You can always use unicode-regex-range-character-class.pl
space => [\u0009-\u000D\u0020\u0085\u00A0\u1680\u180E\u2000-\u200A\u20 +28-\u2029\u202F\u205F\u3000]
so
$ perl -pe " s{\\u(....)}{\\x{$1}}g " [\u0009-\u000D\u0020\u0085\u00A0\u1680\u180E\u2000-\u200A\u2028-\u2029 +\u202F\u205F\u3000] [\x{0009}-\x{000D}\x{0020}\x{0085}\x{00A0}\x{1680}\x{180E}\x{2000}-\x{ +200A}\x{2028}-\x{2029}\x{202F}\x{205F}\x{3000}]
Thus
#!/usr/bin/perl -- use warnings;use strict; use Data::Dump; $_ = qq{\xC2\xA01.00};; utf8::decode($_); dd[$_]; s{^[\x{0009}-\x{000D}\x{0020}\x{0085}\x{00A0}\x{1680}\x{180E}\x{2000}- +\x{200A}\x{2028}-\x{2029}\x{202F}\x{205F}\x{3000}]+}{}g; dd[$_]; __END__ ["\xA01.00"] ["1.00"]
Although, in 5.10 you could probably just use s{^\p{space}+}{}g;
In reply to Re^5: This looks like whitespace in my CSV but doesn't seem to be
by Anonymous Monk
in thread This looks like whitespace in my CSV but doesn't seem to be
by ghenry
For: | Use: | ||
& | & | ||
< | < | ||
> | > | ||
[ | [ | ||
] | ] |