summaryrefslogtreecommitdiff
path: root/tests/test_util.py
blob: aa7b7acb899b3256e82f2151d89c76fea641145f (plain)
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
# -*- coding: utf-8 -*-
"""
    Test suite for the util module
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    :copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re

from pytest import raises

from pygments import util, console


class FakeLexer(object):
    def analyse(text):
        return text
    analyse = util.make_analysator(analyse)


def test_getoptions():
    assert util.get_bool_opt({}, 'a', True) is True
    assert util.get_bool_opt({}, 'a', 1) is True
    assert util.get_bool_opt({}, 'a', 'true') is True
    assert util.get_bool_opt({}, 'a', 'no') is False
    assert raises(util.OptionError, util.get_bool_opt, {}, 'a', [])
    assert raises(util.OptionError, util.get_bool_opt, {}, 'a', 'foo')

    assert util.get_int_opt({}, 'a', 1) == 1
    assert raises(util.OptionError, util.get_int_opt, {}, 'a', [])
    assert raises(util.OptionError, util.get_int_opt, {}, 'a', 'bar')

    assert util.get_list_opt({}, 'a', [1]) == [1]
    assert util.get_list_opt({}, 'a', '1 2') == ['1', '2']
    assert raises(util.OptionError, util.get_list_opt, {}, 'a', 1)

    assert util.get_choice_opt({}, 'a', ['foo', 'bar'], 'bar') == 'bar'
    assert util.get_choice_opt({}, 'a', ['foo', 'bar'], 'Bar', True) == 'bar'
    assert raises(util.OptionError, util.get_choice_opt, {}, 'a',
                  ['foo', 'bar'], 'baz')


def test_docstring_headline():
    def f1():
        """
        docstring headline

        other text
        """
    def f2():
        """
        docstring
        headline

        other text
        """
    def f3():
        pass

    assert util.docstring_headline(f1) == 'docstring headline'
    assert util.docstring_headline(f2) == 'docstring headline'
    assert util.docstring_headline(f3) == ''


def test_analysator_returns_float():
    # If an analysator wrapped by make_analysator returns a floating point
    # number, then that number will be returned by the wrapper.
    assert FakeLexer.analyse('0.5') == 0.5


def test_analysator_returns_boolean():
    # If an analysator wrapped by make_analysator returns a boolean value,
    # then the wrapper will return 1.0 if the boolean was True or 0.0 if
    # it was False.
    assert FakeLexer.analyse(True) == 1.0
    assert FakeLexer.analyse(False) == 0.0


def test_analysator_raises_exception():
    # If an analysator wrapped by make_analysator raises an exception,
    # then the wrapper will return 0.0.
    class ErrorLexer(object):
        def analyse(text):
            raise RuntimeError('something bad happened')
        analyse = util.make_analysator(analyse)
    assert ErrorLexer.analyse('') == 0.0


def test_analysator_value_error():
    # When converting the analysator's return value to a float a
    # ValueError may occur.  If that happens 0.0 is returned instead.
    assert FakeLexer.analyse('bad input') == 0.0


def test_analysator_type_error():
    # When converting the analysator's return value to a float a
    # TypeError may occur.  If that happens 0.0 is returned instead.
    assert FakeLexer.analyse('xxx') == 0.0


def test_shebang_matches():
    assert util.shebang_matches('#!/usr/bin/env python\n', r'python(2\.\d)?')
    assert util.shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?')
    assert util.shebang_matches('#!/usr/bin/startsomethingwith python',
                                r'python(2\.\d)?')
    assert util.shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?')

    assert not util.shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?')
    assert not util.shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?')
    assert not util.shebang_matches('#!', r'python')


def test_doctype_matches():
    assert util.doctype_matches('<!DOCTYPE html> <html>', 'html.*')
    assert not util.doctype_matches(
        '<?xml ?> <DOCTYPE html PUBLIC "a"> <html>', 'html.*')
    assert util.html_doctype_matches(
        '<?xml ?><!DOCTYPE html PUBLIC  "-//W3C//DTD XHTML 1.0 Strict//EN">')


def test_xml():
    assert util.looks_like_xml(
        '<?xml ?><!DOCTYPE html PUBLIC  "-//W3C//DTD XHTML 1.0 Strict//EN">')
    assert util.looks_like_xml('<html xmlns>abc</html>')
    assert not util.looks_like_xml('<html>')


def test_unirange():
    first_non_bmp = u'\U00010000'
    r = re.compile(util.unirange(0x10000, 0x20000))
    m = r.match(first_non_bmp)
    assert m
    assert m.end() == len(first_non_bmp)
    assert not r.match(u'\uffff')
    assert not r.match(u'xxx')
    # Tests that end is inclusive
    r = re.compile(util.unirange(0x10000, 0x10000) + '+')
    # Tests that the plus works for the entire unicode point, if narrow
    # build
    m = r.match(first_non_bmp * 2)
    assert m
    assert m.end() == len(first_non_bmp) * 2


def test_format_lines():
    lst = ['cat', 'dog']
    output = util.format_lines('var', lst)
    d = {}
    exec(output, d)
    assert isinstance(d['var'], tuple)
    assert ('cat', 'dog') == d['var']


def test_duplicates_removed_seq_types():
    # tuple
    x = util.duplicates_removed(('a', 'a', 'b'))
    assert ['a', 'b'] == x
    # list
    x = util.duplicates_removed(['a', 'a', 'b'])
    assert ['a', 'b'] == x
    # iterator
    x = util.duplicates_removed(iter(('a', 'a', 'b')))
    assert ['a', 'b'] == x


def test_duplicates_removed_nonconsecutive():
    # keeps first
    x = util.duplicates_removed(('a', 'b', 'a'))
    assert ['a', 'b'] == x


def test_guess_decode():
    # UTF-8 should be decoded as UTF-8
    s = util.guess_decode(u'\xff'.encode('utf-8'))
    assert s == (u'\xff', 'utf-8')

    # otherwise, it could be latin1 or the locale encoding...
    import locale
    s = util.guess_decode(b'\xff')
    assert s[1] in ('latin1', locale.getpreferredencoding())


def test_guess_decode_from_terminal():
    class Term:
        encoding = 'utf-7'

    s = util.guess_decode_from_terminal(u'\xff'.encode('utf-7'), Term)
    assert s == (u'\xff', 'utf-7')

    s = util.guess_decode_from_terminal(u'\xff'.encode('utf-8'), Term)
    assert s == (u'\xff', 'utf-8')


def test_add_metaclass():
    class Meta(type):
        pass

    @util.add_metaclass(Meta)
    class Cls:
        pass

    assert type(Cls) is Meta


def test_console_ansiformat():
    f = console.ansiformat
    c = console.codes
    all_attrs = f('+*_blue_*+', 'text')
    assert c['blue'] in all_attrs and c['blink'] in all_attrs
    assert c['bold'] in all_attrs and c['underline'] in all_attrs
    assert c['reset'] in all_attrs
    assert raises(KeyError, f, '*mauve*', 'text')


def test_console_functions():
    assert console.reset_color() == console.codes['reset']
    assert console.colorize('blue', 'text') == \
        console.codes['blue'] + 'text' + console.codes['reset']