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
|
#! /usr/bin/env python3
# $Id: test_east_asian_text.py 9425 2023-06-30 14:56:47Z milde $
# Author: David Goodger <goodger@python.org>
# Copyright: This module has been placed in the public domain.
"""
Tests for East Asian text with double-width characters.
"""
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.rst import Parser
from docutils.utils import new_document
class ParserTestCase(unittest.TestCase):
def test_parser(self):
parser = Parser()
settings = get_default_settings(Parser)
settings.warning_stream = ''
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(case_expected, output)
totest = {}
totest['double_width'] = [
["""\
タイトル1
=========
タイトル2
========
""",
"""\
<document source="test data">
<section ids="section-1" names="タイトル1">
<title>
タイトル1
<section ids="section-2" names="タイトル2">
<title>
タイトル2
<system_message level="2" line="5" source="test data" type="WARNING">
<paragraph>
Title underline too short.
<literal_block xml:space="preserve">
タイトル2
========
"""],
["""
+-----------------------+
| * ヒョウ:ダイ1ギョウ |
| * ダイ2ギョウ |
+-----------------------+
| \\* ダイ1ギョウ |
| * ダイ2ギョウ |
+-----------------------+
""",
"""\
<document source="test data">
<table>
<tgroup cols="1">
<colspec colwidth="23">
<tbody>
<row>
<entry>
<bullet_list bullet="*">
<list_item>
<paragraph>
ヒョウ:ダイ1ギョウ
<list_item>
<paragraph>
ダイ2ギョウ
<row>
<entry>
<paragraph>
* ダイ1ギョウ
* ダイ2ギョウ
"""],
["""\
Complex spanning pattern (no edge knows all rows/cols):
+--------+---------------------+
| 北西・ | 北・北東セル |
| 西セル +--------------+------+
| | 真ん中のセル | 東・ |
+--------+--------------+ 南東 |
| 南西・南セル | セル |
+-----------------------+------+
""",
"""\
<document source="test data">
<paragraph>
Complex spanning pattern (no edge knows all rows/cols):
<table>
<tgroup cols="3">
<colspec colwidth="8">
<colspec colwidth="14">
<colspec colwidth="6">
<tbody>
<row>
<entry morerows="1">
<paragraph>
北西・
西セル
<entry morecols="1">
<paragraph>
北・北東セル
<row>
<entry>
<paragraph>
真ん中のセル
<entry morerows="1">
<paragraph>
東・
南東
セル
<row>
<entry morecols="1">
<paragraph>
南西・南セル
"""],
["""\
========= =========
ダイ1ラン ダイ2ラン
========= =========
======== =========
ダイ1ラン ダイ2ラン
======== =========
""",
"""\
<document source="test data">
<table>
<tgroup cols="2">
<colspec colwidth="9">
<colspec colwidth="9">
<tbody>
<row>
<entry>
<paragraph>
ダイ1ラン
<entry>
<paragraph>
ダイ2ラン
<system_message level="3" line="6" source="test data" type="ERROR">
<paragraph>
Malformed table.
Text in column margin in table line 2.
<literal_block xml:space="preserve">
======== =========
ダイ1ラン ダイ2ラン
======== =========
"""],
["""\
Some ambiguous-width characters:
= ===================================
© copyright sign
® registered sign
« left pointing guillemet
» right pointing guillemet
– en-dash
— em-dash
‘ single turned comma quotation mark
’ single comma quotation mark
‚ low single comma quotation mark
“ double turned comma quotation mark
” double comma quotation mark
„ low double comma quotation mark
† dagger
‡ double dagger
… ellipsis
™ trade mark sign
⇔ left-right double arrow
= ===================================
""",
b"""\
<document source="test data">
<paragraph>
Some ambiguous-width characters:
<table>
<tgroup cols="2">
<colspec colwidth="1">
<colspec colwidth="35">
<tbody>
<row>
<entry>
<paragraph>
\xa9
<entry>
<paragraph>
copyright sign
<row>
<entry>
<paragraph>
\xae
<entry>
<paragraph>
registered sign
<row>
<entry>
<paragraph>
\xab
<entry>
<paragraph>
left pointing guillemet
<row>
<entry>
<paragraph>
\xbb
<entry>
<paragraph>
right pointing guillemet
<row>
<entry>
<paragraph>
\\u2013
<entry>
<paragraph>
en-dash
<row>
<entry>
<paragraph>
\\u2014
<entry>
<paragraph>
em-dash
<row>
<entry>
<paragraph>
\\u2018
<entry>
<paragraph>
single turned comma quotation mark
<row>
<entry>
<paragraph>
\\u2019
<entry>
<paragraph>
single comma quotation mark
<row>
<entry>
<paragraph>
\\u201a
<entry>
<paragraph>
low single comma quotation mark
<row>
<entry>
<paragraph>
\\u201c
<entry>
<paragraph>
double turned comma quotation mark
<row>
<entry>
<paragraph>
\\u201d
<entry>
<paragraph>
double comma quotation mark
<row>
<entry>
<paragraph>
\\u201e
<entry>
<paragraph>
low double comma quotation mark
<row>
<entry>
<paragraph>
\\u2020
<entry>
<paragraph>
dagger
<row>
<entry>
<paragraph>
\\u2021
<entry>
<paragraph>
double dagger
<row>
<entry>
<paragraph>
\\u2026
<entry>
<paragraph>
ellipsis
<row>
<entry>
<paragraph>
\\u2122
<entry>
<paragraph>
trade mark sign
<row>
<entry>
<paragraph>
\\u21d4
<entry>
<paragraph>
left-right double arrow
""".decode('raw_unicode_escape')],
]
'''
["""\
""",
"""\
"""],
'''
if __name__ == '__main__':
unittest.main()
|
