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
|
# -*- coding: utf-8 -*-
"""
Data Tests
~~~~~~~~~~
:copyright: Copyright 2006-2016 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import pytest
from pygments.lexers import JsonLexer, JsonBareObjectLexer, YamlLexer
from pygments.token import Token
@pytest.fixture(scope='module')
def lexer_json():
yield JsonLexer()
@pytest.fixture(scope='module')
def lexer_bare():
yield JsonBareObjectLexer()
@pytest.fixture(scope='module')
def lexer_yaml():
yield YamlLexer()
def test_basic_json(lexer_json):
fragment = '{"foo": "bar", "foo2": [1, 2, 3]}\n'
tokens = [
(Token.Punctuation, '{'),
(Token.Name.Tag, '"foo"'),
(Token.Punctuation, ':'),
(Token.Text, ' '),
(Token.Literal.String.Double, '"bar"'),
(Token.Punctuation, ','),
(Token.Text, ' '),
(Token.Name.Tag, '"foo2"'),
(Token.Punctuation, ':'),
(Token.Text, ' '),
(Token.Punctuation, '['),
(Token.Literal.Number.Integer, '1'),
(Token.Punctuation, ','),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '2'),
(Token.Punctuation, ','),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '3'),
(Token.Punctuation, ']'),
(Token.Punctuation, '}'),
(Token.Text, '\n'),
]
assert list(lexer_json.get_tokens(fragment)) == tokens
def test_json_escape_backtracking(lexer_json):
# This tests that an (invalid) sequence of escapes doesn't cause the lexer
# to fall into catastrophic backtracking. unfortunately, if it's broken
# this test will hang and that's how we know it's broken :(
fragment = r'{"\u00D0000\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\63CD'
tokens = (
[(Token.Punctuation, '{'),
(Token.Error, r'"'),
(Token.Error, '\\'),
(Token.Error, r'u'),
(Token.Error, r'0'),
(Token.Error, r'0'),
(Token.Error, r'D'),
(Token.Error, r'0'),
(Token.Error, r'0'),
(Token.Error, r'0'),
(Token.Error, r'0')]
+ [(Token.Error, '\\')] * 178
+ [(Token.Error, r'6'),
(Token.Error, r'3'),
(Token.Error, r'C'),
(Token.Error, r'D'),
(Token.Text, '\n')]
)
assert list(lexer_json.get_tokens(fragment)) == tokens
def test_basic_bare(lexer_bare):
# This is the same as testBasic for JsonLexer above, except the
# enclosing curly braces are removed.
fragment = '"foo": "bar", "foo2": [1, 2, 3]\n'
tokens = [
(Token.Name.Tag, '"foo"'),
(Token.Punctuation, ':'),
(Token.Text, ' '),
(Token.Literal.String.Double, '"bar"'),
(Token.Punctuation, ','),
(Token.Text, ' '),
(Token.Name.Tag, '"foo2"'),
(Token.Punctuation, ':'),
(Token.Text, ' '),
(Token.Punctuation, '['),
(Token.Literal.Number.Integer, '1'),
(Token.Punctuation, ','),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '2'),
(Token.Punctuation, ','),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '3'),
(Token.Punctuation, ']'),
(Token.Text, '\n'),
]
assert list(lexer_bare.get_tokens(fragment)) == tokens
def test_closing_curly(lexer_bare):
# This can be an Error token, but should not be a can't-pop-from-stack
# exception.
fragment = '}"a"\n'
tokens = [
(Token.Error, '}'),
(Token.Name.Tag, '"a"'),
(Token.Text, '\n'),
]
assert list(lexer_bare.get_tokens(fragment)) == tokens
def test_closing_curly_in_value(lexer_bare):
fragment = '"": ""}\n'
tokens = [
(Token.Name.Tag, '""'),
(Token.Punctuation, ':'),
(Token.Text, ' '),
(Token.Literal.String.Double, '""'),
(Token.Error, '}'),
(Token.Text, '\n'),
]
assert list(lexer_bare.get_tokens(fragment)) == tokens
def test_yaml(lexer_yaml):
# Bug #1528: This previously parsed 'token # innocent' as a tag
fragment = 'here: token # innocent: comment\n'
tokens = [
(Token.Name.Tag, 'here'),
(Token.Punctuation, ':'),
(Token.Text, ' '),
(Token.Literal.Scalar.Plain, 'token'),
(Token.Text, ' '),
(Token.Comment.Single, '# innocent: comment'),
(Token.Text, '\n'),
]
assert list(lexer_yaml.get_tokens(fragment)) == tokens
|
