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
This commit is contained in:
pelya
2011-04-01 14:32:12 +03:00
parent a7cf867372
commit 9586a42a30
3953 changed files with 1480069 additions and 1 deletions

View File

@@ -0,0 +1,6 @@
Demo/parser
Doc/libparser.tex
Lib/AST.py
Lib/symbol.py
Lib/token.py
Modules/parsermodule.c

View File

@@ -0,0 +1,31 @@
These files are from the large example of using the `parser' module. Refer
to the Python Library Reference for more information.
It also contains examples for the AST parser.
Files:
------
FILES -- list of files associated with the parser module.
README -- this file.
example.py -- module that uses the `parser' module to extract
information from the parse tree of Python source
code.
docstring.py -- sample source file containing only a module docstring.
simple.py -- sample source containing a "short form" definition.
source.py -- sample source code used to demonstrate ability to
handle nested constructs easily using the functions
and classes in example.py.
test_parser.py program to put the parser module through its paces.
unparse.py AST (2.5) based example to recreate source code
from an AST. This is incomplete; contributions
are welcome.
Enjoy!

View File

@@ -0,0 +1,2 @@
"""Some documentation.
"""

View File

@@ -0,0 +1,190 @@
"""Simple code to extract class & function docstrings from a module.
This code is used as an example in the library reference manual in the
section on using the parser module. Refer to the manual for a thorough
discussion of the operation of this code.
"""
import os
import parser
import symbol
import token
import types
from types import ListType, TupleType
def get_docs(fileName):
"""Retrieve information from the parse tree of a source file.
fileName
Name of the file to read Python source code from.
"""
source = open(fileName).read()
basename = os.path.basename(os.path.splitext(fileName)[0])
ast = parser.suite(source)
return ModuleInfo(ast.totuple(), basename)
class SuiteInfoBase:
_docstring = ''
_name = ''
def __init__(self, tree = None):
self._class_info = {}
self._function_info = {}
if tree:
self._extract_info(tree)
def _extract_info(self, tree):
# extract docstring
if len(tree) == 2:
found, vars = match(DOCSTRING_STMT_PATTERN[1], tree[1])
else:
found, vars = match(DOCSTRING_STMT_PATTERN, tree[3])
if found:
self._docstring = eval(vars['docstring'])
# discover inner definitions
for node in tree[1:]:
found, vars = match(COMPOUND_STMT_PATTERN, node)
if found:
cstmt = vars['compound']
if cstmt[0] == symbol.funcdef:
name = cstmt[2][1]
self._function_info[name] = FunctionInfo(cstmt)
elif cstmt[0] == symbol.classdef:
name = cstmt[2][1]
self._class_info[name] = ClassInfo(cstmt)
def get_docstring(self):
return self._docstring
def get_name(self):
return self._name
def get_class_names(self):
return self._class_info.keys()
def get_class_info(self, name):
return self._class_info[name]
def __getitem__(self, name):
try:
return self._class_info[name]
except KeyError:
return self._function_info[name]
class SuiteFuncInfo:
# Mixin class providing access to function names and info.
def get_function_names(self):
return self._function_info.keys()
def get_function_info(self, name):
return self._function_info[name]
class FunctionInfo(SuiteInfoBase, SuiteFuncInfo):
def __init__(self, tree = None):
self._name = tree[2][1]
SuiteInfoBase.__init__(self, tree and tree[-1] or None)
class ClassInfo(SuiteInfoBase):
def __init__(self, tree = None):
self._name = tree[2][1]
SuiteInfoBase.__init__(self, tree and tree[-1] or None)
def get_method_names(self):
return self._function_info.keys()
def get_method_info(self, name):
return self._function_info[name]
class ModuleInfo(SuiteInfoBase, SuiteFuncInfo):
def __init__(self, tree = None, name = "<string>"):
self._name = name
SuiteInfoBase.__init__(self, tree)
if tree:
found, vars = match(DOCSTRING_STMT_PATTERN, tree[1])
if found:
self._docstring = vars["docstring"]
def match(pattern, data, vars=None):
"""Match `data' to `pattern', with variable extraction.
pattern
Pattern to match against, possibly containing variables.
data
Data to be checked and against which variables are extracted.
vars
Dictionary of variables which have already been found. If not
provided, an empty dictionary is created.
The `pattern' value may contain variables of the form ['varname'] which
are allowed to match anything. The value that is matched is returned as
part of a dictionary which maps 'varname' to the matched value. 'varname'
is not required to be a string object, but using strings makes patterns
and the code which uses them more readable.
This function returns two values: a boolean indicating whether a match
was found and a dictionary mapping variable names to their associated
values.
"""
if vars is None:
vars = {}
if type(pattern) is ListType: # 'variables' are ['varname']
vars[pattern[0]] = data
return 1, vars
if type(pattern) is not TupleType:
return (pattern == data), vars
if len(data) != len(pattern):
return 0, vars
for pattern, data in map(None, pattern, data):
same, vars = match(pattern, data, vars)
if not same:
break
return same, vars
# This pattern identifies compound statements, allowing them to be readily
# differentiated from simple statements.
#
COMPOUND_STMT_PATTERN = (
symbol.stmt,
(symbol.compound_stmt, ['compound'])
)
# This pattern will match a 'stmt' node which *might* represent a docstring;
# docstrings require that the statement which provides the docstring be the
# first statement in the class or function, which this pattern does not check.
#
DOCSTRING_STMT_PATTERN = (
symbol.stmt,
(symbol.simple_stmt,
(symbol.small_stmt,
(symbol.expr_stmt,
(symbol.testlist,
(symbol.test,
(symbol.and_test,
(symbol.not_test,
(symbol.comparison,
(symbol.expr,
(symbol.xor_expr,
(symbol.and_expr,
(symbol.shift_expr,
(symbol.arith_expr,
(symbol.term,
(symbol.factor,
(symbol.power,
(symbol.atom,
(token.STRING, ['docstring'])
)))))))))))))))),
(token.NEWLINE, '')
))

View File

@@ -0,0 +1 @@
def f(): "maybe a docstring"

View File

@@ -0,0 +1,27 @@
"""Exmaple file to be parsed for the parsermodule example.
The classes and functions in this module exist only to exhibit the ability
of the handling information extraction from nested definitions using parse
trees. They shouldn't interest you otherwise!
"""
class Simple:
"This class does very little."
def method(self):
"This method does almost nothing."
return 1
class Nested:
"This is a nested class."
def nested_method(self):
"Method of Nested class."
def nested_function():
"Function in method of Nested class."
pass
return nested_function
def function():
"This function lives at the module level."
return 0

View File

@@ -0,0 +1,48 @@
#! /usr/bin/env python
# (Force the script to use the latest build.)
#
# test_parser.py
import parser, traceback
_numFailed = 0
def testChunk(t, fileName):
global _numFailed
print '----', fileName,
try:
ast = parser.suite(t)
tup = parser.ast2tuple(ast)
# this discards the first AST; a huge memory savings when running
# against a large source file like Tkinter.py.
ast = None
new = parser.tuple2ast(tup)
except parser.ParserError, err:
print
print 'parser module raised exception on input file', fileName + ':'
traceback.print_exc()
_numFailed = _numFailed + 1
else:
if tup != parser.ast2tuple(new):
print
print 'parser module failed on input file', fileName
_numFailed = _numFailed + 1
else:
print 'o.k.'
def testFile(fileName):
t = open(fileName).read()
testChunk(t, fileName)
def test():
import sys
args = sys.argv[1:]
if not args:
import glob
args = glob.glob("*.py")
args.sort()
map(testFile, args)
sys.exit(_numFailed != 0)
if __name__ == '__main__':
test()

View File

@@ -0,0 +1,100 @@
\input texinfo @c -*-texinfo-*-
@c %**start of header
@setfilename parser.info
@settitle Python Parser Module Reference
@setchapternewpage odd
@footnotestyle end
@c %**end of header
@ifinfo
This file describes the interfaces
published by the optional @code{parser} module and gives examples of
how they may be used. It contains the same text as the chapter on the
@code{parser} module in the @cite{Python Library Reference}, but is
presented as a separate document.
Copyright 1995-1996 by Fred L. Drake, Jr., Reston, Virginia, USA, and
Virginia Polytechnic Institute and State University, Blacksburg,
Virginia, USA. Portions of the software copyright 1991-1995 by
Stichting Mathematisch Centrum, Amsterdam, The Netherlands. Copying is
permitted under the terms associated with the main Python distribution,
with the additional restriction that this additional notice be included
and maintained on all distributed copies.
All Rights Reserved
Permission to use, copy, modify, and distribute this software and its
documentation for any purpose and without fee is hereby granted,
provided that the above copyright notice appear in all copies and that
both that copyright notice and this permission notice appear in
supporting documentation, and that the names of Fred L. Drake, Jr. and
Virginia Polytechnic Institute and State University not be used in
advertising or publicity pertaining to distribution of the software
without specific, written prior permission.
FRED L. DRAKE, JR. AND VIRGINIA POLYTECHNIC INSTITUTE AND STATE
UNIVERSITY DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
EVENT SHALL FRED L. DRAKE, JR. OR VIRGINIA POLYTECHNIC INSTITUTE AND
STATE UNIVERSITY BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL
DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
@end ifinfo
@titlepage
@title Python Parser Module Reference
@author Fred L. Drake, Jr.
@c The following two commands start the copyright page.
@page
@vskip 0pt plus 1filll
Copyright 1995-1996 by Fred L. Drake, Jr., Reston, Virginia, USA, and
Virginia Polytechnic Institute and State University, Blacksburg,
Virginia, USA. Portions of the software copyright 1991-1995 by
Stichting Mathematisch Centrum, Amsterdam, The Netherlands. Copying is
permitted under the terms associated with the main Python distribution,
with the additional restriction that this additional notice be included
and maintained on all distributed copies.
@center All Rights Reserved
Permission to use, copy, modify, and distribute this software and its
documentation for any purpose and without fee is hereby granted,
provided that the above copyright notice appear in all copies and that
both that copyright notice and this permission notice appear in
supporting documentation, and that the names of Fred L. Drake, Jr. and
Virginia Polytechnic Institute and State University not be used in
advertising or publicity pertaining to distribution of the software
without specific, written prior permission.
FRED L. DRAKE, JR. AND VIRGINIA POLYTECHNIC INSTITUTE AND STATE
UNIVERSITY DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO
EVENT SHALL FRED L. DRAKE, JR. OR VIRGINIA POLYTECHNIC INSTITUTE AND
STATE UNIVERSITY BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL
DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
PERFORMANCE OF THIS SOFTWARE.
@end titlepage
@node Top, Overview, (dir), (dir)
@top The Python Parser Module
@ifinfo
This file describes the interfaces
published by the optional @code{parser} module and gives examples of
how they may be used. It contains the same text as the chapter on the
@code{parser} module in the @cite{Python Library Reference}, but is
presented as a separate document.
This version corresponds to Python version 1.4 (1 Sept. 1996).
@end ifinfo
@c placeholder for the master menu -- patched by texinfo-all-menus-update
@menu
@end menu

View File

@@ -0,0 +1,518 @@
"Usage: unparse.py <path to source file>"
import sys
import _ast
import cStringIO
import os
def interleave(inter, f, seq):
"""Call f on each item in seq, calling inter() in between.
"""
seq = iter(seq)
try:
f(seq.next())
except StopIteration:
pass
else:
for x in seq:
inter()
f(x)
class Unparser:
"""Methods in this class recursively traverse an AST and
output source code for the abstract syntax; original formatting
is disregarged. """
def __init__(self, tree, file = sys.stdout):
"""Unparser(tree, file=sys.stdout) -> None.
Print the source for tree to file."""
self.f = file
self._indent = 0
self.dispatch(tree)
print >>self.f,""
self.f.flush()
def fill(self, text = ""):
"Indent a piece of text, according to the current indentation level"
self.f.write("\n"+" "*self._indent + text)
def write(self, text):
"Append a piece of text to the current line."
self.f.write(text)
def enter(self):
"Print ':', and increase the indentation."
self.write(":")
self._indent += 1
def leave(self):
"Decrease the indentation level."
self._indent -= 1
def dispatch(self, tree):
"Dispatcher function, dispatching tree type T to method _T."
if isinstance(tree, list):
for t in tree:
self.dispatch(t)
return
meth = getattr(self, "_"+tree.__class__.__name__)
meth(tree)
############### Unparsing methods ######################
# There should be one method per concrete grammar type #
# Constructors should be grouped by sum type. Ideally, #
# this would follow the order in the grammar, but #
# currently doesn't. #
########################################################
def _Module(self, tree):
for stmt in tree.body:
self.dispatch(stmt)
# stmt
def _Expr(self, tree):
self.fill()
self.dispatch(tree.value)
def _Import(self, t):
self.fill("import ")
interleave(lambda: self.write(", "), self.dispatch, t.names)
def _ImportFrom(self, t):
self.fill("from ")
self.write(t.module)
self.write(" import ")
interleave(lambda: self.write(", "), self.dispatch, t.names)
# XXX(jpe) what is level for?
def _Assign(self, t):
self.fill()
for target in t.targets:
self.dispatch(target)
self.write(" = ")
self.dispatch(t.value)
def _AugAssign(self, t):
self.fill()
self.dispatch(t.target)
self.write(" "+self.binop[t.op.__class__.__name__]+"= ")
self.dispatch(t.value)
def _Return(self, t):
self.fill("return")
if t.value:
self.write(" ")
self.dispatch(t.value)
def _Pass(self, t):
self.fill("pass")
def _Break(self, t):
self.fill("break")
def _Continue(self, t):
self.fill("continue")
def _Delete(self, t):
self.fill("del ")
self.dispatch(t.targets)
def _Assert(self, t):
self.fill("assert ")
self.dispatch(t.test)
if t.msg:
self.write(", ")
self.dispatch(t.msg)
def _Exec(self, t):
self.fill("exec ")
self.dispatch(t.body)
if t.globals:
self.write(" in ")
self.dispatch(t.globals)
if t.locals:
self.write(", ")
self.dispatch(t.locals)
def _Print(self, t):
self.fill("print ")
do_comma = False
if t.dest:
self.write(">>")
self.dispatch(t.dest)
do_comma = True
for e in t.values:
if do_comma:self.write(", ")
else:do_comma=True
self.dispatch(e)
if not t.nl:
self.write(",")
def _Global(self, t):
self.fill("global ")
interleave(lambda: self.write(", "), self.write, t.names)
def _Yield(self, t):
self.write("(")
self.write("yield")
if t.value:
self.write(" ")
self.dispatch(t.value)
self.write(")")
def _Raise(self, t):
self.fill('raise ')
if t.type:
self.dispatch(t.type)
if t.inst:
self.write(", ")
self.dispatch(t.inst)
if t.tback:
self.write(", ")
self.dispatch(t.tback)
def _TryExcept(self, t):
self.fill("try")
self.enter()
self.dispatch(t.body)
self.leave()
for ex in t.handlers:
self.dispatch(ex)
if t.orelse:
self.fill("else")
self.enter()
self.dispatch(t.orelse)
self.leave()
def _TryFinally(self, t):
self.fill("try")
self.enter()
self.dispatch(t.body)
self.leave()
self.fill("finally")
self.enter()
self.dispatch(t.finalbody)
self.leave()
def _ExceptHandler(self, t):
self.fill("except")
if t.type:
self.write(" ")
self.dispatch(t.type)
if t.name:
self.write(", ")
self.dispatch(t.name)
self.enter()
self.dispatch(t.body)
self.leave()
def _ClassDef(self, t):
self.write("\n")
self.fill("class "+t.name)
if t.bases:
self.write("(")
for a in t.bases:
self.dispatch(a)
self.write(", ")
self.write(")")
self.enter()
self.dispatch(t.body)
self.leave()
def _FunctionDef(self, t):
self.write("\n")
for deco in t.decorator_list:
self.fill("@")
self.dispatch(deco)
self.fill("def "+t.name + "(")
self.dispatch(t.args)
self.write(")")
self.enter()
self.dispatch(t.body)
self.leave()
def _For(self, t):
self.fill("for ")
self.dispatch(t.target)
self.write(" in ")
self.dispatch(t.iter)
self.enter()
self.dispatch(t.body)
self.leave()
if t.orelse:
self.fill("else")
self.enter()
self.dispatch(t.orelse)
self.leave
def _If(self, t):
self.fill("if ")
self.dispatch(t.test)
self.enter()
# XXX elif?
self.dispatch(t.body)
self.leave()
if t.orelse:
self.fill("else")
self.enter()
self.dispatch(t.orelse)
self.leave()
def _While(self, t):
self.fill("while ")
self.dispatch(t.test)
self.enter()
self.dispatch(t.body)
self.leave()
if t.orelse:
self.fill("else")
self.enter()
self.dispatch(t.orelse)
self.leave
def _With(self, t):
self.fill("with ")
self.dispatch(t.context_expr)
if t.optional_vars:
self.write(" as ")
self.dispatch(t.optional_vars)
self.enter()
self.dispatch(t.body)
self.leave()
# expr
def _Str(self, tree):
self.write(repr(tree.s))
def _Name(self, t):
self.write(t.id)
def _Repr(self, t):
self.write("`")
self.dispatch(t.value)
self.write("`")
def _Num(self, t):
self.write(repr(t.n))
def _List(self, t):
self.write("[")
interleave(lambda: self.write(", "), self.dispatch, t.elts)
self.write("]")
def _ListComp(self, t):
self.write("[")
self.dispatch(t.elt)
for gen in t.generators:
self.dispatch(gen)
self.write("]")
def _GeneratorExp(self, t):
self.write("(")
self.dispatch(t.elt)
for gen in t.generators:
self.dispatch(gen)
self.write(")")
def _comprehension(self, t):
self.write(" for ")
self.dispatch(t.target)
self.write(" in ")
self.dispatch(t.iter)
for if_clause in t.ifs:
self.write(" if ")
self.dispatch(if_clause)
def _IfExp(self, t):
self.write("(")
self.dispatch(t.body)
self.write(" if ")
self.dispatch(t.test)
self.write(" else ")
self.dispatch(t.orelse)
self.write(")")
def _Dict(self, t):
self.write("{")
def writem((k, v)):
self.dispatch(k)
self.write(": ")
self.dispatch(v)
interleave(lambda: self.write(", "), writem, zip(t.keys, t.values))
self.write("}")
def _Tuple(self, t):
self.write("(")
if len(t.elts) == 1:
(elt,) = t.elts
self.dispatch(elt)
self.write(",")
else:
interleave(lambda: self.write(", "), self.dispatch, t.elts)
self.write(")")
unop = {"Invert":"~", "Not": "not", "UAdd":"+", "USub":"-"}
def _UnaryOp(self, t):
self.write(self.unop[t.op.__class__.__name__])
self.write("(")
self.dispatch(t.operand)
self.write(")")
binop = { "Add":"+", "Sub":"-", "Mult":"*", "Div":"/", "Mod":"%",
"LShift":">>", "RShift":"<<", "BitOr":"|", "BitXor":"^", "BitAnd":"&",
"FloorDiv":"//", "Pow": "**"}
def _BinOp(self, t):
self.write("(")
self.dispatch(t.left)
self.write(" " + self.binop[t.op.__class__.__name__] + " ")
self.dispatch(t.right)
self.write(")")
cmpops = {"Eq":"==", "NotEq":"!=", "Lt":"<", "LtE":"<=", "Gt":">", "GtE":">=",
"Is":"is", "IsNot":"is not", "In":"in", "NotIn":"not in"}
def _Compare(self, t):
self.write("(")
self.dispatch(t.left)
for o, e in zip(t.ops, t.comparators):
self.write(" " + self.cmpops[o.__class__.__name__] + " ")
self.dispatch(e)
self.write(")")
boolops = {_ast.And: 'and', _ast.Or: 'or'}
def _BoolOp(self, t):
self.write("(")
s = " %s " % self.boolops[t.op.__class__]
interleave(lambda: self.write(s), self.dispatch, t.values)
self.write(")")
def _Attribute(self,t):
self.dispatch(t.value)
self.write(".")
self.write(t.attr)
def _Call(self, t):
self.dispatch(t.func)
self.write("(")
comma = False
for e in t.args:
if comma: self.write(", ")
else: comma = True
self.dispatch(e)
for e in t.keywords:
if comma: self.write(", ")
else: comma = True
self.dispatch(e)
if t.starargs:
if comma: self.write(", ")
else: comma = True
self.write("*")
self.dispatch(t.starargs)
if t.kwargs:
if comma: self.write(", ")
else: comma = True
self.write("**")
self.dispatch(t.kwargs)
self.write(")")
def _Subscript(self, t):
self.dispatch(t.value)
self.write("[")
self.dispatch(t.slice)
self.write("]")
# slice
def _Ellipsis(self, t):
self.write("...")
def _Index(self, t):
self.dispatch(t.value)
def _Slice(self, t):
if t.lower:
self.dispatch(t.lower)
self.write(":")
if t.upper:
self.dispatch(t.upper)
if t.step:
self.write(":")
self.dispatch(t.step)
def _ExtSlice(self, t):
interleave(lambda: self.write(', '), self.dispatch, t.dims)
# others
def _arguments(self, t):
first = True
nonDef = len(t.args)-len(t.defaults)
for a in t.args[0:nonDef]:
if first:first = False
else: self.write(", ")
self.dispatch(a)
for a,d in zip(t.args[nonDef:], t.defaults):
if first:first = False
else: self.write(", ")
self.dispatch(a),
self.write("=")
self.dispatch(d)
if t.vararg:
if first:first = False
else: self.write(", ")
self.write("*"+t.vararg)
if t.kwarg:
if first:first = False
else: self.write(", ")
self.write("**"+t.kwarg)
def _keyword(self, t):
self.write(t.arg)
self.write("=")
self.dispatch(t.value)
def _Lambda(self, t):
self.write("lambda ")
self.dispatch(t.args)
self.write(": ")
self.dispatch(t.body)
def _alias(self, t):
self.write(t.name)
if t.asname:
self.write(" as "+t.asname)
def roundtrip(filename, output=sys.stdout):
source = open(filename).read()
tree = compile(source, filename, "exec", _ast.PyCF_ONLY_AST)
Unparser(tree, output)
def testdir(a):
try:
names = [n for n in os.listdir(a) if n.endswith('.py')]
except OSError:
print >> sys.stderr, "Directory not readable: %s" % a
else:
for n in names:
fullname = os.path.join(a, n)
if os.path.isfile(fullname):
output = cStringIO.StringIO()
print 'Testing %s' % fullname
try:
roundtrip(fullname, output)
except Exception, e:
print ' Failed to compile, exception is %s' % repr(e)
elif os.path.isdir(fullname):
testdir(fullname)
def main(args):
if args[0] == '--testdir':
for a in args[1:]:
testdir(a)
else:
for a in args:
roundtrip(a)
if __name__=='__main__':
main(sys.argv[1:])