summaryrefslogtreecommitdiffstats
path: root/tests/test_md_tw.py
blob: 18fb1ac3c1b1809ee07668d5adef43fc9d5739a0 (plain) (blame)
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
# -*- coding: utf-8 -*-
#
#   Copyright © 2018 rsiddharth <s@ricketyspace.net>.
#
#    This file is part of markdown-textwrap.
#
#   markdown-textwrap is free software: you can redistribute it
#   and/or modify it under the terms of the GNU General Public License
#   as published by the Free Software Foundation, either version 3 of
#   the License, or (at your option) any later version.
#
#   markdown-textwrap is distributed in the hope that it will be
#   useful, but WITHOUT ANY WARRANTY; without even the implied
#   warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
#   See the GNU General Public License for more details.
#
#   You should have received a copy of the GNU General Public License
#   along with markdown-textwrap (see COPYING).  If not, see
#   <http://www.gnu.org/licenses/>.

import textwrap

from mistune import Renderer
from nose.tools import assert_equal
from pkg_resources import resource_string, resource_filename

from md_tw import TWBlockLexer, TWInlineLexer, TWRenderer, TWMarkdown

def _get_data(f):
    rs = resource_string(__name__, '/'.join(['data', f]))
    return rs.decode()


def _get_data_path(f):
    return resource_filename(__name__, '/'.join(['data', f]))


class TestTWBlockLexer(object):

    def setup(self):
        self.bl = TWBlockLexer()

    def _parse(self, file_):
        txt = _get_data(file_)
        return self.bl.parse(txt)

    def _validate(self, tokens, type_, expected):
        for token in tokens:
            if token['type'] == type_:
                assert_equal(token['text'], expected.pop(0))

    def test_parse_block_code(self):
        tokens = self._parse('blexer-block-code.md')

        expected_bc = [
            '    $ echo \'Zap!\'\n    $ rm -rf /\n\n',
            '    $ :(){:|:&};:\n\n'
            ]
        self._validate(tokens, 'code', expected_bc)

    def test_parse_fences(self):
        tokens = self._parse('blexer-fences.md')

        expected_fences = [
            '```bash\n$ echo \'Zap!\'\n$ rm -rf /\n```\n',
            '```bash\n$ :(){:|:&};:\n```\n'
            ]

        self._validate(tokens, 'code', expected_fences)

    def test_parse_heading(self):
        tokens = self._parse('blexer-heading.md')

        expected_hs = [
            '# Milky Chance\n\n',
            '## Flashed\n\n',
            '### Junk Mind\n\n',
            ]

        self._validate(tokens, 'heading', expected_hs)

    def test_parse_lheading(self):
        tokens = self._parse('blexer-lheading.md')

        expected_lhs = [
            'Milky Chance\n============\n\n',
            'Flashed\n-------\n\n',
            '### Junk Mind\n\n',
            ]

        self._validate(tokens, 'heading', expected_lhs)

    def test_parse_hrule(self):
        tokens = self._parse('blexer-hrules.md')

        expected_hrs = [
            '* * *\n\n',
            '***\n\n',
            '*****\n\n',
            '- - -\n\n',
            '---------------------------------------\n\n'
            ]

        self._validate(tokens, 'hrule', expected_hrs)

    def test_parse_list_block(self):
        tokens = self._parse('blexer-lists.md')

        def process(tokens):
            token = tokens.pop(0)
            while token:
                type_ = token['type']

                expected_token = None
                if type_ in expected:
                    expected_token = expected[type_].pop(0)

                validate(token, expected_token)

                if type_ == 'list_end':
                    break
                else:
                    token = tokens.pop(0)

            return tokens

        def validate(token, expected_token=None):
            type_ = token['type']

            if type_ == 'list_item_start':
                assert 'text' in token
                assert 'spaces' in token
            elif type_ == 'list_item_end':
                assert 'spaces' in token

            if not expected_token:
                return

            if 'text' in token:
                assert_equal(token['text'], expected_token['text'])
            if 'spaces' in token:
                assert_equal(token['spaces'], expected_token['spaces'])

            return

        # test list 1
        expected = {
            'list_item_start': [
                {'text': '+   ', 'spaces': 4},
                {'text': '+   ', 'spaces': 4},
                {'text': '+   ', 'spaces': 4}
                ],
            'text': [
                {'text': 'Re: Your Brains'},
                {'text': 'Shop Vac'},
                {'text': 'Flickr'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                {'spaces': 4}
                ]
            }
        tokens = process(tokens)

        # test list 2
        expected = {
            'list_item_start': [
                {'text': '1.  ', 'spaces': 4},
                {'text': '2.  ', 'spaces': 4},
                {'text': '3.  ', 'spaces': 4}
                ],
            'text': [
                {'text': 'First of May'},
                {'text': 'You Ruined Everything'},
                {'text': 'Sucker Punch'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                {'spaces': 4}
                ]
            }
        token = process(tokens)

        # test list 3
        expected = {
            'list_item_start': [
                {'text': '*   ', 'spaces': 4},
                {'text': '*   ', 'spaces': 4},
                ],
            'text': [
                {'text': 'Lorem ipsum dolor sit amet, consectetuer adipiscing elit.'},
                {'text': 'Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,'},
                {'text': 'viverra nec, fringilla in, laoreet vitae, risus.'},
                {'text': 'Donec sit amet nisl. Aliquam semper ipsum sit amet velit.'},
                {'text': 'Suspendisse id sem consectetuer libero luctus adipiscing.'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

        # test list 4
        expected = {
            'list_item_start': [
                {'text': '*   ', 'spaces': 4},
                {'text': '*   ', 'spaces': 4},
                ],
            'text': [
                {'text': 'Lorem ipsum dolor sit amet, consectetuer adipiscing elit.'},
                {'text': 'Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi,'},
                {'text': 'viverra nec, fringilla in, laoreet vitae, risus.'},
                {'text': 'Donec sit amet nisl. Aliquam semper ipsum sit amet velit.'},
                {'text': 'Suspendisse id sem consectetuer libero luctus adipiscing.'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

        # test list 5
        expected = {
            'loose_item_start': [
                {'text': '*   ', 'spaces': 4},
                {'text': '*   ', 'spaces': 4},
                ],
            'text': [
                {'text': 'Codey Monkey'},
                {'text': 'Tom Cruise Crazy'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                ]
            }
        tokens = process(token)

        # test list 5
        expected = {
            'loose_item_start': [
                {'text': '1.  ', 'spaces': 4},
                {'text': '2.  ', 'spaces': 4},
                ],
            'text': [
                {'text': 'This is a list item with two paragraphs. Lorem ipsum dolor'},
                {'text': 'sit amet, consectetuer adipiscing elit. Aliquam hendrerit'},
                {'text': 'mi posuere lectus.'},
                {'text': 'Vestibulum enim wisi, viverra nec, fringilla in, laoreet'},
                {'text': 'vitae, risus. Donec sit amet nisl. Aliquam semper ipsum'},
                {'text': 'sit amet velit.'},
                {'text': 'Suspendisse id sem consectetuer libero luctus adipiscing.'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

        # test list 6
        expected = {
            'loose_item_start': [
                {'text': '*   ', 'spaces': 4},
                {'text': '*   ', 'spaces': 4},
                ],
            'text': [
                {'text': 'This is a list item with two paragraphs.'},
                {'text': 'This is the second paragraph in the list item. You\'re'},
                {'text': 'only required to indent the first line. Lorem ipsum dolor'},
                {'text': 'sit amet, consectetuer adipiscing elit.'},
                {'text': 'Another item in the same list.'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

        # test list 7
        expected = {
            'loose_item_start': [
                {'text': '*   ', 'spaces': 4},
                ],
            'text': [
                {'text': 'A list item with a blockquote:'},
                ],
            'list_item_end': [
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

        # test list 7
        expected = {
            'loose_item_start': [
                {'text': '*   ', 'spaces': 4},
                ],
            'text': [
                {'text': 'A list item with a code block:'},
                ],
            'list_item_end': [
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

        # test list 7
        expected = {
            'loose_item_start': [
                {'text': '1.  ', 'spaces': 4},
                {'text': '1.  ', 'spaces': 4},
                ],
            'text': [
                {'text': 'This is a list item has a nested list.'},
                {'text': 'Lorem ipsum dolor sit amet, consectetuer adipiscing'},
                {'text': 'elit. Aliquam hendrerit mi posuere lectus.'},
                ],
            'list_item_end': [
                {'spaces': 4},
                {'spaces': 4},
                ]
            }
        tokens = process(tokens)

    def test_parse_block_quote(self):
        tokens = self._parse('blexer-blockquote.md')

        def process(tokens):
            token = tokens.pop(0)
            while token:
                type_ = token['type']

                expected_token = None
                if type_ in expected:
                    expected_token = expected[type_].pop(0)

                validate(token, expected_token)

                if type_ == 'block_quote_end':
                    break
                else:
                    token = tokens.pop(0)

            return tokens

        def validate(token, expected_token=None):
            type_ = token['type']

            if type_ == 'block_quote_start':
                assert 'text' in token
                assert 'spaces' in token
            elif type_ == 'block_quote_end':
                assert 'spaces' in token

            if not expected_token:
                return

            if 'text' in token:
                assert_equal(token['text'], expected_token['text'])
            if 'spaces' in token:
                assert_equal(token['spaces'], expected_token['spaces'])

            return

        # test blockquote 1
        expected = {
            'block_quote_start': [
                {'text': '> ', 'spaces': 2},
                ],
            'paragraph': [
                {'text': 'This is a blockquote with two paragraphs. Lorem '
                     'ipsum dolor sit amet,\nconsectetuer adipiscing '
                     'elit. Aliquam hendrerit mi posuere lectus.\nVestibulum '
                'enim wisi, viverra nec, fringilla in, laoreet vitae, risus.'},
                {'text': 'Donec sit amet nisl. Aliquam semper ipsum sit '
                     'amet velit. Suspendisse\nid sem consectetuer '
                'libero luctus adipiscing.'},
                ],
            'block_quote_end': [
                {'spaces': 2},
                ]
            }
        tokens = process(tokens)
        token = tokens.pop(0) # Remove paragraph after blockquote.

        # test blockquote 2
        expected = {
            'block_quote_start': [
                {'text': '> ', 'spaces': 2},
                ],
            'paragraph': [
                {'text': 'This is a blockquote with two paragraphs. Lorem '
                     'ipsum dolor sit amet,\nconsectetuer adipiscing '
                     'elit. Aliquam hendrerit mi posuere lectus.\nVestibulum '
                'enim wisi, viverra nec, fringilla in, laoreet vitae, risus.'},
                {'text': 'Donec sit amet nisl. Aliquam semper ipsum sit '
                     'amet velit. Suspendisse\nid sem consectetuer '
                'libero luctus adipiscing.'},
                ],
            'block_quote_end': [
                {'spaces': 2},
                ]
            }
        tokens = process(tokens)
        token = tokens.pop(0) # Remove paragraph after blockquote.

        # test blockquote 3
        expected = {
            'block_quote_start': [
                {'text': '> ', 'spaces': 2},
                {'text': '> ', 'spaces': 2},
                ],
            'paragraph': [
                {'text': 'This is the first level of quoting.'},
                {'text': 'This is nested blockquote.'},
                {'text': 'Back to the first level.'}
                ],
            'block_quote_end': [
                {'spaces': 2},
                {'spaces': 2},
                ]
            }
        tokens = process(tokens)
        tokens = process(tokens)
        token = tokens.pop(0) # Remove paragraph after blockquote.

        # test blockquote 4
        expected = {
            'block_quote_start': [
                {'text': '> ', 'spaces': 2},
                ],
            'heading': [
                {'text': '## This is a header.\n\n'}
                ],
            'list_item_start': [
                {'text': '1.   ', 'spaces': 5},
                {'text': '2.   ', 'spaces': 5}
                ],
            'text': [
                {'text': 'This is the first list item.'},
                {'text': 'This is the second list item.'}
                ],
            'list_item_end': [
                {'spaces': 5},
                {'spaces': 5}
                ],
            'paragraph': [
                {'text': 'Here\'s some example code:'}
                ],
            'code': [
                {'text': '    return shell_exec("echo $input | '
                     '$markdown_script");'}
                ],
            'block_quote_end': [
                {'spaces': 2},
                ]
            }
        tokens = process(tokens)

    def test_parse_def_links(self):
        tokens = self._parse('blexer-def-links.md')

        expected_dls = [
            '[bob]: http://bob.name/ "Bob\'s home"\n',
            '[alice]: <http://alice.name/> "Alice\'s home"\n\n',
            '[bar]: http://bar.beer/  "Foo Bar Beer"\n\n',
            '[GNU.org]: http://gnu.org\n\n',
            '  [1]: http://google.com/        "Google"\n',
            '  [2]: http://search.yahoo.com/  "Yahoo Search"\n',
            '  [3]: http://search.msn.com/    "MSN Search"\n\n',
            '  [google]: http://google.com/        "Google"\n',
            '  [yahoo]:  http://search.yahoo.com/  "Yahoo Search"\n',
            '  [msn]:    http://search.msn.com/    "MSN Search"',
            ]
        self._validate(tokens, 'def_links', expected_dls)

    def test_parse_def_footnotes(self):
        tokens = self._parse('blexer-footnotes.md')

        def process(tokens):
            token = tokens.pop(0)
            while token:
                type_ = token['type']

                expected_token = None
                if type_ in expected:
                    expected_token = expected[type_].pop(0)

                validate(token, expected_token)

                if type_ == 'footnote_end':
                    break
                else:
                    token = tokens.pop(0)

            return tokens

        def validate(token, expected_token=None):
            type_ = token['type']

            if type_ == 'footnote_start':
                assert 'multiline' in token
                assert 'spaces' in token
            elif type_ == 'footnote_end':
                assert 'spaces' in token

            if not expected_token:
                return

            if 'text' in token:
                assert_equal(token['text'], expected_token['text'])
            if 'spaces' in token:
                assert_equal(token['spaces'], expected_token['spaces'])

            return

        # test footnote 1
        expected = {
            'footnote_start': [
                {'multiline': False, 'spaces': 0},
                ],
            'paragraph': [
                {'text': 'This phrase has a single line footnote[^foot1].'},
                {'text': 'Lorem ipsum dolor sit amet, consectetuer'
                     ' adipiscing elit.'},
                ],
            'footnote_end': [
                {'spaces': 0}
                ]
            }
        tokens = process(tokens)

        # test footnote 2
        expected = {
            'footnote_start': [
                {'multiline': True, 'spaces': 4},
                ],
            'paragraph': [
                {'text': 'This other phrase has a multiline footnote[^foot2].'},
                {'text': 'Vestibulum enim wisi, viverra nec, fringilla in, '
                     'laoreet\nvitae, risus. Donec sit amet nisl. Aliquam '
                'semper ipsum sit amet\nvelit.'},
                ],
            'footnote_end': [
                {'spaces': 4}
                ]
            }
        tokens = process(tokens)

        # test footnote 3
        expected = {
            'footnote_start': [
                {'multiline': True, 'spaces': 3},
                ],
            'paragraph': [
                {'text': 'This phrase has a blockquote in its footnote[^foot3].'},
                {'text': 'A footnote with blockquotes'},
                {'text': 'Start of block quote in footnote:'},
                {'text': 'This is a blockquote with two paragraphs. Lorem'
                     ' ipsum dolor sit amet,\nconsectetuer adipiscing elit.'
                ' Aliquam hendrerit mi posuere lectus.\nVestibulum enim wisi,'
                ' viverra nec, fringilla in, laoreet vitae, risus.'},
                {'text': 'Donec sit amet nisl. Aliquam semper ipsum sit amet '
                     'velit. Suspendisse\nid sem consectetuer libero luctus '
                'adipiscing.'},
                {'text': 'End of block quote in foot note.'},
                ],
            'footnote_end': [
                {'spaces': 3}
                ]
            }
        tokens = process(tokens)

    def test_parse_block_html(self):
        tokens = self._parse('blexer-block-html.md')

        def process(tokens):
            token = tokens.pop(0)
            while token:
                type_ = token['type']

                expected_token = None
                if type_ in expected:
                    expected_token = expected[type_].pop(0)

                validate(token, expected_token)

                if type_ in ['open_html', 'close_html']:
                    break
                else:
                    token = tokens.pop(0)

            return tokens

        def validate(token, expected_token=None):
            type_ = token['type']

            if type_ == 'open_html':
                assert 'tag' in token
                assert 'extra' in token
                assert 'text' in token
            elif type_ == 'close_html':
                assert 'text' in token

            if not expected_token:
                return

            if 'text' in token:
                assert_equal(token['text'], expected_token['text'])
            if 'extra' in token:
                assert_equal(token['extra'], expected_token['extra'])
            if 'tag' in token:
                assert_equal(token['tag'], expected_token['tag'])
            return

        expected = {
            'open_html': [
                {
                    'tag': 'table',
                    'extra': '',
                    'text': '\n    <tr>\n        <td>Monte Carlo</td>'
                    '\n    </tr>\n'
                },
            ],
            }
        tokens = process(tokens)

        expected = {
            'open_html': [
                {
                    'tag': 'div',
                    'extra': ' class="parley"',
                    'text': '\n  <article>\n    '
                    '<p>A dispute conference; human snafu.</p>\n  '
                    '</article>\n'
                }
            ],
            }
        tokens = process(tokens)

        expected = {
            'close_html': [
                {'text': '<hr />\n\n'}
                ]
            }
        tokens = process(tokens)

    def teardown(self):
        pass


class TestTWInlineLexer(object):

    def setup(self):
        renderer = Renderer()
        self.il = TWInlineLexer(renderer)

    def teardown(self):
        pass


class TestTWRenderer(object):

    def setup(self):
        pass


    def test_tw_obj_with_default_width(self):
        renderer = TWRenderer()

        # Check existence of textwrap.TexWrapper object.
        assert isinstance(renderer.tw, textwrap.TextWrapper)

        # Check its width
        assert_equal(renderer.tw.width, 72)


    def test_tw_obj_with_custom_width(self):
        renderer = TWRenderer(tw_width=80)

        # Check existence of textwrap.TexWrapper object.
        assert isinstance(renderer.tw, textwrap.TextWrapper)

        # Check its width
        assert_equal(renderer.tw.width, 80)


    def test_tw_set_options_with_valid_opts(self):
        renderer  = TWRenderer()

        # Set valid options
        renderer._tw_set_options(
            width=80,
            initial_indent='> ',
            subsequent_indent=' ',
            drop_whitespace=False)

        # Confirm options are set.
        assert_equal(renderer.tw.width, 80)
        assert_equal(renderer.tw.initial_indent, '> ')
        assert_equal(renderer.tw.subsequent_indent, ' ')
        assert_equal(renderer.tw.drop_whitespace, False)


    def test_tw_set_options_with_invalid_opts(self):
        renderer = TWRenderer()

        # Set invalid options
        renderer._tw_set_options(
            erase_bumps=True,
            destroy_ampersands=False,
            end_width='வருகிறேன்',
            insert_between_paragraphs='time bombs')

        # Confirm options are not set.
        assert_equal(getattr(renderer.tw, 'erase_bumps', None), None)
        assert_equal(getattr(renderer.tw, 'destroy_ampersands',
                                 None), None)
        assert_equal(getattr(renderer.tw, 'end_width', None), None)
        assert_equal(getattr(renderer.tw, 'insert_between_paragraphs',
                                 None), None)


    def teardown(self):
        pass


class TestTWMarkdown(object):

    def setup(self):
        self.md = TWMarkdown()


    def test_renderer_obj(self):
        assert isinstance(self.md.renderer, TWRenderer)


    def test_inline_obj(self):
        assert isinstance(self.md.inline, TWInlineLexer)


    def test_block_obj(self):
        assert isinstance(self.md.block, TWBlockLexer)


    def teardown(self):
        pass