Twitter-Text
view release on metacpan or search on metacpan
lib/Twitter/Text/Regexp.pm view on Meta::CPAN
0x2029, # White_Space # Zp PARAGRAPH SEPARATOR
0x202F, # White_Space # Zs NARROW NO-BREAK SPACE
0x205F, # White_Space # Zs MEDIUM MATHEMATICAL SPACE
0x3000, # White_Space # Zs IDEOGRAPHIC SPACE
);
our $DIRECTIONAL_CHARACTERS = join '', map { pack 'U', $_ } (
0x061C, # ARABIC LETTER MARK (ALM)
0x200E, # LEFT-TO-RIGHT MARK (LRM)
0x200F, # RIGHT-TO-LEFT MARK (RLM)
0x202A, # LEFT-TO-RIGHT EMBEDDING (LRE)
0x202B, # RIGHT-TO-LEFT EMBEDDING (RLE)
0x202C, # POP DIRECTIONAL FORMATTING (PDF)
0x202D, # LEFT-TO-RIGHT OVERRIDE (LRO)
0x202E, # RIGHT-TO-LEFT OVERRIDE (RLO)
0x2066, # LEFT-TO-RIGHT ISOLATE (LRI)
0x2067, # RIGHT-TO-LEFT ISOLATE (RLI)
0x2068, # FIRST STRONG ISOLATE (FSI)
0x2069, # POP DIRECTIONAL ISOLATE (PDI)
);
our $DOMAIN_VALID_CHARS = "[^$DIRECTIONAL_CHARACTERS$PUNCTUATION_CHARS$SPACE_CHARS$CTRL_CHARS$INVALID_CHARACTERS$UNICODE_SPACES]";
( run in 1.281 second using v1.01-cache-2.11-cpan-71847e10f99 )