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
|
#!/usr/bin/env python3
# :Copyright: © 2020 Günter Milde.
# :License: Released under the terms of the `2-Clause BSD license`_, in short:
#
# Copying and distribution of this file, with or without modification,
# are permitted in any medium without royalty provided the copyright
# notice and this notice are preserved.
# This file is offered as-is, without any warranty.
#
# .. _2-Clause BSD license: https://opensource.org/licenses/BSD-2-Clause
"""
Test for section headings in CommonMark parsers.
Cf. the `CommonMark Specification <https://spec.commonmark.org/>`__
"""
from pathlib import Path
import sys
import unittest
if __name__ == '__main__':
# prepend the "docutils root" to the Python library path
# so we import the local `docutils` package.
sys.path.insert(0, str(Path(__file__).resolve().parents[3]))
from docutils.frontend import get_default_settings
from docutils.parsers.recommonmark_wrapper import Parser
from docutils.utils import new_document
class RecommonmarkParserTestCase(unittest.TestCase):
def test_parser(self):
parser = Parser()
settings = get_default_settings(Parser)
for name, cases in totest.items():
for casenum, (case_input, case_expected) in enumerate(cases):
with self.subTest(id=f'totest[{name!r}][{casenum}]'):
document = new_document('test data', settings.copy())
parser.parse(case_input, document)
output = document.pformat()
self.assertEqual(output, case_expected)
totest = {}
totest['section_headers'] = [
["""\
The Title
=========
Paragraph.
""",
r"""<document source="test data">
<section ids="the-title" names="the\ title">
<title>
The Title
<paragraph>
Paragraph.
"""],
["""\
Another Section Title
=====================
Paragraph (no blank line required).
""",
r"""<document source="test data">
<section ids="another-section-title" names="another\ section\ title">
<title>
Another Section Title
<paragraph>
Paragraph (no blank line required).
"""],
["""\
Paragraph.
Title
=====
Paragraph.
""",
"""\
<document source="test data">
<paragraph>
Paragraph.
<section ids="title" names="title">
<title>
Title
<paragraph>
Paragraph.
"""],
# ["""\
# Test unexpected section titles.
#
# * Title
# =====
#
# Paragraph.
# """,
# """\
# <document source="test data">
# <paragraph>
# Test unexpected section titles.
# <system_message level="3" source="test data" type="ERROR">
# <paragraph>
# Parsing with "recommonmark" returned the error:
# 'NoneType' object has no attribute 'note_implicit_target'
# """],
["""\
Title
==
A short underline is no problem in CommonMark
""",
"""\
<document source="test data">
<section ids="title" names="title">
<title>
Title
<paragraph>
A short underline is no problem in CommonMark
"""],
["""\
Test return to existing, highest-level section (Title 3).
Title 1
=======
Paragraph 1.
Title 2
-------
Paragraph 2.
Title 3
=======
Paragraph 3.
Title 4
-------
Paragraph 4.
""",
r"""<document source="test data">
<paragraph>
Test return to existing, highest-level section (Title 3).
<section ids="title-1" names="title\ 1">
<title>
Title 1
<paragraph>
Paragraph 1.
<section ids="title-2" names="title\ 2">
<title>
Title 2
<paragraph>
Paragraph 2.
<section ids="title-3" names="title\ 3">
<title>
Title 3
<paragraph>
Paragraph 3.
<section ids="title-4" names="title\ 4">
<title>
Title 4
<paragraph>
Paragraph 4.
"""],
["""\
Test bad subsection order.
## Title 1
## Title 2
# Title 3
#### Title 4
### Title 5
""",
r"""<document source="test data">
<paragraph>
Test bad subsection order.
<section ids="title-1" names="title\ 1">
<title>
Title 1
<section ids="title-2" names="title\ 2">
<title>
Title 2
<section ids="title-3" names="title\ 3">
<title>
Title 3
<section ids="title-4" names="title\ 4">
<title>
Title 4
<section ids="title-5" names="title\ 5">
<title>
Title 5
"""],
["""\
Title containing *inline* ``markup``
====================================
Paragraph.
""",
"""\
<document source="test data">
<section ids="title-containing-inline-markup" names="title\\ containing\\ inline\\ markup">
<title>
Title containing \n\
<emphasis>
inline
\n\
<literal classes="code">
markup
<paragraph>
Paragraph.
"""],
["""\
1. Not a numbered title but an enumerated list
==============================================
Paragraph.
""",
"""\
<document source="test data">
<enumerated_list>
<list_item>
<paragraph>
Not a numbered title but an enumerated list
==============================================
<paragraph>
Paragraph.
"""],
["""\
ABC
===
Short title.
""",
"""\
<document source="test data">
<section ids="abc" names="abc">
<title>
ABC
<paragraph>
Short title.
"""],
["""\
Empty Section
=============
""",
"""\
<document source="test data">
<section ids="empty-section" names="empty\\ section">
<title>
Empty Section
"""],
]
if __name__ == '__main__':
unittest.main()
|
