source: trunk/essentials/dev-lang/python/Lib/pyclbr.py@ 3226

"""Parse a Python module and describe its classes and methods.

Parse enough of a Python file to recognize imports and class and
method definitions, and to find out the superclasses of a class.

The interface consists of a single function:
        readmodule_ex(module [, path])
where module is the name of a Python module, and 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.  One special key/value pair
is present for packages: the key '__path__' has a list as its value
which contains the package search path.

A class is described by the class Class in this module.  Instances
of this class have the following instance variables:
        module -- the module name
        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.

A function is described by the class Function in this module.
Instances of this class have the following instance variables:
        module -- the module name
        name -- the name of the class
        file -- the file in which the class was defined
        lineno -- the line in the file on which the class statement occurred
"""

import sys
import imp
import tokenize # Python tokenizer
from token import NAME, DEDENT, NEWLINE, OP
from operator import itemgetter

__all__ = ["readmodule", "readmodule_ex", "Class", "Function"]

_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 to represent a top-level Python function'''
    def __init__(self, module, name, file, lineno):
        self.module = module
        self.name = name
        self.file = file
        self.lineno = lineno

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

    Call readmodule_ex() and then only keep Class objects from the
    resulting dictionary.'''

    dict = _readmodule(module, path)
    res = {}
    for key, value in dict.items():
        if isinstance(value, Class):
            res[key] = value
    return res

def readmodule_ex(module, path=[]):
    '''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.

    If INPACKAGE is true, it must be the dotted name of the package in
    which we are searching for a submodule, and then PATH must be the
    package search path; otherwise, we are searching for a top-level
    module, and PATH is combined with sys.path.
    '''
    return _readmodule(module, path)

def _readmodule(module, path, inpackage=None):
    '''Do the hard work for readmodule[_ex].'''
    # Compute the full module name (prepending inpackage if set)
    if inpackage:
        fullmodule = "%s.%s" % (inpackage, module)
    else:
        fullmodule = module

    # Check in the cache
    if fullmodule in _modules:
        return _modules[fullmodule]

    # Initialize the dict for this module's contents
    dict = {}

    # Check if it is a built-in module; we don't do much for these
    if module in sys.builtin_module_names and not inpackage:
        _modules[module] = dict
        return dict

    # Check for a dotted module name
    i = module.rfind('.')