1#! /usr/bin/python
2#
3# Protocol Buffers - Google's data interchange format
4# Copyright 2008 Google Inc.  All rights reserved.
5# http://code.google.com/p/protobuf/
6#
7# Redistribution and use in source and binary forms, with or without
8# modification, are permitted provided that the following conditions are
9# met:
10#
11#     * Redistributions of source code must retain the above copyright
12# notice, this list of conditions and the following disclaimer.
13#     * Redistributions in binary form must reproduce the above
14# copyright notice, this list of conditions and the following disclaimer
15# in the documentation and/or other materials provided with the
16# distribution.
17#     * Neither the name of Google Inc. nor the names of its
18# contributors may be used to endorse or promote products derived from
19# this software without specific prior written permission.
20#
21# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
27# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
31# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32
33"""Test for google.protobuf.text_format."""
34
35__author__ = 'kenton@google.com (Kenton Varda)'
36
37import difflib
38import re
39
40import unittest
41from google.protobuf import text_format
42from google.protobuf.internal import test_util
43from google.protobuf import unittest_pb2
44from google.protobuf import unittest_mset_pb2
45
46
47class TextFormatTest(unittest.TestCase):
48  def ReadGolden(self, golden_filename):
49    f = test_util.GoldenFile(golden_filename)
50    golden_lines = f.readlines()
51    f.close()
52    return golden_lines
53
54  def CompareToGoldenFile(self, text, golden_filename):
55    golden_lines = self.ReadGolden(golden_filename)
56    self.CompareToGoldenLines(text, golden_lines)
57
58  def CompareToGoldenText(self, text, golden_text):
59    self.CompareToGoldenLines(text, golden_text.splitlines(1))
60
61  def CompareToGoldenLines(self, text, golden_lines):
62    actual_lines = text.splitlines(1)
63    self.assertEqual(golden_lines, actual_lines,
64      "Text doesn't match golden.  Diff:\n" +
65      ''.join(difflib.ndiff(golden_lines, actual_lines)))
66
67  def testPrintAllFields(self):
68    message = unittest_pb2.TestAllTypes()
69    test_util.SetAllFields(message)
70    self.CompareToGoldenFile(
71      self.RemoveRedundantZeros(text_format.MessageToString(message)),
72      'text_format_unittest_data.txt')
73
74  def testPrintAllExtensions(self):
75    message = unittest_pb2.TestAllExtensions()
76    test_util.SetAllExtensions(message)
77    self.CompareToGoldenFile(
78      self.RemoveRedundantZeros(text_format.MessageToString(message)),
79      'text_format_unittest_extensions_data.txt')
80
81  def testPrintMessageSet(self):
82    message = unittest_mset_pb2.TestMessageSetContainer()
83    ext1 = unittest_mset_pb2.TestMessageSetExtension1.message_set_extension
84    ext2 = unittest_mset_pb2.TestMessageSetExtension2.message_set_extension
85    message.message_set.Extensions[ext1].i = 23
86    message.message_set.Extensions[ext2].str = 'foo'
87    self.CompareToGoldenText(text_format.MessageToString(message),
88      'message_set {\n'
89      '  [protobuf_unittest.TestMessageSetExtension1] {\n'
90      '    i: 23\n'
91      '  }\n'
92      '  [protobuf_unittest.TestMessageSetExtension2] {\n'
93      '    str: \"foo\"\n'
94      '  }\n'
95      '}\n')
96
97  def testPrintBadEnumValue(self):
98    message = unittest_pb2.TestAllTypes()
99    message.optional_nested_enum = 100
100    message.optional_foreign_enum = 101
101    message.optional_import_enum = 102
102    self.CompareToGoldenText(
103        text_format.MessageToString(message),
104        'optional_nested_enum: 100\n'
105        'optional_foreign_enum: 101\n'
106        'optional_import_enum: 102\n')
107
108  def testPrintBadEnumValueExtensions(self):
109    message = unittest_pb2.TestAllExtensions()
110    message.Extensions[unittest_pb2.optional_nested_enum_extension] = 100
111    message.Extensions[unittest_pb2.optional_foreign_enum_extension] = 101
112    message.Extensions[unittest_pb2.optional_import_enum_extension] = 102
113    self.CompareToGoldenText(
114        text_format.MessageToString(message),
115        '[protobuf_unittest.optional_nested_enum_extension]: 100\n'
116        '[protobuf_unittest.optional_foreign_enum_extension]: 101\n'
117        '[protobuf_unittest.optional_import_enum_extension]: 102\n')
118
119  def testPrintExotic(self):
120    message = unittest_pb2.TestAllTypes()
121    message.repeated_int64.append(-9223372036854775808)
122    message.repeated_uint64.append(18446744073709551615)
123    message.repeated_double.append(123.456)
124    message.repeated_double.append(1.23e22)
125    message.repeated_double.append(1.23e-18)
126    message.repeated_string.append('\000\001\a\b\f\n\r\t\v\\\'"')
127    message.repeated_string.append(u'\u00fc\ua71f')
128    self.CompareToGoldenText(
129      self.RemoveRedundantZeros(text_format.MessageToString(message)),
130      'repeated_int64: -9223372036854775808\n'
131      'repeated_uint64: 18446744073709551615\n'
132      'repeated_double: 123.456\n'
133      'repeated_double: 1.23e+22\n'
134      'repeated_double: 1.23e-18\n'
135      'repeated_string: '
136        '"\\000\\001\\007\\010\\014\\n\\r\\t\\013\\\\\\\'\\""\n'
137      'repeated_string: "\\303\\274\\352\\234\\237"\n')
138
139  def testPrintNestedMessageAsOneLine(self):
140    message = unittest_pb2.TestAllTypes()
141    msg = message.repeated_nested_message.add()
142    msg.bb = 42;
143    self.CompareToGoldenText(
144        text_format.MessageToString(message, as_one_line=True),
145        'repeated_nested_message { bb: 42 }')
146
147  def testPrintRepeatedFieldsAsOneLine(self):
148    message = unittest_pb2.TestAllTypes()
149    message.repeated_int32.append(1)
150    message.repeated_int32.append(1)
151    message.repeated_int32.append(3)
152    message.repeated_string.append("Google")
153    message.repeated_string.append("Zurich")
154    self.CompareToGoldenText(
155        text_format.MessageToString(message, as_one_line=True),
156        'repeated_int32: 1 repeated_int32: 1 repeated_int32: 3 '
157        'repeated_string: "Google" repeated_string: "Zurich"')
158
159  def testPrintNestedNewLineInStringAsOneLine(self):
160    message = unittest_pb2.TestAllTypes()
161    message.optional_string = "a\nnew\nline"
162    self.CompareToGoldenText(
163        text_format.MessageToString(message, as_one_line=True),
164        'optional_string: "a\\nnew\\nline"')
165
166  def testPrintMessageSetAsOneLine(self):
167    message = unittest_mset_pb2.TestMessageSetContainer()
168    ext1 = unittest_mset_pb2.TestMessageSetExtension1.message_set_extension
169    ext2 = unittest_mset_pb2.TestMessageSetExtension2.message_set_extension
170    message.message_set.Extensions[ext1].i = 23
171    message.message_set.Extensions[ext2].str = 'foo'
172    self.CompareToGoldenText(
173        text_format.MessageToString(message, as_one_line=True),
174        'message_set {'
175        ' [protobuf_unittest.TestMessageSetExtension1] {'
176        ' i: 23'
177        ' }'
178        ' [protobuf_unittest.TestMessageSetExtension2] {'
179        ' str: \"foo\"'
180        ' }'
181        ' }')
182
183  def testPrintExoticAsOneLine(self):
184    message = unittest_pb2.TestAllTypes()
185    message.repeated_int64.append(-9223372036854775808)
186    message.repeated_uint64.append(18446744073709551615)
187    message.repeated_double.append(123.456)
188    message.repeated_double.append(1.23e22)
189    message.repeated_double.append(1.23e-18)
190    message.repeated_string.append('\000\001\a\b\f\n\r\t\v\\\'"')
191    message.repeated_string.append(u'\u00fc\ua71f')
192    self.CompareToGoldenText(
193      self.RemoveRedundantZeros(
194          text_format.MessageToString(message, as_one_line=True)),
195      'repeated_int64: -9223372036854775808'
196      ' repeated_uint64: 18446744073709551615'
197      ' repeated_double: 123.456'
198      ' repeated_double: 1.23e+22'
199      ' repeated_double: 1.23e-18'
200      ' repeated_string: '
201      '"\\000\\001\\007\\010\\014\\n\\r\\t\\013\\\\\\\'\\""'
202      ' repeated_string: "\\303\\274\\352\\234\\237"')
203
204  def testRoundTripExoticAsOneLine(self):
205    message = unittest_pb2.TestAllTypes()
206    message.repeated_int64.append(-9223372036854775808)
207    message.repeated_uint64.append(18446744073709551615)
208    message.repeated_double.append(123.456)
209    message.repeated_double.append(1.23e22)
210    message.repeated_double.append(1.23e-18)
211    message.repeated_string.append('\000\001\a\b\f\n\r\t\v\\\'"')
212    message.repeated_string.append(u'\u00fc\ua71f')
213
214    # Test as_utf8 = False.
215    wire_text = text_format.MessageToString(
216        message, as_one_line=True, as_utf8=False)
217    parsed_message = unittest_pb2.TestAllTypes()
218    text_format.Merge(wire_text, parsed_message)
219    self.assertEquals(message, parsed_message)
220
221    # Test as_utf8 = True.
222    wire_text = text_format.MessageToString(
223        message, as_one_line=True, as_utf8=True)
224    parsed_message = unittest_pb2.TestAllTypes()
225    text_format.Merge(wire_text, parsed_message)
226    self.assertEquals(message, parsed_message)
227
228  def testPrintRawUtf8String(self):
229    message = unittest_pb2.TestAllTypes()
230    message.repeated_string.append(u'\u00fc\ua71f')
231    text = text_format.MessageToString(message, as_utf8 = True)
232    self.CompareToGoldenText(text, 'repeated_string: "\303\274\352\234\237"\n')
233    parsed_message = unittest_pb2.TestAllTypes()
234    text_format.Merge(text, parsed_message)
235    self.assertEquals(message, parsed_message)
236
237  def testMessageToString(self):
238    message = unittest_pb2.ForeignMessage()
239    message.c = 123
240    self.assertEqual('c: 123\n', str(message))
241
242  def RemoveRedundantZeros(self, text):
243    # Some platforms print 1e+5 as 1e+005.  This is fine, but we need to remove
244    # these zeros in order to match the golden file.
245    text = text.replace('e+0','e+').replace('e+0','e+') \
246               .replace('e-0','e-').replace('e-0','e-')
247    # Floating point fields are printed with .0 suffix even if they are
248    # actualy integer numbers.
249    text = re.compile('\.0$', re.MULTILINE).sub('', text)
250    return text
251
252  def testMergeGolden(self):
253    golden_text = '\n'.join(self.ReadGolden('text_format_unittest_data.txt'))
254    parsed_message = unittest_pb2.TestAllTypes()
255    text_format.Merge(golden_text, parsed_message)
256
257    message = unittest_pb2.TestAllTypes()
258    test_util.SetAllFields(message)
259    self.assertEquals(message, parsed_message)
260
261  def testMergeGoldenExtensions(self):
262    golden_text = '\n'.join(self.ReadGolden(
263        'text_format_unittest_extensions_data.txt'))
264    parsed_message = unittest_pb2.TestAllExtensions()
265    text_format.Merge(golden_text, parsed_message)
266
267    message = unittest_pb2.TestAllExtensions()
268    test_util.SetAllExtensions(message)
269    self.assertEquals(message, parsed_message)
270
271  def testMergeAllFields(self):
272    message = unittest_pb2.TestAllTypes()
273    test_util.SetAllFields(message)
274    ascii_text = text_format.MessageToString(message)
275
276    parsed_message = unittest_pb2.TestAllTypes()
277    text_format.Merge(ascii_text, parsed_message)
278    self.assertEqual(message, parsed_message)
279    test_util.ExpectAllFieldsSet(self, message)
280
281  def testMergeAllExtensions(self):
282    message = unittest_pb2.TestAllExtensions()
283    test_util.SetAllExtensions(message)
284    ascii_text = text_format.MessageToString(message)
285
286    parsed_message = unittest_pb2.TestAllExtensions()
287    text_format.Merge(ascii_text, parsed_message)
288    self.assertEqual(message, parsed_message)
289
290  def testMergeMessageSet(self):
291    message = unittest_pb2.TestAllTypes()
292    text = ('repeated_uint64: 1\n'
293            'repeated_uint64: 2\n')
294    text_format.Merge(text, message)
295    self.assertEqual(1, message.repeated_uint64[0])
296    self.assertEqual(2, message.repeated_uint64[1])
297
298    message = unittest_mset_pb2.TestMessageSetContainer()
299    text = ('message_set {\n'
300            '  [protobuf_unittest.TestMessageSetExtension1] {\n'
301            '    i: 23\n'
302            '  }\n'
303            '  [protobuf_unittest.TestMessageSetExtension2] {\n'
304            '    str: \"foo\"\n'
305            '  }\n'
306            '}\n')
307    text_format.Merge(text, message)
308    ext1 = unittest_mset_pb2.TestMessageSetExtension1.message_set_extension
309    ext2 = unittest_mset_pb2.TestMessageSetExtension2.message_set_extension
310    self.assertEquals(23, message.message_set.Extensions[ext1].i)
311    self.assertEquals('foo', message.message_set.Extensions[ext2].str)
312
313  def testMergeExotic(self):
314    message = unittest_pb2.TestAllTypes()
315    text = ('repeated_int64: -9223372036854775808\n'
316            'repeated_uint64: 18446744073709551615\n'
317            'repeated_double: 123.456\n'
318            'repeated_double: 1.23e+22\n'
319            'repeated_double: 1.23e-18\n'
320            'repeated_string: \n'
321            '"\\000\\001\\007\\010\\014\\n\\r\\t\\013\\\\\\\'\\""\n'
322            'repeated_string: "foo" \'corge\' "grault"\n'
323            'repeated_string: "\\303\\274\\352\\234\\237"\n'
324            'repeated_string: "\\xc3\\xbc"\n'
325            'repeated_string: "\xc3\xbc"\n')
326    text_format.Merge(text, message)
327
328    self.assertEqual(-9223372036854775808, message.repeated_int64[0])
329    self.assertEqual(18446744073709551615, message.repeated_uint64[0])
330    self.assertEqual(123.456, message.repeated_double[0])
331    self.assertEqual(1.23e22, message.repeated_double[1])
332    self.assertEqual(1.23e-18, message.repeated_double[2])
333    self.assertEqual(
334        '\000\001\a\b\f\n\r\t\v\\\'"', message.repeated_string[0])
335    self.assertEqual('foocorgegrault', message.repeated_string[1])
336    self.assertEqual(u'\u00fc\ua71f', message.repeated_string[2])
337    self.assertEqual(u'\u00fc', message.repeated_string[3])
338
339  def testMergeEmptyText(self):
340    message = unittest_pb2.TestAllTypes()
341    text = ''
342    text_format.Merge(text, message)
343    self.assertEquals(unittest_pb2.TestAllTypes(), message)
344
345  def testMergeInvalidUtf8(self):
346    message = unittest_pb2.TestAllTypes()
347    text = 'repeated_string: "\\xc3\\xc3"'
348    self.assertRaises(text_format.ParseError, text_format.Merge, text, message)
349
350  def testMergeSingleWord(self):
351    message = unittest_pb2.TestAllTypes()
352    text = 'foo'
353    self.assertRaisesWithMessage(
354        text_format.ParseError,
355        ('1:1 : Message type "protobuf_unittest.TestAllTypes" has no field named '
356         '"foo".'),
357        text_format.Merge, text, message)
358
359  def testMergeUnknownField(self):
360    message = unittest_pb2.TestAllTypes()
361    text = 'unknown_field: 8\n'
362    self.assertRaisesWithMessage(
363        text_format.ParseError,
364        ('1:1 : Message type "protobuf_unittest.TestAllTypes" has no field named '
365         '"unknown_field".'),
366        text_format.Merge, text, message)
367
368  def testMergeBadExtension(self):
369    message = unittest_pb2.TestAllExtensions()
370    text = '[unknown_extension]: 8\n'
371    self.assertRaisesWithMessage(
372        text_format.ParseError,
373        '1:2 : Extension "unknown_extension" not registered.',
374        text_format.Merge, text, message)
375    message = unittest_pb2.TestAllTypes()
376    self.assertRaisesWithMessage(
377        text_format.ParseError,
378        ('1:2 : Message type "protobuf_unittest.TestAllTypes" does not have '
379         'extensions.'),
380        text_format.Merge, text, message)
381
382  def testMergeGroupNotClosed(self):
383    message = unittest_pb2.TestAllTypes()
384    text = 'RepeatedGroup: <'
385    self.assertRaisesWithMessage(
386        text_format.ParseError, '1:16 : Expected ">".',
387        text_format.Merge, text, message)
388
389    text = 'RepeatedGroup: {'
390    self.assertRaisesWithMessage(
391        text_format.ParseError, '1:16 : Expected "}".',
392        text_format.Merge, text, message)
393
394  def testMergeEmptyGroup(self):
395    message = unittest_pb2.TestAllTypes()
396    text = 'OptionalGroup: {}'
397    text_format.Merge(text, message)
398    self.assertTrue(message.HasField('optionalgroup'))
399
400    message.Clear()
401
402    message = unittest_pb2.TestAllTypes()
403    text = 'OptionalGroup: <>'
404    text_format.Merge(text, message)
405    self.assertTrue(message.HasField('optionalgroup'))
406
407  def testMergeBadEnumValue(self):
408    message = unittest_pb2.TestAllTypes()
409    text = 'optional_nested_enum: BARR'
410    self.assertRaisesWithMessage(
411        text_format.ParseError,
412        ('1:23 : Enum type "protobuf_unittest.TestAllTypes.NestedEnum" '
413         'has no value named BARR.'),
414        text_format.Merge, text, message)
415
416    message = unittest_pb2.TestAllTypes()
417    text = 'optional_nested_enum: 100'
418    self.assertRaisesWithMessage(
419        text_format.ParseError,
420        ('1:23 : Enum type "protobuf_unittest.TestAllTypes.NestedEnum" '
421         'has no value with number 100.'),
422        text_format.Merge, text, message)
423
424  def testMergeBadIntValue(self):
425    message = unittest_pb2.TestAllTypes()
426    text = 'optional_int32: bork'
427    self.assertRaisesWithMessage(
428        text_format.ParseError,
429        ('1:17 : Couldn\'t parse integer: bork'),
430        text_format.Merge, text, message)
431
432  def testMergeStringFieldUnescape(self):
433    message = unittest_pb2.TestAllTypes()
434    text = r'''repeated_string: "\xf\x62"
435               repeated_string: "\\xf\\x62"
436               repeated_string: "\\\xf\\\x62"
437               repeated_string: "\\\\xf\\\\x62"
438               repeated_string: "\\\\\xf\\\\\x62"
439               repeated_string: "\x5cx20"'''
440    text_format.Merge(text, message)
441
442    SLASH = '\\'
443    self.assertEqual('\x0fb', message.repeated_string[0])
444    self.assertEqual(SLASH + 'xf' + SLASH + 'x62', message.repeated_string[1])
445    self.assertEqual(SLASH + '\x0f' + SLASH + 'b', message.repeated_string[2])
446    self.assertEqual(SLASH + SLASH + 'xf' + SLASH + SLASH + 'x62',
447                     message.repeated_string[3])
448    self.assertEqual(SLASH + SLASH + '\x0f' + SLASH + SLASH + 'b',
449                     message.repeated_string[4])
450    self.assertEqual(SLASH + 'x20', message.repeated_string[5])
451
452  def assertRaisesWithMessage(self, e_class, e, func, *args, **kwargs):
453    """Same as assertRaises, but also compares the exception message."""
454    if hasattr(e_class, '__name__'):
455      exc_name = e_class.__name__
456    else:
457      exc_name = str(e_class)
458
459    try:
460      func(*args, **kwargs)
461    except e_class as expr:
462      if str(expr) != e:
463        msg = '%s raised, but with wrong message: "%s" instead of "%s"'
464        raise self.failureException(msg % (exc_name,
465                                           str(expr).encode('string_escape'),
466                                           e.encode('string_escape')))
467      return
468    else:
469      raise self.failureException('%s not raised' % exc_name)
470
471
472class TokenizerTest(unittest.TestCase):
473
474  def testSimpleTokenCases(self):
475    text = ('identifier1:"string1"\n     \n\n'
476            'identifier2 : \n \n123  \n  identifier3 :\'string\'\n'
477            'identifiER_4 : 1.1e+2 ID5:-0.23 ID6:\'aaaa\\\'bbbb\'\n'
478            'ID7 : "aa\\"bb"\n\n\n\n ID8: {A:inf B:-inf C:true D:false}\n'
479            'ID9: 22 ID10: -111111111111111111 ID11: -22\n'
480            'ID12: 2222222222222222222 ID13: 1.23456f ID14: 1.2e+2f '
481            'false_bool:  0 true_BOOL:t \n true_bool1:  1 false_BOOL1:f ' )
482    tokenizer = text_format._Tokenizer(text)
483    methods = [(tokenizer.ConsumeIdentifier, 'identifier1'),
484               ':',
485               (tokenizer.ConsumeString, 'string1'),
486               (tokenizer.ConsumeIdentifier, 'identifier2'),
487               ':',
488               (tokenizer.ConsumeInt32, 123),
489               (tokenizer.ConsumeIdentifier, 'identifier3'),
490               ':',
491               (tokenizer.ConsumeString, 'string'),
492               (tokenizer.ConsumeIdentifier, 'identifiER_4'),
493               ':',
494               (tokenizer.ConsumeFloat, 1.1e+2),
495               (tokenizer.ConsumeIdentifier, 'ID5'),
496               ':',
497               (tokenizer.ConsumeFloat, -0.23),
498               (tokenizer.ConsumeIdentifier, 'ID6'),
499               ':',
500               (tokenizer.ConsumeString, 'aaaa\'bbbb'),
501               (tokenizer.ConsumeIdentifier, 'ID7'),
502               ':',
503               (tokenizer.ConsumeString, 'aa\"bb'),
504               (tokenizer.ConsumeIdentifier, 'ID8'),
505               ':',
506               '{',
507               (tokenizer.ConsumeIdentifier, 'A'),
508               ':',
509               (tokenizer.ConsumeFloat, float('inf')),
510               (tokenizer.ConsumeIdentifier, 'B'),
511               ':',
512               (tokenizer.ConsumeFloat, -float('inf')),
513               (tokenizer.ConsumeIdentifier, 'C'),
514               ':',
515               (tokenizer.ConsumeBool, True),
516               (tokenizer.ConsumeIdentifier, 'D'),
517               ':',
518               (tokenizer.ConsumeBool, False),
519               '}',
520               (tokenizer.ConsumeIdentifier, 'ID9'),
521               ':',
522               (tokenizer.ConsumeUint32, 22),
523               (tokenizer.ConsumeIdentifier, 'ID10'),
524               ':',
525               (tokenizer.ConsumeInt64, -111111111111111111),
526               (tokenizer.ConsumeIdentifier, 'ID11'),
527               ':',
528               (tokenizer.ConsumeInt32, -22),
529               (tokenizer.ConsumeIdentifier, 'ID12'),
530               ':',
531               (tokenizer.ConsumeUint64, 2222222222222222222),
532               (tokenizer.ConsumeIdentifier, 'ID13'),
533               ':',
534               (tokenizer.ConsumeFloat, 1.23456),
535               (tokenizer.ConsumeIdentifier, 'ID14'),
536               ':',
537               (tokenizer.ConsumeFloat, 1.2e+2),
538               (tokenizer.ConsumeIdentifier, 'false_bool'),
539               ':',
540               (tokenizer.ConsumeBool, False),
541               (tokenizer.ConsumeIdentifier, 'true_BOOL'),
542               ':',
543               (tokenizer.ConsumeBool, True),
544               (tokenizer.ConsumeIdentifier, 'true_bool1'),
545               ':',
546               (tokenizer.ConsumeBool, True),
547               (tokenizer.ConsumeIdentifier, 'false_BOOL1'),
548               ':',
549               (tokenizer.ConsumeBool, False)]
550
551    i = 0
552    while not tokenizer.AtEnd():
553      m = methods[i]
554      if type(m) == str:
555        token = tokenizer.token
556        self.assertEqual(token, m)
557        tokenizer.NextToken()
558      else:
559        self.assertEqual(m[1], m[0]())
560      i += 1
561
562  def testConsumeIntegers(self):
563    # This test only tests the failures in the integer parsing methods as well
564    # as the '0' special cases.
565    int64_max = (1 << 63) - 1
566    uint32_max = (1 << 32) - 1
567    text = '-1 %d %d' % (uint32_max + 1, int64_max + 1)
568    tokenizer = text_format._Tokenizer(text)
569    self.assertRaises(text_format.ParseError, tokenizer.ConsumeUint32)
570    self.assertRaises(text_format.ParseError, tokenizer.ConsumeUint64)
571    self.assertEqual(-1, tokenizer.ConsumeInt32())
572
573    self.assertRaises(text_format.ParseError, tokenizer.ConsumeUint32)
574    self.assertRaises(text_format.ParseError, tokenizer.ConsumeInt32)
575    self.assertEqual(uint32_max + 1, tokenizer.ConsumeInt64())
576
577    self.assertRaises(text_format.ParseError, tokenizer.ConsumeInt64)
578    self.assertEqual(int64_max + 1, tokenizer.ConsumeUint64())
579    self.assertTrue(tokenizer.AtEnd())
580
581    text = '-0 -0 0 0'
582    tokenizer = text_format._Tokenizer(text)
583    self.assertEqual(0, tokenizer.ConsumeUint32())
584    self.assertEqual(0, tokenizer.ConsumeUint64())
585    self.assertEqual(0, tokenizer.ConsumeUint32())
586    self.assertEqual(0, tokenizer.ConsumeUint64())
587    self.assertTrue(tokenizer.AtEnd())
588
589  def testConsumeByteString(self):
590    text = '"string1\''
591    tokenizer = text_format._Tokenizer(text)
592    self.assertRaises(text_format.ParseError, tokenizer.ConsumeByteString)
593
594    text = 'string1"'
595    tokenizer = text_format._Tokenizer(text)
596    self.assertRaises(text_format.ParseError, tokenizer.ConsumeByteString)
597
598    text = '\n"\\xt"'
599    tokenizer = text_format._Tokenizer(text)
600    self.assertRaises(text_format.ParseError, tokenizer.ConsumeByteString)
601
602    text = '\n"\\"'
603    tokenizer = text_format._Tokenizer(text)
604    self.assertRaises(text_format.ParseError, tokenizer.ConsumeByteString)
605
606    text = '\n"\\x"'
607    tokenizer = text_format._Tokenizer(text)
608    self.assertRaises(text_format.ParseError, tokenizer.ConsumeByteString)
609
610  def testConsumeBool(self):
611    text = 'not-a-bool'
612    tokenizer = text_format._Tokenizer(text)
613    self.assertRaises(text_format.ParseError, tokenizer.ConsumeBool)
614
615
616if __name__ == '__main__':
617  unittest.main()
618