec, int32_t capacity, UErrorCode &status);
/**
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override.
* This method is to implement a simple version of RTTI, since not all
* C++ compilers support genuine RTTI. Polymorphic operator==() and
* clone() methods call this method.
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @stable ICU 2.0
*/
virtual UClassID getDynamicClassID(void) const;
/**
* Returns the class ID for this class. This is useful only for
* comparing to a return value from getDynamicClassID(). For example:
*
* Base* polymorphic_pointer = createPolymorphicObject();
* if (polymorphic_pointer->getDynamicClassID() ==
* Derived::getStaticClassID()) ...
*
* @return The class ID for all objects of this class.
* @stable ICU 2.0
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Deprecated functionality. Use clone() instead.
*
* Create a clone (copy) of this break iterator in memory provided
* by the caller. The idea is to increase performance by avoiding
* a storage allocation. Use of this functoin is NOT RECOMMENDED.
* Performance gains are minimal, and correct buffer management is
* tricky. Use clone() instead.
*
* @param stackBuffer The pointer to the memory into which the cloned object
* should be placed. If NULL, allocate heap memory
* for the cloned object.
* @param BufferSize The size of the buffer. If zero, return the required
* buffer size, but do not clone the object. If the
* size was too small (but not zero), allocate heap
* storage for the cloned object.
*
* @param status Error status. U_SAFECLONE_ALLOCATED_WARNING will be
* returned if the the provided buffer was too small, and
* the clone was therefore put on the heap.
*
* @return Pointer to the clone object. This may differ from the stackBuffer
* address if the byte alignment of the stack buffer was not suitable
* or if the stackBuffer was too small to hold the clone.
* @deprecated ICU 52. Use clone() instead.
*/
virtual BreakIterator * createBufferClone(void *stackBuffer,
int32_t &BufferSize,
UErrorCode &status);
/**
* Return the binary form of compiled break rules,
* which can then be used to create a new break iterator at some
* time in the future. Creating a break iterator from pre-compiled rules
* is much faster than building one from the source form of the
* break rules.
*
* The binary data can only be used with the same version of ICU
* and on the same platform type (processor endian-ness)
*
* @param length Returns the length of the binary data. (Out paramter.)
*
* @return A pointer to the binary (compiled) rule data. The storage
* belongs to the RulesBasedBreakIterator object, not the
* caller, and must not be modified or deleted.
* @stable ICU 4.8
*/
virtual const uint8_t *getBinaryRules(uint32_t &length);
/**
* Set the subject text string upon which the break iterator is operating
* without changing any other aspect of the matching state.
* The new and previous text strings must have the same content.
*
* This function is intended for use in environments where ICU is operating on
* strings that may move around in memory. It provides a mechanism for notifying
* ICU that the string has been relocated, and providing a new UText to access the
* string in its new position.
*
* Note that the break iterator implementation never copies the underlying text
* of a string being processed, but always operates directly on the original text
* provided by the user. Refreshing simply drops the references to the old text
* and replaces them with references to the new.
*
* Caution: this function is normally used only by very specialized,
* system-level code. One example use case is with garbage collection that moves
* the text in memory.
*
* @param input The new (moved) text string.
* @param status Receives errors detected by this function.
* @return *this
*
* @stable ICU 49
*/
virtual RuleBasedBreakIterator &refreshInputText(UText *input, UErrorCode &status);
protected:
//=======================================================================
// implementation
//=======================================================================
/**
* Dumps caches and performs other actions associated with a complete change
* in text or iteration position.
* @internal
*/
virtual void reset(void);
#if 0
/**
* Return true if the category lookup for this char
* indicates that it is in the set of dictionary lookup chars.
* This function is intended for use by dictionary based break iterators.
* @return true if the category lookup for this char
* indicates that it is in the set of dictionary lookup chars.
* @internal
*/
virtual UBool isDictionaryChar(UChar32);
/**
* Get the type of the break iterator.
* @internal
*/
virtual int32_t getBreakType() const;
#endif
/**
* Set the type of the break iterator.
* @internal
*/
virtual void setBreakType(int32_t type);
#ifndef U_HIDE_INTERNAL_API
/**
* Common initialization function, used by constructors and bufferClone.
* @internal
*/
void init();
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* This method backs the iterator back up to a "safe position" in the text.
* This is a position that we know, without any context, must be a break position.
* The various calling methods then iterate forward from this safe position to
* the appropriate position to return. (For more information, see the description
* of buildBackwardsStateTable() in RuleBasedBreakIterator.Builder.)
* @param statetable state table used of moving backwards
* @internal
*/
int32_t handlePrevious(const RBBIStateTable *statetable);
/**
* This method is the actual implementation of the next() method. All iteration
* vectors through here. This method initializes the state machine to state 1
* and advances through the text character by character until we reach the end
* of the text or the state machine transitions to state 0. We update our return
* value every time the state machine passes through a possible end state.
* @param statetable state table used of moving forwards
* @internal
*/
int32_t handleNext(const RBBIStateTable *statetable);
protected:
#ifndef U_HIDE_INTERNAL_API
/**
* This is the function that actually implements dictionary-based
* breaking. Covering at least the range from startPos to endPos,
* it checks for dictionary characters, and if it finds them determines
* the appropriate object to deal with them. It may cache found breaks in
* fCachedBreakPositions as it goes. It may well also look at text outside
* the range startPos to endPos.
* If going forward, endPos is the normal Unicode break result, and
* if goind in reverse, startPos is the normal Unicode break result
* @param startPos The start position of a range of text
* @param endPos The end position of a range of text
* @param reverse The call is for the reverse direction
* @internal
*/
int32_t checkDictionary(int32_t startPos, int32_t endPos, UBool reverse);
#endif /* U_HIDE_INTERNAL_API */
private:
/**
* This function returns the appropriate LanguageBreakEngine for a
* given character c.
* @param c A character in the dictionary set
* @internal
*/
const LanguageBreakEngine *getLanguageBreakEngine(UChar32 c);
/**
* @internal
*/
void makeRuleStatusValid();
};
//------------------------------------------------------------------------------
//
// Inline Functions Definitions ...
//
//------------------------------------------------------------------------------
inline UBool RuleBasedBreakIterator::operator!=(const BreakIterator& that) const {
return !operator==(that);
}
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_BREAK_ITERATION */
#endif
project/jni/icuuc/include/unicode/rbnf.h
-992
View File
@@ -1,992 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 1997-2013, International Business Machines Corporation and others.
* All Rights Reserved.
*******************************************************************************
*/
#ifndef RBNF_H
#define RBNF_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Rule Based Number Format
*/
/**
* \def U_HAVE_RBNF
* This will be 0 if RBNF support is not included in ICU
* and 1 if it is.
*
* @stable ICU 2.4
*/
#if UCONFIG_NO_FORMATTING
#define U_HAVE_RBNF 0
#else
#define U_HAVE_RBNF 1
#include "unicode/coll.h"
#include "unicode/dcfmtsym.h"
#include "unicode/fmtable.h"
#include "unicode/locid.h"
#include "unicode/numfmt.h"
#include "unicode/unistr.h"
#include "unicode/strenum.h"
U_NAMESPACE_BEGIN
class NFRuleSet;
class LocalizationInfo;
/**
* Tags for the predefined rulesets.
*
* @stable ICU 2.2
*/
enum URBNFRuleSetTag {
URBNF_SPELLOUT,
URBNF_ORDINAL,
URBNF_DURATION,
URBNF_NUMBERING_SYSTEM,
URBNF_COUNT
};
#if UCONFIG_NO_COLLATION
class Collator;
#endif
/**
* The RuleBasedNumberFormat class formats numbers according to a set of rules. This number formatter is
* typically used for spelling out numeric values in words (e.g., 25,3476 as
* &quot;twenty-five thousand three hundred seventy-six&quot; or &quot;vingt-cinq mille trois
* cents soixante-seize&quot; or
* &quot;f&uuml;nfundzwanzigtausenddreihundertsechsundsiebzig&quot;), but can also be used for
* other complicated formatting tasks, such as formatting a number of seconds as hours,
* minutes and seconds (e.g., 3,730 as &quot;1:02:10&quot;).
*
* <p>The resources contain three predefined formatters for each locale: spellout, which
* spells out a value in words (123 is &quot;one hundred twenty-three&quot;); ordinal, which
* appends an ordinal suffix to the end of a numeral (123 is &quot;123rd&quot;); and
* duration, which shows a duration in seconds as hours, minutes, and seconds (123 is
* &quot;2:03&quot;).&nbsp; The client can also define more specialized <tt>RuleBasedNumberFormat</tt>s
* by supplying programmer-defined rule sets.</p>
*
* <p>The behavior of a <tt>RuleBasedNumberFormat</tt> is specified by a textual description
* that is either passed to the constructor as a <tt>String</tt> or loaded from a resource
* bundle. In its simplest form, the description consists of a semicolon-delimited list of <em>rules.</em>
* Each rule has a string of output text and a value or range of values it is applicable to.
* In a typical spellout rule set, the first twenty rules are the words for the numbers from
* 0 to 19:</p>
*
* <pre>zero; one; two; three; four; five; six; seven; eight; nine;
* ten; eleven; twelve; thirteen; fourteen; fifteen; sixteen; seventeen; eighteen; nineteen;</pre>
*
* <p>For larger numbers, we can use the preceding set of rules to format the ones place, and
* we only have to supply the words for the multiples of 10:</p>
*
* <pre> 20: twenty[-&gt;&gt;];
* 30: thirty[-&gt;&gt;];
* 40: forty[-&gt;&gt;];
* 50: fifty[-&gt;&gt;];
* 60: sixty[-&gt;&gt;];
* 70: seventy[-&gt;&gt;];
* 80: eighty[-&gt;&gt;];
* 90: ninety[-&gt;&gt;];</pre>
*
* <p>In these rules, the <em>base value</em> is spelled out explicitly and set off from the
* rule's output text with a colon. The rules are in a sorted list, and a rule is applicable
* to all numbers from its own base value to one less than the next rule's base value. The
* &quot;&gt;&gt;&quot; token is called a <em>substitution</em> and tells the fomatter to
* isolate the number's ones digit, format it using this same set of rules, and place the
* result at the position of the &quot;&gt;&gt;&quot; token. Text in brackets is omitted if
* the number being formatted is an even multiple of 10 (the hyphen is a literal hyphen; 24
* is &quot;twenty-four,&quot; not &quot;twenty four&quot;).</p>
*
* <p>For even larger numbers, we can actually look up several parts of the number in the
* list:</p>
*
* <pre>100: &lt;&lt; hundred[ &gt;&gt;];</pre>
*
* <p>The &quot;&lt;&lt;&quot; represents a new kind of substitution. The &lt;&lt; isolates
* the hundreds digit (and any digits to its left), formats it using this same rule set, and
* places the result where the &quot;&lt;&lt;&quot; was. Notice also that the meaning of
* &gt;&gt; has changed: it now refers to both the tens and the ones digits. The meaning of
* both substitutions depends on the rule's base value. The base value determines the rule's <em>divisor,</em>
* which is the highest power of 10 that is less than or equal to the base value (the user
* can change this). To fill in the substitutions, the formatter divides the number being
* formatted by the divisor. The integral quotient is used to fill in the &lt;&lt;
* substitution, and the remainder is used to fill in the &gt;&gt; substitution. The meaning
* of the brackets changes similarly: text in brackets is omitted if the value being
* formatted is an even multiple of the rule's divisor. The rules are applied recursively, so
* if a substitution is filled in with text that includes another substitution, that
* substitution is also filled in.</p>
*
* <p>This rule covers values up to 999, at which point we add another rule:</p>
*
* <pre>1000: &lt;&lt; thousand[ &gt;&gt;];</pre>
*
* <p>Again, the meanings of the brackets and substitution tokens shift because the rule's
* base value is a higher power of 10, changing the rule's divisor. This rule can actually be
* used all the way up to 999,999. This allows us to finish out the rules as follows:</p>
*
* <pre> 1,000,000: &lt;&lt; million[ &gt;&gt;];
* 1,000,000,000: &lt;&lt; billion[ &gt;&gt;];
* 1,000,000,000,000: &lt;&lt; trillion[ &gt;&gt;];
* 1,000,000,000,000,000: OUT OF RANGE!;</pre>
*
* <p>Commas, periods, and spaces can be used in the base values to improve legibility and
* are ignored by the rule parser. The last rule in the list is customarily treated as an
* &quot;overflow rule,&quot; applying to everything from its base value on up, and often (as
* in this example) being used to print out an error message or default representation.
* Notice also that the size of the major groupings in large numbers is controlled by the
* spacing of the rules: because in English we group numbers by thousand, the higher rules
* are separated from each other by a factor of 1,000.</p>
*
* <p>To see how these rules actually work in practice, consider the following example:
* Formatting 25,430 with this rule set would work like this:</p>
*
* <table border="0" width="100%">
* <tr>
* <td><strong>&lt;&lt; thousand &gt;&gt;</strong></td>
* <td>[the rule whose base value is 1,000 is applicable to 25,340]</td>
* </tr>
* <tr>
* <td><strong>twenty-&gt;&gt;</strong> thousand &gt;&gt;</td>
* <td>[25,340 over 1,000 is 25. The rule for 20 applies.]</td>
* </tr>
* <tr>
* <td>twenty-<strong>five</strong> thousand &gt;&gt;</td>
* <td>[25 mod 10 is 5. The rule for 5 is &quot;five.&quot;</td>
* </tr>
* <tr>
* <td>twenty-five thousand <strong>&lt;&lt; hundred &gt;&gt;</strong></td>
* <td>[25,340 mod 1,000 is 340. The rule for 100 applies.]</td>
* </tr>
* <tr>
* <td>twenty-five thousand <strong>three</strong> hundred &gt;&gt;</td>
* <td>[340 over 100 is 3. The rule for 3 is &quot;three.&quot;]</td>
* </tr>
* <tr>
* <td>twenty-five thousand three hundred <strong>forty</strong></td>
* <td>[340 mod 100 is 40. The rule for 40 applies. Since 40 divides
* evenly by 10, the hyphen and substitution in the brackets are omitted.]</td>
* </tr>
* </table>
*
* <p>The above syntax suffices only to format positive integers. To format negative numbers,
* we add a special rule:</p>
*
* <pre>-x: minus &gt;&gt;;</pre>
*
* <p>This is called a <em>negative-number rule,</em> and is identified by &quot;-x&quot;
* where the base value would be. This rule is used to format all negative numbers. the
* &gt;&gt; token here means &quot;find the number's absolute value, format it with these
* rules, and put the result here.&quot;</p>
*
* <p>We also add a special rule called a <em>fraction rule </em>for numbers with fractional
* parts:</p>
*
* <pre>x.x: &lt;&lt; point &gt;&gt;;</pre>
*
* <p>This rule is used for all positive non-integers (negative non-integers pass through the
* negative-number rule first and then through this rule). Here, the &lt;&lt; token refers to
* the number's integral part, and the &gt;&gt; to the number's fractional part. The
* fractional part is formatted as a series of single-digit numbers (e.g., 123.456 would be
* formatted as &quot;one hundred twenty-three point four five six&quot;).</p>
*
* <p>To see how this rule syntax is applied to various languages, examine the resource data.</p>
*
* <p>There is actually much more flexibility built into the rule language than the
* description above shows. A formatter may own multiple rule sets, which can be selected by
* the caller, and which can use each other to fill in their substitutions. Substitutions can
* also be filled in with digits, using a DecimalFormat object. There is syntax that can be
* used to alter a rule's divisor in various ways. And there is provision for much more
* flexible fraction handling. A complete description of the rule syntax follows:</p>
*
* <hr>
*
* <p>The description of a <tt>RuleBasedNumberFormat</tt>'s behavior consists of one or more <em>rule
* sets.</em> Each rule set consists of a name, a colon, and a list of <em>rules.</em> A rule
* set name must begin with a % sign. Rule sets with names that begin with a single % sign
* are <em>public:</em> the caller can specify that they be used to format and parse numbers.
* Rule sets with names that begin with %% are <em>private:</em> they exist only for the use
* of other rule sets. If a formatter only has one rule set, the name may be omitted.</p>
*
* <p>The user can also specify a special &quot;rule set&quot; named <tt>%%lenient-parse</tt>.
* The body of <tt>%%lenient-parse</tt> isn't a set of number-formatting rules, but a <tt>RuleBasedCollator</tt>
* description which is used to define equivalences for lenient parsing. For more information
* on the syntax, see <tt>RuleBasedCollator</tt>. For more information on lenient parsing,
* see <tt>setLenientParse()</tt>. <em>Note:</em> symbols that have syntactic meaning
* in collation rules, such as '&amp;', have no particular meaning when appearing outside
* of the <tt>lenient-parse</tt> rule set.</p>
*
* <p>The body of a rule set consists of an ordered, semicolon-delimited list of <em>rules.</em>
* Internally, every rule has a base value, a divisor, rule text, and zero, one, or two <em>substitutions.</em>
* These parameters are controlled by the description syntax, which consists of a <em>rule
* descriptor,</em> a colon, and a <em>rule body.</em></p>
*
* <p>A rule descriptor can take one of the following forms (text in <em>italics</em> is the
* name of a token):</p>
*
* <table border="0" width="100%">
* <tr>
* <td><em>bv</em>:</td>
* <td><em>bv</em> specifies the rule's base value. <em>bv</em> is a decimal
* number expressed using ASCII digits. <em>bv</em> may contain spaces, period, and commas,
* which are ignored. The rule's divisor is the highest power of 10 less than or equal to
* the base value.</td>
* </tr>
* <tr>
* <td><em>bv</em>/<em>rad</em>:</td>
* <td><em>bv</em> specifies the rule's base value. The rule's divisor is the
* highest power of <em>rad</em> less than or equal to the base value.</td>
* </tr>
* <tr>
* <td><em>bv</em>&gt;:</td>
* <td><em>bv</em> specifies the rule's base value. To calculate the divisor,
* let the radix be 10, and the exponent be the highest exponent of the radix that yields a
* result less than or equal to the base value. Every &gt; character after the base value
* decreases the exponent by 1. If the exponent is positive or 0, the divisor is the radix
* raised to the power of the exponent; otherwise, the divisor is 1.</td>
* </tr>
* <tr>
* <td><em>bv</em>/<em>rad</em>&gt;:</td>
* <td><em>bv</em> specifies the rule's base value. To calculate the divisor,
* let the radix be <em>rad</em>, and the exponent be the highest exponent of the radix that
* yields a result less than or equal to the base value. Every &gt; character after the radix
* decreases the exponent by 1. If the exponent is positive or 0, the divisor is the radix
* raised to the power of the exponent; otherwise, the divisor is 1.</td>
* </tr>
* <tr>
* <td>-x:</td>
* <td>The rule is a negative-number rule.</td>
* </tr>
* <tr>
* <td>x.x:</td>
* <td>The rule is an <em>improper fraction rule.</em></td>
* </tr>
* <tr>
* <td>0.x:</td>
* <td>The rule is a <em>proper fraction rule.</em></td>
* </tr>
* <tr>
* <td>x.0:</td>
* <td>The rule is a <em>master rule.</em></td>
* </tr>
* <tr>
* <td><em>nothing</em></td>
* <td>If the rule's rule descriptor is left out, the base value is one plus the
* preceding rule's base value (or zero if this is the first rule in the list) in a normal
* rule set.&nbsp; In a fraction rule set, the base value is the same as the preceding rule's
* base value.</td>
* </tr>
* </table>
*
* <p>A rule set may be either a regular rule set or a <em>fraction rule set,</em> depending
* on whether it is used to format a number's integral part (or the whole number) or a
* number's fractional part. Using a rule set to format a rule's fractional part makes it a
* fraction rule set.</p>
*
* <p>Which rule is used to format a number is defined according to one of the following
* algorithms: If the rule set is a regular rule set, do the following:
*
* <ul>
* <li>If the rule set includes a master rule (and the number was passed in as a <tt>double</tt>),
* use the master rule.&nbsp; (If the number being formatted was passed in as a <tt>long</tt>,
* the master rule is ignored.)</li>
* <li>If the number is negative, use the negative-number rule.</li>
* <li>If the number has a fractional part and is greater than 1, use the improper fraction
* rule.</li>
* <li>If the number has a fractional part and is between 0 and 1, use the proper fraction
* rule.</li>
* <li>Binary-search the rule list for the rule with the highest base value less than or equal
* to the number. If that rule has two substitutions, its base value is not an even multiple
* of its divisor, and the number <em>is</em> an even multiple of the rule's divisor, use the
* rule that precedes it in the rule list. Otherwise, use the rule itself.</li>
* </ul>
*
* <p>If the rule set is a fraction rule set, do the following:
*
* <ul>
* <li>Ignore negative-number and fraction rules.</li>
* <li>For each rule in the list, multiply the number being formatted (which will always be
* between 0 and 1) by the rule's base value. Keep track of the distance between the result
* the nearest integer.</li>
* <li>Use the rule that produced the result closest to zero in the above calculation. In the
* event of a tie or a direct hit, use the first matching rule encountered. (The idea here is
* to try each rule's base value as a possible denominator of a fraction. Whichever
* denominator produces the fraction closest in value to the number being formatted wins.) If
* the rule following the matching rule has the same base value, use it if the numerator of
* the fraction is anything other than 1; if the numerator is 1, use the original matching
* rule. (This is to allow singular and plural forms of the rule text without a lot of extra
* hassle.)</li>
* </ul>
*
* <p>A rule's body consists of a string of characters terminated by a semicolon. The rule
* may include zero, one, or two <em>substitution tokens,</em> and a range of text in
* brackets. The brackets denote optional text (and may also include one or both
* substitutions). The exact meanings of the substitution tokens, and under what conditions
* optional text is omitted, depend on the syntax of the substitution token and the context.
* The rest of the text in a rule body is literal text that is output when the rule matches
* the number being formatted.</p>
*
* <p>A substitution token begins and ends with a <em>token character.</em> The token
* character and the context together specify a mathematical operation to be performed on the
* number being formatted. An optional <em>substitution descriptor </em>specifies how the
* value resulting from that operation is used to fill in the substitution. The position of
* the substitution token in the rule body specifies the location of the resultant text in
* the original rule text.</p>
*
* <p>The meanings of the substitution token characters are as follows:</p>
*
* <table border="0" width="100%">
* <tr>
* <td>&gt;&gt;</td>
* <td>in normal rule</td>
* <td>Divide the number by the rule's divisor and format the remainder</td>
* </tr>
* <tr>
* <td></td>
* <td>in negative-number rule</td>
* <td>Find the absolute value of the number and format the result</td>
* </tr>
* <tr>
* <td></td>
* <td>in fraction or master rule</td>
* <td>Isolate the number's fractional part and format it.</td>
* </tr>
* <tr>
* <td></td>
* <td>in rule in fraction rule set</td>
* <td>Not allowed.</td>
* </tr>
* <tr>
* <td>&gt;&gt;&gt;</td>
* <td>in normal rule</td>
* <td>Divide the number by the rule's divisor and format the remainder,
* but bypass the normal rule-selection process and just use the
* rule that precedes this one in this rule list.</td>
* </tr>
* <tr>
* <td></td>
* <td>in all other rules</td>
* <td>Not allowed.</td>
* </tr>
* <tr>
* <td>&lt;&lt;</td>
* <td>in normal rule</td>
* <td>Divide the number by the rule's divisor and format the quotient</td>
* </tr>
* <tr>
* <td></td>
* <td>in negative-number rule</td>
* <td>Not allowed.</td>
* </tr>
* <tr>
* <td></td>
* <td>in fraction or master rule</td>
* <td>Isolate the number's integral part and format it.</td>
* </tr>
* <tr>
* <td></td>
* <td>in rule in fraction rule set</td>
* <td>Multiply the number by the rule's base value and format the result.</td>
* </tr>
* <tr>
* <td>==</td>
* <td>in all rule sets</td>
* <td>Format the number unchanged</td>
* </tr>
* <tr>
* <td>[]</td>
* <td>in normal rule</td>
* <td>Omit the optional text if the number is an even multiple of the rule's divisor</td>
* </tr>
* <tr>
* <td></td>
* <td>in negative-number rule</td>
* <td>Not allowed.</td>
* </tr>
* <tr>
* <td></td>
* <td>in improper-fraction rule</td>
* <td>Omit the optional text if the number is between 0 and 1 (same as specifying both an
* x.x rule and a 0.x rule)</td>
* </tr>
* <tr>
* <td></td>
* <td>in master rule</td>
* <td>Omit the optional text if the number is an integer (same as specifying both an x.x
* rule and an x.0 rule)</td>
* </tr>
* <tr>
* <td></td>
* <td>in proper-fraction rule</td>
* <td>Not allowed.</td>
* </tr>
* <tr>
* <td></td>
* <td>in rule in fraction rule set</td>
* <td>Omit the optional text if multiplying the number by the rule's base value yields 1.</td>
* </tr>
* </table>
*
* <p>The substitution descriptor (i.e., the text between the token characters) may take one
* of three forms:</p>
*
* <table border="0" width="100%">
* <tr>
* <td>a rule set name</td>
* <td>Perform the mathematical operation on the number, and format the result using the
* named rule set.</td>
* </tr>
* <tr>
* <td>a DecimalFormat pattern</td>
* <td>Perform the mathematical operation on the number, and format the result using a
* DecimalFormat with the specified pattern.&nbsp; The pattern must begin with 0 or #.</td>
* </tr>
* <tr>
* <td>nothing</td>
* <td>Perform the mathematical operation on the number, and format the result using the rule
* set containing the current rule, except:
* <ul>
* <li>You can't have an empty substitution descriptor with a == substitution.</li>
* <li>If you omit the substitution descriptor in a &gt;&gt; substitution in a fraction rule,
* format the result one digit at a time using the rule set containing the current rule.</li>
* <li>If you omit the substitution descriptor in a &lt;&lt; substitution in a rule in a
* fraction rule set, format the result using the default rule set for this formatter.</li>
* </ul>
* </td>
* </tr>
* </table>
*
* <p>Whitespace is ignored between a rule set name and a rule set body, between a rule
* descriptor and a rule body, or between rules. If a rule body begins with an apostrophe,
* the apostrophe is ignored, but all text after it becomes significant (this is how you can
* have a rule's rule text begin with whitespace). There is no escape function: the semicolon
* is not allowed in rule set names or in rule text, and the colon is not allowed in rule set
* names. The characters beginning a substitution token are always treated as the beginning
* of a substitution token.</p>
*
* <p>See the resource data and the demo program for annotated examples of real rule sets
* using these features.</p>
*
* <p><em>User subclasses are not supported.</em> While clients may write
* subclasses, such code will not necessarily work and will not be
* guaranteed to work stably from release to release.
*
* <p><b>Localizations</b></p>
* <p>Constructors are available that allow the specification of localizations for the
* public rule sets (and also allow more control over what public rule sets are available).
* Localization data is represented as a textual description. The description represents
* an array of arrays of string. The first element is an array of the public rule set names,
* each of these must be one of the public rule set names that appear in the rules. Only
* names in this array will be treated as public rule set names by the API. Each subsequent
* element is an array of localizations of these names. The first element of one of these
* subarrays is the locale name, and the remaining elements are localizations of the
* public rule set names, in the same order as they were listed in the first arrray.</p>
* <p>In the syntax, angle brackets '<', '>' are used to delimit the arrays, and comma ',' is used
* to separate elements of an array. Whitespace is ignored, unless quoted.</p>
* <p>For example:<pre>
* < < %foo, %bar, %baz >,
* < en, Foo, Bar, Baz >,
* < fr, 'le Foo', 'le Bar', 'le Baz' >
* < zh, \\u7532, \\u4e59, \\u4e19 > >
* </pre></p>
* @author Richard Gillam
* @see NumberFormat
* @see DecimalFormat
* @stable ICU 2.0
*/
class U_I18N_API RuleBasedNumberFormat : public NumberFormat {
public:
//-----------------------------------------------------------------------
// constructors
//-----------------------------------------------------------------------
/**
* Creates a RuleBasedNumberFormat that behaves according to the description
* passed in. The formatter uses the default locale.
* @param rules A description of the formatter's desired behavior.
* See the class documentation for a complete explanation of the description
* syntax.
* @param perror The parse error if an error was encountered.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 3.2
*/
RuleBasedNumberFormat(const UnicodeString& rules, UParseError& perror, UErrorCode& status);
/**
* Creates a RuleBasedNumberFormat that behaves according to the description
* passed in. The formatter uses the default locale.
* <p>
* The localizations data provides information about the public
* rule sets and their localized display names for different
* locales. The first element in the list is an array of the names
* of the public rule sets. The first element in this array is
* the initial default ruleset. The remaining elements in the
* list are arrays of localizations of the names of the public
* rule sets. Each of these is one longer than the initial array,
* with the first String being the ULocale ID, and the remaining
* Strings being the localizations of the rule set names, in the
* same order as the initial array. Arrays are NULL-terminated.
* @param rules A description of the formatter's desired behavior.
* See the class documentation for a complete explanation of the description
* syntax.
* @param localizations the localization information.
* names in the description. These will be copied by the constructor.
* @param perror The parse error if an error was encountered.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 3.2
*/
RuleBasedNumberFormat(const UnicodeString& rules, const UnicodeString& localizations,
UParseError& perror, UErrorCode& status);
/**
* Creates a RuleBasedNumberFormat that behaves according to the rules
* passed in. The formatter uses the specified locale to determine the
* characters to use when formatting numerals, and to define equivalences
* for lenient parsing.
* @param rules The formatter rules.
* See the class documentation for a complete explanation of the rule
* syntax.
* @param locale A locale that governs which characters are used for
* formatting values in numerals and which characters are equivalent in
* lenient parsing.
* @param perror The parse error if an error was encountered.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 2.0
*/
RuleBasedNumberFormat(const UnicodeString& rules, const Locale& locale,
UParseError& perror, UErrorCode& status);
/**
* Creates a RuleBasedNumberFormat that behaves according to the description
* passed in. The formatter uses the default locale.
* <p>
* The localizations data provides information about the public
* rule sets and their localized display names for different
* locales. The first element in the list is an array of the names
* of the public rule sets. The first element in this array is
* the initial default ruleset. The remaining elements in the
* list are arrays of localizations of the names of the public
* rule sets. Each of these is one longer than the initial array,
* with the first String being the ULocale ID, and the remaining
* Strings being the localizations of the rule set names, in the
* same order as the initial array. Arrays are NULL-terminated.
* @param rules A description of the formatter's desired behavior.
* See the class documentation for a complete explanation of the description
* syntax.
* @param localizations a list of localizations for the rule set
* names in the description. These will be copied by the constructor.
* @param locale A locale that governs which characters are used for
* formatting values in numerals and which characters are equivalent in
* lenient parsing.
* @param perror The parse error if an error was encountered.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 3.2
*/
RuleBasedNumberFormat(const UnicodeString& rules, const UnicodeString& localizations,
const Locale& locale, UParseError& perror, UErrorCode& status);
/**
* Creates a RuleBasedNumberFormat from a predefined ruleset. The selector
* code choosed among three possible predefined formats: spellout, ordinal,
* and duration.
* @param tag A selector code specifying which kind of formatter to create for that
* locale. There are four legal values: URBNF_SPELLOUT, which creates a formatter that
* spells out a value in words in the desired language, URBNF_ORDINAL, which attaches
* an ordinal suffix from the desired language to the end of a number (e.g. "123rd"),
* URBNF_DURATION, which formats a duration in seconds as hours, minutes, and seconds,
* and URBNF_NUMBERING_SYSTEM, which is used to invoke rules for alternate numbering
* systems such as the Hebrew numbering system, or for Roman Numerals, etc.
* @param locale The locale for the formatter.
* @param status The status indicating whether the constructor succeeded.
* @stable ICU 2.0
*/
RuleBasedNumberFormat(URBNFRuleSetTag tag, const Locale& locale, UErrorCode& status);
//-----------------------------------------------------------------------
// boilerplate
//-----------------------------------------------------------------------
/**
* Copy constructor
* @param rhs the object to be copied from.
* @stable ICU 2.6
*/
RuleBasedNumberFormat(const RuleBasedNumberFormat& rhs);
/**
* Assignment operator
* @param rhs the object to be copied from.
* @stable ICU 2.6
*/
RuleBasedNumberFormat& operator=(const RuleBasedNumberFormat& rhs);
/**
* Release memory allocated for a RuleBasedNumberFormat when you are finished with it.
* @stable ICU 2.6
*/
virtual ~RuleBasedNumberFormat();
/**
* Clone this object polymorphically. The caller is responsible
* for deleting the result when done.
* @return A copy of the object.
* @stable ICU 2.6
*/
virtual Format* clone(void) const;
/**
* Return true if the given Format objects are semantically equal.
* Objects of different subclasses are considered unequal.
* @param other the object to be compared with.
* @return true if the given Format objects are semantically equal.
* @stable ICU 2.6
*/
virtual UBool operator==(const Format& other) const;
//-----------------------------------------------------------------------
// public API functions
//-----------------------------------------------------------------------
/**
* return the rules that were provided to the RuleBasedNumberFormat.
* @return the result String that was passed in
* @stable ICU 2.0
*/
virtual UnicodeString getRules() const;
/**
* Return the number of public rule set names.
* @return the number of public rule set names.
* @stable ICU 2.0
*/
virtual int32_t getNumberOfRuleSetNames() const;
/**
* Return the name of the index'th public ruleSet. If index is not valid,
* the function returns null.
* @param index the index of the ruleset
* @return the name of the index'th public ruleSet.
* @stable ICU 2.0
*/
virtual UnicodeString getRuleSetName(int32_t index) const;
/**
* Return the number of locales for which we have localized rule set display names.
* @return the number of locales for which we have localized rule set display names.
* @stable ICU 3.2
*/
virtual int32_t getNumberOfRuleSetDisplayNameLocales(void) const;
/**
* Return the index'th display name locale.
* @param index the index of the locale
* @param status set to a failure code when this function fails
* @return the locale
* @see #getNumberOfRuleSetDisplayNameLocales
* @stable ICU 3.2
*/
virtual Locale getRuleSetDisplayNameLocale(int32_t index, UErrorCode& status) const;
/**
* Return the rule set display names for the provided locale. These are in the same order
* as those returned by getRuleSetName. The locale is matched against the locales for
* which there is display name data, using normal fallback rules. If no locale matches,
* the default display names are returned. (These are the internal rule set names minus
* the leading '%'.)
* @param index the index of the rule set
* @param locale the locale (returned by getRuleSetDisplayNameLocales) for which the localized
* display name is desired
* @return the display name for the given index, which might be bogus if there is an error
* @see #getRuleSetName
* @stable ICU 3.2
*/
virtual UnicodeString getRuleSetDisplayName(int32_t index,
const Locale& locale = Locale::getDefault());
/**
* Return the rule set display name for the provided rule set and locale.
* The locale is matched against the locales for which there is display name data, using
* normal fallback rules. If no locale matches, the default display name is returned.
* @return the display name for the rule set
* @stable ICU 3.2
* @see #getRuleSetDisplayName
*/
virtual UnicodeString getRuleSetDisplayName(const UnicodeString& ruleSetName,
const Locale& locale = Locale::getDefault());
using NumberFormat::format;
/**
* Formats the specified 32-bit number using the default ruleset.
* @param number The number to format.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(int32_t number,
UnicodeString& toAppendTo,
FieldPosition& pos) const;
/**
* Formats the specified 64-bit number using the default ruleset.
* @param number The number to format.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @return A textual representation of the number.
* @stable ICU 2.1
*/
virtual UnicodeString& format(int64_t number,
UnicodeString& toAppendTo,
FieldPosition& pos) const;
/**
* Formats the specified number using the default ruleset.
* @param number The number to format.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(double number,
UnicodeString& toAppendTo,
FieldPosition& pos) const;
/**
* Formats the specified number using the named ruleset.
* @param number The number to format.
* @param ruleSetName The name of the rule set to format the number with.
* This must be the name of a valid public rule set for this formatter.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @param status the status
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(int32_t number,
const UnicodeString& ruleSetName,
UnicodeString& toAppendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Formats the specified 64-bit number using the named ruleset.
* @param number The number to format.
* @param ruleSetName The name of the rule set to format the number with.
* This must be the name of a valid public rule set for this formatter.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @param status the status
* @return A textual representation of the number.
* @stable ICU 2.1
*/
virtual UnicodeString& format(int64_t number,
const UnicodeString& ruleSetName,
UnicodeString& toAppendTo,
FieldPosition& pos,
UErrorCode& status) const;
/**
* Formats the specified number using the named ruleset.
* @param number The number to format.
* @param ruleSetName The name of the rule set to format the number with.
* This must be the name of a valid public rule set for this formatter.
* @param toAppendTo the string that will hold the (appended) result
* @param pos the fieldposition
* @param status the status
* @return A textual representation of the number.
* @stable ICU 2.0
*/
virtual UnicodeString& format(double number,
const UnicodeString& ruleSetName,
UnicodeString& toAppendTo,
FieldPosition& pos,
UErrorCode& status) const;
using NumberFormat::parse;
/**
* Parses the specfied string, beginning at the specified position, according
* to this formatter's rules. This will match the string against all of the
* formatter's public rule sets and return the value corresponding to the longest
* parseable substring. This function's behavior is affected by the lenient
* parse mode.
* @param text The string to parse
* @param result the result of the parse, either a double or a long.
* @param parsePosition On entry, contains the position of the first character
* in "text" to examine. On exit, has been updated to contain the position
* of the first character in "text" that wasn't consumed by the parse.
* @see #setLenient
* @stable ICU 2.0
*/
virtual void parse(const UnicodeString& text,
Formattable& result,
ParsePosition& parsePosition) const;
#if !UCONFIG_NO_COLLATION
/**
* Turns lenient parse mode on and off.
*
* When in lenient parse mode, the formatter uses a Collator for parsing the text.
* Only primary differences are treated as significant. This means that case
* differences, accent differences, alternate spellings of the same letter
* (e.g., ae and a-umlaut in German), ignorable characters, etc. are ignored in
* matching the text. In many cases, numerals will be accepted in place of words
* or phrases as well.
*
* For example, all of the following will correctly parse as 255 in English in
* lenient-parse mode:
* <br>"two hundred fifty-five"
* <br>"two hundred fifty five"
* <br>"TWO HUNDRED FIFTY-FIVE"
* <br>"twohundredfiftyfive"
* <br>"2 hundred fifty-5"
*
* The Collator used is determined by the locale that was
* passed to this object on construction. The description passed to this object
* on construction may supply additional collation rules that are appended to the
* end of the default collator for the locale, enabling additional equivalences
* (such as adding more ignorable characters or permitting spelled-out version of
* symbols; see the demo program for examples).
*
* It's important to emphasize that even strict parsing is relatively lenient: it
* will accept some text that it won't produce as output. In English, for example,
* it will correctly parse "two hundred zero" and "fifteen hundred".
*
* @param enabled If true, turns lenient-parse mode on; if false, turns it off.
* @see RuleBasedCollator
* @stable ICU 2.0
*/
virtual void setLenient(UBool enabled);
/**
* Returns true if lenient-parse mode is turned on. Lenient parsing is off
* by default.
* @return true if lenient-parse mode is turned on.
* @see #setLenient
* @stable ICU 2.0
*/
virtual inline UBool isLenient(void) const;
#endif
/**
* Override the default rule set to use. If ruleSetName is null, reset
* to the initial default rule set. If the rule set is not a public rule set name,
* U_ILLEGAL_ARGUMENT_ERROR is returned in status.
* @param ruleSetName the name of the rule set, or null to reset the initial default.
* @param status set to failure code when a problem occurs.
* @stable ICU 2.6
*/
virtual void setDefaultRuleSet(const UnicodeString& ruleSetName, UErrorCode& status);
/**
* Return the name of the current default rule set. If the current rule set is
* not public, returns a bogus (and empty) UnicodeString.
* @return the name of the current default rule set
* @stable ICU 3.0
*/
virtual UnicodeString getDefaultRuleSetName() const;
public:
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.8
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.8
*/
virtual UClassID getDynamicClassID(void) const;
/**
* Sets the decimal format symbols, which is generally not changed
* by the programmer or user. The formatter takes ownership of
* symbolsToAdopt; the client must not delete it.
*
* @param symbolsToAdopt DecimalFormatSymbols to be adopted.
* @stable ICU 49
*/
virtual void adoptDecimalFormatSymbols(DecimalFormatSymbols* symbolsToAdopt);
/**
* Sets the decimal format symbols, which is generally not changed
* by the programmer or user. A clone of the symbols is created and
* the symbols is _not_ adopted; the client is still responsible for
* deleting it.
*
* @param symbols DecimalFormatSymbols.
* @stable ICU 49
*/
virtual void setDecimalFormatSymbols(const DecimalFormatSymbols& symbols);
private:
RuleBasedNumberFormat(); // default constructor not implemented
// this will ref the localizations if they are not NULL
// caller must deref to get adoption
RuleBasedNumberFormat(const UnicodeString& description, LocalizationInfo* localizations,
const Locale& locale, UParseError& perror, UErrorCode& status);
void init(const UnicodeString& rules, LocalizationInfo* localizations, UParseError& perror, UErrorCode& status);
void dispose();
void stripWhitespace(UnicodeString& src);
void initDefaultRuleSet();
void format(double number, NFRuleSet& ruleSet);
NFRuleSet* findRuleSet(const UnicodeString& name, UErrorCode& status) const;
/* friend access */
friend class NFSubstitution;
friend class NFRule;
friend class FractionalPartSubstitution;
inline NFRuleSet * getDefaultRuleSet() const;
Collator * getCollator() const;
DecimalFormatSymbols * getDecimalFormatSymbols() const;
private:
NFRuleSet **ruleSets;
UnicodeString* ruleSetDescriptions;
int32_t numRuleSets;
NFRuleSet *defaultRuleSet;
Locale locale;
Collator* collator;
DecimalFormatSymbols* decimalFormatSymbols;
UBool lenient;
UnicodeString* lenientParseRules;
LocalizationInfo* localizations;
};
// ---------------
#if !UCONFIG_NO_COLLATION
inline UBool
RuleBasedNumberFormat::isLenient(void) const {
return lenient;
}
#endif
inline NFRuleSet*
RuleBasedNumberFormat::getDefaultRuleSet() const {
return defaultRuleSet;
}
U_NAMESPACE_END
/* U_HAVE_RBNF */
#endif
/* RBNF_H */
#endif
project/jni/icuuc/include/unicode/rbtz.h
-362
View File
@@ -1,362 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2007-2013, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*/
#ifndef RBTZ_H
#define RBTZ_H
#include "unicode/utypes.h"
/**
* \file
* \brief C++ API: Rule based customizable time zone
*/
#if !UCONFIG_NO_FORMATTING
#include "unicode/basictz.h"
#include "unicode/unistr.h"
U_NAMESPACE_BEGIN
// forward declaration
class UVector;
struct Transition;
/**
* a BasicTimeZone subclass implemented in terms of InitialTimeZoneRule and TimeZoneRule instances
* @see BasicTimeZone
* @see InitialTimeZoneRule
* @see TimeZoneRule
*/
class U_I18N_API RuleBasedTimeZone : public BasicTimeZone {
public:
/**
* Constructs a <code>RuleBasedTimeZone</code> object with the ID and the
* <code>InitialTimeZoneRule</code>. The input <code>InitialTimeZoneRule</code>
* is adopted by this <code>RuleBasedTimeZone</code>, thus the caller must not
* delete it.
* @param id The time zone ID.
* @param initialRule The initial time zone rule.
* @stable ICU 3.8
*/
RuleBasedTimeZone(const UnicodeString& id, InitialTimeZoneRule* initialRule);
/**
* Copy constructor.
* @param source The RuleBasedTimeZone object to be copied.
* @stable ICU 3.8
*/
RuleBasedTimeZone(const RuleBasedTimeZone& source);
/**
* Destructor.
* @stable ICU 3.8
*/
virtual ~RuleBasedTimeZone();
/**
* Assignment operator.
* @param right The object to be copied.
* @stable ICU 3.8
*/
RuleBasedTimeZone& operator=(const RuleBasedTimeZone& right);
/**
* Return true if the given <code>TimeZone</code> objects are
* semantically equal. Objects of different subclasses are considered unequal.
* @param that The object to be compared with.
* @return true if the given <code>TimeZone</code> objects are
*semantically equal.
* @stable ICU 3.8
*/
virtual UBool operator==(const TimeZone& that) const;
/**
* Return true if the given <code>TimeZone</code> objects are
* semantically unequal. Objects of different subclasses are considered unequal.
* @param that The object to be compared with.
* @return true if the given <code>TimeZone</code> objects are
* semantically unequal.
* @stable ICU 3.8
*/
virtual UBool operator!=(const TimeZone& that) const;
/**
* Adds the <code>TimeZoneRule</code> which represents time transitions.
* The <code>TimeZoneRule</code> must have start times, that is, the result
* of isTransitionRule() must be true. Otherwise, U_ILLEGAL_ARGUMENT_ERROR
* is set to the error code.
* The input <code>TimeZoneRule</code> is adopted by this
* <code>RuleBasedTimeZone</code> on successful completion of this method,
* thus, the caller must not delete it when no error is returned.
* After all rules are added, the caller must call complete() method to
* make this <code>RuleBasedTimeZone</code> ready to handle common time
* zone functions.
* @param rule The <code>TimeZoneRule</code>.
* @param status Output param to filled in with a success or an error.
* @stable ICU 3.8
*/
void addTransitionRule(TimeZoneRule* rule, UErrorCode& status);
/**
* Makes the <code>TimeZoneRule</code> ready to handle actual timezone
* calcuation APIs. This method collects time zone rules specified
* by the caller via the constructor and addTransitionRule() and
* builds internal structure for making the object ready to support
* time zone APIs such as getOffset(), getNextTransition() and others.
* @param status Output param to filled in with a success or an error.
* @stable ICU 3.8
*/
void complete(UErrorCode& status);
/**
* Clones TimeZone objects polymorphically. Clients are responsible for deleting
* the TimeZone object cloned.
*
* @return A new copy of this TimeZone object.
* @stable ICU 3.8
*/
virtual TimeZone* clone(void) const;
/**
* Returns the TimeZone's adjusted GMT offset (i.e., the number of milliseconds to add
* to GMT to get local time in this time zone, taking daylight savings time into
* account) as of a particular reference date. The reference date is used to determine
* whether daylight savings time is in effect and needs to be figured into the offset
* that is returned (in other words, what is the adjusted GMT offset in this time zone
* at this particular date and time?). For the time zones produced by createTimeZone(),
* the reference data is specified according to the Gregorian calendar, and the date
* and time fields are local standard time.
*
* <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload,
* which returns both the raw and the DST offset for a given time. This method
* is retained only for backward compatibility.
*
* @param era The reference date's era
* @param year The reference date's year
* @param month The reference date's month (0-based; 0 is January)
* @param day The reference date's day-in-month (1-based)
* @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday)
* @param millis The reference date's milliseconds in day, local standard time
* @param status Output param to filled in with a success or an error.
* @return The offset in milliseconds to add to GMT to get local time.
* @stable ICU 3.8
*/
virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day,
uint8_t dayOfWeek, int32_t millis, UErrorCode& status) const;
/**
* Gets the time zone offset, for current date, modified in case of
* daylight savings. This is the offset to add *to* UTC to get local time.
*
* <p>Note: Don't call this method. Instead, call the getOffset(UDate...) overload,
* which returns both the raw and the DST offset for a given time. This method
* is retained only for backward compatibility.
*
* @param era The reference date's era
* @param year The reference date's year
* @param month The reference date's month (0-based; 0 is January)
* @param day The reference date's day-in-month (1-based)
* @param dayOfWeek The reference date's day-of-week (1-based; 1 is Sunday)
* @param millis The reference date's milliseconds in day, local standard time
* @param monthLength The length of the given month in days.
* @param status Output param to filled in with a success or an error.
* @return The offset in milliseconds to add to GMT to get local time.
* @stable ICU 3.8
*/
virtual int32_t getOffset(uint8_t era, int32_t year, int32_t month, int32_t day,
uint8_t dayOfWeek, int32_t millis,
int32_t monthLength, UErrorCode& status) const;
/**
* Returns the time zone raw and GMT offset for the given moment
* in time. Upon return, local-millis = GMT-millis + rawOffset +
* dstOffset. All computations are performed in the proleptic
* Gregorian calendar. The default implementation in the TimeZone
* class delegates to the 8-argument getOffset().
*
* @param date moment in time for which to return offsets, in
* units of milliseconds from January 1, 1970 0:00 GMT, either GMT
* time or local wall time, depending on `local'.
* @param local if true, `date' is local wall time; otherwise it
* is in GMT time.
* @param rawOffset output parameter to receive the raw offset, that
* is, the offset not including DST adjustments
* @param dstOffset output parameter to receive the DST offset,
* that is, the offset to be added to `rawOffset' to obtain the
* total offset between local and GMT time. If DST is not in
* effect, this value is zero; otherwise it is a positive value,
* typically one hour.
* @param ec input-output error code
* @stable ICU 3.8
*/
virtual void getOffset(UDate date, UBool local, int32_t& rawOffset,
int32_t& dstOffset, UErrorCode& ec) const;
/**
* Sets the TimeZone's raw GMT offset (i.e., the number of milliseconds to add
* to GMT to get local time, before taking daylight savings time into account).
*
* @param offsetMillis The new raw GMT offset for this time zone.
* @stable ICU 3.8
*/
virtual void setRawOffset(int32_t offsetMillis);
/**
* Returns the TimeZone's raw GMT offset (i.e., the number of milliseconds to add
* to GMT to get local time, before taking daylight savings time into account).
*
* @return The TimeZone's raw GMT offset.
* @stable ICU 3.8
*/
virtual int32_t getRawOffset(void) const;
/**
* Queries if this time zone uses daylight savings time.
* @return true if this time zone uses daylight savings time,
* false, otherwise.
* @stable ICU 3.8
*/
virtual UBool useDaylightTime(void) const;
/**
* Queries if the given date is in daylight savings time in
* this time zone.
* This method is wasteful since it creates a new GregorianCalendar and
* deletes it each time it is called. This is a deprecated method
* and provided only for Java compatibility.
*
* @param date the given UDate.
* @param status Output param filled in with success/error code.
* @return true if the given date is in daylight savings time,
* false, otherwise.
* @deprecated ICU 2.4. Use Calendar::inDaylightTime() instead.
*/
virtual UBool inDaylightTime(UDate date, UErrorCode& status) const;
/**
* Returns true if this zone has the same rule and offset as another zone.
* That is, if this zone differs only in ID, if at all.
* @param other the <code>TimeZone</code> object to be compared with
* @return true if the given zone is the same as this one,
* with the possible exception of the ID
* @stable ICU 3.8
*/
virtual UBool hasSameRules(const TimeZone& other) const;
/**
* Gets the first time zone transition after the base time.
* @param base The base time.
* @param inclusive Whether the base time is inclusive or not.
* @param result Receives the first transition after the base time.
* @return TRUE if the transition is found.
* @stable ICU 3.8
*/
virtual UBool getNextTransition(UDate base, UBool inclusive, TimeZoneTransition& result) const;
/**
* Gets the most recent time zone transition before the base time.
* @param base The base time.
* @param inclusive Whether the base time is inclusive or not.
* @param result Receives the most recent transition before the base time.
* @return TRUE if the transition is found.
* @stable ICU 3.8
*/
virtual UBool getPreviousTransition(UDate base, UBool inclusive, TimeZoneTransition& result) const;
/**
* Returns the number of <code>TimeZoneRule</code>s which represents time transitions,
* for this time zone, that is, all <code>TimeZoneRule</code>s for this time zone except
* <code>InitialTimeZoneRule</code>. The return value range is 0 or any positive value.
* @param status Receives error status code.
* @return The number of <code>TimeZoneRule</code>s representing time transitions.
* @stable ICU 3.8
*/
virtual int32_t countTransitionRules(UErrorCode& status) const;
/**
* Gets the <code>InitialTimeZoneRule</code> and the set of <code>TimeZoneRule</code>
* which represent time transitions for this time zone. On successful return,
* the argument initial points to non-NULL <code>InitialTimeZoneRule</code> and
* the array trsrules is filled with 0 or multiple <code>TimeZoneRule</code>
* instances up to the size specified by trscount. The results are referencing the
* rule instance held by this time zone instance. Therefore, after this time zone
* is destructed, they are no longer available.
* @param initial Receives the initial timezone rule
* @param trsrules Receives the timezone transition rules
* @param trscount On input, specify the size of the array 'transitions' receiving
* the timezone transition rules. On output, actual number of
* rules filled in the array will be set.
* @param status Receives error status code.
* @stable ICU 3.8
*/
virtual void getTimeZoneRules(const InitialTimeZoneRule*& initial,
const TimeZoneRule* trsrules[], int32_t& trscount, UErrorCode& status) const;
/**
* Get time zone offsets from local wall time.
* @internal
*/
virtual void getOffsetFromLocal(UDate date, int32_t nonExistingTimeOpt, int32_t duplicatedTimeOpt,
int32_t& rawOffset, int32_t& dstOffset, UErrorCode& status) const;
private:
void deleteRules(void);
void deleteTransitions(void);
UVector* copyRules(UVector* source);
TimeZoneRule* findRuleInFinal(UDate date, UBool local,
int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt) const;
UBool findNext(UDate base, UBool inclusive, UDate& time, TimeZoneRule*& from, TimeZoneRule*& to) const;
UBool findPrev(UDate base, UBool inclusive, UDate& time, TimeZoneRule*& from, TimeZoneRule*& to) const;
int32_t getLocalDelta(int32_t rawBefore, int32_t dstBefore, int32_t rawAfter, int32_t dstAfter,
int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt) const;
UDate getTransitionTime(Transition* transition, UBool local,
int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt) const;
void getOffsetInternal(UDate date, UBool local, int32_t NonExistingTimeOpt, int32_t DuplicatedTimeOpt,
int32_t& rawOffset, int32_t& dstOffset, UErrorCode& ec) const;
void completeConst(UErrorCode &status) const;
InitialTimeZoneRule *fInitialRule;
UVector *fHistoricRules;
UVector *fFinalRules;
UVector *fHistoricTransitions;
UBool fUpToDate;
public:
/**
* Return the class ID for this class. This is useful only for comparing to
* a return value from getDynamicClassID(). For example:
* <pre>
* . Base* polymorphic_pointer = createPolymorphicObject();
* . if (polymorphic_pointer->getDynamicClassID() ==
* . erived::getStaticClassID()) ...
* </pre>
* @return The class ID for all objects of this class.
* @stable ICU 3.8
*/
static UClassID U_EXPORT2 getStaticClassID(void);
/**
* Returns a unique class ID POLYMORPHICALLY. Pure virtual override. This
* method is to implement a simple version of RTTI, since not all C++
* compilers support genuine RTTI. Polymorphic operator==() and clone()
* methods call this method.
*
* @return The class ID for this object. All objects of a
* given class have the same class ID. Objects of
* other classes have different class IDs.
* @stable ICU 3.8
*/
virtual UClassID getDynamicClassID(void) const;
};
U_NAMESPACE_END
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // RBTZ_H
//eof
project/jni/icuuc/include/unicode/regex.h
-1849
View File
File diff suppressed because it is too large Load Diff
project/jni/icuuc/include/unicode/region.h
-225
View File
@@ -1,225 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2013, International Business Machines Corporation and others.
* All Rights Reserved.
*******************************************************************************
*/
#ifndef REGION_H
#define REGION_H
/**
* \file
* \brief C++ API: Region classes (territory containment)
*/
#include "unicode/utypes.h"
#include "unicode/uregion.h"
#if !UCONFIG_NO_FORMATTING
#ifndef U_HIDE_DRAFT_API
#include "unicode/uobject.h"
#include "unicode/uniset.h"
#include "unicode/unistr.h"
#include "unicode/strenum.h"
U_NAMESPACE_BEGIN
/**
* <code>Region</code> is the class representing a Unicode Region Code, also known as a
* Unicode Region Subtag, which is defined based upon the BCP 47 standard. We often think of
* "regions" as "countries" when defining the characteristics of a locale. Region codes There are different
* types of region codes that are important to distinguish.
* <p>
* Macroregion - A code for a "macro geographical (continental) region, geographical sub-region, or
* selected economic and other grouping" as defined in
* UN M.49 (http://unstats.un.org/unsd/methods/m49/m49regin.htm).
* These are typically 3-digit codes, but contain some 2-letter codes, such as the LDML code QO
* added for Outlying Oceania. Not all UNM.49 codes are defined in LDML, but most of them are.
* Macroregions are represented in ICU by one of three region types: WORLD ( region code 001 ),
* CONTINENTS ( regions contained directly by WORLD ), and SUBCONTINENTS ( things contained directly
* by a continent ).
* <p>
* TERRITORY - A Region that is not a Macroregion. These are typically codes for countries, but also
* include areas that are not separate countries, such as the code "AQ" for Antarctica or the code
* "HK" for Hong Kong (SAR China). Overseas dependencies of countries may or may not have separate
* codes. The codes are typically 2-letter codes aligned with the ISO 3166 standard, but BCP47 allows
* for the use of 3-digit codes in the future.
* <p>
* UNKNOWN - The code ZZ is defined by Unicode LDML for use to indicate that the Region is unknown,
* or that the value supplied as a region was invalid.
* <p>
* DEPRECATED - Region codes that have been defined in the past but are no longer in modern usage,
* usually due to a country splitting into multiple territories or changing its name.
* <p>
* GROUPING - A widely understood grouping of territories that has a well defined membership such
* that a region code has been assigned for it. Some of these are UNM.49 codes that do't fall into
* the world/continent/sub-continent hierarchy, while others are just well known groupings that have
* their own region code. Region "EU" (European Union) is one such region code that is a grouping.
* Groupings will never be returned by the getContainingRegion() API, since a different type of region
* ( WORLD, CONTINENT, or SUBCONTINENT ) will always be the containing region instead.
*
* The Region class is not intended for public subclassing.
*
* @author John Emmons
* @draft ICU 51
*/
class U_I18N_API Region : public UObject {
public:
/**
* Destructor.
* @draft ICU 51
*/
virtual ~Region();
/**
* Returns true if the two regions are equal.
* @draft ICU 51
*/
UBool operator==(const Region &that) const;
/**
* Returns true if the two regions are NOT equal; that is, if operator ==() returns false.
* @draft ICU 51
*/
UBool operator!=(const Region &that) const;
/**
* Returns a pointer to a Region using the given region code. The region code can be either 2-letter ISO code,
* 3-letter ISO code, UNM.49 numeric code, or other valid Unicode Region Code as defined by the LDML specification.
* The identifier will be canonicalized internally using the supplemental metadata as defined in the CLDR.
* If the region code is NULL or not recognized, the appropriate error code will be set ( U_ILLEGAL_ARGUMENT_ERROR )
* @draft ICU 51
*/
static const Region* U_EXPORT2 getInstance(const char *region_code, UErrorCode &status);
/**
* Returns a pointer to a Region using the given numeric region code. If the numeric region code is not recognized,
* the appropriate error code will be set ( U_ILLEGAL_ARGUMENT_ERROR ).
* @draft ICU 51
*/
static const Region* U_EXPORT2 getInstance (int32_t code, UErrorCode &status);
/**
* Returns an enumeration over the IDs of all known regions that match the given type.
* @draft ICU 51
*/
static StringEnumeration* U_EXPORT2 getAvailable(URegionType type);
/**
* Returns a pointer to the region that contains this region. Returns NULL if this region is code "001" (World)
* or "ZZ" (Unknown region). For example, calling this method with region "IT" (Italy) returns the
* region "039" (Southern Europe).
* @draft ICU 51
*/
const Region* getContainingRegion() const;
/**
* Return a pointer to the region that geographically contains this region and matches the given type,
* moving multiple steps up the containment chain if necessary. Returns NULL if no containing region can be found
* that matches the given type. Note: The URegionTypes = "URGN_GROUPING", "URGN_DEPRECATED", or "URGN_UNKNOWN"
* are not appropriate for use in this API. NULL will be returned in this case. For example, calling this method
* with region "IT" (Italy) for type "URGN_CONTINENT" returns the region "150" ( Europe ).
* @draft ICU 51
*/
const Region* getContainingRegion(URegionType type) const;
/**
* Return an enumeration over the IDs of all the regions that are immediate children of this region in the
* region hierarchy. These returned regions could be either macro regions, territories, or a mixture of the two,
* depending on the containment data as defined in CLDR. This API may return NULL if this region doesn't have
* any sub-regions. For example, calling this method with region "150" (Europe) returns an enumeration containing
* the various sub regions of Europe - "039" (Southern Europe) - "151" (Eastern Europe) - "154" (Northern Europe)
* and "155" (Western Europe).
* @draft ICU 51
*/
StringEnumeration* getContainedRegions() const;
/**
* Returns an enumeration over the IDs of all the regions that are children of this region anywhere in the region
* hierarchy and match the given type. This API may return an empty enumeration if this region doesn't have any
* sub-regions that match the given type. For example, calling this method with region "150" (Europe) and type
* "URGN_TERRITORY" returns a set containing all the territories in Europe ( "FR" (France) - "IT" (Italy) - "DE" (Germany) etc. )
* @draft ICU 51
*/
StringEnumeration* getContainedRegions( URegionType type ) const;
/**
* Returns true if this region contains the supplied other region anywhere in the region hierarchy.
* @draft ICU 51
*/
UBool contains(const Region &other) const;
/**
* For deprecated regions, return an enumeration over the IDs of the regions that are the preferred replacement
* regions for this region. Returns null for a non-deprecated region. For example, calling this method with region
* "SU" (Soviet Union) would return a list of the regions containing "RU" (Russia), "AM" (Armenia), "AZ" (Azerbaijan), etc...
* @draft ICU 51
*/
StringEnumeration* getPreferredValues() const;
/**
* Return this region's canonical region code.
* @draft ICU 51
*/
const char* getRegionCode() const;
/**
* Return this region's numeric code.
* Returns a negative value if the given region does not have a numeric code assigned to it.
* @draft ICU 51
*/
int32_t getNumericCode() const;
/**
* Returns the region type of this region.
* @draft ICU 51
*/
URegionType getType() const;
#ifndef U_HIDE_INTERNAL_API
/**
* Cleans up statically allocated memory.
* @internal
*/
static void cleanupRegionData();
#endif /* U_HIDE_INTERNAL_API */
private:
char id[4];
UnicodeString idStr;
int32_t code;
URegionType type;
Region *containingRegion;
UVector *containedRegions;
UVector *preferredValues;
/**
* Default Constructor. Internal - use factory methods only.
*/
Region();
/*
* Initializes the region data from the ICU resource bundles. The region data
* contains the basic relationships such as which regions are known, what the numeric
* codes are, any known aliases, and the territory containment data.
*
* If the region data has already loaded, then this method simply returns without doing
* anything meaningful.
*/
static void loadRegionData();
};
U_NAMESPACE_END
#endif /* U_HIDE_DRAFT_API */
#endif /* #if !UCONFIG_NO_FORMATTING */
#endif // REGION_H
//eof
project/jni/icuuc/include/unicode/rep.h
-261
View File
@@ -1,261 +0,0 @@
/*
**************************************************************************
* Copyright (C) 1999-2012, International Business Machines Corporation and
* others. All Rights Reserved.
**************************************************************************
* Date Name Description
* 11/17/99 aliu Creation. Ported from java. Modified to
* match current UnicodeString API. Forced
* to use name "handleReplaceBetween" because
* of existing methods in UnicodeString.
**************************************************************************
*/
#ifndef REP_H
#define REP_H
#include "unicode/uobject.h"
/**
* \file
* \brief C++ API: Replaceable String
*/
U_NAMESPACE_BEGIN
class UnicodeString;
/**
* <code>Replaceable</code> is an abstract base class representing a
* string of characters that supports the replacement of a range of
* itself with a new string of characters. It is used by APIs that
* change a piece of text while retaining metadata. Metadata is data
* other than the Unicode characters returned by char32At(). One
* example of metadata is style attributes; another is an edit
* history, marking each character with an author and revision number.
*
* <p>An implicit aspect of the <code>Replaceable</code> API is that
* during a replace operation, new characters take on the metadata of
* the old characters. For example, if the string "the <b>bold</b>
* font" has range (4, 8) replaced with "strong", then it becomes "the
* <b>strong</b> font".
*
* <p><code>Replaceable</code> specifies ranges using a start
* offset and a limit offset. The range of characters thus specified
* includes the characters at offset start..limit-1. That is, the
* start offset is inclusive, and the limit offset is exclusive.
*
* <p><code>Replaceable</code> also includes API to access characters
* in the string: <code>length()</code>, <code>charAt()</code>,
* <code>char32At()</code>, and <code>extractBetween()</code>.
*
* <p>For a subclass to support metadata, typical behavior of
* <code>replace()</code> is the following:
* <ul>
* <li>Set the metadata of the new text to the metadata of the first
* character replaced</li>
* <li>If no characters are replaced, use the metadata of the
* previous character</li>
* <li>If there is no previous character (i.e. start == 0), use the
* following character</li>
* <li>If there is no following character (i.e. the replaceable was
* empty), use default metadata.<br>
* <li>If the code point U+FFFF is seen, it should be interpreted as
* a special marker having no metadata<li>
* </li>
* </ul>
* If this is not the behavior, the subclass should document any differences.
* @author Alan Liu
* @stable ICU 2.0
*/
class U_COMMON_API Replaceable : public UObject {
public:
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~Replaceable();
/**
* Returns the number of 16-bit code units in the text.
* @return number of 16-bit code units in text
* @stable ICU 1.8
*/
inline int32_t length() const;
/**
* Returns the 16-bit code unit at the given offset into the text.
* @param offset an integer between 0 and <code>length()</code>-1
* inclusive
* @return 16-bit code unit of text at given offset
* @stable ICU 1.8
*/
inline UChar charAt(int32_t offset) const;
/**
* Returns the 32-bit code point at the given 16-bit offset into
* the text. This assumes the text is stored as 16-bit code units
* with surrogate pairs intermixed. If the offset of a leading or
* trailing code unit of a surrogate pair is given, return the
* code point of the surrogate pair.
*
* @param offset an integer between 0 and <code>length()</code>-1
* inclusive
* @return 32-bit code point of text at given offset
* @stable ICU 1.8
*/
inline UChar32 char32At(int32_t offset) const;
/**
* Copies characters in the range [<tt>start</tt>, <tt>limit</tt>)
* into the UnicodeString <tt>target</tt>.
* @param start offset of first character which will be copied
* @param limit offset immediately following the last character to
* be copied
* @param target UnicodeString into which to copy characters.
* @return A reference to <TT>target</TT>
* @stable ICU 2.1
*/
virtual void extractBetween(int32_t start,
int32_t limit,
UnicodeString& target) const = 0;
/**
* Replaces a substring of this object with the given text. If the
* characters being replaced have metadata, the new characters
* that replace them should be given the same metadata.
*
* <p>Subclasses must ensure that if the text between start and
* limit is equal to the replacement text, that replace has no
* effect. That is, any metadata
* should be unaffected. In addition, subclasses are encouraged to
* check for initial and trailing identical characters, and make a
* smaller replacement if possible. This will preserve as much
* metadata as possible.
* @param start the beginning index, inclusive; <code>0 <= start
* <= limit</code>.
* @param limit the ending index, exclusive; <code>start <= limit
* <= length()</code>.
* @param text the text to replace characters <code>start</code>
* to <code>limit - 1</code>
* @stable ICU 2.0
*/
virtual void handleReplaceBetween(int32_t start,
int32_t limit,
const UnicodeString& text) = 0;
// Note: All other methods in this class take the names of
// existing UnicodeString methods. This method is the exception.
// It is named differently because all replace methods of
// UnicodeString return a UnicodeString&. The 'between' is
// required in order to conform to the UnicodeString naming
// convention; API taking start/length are named <operation>, and
// those taking start/limit are named <operationBetween>. The
// 'handle' is added because 'replaceBetween' and
// 'doReplaceBetween' are already taken.
/**
* Copies a substring of this object, retaining metadata.
* This method is used to duplicate or reorder substrings.
* The destination index must not overlap the source range.
*
* @param start the beginning index, inclusive; <code>0 <= start <=
* limit</code>.
* @param limit the ending index, exclusive; <code>start <= limit <=
* length()</code>.
* @param dest the destination index. The characters from
* <code>start..limit-1</code> will be copied to <code>dest</code>.
* Implementations of this method may assume that <code>dest <= start ||
* dest >= limit</code>.
* @stable ICU 2.0
*/
virtual void copy(int32_t start, int32_t limit, int32_t dest) = 0;
/**
* Returns true if this object contains metadata. If a
* Replaceable object has metadata, calls to the Replaceable API
* must be made so as to preserve metadata. If it does not, calls
* to the Replaceable API may be optimized to improve performance.
* The default implementation returns true.
* @return true if this object contains metadata
* @stable ICU 2.2
*/
virtual UBool hasMetaData() const;
/**
* Clone this object, an instance of a subclass of Replaceable.
* Clones can be used concurrently in multiple threads.
* If a subclass does not implement clone(), or if an error occurs,
* then NULL is returned.
* The clone functions in all subclasses return a pointer to a Replaceable
* because some compilers do not support covariant (same-as-this)
* return types; cast to the appropriate subclass if necessary.
* The caller must delete the clone.
*
* @return a clone of this object
*
* @see getDynamicClassID
* @stable ICU 2.6
*/
virtual Replaceable *clone() const;
protected:
/**
* Default constructor.
* @stable ICU 2.4
*/
inline Replaceable();
/*
* Assignment operator not declared. The compiler will provide one
* which does nothing since this class does not contain any data members.
* API/code coverage may show the assignment operator as present and
* untested - ignore.
* Subclasses need this assignment operator if they use compiler-provided
* assignment operators of their own. An alternative to not declaring one
* here would be to declare and empty-implement a protected or public one.
Replaceable &Replaceable::operator=(const Replaceable &);
*/
/**
* Virtual version of length().
* @stable ICU 2.4
*/
virtual int32_t getLength() const = 0;
/**
* Virtual version of charAt().
* @stable ICU 2.4
*/
virtual UChar getCharAt(int32_t offset) const = 0;
/**
* Virtual version of char32At().
* @stable ICU 2.4
*/
virtual UChar32 getChar32At(int32_t offset) const = 0;
};
inline Replaceable::Replaceable() {}
inline int32_t
Replaceable::length() const {
return getLength();
}
inline UChar
Replaceable::charAt(int32_t offset) const {
return getCharAt(offset);
}
inline UChar32
Replaceable::char32At(int32_t offset) const {
return getChar32At(offset);
}
// There is no rep.cpp, see unistr.cpp for Replaceable function implementations.
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/resbund.h
-490
View File
@@ -1,490 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 1996-2013, International Business Machines Corporation
* and others. All Rights Reserved.
*
******************************************************************************
*
* File resbund.h
*
* CREATED BY
* Richard Gillam
*
* Modification History:
*
* Date Name Description
* 2/5/97 aliu Added scanForLocaleInFile. Added
* constructor which attempts to read resource bundle
* from a specific file, without searching other files.
* 2/11/97 aliu Added UErrorCode return values to constructors. Fixed
* infinite loops in scanForFile and scanForLocale.
* Modified getRawResourceData to not delete storage
* in localeData and resourceData which it doesn't own.
* Added Mac compatibility #ifdefs for tellp() and
* ios::nocreate.
* 2/18/97 helena Updated with 100% documentation coverage.
* 3/13/97 aliu Rewrote to load in entire resource bundle and store
* it as a Hashtable of ResourceBundleData objects.
* Added state table to govern parsing of files.
* Modified to load locale index out of new file
* distinct from default.txt.
* 3/25/97 aliu Modified to support 2-d arrays, needed for timezone
* data. Added support for custom file suffixes. Again,
* needed to support timezone data.
* 4/7/97 aliu Cleaned up.
* 03/02/99 stephen Removed dependency on FILE*.
* 03/29/99 helena Merged Bertrand and Stephen's changes.
* 06/11/99 stephen Removed parsing of .txt files.
* Reworked to use new binary format.
* Cleaned up.
* 06/14/99 stephen Removed methods taking a filename suffix.
* 11/09/99 weiv Added getLocale(), fRealLocale, removed fRealLocaleID
******************************************************************************
*/
#ifndef RESBUND_H
#define RESBUND_H
#include "unicode/utypes.h"
#include "unicode/uobject.h"
#include "unicode/ures.h"
#include "unicode/unistr.h"
#include "unicode/locid.h"
/**
* \file
* \brief C++ API: Resource Bundle
*/
U_NAMESPACE_BEGIN
/**
* A class representing a collection of resource information pertaining to a given
* locale. A resource bundle provides a way of accessing locale- specfic information in
* a data file. You create a resource bundle that manages the resources for a given
* locale and then ask it for individual resources.
* <P>
* Resource bundles in ICU4C are currently defined using text files which conform to the following
* <a href="http://source.icu-project.org/repos/icu/icuhtml/trunk/design/bnf_rb.txt">BNF definition</a>.
* More on resource bundle concepts and syntax can be found in the
* <a href="http://icu-project.org/userguide/ResourceManagement.html">Users Guide</a>.
* <P>
*
* The ResourceBundle class is not suitable for subclassing.
*
* @stable ICU 2.0
*/
class U_COMMON_API ResourceBundle : public UObject {
public:
/**
* Constructor
*
* @param packageName The packageName and locale together point to an ICU udata object,
* as defined by <code> udata_open( packageName, "res", locale, err) </code>
* or equivalent. Typically, packageName will refer to a (.dat) file, or to
* a package registered with udata_setAppData(). Using a full file or directory
* pathname for packageName is deprecated.
* @param locale This is the locale this resource bundle is for. To get resources
* for the French locale, for example, you would create a
* ResourceBundle passing Locale::FRENCH for the "locale" parameter,
* and all subsequent calls to that resource bundle will return
* resources that pertain to the French locale. If the caller doesn't
* pass a locale parameter, the default locale for the system (as
* returned by Locale::getDefault()) will be used.
* @param err The Error Code.
* The UErrorCode& err parameter is used to return status information to the user. To
* check whether the construction succeeded or not, you should check the value of
* U_SUCCESS(err). If you wish more detailed information, you can check for
* informational error results which still indicate success. U_USING_FALLBACK_WARNING
* indicates that a fall back locale was used. For example, 'de_CH' was requested,
* but nothing was found there, so 'de' was used. U_USING_DEFAULT_WARNING indicates that
* the default locale data was used; neither the requested locale nor any of its
* fall back locales could be found.
* @stable ICU 2.0
*/
ResourceBundle(const UnicodeString& packageName,
const Locale& locale,
UErrorCode& err);
/**
* Construct a resource bundle for the default bundle in the specified package.
*
* @param packageName The packageName and locale together point to an ICU udata object,
* as defined by <code> udata_open( packageName, "res", locale, err) </code>
* or equivalent. Typically, packageName will refer to a (.dat) file, or to
* a package registered with udata_setAppData(). Using a full file or directory
* pathname for packageName is deprecated.
* @param err A UErrorCode value
* @stable ICU 2.0
*/
ResourceBundle(const UnicodeString& packageName,
UErrorCode& err);
/**
* Construct a resource bundle for the ICU default bundle.
*
* @param err A UErrorCode value
* @stable ICU 2.0
*/
ResourceBundle(UErrorCode &err);
/**
* Standard constructor, onstructs a resource bundle for the locale-specific
* bundle in the specified package.
*
* @param packageName The packageName and locale together point to an ICU udata object,
* as defined by <code> udata_open( packageName, "res", locale, err) </code>
* or equivalent. Typically, packageName will refer to a (.dat) file, or to
* a package registered with udata_setAppData(). Using a full file or directory
* pathname for packageName is deprecated.
* NULL is used to refer to ICU data.
* @param locale The locale for which to open a resource bundle.
* @param err A UErrorCode value
* @stable ICU 2.0
*/
ResourceBundle(const char* packageName,
const Locale& locale,
UErrorCode& err);
/**
* Copy constructor.
*
* @param original The resource bundle to copy.
* @stable ICU 2.0
*/
ResourceBundle(const ResourceBundle &original);
/**
* Constructor from a C UResourceBundle. The resource bundle is
* copied and not adopted. ures_close will still need to be used on the
* original resource bundle.
*
* @param res A pointer to the C resource bundle.
* @param status A UErrorCode value.
* @stable ICU 2.0
*/
ResourceBundle(UResourceBundle *res,
UErrorCode &status);
/**
* Assignment operator.
*
* @param other The resource bundle to copy.
* @stable ICU 2.0
*/
ResourceBundle&
operator=(const ResourceBundle& other);
/** Destructor.
* @stable ICU 2.0
*/
virtual ~ResourceBundle();
/**
* Clone this object.
* Clones can be used concurrently in multiple threads.
* If an error occurs, then NULL is returned.
* The caller must delete the clone.
*
* @return a clone of this object
*
* @see getDynamicClassID
* @stable ICU 2.8
*/
ResourceBundle *clone() const;
/**
* Returns the size of a resource. Size for scalar types is always 1, and for vector/table types is
* the number of child resources.
* @warning Integer array is treated as a scalar type. There are no
* APIs to access individual members of an integer array. It
* is always returned as a whole.
*
* @return number of resources in a given resource.
* @stable ICU 2.0
*/
int32_t
getSize(void) const;
/**
* returns a string from a string resource type
*
* @param status fills in the outgoing error code
* could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found
* could be a warning
* e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT>
* @return a pointer to a zero-terminated UChar array which lives in a memory mapped/DLL file.
* @stable ICU 2.0
*/
UnicodeString
getString(UErrorCode& status) const;
/**
* returns a binary data from a resource. Can be used at most primitive resource types (binaries,
* strings, ints)
*
* @param len fills in the length of resulting byte chunk
* @param status fills in the outgoing error code
* could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found
* could be a warning
* e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT>
* @return a pointer to a chunk of unsigned bytes which live in a memory mapped/DLL file.
* @stable ICU 2.0
*/
const uint8_t*
getBinary(int32_t& len, UErrorCode& status) const;
/**
* returns an integer vector from a resource.
*
* @param len fills in the length of resulting integer vector
* @param status fills in the outgoing error code
* could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found
* could be a warning
* e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT>
* @return a pointer to a vector of integers that lives in a memory mapped/DLL file.
* @stable ICU 2.0
*/
const int32_t*
getIntVector(int32_t& len, UErrorCode& status) const;
/**
* returns an unsigned integer from a resource.
* This integer is originally 28 bits.
*
* @param status fills in the outgoing error code
* could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found
* could be a warning
* e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT>
* @return an unsigned integer value
* @stable ICU 2.0
*/
uint32_t
getUInt(UErrorCode& status) const;
/**
* returns a signed integer from a resource.
* This integer is originally 28 bit and the sign gets propagated.
*
* @param status fills in the outgoing error code
* could be <TT>U_MISSING_RESOURCE_ERROR</TT> if the key is not found
* could be a warning
* e.g.: <TT>U_USING_FALLBACK_WARNING</TT>,<TT>U_USING_DEFAULT_WARNING </TT>
* @return a signed integer value
* @stable ICU 2.0
*/
int32_t
getInt(UErrorCode& status) const;
/**
* Checks whether the resource has another element to iterate over.
*
* @return TRUE if there are more elements, FALSE if there is no more elements
* @stable ICU 2.0
*/
UBool
hasNext(void) const;
/**
* Resets the internal context of a resource so that iteration starts from the first element.
*
* @stable ICU 2.0
*/
void
resetIterator(void);
/**
* Returns the key associated with this resource. Not all the resources have a key - only
* those that are members of a table.
*
* @return a key associated to this resource, or NULL if it doesn't have a key
* @stable ICU 2.0
*/
const char*
getKey(void) const;
/**
* Gets the locale ID of the resource bundle as a string.
* Same as getLocale().getName() .
*
* @return the locale ID of the resource bundle as a string
* @stable ICU 2.0
*/
const char*
getName(void) const;
/**
* Returns the type of a resource. Available types are defined in enum UResType
*
* @return type of the given resource.
* @stable ICU 2.0
*/
UResType
getType(void) const;
/**
* Returns the next resource in a given resource or NULL if there are no more resources
*
* @param status fills in the outgoing error code
* @return ResourceBundle object.
* @stable ICU 2.0
*/
ResourceBundle
getNext(UErrorCode& status);
/**
* Returns the next string in a resource or NULL if there are no more resources
* to iterate over.
*
* @param status fills in the outgoing error code
* @return an UnicodeString object.
* @stable ICU 2.0
*/
UnicodeString
getNextString(UErrorCode& status);
/**
* Returns the next string in a resource or NULL if there are no more resources
* to iterate over.
*
* @param key fill in for key associated with this string
* @param status fills in the outgoing error code
* @return an UnicodeString object.
* @stable ICU 2.0
*/
UnicodeString
getNextString(const char ** key,
UErrorCode& status);
/**
* Returns the resource in a resource at the specified index.
*
* @param index an index to the wanted resource.
* @param status fills in the outgoing error code
* @return ResourceBundle object. If there is an error, resource is invalid.
* @stable ICU 2.0
*/
ResourceBundle
get(int32_t index,
UErrorCode& status) const;
/**
* Returns the string in a given resource at the specified index.
*
* @param index an index to the wanted string.
* @param status fills in the outgoing error code
* @return an UnicodeString object. If there is an error, string is bogus
* @stable ICU 2.0
*/
UnicodeString
getStringEx(int32_t index,
UErrorCode& status) const;
/**
* Returns a resource in a resource that has a given key. This procedure works only with table
* resources.
*
* @param key a key associated with the wanted resource
* @param status fills in the outgoing error code.
* @return ResourceBundle object. If there is an error, resource is invalid.
* @stable ICU 2.0
*/
ResourceBundle
get(const char* key,
UErrorCode& status) const;
/**
* Returns a string in a resource that has a given key. This procedure works only with table
* resources.
*
* @param key a key associated with the wanted string
* @param status fills in the outgoing error code
* @return an UnicodeString object. If there is an error, string is bogus
* @stable ICU 2.0
*/
UnicodeString
getStringEx(const char* key,
UErrorCode& status) const;
#ifndef U_HIDE_DEPRECATED_API
/**
* Return the version number associated with this ResourceBundle as a string. Please
* use getVersion, as this method is going to be deprecated.
*
* @return A version number string as specified in the resource bundle or its parent.
* The caller does not own this string.
* @see getVersion
* @deprecated ICU 2.8 Use getVersion instead.
*/
const char*
getVersionNumber(void) const;
#endif /* U_HIDE_DEPRECATED_API */
/**
* Return the version number associated with this ResourceBundle as a UVersionInfo array.
*
* @param versionInfo A UVersionInfo array that is filled with the version number
* as specified in the resource bundle or its parent.
* @stable ICU 2.0
*/
void
getVersion(UVersionInfo versionInfo) const;
#ifndef U_HIDE_DEPRECATED_API
/**
* Return the Locale associated with this ResourceBundle.
*
* @return a Locale object
* @deprecated ICU 2.8 Use getLocale(ULocDataLocaleType type, UErrorCode &status) overload instead.
*/
const Locale&
getLocale(void) const;
#endif /* U_HIDE_DEPRECATED_API */
/**
* Return the Locale associated with this ResourceBundle.
* @param type You can choose between requested, valid and actual
* locale. For description see the definition of
* ULocDataLocaleType in uloc.h
* @param status just for catching illegal arguments
*
* @return a Locale object
* @stable ICU 2.8
*/
const Locale
getLocale(ULocDataLocaleType type, UErrorCode &status) const;
#ifndef U_HIDE_INTERNAL_API
/**
* This API implements multilevel fallback
* @internal
*/
ResourceBundle
getWithFallback(const char* key, UErrorCode& status);
#endif /* U_HIDE_INTERNAL_API */
/**
* ICU "poor man's RTTI", returns a UClassID for the actual class.
*
* @stable ICU 2.2
*/
virtual UClassID getDynamicClassID() const;
/**
* ICU "poor man's RTTI", returns a UClassID for this class.
*
* @stable ICU 2.2
*/
static UClassID U_EXPORT2 getStaticClassID();
private:
ResourceBundle(); // default constructor not implemented
UResourceBundle *fResource;
void constructForLocale(const UnicodeString& path, const Locale& locale, UErrorCode& error);
Locale *fLocale;
};
U_NAMESPACE_END
#endif
project/jni/icuuc/include/unicode/schriter.h
-187
View File
@@ -1,187 +0,0 @@
/*
******************************************************************************
*
* Copyright (C) 1998-2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
******************************************************************************
*
* File schriter.h
*
* Modification History:
*
* Date Name Description
* 05/05/99 stephen Cleaned up.
******************************************************************************
*/
#ifndef SCHRITER_H
#define SCHRITER_H
#include "unicode/utypes.h"
#include "unicode/chariter.h"
#include "unicode/uchriter.h"
/**
* \file
* \brief C++ API: String Character Iterator
*/
U_NAMESPACE_BEGIN
/**
* A concrete subclass of CharacterIterator that iterates over the
* characters (code units or code points) in a UnicodeString.
* It's possible not only to create an
* iterator that iterates over an entire UnicodeString, but also to
* create one that iterates over only a subrange of a UnicodeString
* (iterators over different subranges of the same UnicodeString don't
* compare equal).
* @see CharacterIterator
* @see ForwardCharacterIterator
* @stable ICU 2.0
*/
class U_COMMON_API StringCharacterIterator : public UCharCharacterIterator {
public:
/**
* Create an iterator over the UnicodeString referred to by "textStr".
* The UnicodeString object is copied.
* The iteration range is the whole string, and the starting position is 0.
* @param textStr The unicode string used to create an iterator
* @stable ICU 2.0
*/
StringCharacterIterator(const UnicodeString& textStr);
/**
* Create an iterator over the UnicodeString referred to by "textStr".
* The iteration range is the whole string, and the starting
* position is specified by "textPos". If "textPos" is outside the valid
* iteration range, the behavior of this object is undefined.
* @param textStr The unicode string used to create an iterator
* @param textPos The starting position of the iteration
* @stable ICU 2.0
*/
StringCharacterIterator(const UnicodeString& textStr,
int32_t textPos);
/**
* Create an iterator over the UnicodeString referred to by "textStr".
* The UnicodeString object is copied.
* The iteration range begins with the code unit specified by
* "textBegin" and ends with the code unit BEFORE the code unit specfied
* by "textEnd". The starting position is specified by "textPos". If
* "textBegin" and "textEnd" don't form a valid range on "text" (i.e.,
* textBegin >= textEnd or either is negative or greater than text.size()),
* or "textPos" is outside the range defined by "textBegin" and "textEnd",
* the behavior of this iterator is undefined.
* @param textStr The unicode string used to create the StringCharacterIterator
* @param textBegin The begin position of the iteration range
* @param textEnd The end position of the iteration range
* @param textPos The starting position of the iteration
* @stable ICU 2.0
*/
StringCharacterIterator(const UnicodeString& textStr,
int32_t textBegin,
int32_t textEnd,
int32_t textPos);
/**
* Copy constructor. The new iterator iterates over the same range
* of the same string as "that", and its initial position is the
* same as "that"'s current position.
* The UnicodeString object in "that" is copied.
* @param that The StringCharacterIterator to be copied
* @stable ICU 2.0
*/
StringCharacterIterator(const StringCharacterIterator& that);
/**
* Destructor.
* @stable ICU 2.0
*/
virtual ~StringCharacterIterator();
/**
* Assignment operator. *this is altered to iterate over the same
* range of the same string as "that", and refers to the same
* character within that string as "that" does.
* @param that The object to be copied.
* @return the newly created object.
* @stable ICU 2.0
*/
StringCharacterIterator&
operator=(const StringCharacterIterator& that);
/**
* Returns true if the iterators iterate over the same range of the
* same string and are pointing at the same character.
* @param that The ForwardCharacterIterator to be compared for equality
* @return true if the iterators iterate over the same range of the
* same string and are pointing at the same character.
* @stable ICU 2.0
*/
virtual UBool operator==(const ForwardCharacterIterator& that) const;
/**
* Returns a new StringCharacterIterator referring to the same
* character in the same range of the same string as this one. The
* caller must delete the new iterator.
* @return the newly cloned object.
* @stable ICU 2.0
*/
virtual CharacterIterator* clone(void) const;
/**
* Sets the iterator to iterate over the provided string.
* @param newText The string to be iterated over
* @stable ICU 2.0
*/
void setText(const UnicodeString& newText);
/**
* Copies the UnicodeString under iteration into the UnicodeString
* referred to by "result". Even if this iterator iterates across
* only a part of this string, the whole string is copied.
* @param result Receives a copy of the text under iteration.
* @stable ICU 2.0
*/
virtual void getText(UnicodeString& result);
/**
* Return a class ID for this object (not really public)
* @return a class ID for this object.
* @stable ICU 2.0
*/
virtual UClassID getDynamicClassID(void) const;
/**
* Return a class ID for this class (not really public)
* @return a class ID for this class
* @stable ICU 2.0
*/
static UClassID U_EXPORT2 getStaticClassID(void);
protected:
/**
* Default constructor, iteration over empty string.
* @stable ICU 2.0
*/
StringCharacterIterator();
/**
* Sets the iterator to iterate over the provided string.
* @param newText The string to be iterated over
* @param newTextLength The length of the String
* @stable ICU 2.0
*/
void setText(const UChar* newText, int32_t newTextLength);
/**
* Copy of the iterated string object.
* @stable ICU 2.0
*/
UnicodeString text;
};
U_NAMESPACE_END
#endif

Some files were not shown because too many files have changed in this diff Show More