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
|
# -*- coding: utf-8 -*-
"""
Pygments basic API tests
~~~~~~~~~~~~~~~~~~~~~~~~
:copyright: Copyright 2006-2009 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import os
import unittest
import random
from pygments import lexers, formatters, filters, format
from pygments.token import _TokenType, Text
from pygments.lexer import RegexLexer
from pygments.formatters.img import FontNotFound
from pygments.util import BytesIO, StringIO, bytes, b
import support
TESTFILE, TESTDIR = support.location(__file__)
test_content = [chr(i) for i in xrange(33, 128)] * 5
random.shuffle(test_content)
test_content = ''.join(test_content) + '\n'
class LexersTest(unittest.TestCase):
def test_import_all(self):
# instantiate every lexer, to see if the token type defs are correct
for x in lexers.LEXERS.keys():
c = getattr(lexers, x)()
def test_lexer_classes(self):
a = self.assert_
ae = self.assertEquals
# test that every lexer class has the correct public API
for lexer in lexers._iter_lexerclasses():
a(type(lexer.name) is str)
for attr in 'aliases', 'filenames', 'alias_filenames', 'mimetypes':
a(hasattr(lexer, attr))
a(type(getattr(lexer, attr)) is list, "%s: %s attribute wrong" %
(lexer, attr))
result = lexer.analyse_text("abc")
a(isinstance(result, float) and 0.0 <= result <= 1.0)
inst = lexer(opt1="val1", opt2="val2")
if issubclass(lexer, RegexLexer):
if not hasattr(lexer, '_tokens'):
# if there's no "_tokens", the lexer has to be one with
# multiple tokendef variants
a(lexer.token_variants)
for variant in lexer.tokens:
a('root' in lexer.tokens[variant])
else:
a('root' in lexer._tokens, '%s has no root state' % lexer)
tokens = list(inst.get_tokens(test_content))
txt = ""
for token in tokens:
a(isinstance(token, tuple))
a(isinstance(token[0], _TokenType))
if isinstance(token[1], str):
print repr(token[1])
a(isinstance(token[1], unicode))
txt += token[1]
ae(txt, test_content, "%s lexer roundtrip failed: %r != %r" %
(lexer.name, test_content, txt))
def test_get_lexers(self):
a = self.assert_
ae = self.assertEquals
# test that the lexers functions work
for func, args in [(lexers.get_lexer_by_name, ("python",)),
(lexers.get_lexer_for_filename, ("test.py",)),
(lexers.get_lexer_for_mimetype, ("text/x-python",)),
(lexers.guess_lexer, ("#!/usr/bin/python -O\nprint",)),
(lexers.guess_lexer_for_filename, ("a.py", "<%= @foo %>"))
]:
x = func(opt="val", *args)
a(isinstance(x, lexers.PythonLexer))
ae(x.options["opt"], "val")
class FiltersTest(unittest.TestCase):
def test_basic(self):
filter_args = {
'whitespace': {'spaces': True, 'tabs': True, 'newlines': True},
'highlight': {'names': ['isinstance', 'lexers', 'x']},
}
for x in filters.FILTERS.keys():
lx = lexers.PythonLexer()
lx.add_filter(x, **filter_args.get(x, {}))
text = open(TESTFILE, 'rb').read().decode('utf-8')
tokens = list(lx.get_tokens(text))
roundtext = ''.join([t[1] for t in tokens])
if x not in ('whitespace', 'keywordcase'):
# these filters change the text
self.assertEquals(roundtext, text,
"lexer roundtrip with %s filter failed" % x)
def test_raiseonerror(self):
lx = lexers.PythonLexer()
lx.add_filter('raiseonerror', excclass=RuntimeError)
self.assertRaises(RuntimeError, list, lx.get_tokens('$'))
def test_whitespace(self):
lx = lexers.PythonLexer()
lx.add_filter('whitespace', spaces='%')
text = open(TESTFILE, 'rb').read().decode('utf-8')
lxtext = ''.join([t[1] for t in list(lx.get_tokens(text))])
self.failIf(' ' in lxtext)
def test_keywordcase(self):
lx = lexers.PythonLexer()
lx.add_filter('keywordcase', case='capitalize')
text = open(TESTFILE, 'rb').read().decode('utf-8')
lxtext = ''.join([t[1] for t in list(lx.get_tokens(text))])
self.assert_('Def' in lxtext and 'Class' in lxtext)
def test_codetag(self):
lx = lexers.PythonLexer()
lx.add_filter('codetagify')
text = u'# BUG: text'
tokens = list(lx.get_tokens(text))
self.assertEquals('# ', tokens[0][1])
self.assertEquals('BUG', tokens[1][1])
def test_codetag_boundary(self):
# http://dev.pocoo.org/projects/pygments/ticket/368
lx = lexers.PythonLexer()
lx.add_filter('codetagify')
text = u'# DEBUG: text'
tokens = list(lx.get_tokens(text))
self.assertEquals('# DEBUG: text', tokens[0][1])
class FormattersTest(unittest.TestCase):
def test_public_api(self):
a = self.assert_
ae = self.assertEquals
ts = list(lexers.PythonLexer().get_tokens("def f(): pass"))
out = StringIO()
# test that every formatter class has the correct public API
for formatter, info in formatters.FORMATTERS.iteritems():
a(len(info) == 4)
a(info[0], "missing formatter name") # name
a(info[1], "missing formatter aliases") # aliases
a(info[3], "missing formatter docstring") # doc
if formatter.name == 'Raw tokens':
# will not work with Unicode output file
continue
try:
inst = formatter(opt1="val1")
except (ImportError, FontNotFound):
continue
try:
inst.get_style_defs()
except NotImplementedError:
# may be raised by formatters for which it doesn't make sense
pass
inst.format(ts, out)
def test_encodings(self):
from pygments.formatters import HtmlFormatter
# unicode output
fmt = HtmlFormatter()
tokens = [(Text, u"ä")]
out = format(tokens, fmt)
self.assert_(type(out) is unicode)
self.assert_(u"ä" in out)
# encoding option
fmt = HtmlFormatter(encoding="latin1")
tokens = [(Text, u"ä")]
self.assert_(u"ä".encode("latin1") in format(tokens, fmt))
# encoding and outencoding option
fmt = HtmlFormatter(encoding="latin1", outencoding="utf8")
tokens = [(Text, u"ä")]
self.assert_(u"ä".encode("utf8") in format(tokens, fmt))
def test_styles(self):
from pygments.formatters import HtmlFormatter
fmt = HtmlFormatter(style="pastie")
def test_unicode_handling(self):
# test that the formatter supports encoding and Unicode
tokens = list(lexers.PythonLexer(encoding='utf-8').
get_tokens("def f(): 'ä'"))
for formatter, info in formatters.FORMATTERS.iteritems():
try:
inst = formatter(encoding=None)
except (ImportError, FontNotFound):
# some dependency or font not installed
continue
if formatter.name != 'Raw tokens':
out = format(tokens, inst)
if formatter.unicodeoutput:
self.assert_(type(out) is unicode)
inst = formatter(encoding='utf-8')
out = format(tokens, inst)
self.assert_(type(out) is bytes, '%s: %r' % (formatter, out))
# Cannot test for encoding, since formatters may have to escape
# non-ASCII characters.
else:
inst = formatter()
out = format(tokens, inst)
self.assert_(type(out) is bytes, '%s: %r' % (formatter, out))
def test_get_formatters(self):
a = self.assert_
ae = self.assertEquals
# test that the formatters functions work
x = formatters.get_formatter_by_name("html", opt="val")
a(isinstance(x, formatters.HtmlFormatter))
ae(x.options["opt"], "val")
x = formatters.get_formatter_for_filename("a.html", opt="val")
a(isinstance(x, formatters.HtmlFormatter))
ae(x.options["opt"], "val")
|
