From d86eb93366df577f6a6bdaef0032ee9ee9cf10b4 Mon Sep 17 00:00:00 2001
From: Tom Feist <shabble@cowu.be>
Date: Thu, 16 Sep 2010 15:27:29 +0100
Subject: modified it to use DaringFireball liberal uri match rather than
 re::common to handle more cases

---
 tinyurl-tabcomplete/complete-tiny-url.pl | 45 +++++++++++++++++++++++++++++---
 1 file changed, 42 insertions(+), 3 deletions(-)

(limited to 'tinyurl-tabcomplete/complete-tiny-url.pl')

diff --git a/tinyurl-tabcomplete/complete-tiny-url.pl b/tinyurl-tabcomplete/complete-tiny-url.pl
index def9440..e3100e4 100644
--- a/tinyurl-tabcomplete/complete-tiny-url.pl
+++ b/tinyurl-tabcomplete/complete-tiny-url.pl
@@ -2,7 +2,6 @@ use strict;
 use vars qw($VERSION %IRSSI);
 
 use Irssi;
-use Regexp::Common qw/URI/;
 use WWW::Shorten::TinyURL;
 
 $VERSION = '2.1';
@@ -17,13 +16,53 @@ $VERSION = '2.1';
 sub do_complete {
 	my ($strings, $window, $word, $linestart, $want_space) = @_;
 	return if $word eq '';
-    if ($word =~ m/$RE{URI}{HTTP}{-keep}/) {
-        my $uri = makeashorterlink($1);
+    if (defined (my $found_uri = match_uri($word))) {
+        my $uri = makeashorterlink($found_uri);
         push @$strings, $uri if $uri;
         $$want_space = 1;
         Irssi::signal_stop();
     }
 }
 
+sub match_uri {
+    my $text = shift;
+
+    my $regex = qr((?xi)
+\b
+(                           # Capture 1: entire matched URL
+  (?:
+    [a-z][\w-]+:                # URL protocol and colon
+    (?:
+      /{1,3}                        # 1-3 slashes
+      |                             #   or
+      [a-z0-9%]                     # Single letter or digit or '%'
+                                    # (Trying not to match e.g. "URI::Escape")
+    )
+    |                           #   or
+    www\d{0,3}[.]               # "www.", "www1.", "www2." … "www999."
+    |                           #   or
+    [a-z0-9.\-]+[.][a-z]{2,4}/  # looks like domain name followed by a slash
+  )
+  (?:                           # One or more:
+    [^\s()<>]+                      # Run of non-space, non-()<>
+    |                               #   or
+    \(([^\s()<>]+|(\([^\s()<>]+\)))*\)  # balanced parens, up to 2 levels
+  )+
+  (?:                           # End with:
+    \(([^\s()<>]+|(\([^\s()<>]+\)))*\)  # balanced parens, up to 2 levels
+    |                                   #   or
+    [^\s`!()\[\]{};:'".,<>?«»“”‘’]        # not a space or one of these punct chars
+  )
+));
+
+    if ($text =~ $regex) {
+        my $uri = $1;
+        $uri = 'http://' . $uri if $uri !~ m(http://);
+        return $uri;
+    } else {
+        return '';
+    }
+}
+
 Irssi::signal_add_first( 'complete word',  \&do_complete);
 
-- 
cgit v1.2.3