Andrew Gallant 1e7efa4180 regex: add unicode and perf features
This commit sets up the infrastructure for supporting various `unicode`
and `perf` features, which permit decreasing binary size, compile times
and the size of the dependency tree.

Most of the work here is in modifying the regex tests to make them
work in concert with the available Unicode features. In cases where
Unicode is irrelevant, we just turn it off. In other cases, we require
the Unicode features to run the tests.

This also introduces a new error in the compiler where by if a Unicode
word boundary is used, but the `unicode-perl` feature is disabled, then
the regex will fail to compile. (Because the necessary data to match
Unicode word boundaries isn't available.)
2019-09-03 12:35:17 -04:00

32 lines
895 B
Rust

mat!(match_flag_case, "(?-u)(?i)abc", "ABC", Some((0, 3)));
mat!(match_flag_weird_case, "(?-u)(?i)a(?-i)bc", "Abc", Some((0, 3)));
mat!(match_flag_weird_case_not, "(?-u)(?i)a(?-i)bc", "ABC", None);
mat!(match_flag_case_dotnl, "(?-u)(?is)a(?u:.)", "A\n", Some((0, 2)));
mat!(
match_flag_case_dotnl_toggle,
"(?-u)(?is)a(?u:.)(?-is)a(?u:.)",
"A\nab",
Some((0, 4))
);
mat!(
match_flag_case_dotnl_toggle_not,
"(?-u)(?is)a(?u:.)(?-is)a(?u:.)",
"A\na\n",
None
);
mat!(
match_flag_case_dotnl_toggle_ok,
"(?-u)(?is)a(?u:.)(?-is:a(?u:.))?",
"A\na\n",
Some((0, 2))
);
mat!(
match_flag_multi,
r"(?-u)(?m)(?:^\d+$\n?)+",
"123\n456\n789",
Some((0, 11))
);
mat!(match_flag_ungreedy, "(?U)a+", "aa", Some((0, 1)));
mat!(match_flag_ungreedy_greedy, "(?U)a+?", "aa", Some((0, 2)));
mat!(match_flag_ungreedy_noop, "(?U)(?-U)a+", "aa", Some((0, 2)));