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
|
# coding: utf-8
"""
Tests for the tokenizer
-----------------------
:copyright: (c) 2012 by Simon Sapin.
:license: BSD, see LICENSE for more details.
"""
from __future__ import unicode_literals
import os
import sys
import pytest
from tinycss.tokenizer import (
cython_tokenize_flat, python_tokenize_flat, regroup)
def test_speedups():
is_pypy = hasattr(sys, 'pypy_translation_info')
env_skip_tests = os.environ.get('TINYCSS_SKIP_SPEEDUPS_TESTS')
# pragma: no cover
if is_pypy or env_skip_tests:
return
assert cython_tokenize_flat is not None, (
'Cython speedups are not installed, related tests will '
'be skipped. Set the TINYCSS_SKIP_SPEEDUPS_TESTS environment '
'variable if this is expected.')
@pytest.mark.parametrize(('tokenize', 'css_source', 'expected_tokens'), [
(tokenize,) + test_data
for tokenize in (python_tokenize_flat, cython_tokenize_flat)
for test_data in [
('', []),
('red -->', [('IDENT', 'red'), ('S', ' '), ('CDC', '-->')]),
# Longest match rule: no CDC
('red-->', [('IDENT', 'red--'), ('DELIM', '>')]),
(r'p[example="foo(int x) { this.x = x;}"]', [
('IDENT', 'p'),
('[', '['),
('IDENT', 'example'),
('DELIM', '='),
('STRING', 'foo(int x) { this.x = x;}'),
(']', ']')]),
# Numbers are parsed
('42 .5 -4pX 1.25em 30%', [
('INTEGER', 42), ('S', ' '),
('NUMBER', .5), ('S', ' '),
# units are normalized to lower-case:
('DIMENSION', -4, 'px'), ('S', ' '),
('DIMENSION', 1.25, 'em'), ('S', ' '),
('PERCENTAGE', 30, '%')]),
# URLs are extracted
('url(foo.png)', [('URI', 'foo.png')]),
('url("foo.png")', [('URI', 'foo.png')]),
# Escaping
(r'/* Comment with a \ backslash */', [
('COMMENT', '/* Comment with a \ backslash */')]), # Unchanged
# backslash followed by a newline in a string: ignored
('"Lorem\\\nIpsum"', [('STRING', 'LoremIpsum')]),
# backslash followed by a newline outside a string: stands for itself
('Lorem\\\nIpsum', [
('IDENT', 'Lorem'), ('DELIM', '\\'),
('S', '\n'), ('IDENT', 'Ipsum')]),
# Cancel the meaning of special characters
(r'"Lore\m Ipsum"', [('STRING', 'Lorem Ipsum')]), # or not specal
(r'"Lorem \49psum"', [('STRING', 'Lorem Ipsum')]),
(r'"Lorem \49 psum"', [('STRING', 'Lorem Ipsum')]),
(r'"Lorem\"Ipsum"', [('STRING', 'Lorem"Ipsum')]),
(r'"Lorem\\Ipsum"', [('STRING', r'Lorem\Ipsum')]),
(r'"Lorem\5c Ipsum"', [('STRING', r'Lorem\Ipsum')]),
(r'Lorem\+Ipsum', [('IDENT', 'Lorem+Ipsum')]),
(r'Lorem+Ipsum', [
('IDENT', 'Lorem'), ('DELIM', '+'), ('IDENT', 'Ipsum')]),
(r'url(foo\).png)', [('URI', 'foo).png')]),
# Unicode and backslash escaping
('\\26 B', [('IDENT', '&B')]),
('\\&B', [('IDENT', '&B')]),
('@\\26\tB', [('ATKEYWORD', '@&B')]),
('@\\&B', [('ATKEYWORD', '@&B')]),
('#\\26\nB', [('HASH', '#&B')]),
('#\\&B', [('HASH', '#&B')]),
('\\26\r\nB(', [('FUNCTION', '&B(')]),
('\\&B(', [('FUNCTION', '&B(')]),
(r'12.5\000026B', [('DIMENSION', 12.5, '&b')]),
(r'12.5\0000263B', [('DIMENSION', 12.5, '&3b')]), # max 6 digits
(r'12.5\&B', [('DIMENSION', 12.5, '&b')]),
(r'"\26 B"', [('STRING', '&B')]),
(r"'\000026B'", [('STRING', '&B')]),
(r'"\&B"', [('STRING', '&B')]),
(r'url("\26 B")', [('URI', '&B')]),
(r'url(\26 B)', [('URI', '&B')]),
(r'url("\&B")', [('URI', '&B')]),
(r'url(\&B)', [('URI', '&B')]),
(r'Lorem\110000Ipsum', [('IDENT', 'Lorem\uFFFDIpsum')]),
# Bad strings
# String ends at EOF without closing: no error, parsed
('"Lorem\\26Ipsum', [('STRING', 'Lorem&Ipsum')]),
# Unescaped newline: ends the string, error, unparsed
('"Lorem\\26Ipsum\n', [
('BAD_STRING', r'"Lorem\26Ipsum'), ('S', '\n')]),
# Tokenization restarts after the newline, so the second " starts
# a new string (which ends at EOF without errors, as above.)
('"Lorem\\26Ipsum\ndolor" sit', [
('BAD_STRING', r'"Lorem\26Ipsum'), ('S', '\n'),
('IDENT', 'dolor'), ('STRING', ' sit')]),
]])
def test_tokens(tokenize, css_source, expected_tokens):
if tokenize is None: # pragma: no cover
pytest.skip('Speedups not available')
sources = [css_source]
if sys.version_info[0] < 3:
# On Python 2.x, ASCII-only bytestrings can be used
# where Unicode is expected.
sources.append(css_source.encode('ascii'))
for css_source in sources:
tokens = tokenize(css_source, ignore_comments=False)
result = [
(token.type, token.value) + (
() if token.unit is None else (token.unit,))
for token in tokens
]
assert result == expected_tokens
@pytest.mark.parametrize('tokenize', [
python_tokenize_flat, cython_tokenize_flat])
def test_positions(tokenize):
"""Test the reported line/column position of each token."""
if tokenize is None: # pragma: no cover
pytest.skip('Speedups not available')
css = '/* Lorem\nipsum */\fa {\n color: red;\tcontent: "dolor\\\fsit" }'
tokens = tokenize(css, ignore_comments=False)
result = [(token.type, token.line, token.column) for token in tokens]
assert result == [
('COMMENT', 1, 1), ('S', 2, 9),
('IDENT', 3, 1), ('S', 3, 2), ('{', 3, 3),
('S', 3, 4), ('IDENT', 4, 5), (':', 4, 10),
('S', 4, 11), ('IDENT', 4, 12), (';', 4, 15), ('S', 4, 16),
('IDENT', 4, 17), (':', 4, 24), ('S', 4, 25), ('STRING', 4, 26),
('S', 5, 5), ('}', 5, 6)]
@pytest.mark.parametrize(('tokenize', 'css_source', 'expected_tokens'), [
(tokenize,) + test_data
for tokenize in (python_tokenize_flat, cython_tokenize_flat)
for test_data in [
('', []),
(r'Lorem\26 "i\psum"4px', [
('IDENT', 'Lorem&'), ('STRING', 'ipsum'), ('DIMENSION', 4)]),
('not([[lorem]]{ipsum (42)})', [
('FUNCTION', 'not', [
('[', [
('[', [
('IDENT', 'lorem'),
]),
]),
('{', [
('IDENT', 'ipsum'),
('S', ' '),
('(', [
('INTEGER', 42),
])
])
])]),
# Close everything at EOF, no error
('a[b{"d', [
('IDENT', 'a'),
('[', [
('IDENT', 'b'),
('{', [
('STRING', 'd'),
]),
]),
]),
# Any remaining ), ] or } token is a nesting error
('a[b{d]e}', [
('IDENT', 'a'),
('[', [
('IDENT', 'b'),
('{', [
('IDENT', 'd'),
(']', ']'), # The error is visible here
('IDENT', 'e'),
]),
]),
]),
# ref:
('a[b{d}e]', [
('IDENT', 'a'),
('[', [
('IDENT', 'b'),
('{', [
('IDENT', 'd'),
]),
('IDENT', 'e'),
]),
]),
]])
def test_token_grouping(tokenize, css_source, expected_tokens):
if tokenize is None: # pragma: no cover
pytest.skip('Speedups not available')
tokens = regroup(tokenize(css_source, ignore_comments=False))
result = list(jsonify(tokens))
assert result == expected_tokens
def jsonify(tokens):
"""Turn tokens into "JSON-compatible" data structures."""
for token in tokens:
if token.type == 'FUNCTION':
yield (token.type, token.function_name,
list(jsonify(token.content)))
elif token.is_container:
yield token.type, list(jsonify(token.content))
else:
yield token.type, token.value
@pytest.mark.parametrize(('tokenize', 'ignore_comments', 'expected_tokens'), [
(tokenize,) + test_data
for tokenize in (python_tokenize_flat, cython_tokenize_flat)
for test_data in [
(False, [
('COMMENT', '/* lorem */'),
('S', ' '),
('IDENT', 'ipsum'),
('[', [
('IDENT', 'dolor'),
('COMMENT', '/* sit */'),
]),
('BAD_COMMENT', '/* amet')
]),
(True, [
('S', ' '),
('IDENT', 'ipsum'),
('[', [
('IDENT', 'dolor'),
]),
]),
]])
def test_comments(tokenize, ignore_comments, expected_tokens):
if tokenize is None: # pragma: no cover
pytest.skip('Speedups not available')
css_source = '/* lorem */ ipsum[dolor/* sit */]/* amet'
tokens = regroup(tokenize(css_source, ignore_comments))
result = list(jsonify(tokens))
assert result == expected_tokens
@pytest.mark.parametrize(('tokenize', 'css_source'), [
(tokenize, test_data)
for tokenize in (python_tokenize_flat, cython_tokenize_flat)
for test_data in [
r'p[example="foo(int x) { this.x = x;}"]',
'"Lorem\\26Ipsum\ndolor" sit',
'/* Lorem\nipsum */\fa {\n color: red;\tcontent: "dolor\\\fsit" }',
'not([[lorem]]{ipsum (42)})',
'a[b{d]e}',
'a[b{"d',
]])
def test_token_serialize_css(tokenize, css_source):
if tokenize is None: # pragma: no cover
pytest.skip('Speedups not available')
for _regroup in [regroup, lambda x: x]:
tokens = _regroup(tokenize(css_source, ignore_comments=False))
result = ''.join(token.as_css() for token in tokens)
assert result == css_source
@pytest.mark.parametrize(('tokenize', 'css_source'), [
(tokenize, test_data)
for tokenize in (python_tokenize_flat, cython_tokenize_flat)
for test_data in [
'(8, foo, [z])', '[8, foo, (z)]', '{8, foo, [z]}', 'func(8, foo, [z])'
]
])
def test_token_api(tokenize, css_source):
if tokenize is None: # pragma: no cover
pytest.skip('Speedups not available')
tokens = list(regroup(tokenize(css_source)))
assert len(tokens) == 1
token = tokens[0]
expected_len = 7 # 2 spaces, 2 commas, 3 others.
assert len(token.content) == expected_len
|
