summaryrefslogtreecommitdiff
path: root/lib/util.php
diff options
context:
space:
mode:
authorCraig Andrews <candrews@integralblue.com>2009-08-25 11:21:45 -0400
committerCraig Andrews <candrews@integralblue.com>2009-08-25 11:21:45 -0400
commit6a3a25b5a2b65e54841cc60c4f2254f6d7b6b54b (patch)
tree00e43400f3a117fe570a8c6bfe8a29b3333888c6 /lib/util.php
parent9ec39110201dc1b088786c8e31ca96847645d8bc (diff)
Improved the URL tests, and improve the matcher so more tests are passed. The remaining failing tests I believe are incorrect.
Diffstat (limited to 'lib/util.php')
-rw-r--r--lib/util.php24
1 files changed, 14 insertions, 10 deletions
diff --git a/lib/util.php b/lib/util.php
index 2be4213e7..ee3fe5ddc 100644
--- a/lib/util.php
+++ b/lib/util.php
@@ -412,30 +412,34 @@ function common_render_text($text)
function common_replace_urls_callback($text, $callback, $notice_id = null) {
// Start off with a regex
$regex = '#'.
- '(?:^|[\s\(\)\[\]\{\}]+)'.
- '('.
+ '(?:^|[\s\(\)\[\]\{\}\\\'\\\";]+)(?![\@\!\#])'.
+ '('.
'(?:'.
'(?:'. //Known protocols
'(?:'.
'(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://'.
'|'.
'(?:mailto|aim|tel|xmpp):'.
- ')[^\s\/]+'.
+ ')'.
+ '(?:[\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})))'.
')|(?:'. //DNS
- '\S+\.(?:museum|travel|onion|local|[a-z]{2,4})'.
- ')'.
+ '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+ '[\pN\pL\-\_]+(?:\.[\pN\pL\-\_]+)*\.(?:museum|travel|onion|local|[a-z]{2,4})'.
+ ')(?![\pN\pL\-\_])'.
')'.
'(?:'.
- '$|(?:'.
- '/[^\s\(\)\[\]\{\}]*'.
- ')'.
- ')'.
+ '(?:\:\d+)?'. //:port
+ '(?:/[\pN\pL$\!\(\)\.\-\_\+\/\=\&\;]*)?'. // /path
+ '(?:\?[\pN\pL\$\!\(\)\.\-\_\+\/\=\&\;\/]*)?'. // ?query string
+ '(?:\#[\pN\pL$\!\(\)\.\-\_\+\/\=\&\;\/\?\#]*)?'. // #fragment
+ ')(?<![\?\.\,\#\)])'.
')'.
- '#ix';
+ '#ixu';
return preg_replace_callback($regex, curry(callback_helper,$callback,$notice_id) ,$text);
}