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
|
#!/usr/bin/env python3
# :Copyright: © 2024 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
"""Tests for `docutils.parsers.docutils_xml.Parser.parse()`."""
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 import docutils_xml
from docutils.utils import new_document
parser = docutils_xml.Parser()
class XmlParserTestCase(unittest.TestCase):
def test_parse(self):
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)
parser.parse(case_input, document)
output = document.pformat()
self.assertEqual(case_expected, output)
totest = {}
totest['simple'] = [
["""\
<document>
<paragraph>A paragraph.</paragraph>
</document>
""",
"""\
<document source="test data">
<paragraph>
A paragraph.
"""],
["""\
<document source="test sample">
<paragraph>A paragraph
with two lines.</paragraph>
</document>
""",
"""\
<document source="test sample">
<paragraph>
A paragraph
with two lines.
"""],
["""\
<document>
<paragraph>Paragraph 1.</paragraph>
<paragraph>Paragraph 2.</paragraph>
</document>
""",
"""\
<document source="test data">
<paragraph>
Paragraph 1.
<paragraph>
Paragraph 2.
"""],
["""\
<paragraph>Sub-trees are parsed, too.
Line breaks are preserved.</paragraph>
""",
"""\
<document source="test data">
<paragraph>
Sub-trees are parsed, too.
Line breaks are preserved.
"""],
]
totest['inline'] = [
["""\
<paragraph><emphasis>emphatically</emphasis></paragraph>
""",
"""\
<document source="test data">
<paragraph>
<emphasis>
emphatically
"""],
["""\
<paragraph><strong>strong</strong> week</paragraph>
""",
"""\
<document source="test data">
<paragraph>
<strong>
strong
week
"""],
["""\
<document source="test data">
<literal_block xml:space="preserve"> Inline element
with <strong> space at start,
in the middle</strong>
and after end.</literal_block>
</document>
""",
"""\
<document source="test data">
<literal_block xml:space="preserve">
Inline element
with \n\
<strong>
space at start,
in the middle
\n\
and after end.
"""],
]
totest['attributes'] = [
["""\
<paragraph classes="top secret">classified text</paragraph>
""",
"""\
<document source="test data">
<paragraph classes="top secret">
classified text
"""],
[r"""
<paragraph ids="ref-2 ref-1" names="ref\ 2 ref\ 1">target paragraph</paragraph>
""",
r"""<document source="test data">
<paragraph ids="ref-2 ref-1" names="ref\ 2 ref\ 1">
target paragraph
"""],
]
totest['invalid'] = [
["""\
<document>
<tip>
spurious text
<paragraph>A paragraph.</paragraph>
</tip>
</document>
""",
"""\
<document source="test data">
<tip>
spurious text
<paragraph>
A paragraph.
"""],
["""\
<document>
spurious text
<paragraph>A paragraph.</paragraph>
</document>
""",
"""\
<document source="test data">
spurious text
<paragraph>
A paragraph.
"""],
["""\
<document>
<tip>
<paragraph>A paragraph.</paragraph>
spurious tailing text
</tip>
</document>
""",
"""\
<document source="test data">
<tip>
<paragraph>
A paragraph.
spurious tailing text
"""],
["""\
<document>
<paragraph>A paragraph.</paragraph>
spurious tailing text
</document>
""",
"""\
<document source="test data">
<paragraph>
A paragraph.
spurious tailing text
"""],
["""\
just spurious text
""",
"""\
<document source="test data">
<paragraph>
<problematic>
No XML element found.
"""],
]
if __name__ == '__main__':
unittest.main()
|
