vendor/regex-automata/tests/data/no-unicode.toml

   1 [[tests]]
   2 name = "invalid-utf8-literal1"
   3 regex = '\xFF'
   4 input = '\xFF'
   5 matches = [[0, 1]]
   6 unicode = false
   7 utf8 = false
   8 unescape = true
   9
  10
  11 [[tests]]
  12 name = "mixed"
  13 regex = '(.+)(?-u)(.+)'
  14 input = '\xCE\x93\xCE\x94\xFF'
  15 matches = [[0, 5]]
  16 utf8 = false
  17 unescape = true
  18
  19
  20 [[tests]]
  21 name = "case1"
  22 regex = "a"
  23 input = "A"
  24 matches = [[0, 1]]
  25 case_insensitive = true
  26 unicode = false
  27
  28 [[tests]]
  29 name = "case2"
  30 regex = "[a-z]+"
  31 input = "AaAaA"
  32 matches = [[0, 5]]
  33 case_insensitive = true
  34 unicode = false
  35
  36 [[tests]]
  37 name = "case3"
  38 regex = "[a-z]+"
  39 input = "aA\u212AaA"
  40 matches = [[0, 7]]
  41 case_insensitive = true
  42
  43 [[tests]]
  44 name = "case4"
  45 regex = "[a-z]+"
  46 input = "aA\u212AaA"
  47 matches = [[0, 2], [5, 7]]
  48 case_insensitive = true
  49 unicode = false
  50
  51
  52 [[tests]]
  53 name = "negate1"
  54 regex = "[^a]"
  55 input = "δ"
  56 matches = [[0, 2]]
  57
  58 [[tests]]
  59 name = "negate2"
  60 regex = "[^a]"
  61 input = "δ"
  62 matches = [[0, 1], [1, 2]]
  63 unicode = false
  64 utf8 = false
  65
  66
  67 [[tests]]
  68 name = "dotstar-prefix1"
  69 regex = "a"
  70 input = '\xFFa'
  71 matches = [[1, 2]]
  72 unicode = false
  73 utf8 = false
  74 unescape = true
  75
  76 [[tests]]
  77 name = "dotstar-prefix2"
  78 regex = "a"
  79 input = '\xFFa'
  80 matches = [[1, 2]]
  81 utf8 = false
  82 unescape = true
  83
  84
  85 [[tests]]
  86 name = "null-bytes1"
  87 regex = '[^\x00]+\x00'
  88 input = 'foo\x00'
  89 matches = [[0, 4]]
  90 unicode = false
  91 utf8 = false
  92 unescape = true
  93
  94
  95 [[tests]]
  96 name = "word-ascii"
  97 regex = '\w+'
  98 input = "aδ"
  99 matches = [[0, 1]]
 100 unicode = false
 101
 102 [[tests]]
 103 name = "word-unicode"
 104 regex = '\w+'
 105 input = "aδ"
 106 matches = [[0, 3]]
 107
 108 [[tests]]
 109 name = "decimal-ascii"
 110 regex = '\d+'
 111 input = "1२३9"
 112 matches = [[0, 1], [7, 8]]
 113 unicode = false
 114
 115 [[tests]]
 116 name = "decimal-unicode"
 117 regex = '\d+'
 118 input = "1२३9"
 119 matches = [[0, 8]]
 120
 121 [[tests]]
 122 name = "space-ascii"
 123 regex = '\s+'
 124 input = " \u1680"
 125 matches = [[0, 1]]
 126 unicode = false
 127
 128 [[tests]]
 129 name = "space-unicode"
 130 regex = '\s+'
 131 input = " \u1680"
 132 matches = [[0, 4]]
 133
 134
 135 [[tests]]
 136 # See: https://github.com/rust-lang/regex/issues/484
 137 name = "iter1-bytes"
 138 regex = ''
 139 input = "☃"
 140 matches = [[0, 0], [1, 1], [2, 2], [3, 3]]
 141 utf8 = false
 142
 143 [[tests]]
 144 # See: https://github.com/rust-lang/regex/issues/484
 145 name = "iter1-utf8"
 146 regex = ''
 147 input = "☃"
 148 matches = [[0, 0], [3, 3]]
 149
 150 [[tests]]
 151 # See: https://github.com/rust-lang/regex/issues/484
 152 # Note that iter2-utf8 doesn't make sense here, since the input isn't UTF-8.
 153 name = "iter2-bytes"
 154 regex = ''
 155 input = 'b\xFFr'
 156 matches = [[0, 0], [1, 1], [2, 2], [3, 3]]
 157 unescape = true
 158 utf8 = false