summaryrefslogtreecommitdiffstats
path: root/Lib/inspect.py
blob: 8f79bc34416709769b52081d582ed668f32b6986 (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
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
# -*- coding: iso-8859-1 -*-
"""Get useful information from live Python objects.

This module encapsulates the interface provided by the internal special
attributes (func_*, co_*, im_*, tb_*, etc.) in a friendlier fashion.
It also provides some help for examining source code and class layout.

Here are some of the useful functions provided by this module:

    ismodule(), isclass(), ismethod(), isfunction(), isgeneratorfunction(),
        isgenerator(), istraceback(), isframe(), iscode(), isbuiltin(),
        isroutine() - check object types
    getmembers() - get members of an object that satisfy a given condition

    getfile(), getsourcefile(), getsource() - find an object's source code
    getdoc(), getcomments() - get documentation on an object
    getmodule() - determine the module that an object came from
    getclasstree() - arrange classes so as to represent their hierarchy

    getargspec(), getargvalues(), getcallargs() - get info about function arguments
    formatargspec(), formatargvalues() - format an argument spec
    getouterframes(), getinnerframes() - get info about frames
    currentframe() - get the current stack frame
    stack(), trace() - get info about frames on the stack or in a traceback
"""

# This module is in the public domain.  No warranties.

__author__ = 'Ka-Ping Yee <ping@lfw.org>'
__date__ = '1 Jan 2001'

import sys
import os
import types
import string
import re
import dis
import imp
import tokenize
import linecache
from operator import attrgetter
from collections import namedtuple

# These constants are from Include/code.h.
CO_OPTIMIZED, CO_NEWLOCALS, CO_VARARGS, CO_VARKEYWORDS = 0x1, 0x2, 0x4, 0x8
CO_NESTED, CO_GENERATOR, CO_NOFREE = 0x10, 0x20, 0x40
# See Include/object.h
TPFLAGS_IS_ABSTRACT = 1 << 20

# ----------------------------------------------------------- type-checking
def ismodule(object):
    """Return true if the object is a module.

    Module objects provide these attributes:
        __doc__         documentation string
        __file__        filename (missing for built-in modules)"""
    return isinstance(object, types.ModuleType)

def isclass(object):
    """Return true if the object is a class.

    Class objects provide these attributes:
        __doc__         documentation string
        __module__      name of module in which this class was defined"""
    return isinstance(object, (type, types.ClassType))

def ismethod(object):
    """Return true if the object is an instance method.

    Instance method objects provide these attributes:
        __doc__         documentation string
        __name__        name with which this method was defined
        im_class        class object in which this method belongs
        im_func         function object containing implementation of method
        im_self         instance to which this method is bound, or None"""
    return isinstance(object, types.MethodType)

def ismethoddescriptor(object):
    """Return true if the object is a method descriptor.

    But not if ismethod() or isclass() or isfunction() are true.

    This is new in Python 2.2, and, for example, is true of int.__add__.
    An object passing this test has a __get__ attribute but not a __set__
    attribute, but beyond that the set of attributes varies.  __name__ is
    usually sensible, and __doc__ often is.

    Methods implemented via descriptors that also pass one of the other
    tests return false from the ismethoddescriptor() test, simply because
    the other tests promise more -- you can, e.g., count on having the
    im_func attribute (etc) when an object passes ismethod()."""
    return (hasattr(object, "__get__")
            and not hasattr(object, "__set__") # else it's a data descriptor
            and not ismethod(object)           # mutual exclusion
            and not isfunction(object)
            and not isclass(object))

def isdatadescriptor(object):
    """Return true if the object is a data descriptor.

    Data descriptors have both a __get__ and a __set__ attribute.  Examples are
    properties (defined in Python) and getsets and members (defined in C).
    Typically, data descriptors will also have __name__ and __doc__ attributes
    (properties, getsets, and members have both of these attributes), but this
    is not guaranteed."""
    return (hasattr(object, "__set__") and hasattr(object, "__get__"))

if hasattr(types, 'MemberDescriptorType'):
    # CPython and equivalent
    def ismemberdescriptor(object):
        """Return true if the object is a member descriptor.

        Member descriptors are specialized descriptors defined in extension
        modules."""
        return isinstance(object, types.MemberDescriptorType)
else:
    # Other implementations
    def ismemberdescriptor(object):
        """Return true if the object is a member descriptor.

        Member descriptors are specialized descriptors defined in extension
        modules."""
        return False

if hasattr(types, 'GetSetDescriptorType'):
    # CPython and equivalent
    def isgetsetdescriptor(object):
        """Return true if the object is a getset descriptor.

        getset descriptors are specialized descriptors defined in extension
        modules."""
        return isinstance(object, types.GetSetDescriptorType)
else:
    # Other implementations
    def isgetsetdescriptor(object):
        """Return true if the object is a getset descriptor.

        getset descriptors are specialized descriptors defined in extension
        modules."""
        return False

def isfunction(object):
    """Return true if the object is a user-defined function.

    Function objects provide these attributes:
        __doc__         documentation string
        __name__        name with which this function was defined
        func_code       code object containing compiled function bytecode
        func_defaults   tuple of any default values for arguments
        func_doc        (same as __doc__)
        func_globals    global namespace in which this function was defined
        func_name       (same as __name__)"""
    return isinstance(object, types.FunctionType)

def isgeneratorfunction(object):
    """Return true if the object is a user-defined generator function.

    Generator function objects provides same attributes as functions.

    See isfunction.__doc__ for attributes listing."""
    return bool((isfunction(object) or ismethod(object)) and
                object.func_code.co_flags & CO_GENERATOR)

def isgenerator(object):
    """Return true if the object is a generator.

    Generator objects provide these attributes:
        __iter__        defined to support interation over container
        close           raises a new GeneratorExit exception inside the
                        generator to terminate the iteration
        gi_code         code object
        gi_frame        frame object or possibly None once the generator has
                        been exhausted
        gi_running      set to 1 when generator is executing, 0 otherwise
        next            return the next item from the container
        send            resumes the generator and "sends" a value that becomes
                        the result of the current yield-expression
        throw           used to raise an exception inside the generator"""
    return isinstance(object, types.GeneratorType)

def istraceback(object):
    """Return true if the object is a traceback.

    Traceback objects provide these attributes:
        tb_frame        frame object at this level
        tb_lasti        index of last attempted instruction in bytecode
        tb_lineno       current line number in Python source code
        tb_next         next inner traceback object (called by this level)"""
    return isinstance(object, types.TracebackType)

def isframe(object):
    """Return true if the object is a frame object.

    Frame objects provide these attributes:
        f_back          next outer frame object (this frame's caller)
        f_builtins      built-in namespace seen by this frame
        f_code          code object being executed in this frame
        f_exc_traceback traceback if raised in this frame, or None
        f_exc_type      exception type if raised in this frame, or None
        f_exc_value     exception value if raised in this frame, or None
        f_globals       global namespace seen by this frame
        f_lasti         index of last attempted instruction in bytecode
        f_lineno        current line number in Python source code
        f_locals        local namespace seen by this frame
        f_restricted    0 or 1 if frame is in restricted execution mode
        f_trace         tracing function for this frame, or None"""
    return isinstance(object, types.FrameType)

def iscode(object):
    """Return true if the object is a code object.

    Code objects provide these attributes:
        co_argcount     number of arguments (not including * or ** args)
        co_code         string of raw compiled bytecode
        co_consts       tuple of constants used in the bytecode
        co_filename     name of file in which this code object was created
        co_firstlineno  number of first line in Python source code
        co_flags        bitmap: 1=optimized | 2=newlocals | 4=*arg | 8=**arg
        co_lnotab       encoded mapping of line numbers to bytecode indices
        co_name         name with which this code object was defined
        co_names        tuple of names of local variables
        co_nlocals      number of local variables
        co_stacksize    virtual machine stack space required
        co_varnames     tuple of names of arguments and local variables"""
    return isinstance(object, types.CodeType)

def isbuiltin(object):
    """Return true if the object is a built-in function or method.

    Built-in functions and methods provide these attributes:
        __doc__         documentation string
        __name__        original name of this function or method
        __self__        instance to which a method is bound, or None"""
    return isinstance(object, types.BuiltinFunctionType)

def isroutine(object):
    """Return true if the object is any kind of function or method."""
    return (isbuiltin(object)
            or isfunction(object)
            or ismethod(object)
            or ismethoddescriptor(object))

def isabstract(object):
    """Return true if the object is an abstract base class (ABC)."""
    return bool(isinstance(object, type) and object.__flags__ & TPFLAGS_IS_ABSTRACT)

def getmembers(object, predicate=None):
    """Return all members of an object as (name, value) pairs sorted by name.
    Optionally, only return members that satisfy a given predicate."""
    results = []
    for key in dir(object):
        try:
            value = getattr(object, key)
        except AttributeError:
            continue
        if not predicate or predicate(value):
            results.append((key, value))
    results.sort()
    return results

Attribute = namedtuple('Attribute', 'name kind defining_class object')

def classify_class_attrs(cls):
    """Return list of attribute-descriptor tuples.

    For each name in dir(cls), the return list contains a 4-tuple
    with these elements:

        0. The name (a string).

        1. The kind of attribute this is, one of these strings:
               'class method'    created via classmethod()
               'static method'   created via staticmethod()
               'property'        created via property()
               'method'          any other flavor of method
               'data'            not a method

        2. The class which defined this attribute (a class).

        3. The object as obtained directly from the defining class's
           __dict__, not via getattr.  This is especially important for
           data attributes:  C.data is just a data object, but
           C.__dict__['data'] may be a data descriptor with additional
           info, like a __doc__ string.
    """

    mro = getmro(cls)
    names = dir(cls)
    result = []
    for name in names:
        # Get the object associated with the name.
        # Getting an obj from the __dict__ sometimes reveals more than
        # using getattr.  Static and class methods are dramatic examples.
        if name in cls.__dict__:
            obj = cls.__dict__[name]
        else:
            obj = getattr(cls, name)

        # Figure out where it was defined.
        homecls = getattr(obj, "__objclass__", None)
        if homecls is None:
            # search the dicts.
            for base in mro:
                if name in base.__dict__:
                    homecls = base
                    break

        # Get the object again, in order to get it from the defining
        # __dict__ instead of via getattr (if possible).
        if homecls is not None and name in homecls.__dict__:
            obj = homecls.__dict__[name]

        # Also get the object via getattr.
        obj_via_getattr = getattr(cls, name)

        # Classify the object.
        if isinstance(obj, staticmethod):
            kind = "static method"
        elif isinstance(obj, classmethod):
            kind = "class method"
        elif isinstance(obj, property):
            kind = "property"
        elif (ismethod(obj_via_getattr) or
              ismethoddescriptor(obj_via_getattr)):
            kind = "method"
        else:
            kind = "data"

        result.append(Attribute(name, kind, homecls, obj))

    return result

# ----------------------------------------------------------- class helpers
def _searchbases(cls, accum):
    # Simulate the "classic class" search order.
    if cls in accum:
        return
    accum.append(cls)
    for base in cls.__bases__:
        _searchbases(base, accum)

def getmro(cls):
    "Return tuple of base classes (including cls) in method resolution order."
    if hasattr(cls, "__mro__"):
        return cls.__mro__
    else:
        result = []
        _searchbases(cls, result)
        return tuple(result)

# -------------------------------------------------- source code extraction
def indentsize(line):
    """Return the indent size, in spaces, at the start of a line of text."""
    expline = string.expandtabs(line)
    return len(expline) - len(string.lstrip(expline))

def getdoc(object):
    """Get the documentation string for an object.

    All tabs are expanded to spaces.  To clean up docstrings that are
    indented to line up with blocks of code, any whitespace than can be
    uniformly removed from the second line onwards is removed."""
    try:
        doc = object.__doc__
    except AttributeError:
        return None
    if not isinstance(doc, types.StringTypes):
        return None
    return cleandoc(doc)

def cleandoc(doc):
    """Clean up indentation from docstrings.

    Any whitespace that can be uniformly removed from the second line
    onwards is removed."""
    try:
        lines = string.split(string.expandtabs(doc), '\n')
    except UnicodeError:
        return None
    else:
        # Find minimum indentation of any non-blank lines after first line.
        margin = sys.maxint
        for line in lines[1:]:
            content = len(string.lstrip(line))
            if content:
                indent = len(line) - content
                margin = min(margin, indent)
        # Remove indentation.
        if lines:
            lines[0] = lines[0].lstrip()
        if margin < sys.maxint:
            for i in range(1, len(lines)): lines[i] = lines[i][margin:]
        # Remove any trailing or leading blank lines.
        while lines and not lines[-1]:
            lines.pop()
        while lines and not lines[0]:
            lines.pop(0)
        return string.join(lines, '\n')

def getfile(object):
    """Work out which source or compiled file an object was defined in."""
    if ismodule(object):
        if hasattr(object, '__file__'):
            return object.__file__
        raise TypeError('{!r} is a built-in module'.format(object))
    if isclass(object):
        object = sys.modules.get(object.__module__)
        if hasattr(object, '__file__'):
            return object.__file__
        raise TypeError('{!r} is a built-in class'.format(object))
    if ismethod(object):
        object = object.im_func
    if isfunction(object):
        object = object.func_code
    if istraceback(object):
        object = object.tb_frame
    if isframe(object):
        object = object.f_code
    if iscode(object):
        return object.co_filename
    raise TypeError('{!r} is not a module, class, method, '
                    'function, traceback, frame, or code object'.format(object))

ModuleInfo = namedtuple('ModuleInfo', 'name suffix mode module_type')

def getmoduleinfo(path):
    """Get the module name, suffix, mode, and module type for a given file."""
    filename = os.path.basename(path)
    suffixes = map(lambda info:
                   (-len(info[0]), info[0], info[1], info[2]),
                    imp.get_suffixes())
    suffixes.sort() # try longest suffixes first, in case they overlap
    for neglen, suffix, mode, mtype in suffixes:
        if filename[neglen:] == suffix:
            return ModuleInfo(filename[:neglen], suffix, mode, mtype)

def getmodulename(path):
    """Return the module name for a given file, or None."""
    info = getmoduleinfo(path)
    if info: return info[0]

def getsourcefile(object):
    """Return the filename that can be used to locate an object's source.
    Return None if no way can be identified to get the source.
    """
    filename = getfile(object)
    if string.lower(filename[-4:]) in ('.pyc', '.pyo'):
        filename = filename[:-4] + '.py'
    for suffix, mode, kind in imp.get_suffixes():
        if 'b' in mode and string.lower(filename[-len(suffix):]) == suffix:
            # Looks like a binary file.  We want to only return a text file.
            return None
    if os.path.exists(filename):
        return filename
    # only return a non-existent filename if the module has a PEP 302 loader
    if hasattr(getmodule(object, filename), '__loader__'):
        return filename
    # or it is in the linecache
    if filename in linecache.cache:
        return filename

def getabsfile(object, _filename=None):
    """Return an absolute path to the source or compiled file for an object.

    The idea is for each object to have a unique origin, so this routine
    normalizes the result as much as possible."""
    if _filename is None:
        _filename = getsourcefile(object) or getfile(object)
    return os.path.normcase(os.path.abspath(_filename))

modulesbyfile = {}
_filesbymodname = {}

def getmodule(object, _filename=None):
    """Return the module an object was defined in, or None if not found."""
    if ismodule(object):
        return object
    if hasattr(object, '__module__'):
        return sys.modules.get(object.__module__)
    # Try the filename to modulename cache
    if _filename is not None and _filename in modulesbyfile:
        return sys.modules.get(modulesbyfile[_filename])
    # Try the cache again with the absolute file name
    try:
        file = getabsfile(object, _filename)
    except TypeError:
        return None
    if file in modulesbyfile:
        return sys.modules.get(modulesbyfile[file])
    # Update the filename to module name cache and check yet again
    # Copy sys.modules in order to cope with changes while iterating
    for modname, module in sys.modules.items():
        if ismodule(module) and hasattr(module, '__file__'):
            f = module.__file__
            if f == _filesbymodname.get(modname, None):
                # Have already mapped this module, so skip it
                continue
            _filesbymodname[modname] = f
            f = getabsfile(module)
            # Always map to the name the module knows itself by
            modulesbyfile[f] = modulesbyfile[
                os.path.realpath(f)] = module.__name__
    if file in modulesbyfile:
        return sys.modules.get(modulesbyfile[file])
    # Check the main module
    main = sys.modules['__main__']
    if not hasattr(object, '__name__'):
        return None
    if hasattr(main, object.__name__):
        mainobject = getattr(main, object.__name__)
        if mainobject is object:
            return main
    # Check builtins
    builtin = sys.modules['__builtin__']
    if hasattr(builtin, object.__name__):
        builtinobject = getattr(builtin, object.__name__)
        if builtinobject is object:
            return builtin

def findsource(object):
    """Return the entire source file and starting line number for an object.

    The argument may be a module, class, method, function, traceback, frame,
    or code object.  The source code is returned as a list of all the lines
    in the file and the line number indexes a line in that list.  An IOError
    is raised if the source code cannot be retrieved."""
    file = getsourcefile(object)
    if not file:
        raise IOError('source code not available')
    module = getmodule(object, file)
    if module:
        lines = linecache.getlines(file, module.__dict__)
    else:
        lines = linecache.getlines(file)
    if not lines:
        raise IOError('could not get source code')

    if ismodule(object):
        return lines, 0

    if isclass(object):
        name = object.__name__
        pat = re.compile(r'^(\s*)class\s*' + name + r'\b')
        # make some effort to find the best matching class definition:
        # use the one with the least indentation, which is the one
        # that's most probably not inside a function definition.
        candidates = []
        for i in range(len(lines)):
            match = pat.match(lines[i])
            if match:
                # if it's at toplevel, it's already the best one
                if lines[i][0] == 'c':
                    return lines, i
                # else add whitespace to candidate list
                candidates.append((match.group(1), i))
        if candidates:
            # this will sort by whitespace, and by line number,
            # less whitespace first
            candidates.sort()
            return lines, candidates[0][1]
        else:
            raise IOError('could not find class definition')

    if ismethod(object):
        object = object.im_func
    if isfunction(object):
        object = object.func_code
    if istraceback(object):
        object = object.tb_frame
    if isframe(object):
        object = object.f_code
    if iscode(object):
        if not hasattr(object, 'co_firstlineno'):
            raise IOError('could not find function definition')
        lnum = object.co_firstlineno - 1
        pat = re.compile(r'^(\s*def\s)|(.*(?<!\w)lambda(:|\s))|^(\s*@)')
        while lnum > 0:
            if pat.match(lines[lnum]): break
            lnum = lnum - 1
        return lines, lnum
    raise IOError('could not find code object')

def getcomments(object):
    """Get lines of comments immediately preceding an object's source code.

    Returns None when source can't be found.
    """
    try:
        lines, lnum = findsource(object)
    except (IOError, TypeError):
        return None

    if ismodule(object):
        # Look for a comment block at the top of the file.
        start = 0
        if lines and lines[0][:2] == '#!': start = 1
        while start < len(lines) and string.strip(lines[start]) in ('', '#'):
            start = start + 1
        if start < len(lines) and lines[start][:1] == '#':
            comments = []
            end = start
            while end < len(lines) and lines[end][:1] == '#':
                comments.append(string.expandtabs(lines[end]))
                end = end + 1
            return string.join(comments, '')

    # Look for a preceding block of comments at the same indentation.
    elif lnum > 0:
        indent = indentsize(lines[lnum])
        end = lnum - 1
        if end >= 0 and string.lstrip(lines[end])[:1] == '#' and \
            indentsize(lines[end]) == indent:
            comments = [string.lstrip(string.expandtabs(lines[end]))]
            if end > 0:
                end = end - 1
                comment = string.lstrip(string.expandtabs(lines[end]))
                while comment[:1] == '#' and indentsize(lines[end]) == indent:
                    comments[:0] = [comment]
                    end = end - 1
                    if end < 0: break
                    comment = string.lstrip(string.expandtabs(lines[end]))
            while comments and string.strip(comments[0]) == '#':
                comments[:1] = []
            while comments and string.strip(comments[-1]) == '#':
                comments[-1:] = []
            return string.join(comments, '')

class EndOfBlock(Exception): pass

class BlockFinder:
    """Provide a tokeneater() method to detect the end of a code block."""
    def __init__(self):
        self.indent = 0
        self.islambda = False
        self.started = False
        self.passline = False
        self.last = 1

    def tokeneater(self, type, token, srow_scol, erow_ecol, line):
        srow, scol = srow_scol
        erow, ecol = erow_ecol
        if not self.started:
            # look for the first "def", "class" or "lambda"
            if token in ("def", "class", "lambda"):
                if token == "lambda":
                    self.islambda = True
                self.started = True
            self.passline = True    # skip to the end of the line
        elif type == tokenize.NEWLINE:
            self.passline = False   # stop skipping when a NEWLINE is seen
            self.last = srow
            if self.islambda:       # lambdas always end at the first NEWLINE
                raise EndOfBlock
        elif self.passline:
            pass
        elif type == tokenize.INDENT:
            self.indent = self.indent + 1
            self.passline = True
        elif type == tokenize.DEDENT:
            self.indent = self.indent - 1
            # the end of matching indent/dedent pairs end a block
            # (note that this only works for "def"/"class" blocks,
            #  not e.g. for "if: else:" or "try: finally:" blocks)
            if self.indent <= 0:
                raise EndOfBlock
        elif self.indent == 0 and type not in (tokenize.COMMENT, tokenize.NL):
            # any other token on the same indentation level end the previous
            # block as well, except the pseudo-tokens COMMENT and NL.
            raise EndOfBlock

def getblock(lines):
    """Extract the block of code at the top of the given list of lines."""
    blockfinder = BlockFinder()
    try:
        tokenize.tokenize(iter(lines).next, blockfinder.tokeneater)
    except (EndOfBlock, IndentationError):
        pass
    return lines[:blockfinder.last]

def getsourcelines(object):
    """Return a list of source lines and starting line number for an object.

    The argument may be a module, class, method, function, traceback, frame,
    or code object.  The source code is returned as a list of the lines
    corresponding to the object and the line number indicates where in the
    original source file the first line of code was found.  An IOError is
    raised if the source code cannot be retrieved."""
    lines, lnum = findsource(object)

    if ismodule(object): return lines, 0
    else: return getblock(lines[lnum:]), lnum + 1

def getsource(object):
    """Return the text of the source code for an object.

    The argument may be a module, class, method, function, traceback, frame,
    or code object.  The source code is returned as a single string.  An
    IOError is raised if the source code cannot be retrieved."""
    lines, lnum = getsourcelines(object)
    return string.join(lines, '')

# --------------------------------------------------- class tree extraction
def walktree(classes, children, parent):
    """Recursive helper function for getclasstree()."""
    results = []
    classes.sort(key=attrgetter('__module__', '__name__'))
    for c in classes:
        results.append((c, c.__bases__))
        if c in children:
            results.append(walktree(children[c], children, c))
    return results

def getclasstree(classes, unique=0):
    """Arrange the given list of classes into a hierarchy of nested lists.

    Where a nested list appears, it contains classes derived from the class
    whose entry immediately precedes the list.  Each entry is a 2-tuple
    containing a class and a tuple of its base classes.  If the 'unique'
    argument is true, exactly one entry appears in the returned structure
    for each class in the given list.  Otherwise, classes using multiple
    inheritance and their descendants will appear multiple times."""
    children = {}
    roots = []
    for c in classes:
        if c.__bases__:
            for parent in c.__bases__:
                if not parent in children:
                    children[parent] = []
                children[parent].append(c)
                if unique and parent in classes: break
        elif c not in roots:
            roots.append(c)
    for parent in children:
        if parent not in classes:
            roots.append(parent)
    return walktree(roots, children, None)

# ------------------------------------------------ argument list extraction
Arguments = namedtuple('Arguments', 'args varargs keywords')

def getargs(co):
    """Get information about the arguments accepted by a code object.

    Three things are returned: (args, varargs, varkw), where 'args' is
    a list of argument names (possibly containing nested lists), and
    'varargs' and 'varkw' are the names of the * and ** arguments or None."""

    if not iscode(co):
        raise TypeError('{!r} is not a code object'.format(co))

    nargs = co.co_argcount
    names = co.co_varnames
    args = list(names[:nargs])
    step = 0

    # The following acrobatics are for anonymous (tuple) arguments.
    for i in range(nargs):
        if args[i][:1] in ('', '.'):
            stack, remain, count = [], [], []
            while step < len(co.co_code):
                op = ord(co.co_code[step])
                step = step + 1
                if op >= dis.HAVE_ARGUMENT:
                    opname = dis.opname[op]
                    value = ord(co.co_code[step]) + ord(co.co_code[step+1])*256
                    step = step + 2
                    if opname in ('UNPACK_TUPLE', 'UNPACK_SEQUENCE'):
                        remain.append(value)
                        count.append(value)
                    elif opname == 'STORE_FAST':
                        stack.append(names[value])

                        # Special case for sublists of length 1: def foo((bar))
                        # doesn't generate the UNPACK_TUPLE bytecode, so if
                        # `remain` is empty here, we have such a sublist.
                        if not remain:
                            stack[0] = [stack[0]]
                            break
                        else:
                            remain[-1] = remain[-1] - 1
                            while remain[-1] == 0:
                                remain.pop()
                                size = count.pop()
                                stack[-size:] = [stack[-size:]]
                                if not remain: break
                                remain[-1] = remain[-1] - 1
                            if not remain: break
            args[i] = stack[0]

    varargs = None
    if co.co_flags & CO_VARARGS:
        varargs = co.co_varnames[nargs]
        nargs = nargs + 1
    varkw = None
    if co.co_flags & CO_VARKEYWORDS:
        varkw = co.co_varnames[nargs]
    return Arguments(args, varargs, varkw)

ArgSpec = namedtuple('ArgSpec', 'args varargs keywords defaults')

def getargspec(func):
    """Get the names and default values of a function's arguments.

    A tuple of four things is returned: (args, varargs, varkw, defaults).
    'args' is a list of the argument names (it may contain nested lists).
    'varargs' and 'varkw' are the names of the * and ** arguments or None.
    'defaults' is an n-tuple of the default values of the last n arguments.
    """

    if ismethod(func):
        func = func.im_func
    if not isfunction(func):
        raise TypeError('{!r} is not a Python function'.format(func))
    args, varargs, varkw = getargs(func.func_code)
    return ArgSpec(args, varargs, varkw, func.func_defaults)

ArgInfo = namedtuple('ArgInfo', 'args varargs keywords locals')

def getargvalues(frame):
    """Get information about arguments passed into a particular frame.

    A tuple of four things is returned: (args, varargs, varkw, locals).
    'args' is a list of the argument names (it may contain nested lists).
    'varargs' and 'varkw' are the names of the * and ** arguments or None.
    'locals' is the locals dictionary of the given frame."""
    args, varargs, varkw = getargs(frame.f_code)
    return ArgInfo(args, varargs, varkw, frame.f_locals)

def joinseq(seq):
    if len(seq) == 1:
        return '(' + seq[0] + ',)'
    else:
        return '(' + string.join(seq, ', ') + ')'

def strseq(object, convert, join=joinseq):
    """Recursively walk a sequence, stringifying each element."""
    if type(object) in (list, tuple):
        return join(map(lambda o, c=convert, j=join: strseq(o, c, j), object))
    else:
        return convert(object)

def formatargspec(args, varargs=None, varkw=None, defaults=None,
                  formatarg=str,
                  formatvarargs=lambda name: '*' + name,
                  formatvarkw=lambda name: '**' + name,
                  formatvalue=lambda value: '=' + repr(value),
                  join=joinseq):
    """Format an argument spec from the 4 values returned by getargspec.

    The first four arguments are (args, varargs, varkw, defaults).  The
    other four arguments are the corresponding optional formatting functions
    that are called to turn names and values into strings.  The ninth
    argument is an optional function to format the sequence of arguments."""
    specs = []
    if defaults:
        firstdefault = len(args) - len(defaults)
    for i, arg in enumerate(args):
        spec = strseq(arg, formatarg, join)
        if defaults and i >= firstdefault:
            spec = spec + formatvalue(defaults[i - firstdefault])
        specs.append(spec)
    if varargs is not None:
        specs.append(formatvarargs(varargs))
    if varkw is not None:
        specs.append(formatvarkw(varkw))
    return '(' + string.join(specs, ', ') + ')'

def formatargvalues(args, varargs, varkw, locals,
                    formatarg=str,
                    formatvarargs=lambda name: '*' + name,
                    formatvarkw=lambda name: '**' + name,
                    formatvalue=lambda value: '=' + repr(value),
                    join=joinseq):
    """Format an argument spec from the 4 values returned by getargvalues.

    The first four arguments are (args, varargs, varkw, locals).  The
    next four arguments are the corresponding optional formatting functions
    that are called to turn names and values into strings.  The ninth
    argument is an optional function to format the sequence of arguments."""
    def convert(name, locals=locals,
                formatarg=formatarg, formatvalue=formatvalue):
        return formatarg(name) + formatvalue(locals[name])
    specs = []
    for i in range(len(args)):
        specs.append(strseq(args[i], convert, join))
    if varargs:
        specs.append(formatvarargs(varargs) + formatvalue(locals[varargs]))
    if varkw:
        specs.append(formatvarkw(varkw) + formatvalue(locals[varkw]))
    return '(' + string.join(specs, ', ') + ')'

def getcallargs(func, *positional, **named):
    """Get the mapping of arguments to values.

    A dict is returned, with keys the function argument names (including the
    names of the * and ** arguments, if any), and values the respective bound
    values from 'positional' and 'named'."""
    args, varargs, varkw, defaults = getargspec(func)
    f_name = func.__name__
    arg2value = {}

    # The following closures are basically because of tuple parameter unpacking.
    assigned_tuple_params = []
    def assign(arg, value):
        if isinstance(arg, str):
            arg2value[arg] = value
        else:
            assigned_tuple_params.append(arg)
            value = iter(value)
            for i, subarg in enumerate(arg):
                try:
                    subvalue = next(value)
                except StopIteration:
                    raise ValueError('need more than %d %s to unpack' %
                                     (i, 'values' if i > 1 else 'value'))
                assign(subarg,subvalue)
            try:
                next(value)
            except StopIteration:
                pass
            else:
                raise ValueError('too many values to unpack')
    def is_assigned(arg):
        if isinstance(arg,str):
            return arg in arg2value
        return arg in assigned_tuple_params
    if ismethod(func) and func.im_self is not None:
        # implicit 'self' (or 'cls' for classmethods) argument
        positional = (func.im_self,) + positional
    num_pos = len(positional)
    num_total = num_pos + len(named)
    num_args = len(args)
    num_defaults = len(defaults) if defaults else 0
    for arg, value in zip(args, positional):
        assign(arg, value)
    if varargs:
        if num_pos > num_args:
            assign(varargs, positional[-(num_pos-num_args):])
        else:
            assign(varargs, ())
    elif 0 < num_args < num_pos:
        raise TypeError('%s() takes %s %d %s (%d given)' % (
            f_name, 'at most' if defaults else 'exactly', num_args,
            'arguments' if num_args > 1 else 'argument', num_total))
    elif num_args == 0 and num_total:
        raise TypeError('%s() takes no arguments (%d given)' %
                        (f_name, num_total))
    for arg in args:
        if isinstance(arg, str) and arg in named:
            if is_assigned(arg):
                raise TypeError("%s() got multiple values for keyword "
                                "argument '%s'" % (f_name, arg))
            else:
                assign(arg, named.pop(arg))
    if defaults:    # fill in any missing values with the defaults
        for arg, value in zip(args[-num_defaults:], defaults):
            if not is_assigned(arg):
                assign(arg, value)
    if varkw:
        assign(varkw, named)
    elif named:
        unexpected = next(iter(named))
        if isinstance(unexpected, unicode):
            unexpected = unexpected.encode(sys.getdefaultencoding(), 'replace')
        raise TypeError("%s() got an unexpected keyword argument '%s'" %
                        (f_name, unexpected))
    unassigned = num_args - len([arg for arg in args if is_assigned(arg)])
    if unassigned:
        num_required = num_args - num_defaults
        raise TypeError('%s() takes %s %d %s (%d given)' % (
            f_name, 'at least' if defaults else 'exactly', num_required,
            'arguments' if num_required > 1 else 'argument', num_total))
    return arg2value

# -------------------------------------------------- stack frame extraction

Traceback = namedtuple('Traceback', 'filename lineno function code_context index')

def getframeinfo(frame, context=1):
    """Get information about a frame or traceback object.

    A tuple of five things is returned: the filename, the line number of
    the current line, the function name, a list of lines of context from
    the source code, and the index of the current line within that list.
    The optional second argument specifies the number of lines of context
    to return, which are centered around the current line."""
    if istraceback(frame):
        lineno = frame.tb_lineno
        frame = frame.tb_frame
    else:
        lineno = frame.f_lineno
    if not isframe(frame):
        raise TypeError('{!r} is not a frame or traceback object'.format(frame))

    filename = getsourcefile(frame) or getfile(frame)
    if context > 0:
        start = lineno - 1 - context//2
        try:
            lines, lnum = findsource(frame)
        except IOError:
            lines = index = None
        else:
            start = max(start, 1)
            start = max(0, min(start, len(lines) - context))
            lines = lines[start:start+context]
            index = lineno - 1 - start
    else:
        lines = index = None

    return Traceback(filename, lineno, frame.f_code.co_name, lines, index)

def getlineno(frame):
    """Get the line number from a frame object, allowing for optimization."""
    # FrameType.f_lineno is now a descriptor that grovels co_lnotab
    return frame.f_lineno

def getouterframes(frame, context=1):
    """Get a list of records for a frame and all higher (calling) frames.

    Each record contains a frame object, filename, line number, function
    name, a list of lines of context, and index within the context."""
    framelist = []
    while frame:
        framelist.append((frame,) + getframeinfo(frame, context))
        frame = frame.f_back
    return framelist

def getinnerframes(tb, context=1):
    """Get a list of records for a traceback's frame and all lower frames.

    Each record contains a frame object, filename, line number, function
    name, a list of lines of context, and index within the context."""
    framelist = []
    while tb:
        framelist.append((tb.tb_frame,) + getframeinfo(tb, context))
        tb = tb.tb_next
    return framelist

if hasattr(sys, '_getframe'):
    currentframe = sys._getframe
else:
    currentframe = lambda _=None: None

def stack(context=1):
    """Return a list of records for the stack above the caller's frame."""
    return getouterframes(sys._getframe(1), context)

def trace(context=1):
    """Return a list of records for the stack below the current exception."""
    return getinnerframes(sys.exc_info()[2], context)