From 210bc4248b5e0c8bd577ac51c2f8df9ac05166ae Mon Sep 17 00:00:00 2001
From: Craig Andrews <candrews@integralblue.com>
Date: Tue, 25 Aug 2009 14:12:31 -0400
Subject: [PATCH] All tests pass except for those that require matching parens
 or brackets

---
 lib/util.php               | 40 ++++++++++++++++++++++++--------------
 tests/URLDetectionTest.php | 13 ++++++++++---
 2 files changed, 35 insertions(+), 18 deletions(-)

diff --git a/lib/util.php b/lib/util.php
index ee3fe5ddcf..36d1e4c0ad 100644
--- a/lib/util.php
+++ b/lib/util.php
@@ -413,45 +413,55 @@ function common_replace_urls_callback($text, $callback, $notice_id = null) {
     // Start off with a regex
     $regex = '#'.
     '(?:^|[\s\(\)\[\]\{\}\\\'\\\";]+)(?![\@\!\#])'.
-    '('.
+    '(?P<url>'.
         '(?:'.
             '(?:'. //Known protocols
                 '(?:'.
-                    '(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://'.
+                    '(?:(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://)'.
                     '|'.
-                    '(?:mailto|aim|tel|xmpp):'.
+                    '(?:(?:mailto|aim|tel|xmpp):)'.
+                ')'.
+                '(?:[\pN\pL\-\_\+]+(?::[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+                '(?:'.
+                    '(?:'.
+                        '\[[\pN\pL\-\_\:\.]+(?<![\.\:])\]'. //[dns]
+                    ')|(?:'.
+                        '[\pN\pL\-\_\:\.]+(?<![\.\:])'. //dns
+                    ')'.
                 ')'.
-                '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
-                '[\pN\pL\-\_\:\.]+(?<![\.\:])'. //dns
             ')'.
             '|(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)'. //IPv4
             '|(?:'. //IPv6
-                '(?:(?:(?:[0-9A-Fa-f]{1,4}:){7}(?:(?:[0-9A-Fa-f]{1,4})|:))|(?:(?:[0-9A-Fa-f]{1,4}:){6}(?::|(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})|(?::[0-9A-Fa-f]{1,4})))|(?:(?:[0-9A-Fa-f]{1,4}:){5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){4}(?::[0-9A-Fa-f]{1,4}){0,1}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){3}(?::[0-9A-Fa-f]{1,4}){0,2}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){2}(?::[0-9A-Fa-f]{1,4}){0,3}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:)(?::[0-9A-Fa-f]{1,4}){0,4}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?::(?::[0-9A-Fa-f]{1,4}){0,5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})))'.
+                '\[?(?:(?:(?:[0-9A-Fa-f]{1,4}:){7}(?:(?:[0-9A-Fa-f]{1,4})|:))|(?:(?:[0-9A-Fa-f]{1,4}:){6}(?::|(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})|(?::[0-9A-Fa-f]{1,4})))|(?:(?:[0-9A-Fa-f]{1,4}:){5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){4}(?::[0-9A-Fa-f]{1,4}){0,1}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){3}(?::[0-9A-Fa-f]{1,4}){0,2}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){2}(?::[0-9A-Fa-f]{1,4}){0,3}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:)(?::[0-9A-Fa-f]{1,4}){0,4}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?::(?::[0-9A-Fa-f]{1,4}){0,5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})))\]?'.
             ')|(?:'. //DNS
                 '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
-                '[\pN\pL\-\_]+(?:\.[\pN\pL\-\_]+)*\.(?:museum|travel|onion|local|[a-z]{2,4})'.
+                '[\pN\pL\-\_]+(?:\.[\pN\pL\-\_]+)*\.'.
+                //tld list from http://data.iana.org/TLD/tlds-alpha-by-domain.txt, also added local, loc, and onion
+                '(?:AC|AD|AE|AERO|AF|AG|AI|AL|AM|AN|AO|AQ|AR|ARPA|AS|ASIA|AT|AU|AW|AX|AZ|BA|BB|BD|BE|BF|BG|BH|BI|BIZ|BJ|BM|BN|BO|BR|BS|BT|BV|BW|BY|BZ|CA|CAT|CC|CD|CF|CG|CH|CI|CK|CL|CM|CN|CO|COM|COOP|CR|CU|CV|CX|CY|CZ|DE|DJ|DK|DM|DO|DZ|EC|EDU|EE|EG|ER|ES|ET|EU|FI|FJ|FK|FM|FO|FR|GA|GB|GD|GE|GF|GG|GH|GI|GL|GM|GN|GOV|GP|GQ|GR|GS|GT|GU|GW|GY|HK|HM|HN|HR|HT|HU|ID|IE|IL|IM|IN|INFO|INT|IO|IQ|IR|IS|IT|JE|JM|JO|JOBS|JP|KE|KG|KH|KI|KM|KN|KP|KR|KW|KY|KZ|LA|LB|LC|LI|LK|LR|LS|LT|LU|LV|LY|MA|MC|MD|ME|MG|MH|MIL|MK|ML|MM|MN|MO|MOBI|MP|MQ|MR|MS|MT|MU|MUSEUM|MV|MW|MX|MY|MZ|NA|NAME|NC|NE|NET|NF|NG|NI|NL|NO|NP|NR|NU|NZ|OM|ORG|PA|PE|PF|PG|PH|PK|PL|PM|PN|PR|PRO|PS|PT|PW|PY|QA|RE|RO|RS|RU|RW|SA|SB|SC|SD|SE|SG|SH|SI|SJ|SK|SL|SM|SN|SO|SR|ST|SU|SV|SY|SZ|TC|TD|TEL|TF|TG|TH|TJ|TK|TL|TM|TN|TO|TP|TR|TRAVEL|TT|TV|TW|TZ|UA|UG|UK|US|UY|UZ|VA|VC|VE|VG|VI|VN|VU|WF|WS|XN--0ZWM56D|XN--11B5BS3A9AJ6G|XN--80AKHBYKNJ4F|XN--9T4B11YI5A|XN--DEBA0AD|XN--G6W251D|XN--HGBK6AJ7F53BBA|XN--HLCJ6AYA9ESC7A|XN--JXALPDLP|XN--KGBECHTV|XN--ZCKZAH|YE|YT|YU|ZA|ZM|ZW|local|loc|onion)'.
             ')(?![\pN\pL\-\_])'.
         ')'.
         '(?:'.
             '(?:\:\d+)?'. //:port
-            '(?:/[\pN\pL$\!\(\)\.\-\_\+\/\=\&\;]*)?'. // /path
-            '(?:\?[\pN\pL\$\!\(\)\.\-\_\+\/\=\&\;\/]*)?'. // ?query string
-            '(?:\#[\pN\pL$\!\(\)\.\-\_\+\/\=\&\;\/\?\#]*)?'. // #fragment
-        ')(?<![\?\.\,\#\)])'.
+            '(?:/[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;]*)?'. // /path
+            '(?:\?[\pN\pL\$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\/]*)?'. // ?query string
+            '(?:\#[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\/\?\#]*)?'. // #fragment
+        ')(?<![\?\.\,\#\)\]\,])'.
     ')'.
     '#ixu';
+    preg_match_all($regex,$text,$matches);
+    //print_r($matches);
     return preg_replace_callback($regex, curry(callback_helper,$callback,$notice_id) ,$text);
 }
 
 function callback_helper($matches, $callback, $notice_id) {
-    $pos = strpos($matches[0],$matches[1]);
+    $pos = strpos($matches[0],$matches['url']);
     $left = substr($matches[0],0,$pos);
-    $right = substr($matches[0],$pos+strlen($matches[1]));
+    $right = substr($matches[0],$pos+strlen($matches['url']));
     
     if(empty($notice_id)){
-        $result = call_user_func_array($callback,$matches[1]);
+        $result = call_user_func_array($callback,$matches['url']);
     }else{
-        $result = call_user_func_array($callback, array($matches[1],$notice_id) );
+        $result = call_user_func_array($callback, array($matches['url'],$notice_id) );
     }
     return $left . $result . $right;
 }
diff --git a/tests/URLDetectionTest.php b/tests/URLDetectionTest.php
index 05c02d6bb5..7b2e8c5ae7 100644
--- a/tests/URLDetectionTest.php
+++ b/tests/URLDetectionTest.php
@@ -25,16 +25,24 @@ class URLDetectionTest extends PHPUnit_Framework_TestCase
     static public function provider()
     {
         return array(
+                     array('http://127.0.0.1',
+                           '<a href="http://127.0.0.1/" rel="external">http://127.0.0.1</a>'),
                      array('127.0.0.1',
                            '<a href="http://127.0.0.1/" rel="external">127.0.0.1</a>'),
+                     array('127.0.0.1:99',
+                           '<a href="http://127.0.0.1:99/" rel="external">127.0.0.1:99</a>'),
                      array('127.0.0.1/test.php',
                            '<a href="http://127.0.0.1/test.php" rel="external">127.0.0.1/test.php</a>'),
+                     array('http://[::1]:99/test.php',
+                           '<a href="http://[::1]:99/test.php" rel="external">http://[::1]:99/test.php</a>'),
                      array('http://::1/test.php',
                            '<a href="http://::1/test.php" rel="external">http://::1/test.php</a>'),
                      array('http://::1',
                            '<a href="http://::1/" rel="external">http://::1</a>'),
                      array('2001:4978:1b5:0:21d:e0ff:fe66:59ab/test.php',
                            '<a href="http://2001:4978:1b5:0:21d:e0ff:fe66:59ab/test.php" rel="external">2001:4978:1b5:0:21d:e0ff:fe66:59ab/test.php</a>'),
+                     array('[2001:4978:1b5:0:21d:e0ff:fe66:59ab]:99/test.php',
+                           '<a href="http://[2001:4978:1b5:0:21d:e0ff:fe66:59ab]:99/test.php" rel="external">[2001:4978:1b5:0:21d:e0ff:fe66:59ab]:99/test.php</a>'),
                      array('2001:4978:1b5:0:21d:e0ff:fe66:59ab',
                            '<a href="http://2001:4978:1b5:0:21d:e0ff:fe66:59ab/" rel="external">2001:4978:1b5:0:21d:e0ff:fe66:59ab</a>'),
                      array('http://127.0.0.1',
@@ -145,14 +153,13 @@ class URLDetectionTest extends PHPUnit_Framework_TestCase
                            '&lt;<a href="http://example.com/" rel="external">http://example.com</a>&gt;'),
                      array('http://example.com/path/(foo)/bar',
                            '<a href="http://example.com/path/(foo)/bar" rel="external">http://example.com/path/(foo)/bar</a>'),
-                     //Not a valid url - urls cannot contain unencoded square brackets
                      array('http://example.com/path/[foo]/bar',
                            '<a href="http://example.com/path/[foo]/bar" rel="external">http://example.com/path/[foo]/bar</a>'),
                      array('http://example.com/path/foo/(bar)',
                            '<a href="http://example.com/path/foo/(bar)" rel="external">http://example.com/path/foo/(bar)</a>'),
                      //Not a valid url - urls cannot contain unencoded square brackets
-                     //array('http://example.com/path/foo/[bar]',
-                     //      '<a href="http://example.com/path/foo/[bar]" rel="external">http://example.com/path/foo/[bar]</a>'),
+                     array('http://example.com/path/foo/[bar]',
+                           '<a href="http://example.com/path/foo/[bar]" rel="external">http://example.com/path/foo/[bar]</a>'),
                      array('Hey, check out my cool site http://example.com okay?',
                            'Hey, check out my cool site <a href="http://example.com/" rel="external">http://example.com</a> okay?'),
                      array('What about parens (e.g. http://example.com/path/foo/(bar))?',