gruber-url-regex.rb

#!/opt/local/bin/ruby1.9

require 'yaml'

urls = YAML::load <<-STR
http://foo.com/blah_blah                                                  : http://foo.com/blah_blah
http://foo.com/blah_blah/                                                 : http://foo.com/blah_blah/
(Something like http://foo.com/blah_blah)                                 : http://foo.com/blah_blah
http://foo.com/blah_blah_(wikipedia)                                      : http://foo.com/blah_blah_(wikipedia)
http://foo.com/blah-blah-(wiki-pedia)                                     : http://foo.com/blah-blah-(wiki-pedia)
(Something like http://foo.com/blah_blah_(wikipedia))                     : http://foo.com/blah_blah_(wikipedia)
(Something like http://foo.com/blah_-blah_(wikip-edia))                   : http://foo.com/blah_-blah_(wikip-edia)
http://foo.com/blah_blah.                                                 : http://foo.com/blah_blah
http://foo.com/blah_blah/.                                                : http://foo.com/blah_blah/
<http://foo.com/blah_blah>                                                : http://foo.com/blah_blah
<http://foo.com/blah_blah/>                                               : http://foo.com/blah_blah/
http://foo.com/blah_blah,                                                 : http://foo.com/blah_blah
http://www.example.com/wpstyle/?p=364.                                    : http://www.example.com/wpstyle/?p=364
http://www.example.com/wpstyle/?p=364;asdf=123&qewr=78.                   : http://www.example.com/wpstyle/?p=364;asdf=123&qewr=78
http://✪df.ws/123                                                         : http://✪df.ws/123
rdar://1234                                                               : rdar://1234
rdar:/1234                                                                : rdar:/1234
http://userid:password@example.com:8080                                   : http://userid:password@example.com:8080
http://userid@example.com                                                 : http://userid@example.com
http://userid@example.com:8080                                            : http://userid@example.com:8080
http://userid:password@example.com                                        : http://userid:password@example.com
http://example.com:8080                                                   : http://example.com:8080
http://exa-mple.com:8080                                                  : http://exa-mple.com:8080
x-yojimbo-item://6303E4C1-xxxx-45A6-AB9D-3A908F59AE0E                     : x-yojimbo-item://6303E4C1-xxxx-45A6-AB9D-3A908F59AE0E
message://%3c330e7f8409726r6a4ba78dkf1fd71420c1bf6ff@mail.gmail.com%3e    : message://%3c330e7f8409726r6a4ba78dkf1fd71420c1bf6ff@mail.gmail.com%3e
http://➡.ws/䨹                                                             : http://➡.ws/䨹
www.➡.ws/䨹                                                                : www.➡.ws/䨹
<tag>http://example.com</tag>                                             : http://example.com
Just a www.example.com link.                                              : www.example.com
STR


RX   = %r{\b(([\w-]+://?|www[.])[^\s()<>]+(?:\([\w\d]+\)|([^[:punct:]\s]|/)))}
# RX = %r{\b(([\w-]+://?|www[.])[^\s()<>]+(?:\([\w-]+\)|([^[:punct:]\s<>]|/)))}
# FIXES ::                                     ^^^^^                  ^^

y urls.entries.map { |k, v| k =~ RX; [v, $&] }.select { |(s, m)| s != m }