summaryrefslogtreecommitdiffstats
path: root/Lib/pyclbr.py
blob: fad46add86e37701b03ca9a75b26cd37f00d7f82 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
"""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 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
    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_ex(package, path, inpackage)
        child = readmodule_ex(submodule, parent['__path__'], 1)
        return child

    if module in _modules:
        # 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
    # 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 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)
                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_ex(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_ex(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 n in d:
                    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:
                        if n[0] != '_' and \
                           not n in dict:
                            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))