2000-02-04 23:39:30 +08:00
|
|
|
"""Parse a Python file and retrieve classes and methods.
|
1995-07-28 17:30:01 +08:00
|
|
|
|
|
|
|
Parse enough of a Python file to recognize class and method
|
|
|
|
definitions and to find out the superclasses of a class.
|
|
|
|
|
|
|
|
The interface consists of a single function:
|
2001-01-15 08:50:52 +08:00
|
|
|
readmodule(module, path)
|
1995-07-28 17:30:01 +08:00
|
|
|
module is the name of a Python module, path is an optional list of
|
|
|
|
directories where the module is to be searched. If present, path is
|
|
|
|
prepended to the system search path sys.path.
|
|
|
|
The return value is a dictionary. The keys of the dictionary are
|
|
|
|
the names of the classes defined in the module (including classes
|
|
|
|
that are defined via the from XXX import YYY construct). The values
|
|
|
|
are class instances of the class Class defined here.
|
|
|
|
|
|
|
|
A class is described by the class Class in this module. Instances
|
|
|
|
of this class have the following instance variables:
|
2001-01-15 08:50:52 +08:00
|
|
|
name -- the name of the class
|
|
|
|
super -- a list of super classes (Class instances)
|
|
|
|
methods -- a dictionary of methods
|
|
|
|
file -- the file in which the class was defined
|
|
|
|
lineno -- the line in the file on which the class statement occurred
|
1995-07-28 17:30:01 +08:00
|
|
|
The dictionary of methods uses the method names as keys and the line
|
|
|
|
numbers on which the method was defined as values.
|
|
|
|
If the name of a super class is not recognized, the corresponding
|
|
|
|
entry in the list of super classes is not a class instance but a
|
|
|
|
string giving the name of the super class. Since import statements
|
|
|
|
are recognized and imported modules are scanned as well, this
|
|
|
|
shouldn't happen often.
|
|
|
|
|
|
|
|
BUGS
|
2001-10-25 04:22:40 +08:00
|
|
|
- Continuation lines are not dealt with at all, except inside strings.
|
|
|
|
- Nested classes and functions can confuse it.
|
1999-06-11 03:05:54 +08:00
|
|
|
- Code that doesn't pass tabnanny or python -t will confuse it, unless
|
|
|
|
you set the module TABWIDTH vrbl (default 8) to the correct tab width
|
|
|
|
for the file.
|
|
|
|
|
|
|
|
PACKAGE RELATED BUGS
|
|
|
|
- If you have a package and a module inside that or another package
|
|
|
|
with the same name, module caching doesn't work properly since the
|
|
|
|
key is the base name of the module/package.
|
|
|
|
- The only entry that is returned when you readmodule a package is a
|
|
|
|
__path__ whose value is a list which confuses certain class browsers.
|
|
|
|
- When code does:
|
|
|
|
from package import subpackage
|
|
|
|
class MyClass(subpackage.SuperClass):
|
|
|
|
...
|
|
|
|
It can't locate the parent. It probably needs to have the same
|
|
|
|
hairy logic that the import locator already does. (This logic
|
|
|
|
exists coded in Python in the freeze package.)
|
2000-02-04 23:39:30 +08:00
|
|
|
"""
|
1995-07-28 17:30:01 +08:00
|
|
|
|
|
|
|
import sys
|
|
|
|
import imp
|
1997-10-24 22:46:16 +08:00
|
|
|
import re
|
1995-07-28 17:30:01 +08:00
|
|
|
import string
|
|
|
|
|
2001-02-12 10:00:42 +08:00
|
|
|
__all__ = ["readmodule"]
|
|
|
|
|
1999-06-08 20:53:21 +08:00
|
|
|
TABWIDTH = 8
|
|
|
|
|
1999-06-07 23:25:18 +08:00
|
|
|
_getnext = re.compile(r"""
|
1999-06-08 20:53:21 +08:00
|
|
|
(?P<String>
|
|
|
|
\""" [^"\\]* (?:
|
2001-01-15 08:50:52 +08:00
|
|
|
(?: \\. | "(?!"") )
|
|
|
|
[^"\\]*
|
|
|
|
)*
|
1999-06-08 20:53:21 +08:00
|
|
|
\"""
|
|
|
|
|
|
|
|
| ''' [^'\\]* (?:
|
2001-01-15 08:50:52 +08:00
|
|
|
(?: \\. | '(?!'') )
|
|
|
|
[^'\\]*
|
|
|
|
)*
|
|
|
|
'''
|
2001-10-25 04:22:40 +08:00
|
|
|
|
|
|
|
| " [^"\\\n]* (?: \\. [^"\\\n]*)* "
|
|
|
|
|
|
|
|
| ' [^'\\\n]* (?: \\. [^'\\\n]*)* '
|
1999-06-08 20:53:21 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
| (?P<Method>
|
2001-01-15 08:50:52 +08:00
|
|
|
^
|
|
|
|
(?P<MethodIndent> [ \t]* )
|
|
|
|
def [ \t]+
|
|
|
|
(?P<MethodName> [a-zA-Z_] \w* )
|
|
|
|
[ \t]* \(
|
1999-06-07 23:25:18 +08:00
|
|
|
)
|
1995-07-28 17:30:01 +08:00
|
|
|
|
1999-06-07 23:25:18 +08:00
|
|
|
| (?P<Class>
|
2001-01-15 08:50:52 +08:00
|
|
|
^
|
|
|
|
(?P<ClassIndent> [ \t]* )
|
|
|
|
class [ \t]+
|
|
|
|
(?P<ClassName> [a-zA-Z_] \w* )
|
|
|
|
[ \t]*
|
|
|
|
(?P<ClassSupers> \( [^)\n]* \) )?
|
|
|
|
[ \t]* :
|
1999-06-07 23:25:18 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
| (?P<Import>
|
2001-01-15 08:50:52 +08:00
|
|
|
^ import [ \t]+
|
|
|
|
(?P<ImportList> [^#;\n]+ )
|
1999-06-07 23:25:18 +08:00
|
|
|
)
|
|
|
|
|
|
|
|
| (?P<ImportFrom>
|
2001-01-15 08:50:52 +08:00
|
|
|
^ from [ \t]+
|
|
|
|
(?P<ImportFromPath>
|
|
|
|
[a-zA-Z_] \w*
|
|
|
|
(?:
|
|
|
|
[ \t]* \. [ \t]* [a-zA-Z_] \w*
|
|
|
|
)*
|
|
|
|
)
|
|
|
|
[ \t]+
|
|
|
|
import [ \t]+
|
|
|
|
(?P<ImportFromList> [^#;\n]+ )
|
1999-06-07 23:25:18 +08:00
|
|
|
)
|
|
|
|
""", re.VERBOSE | re.DOTALL | re.MULTILINE).search
|
|
|
|
|
|
|
|
_modules = {} # cache of modules we've seen
|
1995-07-28 17:30:01 +08:00
|
|
|
|
|
|
|
# each Python class is represented by an instance of this class
|
|
|
|
class Class:
|
2001-01-15 08:50:52 +08:00
|
|
|
'''Class to represent a Python class.'''
|
|
|
|
def __init__(self, module, name, super, file, lineno):
|
|
|
|
self.module = module
|
|
|
|
self.name = name
|
|
|
|
if super is None:
|
|
|
|
super = []
|
|
|
|
self.super = super
|
|
|
|
self.methods = {}
|
|
|
|
self.file = file
|
|
|
|
self.lineno = lineno
|
|
|
|
|
|
|
|
def _addmethod(self, name, lineno):
|
|
|
|
self.methods[name] = lineno
|
1995-07-28 17:30:01 +08:00
|
|
|
|
1999-06-10 22:39:39 +08:00
|
|
|
class Function(Class):
|
2001-01-15 08:50:52 +08:00
|
|
|
'''Class to represent a top-level Python function'''
|
|
|
|
def __init__(self, module, name, file, lineno):
|
|
|
|
Class.__init__(self, module, name, None, file, lineno)
|
|
|
|
def _addmethod(self, name, lineno):
|
|
|
|
assert 0, "Function._addmethod() shouldn't be called"
|
1999-06-10 22:39:39 +08:00
|
|
|
|
1998-10-12 23:21:38 +08:00
|
|
|
def readmodule(module, path=[], inpackage=0):
|
2001-01-15 08:50:52 +08:00
|
|
|
'''Backwards compatible interface.
|
1999-06-10 22:39:39 +08:00
|
|
|
|
2001-01-15 08:50:52 +08:00
|
|
|
Like readmodule_ex() but strips Function objects from the
|
|
|
|
resulting dictionary.'''
|
1999-06-10 22:39:39 +08:00
|
|
|
|
2001-01-15 08:50:52 +08:00
|
|
|
dict = readmodule_ex(module, path, inpackage)
|
|
|
|
res = {}
|
|
|
|
for key, value in dict.items():
|
|
|
|
if not isinstance(value, Function):
|
|
|
|
res[key] = value
|
|
|
|
return res
|
1999-06-10 22:39:39 +08:00
|
|
|
|
|
|
|
def readmodule_ex(module, path=[], inpackage=0):
|
2001-01-15 08:50:52 +08:00
|
|
|
'''Read a module file and return a dictionary of classes.
|
|
|
|
|
|
|
|
Search for MODULE in PATH and sys.path, read and parse the
|
|
|
|
module and return a dictionary with one entry for each class
|
|
|
|
found in the module.'''
|
|
|
|
|
|
|
|
dict = {}
|
|
|
|
|
2001-02-09 17:39:08 +08:00
|
|
|
i = module.rfind('.')
|
2001-01-15 08:50:52 +08:00
|
|
|
if i >= 0:
|
|
|
|
# Dotted module name
|
2001-02-09 17:39:08 +08:00
|
|
|
package = module[:i].strip()
|
|
|
|
submodule = module[i+1:].strip()
|
2001-08-14 04:20:51 +08:00
|
|
|
parent = readmodule_ex(package, path, inpackage)
|
|
|
|
child = readmodule_ex(submodule, parent['__path__'], 1)
|
2001-01-15 08:50:52 +08:00
|
|
|
return child
|
|
|
|
|
2002-06-01 22:18:47 +08:00
|
|
|
if module in _modules:
|
2001-01-15 08:50:52 +08:00
|
|
|
# we've seen this module before...
|
|
|
|
return _modules[module]
|
|
|
|
if module in sys.builtin_module_names:
|
|
|
|
# this is a built-in module
|
|
|
|
_modules[module] = dict
|
|
|
|
return dict
|
|
|
|
|
|
|
|
# search the path for the module
|
|
|
|
f = None
|
|
|
|
if inpackage:
|
|
|
|
try:
|
|
|
|
f, file, (suff, mode, type) = \
|
|
|
|
imp.find_module(module, path)
|
|
|
|
except ImportError:
|
|
|
|
f = None
|
|
|
|
if f is None:
|
|
|
|
fullpath = list(path) + sys.path
|
|
|
|
f, file, (suff, mode, type) = imp.find_module(module, fullpath)
|
|
|
|
if type == imp.PKG_DIRECTORY:
|
|
|
|
dict['__path__'] = [file]
|
|
|
|
_modules[module] = dict
|
|
|
|
path = [file] + path
|
|
|
|
f, file, (suff, mode, type) = \
|
|
|
|
imp.find_module('__init__', [file])
|
|
|
|
if type != imp.PY_SOURCE:
|
|
|
|
# not Python source, can't do anything with this module
|
|
|
|
f.close()
|
|
|
|
_modules[module] = dict
|
|
|
|
return dict
|
|
|
|
|
|
|
|
_modules[module] = dict
|
|
|
|
classstack = [] # stack of (class, indent) pairs
|
|
|
|
src = f.read()
|
|
|
|
f.close()
|
|
|
|
|
|
|
|
# To avoid having to stop the regexp at each newline, instead
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 23:58:32 +08:00
|
|
|
# when we need a line number we simply count the number of
|
2001-01-15 08:50:52 +08:00
|
|
|
# newlines in the string since the last time we did this; i.e.,
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 23:58:32 +08:00
|
|
|
# lineno += src.count('\n', last_lineno_pos, here)
|
2001-01-15 08:50:52 +08:00
|
|
|
# last_lineno_pos = here
|
|
|
|
lineno, last_lineno_pos = 1, 0
|
|
|
|
i = 0
|
|
|
|
while 1:
|
|
|
|
m = _getnext(src, i)
|
|
|
|
if not m:
|
|
|
|
break
|
|
|
|
start, i = m.span()
|
|
|
|
|
|
|
|
if m.start("Method") >= 0:
|
|
|
|
# found a method definition or function
|
|
|
|
thisindent = _indent(m.group("MethodIndent"))
|
|
|
|
meth_name = m.group("MethodName")
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 23:58:32 +08:00
|
|
|
lineno += src.count('\n', last_lineno_pos, start)
|
2001-01-15 08:50:52 +08:00
|
|
|
last_lineno_pos = start
|
|
|
|
# close all classes indented at least as much
|
|
|
|
while classstack and \
|
|
|
|
classstack[-1][1] >= thisindent:
|
|
|
|
del classstack[-1]
|
|
|
|
if classstack:
|
|
|
|
# it's a class method
|
|
|
|
cur_class = classstack[-1][0]
|
|
|
|
cur_class._addmethod(meth_name, lineno)
|
|
|
|
else:
|
|
|
|
# it's a function
|
|
|
|
f = Function(module, meth_name,
|
|
|
|
file, lineno)
|
|
|
|
dict[meth_name] = f
|
|
|
|
|
|
|
|
elif m.start("String") >= 0:
|
|
|
|
pass
|
|
|
|
|
|
|
|
elif m.start("Class") >= 0:
|
|
|
|
# we found a class definition
|
|
|
|
thisindent = _indent(m.group("ClassIndent"))
|
|
|
|
# close all classes indented at least as much
|
|
|
|
while classstack and \
|
|
|
|
classstack[-1][1] >= thisindent:
|
|
|
|
del classstack[-1]
|
Remove uses of the string and types modules:
x in string.whitespace => x.isspace()
type(x) in types.StringTypes => isinstance(x, basestring)
isinstance(x, types.StringTypes) => isinstance(x, basestring)
type(x) is types.StringType => isinstance(x, str)
type(x) == types.StringType => isinstance(x, str)
string.split(x, ...) => x.split(...)
string.join(x, y) => y.join(x)
string.zfill(x, ...) => x.zfill(...)
string.count(x, ...) => x.count(...)
hasattr(types, "UnicodeType") => try: unicode except NameError:
type(x) != types.TupleTuple => not isinstance(x, tuple)
isinstance(x, types.TupleType) => isinstance(x, tuple)
type(x) is types.IntType => isinstance(x, int)
Do not mention the string module in the rlcompleter docstring.
This partially applies SF patch http://www.python.org/sf/562373
(with basestring instead of string). (It excludes the changes to
unittest.py and does not change the os.stat stuff.)
2002-06-03 23:58:32 +08:00
|
|
|
lineno += src.count('\n', last_lineno_pos, start)
|
2001-01-15 08:50:52 +08:00
|
|
|
last_lineno_pos = start
|
|
|
|
class_name = m.group("ClassName")
|
|
|
|
inherit = m.group("ClassSupers")
|
|
|
|
if inherit:
|
|
|
|
# the class inherits from other classes
|
2001-02-09 17:39:08 +08:00
|
|
|
inherit = inherit[1:-1].strip()
|
2001-01-15 08:50:52 +08:00
|
|
|
names = []
|
2001-02-09 17:39:08 +08:00
|
|
|
for n in inherit.split(','):
|
|
|
|
n = n.strip()
|
2002-06-01 22:18:47 +08:00
|
|
|
if n in dict:
|
2001-01-15 08:50:52 +08:00
|
|
|
# we know this super class
|
|
|
|
n = dict[n]
|
|
|
|
else:
|
2001-02-09 17:39:08 +08:00
|
|
|
c = n.split('.')
|
2001-01-15 08:50:52 +08:00
|
|
|
if len(c) > 1:
|
|
|
|
# super class
|
|
|
|
# is of the
|
|
|
|
# form module.class:
|
|
|
|
# look in
|
|
|
|
# module for class
|
|
|
|
m = c[-2]
|
|
|
|
c = c[-1]
|
2002-06-01 22:18:47 +08:00
|
|
|
if m in _modules:
|
2001-01-15 08:50:52 +08:00
|
|
|
d = _modules[m]
|
2002-06-01 22:18:47 +08:00
|
|
|
if c in d:
|
2001-01-15 08:50:52 +08:00
|
|
|
n = d[c]
|
|
|
|
names.append(n)
|
|
|
|
inherit = names
|
|
|
|
# remember this class
|
|
|
|
cur_class = Class(module, class_name, inherit,
|
|
|
|
file, lineno)
|
|
|
|
dict[class_name] = cur_class
|
|
|
|
classstack.append((cur_class, thisindent))
|
|
|
|
|
|
|
|
elif m.start("Import") >= 0:
|
|
|
|
# import module
|
2001-02-09 17:39:08 +08:00
|
|
|
for n in m.group("ImportList").split(','):
|
|
|
|
n = n.strip()
|
2001-01-15 08:50:52 +08:00
|
|
|
try:
|
|
|
|
# recursively read the imported module
|
2001-08-14 04:20:51 +08:00
|
|
|
d = readmodule_ex(n, path, inpackage)
|
2001-01-15 08:50:52 +08:00
|
|
|
except:
|
|
|
|
##print 'module', n, 'not found'
|
|
|
|
pass
|
|
|
|
|
|
|
|
elif m.start("ImportFrom") >= 0:
|
|
|
|
# from module import stuff
|
|
|
|
mod = m.group("ImportFromPath")
|
2001-02-09 17:39:08 +08:00
|
|
|
names = m.group("ImportFromList").split(',')
|
2001-01-15 08:50:52 +08:00
|
|
|
try:
|
|
|
|
# recursively read the imported module
|
2001-08-14 04:20:51 +08:00
|
|
|
d = readmodule_ex(mod, path, inpackage)
|
2001-01-15 08:50:52 +08:00
|
|
|
except:
|
|
|
|
##print 'module', mod, 'not found'
|
|
|
|
continue
|
|
|
|
# add any classes that were defined in the
|
|
|
|
# imported module to our name space if they
|
|
|
|
# were mentioned in the list
|
|
|
|
for n in names:
|
2001-02-09 17:39:08 +08:00
|
|
|
n = n.strip()
|
2002-06-01 22:18:47 +08:00
|
|
|
if n in d:
|
2001-01-15 08:50:52 +08:00
|
|
|
dict[n] = d[n]
|
|
|
|
elif n == '*':
|
|
|
|
# only add a name if not
|
|
|
|
# already there (to mimic what
|
|
|
|
# Python does internally)
|
|
|
|
# also don't add names that
|
|
|
|
# start with _
|
2002-06-03 02:55:56 +08:00
|
|
|
for n in d:
|
2001-01-15 08:50:52 +08:00
|
|
|
if n[0] != '_' and \
|
2002-06-01 22:18:47 +08:00
|
|
|
not n in dict:
|
2001-01-15 08:50:52 +08:00
|
|
|
dict[n] = d[n]
|
|
|
|
else:
|
|
|
|
assert 0, "regexp _getnext found something unexpected"
|
|
|
|
|
|
|
|
return dict
|
1999-06-08 20:53:21 +08:00
|
|
|
|
|
|
|
def _indent(ws, _expandtabs=string.expandtabs):
|
2001-01-15 08:50:52 +08:00
|
|
|
return len(_expandtabs(ws, TABWIDTH))
|