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
|
# -*- coding: utf-8 -*-
"""
MATLAB Tests
~~~~~~~~~~~
:copyright: Copyright 2006-2020 by the Pygments team, see AUTHORS.
:license: BSD, see LICENSE for details.
"""
import pytest
from pygments.token import Token
from pygments.lexers import MatlabLexer
@pytest.fixture(scope='module')
def lexer():
yield MatlabLexer()
def test_single_line(lexer):
"""
Test that a single line with strings, a method, and numbers is parsed correctly.
"""
fragment = "set('T',300,'P',101325);\n"
tokens = [
(Token.Name, 'set'),
(Token.Punctuation, '('),
(Token.Literal.String, "'"),
(Token.Literal.String, "T'"),
(Token.Punctuation, ','),
(Token.Literal.Number.Integer, '300'),
(Token.Punctuation, ','),
(Token.Literal.String, "'"),
(Token.Literal.String, "P'"),
(Token.Punctuation, ','),
(Token.Literal.Number.Integer, '101325'),
(Token.Punctuation, ')'),
(Token.Punctuation, ';'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_line_continuation(lexer):
"""
Test that line continuation by ellipses does not produce generic
output on the second line.
"""
fragment = "set('T',300,...\n'P',101325);\n"
tokens = [
(Token.Name, 'set'),
(Token.Punctuation, '('),
(Token.Literal.String, "'"),
(Token.Literal.String, "T'"),
(Token.Punctuation, ','),
(Token.Literal.Number.Integer, '300'),
(Token.Punctuation, ','),
(Token.Keyword, '...'),
(Token.Text, '\n'),
(Token.Literal.String, "'"),
(Token.Literal.String, "P'"),
(Token.Punctuation, ','),
(Token.Literal.Number.Integer, '101325'),
(Token.Punctuation, ')'),
(Token.Punctuation, ';'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_keywords_ended_by_newline(lexer):
"""Test that keywords on their own line are marked as keywords."""
fragment = "if x > 100\n disp('x > 100')\nelse\n disp('x < 100')\nend\n"
tokens = [
(Token.Keyword, 'if'),
(Token.Text, ' '),
(Token.Name, 'x'),
(Token.Text, ' '),
(Token.Operator, '>'),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '100'),
(Token.Text, '\n'),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Name.Builtin, 'disp'),
(Token.Punctuation, '('),
(Token.Literal.String, "'"),
(Token.Literal.String, "x > 100'"),
(Token.Punctuation, ')'),
(Token.Text, '\n'),
(Token.Keyword, 'else'),
(Token.Text, '\n'),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Name.Builtin, 'disp'),
(Token.Punctuation, '('),
(Token.Literal.String, "'"),
(Token.Literal.String, "x < 100'"),
(Token.Punctuation, ')'),
(Token.Text, '\n'),
(Token.Keyword, 'end'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_comment_after_continuation(lexer):
"""
Test that text after the line continuation ellipses is marked as a comment.
"""
fragment = "set('T',300,... a comment\n'P',101325);\n"
tokens = [
(Token.Name, 'set'),
(Token.Punctuation, '('),
(Token.Literal.String, "'"),
(Token.Literal.String, "T'"),
(Token.Punctuation, ','),
(Token.Literal.Number.Integer, '300'),
(Token.Punctuation, ','),
(Token.Keyword, '...'),
(Token.Comment, ' a comment'),
(Token.Text, '\n'),
(Token.Literal.String, "'"),
(Token.Literal.String, "P'"),
(Token.Punctuation, ','),
(Token.Literal.Number.Integer, '101325'),
(Token.Punctuation, ')'),
(Token.Punctuation, ';'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_multiple_spaces_variable_assignment(lexer):
"""
Test that multiple spaces with an equal sign doesn't get formatted to a string.
"""
fragment = 'x = 100;\n'
tokens = [
(Token.Name, 'x'),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Punctuation, '='),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '100'),
(Token.Punctuation, ';'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_operator_multiple_space(lexer):
"""
Test that multiple spaces with an operator doesn't get formatted to a string.
"""
fragment = 'x > 100;\n'
tokens = [
(Token.Name, 'x'),
(Token.Text, ' '),
(Token.Text, ' '),
(Token.Operator, '>'),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '100'),
(Token.Punctuation, ';'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_one_space_assignment(lexer):
"""Test that one space before an equal sign is formatted correctly."""
fragment = 'x = 100;\n'
tokens = [
(Token.Name, 'x'),
(Token.Text, ' '),
(Token.Punctuation, '='),
(Token.Text, ' '),
(Token.Literal.Number.Integer, '100'),
(Token.Punctuation, ';'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
def test_command_mode(lexer):
"""
MATLAB allows char function arguments to not be enclosed by parentheses
or contain quote characters, as long as they are space separated. Test
that one common such function is formatted appropriately.
"""
fragment = 'help sin\n'
tokens = [
(Token.Name, 'help'),
(Token.Text, ' '),
(Token.Literal.String, 'sin'),
(Token.Text, '\n'),
]
assert list(lexer.get_tokens(fragment)) == tokens
|
