File: test_regex_commonmark.py

package info (click to toggle)
apostrophe 3.4-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 3,408 kB
  • sloc: python: 5,733; xml: 226; sh: 66; javascript: 50; makefile: 2
file content (381 lines) | stat: -rw-r--r-- 12,844 bytes parent folder | download
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
#!/usr/bin/env python
# -*- Mode: Python; coding: utf-8; indent-tabs-mode: nil; tab-width: 4 -*-
### BEGIN LICENSE
# Copyright (C) 2019, Wolf Vollprecht <w.vollprecht@gmail.com>
#               2021, Manuel Genovés <manuel.genoves@gmail.com>
# This program is free software: you can redistribute it and/or modify it 
# under the terms of the GNU General Public License version 3, as published 
# by the Free Software Foundation.
# 
# This program is distributed in the hope that it will be useful, but 
# WITHOUT ANY WARRANTY; without even the implied warranties of 
# MERCHANTABILITY, SATISFACTORY QUALITY, 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 this program.  If not, see <http://www.gnu.org/licenses/>.
### END LICENSE

import unittest
import regex as re

from apostrophe import markup_regex

def regex_tests(test_texts, regex_pattern):
    """Decorator to generate regex test cases for a unittest.TestCase method."""
    def decorator(test_method):
        def wrapper(self):
            for test, expected in test_texts.items():
                with self.subTest(test=test):
                    match = re.search(regex_pattern, test)
                    if expected is None:
                        self.assertIsNone(match, msg=f"Test failed: {test}")
                    else:
                        self.assertIsNotNone(match, msg=f"Test failed: {test}")
                        if isinstance(expected, dict):
                            for key, value in expected.items():
                                self.assertEqual(match.group(key), value,
                                                 msg=f"{test} - group '{key}'")
                        elif isinstance(expected, bool):
                            self.assertTrue(match, msg=f"Test failed: {test}")
                        else:
                            self.assertEqual(match.group("text"), expected,
                                             msg=f"{test} - text")
        return wrapper
    return decorator

class TestRegex(unittest.TestCase):
    """Test cases based on CommonMark's specs and demo:
       - https://spec.commonmark.org/
       - https://spec.commonmark.org/dingus/

       CommonMark is the Markdown variant chosen as first-class. It's great and encouraged that
       others are supported as well, but when in conflict or undecided, CommonMark should be picked.
    """

    @regex_tests(
        test_texts={
            "*italic*": "italic",
            "*i*": "i", # one letter
            "This is *italic* text": "italic", # in sentence
            "This is *1italic* text": "1italic", # starting with number
            "This is *和italic* text": "和italic", # unicode
            "before*middle*end": "middle", # within word
            "leading * space*": None, # leading space
            "This is **italic** text": None, # bold
            "This is *italic** text": None, # mismatch
            "This is \\*italic** text": None, # escaped
            "This is *italic\\* text": None, # escaped
            "This is **italic* text": None, # mismatch
            "before* middle *end": None, 
            "before* middle*end": None,
            "before*middle *end": "middle ",
            "*partial* match*": "partial", 
            "*multi\nline*": None, # shouldn't match across lines
            "empty * * italic": None # empty
        },
        regex_pattern=markup_regex.ITALIC_ASTERISK
    )
    def test_italic_asterisk(self):
        pass

    @regex_tests(
        test_texts={
            "_italic_": "italic",
            "_i_": "i", # one letter
            "This is _italic_ text": "italic", # in sentence
            "This is _1italic_ text": "1italic", # starting with number
            "This is _和italic_ text": "和italic", # unicode
            "before_middle_end": None, # within word
            "This is __italic__ text": None, # bold
            "This is __italic_ text": None, # mismatch
            "This is _italic__ text": None, # mismatch
            "before_ middle _end": None,
            "before_ middle_end": None,
            "before_middle _end": None,
            "_partial_ match_": "partial", 
            "_multi\nline_": None, # shouldn't match across lines
            "empty _ _ italic": None, # empty
        },
        regex_pattern=markup_regex.ITALIC_UNDERSCORE
    )
    def test_italic_underscore(self):
        pass

    @regex_tests(
        test_texts={
            "**bold**": "bold",
            "__bold__": "bold",
            "**b**": "b",
            "__b__": "b",
            "This is **bold** text": "bold",
            "This is **1bold** text": "1bold",
            "This is **和bold** text": "和bold",
            "This is __bold__ text": "bold",
            "before**middle**end": "middle",
            "before** middle **end": None,
            "before** middle**end": None,
            "before**middle **end": "middle ",
            "**bold__": None,
            "\\**bold**": None,
            "**multi\nline**": None, # shouldn't match across lines
            "empty * * bold": None
        },
        regex_pattern=markup_regex.BOLD
    )
    def test_bold(self):
        pass

    @regex_tests(
        test_texts={
            "**_text_**": "text",
            "***text***": "text",
            "___text___": "text",
            "__*text*__": "text",
            "__*text_**": None,
            "__*text__*": None,
            "***t***": "t",
            "___t___": "t",
            "This is ***text*** text": "text",
            "This is ***1text*** text": "1text",
            "This is ***和text*** text": "和text",
            "This is ___text___ text": "text",
            "before***middle***end": "middle",
            "before*** middle ***end": None,
            "before*** middle***end": None,
            "before***middle ***end": "middle ",
            "empty * * text": None
        },
        regex_pattern=markup_regex.BOLD_ITALIC
    )
    def test_bold_italic(self):
        pass

    @regex_tests(
        test_texts={
            "~~text~~": "text",
            "~~text text~~": "text text",
            "~~text~": None,
            "~~t~~": "t",
            "~~text ~~": None,
            "~~ text~~": None,
            "\\~~text~~": None,
            "~~text\\~~": None,
            "empty ~~ ~~ text": None
        },
        regex_pattern=markup_regex.STRIKETHROUGH
    )
    def test_strikethrough(self):
        pass

    @regex_tests(
        test_texts={
            "`code`": "code",
            "``code with ` backtick``": "code with ` backtick",
            "```multi tick```": "multi tick",
            "` leading space`": " leading space",
            "`trailing space `": "trailing space ",
            "````": None,
            "`": None,
            "`` code `": None,
            "`\nmulti line`": None
        },
        regex_pattern=markup_regex.CODE
    )
    def test_code(self):
        pass

    @regex_tests(
        test_texts={
            "[text](url)": {"text": "text", "url": "url"},
            "[test](http://example.com)": {"text": "test", "url": "http://example.com"},
            "[test](url \"title\")": {"text": "test", "url": "url", "title": "title"},
            "[empty]()": None,
            "[invalid](url": None,
            "[](url)": {"text": "", "url": "url"},
            # "[text](url \"title)": None,
            "[text] (url)": None
        },
        regex_pattern=markup_regex.LINK
    )
    def test_link(self):
        pass

    @regex_tests(
        test_texts={
            "![alt](img.jpg)": {"text": "alt", "url": "img.jpg"},
            "![test](http://example.com/image.png \"title\")": {"text": "test", "url": "http://example.com/image.png", "title": "title"},
            "![empty]()": None,
            "!invalid](url)": None,
            "![alt](url": None
        },
        regex_pattern=markup_regex.IMAGE
    )
    def test_image(self):
        pass

    @regex_tests(
        test_texts={
            "---": True,
            "***": True,
            "___": True,
            "- - -": True,
            "--": None,
            "=====": None,
            "* *": None,
            "*****": True,
            "  ***  ": True,
            "\t---\t": None,
            "-*--": None
        },
        regex_pattern=markup_regex.HORIZONTAL_RULE
    )
    def test_hr(self):
        pass

    @regex_tests(
        test_texts={
            # Valid checklist items
            "- [ ] item": {"check": " ", "text": "item"},
            "+ [X] done": {"check": "X", "text": "done"},
            # Invalid checklist items
            "- [] missing check": None,
            "[ ] standalone": None,
            "-[ ] no space": None,
            "- [x]extra": None,
        },
        regex_pattern=markup_regex.CHECKLIST
    )
    def test_checklist(self):
        pass

    @regex_tests(
        test_texts={
            "# Header 1": "Header 1",
            "## Header 2": "Header 2",
            "### Header 3": "Header 3",
            "#### Header 4": "Header 4",
            "##### Header 5": "Header 5",
            "###### Header 6": "Header 6",
            "#Header 1": None,
            " # Header 1": None,
            "#": None,
            "#######": None,
            "before\n# Header\nafter": "Header"
        },
        regex_pattern=markup_regex.HEADER
    )
    def test_header(self):
        pass

    @regex_tests(
        test_texts={
            "Header 1\n=": None, # techincally correct, but better from an usability POV
            "Header 1##\n=": None,
            "Header 1\n=\n": "Header 1",
            "Header 1##\n=\n": "Header 1##",
            "Header 2\n--  \n": "Header 2",
            "Header 1\n=f": None,
            "Header 1\n =": None
        },
        regex_pattern=markup_regex.HEADER_UNDER
    )
    def test_header_under(self):
        pass

    @regex_tests(
        test_texts={
            "- item": {"indent": "", "symbol": "-", "text": "item"},
            "\t+ item": {"indent": "\t", "symbol": "+", "text": "item"},
            "*item": None,
            "not a list": None
        },
        regex_pattern=markup_regex.LIST
    )
    def test_list(self):
        pass

    @regex_tests(
        test_texts={
            "1. item": {"indent": "", "prefix": "1.", "number": "1", "delimiter": ".", "text": "item"},
            "a) item": {"indent": "", "prefix": "a)", "delimiter": ")", "text": "item"},
            "    2) indented": {"indent": "    ", "prefix": "2)", "number": "2", "delimiter": ")", "text": "indented"},
            "1 item": None
        },
        regex_pattern=markup_regex.ORDERED_LIST
    )
    def test_ordered_list(self):
        pass

    @regex_tests(
        test_texts={
            "> blockquote": "blockquote",
            "   > spaced blockquote": "spaced blockquote",
            "no blockquote": None
        },
        regex_pattern=markup_regex.BLOCK_QUOTE
    )
    def test_block_quote(self):
        pass

    @regex_tests(
        test_texts={
            "```code block```": "code block",
            "~~~example~~~": "example",
            "```not closed": None
        },
        regex_pattern=markup_regex.CODE_BLOCK
    )
    def test_code_block(self):
        pass

    @regex_tests(
        test_texts={
            "$a$": "a",
            "$ab$": "ab",
            "$a b$": "a b",
            "$ a$": None,
            "$abc": None,
            "$$math$$": "math"
        },
        regex_pattern=markup_regex.MATH
    )
    def test_math(self):
        pass

    @regex_tests(
        test_texts={
            "ref[^1]": {"text": "ref", "id": "1"},
            "note[^note]": {"text": "note", "id": "note"},
            "[^id]": None
        },
        regex_pattern=markup_regex.FOOTNOTE_ID
    )
    def test_footnote_id(self):
        pass

    @regex_tests(
        test_texts={
            "[^1]: This is a footnote.\n": {"id": "1", "text": "This is a footnote."},
            "  [^note]:  Footnote text\n": {"id": "note", "text": "Footnote text"},
            "[^2]: First line\n    second line\n": {"id": "2", "text": "First line\n    second line"},
            "Not a footnote": None
        },
        regex_pattern=markup_regex.FOOTNOTE
    )
    def test_footnote(self):
        pass

    @regex_tests(
        test_texts={
            "---\ntitle: Test\ndate: 2025-03-06\n---\n": "title: Test\ndate: 2025-03-06",
            "---\ntitle: Another\ndate: 2025-03-06\n...\n": "title: Another\ndate: 2025-03-06",
            "----\ntitle: Test\ntitle: Test\n----\n": None
        },
        regex_pattern=markup_regex.FRONTMATTER
    )
    def test_frontmatter(self):
        pass

if __name__ == '__main__':
    unittest.main()