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
|
# -*- coding: utf-8 -*-
"""
Python Tests
~~~~~~~~~~~~
:copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import pytest
from pygments.lexers import PythonLexer, Python3Lexer
from pygments.token import Token
@pytest.fixture(scope='module')
def lexer2():
yield PythonLexer()
@pytest.fixture(scope='module')
def lexer3():
yield Python3Lexer()
def test_cls_builtin(lexer2):
"""
Tests that a cls token gets interpreted as a Token.Name.Builtin.Pseudo
"""
fragment = 'class TestClass():\n @classmethod\n def hello(cls):\n pass\n'
tokens = [
(Token.Keyword, 'class'),
(Token.Text, ' '),
(Token.Name.Class, 'TestClass'),
(Token.Punctuation, '('),
(Token.Punctuation, ')'),
(Token.Punctuation, ':'),
(Token.Text, '\n'),
(Token.Text, ' '),
(Token.Name.Decorator, '@classmethod'),
(Token.Text, '\n'),
(Token.Text, ' '),
(Token.Keyword, 'def'),
(Token.Text, ' '),
(Token.Name.Function, 'hello'),
(Token.Punctuation, '('),
(Token.Name.Builtin.Pseudo, 'cls'),
(Token.Punctuation, ')'),
(Token.Punctuation, ':'),
(Token.Text, '\n'),
(Token.Text, ' '),
(Token.Keyword, 'pass'),
(Token.Text, '\n'),
]
assert list(lexer2.get_tokens(fragment)) == tokens
def test_needs_name(lexer3):
"""
Tests that '@' is recognized as an Operator
"""
fragment = u'S = (H @ beta - r).T @ inv(H @ V @ H.T) @ (H @ beta - r)\n'
tokens = [
(Token.Name, u'S'),
(Token.Text, u' '),
(Token.Operator, u'='),
(Token.Text, u' '),
(Token.Punctuation, u'('),
(Token.Name, u'H'),
(Token.Text, u' '),
(Token.Operator, u'@'),
(Token.Text, u' '),
(Token.Name, u'beta'),
(Token.Text, u' '),
(Token.Operator, u'-'),
(Token.Text, u' '),
(Token.Name, u'r'),
(Token.Punctuation, u')'),
(Token.Operator, u'.'),
(Token.Name, u'T'),
(Token.Text, u' '),
(Token.Operator, u'@'),
(Token.Text, u' '),
(Token.Name, u'inv'),
(Token.Punctuation, u'('),
(Token.Name, u'H'),
(Token.Text, u' '),
(Token.Operator, u'@'),
(Token.Text, u' '),
(Token.Name, u'V'),
(Token.Text, u' '),
(Token.Operator, u'@'),
(Token.Text, u' '),
(Token.Name, u'H'),
(Token.Operator, u'.'),
(Token.Name, u'T'),
(Token.Punctuation, u')'),
(Token.Text, u' '),
(Token.Operator, u'@'),
(Token.Text, u' '),
(Token.Punctuation, u'('),
(Token.Name, u'H'),
(Token.Text, u' '),
(Token.Operator, u'@'),
(Token.Text, u' '),
(Token.Name, u'beta'),
(Token.Text, u' '),
(Token.Operator, u'-'),
(Token.Text, u' '),
(Token.Name, u'r'),
(Token.Punctuation, u')'),
(Token.Text, u'\n'),
]
assert list(lexer3.get_tokens(fragment)) == tokens
def test_pep_515(lexer3):
"""
Tests that the lexer can parse numeric literals with underscores
"""
fragments = (
(Token.Literal.Number.Integer, u'1_000_000'),
(Token.Literal.Number.Float, u'1_000.000_001'),
(Token.Literal.Number.Float, u'1_000e1_000j'),
(Token.Literal.Number.Hex, u'0xCAFE_F00D'),
(Token.Literal.Number.Bin, u'0b_0011_1111_0100_1110'),
(Token.Literal.Number.Oct, u'0o_777_123'),
)
for token, fragment in fragments:
tokens = [
(token, fragment),
(Token.Text, u'\n'),
]
assert list(lexer3.get_tokens(fragment)) == tokens
|
