pyclbr.py :  » Language-Interface » ChinesePython » chinesepython2.1.3-0.4 » Lib » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Language Interface » ChinesePython 
ChinesePython » chinesepython2.1.3 0.4 » Lib » pyclbr.py
"""Parse a Python file and retrieve classes and methods.

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:
        readmodule(module, path)
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:
        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
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
- Continuation lines are not dealt with at all, except inside strings.
- Nested classes and functions can confuse it.
- 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.)
"""

import os
import sys
import imp
import re
import string

__all__ = ["readmodule"]

TABWIDTH = 8

_getnext = re.compile(r"""
    (?P<String>
       \""" [^"\\]* (?:
                        (?: \\. | "(?!"") )
                        [^"\\]*
                    )*
       \"""

    |   ''' [^'\\]* (?:
                        (?: \\. | '(?!'') )
                        [^'\\]*
                    )*
        '''

    |   " [^"\\\n]* (?: \\. [^"\\\n]*)* "

    |   ' [^'\\\n]* (?: \\. [^'\\\n]*)* '
    )

|   (?P<Method>
        ^
        (?P<MethodIndent> [ \t]* )
        def [ \t]+
        (?P<MethodName> [a-zA-Z_] \w* )
        [ \t]* \(
    )

|   (?P<Class>
        ^
        (?P<ClassIndent> [ \t]* )
        class [ \t]+
        (?P<ClassName> [a-zA-Z_] \w* )
        [ \t]*
        (?P<ClassSupers> \( [^)\n]* \) )?
        [ \t]* :
    )

|   (?P<Import>
        ^ import [ \t]+
        (?P<ImportList> [^#;\n]+ )
    )

|   (?P<ImportFrom>
        ^ from [ \t]+
        (?P<ImportFromPath>
            [a-zA-Z_] \w*
            (?:
                [ \t]* \. [ \t]* [a-zA-Z_] \w*
            )*
        )
        [ \t]+
        import [ \t]+
        (?P<ImportFromList> [^#;\n]+ )
    )
""", re.VERBOSE | re.DOTALL | re.MULTILINE).search

_modules = {}                           # cache of modules we've seen

# each Python class is represented by an instance of this class
class Class:
    '''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

class Function(Class):
    '''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"

def readmodule(module, path=[], inpackage=0):
    '''Backwards compatible interface.

    Like readmodule_ex() but strips Function objects from the import 
    resulting dictionary.'''

    dict = readmodule_ex(module, path, inpackage)
    res = {}
    for key, value in dict.items():
        if not isinstance(value, Function):
            res[key] = value
    return res

def readmodule_ex(module, path=[], inpackage=0):
    '''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 = {}

    i = module.rfind('.')
    if i >= 0:
        # Dotted module name
        package = module[:i].strip()
        submodule = module[i+1:].strip()
        parent = readmodule(package, path, inpackage)
        child = readmodule(submodule, parent['__path__'], 1)
        return child

    if _modules.has_key(module):
        # 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
    imports = []
    classstack = [] # stack of (class, indent) pairs
    src = f.read()
    f.close()

    # To avoid having to stop the regexp at each newline, instead
    # when we need a line number we simply string.count the number of
    # newlines in the string since the last time we did this; i.e.,
    #    lineno = lineno + \
    #             string.count(src, '\n', last_lineno_pos, here)
    #    last_lineno_pos = here
    countnl = string.count
    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")
            lineno = lineno + \
                     countnl(src, '\n',
                             last_lineno_pos, start)
            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]
            lineno = lineno + \
                     countnl(src, '\n', last_lineno_pos, start)
            last_lineno_pos = start
            class_name = m.group("ClassName")
            inherit = m.group("ClassSupers")
            if inherit:
                # the class inherits from other classes
                inherit = inherit[1:-1].strip()
                names = []
                for n in inherit.split(','):
                    n = n.strip()
                    if dict.has_key(n):
                        # we know this super class
                        n = dict[n]
                    else:
                        c = n.split('.')
                        if len(c) > 1:
                            # super class
                            # is of the
                            # form module.class:
                            # look in
                            # module for class
                            m = c[-2]
                            c = c[-1]
                            if _modules.has_key(m):
                                d = _modules[m]
                                if d.has_key(c):
                                    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
            for n in m.group("ImportList").split(','):
                n = n.strip()
                try:
                    # recursively read the imported module
                    d = readmodule(n, path, inpackage)
                except:
                    ##print 'module', n, 'not found'
                    pass

        elif m.start("ImportFrom") >= 0:
            # from module import stuff
            mod = m.group("ImportFromPath")
            names = m.group("ImportFromList").split(',')
            try:
                # recursively read the imported module
                d = readmodule(mod, path, inpackage)
            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:
                n = n.strip()
                if d.has_key(n):
                    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 _
                    for n in d.keys():
                        if n[0] != '_' and \
                           not dict.has_key(n):
                            dict[n] = d[n]
        else:
            assert 0, "regexp _getnext found something unexpected"

    return dict

def _indent(ws, _expandtabs=string.expandtabs):
    return len(_expandtabs(ws, TABWIDTH))
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.