summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_textwrap.py
blob: 472d125e538c83104fa24841df2ddc17d44493e4 (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
#
# Test suite for the textwrap module.
#
# Original tests written by Greg Ward <gward@python.net>.
# Converted to PyUnit by Peter Hansen <peter@engcorp.com>.
# Currently maintained by Greg Ward.
#
# $Id$
#

import unittest
from test import test_support

from textwrap import TextWrapper, wrap, fill, dedent


class BaseTestCase(unittest.TestCase):
    '''Parent class with utility methods for textwrap tests.'''

    def show(self, textin):
        if isinstance(textin, list):
            result = []
            for i in range(len(textin)):
                result.append("  %d: %r" % (i, textin[i]))
            result = '\n'.join(result)
        elif isinstance(textin, basestring):
            result = "  %s\n" % repr(textin)
        return result


    def check(self, result, expect):
        self.assertEquals(result, expect,
            'expected:\n%s\nbut got:\n%s' % (
                self.show(expect), self.show(result)))

    def check_wrap(self, text, width, expect, **kwargs):
        result = wrap(text, width, **kwargs)
        self.check(result, expect)

    def check_split(self, text, expect):
        result = self.wrapper._split(text)
        self.assertEquals(result, expect,
                          "\nexpected %r\n"
                          "but got  %r" % (expect, result))


class WrapTestCase(BaseTestCase):

    def setUp(self):
        self.wrapper = TextWrapper(width=45)

    def test_simple(self):
        # Simple case: just words, spaces, and a bit of punctuation

        text = "Hello there, how are you this fine day?  I'm glad to hear it!"

        self.check_wrap(text, 12,
                        ["Hello there,",
                         "how are you",
                         "this fine",
                         "day?  I'm",
                         "glad to hear",
                         "it!"])
        self.check_wrap(text, 42,
                        ["Hello there, how are you this fine day?",
                         "I'm glad to hear it!"])
        self.check_wrap(text, 80, [text])


    def test_whitespace(self):
        # Whitespace munging and end-of-sentence detection

        text = """\
This is a paragraph that already has
line breaks.  But some of its lines are much longer than the others,
so it needs to be wrapped.
Some lines are \ttabbed too.
What a mess!
"""

        expect = ["This is a paragraph that already has line",
                  "breaks.  But some of its lines are much",
                  "longer than the others, so it needs to be",
                  "wrapped.  Some lines are  tabbed too.  What a",
                  "mess!"]

        wrapper = TextWrapper(45, fix_sentence_endings=True)
        result = wrapper.wrap(text)
        self.check(result, expect)

        result = wrapper.fill(text)
        self.check(result, '\n'.join(expect))

    def test_fix_sentence_endings(self):
        wrapper = TextWrapper(60, fix_sentence_endings=True)

        # SF #847346: ensure that fix_sentence_endings=True does the
        # right thing even on input short enough that it doesn't need to
        # be wrapped.
        text = "A short line. Note the single space."
        expect = ["A short line.  Note the single space."]
        self.check(wrapper.wrap(text), expect)

        # Test some of the hairy end cases that _fix_sentence_endings()
        # is supposed to handle (the easy stuff is tested in
        # test_whitespace() above).
        text = "Well, Doctor? What do you think?"
        expect = ["Well, Doctor?  What do you think?"]
        self.check(wrapper.wrap(text), expect)

        text = "Well, Doctor?\nWhat do you think?"
        self.check(wrapper.wrap(text), expect)

        text = 'I say, chaps! Anyone for "tennis?"\nHmmph!'
        expect = ['I say, chaps!  Anyone for "tennis?"  Hmmph!']
        self.check(wrapper.wrap(text), expect)

        wrapper.width = 20
        expect = ['I say, chaps!', 'Anyone for "tennis?"', 'Hmmph!']
        self.check(wrapper.wrap(text), expect)

        text = 'And she said, "Go to hell!"\nCan you believe that?'
        expect = ['And she said, "Go to',
                  'hell!"  Can you',
                  'believe that?']
        self.check(wrapper.wrap(text), expect)

        wrapper.width = 60
        expect = ['And she said, "Go to hell!"  Can you believe that?']
        self.check(wrapper.wrap(text), expect)

    def test_wrap_short(self):
        # Wrapping to make short lines longer

        text = "This is a\nshort paragraph."

        self.check_wrap(text, 20, ["This is a short",
                                   "paragraph."])
        self.check_wrap(text, 40, ["This is a short paragraph."])


    def test_wrap_short_1line(self):
        # Test endcases

        text = "This is a short line."

        self.check_wrap(text, 30, ["This is a short line."])
        self.check_wrap(text, 30, ["(1) This is a short line."],
                        initial_indent="(1) ")


    def test_hyphenated(self):
        # Test breaking hyphenated words

        text = ("this-is-a-useful-feature-for-"
                "reformatting-posts-from-tim-peters'ly")

        self.check_wrap(text, 40,
                        ["this-is-a-useful-feature-for-",
                         "reformatting-posts-from-tim-peters'ly"])
        self.check_wrap(text, 41,
                        ["this-is-a-useful-feature-for-",
                         "reformatting-posts-from-tim-peters'ly"])
        self.check_wrap(text, 42,
                        ["this-is-a-useful-feature-for-reformatting-",
                         "posts-from-tim-peters'ly"])

    def test_hyphenated_numbers(self):
        # Test that hyphenated numbers (eg. dates) are not broken like words.
        text = ("Python 1.0.0 was released on 1994-01-26.  Python 1.0.1 was\n"
                "released on 1994-02-15.")

        self.check_wrap(text, 30, ['Python 1.0.0 was released on',
                                   '1994-01-26.  Python 1.0.1 was',
                                   'released on 1994-02-15.'])
        self.check_wrap(text, 40, ['Python 1.0.0 was released on 1994-01-26.',
                                   'Python 1.0.1 was released on 1994-02-15.'])

        text = "I do all my shopping at 7-11."
        self.check_wrap(text, 25, ["I do all my shopping at",
                                   "7-11."])
        self.check_wrap(text, 27, ["I do all my shopping at",
                                   "7-11."])
        self.check_wrap(text, 29, ["I do all my shopping at 7-11."])

    def test_em_dash(self):
        # Test text with em-dashes
        text = "Em-dashes should be written -- thus."
        self.check_wrap(text, 25,
                        ["Em-dashes should be",
                         "written -- thus."])

        # Probe the boundaries of the properly written em-dash,
        # ie. " -- ".
        self.check_wrap(text, 29,
                        ["Em-dashes should be written",
                         "-- thus."])
        expect = ["Em-dashes should be written --",
                  "thus."]
        self.check_wrap(text, 30, expect)
        self.check_wrap(text, 35, expect)
        self.check_wrap(text, 36,
                        ["Em-dashes should be written -- thus."])

        # The improperly written em-dash is handled too, because
        # it's adjacent to non-whitespace on both sides.
        text = "You can also do--this or even---this."
        expect = ["You can also do",
                  "--this or even",
                  "---this."]
        self.check_wrap(text, 15, expect)
        self.check_wrap(text, 16, expect)
        expect = ["You can also do--",
                  "this or even---",
                  "this."]
        self.check_wrap(text, 17, expect)
        self.check_wrap(text, 19, expect)
        expect = ["You can also do--this or even",
                  "---this."]
        self.check_wrap(text, 29, expect)
        self.check_wrap(text, 31, expect)
        expect = ["You can also do--this or even---",
                  "this."]
        self.check_wrap(text, 32, expect)
        self.check_wrap(text, 35, expect)

        # All of the above behaviour could be deduced by probing the
        # _split() method.
        text = "Here's an -- em-dash and--here's another---and another!"
        expect = ["Here's", " ", "an", " ", "--", " ", "em-", "dash", " ",
                  "and", "--", "here's", " ", "another", "---",
                  "and", " ", "another!"]
        self.check_split(text, expect)

        text = "and then--bam!--he was gone"
        expect = ["and", " ", "then", "--", "bam!", "--",
                  "he", " ", "was", " ", "gone"]
        self.check_split(text, expect)


    def test_unix_options (self):
        # Test that Unix-style command-line options are wrapped correctly.
        # Both Optik (OptionParser) and Docutils rely on this behaviour!

        text = "You should use the -n option, or --dry-run in its long form."
        self.check_wrap(text, 20,
                        ["You should use the",
                         "-n option, or --dry-",
                         "run in its long",
                         "form."])
        self.check_wrap(text, 21,
                        ["You should use the -n",
                         "option, or --dry-run",
                         "in its long form."])
        expect = ["You should use the -n option, or",
                  "--dry-run in its long form."]
        self.check_wrap(text, 32, expect)
        self.check_wrap(text, 34, expect)
        self.check_wrap(text, 35, expect)
        self.check_wrap(text, 38, expect)
        expect = ["You should use the -n option, or --dry-",
                  "run in its long form."]
        self.check_wrap(text, 39, expect)
        self.check_wrap(text, 41, expect)
        expect = ["You should use the -n option, or --dry-run",
                  "in its long form."]
        self.check_wrap(text, 42, expect)

        # Again, all of the above can be deduced from _split().
        text = "the -n option, or --dry-run or --dryrun"
        expect = ["the", " ", "-n", " ", "option,", " ", "or", " ",
                  "--dry-", "run", " ", "or", " ", "--dryrun"]
        self.check_split(text, expect)

    def test_funky_hyphens (self):
        # Screwy edge cases cooked up by David Goodger.  All reported
        # in SF bug #596434.
        self.check_split("what the--hey!", ["what", " ", "the", "--", "hey!"])
        self.check_split("what the--", ["what", " ", "the--"])
        self.check_split("what the--.", ["what", " ", "the--."])
        self.check_split("--text--.", ["--text--."])

        # When I first read bug #596434, this is what I thought David
        # was talking about.  I was wrong; these have always worked
        # fine.  The real problem is tested in test_funky_parens()
        # below...
        self.check_split("--option", ["--option"])
        self.check_split("--option-opt", ["--option-", "opt"])
        self.check_split("foo --option-opt bar",
                         ["foo", " ", "--option-", "opt", " ", "bar"])

    def test_punct_hyphens(self):
        # Oh bother, SF #965425 found another problem with hyphens --
        # hyphenated words in single quotes weren't handled correctly.
        # In fact, the bug is that *any* punctuation around a hyphenated
        # word was handled incorrectly, except for a leading "--", which
        # was special-cased for Optik and Docutils.  So test a variety
        # of styles of punctuation around a hyphenated word.
        # (Actually this is based on an Optik bug report, #813077).
        self.check_split("the 'wibble-wobble' widget",
                         ['the', ' ', "'wibble-", "wobble'", ' ', 'widget'])
        self.check_split('the "wibble-wobble" widget',
                         ['the', ' ', '"wibble-', 'wobble"', ' ', 'widget'])
        self.check_split("the (wibble-wobble) widget",
                         ['the', ' ', "(wibble-", "wobble)", ' ', 'widget'])
        self.check_split("the ['wibble-wobble'] widget",
                         ['the', ' ', "['wibble-", "wobble']", ' ', 'widget'])

    def test_funky_parens (self):
        # Second part of SF bug #596434: long option strings inside
        # parentheses.
        self.check_split("foo (--option) bar",
                         ["foo", " ", "(--option)", " ", "bar"])

        # Related stuff -- make sure parens work in simpler contexts.
        self.check_split("foo (bar) baz",
                         ["foo", " ", "(bar)", " ", "baz"])
        self.check_split("blah (ding dong), wubba",
                         ["blah", " ", "(ding", " ", "dong),",
                          " ", "wubba"])

    def test_initial_whitespace(self):
        # SF bug #622849 reported inconsistent handling of leading
        # whitespace; let's test that a bit, shall we?
        text = " This is a sentence with leading whitespace."
        self.check_wrap(text, 50,
                        [" This is a sentence with leading whitespace."])
        self.check_wrap(text, 30,
                        [" This is a sentence with", "leading whitespace."])

    def test_no_drop_whitespace(self):
        # SF patch #1581073
        text = " This is a    sentence with     much whitespace."
        self.check_wrap(text, 10,
                        [" This is a", "    ", "sentence ",
                         "with     ", "much white", "space."],
                        drop_whitespace=False)

    if test_support.have_unicode:
        def test_unicode(self):
            # *Very* simple test of wrapping Unicode strings.  I'm sure
            # there's more to it than this, but let's at least make
            # sure textwrap doesn't crash on Unicode input!
            text = "Hello there, how are you today?"
            self.check_wrap(text, 50, ["Hello there, how are you today?"])
            self.check_wrap(text, 20, ["Hello there, how are", "you today?"])
            olines = self.wrapper.wrap(text)
            assert isinstance(olines, list) and isinstance(olines[0], str)
            otext = self.wrapper.fill(text)
            assert isinstance(otext, str)

    def test_split(self):
        # Ensure that the standard _split() method works as advertised
        # in the comments

        text = "Hello there -- you goof-ball, use the -b option!"

        result = self.wrapper._split(text)
        self.check(result,
             ["Hello", " ", "there", " ", "--", " ", "you", " ", "goof-",
              "ball,", " ", "use", " ", "the", " ", "-b", " ",  "option!"])

    def test_bad_width(self):
        # Ensure that width <= 0 is caught.
        text = "Whatever, it doesn't matter."
        self.assertRaises(ValueError, wrap, text, 0)
        self.assertRaises(ValueError, wrap, text, -1)


class LongWordTestCase (BaseTestCase):
    def setUp(self):
        self.wrapper = TextWrapper()
        self.text = '''\
Did you say "supercalifragilisticexpialidocious?"
How *do* you spell that odd word, anyways?
'''

    def test_break_long(self):
        # Wrap text with long words and lots of punctuation

        self.check_wrap(self.text, 30,
                        ['Did you say "supercalifragilis',
                         'ticexpialidocious?" How *do*',
                         'you spell that odd word,',
                         'anyways?'])
        self.check_wrap(self.text, 50,
                        ['Did you say "supercalifragilisticexpialidocious?"',
                         'How *do* you spell that odd word, anyways?'])

        # SF bug 797650.  Prevent an infinite loop by making sure that at
        # least one character gets split off on every pass.
        self.check_wrap('-'*10+'hello', 10,
                        ['----------',
                         '               h',
                         '               e',
                         '               l',
                         '               l',
                         '               o'],
                        subsequent_indent = ' '*15)

    def test_nobreak_long(self):
        # Test with break_long_words disabled
        self.wrapper.break_long_words = 0
        self.wrapper.width = 30
        expect = ['Did you say',
                  '"supercalifragilisticexpialidocious?"',
                  'How *do* you spell that odd',
                  'word, anyways?'
                  ]
        result = self.wrapper.wrap(self.text)
        self.check(result, expect)

        # Same thing with kwargs passed to standalone wrap() function.
        result = wrap(self.text, width=30, break_long_words=0)
        self.check(result, expect)


class IndentTestCases(BaseTestCase):

    # called before each test method
    def setUp(self):
        self.text = '''\
This paragraph will be filled, first without any indentation,
and then with some (including a hanging indent).'''


    def test_fill(self):
        # Test the fill() method

        expect = '''\
This paragraph will be filled, first
without any indentation, and then with
some (including a hanging indent).'''

        result = fill(self.text, 40)
        self.check(result, expect)


    def test_initial_indent(self):
        # Test initial_indent parameter

        expect = ["     This paragraph will be filled,",
                  "first without any indentation, and then",
                  "with some (including a hanging indent)."]
        result = wrap(self.text, 40, initial_indent="     ")
        self.check(result, expect)

        expect = "\n".join(expect)
        result = fill(self.text, 40, initial_indent="     ")
        self.check(result, expect)


    def test_subsequent_indent(self):
        # Test subsequent_indent parameter

        expect = '''\
  * This paragraph will be filled, first
    without any indentation, and then
    with some (including a hanging
    indent).'''

        result = fill(self.text, 40,
                      initial_indent="  * ", subsequent_indent="    ")
        self.check(result, expect)


# Despite the similar names, DedentTestCase is *not* the inverse
# of IndentTestCase!
class DedentTestCase(unittest.TestCase):

    def assertUnchanged(self, text):
        """assert that dedent() has no effect on 'text'"""
        self.assertEquals(text, dedent(text))

    def test_dedent_nomargin(self):
        # No lines indented.
        text = "Hello there.\nHow are you?\nOh good, I'm glad."
        self.assertUnchanged(text)

        # Similar, with a blank line.
        text = "Hello there.\n\nBoo!"
        self.assertUnchanged(text)

        # Some lines indented, but overall margin is still zero.
        text = "Hello there.\n  This is indented."
        self.assertUnchanged(text)

        # Again, add a blank line.
        text = "Hello there.\n\n  Boo!\n"
        self.assertUnchanged(text)

    def test_dedent_even(self):
        # All lines indented by two spaces.
        text = "  Hello there.\n  How are ya?\n  Oh good."
        expect = "Hello there.\nHow are ya?\nOh good."
        self.assertEquals(expect, dedent(text))

        # Same, with blank lines.
        text = "  Hello there.\n\n  How are ya?\n  Oh good.\n"
        expect = "Hello there.\n\nHow are ya?\nOh good.\n"
        self.assertEquals(expect, dedent(text))

        # Now indent one of the blank lines.
        text = "  Hello there.\n  \n  How are ya?\n  Oh good.\n"
        expect = "Hello there.\n\nHow are ya?\nOh good.\n"
        self.assertEquals(expect, dedent(text))

    def test_dedent_uneven(self):
        # Lines indented unevenly.
        text = '''\
        def foo():
            while 1:
                return foo
        '''
        expect = '''\
def foo():
    while 1:
        return foo
'''
        self.assertEquals(expect, dedent(text))

        # Uneven indentation with a blank line.
        text = "  Foo\n    Bar\n\n   Baz\n"
        expect = "Foo\n  Bar\n\n Baz\n"
        self.assertEquals(expect, dedent(text))

        # Uneven indentation with a whitespace-only line.
        text = "  Foo\n    Bar\n \n   Baz\n"
        expect = "Foo\n  Bar\n\n Baz\n"
        self.assertEquals(expect, dedent(text))

    # dedent() should not mangle internal tabs
    def test_dedent_preserve_internal_tabs(self):
        text = "  hello\tthere\n  how are\tyou?"
        expect = "hello\tthere\nhow are\tyou?"
        self.assertEquals(expect, dedent(text))

        # make sure that it preserves tabs when it's not making any
        # changes at all
        self.assertEquals(expect, dedent(expect))

    # dedent() should not mangle tabs in the margin (i.e.
    # tabs and spaces both count as margin, but are *not*
    # considered equivalent)
    def test_dedent_preserve_margin_tabs(self):
        text = "  hello there\n\thow are you?"
        self.assertUnchanged(text)

        # same effect even if we have 8 spaces
        text = "        hello there\n\thow are you?"
        self.assertUnchanged(text)

        # dedent() only removes whitespace that can be uniformly removed!
        text = "\thello there\n\thow are you?"
        expect = "hello there\nhow are you?"
        self.assertEquals(expect, dedent(text))

        text = "  \thello there\n  \thow are you?"
        self.assertEquals(expect, dedent(text))

        text = "  \t  hello there\n  \t  how are you?"
        self.assertEquals(expect, dedent(text))

        text = "  \thello there\n  \t  how are you?"
        expect = "hello there\n  how are you?"
        self.assertEquals(expect, dedent(text))


def test_main():
    test_support.run_unittest(WrapTestCase,
                              LongWordTestCase,
                              IndentTestCases,
                              DedentTestCase)

if __name__ == '__main__':
    test_main()