summaryrefslogtreecommitdiffstats
path: root/vendor/regex-automata/data/tests/no-unicode.toml
blob: 16e02b42623e2dc56cb2566d05a79fa1f5c64ca3 (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
[[tests]]
name = "invalid-utf8-literal1"
options = ["escaped", "invalid-utf8", "no-unicode"]
pattern = '\xFF'
input = '\xFF'
matches = [[0, 1]]


[[tests]]
name = "no-unicode-mixed"
options = ["escaped", "invalid-utf8"]
pattern = '(.+)(?-u)(.+)'
input = '\xCE\x93\xCE\x94\xFF'
matches = [[0, 5]]


[[tests]]
name = "no-unicode-case1"
options = ["case-insensitive", "no-unicode"]
pattern = "a"
input = "A"
matches = [[0, 1]]

[[tests]]
name = "no-unicode-case2"
options = ["case-insensitive", "no-unicode"]
pattern = "[a-z]+"
input = "AaAaA"
matches = [[0, 5]]

[[tests]]
name = "no-unicode-case3"
options = ["case-insensitive"]
pattern = "[a-z]+"
input = "aA\u212AaA"
matches = [[0, 7]]

[[tests]]
name = "no-unicode-case4"
options = ["case-insensitive", "no-unicode"]
pattern = "[a-z]+"
input = "aA\u212AaA"
matches = [[0, 2]]


[[tests]]
name = "no-unicode-negate1"
options = []
pattern = "[^a]"
input = "δ"
matches = [[0, 2]]

[[tests]]
name = "no-unicode-negate2"
options = ["no-unicode", "invalid-utf8"]
pattern = "[^a]"
input = "δ"
matches = [[0, 1]]


[[tests]]
name = "no-unicode-dotstar-prefix1"
options = ["escaped", "no-unicode", "invalid-utf8"]
pattern = "a"
input = '\xFFa'
matches = [[1, 2]]

[[tests]]
name = "no-unicode-dotstar-prefix2"
options = ["escaped", "invalid-utf8"]
pattern = "a"
input = '\xFFa'
matches = [[1, 2]]


[[tests]]
name = "no-unicode-null-bytes1"
options = ["escaped", "no-unicode", "invalid-utf8"]
pattern = '[^\x00]+\x00'
input = 'foo\x00'
matches = [[0, 4]]


[[tests]]
name = "no-unicode1"
options = ["no-unicode"]
pattern = '\w+'
input = "aδ"
matches = [[0, 1]]

[[tests]]
name = "no-unicode2"
options = []
pattern = '\w+'
input = "aδ"
matches = [[0, 3]]

[[tests]]
name = "no-unicode3"
options = ["no-unicode"]
pattern = '\d+'
input = "1२३9"
matches = [[0, 1]]

[[tests]]
name = "no-unicode4"
pattern = '\d+'
input = "1२३9"
matches = [[0, 8]]

[[tests]]
name = "no-unicode5"
options = ["no-unicode"]
pattern = '\s+'
input = " \u1680"
matches = [[0, 1]]

[[tests]]
name = "no-unicode6"
pattern = '\s+'
input = " \u1680"
matches = [[0, 4]]


[[tests]]
# See: https://github.com/rust-lang/regex/issues/484
name = "no-unicode-iter1"
pattern = ''
input = "☃"
matches = [[0, 0], [1, 1], [2, 2], [3, 3]]

[[tests]]
# See: https://github.com/rust-lang/regex/issues/484
options = ['escaped']
name = "no-unicode-iter2"
pattern = ''
input = 'b\xFFr'
matches = [[0, 0], [1, 1], [2, 2], [3, 3]]