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
|
# -*- coding: utf-8 -*-
from __future__ import print_function, absolute_import, unicode_literals
import unittest
import sys
import re
import logging
if sys.version_info.major > 2:
def unicode(string): return string
basestring = str
from pylatexenc.latexencode import (
UnicodeToLatexEncoder, utf8tolatex
)
from pylatexenc import latexencode
class _DummyContextMgr(object):
def __enter__(self, *args, **kwargs):
pass
def __exit__(self, *args, **kwargs):
pass
class ProvideAssertCmds(object):
def assertLogs(self, *args, **kwargs):
logging.getLogger(__name__).warning(
"Can't check if logger generates correct warnings, skipping this check.")
return _DummyContextMgr()
class TestLatexEncode(unittest.TestCase, ProvideAssertCmds):
def __init__(self, *args, **kwargs):
super(TestLatexEncode, self).__init__(*args, **kwargs)
def test_basic_0(self):
u = UnicodeToLatexEncoder()
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"''\\`A votre sant\\'e!'' s'exclama le ma{\\^\\i}tre de maison \\`a 100\\%.")
def test_basic_1(self):
u = UnicodeToLatexEncoder(non_ascii_only=True, replacement_latex_protection='braces-all')
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"\"{\\`A} votre sant{\\'e}!\" s'exclama le ma{\\^\\i}tre de maison {\\`a} 100%.")
def test_basic_2(self):
u = UnicodeToLatexEncoder(replacement_latex_protection='braces-after-macro')
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"''\\`A votre sant\\'e!'' s'exclama le ma\\^\\i{}tre de maison \\`a 100\\%.")
def test_basic_2a(self):
# Issue #44
u = UnicodeToLatexEncoder(replacement_latex_protection='braces-after-macro')
input = "Jabłoński, François, ⟨.⟩, ~"
self.assertEqual(u.unicode_to_latex(input), "Jab\\l{}o\\'nski, Fran\\c{c}ois, \\ensuremath{\\langle}.\\ensuremath{\\rangle}, \\textasciitilde{}")
def test_basic_2b(self):
u = UnicodeToLatexEncoder(replacement_latex_protection='none')
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"''\\`A votre sant\\'e!'' s'exclama le ma\\^\\itre de maison \\`a 100\\%.")
def test_basic_2c(self):
u = UnicodeToLatexEncoder(non_ascii_only=True)
ascii_chars_convert = " \" # $ % & \\ _ { } ~ "
self.assertEqual(u.unicode_to_latex(ascii_chars_convert), ascii_chars_convert)
def test_basic_2d(self):
u = UnicodeToLatexEncoder(non_ascii_only=False)
ascii_chars_convert = " \" # $ % & \\ _ { } ~ "
self.assertEqual(u.unicode_to_latex(ascii_chars_convert),
" '' \\# \\$ \\% \\& {\\textbackslash} \\_ \\{ \\} {\\textasciitilde} ")
def test_basic_callable_replacement_latex_protection(self):
u = UnicodeToLatexEncoder(replacement_latex_protection=lambda s: '{***{'+s+'}***}')
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"{***{''}***}{***{\\`A}***} votre sant{***{\\'e}***}!{***{''}***} s'exclama le ma{***{\\^\\i}***}tre de maison {***{\\`a}***} 100{***{\\%}***}.")
def test_basic_3(self):
test_unknown_chars = "A unicode character: \N{THAI CHARACTER THO THONG}"
# generates warnings -- that's good
with self.assertLogs(logger='pylatexenc.latexencode', level='WARNING') as cm:
u = UnicodeToLatexEncoder(unknown_char_policy='keep')
self.assertEqual(u.unicode_to_latex(test_unknown_chars), test_unknown_chars) # unchanged
def test_basic_3b(self):
test_unknown_chars = "A unicode character: \N{THAI CHARACTER THO THONG}"
# generates warnings -- that's good
with self.assertLogs(logger='pylatexenc.latexencode', level='WARNING') as cm:
u = UnicodeToLatexEncoder(unknown_char_policy='replace')
self.assertEqual(u.unicode_to_latex(test_unknown_chars),
"A unicode character: {\\bfseries ?}")
def test_basic_3c(self):
test_unknown_chars = "A unicode character: \N{THAI CHARACTER THO THONG}"
u = UnicodeToLatexEncoder(unknown_char_policy='unihex', unknown_char_warning=False)
self.assertEqual(u.unicode_to_latex(test_unknown_chars),
"A unicode character: \\ensuremath{\\langle}\\texttt{U+0E18}\\ensuremath{\\rangle}")
def test_rules_00(self):
def acallable(s, pos):
if s[pos] == "\N{LATIN SMALL LETTER E WITH ACUTE}":
return (1, r"{\'{e}}")
if s.startswith('...', pos):
return (3, r"\ldots")
return None
u = UnicodeToLatexEncoder(conversion_rules=[
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_DICT, {
ord("\N{LATIN CAPITAL LETTER A WITH GRAVE}"): r"{{\`{A}}}",
ord("%"): r"\textpercent",
}),
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_REGEX, [
(re.compile('v(otre)'), r'n\1'),
(re.compile("s'exclama", flags=re.I), r"s'exprima"),
(re.compile('\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}'), r"{\^i}"),
]),
] + latexencode.get_builtin_conversion_rules('defaults') + [
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_CALLABLE, acallable),
])
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison ... \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"''{{\\`{A}}} notre sant\\'e!'' s'exprima le ma{\\^i}tre de maison {\\ldots} \\`a 100{\\textpercent}.")
def test_rules_01(self):
def acallable(s, pos):
if s[pos] == "\N{LATIN SMALL LETTER E WITH ACUTE}":
return (1, r"{\'{e}}")
if s.startswith('...', pos):
return (3, r"\ldots")
return None
u = UnicodeToLatexEncoder(conversion_rules=[
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_DICT, {
ord("\N{LATIN CAPITAL LETTER A WITH GRAVE}"): r"{{\`{A}}}",
ord("%"): r"\textpercent",
}),
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_REGEX, [
(re.compile('v(otre)'), r'n\1'),
(re.compile("s'exclama", flags=re.I), r"s'exprima"),
(re.compile('\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}'), r"{\^i}"),
]),
'unicode-xml', # expand built-in rule names
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_CALLABLE, acallable),
])
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison ... \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"\"{{\\`{A}}} notre sant\\'{e}!\" s'exprima le ma{\\^i}tre de maison {\\ldots} \\`{a} 100{\\textpercent}.")
def test_rules_02(self):
# based on test_basic_0()
u = UnicodeToLatexEncoder(conversion_rules=['defaults'])
#u = UnicodeToLatexEncoder()
input = "* \"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama\N{SUPERSCRIPT TWO} le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"* ''\\`A votre sant\\'e!'' s'exclama{\\texttwosuperior} le ma{\\^\\i}tre de maison \\`a 100\\%.")
def test_rules_03(self):
u = UnicodeToLatexEncoder(conversion_rules=['unicode-xml'])
input = "* \"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama\N{SUPERSCRIPT TWO} le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(u.unicode_to_latex(input),
"{\\ast} \"\\`{A} votre sant\\'{e}!\" s{\\textquotesingle}exclama{^2} le ma\\^{\\i}tre de maison \\`{a} 100\\%.")
def test_issue_no21(self):
# test for https://github.com/phfaist/pylatexenc/issues/21
def capitalize_acronyms(s, pos):
if s[pos] in ('{', '}'):
# preserve existing braces
return (1, s[pos])
m = re.compile(r'\b[A-Z]{2,}\w*\b').match(s, pos)
if m is None:
return None
return (m.end()-m.start(), "{" + m.group() + "}")
u = UnicodeToLatexEncoder(
conversion_rules=[
latexencode.UnicodeToLatexConversionRule(latexencode.RULE_CALLABLE, capitalize_acronyms),
] + latexencode.get_builtin_conversion_rules('defaults')
)
input = "Title with {Some} ABC acronyms LIKe this."
self.assertEqual(
u.unicode_to_latex(input),
"Title with {Some} {ABC} acronyms {LIKe} this."
)
u = UnicodeToLatexEncoder(
conversion_rules=[
latexencode.UnicodeToLatexConversionRule(
latexencode.RULE_REGEX,
[ (re.compile(r'([{}])'), r'\1'), # keep existing braces
(re.compile(r'\b([A-Z]{2,}\w*)\b'), r'{\1}'), ]
),
] + latexencode.get_builtin_conversion_rules('defaults')
)
input = "Title with {Some} ABC acronyms LIKe this."
self.assertEqual(
u.unicode_to_latex(input),
"Title with {Some} {ABC} acronyms {LIKe} this."
)
def test_latex_string_class(self):
class LatexChunkList:
def __init__(self):
self.chunks = []
def __iadd__(self, s):
self.chunks.append(s)
return self
u = UnicodeToLatexEncoder(latex_string_class=LatexChunkList,
replacement_latex_protection='none')
result = u.unicode_to_latex("A é → α")
# result is an object of custom type LatexChunkList
self.assertEqual(
result.chunks,
['A', ' ', r'\'e', ' ', r'\textrightarrow', ' ', r'\ensuremath{\alpha}']
)
class TestPartialLatexEncode(unittest.TestCase, ProvideAssertCmds):
def test_simple_cases(self):
self.assertEqual(
latexencode.PartialLatexToLatexEncoder()
.unicode_to_latex(
r"Check ~ \that{macros are fully & 100% \textbf{pr{\'e}s\`ervées}}."
)
,
r"Check {\textasciitilde} \that{macros are fully \& 100\% \textbf{pr{\'e}s\`erv\'ees}}."
)
self.assertEqual(
latexencode.PartialLatexToLatexEncoder()
.unicode_to_latex(
r"{JILA} {SrI} optical lattice clock with uncertainty of $2.0 \times 10^{-18}$"
)
,
r"{JILA} {SrI} optical lattice clock with uncertainty of $2.0 \times 10^{-18}$"
)
def test_custom_conversion_rules(self):
u = latexencode.PartialLatexToLatexEncoder(
conversion_rules=[
latexencode.UnicodeToLatexConversionRule(
latexencode.RULE_REGEX,
[
# this rule should never kick in because braces are
# preserved as keep_latex_chars
(re.compile(r'([{}])'), r'BRACE<\1>'),
# other replacement rules
(re.compile(r'\b([A-Z]{2,}\w*)\b'), r'{\1}'),
]
),
'defaults',
]
)
input = r"Title with {Some} ABC àcr\^onyms LIKe this."
self.assertEqual(
u.unicode_to_latex(input),
r"Title with {Some} {ABC} \`acr\^onyms {LIKe} this."
)
class TestUtf8tolatex(unittest.TestCase, ProvideAssertCmds):
def __init__(self, *args, **kwargs):
super(TestUtf8tolatex, self).__init__(*args, **kwargs)
def test_basic(self):
input = "\"\N{LATIN CAPITAL LETTER A WITH GRAVE} votre sant\N{LATIN SMALL LETTER E WITH ACUTE}!\" s'exclama le ma\N{LATIN SMALL LETTER I WITH CIRCUMFLEX}tre de maison \N{LATIN SMALL LETTER A WITH GRAVE} 100%."
self.assertEqual(utf8tolatex(input),
"''{\\`A} votre sant{\\'e}!'' s'exclama le ma{\\^\\i}tre de maison {\\`a} 100{\\%}.")
self.assertEqual(utf8tolatex(input, non_ascii_only=True),
"\"{\\`A} votre sant{\\'e}!\" s'exclama le ma{\\^\\i}tre de maison {\\`a} 100%.")
# TODO: in the future, be clever and avoid breaking macros like this ("\itre"):
self.assertEqual(utf8tolatex(input, brackets=False),
"''\\`A votre sant\\'e!'' s'exclama le ma\\^\\itre de maison \\`a 100\\%.")
ascii_chars_convert = " \" # $ % & \\ _ { } ~ "
self.assertEqual(utf8tolatex(ascii_chars_convert, non_ascii_only=True),
ascii_chars_convert)
self.assertEqual(utf8tolatex(ascii_chars_convert, non_ascii_only=False),
" '' {\\#} {\\$} {\\%} {\\&} {\\textbackslash} {\\_} {\\{} {\\}} {\\textasciitilde} ")
test_bad_chars = "A unicode character: \N{THAI CHARACTER THO THONG}"
# generates warnings -- that's good
with self.assertLogs(logger='pylatexenc.latexencode', level='WARNING') as cm:
self.assertEqual(utf8tolatex(test_bad_chars, substitute_bad_chars=False),
test_bad_chars) # unchanged
with self.assertLogs(logger='pylatexenc.latexencode', level='WARNING') as cm:
self.assertEqual(utf8tolatex(test_bad_chars, substitute_bad_chars=True),
"A unicode character: {\\bfseries ?}")
if __name__ == '__main__':
logging.basicConfig(level=logging.DEBUG)
unittest.main()
#
|
