summaryrefslogtreecommitdiffstats
path: root/python/google/protobuf/text_format.py
blob: 2429fa59fb26731f54613176c7d49753fa79ce57 (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
# Protocol Buffers - Google's data interchange format
# Copyright 2008 Google Inc.  All rights reserved.
# https://developers.google.com/protocol-buffers/
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
#     * Redistributions of source code must retain the above copyright
# notice, this list of conditions and the following disclaimer.
#     * Redistributions in binary form must reproduce the above
# copyright notice, this list of conditions and the following disclaimer
# in the documentation and/or other materials provided with the
# distribution.
#     * Neither the name of Google Inc. nor the names of its
# contributors may be used to endorse or promote products derived from
# this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#PY25 compatible for GAE.
#
# Copyright 2007 Google Inc. All Rights Reserved.

"""Contains routines for printing protocol messages in text format."""

__author__ = 'kenton@google.com (Kenton Varda)'

import cStringIO
import re

from google.protobuf.internal import type_checkers
from google.protobuf import descriptor
from google.protobuf import text_encoding

__all__ = ['MessageToString', 'PrintMessage', 'PrintField',
           'PrintFieldValue', 'Merge']


_INTEGER_CHECKERS = (type_checkers.Uint32ValueChecker(),
                     type_checkers.Int32ValueChecker(),
                     type_checkers.Uint64ValueChecker(),
                     type_checkers.Int64ValueChecker())
_FLOAT_INFINITY = re.compile('-?inf(?:inity)?f?', re.IGNORECASE)
_FLOAT_NAN = re.compile('nanf?', re.IGNORECASE)
_FLOAT_TYPES = frozenset([descriptor.FieldDescriptor.CPPTYPE_FLOAT,
                          descriptor.FieldDescriptor.CPPTYPE_DOUBLE])


class Error(Exception):
  """Top-level module error for text_format."""


class ParseError(Error):
  """Thrown in case of ASCII parsing error."""


def MessageToString(message, as_utf8=False, as_one_line=False,
                    pointy_brackets=False, use_index_order=False,
                    float_format=None):
  """Convert protobuf message to text format.

  Floating point values can be formatted compactly with 15 digits of
  precision (which is the most that IEEE 754 "double" can guarantee)
  using float_format='.15g'.

  Args:
    message: The protocol buffers message.
    as_utf8: Produce text output in UTF8 format.
    as_one_line: Don't introduce newlines between fields.
    pointy_brackets: If True, use angle brackets instead of curly braces for
      nesting.
    use_index_order: If True, print fields of a proto message using the order
      defined in source code instead of the field number. By default, use the
      field number order.
    float_format: If set, use this to specify floating point number formatting
      (per the "Format Specification Mini-Language"); otherwise, str() is used.

  Returns:
    A string of the text formatted protocol buffer message.
  """
  out = cStringIO.StringIO()
  PrintMessage(message, out, as_utf8=as_utf8, as_one_line=as_one_line,
               pointy_brackets=pointy_brackets,
               use_index_order=use_index_order,
               float_format=float_format)
  result = out.getvalue()
  out.close()
  if as_one_line:
    return result.rstrip()
  return result


def PrintMessage(message, out, indent=0, as_utf8=False, as_one_line=False,
                 pointy_brackets=False, use_index_order=False,
                 float_format=None):
  fields = message.ListFields()
  if use_index_order:
    fields.sort(key=lambda x: x[0].index)
  for field, value in fields:
    if field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
      for element in value:
        PrintField(field, element, out, indent, as_utf8, as_one_line,
                   pointy_brackets=pointy_brackets,
                   float_format=float_format)
    else:
      PrintField(field, value, out, indent, as_utf8, as_one_line,
                 pointy_brackets=pointy_brackets,
                 float_format=float_format)


def PrintField(field, value, out, indent=0, as_utf8=False, as_one_line=False,
               pointy_brackets=False, float_format=None):
  """Print a single field name/value pair.  For repeated fields, the value
  should be a single element."""

  out.write(' ' * indent)
  if field.is_extension:
    out.write('[')
    if (field.containing_type.GetOptions().message_set_wire_format and
        field.type == descriptor.FieldDescriptor.TYPE_MESSAGE and
        field.message_type == field.extension_scope and
        field.label == descriptor.FieldDescriptor.LABEL_OPTIONAL):
      out.write(field.message_type.full_name)
    else:
      out.write(field.full_name)
    out.write(']')
  elif field.type == descriptor.FieldDescriptor.TYPE_GROUP:
    # For groups, use the capitalized name.
    out.write(field.message_type.name)
  else:
    out.write(field.name)

  if field.cpp_type != descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
    # The colon is optional in this case, but our cross-language golden files
    # don't include it.
    out.write(': ')

  PrintFieldValue(field, value, out, indent, as_utf8, as_one_line,
                  pointy_brackets=pointy_brackets,
                  float_format=float_format)
  if as_one_line:
    out.write(' ')
  else:
    out.write('\n')


def PrintFieldValue(field, value, out, indent=0, as_utf8=False,
                    as_one_line=False, pointy_brackets=False,
                    float_format=None):
  """Print a single field value (not including name).  For repeated fields,
  the value should be a single element."""

  if pointy_brackets:
    openb = '<'
    closeb = '>'
  else:
    openb = '{'
    closeb = '}'

  if field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
    if as_one_line:
      out.write(' %s ' % openb)
      PrintMessage(value, out, indent, as_utf8, as_one_line,
                   pointy_brackets=pointy_brackets,
                   float_format=float_format)
      out.write(closeb)
    else:
      out.write(' %s\n' % openb)
      PrintMessage(value, out, indent + 2, as_utf8, as_one_line,
                   pointy_brackets=pointy_brackets,
                   float_format=float_format)
      out.write(' ' * indent + closeb)
  elif field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_ENUM:
    enum_value = field.enum_type.values_by_number.get(value, None)
    if enum_value is not None:
      out.write(enum_value.name)
    else:
      out.write(str(value))
  elif field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_STRING:
    out.write('\"')
    if isinstance(value, unicode):
      out_value = value.encode('utf-8')
    else:
      out_value = value
    if field.type == descriptor.FieldDescriptor.TYPE_BYTES:
      # We need to escape non-UTF8 chars in TYPE_BYTES field.
      out_as_utf8 = False
    else:
      out_as_utf8 = as_utf8
    out.write(text_encoding.CEscape(out_value, out_as_utf8))
    out.write('\"')
  elif field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_BOOL:
    if value:
      out.write('true')
    else:
      out.write('false')
  elif field.cpp_type in _FLOAT_TYPES and float_format is not None:
    out.write('{1:{0}}'.format(float_format, value))
  else:
    out.write(str(value))


def _ParseOrMerge(lines, message, allow_multiple_scalars):
  """Converts an ASCII representation of a protocol message into a message.

  Args:
    lines: Lines of a message's ASCII representation.
    message: A protocol buffer message to merge into.
    allow_multiple_scalars: Determines if repeated values for a non-repeated
      field are permitted, e.g., the string "foo: 1 foo: 2" for a
      required/optional field named "foo".

  Raises:
    ParseError: On ASCII parsing problems.
  """
  tokenizer = _Tokenizer(lines)
  while not tokenizer.AtEnd():
    _MergeField(tokenizer, message, allow_multiple_scalars)


def Parse(text, message):
  """Parses an ASCII representation of a protocol message into a message.

  Args:
    text: Message ASCII representation.
    message: A protocol buffer message to merge into.

  Returns:
    The same message passed as argument.

  Raises:
    ParseError: On ASCII parsing problems.
  """
  if not isinstance(text, str): text = text.decode('utf-8')
  return ParseLines(text.split('\n'), message)


def Merge(text, message):
  """Parses an ASCII representation of a protocol message into a message.

  Like Parse(), but allows repeated values for a non-repeated field, and uses
  the last one.

  Args:
    text: Message ASCII representation.
    message: A protocol buffer message to merge into.

  Returns:
    The same message passed as argument.

  Raises:
    ParseError: On ASCII parsing problems.
  """
  return MergeLines(text.split('\n'), message)


def ParseLines(lines, message):
  """Parses an ASCII representation of a protocol message into a message.

  Args:
    lines: An iterable of lines of a message's ASCII representation.
    message: A protocol buffer message to merge into.

  Returns:
    The same message passed as argument.

  Raises:
    ParseError: On ASCII parsing problems.
  """
  _ParseOrMerge(lines, message, False)
  return message


def MergeLines(lines, message):
  """Parses an ASCII representation of a protocol message into a message.

  Args:
    lines: An iterable of lines of a message's ASCII representation.
    message: A protocol buffer message to merge into.

  Returns:
    The same message passed as argument.

  Raises:
    ParseError: On ASCII parsing problems.
  """
  _ParseOrMerge(lines, message, True)
  return message


def _MergeField(tokenizer, message, allow_multiple_scalars):
  """Merges a single protocol message field into a message.

  Args:
    tokenizer: A tokenizer to parse the field name and values.
    message: A protocol message to record the data.
    allow_multiple_scalars: Determines if repeated values for a non-repeated
      field are permitted, e.g., the string "foo: 1 foo: 2" for a
      required/optional field named "foo".

  Raises:
    ParseError: In case of ASCII parsing problems.
  """
  message_descriptor = message.DESCRIPTOR
  if tokenizer.TryConsume('['):
    name = [tokenizer.ConsumeIdentifier()]
    while tokenizer.TryConsume('.'):
      name.append(tokenizer.ConsumeIdentifier())
    name = '.'.join(name)

    if not message_descriptor.is_extendable:
      raise tokenizer.ParseErrorPreviousToken(
          'Message type "%s" does not have extensions.' %
          message_descriptor.full_name)
    # pylint: disable=protected-access
    field = message.Extensions._FindExtensionByName(name)
    # pylint: enable=protected-access
    if not field:
      raise tokenizer.ParseErrorPreviousToken(
          'Extension "%s" not registered.' % name)
    elif message_descriptor != field.containing_type:
      raise tokenizer.ParseErrorPreviousToken(
          'Extension "%s" does not extend message type "%s".' % (
              name, message_descriptor.full_name))
    tokenizer.Consume(']')
  else:
    name = tokenizer.ConsumeIdentifier()
    field = message_descriptor.fields_by_name.get(name, None)

    # Group names are expected to be capitalized as they appear in the
    # .proto file, which actually matches their type names, not their field
    # names.
    if not field:
      field = message_descriptor.fields_by_name.get(name.lower(), None)
      if field and field.type != descriptor.FieldDescriptor.TYPE_GROUP:
        field = None

    if (field and field.type == descriptor.FieldDescriptor.TYPE_GROUP and
        field.message_type.name != name):
      field = None

    if not field:
      raise tokenizer.ParseErrorPreviousToken(
          'Message type "%s" has no field named "%s".' % (
              message_descriptor.full_name, name))

  if field.cpp_type == descriptor.FieldDescriptor.CPPTYPE_MESSAGE:
    tokenizer.TryConsume(':')

    if tokenizer.TryConsume('<'):
      end_token = '>'
    else:
      tokenizer.Consume('{')
      end_token = '}'

    if field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
      if field.is_extension:
        sub_message = message.Extensions[field].add()
      else:
        sub_message = getattr(message, field.name).add()
    else:
      if field.is_extension:
        sub_message = message.Extensions[field]
      else:
        sub_message = getattr(message, field.name)
      sub_message.SetInParent()

    while not tokenizer.TryConsume(end_token):
      if tokenizer.AtEnd():
        raise tokenizer.ParseErrorPreviousToken('Expected "%s".' % (end_token))
      _MergeField(tokenizer, sub_message, allow_multiple_scalars)
  else:
    _MergeScalarField(tokenizer, message, field, allow_multiple_scalars)

  # For historical reasons, fields may optionally be separated by commas or
  # semicolons.
  if not tokenizer.TryConsume(','):
    tokenizer.TryConsume(';')


def _MergeScalarField(tokenizer, message, field, allow_multiple_scalars):
  """Merges a single protocol message scalar field into a message.

  Args:
    tokenizer: A tokenizer to parse the field value.
    message: A protocol message to record the data.
    field: The descriptor of the field to be merged.
    allow_multiple_scalars: Determines if repeated values for a non-repeated
      field are permitted, e.g., the string "foo: 1 foo: 2" for a
      required/optional field named "foo".

  Raises:
    ParseError: In case of ASCII parsing problems.
    RuntimeError: On runtime errors.
  """
  tokenizer.Consume(':')
  value = None

  if field.type in (descriptor.FieldDescriptor.TYPE_INT32,
                    descriptor.FieldDescriptor.TYPE_SINT32,
                    descriptor.FieldDescriptor.TYPE_SFIXED32):
    value = tokenizer.ConsumeInt32()
  elif field.type in (descriptor.FieldDescriptor.TYPE_INT64,
                      descriptor.FieldDescriptor.TYPE_SINT64,
                      descriptor.FieldDescriptor.TYPE_SFIXED64):
    value = tokenizer.ConsumeInt64()
  elif field.type in (descriptor.FieldDescriptor.TYPE_UINT32,
                      descriptor.FieldDescriptor.TYPE_FIXED32):
    value = tokenizer.ConsumeUint32()
  elif field.type in (descriptor.FieldDescriptor.TYPE_UINT64,
                      descriptor.FieldDescriptor.TYPE_FIXED64):
    value = tokenizer.ConsumeUint64()
  elif field.type in (descriptor.FieldDescriptor.TYPE_FLOAT,
                      descriptor.FieldDescriptor.TYPE_DOUBLE):
    value = tokenizer.ConsumeFloat()
  elif field.type == descriptor.FieldDescriptor.TYPE_BOOL:
    value = tokenizer.ConsumeBool()
  elif field.type == descriptor.FieldDescriptor.TYPE_STRING:
    value = tokenizer.ConsumeString()
  elif field.type == descriptor.FieldDescriptor.TYPE_BYTES:
    value = tokenizer.ConsumeByteString()
  elif field.type == descriptor.FieldDescriptor.TYPE_ENUM:
    value = tokenizer.ConsumeEnum(field)
  else:
    raise RuntimeError('Unknown field type %d' % field.type)

  if field.label == descriptor.FieldDescriptor.LABEL_REPEATED:
    if field.is_extension:
      message.Extensions[field].append(value)
    else:
      getattr(message, field.name).append(value)
  else:
    if field.is_extension:
      if not allow_multiple_scalars and message.HasExtension(field):
        raise tokenizer.ParseErrorPreviousToken(
            'Message type "%s" should not have multiple "%s" extensions.' %
            (message.DESCRIPTOR.full_name, field.full_name))
      else:
        message.Extensions[field] = value
    else:
      if not allow_multiple_scalars and message.HasField(field.name):
        raise tokenizer.ParseErrorPreviousToken(
            'Message type "%s" should not have multiple "%s" fields.' %
            (message.DESCRIPTOR.full_name, field.name))
      else:
        setattr(message, field.name, value)


class _Tokenizer(object):
  """Protocol buffer ASCII representation tokenizer.

  This class handles the lower level string parsing by splitting it into
  meaningful tokens.

  It was directly ported from the Java protocol buffer API.
  """

  _WHITESPACE = re.compile('(\\s|(#.*$))+', re.MULTILINE)
  _TOKEN = re.compile(
      '[a-zA-Z_][0-9a-zA-Z_+-]*|'           # an identifier
      '[0-9+-][0-9a-zA-Z_.+-]*|'            # a number
      '\"([^\"\n\\\\]|\\\\.)*(\"|\\\\?$)|'  # a double-quoted string
      '\'([^\'\n\\\\]|\\\\.)*(\'|\\\\?$)')  # a single-quoted string
  _IDENTIFIER = re.compile(r'\w+')

  def __init__(self, lines):
    self._position = 0
    self._line = -1
    self._column = 0
    self._token_start = None
    self.token = ''
    self._lines = iter(lines)
    self._current_line = ''
    self._previous_line = 0
    self._previous_column = 0
    self._more_lines = True
    self._SkipWhitespace()
    self.NextToken()

  def AtEnd(self):
    """Checks the end of the text was reached.

    Returns:
      True iff the end was reached.
    """
    return not self.token

  def _PopLine(self):
    while len(self._current_line) <= self._column:
      try:
        self._current_line = self._lines.next()
      except StopIteration:
        self._current_line = ''
        self._more_lines = False
        return
      else:
        self._line += 1
        self._column = 0

  def _SkipWhitespace(self):
    while True:
      self._PopLine()
      match = self._WHITESPACE.match(self._current_line, self._column)
      if not match:
        break
      length = len(match.group(0))
      self._column += length

  def TryConsume(self, token):
    """Tries to consume a given piece of text.

    Args:
      token: Text to consume.

    Returns:
      True iff the text was consumed.
    """
    if self.token == token:
      self.NextToken()
      return True
    return False

  def Consume(self, token):
    """Consumes a piece of text.

    Args:
      token: Text to consume.

    Raises:
      ParseError: If the text couldn't be consumed.
    """
    if not self.TryConsume(token):
      raise self._ParseError('Expected "%s".' % token)

  def ConsumeIdentifier(self):
    """Consumes protocol message field identifier.

    Returns:
      Identifier string.

    Raises:
      ParseError: If an identifier couldn't be consumed.
    """
    result = self.token
    if not self._IDENTIFIER.match(result):
      raise self._ParseError('Expected identifier.')
    self.NextToken()
    return result

  def ConsumeInt32(self):
    """Consumes a signed 32bit integer number.

    Returns:
      The integer parsed.

    Raises:
      ParseError: If a signed 32bit integer couldn't be consumed.
    """
    try:
      result = ParseInteger(self.token, is_signed=True, is_long=False)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeUint32(self):
    """Consumes an unsigned 32bit integer number.

    Returns:
      The integer parsed.

    Raises:
      ParseError: If an unsigned 32bit integer couldn't be consumed.
    """
    try:
      result = ParseInteger(self.token, is_signed=False, is_long=False)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeInt64(self):
    """Consumes a signed 64bit integer number.

    Returns:
      The integer parsed.

    Raises:
      ParseError: If a signed 64bit integer couldn't be consumed.
    """
    try:
      result = ParseInteger(self.token, is_signed=True, is_long=True)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeUint64(self):
    """Consumes an unsigned 64bit integer number.

    Returns:
      The integer parsed.

    Raises:
      ParseError: If an unsigned 64bit integer couldn't be consumed.
    """
    try:
      result = ParseInteger(self.token, is_signed=False, is_long=True)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeFloat(self):
    """Consumes an floating point number.

    Returns:
      The number parsed.

    Raises:
      ParseError: If a floating point number couldn't be consumed.
    """
    try:
      result = ParseFloat(self.token)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeBool(self):
    """Consumes a boolean value.

    Returns:
      The bool parsed.

    Raises:
      ParseError: If a boolean value couldn't be consumed.
    """
    try:
      result = ParseBool(self.token)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeString(self):
    """Consumes a string value.

    Returns:
      The string parsed.

    Raises:
      ParseError: If a string value couldn't be consumed.
    """
    the_bytes = self.ConsumeByteString()
    try:
      return unicode(the_bytes, 'utf-8')
    except UnicodeDecodeError, e:
      raise self._StringParseError(e)

  def ConsumeByteString(self):
    """Consumes a byte array value.

    Returns:
      The array parsed (as a string).

    Raises:
      ParseError: If a byte array value couldn't be consumed.
    """
    the_list = [self._ConsumeSingleByteString()]
    while self.token and self.token[0] in ('\'', '"'):
      the_list.append(self._ConsumeSingleByteString())
    return ''.encode('latin1').join(the_list)  ##PY25
##!PY25    return b''.join(the_list)

  def _ConsumeSingleByteString(self):
    """Consume one token of a string literal.

    String literals (whether bytes or text) can come in multiple adjacent
    tokens which are automatically concatenated, like in C or Python.  This
    method only consumes one token.
    """
    text = self.token
    if len(text) < 1 or text[0] not in ('\'', '"'):
      raise self._ParseError('Expected string.')

    if len(text) < 2 or text[-1] != text[0]:
      raise self._ParseError('String missing ending quote.')

    try:
      result = text_encoding.CUnescape(text[1:-1])
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ConsumeEnum(self, field):
    try:
      result = ParseEnum(field, self.token)
    except ValueError, e:
      raise self._ParseError(str(e))
    self.NextToken()
    return result

  def ParseErrorPreviousToken(self, message):
    """Creates and *returns* a ParseError for the previously read token.

    Args:
      message: A message to set for the exception.

    Returns:
      A ParseError instance.
    """
    return ParseError('%d:%d : %s' % (
        self._previous_line + 1, self._previous_column + 1, message))

  def _ParseError(self, message):
    """Creates and *returns* a ParseError for the current token."""
    return ParseError('%d:%d : %s' % (
        self._line + 1, self._column + 1, message))

  def _StringParseError(self, e):
    return self._ParseError('Couldn\'t parse string: ' + str(e))

  def NextToken(self):
    """Reads the next meaningful token."""
    self._previous_line = self._line
    self._previous_column = self._column

    self._column += len(self.token)
    self._SkipWhitespace()

    if not self._more_lines:
      self.token = ''
      return

    match = self._TOKEN.match(self._current_line, self._column)
    if match:
      token = match.group(0)
      self.token = token
    else:
      self.token = self._current_line[self._column]


def ParseInteger(text, is_signed=False, is_long=False):
  """Parses an integer.

  Args:
    text: The text to parse.
    is_signed: True if a signed integer must be parsed.
    is_long: True if a long integer must be parsed.

  Returns:
    The integer value.

  Raises:
    ValueError: Thrown Iff the text is not a valid integer.
  """
  # Do the actual parsing. Exception handling is propagated to caller.
  try:
    # We force 32-bit values to int and 64-bit values to long to make
    # alternate implementations where the distinction is more significant
    # (e.g. the C++ implementation) simpler.
    if is_long:
      result = long(text, 0)
    else:
      result = int(text, 0)
  except ValueError:
    raise ValueError('Couldn\'t parse integer: %s' % text)

  # Check if the integer is sane. Exceptions handled by callers.
  checker = _INTEGER_CHECKERS[2 * int(is_long) + int(is_signed)]
  checker.CheckValue(result)
  return result


def ParseFloat(text):
  """Parse a floating point number.

  Args:
    text: Text to parse.

  Returns:
    The number parsed.

  Raises:
    ValueError: If a floating point number couldn't be parsed.
  """
  try:
    # Assume Python compatible syntax.
    return float(text)
  except ValueError:
    # Check alternative spellings.
    if _FLOAT_INFINITY.match(text):
      if text[0] == '-':
        return float('-inf')
      else:
        return float('inf')
    elif _FLOAT_NAN.match(text):
      return float('nan')
    else:
      # assume '1.0f' format
      try:
        return float(text.rstrip('f'))
      except ValueError:
        raise ValueError('Couldn\'t parse float: %s' % text)


def ParseBool(text):
  """Parse a boolean value.

  Args:
    text: Text to parse.

  Returns:
    Boolean values parsed

  Raises:
    ValueError: If text is not a valid boolean.
  """
  if text in ('true', 't', '1'):
    return True
  elif text in ('false', 'f', '0'):
    return False
  else:
    raise ValueError('Expected "true" or "false".')


def ParseEnum(field, value):
  """Parse an enum value.

  The value can be specified by a number (the enum value), or by
  a string literal (the enum name).

  Args:
    field: Enum field descriptor.
    value: String value.

  Returns:
    Enum value number.

  Raises:
    ValueError: If the enum value could not be parsed.
  """
  enum_descriptor = field.enum_type
  try:
    number = int(value, 0)
  except ValueError:
    # Identifier.
    enum_value = enum_descriptor.values_by_name.get(value, None)
    if enum_value is None:
      raise ValueError(
          'Enum type "%s" has no value named %s.' % (
              enum_descriptor.full_name, value))
  else:
    # Numeric value.
    enum_value = enum_descriptor.values_by_number.get(number, None)
    if enum_value is None:
      raise ValueError(
          'Enum type "%s" has no value with number %d.' % (
              enum_descriptor.full_name, number))
  return enum_value.number