/Lib/pyclbr.py (d7dba9761851ea8ff4439d557cf704c7f701b501) (13558 bytes) (mode 100644) (type blob)

"""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 io
import sys
import importlib.util
import tokenize
from token import NAME, DEDENT, OP

__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=None):
    '''Backwards compatible interface.

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

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

def readmodule_ex(module, path=None):
    '''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.
    '''
    return _readmodule(module, path or [])

def _readmodule(module, path, inpackage=None):
    '''Do the hard work for readmodule[_ex].

    If INPACKAGE is given, 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.
    '''
    # Compute the full module name (prepending inpackage if set)
    if inpackage is not None:
        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 inpackage is None:
        _modules[module] = dict
        return dict

    # Check for a dotted module name
    i = module.rfind('.')
    if i >= 0:
        package = module[:i]
        submodule = module[i+1:]
        parent = _readmodule(package, path, inpackage)
        if inpackage is not None:
            package = "%s.%s" % (inpackage, package)
        if not '__path__' in parent:
            raise ImportError('No package named {}'.format(package))
        return _readmodule(submodule, parent['__path__'], package)

    # Search the path for the module
    f = None
    if inpackage is not None:
        search_path = path
    else:
        search_path = path + sys.path
    # XXX This will change once issue19944 lands.
    spec = importlib.util._find_spec_from_path(fullmodule, search_path)
    _modules[fullmodule] = dict
    # is module a package?
    if spec.submodule_search_locations is not None:
        dict['__path__'] = spec.submodule_search_locations
    try:
        source = spec.loader.get_source(fullmodule)
        if source is None:
            return dict
    except (AttributeError, ImportError):
        # not Python source, can't do anything with this module
        return dict

    fname = spec.loader.get_filename(fullmodule)

    f = io.StringIO(source)

    stack = [] # stack of (class, indent) pairs

    g = tokenize.generate_tokens(f.readline)
    try:
        for tokentype, token, start, _end, _line in g:
            if tokentype == DEDENT:
                lineno, thisindent = start
                # close nested classes and defs
                while stack and stack[-1][1] >= thisindent:
                    del stack[-1]
            elif token == 'def':
                lineno, thisindent = start
                # close previous nested classes and defs
                while stack and stack[-1][1] >= thisindent:
                    del stack[-1]
                tokentype, meth_name, start = next(g)[0:3]
                if tokentype != NAME:
                    continue # Syntax error
                if stack:
                    cur_class = stack[-1][0]
                    if isinstance(cur_class, Class):
                        # it's a method
                        cur_class._addmethod(meth_name, lineno)
                    # else it's a nested def
                else:
                    # it's a function
                    dict[meth_name] = Function(fullmodule, meth_name,
                                               fname, lineno)
                stack.append((None, thisindent)) # Marker for nested fns
            elif token == 'class':
                lineno, thisindent = start
                # close previous nested classes and defs
                while stack and stack[-1][1] >= thisindent:
                    del stack[-1]
                tokentype, class_name, start = next(g)[0:3]
                if tokentype != NAME:
                    continue # Syntax error
                # parse what follows the class name
                tokentype, token, start = next(g)[0:3]
                inherit = None
                if token == '(':
                    names = [] # List of superclasses
                    # there's a list of superclasses
                    level = 1
                    super = [] # Tokens making up current superclass
                    while True:
                        tokentype, token, start = next(g)[0:3]
                        if token in (')', ',') and level == 1:
                            n = "".join(super)
                            if n in dict:
                                # 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 m in _modules:
                                        d = _modules[m]
                                        if c in d:
                                            n = d[c]
                            names.append(n)
                            super = []
                        if token == '(':
                            level += 1
                        elif token == ')':
                            level -= 1
                            if level == 0:
                                break
                        elif token == ',' and level == 1:
                            pass
                        # only use NAME and OP (== dot) tokens for type name
                        elif tokentype in (NAME, OP) and level == 1:
                            super.append(token)
                        # expressions in the base list are not supported
                    inherit = names
                cur_class = Class(fullmodule, class_name, inherit,
                                  fname, lineno)
                if not stack:
                    dict[class_name] = cur_class
                stack.append((cur_class, thisindent))
            elif token == 'import' and start[1] == 0:
                modules = _getnamelist(g)
                for mod, _mod2 in modules:
                    try:
                        # Recursively read the imported module
                        if inpackage is None:
                            _readmodule(mod, path)
                        else:
                            try:
                                _readmodule(mod, path, inpackage)
                            except ImportError:
                                _readmodule(mod, [])
                    except:
                        # If we can't find or parse the imported module,
                        # too bad -- don't die here.
                        pass
            elif token == 'from' and start[1] == 0:
                mod, token = _getname(g)
                if not mod or token != "import":
                    continue
                names = _getnamelist(g)
                try:
                    # Recursively read the imported module
                    d = _readmodule(mod, path, inpackage)
                except:
                    # If we can't find or parse the imported module,
                    # too bad -- don't die here.
                    continue
                # add any classes that were defined in the imported module
                # to our name space if they were mentioned in the list
                for n, n2 in names:
                    if n in d:
                        dict[n2 or n] = d[n]
                    elif n == '*':
                        # don't add names that start with _
                        for n in d:
                            if n[0] != '_':
                                dict[n] = d[n]
    except StopIteration:
        pass

    f.close()
    return dict

def _getnamelist(g):
    # Helper to get a comma-separated list of dotted names plus 'as'
    # clauses.  Return a list of pairs (name, name2) where name2 is
    # the 'as' name, or None if there is no 'as' clause.
    names = []
    while True:
        name, token = _getname(g)
        if not name:
            break
        if token == 'as':
            name2, token = _getname(g)
        else:
            name2 = None
        names.append((name, name2))
        while token != "," and "\n" not in token:
            token = next(g)[1]
        if token != ",":
            break
    return names

def _getname(g):
    # Helper to get a dotted name, return a pair (name, token) where
    # name is the dotted name, or None if there was no dotted name,
    # and token is the next input token.
    parts = []
    tokentype, token = next(g)[0:2]
    if tokentype != NAME and token != '*':
        return (None, token)
    parts.append(token)
    while True:
        tokentype, token = next(g)[0:2]
        if token != '.':
            break
        tokentype, token = next(g)[0:2]
        if tokentype != NAME:
            break
        parts.append(token)
    return (".".join(parts), token)

def _main():
    # Main program for testing.
    import os
    from operator import itemgetter
    mod = sys.argv[1]
    if os.path.exists(mod):
        path = [os.path.dirname(mod)]
        mod = os.path.basename(mod)
        if mod.lower().endswith(".py"):
            mod = mod[:-3]
    else:
        path = []
    dict = readmodule_ex(mod, path)
    objs = list(dict.values())
    objs.sort(key=lambda a: getattr(a, 'lineno', 0))
    for obj in objs:
        if isinstance(obj, Class):
            print("class", obj.name, obj.super, obj.lineno)
            methods = sorted(obj.methods.items(), key=itemgetter(1))
            for name, lineno in methods:
                if name != "__path__":
                    print("  def", name, lineno)
        elif isinstance(obj, Function):
            print("def", obj.name, obj.lineno)

if __name__ == "__main__":
    _main()


Mode Type Size Ref File
100644 blob 582 58471109208922c9ee8c4b06135725f03ed16814 .bzrignore
100644 blob 545 fcf9df6a7a698e4bd87ed0c1cc4ed70bad8b9887 .codecov.yml
100644 blob 255 82694d81f276b2c59a0a93a4f678e1852e625052 .gitattributes
040000 tree - 7e849e161267e730810fbbe6a848b14d5d002788 .github
100644 blob 1397 8b54c2c4861389f6e8bbfbab5ae0c8b6bbbad041 .gitignore
100644 blob 1060 eb19a6c88d28d05588db25d21525ee2e19c22666 .hgeol
100644 blob 1358 68c607f2e8d420c8dfd0748efcd3b3b5447def16 .hgignore
100644 blob 8917 8f51c2ced49aed46d8b480280b630ea4264c57c3 .hgtags
100644 blob 1328 b9be0f11fdb829f16e9de1921257eb7ee45fac57 .hgtouch
100644 blob 248 0614a299b6221dc7faedaa9139ae8b034e618a85 .mention-bot
100644 blob 3512 e7e8694530ca21a6d7a19da3fab687a3e9d79e9c .travis.yml
040000 tree - ab6ef0c3da91d215c813859260aa9d0724504633 Doc
040000 tree - 5dd6fc9dc09374506491247872c868eca111e256 Grammar
040000 tree - df0de9d4359f11311c74fd0dbad471bb2613a2d4 Include
100644 blob 12773 f5d0b39a0cdddb91a31a537052b7d8d31a4aa79f LICENSE
040000 tree - 35e9c80068a1b6441f6a676002e031d908be567f Lib
040000 tree - 1db7415d4375525eaf8d05ddd5b088de3321041c Mac
100644 blob 58983 4145634c032d543d02295bd2c28a0c6ce839fa86 Makefile.pre.in
040000 tree - 6854ababa88443950a60516508b6994cfd8888db Misc
040000 tree - 92e4f07c6b277cc3dae87514f9cebce860ec55ba Modules
040000 tree - cec92311ba9c836d7f68a2d6e24b27e8287ac690 Objects
040000 tree - ed4f35810e9633502c16ae038c2ce697d3987201 PC
040000 tree - 37a613ac0022a9cfefaf3f13913fec7debe59259 PCbuild
040000 tree - bfcd1ca2e85b8724b1b7be4e0673b90220a04e7c Parser
040000 tree - 3efbcc80237ab7c3d4eb5bf31c893ca6de88e747 Programs
040000 tree - 8f832869b53d99ee02d78ea0cc8491d3882222da Python
100644 blob 9325 9c95815d9e9d91b8dae8e05d8bbc696fe19f796b README.rst
040000 tree - 66b8a7e032e5538a9a2e08422da3716c50e91a4b Tools
100644 blob 10910 9a9cc557281571f0d46c506c0e9d1b9fb25e063c aclocal.m4
100755 blob 42856 1f5c50c0d1529d50b94dc3533ca72a47f0fa5849 config.guess
100755 blob 35740 d654d03cdcd2226a5d7584890717e674a8122f4f config.sub
100755 blob 485283 87504d206837baf5a5781b6e1cc44dcce7138af9 configure
100644 blob 160661 f9bd92ce3da29ea7674a32bd5fe511b1fc4c4d0a configure.ac
100755 blob 7122 0ec27bcd488da5cad6ead13d70accbdbc40d31ef install-sh
100644 blob 41449 21354a5cb84fe5530dd0d460561ba95569abe1d4 pyconfig.h.in
100644 blob 98743 3b3d097454211c790c1602d759918bb65a622c97 setup.py
Hints:
Before first commit, do not forget to setup your git environment:
git config --global user.name "your_name_here"
git config --global user.email "your@email_here"

Clone this repository using HTTP(S):
git clone https://rocketgit.com/user/benf_wspdigital/cpython

Clone this repository using ssh (do not forget to upload a key first):
git clone ssh://rocketgit@ssh.rocketgit.com/user/benf_wspdigital/cpython

Clone this repository using git:
git clone git://git.rocketgit.com/user/benf_wspdigital/cpython

You are allowed to anonymously push to this repository.
This means that your pushed commits will automatically be transformed into a merge request:
... clone the repository ...
... make some changes and some commits ...
git push origin main