| 1 |
# These are tests specifically crafted for regexes that can match arbitrary |
| 2 |
# bytes. In some cases, we also test the Unicode variant as well, just because |
| 3 |
# it's good sense to do so. But also, these tests aren't really about Unicode, |
| 4 |
# but whether matches are only reported at valid UTF-8 boundaries. For most |
| 5 |
# tests in this entire collection, utf8 = true. But for these tests, we use |
| 6 |
# utf8 = false. |
| 7 |
|
| 8 |
[[test]] |
| 9 |
name = "word-boundary-ascii" |
| 10 |
regex = ' \b' |
| 11 |
haystack = " δ" |
| 12 |
matches = [] |
| 13 |
unicode = false |
| 14 |
utf8 = false |
| 15 |
|
| 16 |
[[test]] |
| 17 |
name = "word-boundary-unicode" |
| 18 |
regex = ' \b' |
| 19 |
haystack = " δ" |
| 20 |
matches = [[0, 1]] |
| 21 |
unicode = true |
| 22 |
utf8 = false |
| 23 |
|
| 24 |
[[test]] |
| 25 |
name = "word-boundary-ascii-not" |
| 26 |
regex = ' \B' |
| 27 |
haystack = " δ" |
| 28 |
matches = [[0, 1]] |
| 29 |
unicode = false |
| 30 |
utf8 = false |
| 31 |
|
| 32 |
[[test]] |
| 33 |
name = "word-boundary-unicode-not" |
| 34 |
regex = ' \B' |
| 35 |
haystack = " δ" |
| 36 |
matches = [] |
| 37 |
unicode = true |
| 38 |
utf8 = false |
| 39 |
|
| 40 |
[[test]] |
| 41 |
name = "perl-word-ascii" |
| 42 |
regex = '\w+' |
| 43 |
haystack = "aδ" |
| 44 |
matches = [[0, 1]] |
| 45 |
unicode = false |
| 46 |
utf8 = false |
| 47 |
|
| 48 |
[[test]] |
| 49 |
name = "perl-word-unicode" |
| 50 |
regex = '\w+' |
| 51 |
haystack = "aδ" |
| 52 |
matches = [[0, 3]] |
| 53 |
unicode = true |
| 54 |
utf8 = false |
| 55 |
|
| 56 |
[[test]] |
| 57 |
name = "perl-decimal-ascii" |
| 58 |
regex = '\d+' |
| 59 |
haystack = "1२३9" |
| 60 |
matches = [[0, 1], [7, 8]] |
| 61 |
unicode = false |
| 62 |
utf8 = false |
| 63 |
|
| 64 |
[[test]] |
| 65 |
name = "perl-decimal-unicode" |
| 66 |
regex = '\d+' |
| 67 |
haystack = "1२३9" |
| 68 |
matches = [[0, 8]] |
| 69 |
unicode = true |
| 70 |
utf8 = false |
| 71 |
|
| 72 |
[[test]] |
| 73 |
name = "perl-whitespace-ascii" |
| 74 |
regex = '\s+' |
| 75 |
haystack = " \u1680" |
| 76 |
matches = [[0, 1]] |
| 77 |
unicode = false |
| 78 |
utf8 = false |
| 79 |
|
| 80 |
[[test]] |
| 81 |
name = "perl-whitespace-unicode" |
| 82 |
regex = '\s+' |
| 83 |
haystack = " \u1680" |
| 84 |
matches = [[0, 4]] |
| 85 |
unicode = true |
| 86 |
utf8 = false |
| 87 |
|
| 88 |
# The first `(.+)` matches two Unicode codepoints, but can't match the 5th |
| 89 |
# byte, which isn't valid UTF-8. The second (byte based) `(.+)` takes over and |
| 90 |
# matches. |
| 91 |
[[test]] |
| 92 |
name = "mixed-dot" |
| 93 |
regex = '(.+)(?-u)(.+)' |
| 94 |
haystack = '\xCE\x93\xCE\x94\xFF' |
| 95 |
matches = [ |
| 96 |
[[0, 5], [0, 4], [4, 5]], |
| 97 |
] |
| 98 |
unescape = true |
| 99 |
unicode = true |
| 100 |
utf8 = false |
| 101 |
|
| 102 |
[[test]] |
| 103 |
name = "case-one-ascii" |
| 104 |
regex = 'a' |
| 105 |
haystack = "A" |
| 106 |
matches = [[0, 1]] |
| 107 |
case-insensitive = true |
| 108 |
unicode = false |
| 109 |
utf8 = false |
| 110 |
|
| 111 |
[[test]] |
| 112 |
name = "case-one-unicode" |
| 113 |
regex = 'a' |
| 114 |
haystack = "A" |
| 115 |
matches = [[0, 1]] |
| 116 |
case-insensitive = true |
| 117 |
unicode = true |
| 118 |
utf8 = false |
| 119 |
|
| 120 |
[[test]] |
| 121 |
name = "case-class-simple-ascii" |
| 122 |
regex = '[a-z]+' |
| 123 |
haystack = "AaAaA" |
| 124 |
matches = [[0, 5]] |
| 125 |
case-insensitive = true |
| 126 |
unicode = false |
| 127 |
utf8 = false |
| 128 |
|
| 129 |
[[test]] |
| 130 |
name = "case-class-ascii" |
| 131 |
regex = '[a-z]+' |
| 132 |
haystack = "aA\u212AaA" |
| 133 |
matches = [[0, 2], [5, 7]] |
| 134 |
case-insensitive = true |
| 135 |
unicode = false |
| 136 |
utf8 = false |
| 137 |
|
| 138 |
[[test]] |
| 139 |
name = "case-class-unicode" |
| 140 |
regex = '[a-z]+' |
| 141 |
haystack = "aA\u212AaA" |
| 142 |
matches = [[0, 7]] |
| 143 |
case-insensitive = true |
| 144 |
unicode = true |
| 145 |
utf8 = false |
| 146 |
|
| 147 |
[[test]] |
| 148 |
name = "negate-ascii" |
| 149 |
regex = '[^a]' |
| 150 |
haystack = "δ" |
| 151 |
matches = [[0, 1], [1, 2]] |
| 152 |
unicode = false |
| 153 |
utf8 = false |
| 154 |
|
| 155 |
[[test]] |
| 156 |
name = "negate-unicode" |
| 157 |
regex = '[^a]' |
| 158 |
haystack = "δ" |
| 159 |
matches = [[0, 2]] |
| 160 |
unicode = true |
| 161 |
utf8 = false |
| 162 |
|
| 163 |
# When utf8=true, this won't match, because the implicit '.*?' prefix is |
| 164 |
# Unicode aware and will refuse to match through invalid UTF-8 bytes. |
| 165 |
[[test]] |
| 166 |
name = "dotstar-prefix-ascii" |
| 167 |
regex = 'a' |
| 168 |
haystack = '\xFFa' |
| 169 |
matches = [[1, 2]] |
| 170 |
unescape = true |
| 171 |
unicode = false |
| 172 |
utf8 = false |
| 173 |
|
| 174 |
[[test]] |
| 175 |
name = "dotstar-prefix-unicode" |
| 176 |
regex = 'a' |
| 177 |
haystack = '\xFFa' |
| 178 |
matches = [[1, 2]] |
| 179 |
unescape = true |
| 180 |
unicode = true |
| 181 |
utf8 = false |
| 182 |
|
| 183 |
[[test]] |
| 184 |
name = "null-bytes" |
| 185 |
regex = '(?P<cstr>[^\x00]+)\x00' |
| 186 |
haystack = 'foo\x00' |
| 187 |
matches = [ |
| 188 |
[[0, 4], [0, 3]], |
| 189 |
] |
| 190 |
unescape = true |
| 191 |
unicode = false |
| 192 |
utf8 = false |
| 193 |
|
| 194 |
[[test]] |
| 195 |
name = "invalid-utf8-anchor-100" |
| 196 |
regex = '\xCC?^' |
| 197 |
haystack = '\x8d#;\x1a\xa4s3\x05foobarX\\\x0f0t\xe4\x9b\xa4' |
| 198 |
matches = [[0, 0]] |
| 199 |
unescape = true |
| 200 |
unicode = false |
| 201 |
utf8 = false |
| 202 |
|
| 203 |
[[test]] |
| 204 |
name = "invalid-utf8-anchor-200" |
| 205 |
regex = '^\xf7|4\xff\d\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a##########[] d\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a\x8a##########\[] #####\x80\S7|$' |
| 206 |
haystack = '\x8d#;\x1a\xa4s3\x05foobarX\\\x0f0t\xe4\x9b\xa4' |
| 207 |
matches = [[22, 22]] |
| 208 |
unescape = true |
| 209 |
unicode = false |
| 210 |
utf8 = false |
| 211 |
|
| 212 |
[[test]] |
| 213 |
name = "invalid-utf8-anchor-300" |
| 214 |
regex = '^|ddp\xff\xffdddddlQd@\x80' |
| 215 |
haystack = '\x8d#;\x1a\xa4s3\x05foobarX\\\x0f0t\xe4\x9b\xa4' |
| 216 |
matches = [[0, 0]] |
| 217 |
unescape = true |
| 218 |
unicode = false |
| 219 |
utf8 = false |
| 220 |
|
| 221 |
[[test]] |
| 222 |
name = "word-boundary-ascii-100" |
| 223 |
regex = '\Bx\B' |
| 224 |
haystack = "áxβ" |
| 225 |
matches = [] |
| 226 |
unicode = false |
| 227 |
utf8 = false |
| 228 |
|
| 229 |
[[test]] |
| 230 |
name = "word-boundary-ascii-200" |
| 231 |
regex = '\B' |
| 232 |
haystack = "0\U0007EF5E" |
| 233 |
matches = [[2, 2], [3, 3], [4, 4], [5, 5]] |
| 234 |
unicode = false |
| 235 |
utf8 = false |