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
|
"""
Pygments Markdown lexer tests
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
:copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import pytest
from pygments.token import Generic, Token, String
from pygments.lexers.markup import MarkdownLexer
@pytest.fixture(scope='module')
def lexer():
yield MarkdownLexer()
def assert_same_text(lexer, text):
"""Show that lexed markdown does not remove any content. """
tokens = list(lexer.get_tokens_unprocessed(text))
output = ''.join(t[2] for t in tokens)
assert text == output
def test_code_fence(lexer):
assert_same_text(lexer, r'```\nfoo\n```\n')
def test_code_fence_gsm(lexer):
assert_same_text(lexer, r'```markdown\nfoo\n```\n')
def test_code_fence_gsm_with_no_lexer(lexer):
assert_same_text(lexer, r'```invalid-lexer\nfoo\n```\n')
def test_invalid_atx_heading(lexer):
fragments = (
'#',
'a #',
'*#',
)
for fragment in fragments:
for token, _ in lexer.get_tokens(fragment):
assert token != Generic.Heading
def test_atx_heading(lexer):
fragments = (
'#Heading',
'# Heading',
'# Another heading',
'# Another # heading',
'# Heading #',
)
for fragment in fragments:
tokens = [
(Generic.Heading, fragment),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_invalid_atx_subheading(lexer):
fragments = (
'##',
'a ##',
'*##',
'####### too many hashes'
)
for fragment in fragments:
for token, _ in lexer.get_tokens(fragment):
assert token != Generic.Subheading
def test_atx_subheading(lexer):
fragments = (
'##Subheading',
'## Subheading',
'### Subheading',
'#### Subheading',
'##### Subheading',
'###### Subheading',
'## Another subheading',
'## Another ## subheading',
'###### Subheading #',
'###### Subheading ######',
)
for fragment in fragments:
tokens = [
(Generic.Subheading, fragment),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_invalid_setext_heading(lexer):
fragments = (
'Heading\n',
'Heading\n_',
'Heading\n =====',
'Heading\na=====',
'=====',
'\n=\n',
'Heading\n=====Text'
)
for fragment in fragments:
for token, _ in lexer.get_tokens(fragment):
assert token != Generic.Heading
def test_setext_heading(lexer):
fragments = (
'Heading\n=',
'Heading\n=======',
'Heading\n==========',
)
for fragment in fragments:
tokens = [
(Generic.Heading, fragment.split('\n')[0]),
(Token.Text, '\n'),
(Generic.Heading, fragment.split('\n')[1]),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_invalid_setext_subheading(lexer):
fragments = (
'Subheading\n',
'Subheading\n_',
'Subheading\n -----',
'Subheading\na-----',
'-----',
'\n-\n',
'Subheading\n-----Text'
)
for fragment in fragments:
for token, _ in lexer.get_tokens(fragment):
assert token != Generic.Subheading
def test_setext_subheading(lexer):
fragments = (
'Subheading\n-',
'Subheading\n----------',
'Subheading\n-----------',
)
for fragment in fragments:
tokens = [
(Generic.Subheading, fragment.split('\n')[0]),
(Token.Text, '\n'),
(Generic.Subheading, fragment.split('\n')[1]),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_invalid_code_block(lexer):
fragments = (
'```code```',
'prefix not allowed before ```\ncode block\n```'
' code',
)
for fragment in fragments:
for token, _ in lexer.get_tokens(fragment):
assert token != String.Backtick
|
