rustc/vendor/regex-automata-0.2.0/tests/data/no-unicode.toml
2024-05-29 11:23:22 +02:00

159 lines
2.4 KiB
TOML

[[tests]]
name = "invalid-utf8-literal1"
regex = '\xFF'
input = '\xFF'
matches = [[0, 1]]
unicode = false
utf8 = false
unescape = true
[[tests]]
name = "mixed"
regex = '(.+)(?-u)(.+)'
input = '\xCE\x93\xCE\x94\xFF'
matches = [[0, 5]]
utf8 = false
unescape = true
[[tests]]
name = "case1"
regex = "a"
input = "A"
matches = [[0, 1]]
case_insensitive = true
unicode = false
[[tests]]
name = "case2"
regex = "[a-z]+"
input = "AaAaA"
matches = [[0, 5]]
case_insensitive = true
unicode = false
[[tests]]
name = "case3"
regex = "[a-z]+"
input = "aA\u212AaA"
matches = [[0, 7]]
case_insensitive = true
[[tests]]
name = "case4"
regex = "[a-z]+"
input = "aA\u212AaA"
matches = [[0, 2], [5, 7]]
case_insensitive = true
unicode = false
[[tests]]
name = "negate1"
regex = "[^a]"
input = "δ"
matches = [[0, 2]]
[[tests]]
name = "negate2"
regex = "[^a]"
input = "δ"
matches = [[0, 1], [1, 2]]
unicode = false
utf8 = false
[[tests]]
name = "dotstar-prefix1"
regex = "a"
input = '\xFFa'
matches = [[1, 2]]
unicode = false
utf8 = false
unescape = true
[[tests]]
name = "dotstar-prefix2"
regex = "a"
input = '\xFFa'
matches = [[1, 2]]
utf8 = false
unescape = true
[[tests]]
name = "null-bytes1"
regex = '[^\x00]+\x00'
input = 'foo\x00'
matches = [[0, 4]]
unicode = false
utf8 = false
unescape = true
[[tests]]
name = "word-ascii"
regex = '\w+'
input = "aδ"
matches = [[0, 1]]
unicode = false
[[tests]]
name = "word-unicode"
regex = '\w+'
input = "aδ"
matches = [[0, 3]]
[[tests]]
name = "decimal-ascii"
regex = '\d+'
input = "1२३9"
matches = [[0, 1], [7, 8]]
unicode = false
[[tests]]
name = "decimal-unicode"
regex = '\d+'
input = "1२३9"
matches = [[0, 8]]
[[tests]]
name = "space-ascii"
regex = '\s+'
input = " \u1680"
matches = [[0, 1]]
unicode = false
[[tests]]
name = "space-unicode"
regex = '\s+'
input = " \u1680"
matches = [[0, 4]]
[[tests]]
# See: https://github.com/rust-lang/regex/issues/484
name = "iter1-bytes"
regex = ''
input = "☃"
matches = [[0, 0], [1, 1], [2, 2], [3, 3]]
utf8 = false
[[tests]]
# See: https://github.com/rust-lang/regex/issues/484
name = "iter1-utf8"
regex = ''
input = "☃"
matches = [[0, 0], [3, 3]]
[[tests]]
# See: https://github.com/rust-lang/regex/issues/484
# Note that iter2-utf8 doesn't make sense here, since the input isn't UTF-8.
name = "iter2-bytes"
regex = ''
input = 'b\xFFr'
matches = [[0, 0], [1, 1], [2, 2], [3, 3]]
unescape = true
utf8 = false