Added Python (Thanks to Beholder) - it fails to build properly using my build system,

so there's a precompiled binary included, with a hack in Android.mk to make it work on NDK r4b

project/jni/python/src/Objects/stringlib/README.txt

@@ -0,0 +1,34 @@
+bits shared by the stringobject and unicodeobject implementations (and
+possibly other modules, in a not too distant future).
+
+the stuff in here is included into relevant places; see the individual
+source files for details.
+
+--------------------------------------------------------------------
+the following defines used by the different modules:
+
+STRINGLIB_CHAR
+
+    the type used to hold a character (char or Py_UNICODE)
+
+STRINGLIB_EMPTY
+
+    a PyObject representing the empty string
+
+int STRINGLIB_CMP(STRINGLIB_CHAR*, STRINGLIB_CHAR*, Py_ssize_t)
+
+    compares two strings. returns 0 if they match, and non-zero if not.
+
+Py_ssize_t STRINGLIB_LEN(PyObject*)
+
+    returns the length of the given string object (which must be of the
+    right type)
+
+PyObject* STRINGLIB_NEW(STRINGLIB_CHAR*, Py_ssize_t)
+
+    creates a new string object
+
+STRINGLIB_CHAR* STRINGLIB_STR(PyObject*)
+
+    returns the pointer to the character data for the given string
+    object (which must be of the right type)

project/jni/python/src/Objects/stringlib/count.h

@@ -0,0 +1,36 @@
+/* stringlib: count implementation */
+
+#ifndef STRINGLIB_COUNT_H
+#define STRINGLIB_COUNT_H
+
+#ifndef STRINGLIB_FASTSEARCH_H
+#error must include "stringlib/fastsearch.h" before including this module
+#endif
+
+Py_LOCAL_INLINE(Py_ssize_t)
+stringlib_count(const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+                const STRINGLIB_CHAR* sub, Py_ssize_t sub_len)
+{
+    Py_ssize_t count;
+
+    if (str_len < 0)
+        return 0; /* start > len(str) */
+    if (sub_len == 0)
+        return str_len + 1;
+
+    count = fastsearch(str, str_len, sub, sub_len, FAST_COUNT);
+
+    if (count < 0)
+        count = 0; /* no match */
+
+    return count;
+}
+
+#endif
+
+/*
+Local variables:
+c-basic-offset: 4
+indent-tabs-mode: nil
+End:
+*/

project/jni/python/src/Objects/stringlib/ctype.h

@@ -0,0 +1,110 @@
+/* NOTE: this API is -ONLY- for use with single byte character strings. */
+/* Do not use it with Unicode. */
+
+#include "bytes_methods.h"
+
+static PyObject*
+stringlib_isspace(PyObject *self)
+{
+    return _Py_bytes_isspace(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+static PyObject*
+stringlib_isalpha(PyObject *self)
+{
+    return _Py_bytes_isalpha(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+static PyObject*
+stringlib_isalnum(PyObject *self)
+{
+    return _Py_bytes_isalnum(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+static PyObject*
+stringlib_isdigit(PyObject *self)
+{
+    return _Py_bytes_isdigit(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+static PyObject*
+stringlib_islower(PyObject *self)
+{
+    return _Py_bytes_islower(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+static PyObject*
+stringlib_isupper(PyObject *self)
+{
+    return _Py_bytes_isupper(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+static PyObject*
+stringlib_istitle(PyObject *self)
+{
+    return _Py_bytes_istitle(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+}
+
+
+/* functions that return a new object partially translated by ctype funcs: */
+
+static PyObject*
+stringlib_lower(PyObject *self)
+{
+    PyObject* newobj;
+    newobj = STRINGLIB_NEW(NULL, STRINGLIB_LEN(self));
+    if (!newobj)
+            return NULL;
+    _Py_bytes_lower(STRINGLIB_STR(newobj), STRINGLIB_STR(self),
+                 STRINGLIB_LEN(self));
+    return newobj;
+}
+
+static PyObject*
+stringlib_upper(PyObject *self)
+{
+    PyObject* newobj;
+    newobj = STRINGLIB_NEW(NULL, STRINGLIB_LEN(self));
+    if (!newobj)
+            return NULL;
+    _Py_bytes_upper(STRINGLIB_STR(newobj), STRINGLIB_STR(self),
+                 STRINGLIB_LEN(self));
+    return newobj;
+}
+
+static PyObject*
+stringlib_title(PyObject *self)
+{
+    PyObject* newobj;
+    newobj = STRINGLIB_NEW(NULL, STRINGLIB_LEN(self));
+    if (!newobj)
+            return NULL;
+    _Py_bytes_title(STRINGLIB_STR(newobj), STRINGLIB_STR(self),
+                 STRINGLIB_LEN(self));
+    return newobj;
+}
+
+static PyObject*
+stringlib_capitalize(PyObject *self)
+{
+    PyObject* newobj;
+    newobj = STRINGLIB_NEW(NULL, STRINGLIB_LEN(self));
+    if (!newobj)
+            return NULL;
+    _Py_bytes_capitalize(STRINGLIB_STR(newobj), STRINGLIB_STR(self),
+                      STRINGLIB_LEN(self));
+    return newobj;
+}
+
+static PyObject*
+stringlib_swapcase(PyObject *self)
+{
+    PyObject* newobj;
+    newobj = STRINGLIB_NEW(NULL, STRINGLIB_LEN(self));
+    if (!newobj)
+            return NULL;
+    _Py_bytes_swapcase(STRINGLIB_STR(newobj), STRINGLIB_STR(self),
+                    STRINGLIB_LEN(self));
+    return newobj;
+}
+

project/jni/python/src/Objects/stringlib/fastsearch.h

@@ -0,0 +1,104 @@
+/* stringlib: fastsearch implementation */
+
+#ifndef STRINGLIB_FASTSEARCH_H
+#define STRINGLIB_FASTSEARCH_H
+
+/* fast search/count implementation, based on a mix between boyer-
+   moore and horspool, with a few more bells and whistles on the top.
+   for some more background, see: http://effbot.org/stringlib */
+
+/* note: fastsearch may access s[n], which isn't a problem when using
+   Python's ordinary string types, but may cause problems if you're
+   using this code in other contexts.  also, the count mode returns -1
+   if there cannot possible be a match in the target string, and 0 if
+   it has actually checked for matches, but didn't find any.  callers
+   beware! */
+
+#define FAST_COUNT 0
+#define FAST_SEARCH 1
+
+Py_LOCAL_INLINE(Py_ssize_t)
+fastsearch(const STRINGLIB_CHAR* s, Py_ssize_t n,
+           const STRINGLIB_CHAR* p, Py_ssize_t m,
+           int mode)
+{
+    long mask;
+    Py_ssize_t skip, count = 0;
+    Py_ssize_t i, j, mlast, w;
+
+    w = n - m;
+
+    if (w < 0)
+        return -1;
+
+    /* look for special cases */
+    if (m <= 1) {
+        if (m <= 0)
+            return -1;
+        /* use special case for 1-character strings */
+        if (mode == FAST_COUNT) {
+            for (i = 0; i < n; i++)
+                if (s[i] == p[0])
+                    count++;
+            return count;
+        } else {
+            for (i = 0; i < n; i++)
+                if (s[i] == p[0])
+                    return i;
+        }
+        return -1;
+    }
+
+    mlast = m - 1;
+
+    /* create compressed boyer-moore delta 1 table */
+    skip = mlast - 1;
+    /* process pattern[:-1] */
+    for (mask = i = 0; i < mlast; i++) {
+        mask |= (1 << (p[i] & 0x1F));
+        if (p[i] == p[mlast])
+            skip = mlast - i - 1;
+    }
+    /* process pattern[-1] outside the loop */
+    mask |= (1 << (p[mlast] & 0x1F));
+
+    for (i = 0; i <= w; i++) {
+        /* note: using mlast in the skip path slows things down on x86 */
+        if (s[i+m-1] == p[m-1]) {
+            /* candidate match */
+            for (j = 0; j < mlast; j++)
+                if (s[i+j] != p[j])
+                    break;
+            if (j == mlast) {
+                /* got a match! */
+                if (mode != FAST_COUNT)
+                    return i;
+                count++;
+                i = i + mlast;
+                continue;
+            }
+            /* miss: check if next character is part of pattern */
+            if (!(mask & (1 << (s[i+m] & 0x1F))))
+                i = i + m;
+            else
+                i = i + skip;
+        } else {
+            /* skip: check if next character is part of pattern */
+            if (!(mask & (1 << (s[i+m] & 0x1F))))
+                i = i + m;
+        }
+    }
+
+    if (mode != FAST_COUNT)
+        return -1;
+    return count;
+}
+
+#endif
+
+/*
+Local variables:
+c-basic-offset: 4
+indent-tabs-mode: nil
+End:
+*/

project/jni/python/src/Objects/stringlib/find.h

@@ -0,0 +1,162 @@
+/* stringlib: find/index implementation */
+
+#ifndef STRINGLIB_FIND_H
+#define STRINGLIB_FIND_H
+
+#ifndef STRINGLIB_FASTSEARCH_H
+#error must include "stringlib/fastsearch.h" before including this module
+#endif
+
+Py_LOCAL_INLINE(Py_ssize_t)
+stringlib_find(const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+               const STRINGLIB_CHAR* sub, Py_ssize_t sub_len,
+               Py_ssize_t offset)
+{
+    Py_ssize_t pos;
+
+    if (str_len < 0)
+        return -1;
+    if (sub_len == 0)
+        return offset;
+
+    pos = fastsearch(str, str_len, sub, sub_len, FAST_SEARCH);
+
+    if (pos >= 0)
+        pos += offset;
+
+    return pos;
+}
+
+Py_LOCAL_INLINE(Py_ssize_t)
+stringlib_rfind(const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+                const STRINGLIB_CHAR* sub, Py_ssize_t sub_len,
+                Py_ssize_t offset)
+{
+    /* XXX - create reversefastsearch helper! */
+    if (sub_len == 0) {
+        if (str_len < 0)
+            return -1;
+	return str_len + offset;
+    } else {
+	Py_ssize_t j, pos = -1;
+	for (j = str_len - sub_len; j >= 0; --j)
+            if (STRINGLIB_CMP(str+j, sub, sub_len) == 0) {
+                pos = j + offset;
+                break;
+            }
+        return pos;
+    }
+}
+
+Py_LOCAL_INLINE(Py_ssize_t)
+stringlib_find_slice(const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+                     const STRINGLIB_CHAR* sub, Py_ssize_t sub_len,
+                     Py_ssize_t start, Py_ssize_t end)
+{
+    if (start < 0)
+        start += str_len;
+    if (start < 0)
+        start = 0;
+    if (end > str_len)
+        end = str_len;
+    if (end < 0)
+        end += str_len;
+    if (end < 0)
+        end = 0;
+
+    return stringlib_find(
+        str + start, end - start,
+        sub, sub_len, start
+        );
+}
+
+Py_LOCAL_INLINE(Py_ssize_t)
+stringlib_rfind_slice(const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+                      const STRINGLIB_CHAR* sub, Py_ssize_t sub_len,
+                      Py_ssize_t start, Py_ssize_t end)
+{
+    if (start < 0)
+        start += str_len;
+    if (start < 0)
+        start = 0;
+    if (end > str_len)
+        end = str_len;
+    if (end < 0)
+        end += str_len;
+    if (end < 0)
+        end = 0;
+
+    return stringlib_rfind(str + start, end - start, sub, sub_len, start);
+}
+
+#if defined(STRINGLIB_STR) && !defined(FROM_BYTEARRAY)
+
+Py_LOCAL_INLINE(int)
+stringlib_contains_obj(PyObject* str, PyObject* sub)
+{
+    return stringlib_find(
+        STRINGLIB_STR(str), STRINGLIB_LEN(str),
+        STRINGLIB_STR(sub), STRINGLIB_LEN(sub), 0
+        ) != -1;
+}
+
+#endif /* STRINGLIB_STR */
+
+#ifdef FROM_UNICODE
+
+/*
+This function is a helper for the "find" family (find, rfind, index,
+rindex) of unicodeobject.c file, because they all have the same 
+behaviour for the arguments.
+
+It does not touch the variables received until it knows everything 
+is ok.
+
+Note that we receive a pointer to the pointer of the substring object,
+so when we create that object in this function we don't DECREF it,
+because it continues living in the caller functions (those functions, 
+after finishing using the substring, must DECREF it).
+*/
+
+Py_LOCAL_INLINE(int)
+_ParseTupleFinds (PyObject *args, PyObject **substring, 
+                  Py_ssize_t *start, Py_ssize_t *end) {
+    PyObject *tmp_substring;
+    Py_ssize_t tmp_start = 0;
+    Py_ssize_t tmp_end = PY_SSIZE_T_MAX;
+    PyObject *obj_start=Py_None, *obj_end=Py_None;
+
+    if (!PyArg_ParseTuple(args, "O|OO:find", &tmp_substring,
+         &obj_start, &obj_end))
+        return 0;
+
+    /* To support None in "start" and "end" arguments, meaning
+       the same as if they were not passed.
+    */
+    if (obj_start != Py_None)
+        if (!_PyEval_SliceIndex(obj_start, &tmp_start))
+            return 0;
+    if (obj_end != Py_None)
+        if (!_PyEval_SliceIndex(obj_end, &tmp_end))
+            return 0;
+
+    tmp_substring = PyUnicode_FromObject(tmp_substring);
+    if (!tmp_substring)
+        return 0;
+
+    *start = tmp_start;
+    *end = tmp_end;
+    *substring = tmp_substring;
+    return 1;
+}
+
+#endif /* FROM_UNICODE */
+
+#endif /* STRINGLIB_FIND_H */
+
+/*
+Local variables:
+c-basic-offset: 4
+indent-tabs-mode: nil
+End:
+*/

project/jni/python/src/Objects/stringlib/localeutil.h

@@ -0,0 +1,129 @@
+/* stringlib: locale related helpers implementation */
+
+#ifndef STRINGLIB_LOCALEUTIL_H
+#define STRINGLIB_LOCALEUTIL_H
+
+#include <locale.h>
+
+/**
+ * _Py_InsertThousandsGrouping:
+ * @buffer: A pointer to the start of a string.
+ * @n_buffer: The length of the string.
+ * @n_digits: The number of digits in the string, in which we want
+ *            to put the grouping chars.
+ * @buf_size: The maximum size of the buffer pointed to by buffer.
+ * @count: If non-NULL, points to a variable that will receive the
+ *         number of characters we need to insert (and no formatting
+ *         will actually occur).
+ * @append_zero_char: If non-zero, put a trailing zero at the end of
+ *         of the resulting string, if and only if we modified the
+ *         string.
+ *
+ * Inserts thousand grouping characters (as defined in the current
+ *  locale) into the string between buffer and buffer+n_digits.  If
+ *  count is non-NULL, don't do any formatting, just count the number
+ *  of characters to insert.  This is used by the caller to
+ *  appropriately resize the buffer, if needed.  If count is non-NULL,
+ *  buffer can be NULL (it is not dereferenced at all in that case).
+ *
+ * Return value: 0 on error, else 1.  Note that no error can occur if
+ *  count is non-NULL.
+ *
+ * This name won't be used, the includer of this file should define
+ *  it to be the actual function name, based on unicode or string.
+ **/
+int
+_Py_InsertThousandsGrouping(STRINGLIB_CHAR *buffer,
+			    Py_ssize_t n_buffer,
+			    Py_ssize_t n_digits,
+			    Py_ssize_t buf_size,
+			    Py_ssize_t *count,
+			    int append_zero_char)
+{
+	const char *grouping = 3;
+	const char *thousands_sep = ",";
+	Py_ssize_t thousands_sep_len = strlen(thousands_sep);
+	STRINGLIB_CHAR *pend = NULL; /* current end of buffer */
+	STRINGLIB_CHAR *pmax = NULL; /* max of buffer */
+	char current_grouping;
+	Py_ssize_t remaining = n_digits; /* Number of chars remaining to
+					    be looked at */
+
+	/* Initialize the character count, if we're just counting. */
+	if (count)
+		*count = 0;
+	else {
+		/* We're not just counting, we're modifying buffer */
+		pend = buffer + n_buffer;
+		pmax = buffer + buf_size;
+	}
+
+	/* Starting at the end and working right-to-left, keep track of
+	   what grouping needs to be added and insert that. */
+	current_grouping = *grouping++;
+
+	/* If the first character is 0, perform no grouping at all. */
+	if (current_grouping == 0)
+		return 1;
+
+	while (remaining > current_grouping) {
+		/* Always leave buffer and pend valid at the end of this
+		   loop, since we might leave with a return statement. */
+
+		remaining -= current_grouping;
+		if (count) {
+			/* We're only counting, not touching the memory. */
+			*count += thousands_sep_len;
+		}
+		else {
+			/* Do the formatting. */
+
+			STRINGLIB_CHAR *plast = buffer + remaining;
+
+			/* Is there room to insert thousands_sep_len chars? */
+			if (pmax - pend < thousands_sep_len)
+				/* No room. */
+				return 0;
+
+			/* Move the rest of the string down. */
+			memmove(plast + thousands_sep_len,
+				plast,
+				(pend - plast) * sizeof(STRINGLIB_CHAR));
+			/* Copy the thousands_sep chars into the buffer. */
+#if STRINGLIB_IS_UNICODE
+			/* Convert from the char's of the thousands_sep from
+			   the locale into unicode. */
+			{
+				Py_ssize_t i;
+				for (i = 0; i < thousands_sep_len; ++i)
+					plast[i] = thousands_sep[i];
+			}
+#else
+			/* No conversion, just memcpy the thousands_sep. */
+			memcpy(plast, thousands_sep, thousands_sep_len);
+#endif
+		}
+
+		/* Adjust end pointer. */
+		pend += thousands_sep_len;
+
+		/* Move to the next grouping character, unless we're
+		   repeating (which is designated by a grouping of 0). */
+		if (*grouping != 0) {
+			current_grouping = *grouping++;
+			if (current_grouping == CHAR_MAX)
+				/* We're done. */
+				break;
+		}
+	}
+	if (append_zero_char) {
+		/* Append a zero character to mark the end of the string,
+		   if there's room. */
+		if (pend - (buffer + remaining) < 1)
+			/* No room, error. */
+			return 0;
+		*pend = 0;
+	}
+	return 1;
+}
+#endif /* STRINGLIB_LOCALEUTIL_H */

project/jni/python/src/Objects/stringlib/partition.h

@@ -0,0 +1,111 @@
+/* stringlib: partition implementation */
+
+#ifndef STRINGLIB_PARTITION_H
+#define STRINGLIB_PARTITION_H
+
+#ifndef STRINGLIB_FASTSEARCH_H
+#error must include "stringlib/fastsearch.h" before including this module
+#endif
+
+Py_LOCAL_INLINE(PyObject*)
+stringlib_partition(
+    PyObject* str_obj, const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+    PyObject* sep_obj, const STRINGLIB_CHAR* sep, Py_ssize_t sep_len
+    )
+{
+    PyObject* out;
+    Py_ssize_t pos;
+
+    if (sep_len == 0) {
+        PyErr_SetString(PyExc_ValueError, "empty separator");
+	return NULL;
+    }
+
+    out = PyTuple_New(3);
+    if (!out)
+	return NULL;
+
+    pos = fastsearch(str, str_len, sep, sep_len, FAST_SEARCH);
+
+    if (pos < 0) {
+	Py_INCREF(str_obj);
+	PyTuple_SET_ITEM(out, 0, (PyObject*) str_obj);
+	Py_INCREF(STRINGLIB_EMPTY);
+	PyTuple_SET_ITEM(out, 1, (PyObject*) STRINGLIB_EMPTY);
+	Py_INCREF(STRINGLIB_EMPTY);
+	PyTuple_SET_ITEM(out, 2, (PyObject*) STRINGLIB_EMPTY);
+	return out;
+    }
+
+    PyTuple_SET_ITEM(out, 0, STRINGLIB_NEW(str, pos));
+    Py_INCREF(sep_obj);
+    PyTuple_SET_ITEM(out, 1, sep_obj);
+    pos += sep_len;
+    PyTuple_SET_ITEM(out, 2, STRINGLIB_NEW(str + pos, str_len - pos));
+
+    if (PyErr_Occurred()) {
+	Py_DECREF(out);
+	return NULL;
+    }
+
+    return out;
+}
+
+Py_LOCAL_INLINE(PyObject*)
+stringlib_rpartition(
+    PyObject* str_obj, const STRINGLIB_CHAR* str, Py_ssize_t str_len,
+    PyObject* sep_obj, const STRINGLIB_CHAR* sep, Py_ssize_t sep_len
+    )
+{
+    PyObject* out;
+    Py_ssize_t pos, j;
+
+    if (sep_len == 0) {
+        PyErr_SetString(PyExc_ValueError, "empty separator");
+	return NULL;
+    }
+
+    out = PyTuple_New(3);
+    if (!out)
+	return NULL;
+
+    /* XXX - create reversefastsearch helper! */
+        pos = -1;
+	for (j = str_len - sep_len; j >= 0; --j)
+            if (STRINGLIB_CMP(str+j, sep, sep_len) == 0) {
+                pos = j;
+                break;
+            }
+
+    if (pos < 0) {
+	Py_INCREF(STRINGLIB_EMPTY);
+	PyTuple_SET_ITEM(out, 0, (PyObject*) STRINGLIB_EMPTY);
+	Py_INCREF(STRINGLIB_EMPTY);
+	PyTuple_SET_ITEM(out, 1, (PyObject*) STRINGLIB_EMPTY);
+	Py_INCREF(str_obj);        
+	PyTuple_SET_ITEM(out, 2, (PyObject*) str_obj);
+	return out;
+    }
+
+    PyTuple_SET_ITEM(out, 0, STRINGLIB_NEW(str, pos));
+    Py_INCREF(sep_obj);
+    PyTuple_SET_ITEM(out, 1, sep_obj);
+    pos += sep_len;
+    PyTuple_SET_ITEM(out, 2, STRINGLIB_NEW(str + pos, str_len - pos));
+
+    if (PyErr_Occurred()) {
+	Py_DECREF(out);
+	return NULL;
+    }
+
+    return out;
+}
+
+#endif
+
+/*
+Local variables:
+c-basic-offset: 4
+indent-tabs-mode: nil
+End:
+*/

project/jni/python/src/Objects/stringlib/stringdefs.h

@@ -0,0 +1,28 @@
+#ifndef STRINGLIB_STRINGDEFS_H
+#define STRINGLIB_STRINGDEFS_H
+
+/* this is sort of a hack.  there's at least one place (formatting
+   floats) where some stringlib code takes a different path if it's
+   compiled as unicode. */
+#define STRINGLIB_IS_UNICODE     0
+
+#define STRINGLIB_OBJECT         PyStringObject
+#define STRINGLIB_CHAR           char
+#define STRINGLIB_TYPE_NAME      "string"
+#define STRINGLIB_PARSE_CODE     "S"
+#define STRINGLIB_EMPTY          nullstring
+#define STRINGLIB_ISDECIMAL(x)   ((x >= '0') && (x <= '9'))
+#define STRINGLIB_TODECIMAL(x)   (STRINGLIB_ISDECIMAL(x) ? (x - '0') : -1)
+#define STRINGLIB_TOUPPER        toupper
+#define STRINGLIB_TOLOWER        tolower
+#define STRINGLIB_FILL           memset
+#define STRINGLIB_STR            PyString_AS_STRING
+#define STRINGLIB_LEN            PyString_GET_SIZE
+#define STRINGLIB_NEW            PyString_FromStringAndSize
+#define STRINGLIB_RESIZE         _PyString_Resize
+#define STRINGLIB_CHECK          PyString_Check
+#define STRINGLIB_CMP            memcmp
+#define STRINGLIB_TOSTR          PyObject_Str
+#define STRINGLIB_GROUPING       _PyString_InsertThousandsGrouping
+
+#endif /* !STRINGLIB_STRINGDEFS_H */

project/jni/python/src/Objects/stringlib/transmogrify.h

@@ -0,0 +1,355 @@
+/* NOTE: this API is -ONLY- for use with single byte character strings. */
+/* Do not use it with Unicode. */
+
+#include "bytes_methods.h"
+
+#ifndef STRINGLIB_MUTABLE
+#warning "STRINGLIB_MUTABLE not defined before #include, assuming 0"
+#define STRINGLIB_MUTABLE 0
+#endif
+
+/* the more complicated methods.  parts of these should be pulled out into the
+   shared code in bytes_methods.c to cut down on duplicate code bloat.  */
+
+PyDoc_STRVAR(expandtabs__doc__,
+"B.expandtabs([tabsize]) -> copy of B\n\
+\n\
+Return a copy of B where all tab characters are expanded using spaces.\n\
+If tabsize is not given, a tab size of 8 characters is assumed.");
+
+static PyObject*
+stringlib_expandtabs(PyObject *self, PyObject *args)
+{
+    const char *e, *p;
+    char *q;
+    size_t i, j;
+    PyObject *u;
+    int tabsize = 8;
+    
+    if (!PyArg_ParseTuple(args, "|i:expandtabs", &tabsize))
+        return NULL;
+    
+    /* First pass: determine size of output string */
+    i = j = 0;
+    e = STRINGLIB_STR(self) + STRINGLIB_LEN(self);
+    for (p = STRINGLIB_STR(self); p < e; p++)
+        if (*p == '\t') {
+            if (tabsize > 0) {
+                j += tabsize - (j % tabsize);
+                if (j > PY_SSIZE_T_MAX) {
+                    PyErr_SetString(PyExc_OverflowError,
+                                    "result is too long");
+                    return NULL;
+                }
+            }
+        }
+        else {
+            j++;
+            if (*p == '\n' || *p == '\r') {
+                i += j;
+                j = 0;
+                if (i > PY_SSIZE_T_MAX) {
+                    PyErr_SetString(PyExc_OverflowError,
+                                    "result is too long");
+                    return NULL;
+                }
+            }
+        }
+    
+    if ((i + j) > PY_SSIZE_T_MAX) {
+        PyErr_SetString(PyExc_OverflowError, "result is too long");
+        return NULL;
+    }
+    
+    /* Second pass: create output string and fill it */
+    u = STRINGLIB_NEW(NULL, i + j);
+    if (!u)
+        return NULL;
+    
+    j = 0;
+    q = STRINGLIB_STR(u);
+    
+    for (p = STRINGLIB_STR(self); p < e; p++)
+        if (*p == '\t') {
+            if (tabsize > 0) {
+                i = tabsize - (j % tabsize);
+                j += i;
+                while (i--)
+                    *q++ = ' ';
+            }
+        }
+        else {
+            j++;
+            *q++ = *p;
+            if (*p == '\n' || *p == '\r')
+                j = 0;
+        }
+    
+    return u;
+}
+
+Py_LOCAL_INLINE(PyObject *)
+pad(PyObject *self, Py_ssize_t left, Py_ssize_t right, char fill)
+{
+    PyObject *u;
+
+    if (left < 0)
+        left = 0;
+    if (right < 0)
+        right = 0;
+
+    if (left == 0 && right == 0 && STRINGLIB_CHECK_EXACT(self)) {
+#if STRINGLIB_MUTABLE
+        /* We're defined as returning a copy;  If the object is mutable
+         * that means we must make an identical copy. */
+        return STRINGLIB_NEW(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+#else
+        Py_INCREF(self);
+        return (PyObject *)self;
+#endif /* STRINGLIB_MUTABLE */
+    }
+
+    u = STRINGLIB_NEW(NULL,
+				   left + STRINGLIB_LEN(self) + right);
+    if (u) {
+        if (left)
+            memset(STRINGLIB_STR(u), fill, left);
+        Py_MEMCPY(STRINGLIB_STR(u) + left,
+	       STRINGLIB_STR(self),
+	       STRINGLIB_LEN(self));
+        if (right)
+            memset(STRINGLIB_STR(u) + left + STRINGLIB_LEN(self),
+		   fill, right);
+    }
+
+    return u;
+}
+
+PyDoc_STRVAR(ljust__doc__,
+"B.ljust(width[, fillchar]) -> copy of B\n"
+"\n"
+"Return B left justified in a string of length width. Padding is\n"
+"done using the specified fill character (default is a space).");
+
+static PyObject *
+stringlib_ljust(PyObject *self, PyObject *args)
+{
+    Py_ssize_t width;
+    char fillchar = ' ';
+
+    if (!PyArg_ParseTuple(args, "n|c:ljust", &width, &fillchar))
+        return NULL;
+
+    if (STRINGLIB_LEN(self) >= width && STRINGLIB_CHECK_EXACT(self)) {
+#if STRINGLIB_MUTABLE
+        /* We're defined as returning a copy;  If the object is mutable
+         * that means we must make an identical copy. */
+        return STRINGLIB_NEW(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+#else
+        Py_INCREF(self);
+        return (PyObject*) self;
+#endif
+    }
+
+    return pad(self, 0, width - STRINGLIB_LEN(self), fillchar);
+}
+
+
+PyDoc_STRVAR(rjust__doc__,
+"B.rjust(width[, fillchar]) -> copy of B\n"
+"\n"
+"Return B right justified in a string of length width. Padding is\n"
+"done using the specified fill character (default is a space)");
+
+static PyObject *
+stringlib_rjust(PyObject *self, PyObject *args)
+{
+    Py_ssize_t width;
+    char fillchar = ' ';
+
+    if (!PyArg_ParseTuple(args, "n|c:rjust", &width, &fillchar))
+        return NULL;
+
+    if (STRINGLIB_LEN(self) >= width && STRINGLIB_CHECK_EXACT(self)) {
+#if STRINGLIB_MUTABLE
+        /* We're defined as returning a copy;  If the object is mutable
+         * that means we must make an identical copy. */
+        return STRINGLIB_NEW(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+#else
+        Py_INCREF(self);
+        return (PyObject*) self;
+#endif
+    }
+
+    return pad(self, width - STRINGLIB_LEN(self), 0, fillchar);
+}
+
+
+PyDoc_STRVAR(center__doc__,
+"B.center(width[, fillchar]) -> copy of B\n"
+"\n"
+"Return B centered in a string of length width.  Padding is\n"
+"done using the specified fill character (default is a space).");
+
+static PyObject *
+stringlib_center(PyObject *self, PyObject *args)
+{
+    Py_ssize_t marg, left;
+    Py_ssize_t width;
+    char fillchar = ' ';
+
+    if (!PyArg_ParseTuple(args, "n|c:center", &width, &fillchar))
+        return NULL;
+
+    if (STRINGLIB_LEN(self) >= width && STRINGLIB_CHECK_EXACT(self)) {
+#if STRINGLIB_MUTABLE
+        /* We're defined as returning a copy;  If the object is mutable
+         * that means we must make an identical copy. */
+        return STRINGLIB_NEW(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+#else
+        Py_INCREF(self);
+        return (PyObject*) self;
+#endif
+    }
+
+    marg = width - STRINGLIB_LEN(self);
+    left = marg / 2 + (marg & width & 1);
+
+    return pad(self, left, marg - left, fillchar);
+}
+
+PyDoc_STRVAR(zfill__doc__,
+"B.zfill(width) -> copy of B\n"
+"\n"
+"Pad a numeric string B with zeros on the left, to fill a field\n"
+"of the specified width.  B is never truncated.");
+
+static PyObject *
+stringlib_zfill(PyObject *self, PyObject *args)
+{
+    Py_ssize_t fill;
+    PyObject *s;
+    char *p;
+    Py_ssize_t width;
+
+    if (!PyArg_ParseTuple(args, "n:zfill", &width))
+        return NULL;
+
+    if (STRINGLIB_LEN(self) >= width) {
+        if (STRINGLIB_CHECK_EXACT(self)) {
+#if STRINGLIB_MUTABLE
+            /* We're defined as returning a copy;  If the object is mutable
+             * that means we must make an identical copy. */
+            return STRINGLIB_NEW(STRINGLIB_STR(self), STRINGLIB_LEN(self));
+#else
+            Py_INCREF(self);
+            return (PyObject*) self;
+#endif
+        }
+        else
+            return STRINGLIB_NEW(
+                STRINGLIB_STR(self),
+                STRINGLIB_LEN(self)
+            );
+    }
+
+    fill = width - STRINGLIB_LEN(self);
+
+    s = pad(self, fill, 0, '0');
+
+    if (s == NULL)
+        return NULL;
+
+    p = STRINGLIB_STR(s);
+    if (p[fill] == '+' || p[fill] == '-') {
+        /* move sign to beginning of string */
+        p[0] = p[fill];
+        p[fill] = '0';
+    }
+
+    return (PyObject*) s;
+}
+
+
+#define _STRINGLIB_SPLIT_APPEND(data, left, right)		\
+	str = STRINGLIB_NEW((data) + (left),	                \
+					 (right) - (left));	\
+	if (str == NULL)					\
+		goto onError;					\
+	if (PyList_Append(list, str)) {				\
+		Py_DECREF(str);					\
+		goto onError;					\
+	}							\
+	else							\
+		Py_DECREF(str);
+
+PyDoc_STRVAR(splitlines__doc__,
+"B.splitlines([keepends]) -> list of lines\n\
+\n\
+Return a list of the lines in B, breaking at line boundaries.\n\
+Line breaks are not included in the resulting list unless keepends\n\
+is given and true.");
+
+static PyObject*
+stringlib_splitlines(PyObject *self, PyObject *args)
+{
+    register Py_ssize_t i;
+    register Py_ssize_t j;
+    Py_ssize_t len;
+    int keepends = 0;
+    PyObject *list;
+    PyObject *str;
+    char *data;
+
+    if (!PyArg_ParseTuple(args, "|i:splitlines", &keepends))
+        return NULL;
+
+    data = STRINGLIB_STR(self);
+    len = STRINGLIB_LEN(self);
+
+    /* This does not use the preallocated list because splitlines is
+       usually run with hundreds of newlines.  The overhead of
+       switching between PyList_SET_ITEM and append causes about a
+       2-3% slowdown for that common case.  A smarter implementation
+       could move the if check out, so the SET_ITEMs are done first
+       and the appends only done when the prealloc buffer is full.
+       That's too much work for little gain.*/
+
+    list = PyList_New(0);
+    if (!list)
+        goto onError;
+
+    for (i = j = 0; i < len; ) {
+	Py_ssize_t eol;
+
+	/* Find a line and append it */
+	while (i < len && data[i] != '\n' && data[i] != '\r')
+	    i++;
+
+	/* Skip the line break reading CRLF as one line break */
+	eol = i;
+	if (i < len) {
+	    if (data[i] == '\r' && i + 1 < len &&
+		data[i+1] == '\n')
+		i += 2;
+	    else
+		i++;
+	    if (keepends)
+		eol = i;
+	}
+	_STRINGLIB_SPLIT_APPEND(data, j, eol);
+	j = i;
+    }
+    if (j < len) {
+	_STRINGLIB_SPLIT_APPEND(data, j, len);
+    }
+
+    return list;
+
+ onError:
+    Py_XDECREF(list);
+    return NULL;
+}
+
+#undef _STRINGLIB_SPLIT_APPEND
+

project/jni/python/src/Objects/stringlib/unicodedefs.h

@@ -0,0 +1,53 @@
+#ifndef STRINGLIB_UNICODEDEFS_H
+#define STRINGLIB_UNICODEDEFS_H
+
+/* this is sort of a hack.  there's at least one place (formatting
+   floats) where some stringlib code takes a different path if it's
+   compiled as unicode. */
+#define STRINGLIB_IS_UNICODE     1
+
+#define STRINGLIB_OBJECT         PyUnicodeObject
+#define STRINGLIB_CHAR           Py_UNICODE
+#define STRINGLIB_TYPE_NAME      "unicode"
+#define STRINGLIB_PARSE_CODE     "U"
+#define STRINGLIB_EMPTY          unicode_empty
+#define STRINGLIB_ISDECIMAL      Py_UNICODE_ISDECIMAL
+#define STRINGLIB_TODECIMAL      Py_UNICODE_TODECIMAL
+#define STRINGLIB_TOUPPER        Py_UNICODE_TOUPPER
+#define STRINGLIB_TOLOWER        Py_UNICODE_TOLOWER
+#define STRINGLIB_FILL           Py_UNICODE_FILL
+#define STRINGLIB_STR            PyUnicode_AS_UNICODE
+#define STRINGLIB_LEN            PyUnicode_GET_SIZE
+#define STRINGLIB_NEW            PyUnicode_FromUnicode
+#define STRINGLIB_RESIZE         PyUnicode_Resize
+#define STRINGLIB_CHECK          PyUnicode_Check
+#define STRINGLIB_GROUPING       _PyUnicode_InsertThousandsGrouping
+
+#if PY_VERSION_HEX < 0x03000000
+#define STRINGLIB_TOSTR          PyObject_Unicode
+#else
+#define STRINGLIB_TOSTR          PyObject_Str
+#endif
+
+#define STRINGLIB_WANT_CONTAINS_OBJ 1
+
+/* STRINGLIB_CMP was defined as:
+
+Py_LOCAL_INLINE(int)
+STRINGLIB_CMP(const Py_UNICODE* str, const Py_UNICODE* other, Py_ssize_t len)
+{
+    if (str[0] != other[0])
+        return 1;
+    return memcmp((void*) str, (void*) other, len * sizeof(Py_UNICODE));
+}
+
+but unfortunately that gives a error if the function isn't used in a file that
+includes this file.  So, reluctantly convert it to a macro instead. */
+
+#define STRINGLIB_CMP(str, other, len) \
+    (((str)[0] != (other)[0]) ? \
+     1 : \
+     memcmp((void*) (str), (void*) (other), (len) * sizeof(Py_UNICODE)))
+
+
+#endif /* !STRINGLIB_UNICODEDEFS_H */