summaryrefslogtreecommitdiff
path: root/lib/util.php
diff options
context:
space:
mode:
authorEvan Prodromou <evan@controlyourself.ca>2009-08-25 18:01:46 -0400
committerEvan Prodromou <evan@controlyourself.ca>2009-08-25 18:01:46 -0400
commitd0baab6978f1959382d568d26cc9f8f552a7b764 (patch)
tree32bbe1148e86bb7846ae1f0e581c0f3c0f68956f /lib/util.php
parent077955cb1d45f866d65aebdc42f5e3e71dc74045 (diff)
parenta2117961be463d566c8f3c6ccd9b8e840f171804 (diff)
Merge branch '0.8.x' into testing
Diffstat (limited to 'lib/util.php')
-rw-r--r--lib/util.php90
1 files changed, 70 insertions, 20 deletions
diff --git a/lib/util.php b/lib/util.php
index 2be4213e7..7c1e21913 100644
--- a/lib/util.php
+++ b/lib/util.php
@@ -404,7 +404,7 @@ function common_render_text($text)
$r = preg_replace('/[\x{0}-\x{8}\x{b}-\x{c}\x{e}-\x{19}]/', '', $r);
$r = common_replace_urls_callback($r, 'common_linkify');
- $r = preg_replace('/(^|\(|\[|\s+)#([\pL\pN_\-\.]{1,64})/e', "'\\1#'.common_tag_link('\\2')", $r);
+ $r = preg_replace('/(^|\&quot\;|\'|\(|\[|\{|\s+)#([\pL\pN_\-\.]{1,64})/e', "'\\1#'.common_tag_link('\\2')", $r);
// XXX: machine tags
return $r;
}
@@ -412,44 +412,94 @@ function common_render_text($text)
function common_replace_urls_callback($text, $callback, $notice_id = null) {
// Start off with a regex
$regex = '#'.
- '(?:^|[\s\(\)\[\]\{\}]+)'.
- '('.
+ '(?:^|[\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):'.
- ')[^\s\/]+'.
+ '(?:(?:mailto|aim|tel|xmpp):)'.
+ ')'.
+ '(?:[\pN\pL\-\_\+]+(?::[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+ '(?:'.
+ '(?:'.
+ '\[[\pN\pL\-\_\:\.]+(?<![\.\:])\]'. //[dns]
+ ')|(?:'.
+ '[\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
- '\S+\.(?:museum|travel|onion|local|[a-z]{2,4})'.
- ')'.
+ '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+ '[\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|测试|XN--11B5BS3A9AJ6G|परीक्षा|XN--80AKHBYKNJ4F|испытание|XN--9T4B11YI5A|테스트|XN--DEBA0AD|טעסט|XN--G6W251D|測試|XN--HGBK6AJ7F53BBA|آزمایشی|XN--HLCJ6AYA9ESC7A|பரிட்சை|XN--JXALPDLP|δοκιμή|XN--KGBECHTV|إختبار|XN--ZCKZAH|テスト|YE|YT|YU|ZA|ZM|ZW|local|loc|onion)'.
+ ')(?![\pN\pL\-\_])'.
')'.
'(?:'.
- '$|(?:'.
- '/[^\s\(\)\[\]\{\}]*'.
- ')'.
- ')'.
+ '(?:\:\d+)?'. //:port
+ '(?:/[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;]*)?'. // /path
+ '(?:\?[\pN\pL\$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\/]*)?'. // ?query string
+ '(?:\#[\pN\pL$\[\]\,\!\(\)\.\-\_\+\/\=\&\;\/\?\#]*)?'. // #fragment
+ ')(?<![\?\.\,\#\,])'.
')'.
- '#ix';
+ '#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]);
- $left = substr($matches[0],0,$pos);
- $right = substr($matches[0],$pos+strlen($matches[1]));
+ $url=$matches['url'];
+ $left = strpos($matches[0],$url);
+ $right = $left+strlen($url);
+
+ $groupSymbolSets=array(
+ array(
+ 'left'=>'(',
+ 'right'=>')'
+ ),
+ array(
+ 'left'=>'[',
+ 'right'=>']'
+ ),
+ array(
+ 'left'=>'{',
+ 'right'=>'}'
+ )
+ );
+ $cannotEndWith=array('.','?',',','#');
+ $original_url=$url;
+ do{
+ $original_url=$url;
+ foreach($groupSymbolSets as $groupSymbolSet){
+ if(substr($url,-1)==$groupSymbolSet['right']){
+ $group_left_count = substr_count($url,$groupSymbolSet['left']);
+ $group_right_count = substr_count($url,$groupSymbolSet['right']);
+ if($group_left_count<$group_right_count){
+ $right-=1;
+ $url=substr($url,0,-1);
+ }
+ }
+ }
+ if(in_array(substr($url,-1),$cannotEndWith)){
+ $right-=1;
+ $url=substr($url,0,-1);
+ }
+ }while($original_url!=$url);
+
+
if(empty($notice_id)){
- $result = call_user_func_array($callback,$matches[1]);
+ $result = call_user_func_array($callback,$url);
}else{
- $result = call_user_func_array($callback, array($matches[1],$notice_id) );
+ $result = call_user_func_array($callback, array($url,$notice_id) );
}
- return $left . $result . $right;
+ return substr($matches[0],0,$left) . $result . substr($matches[0],$right);
}
function curry($fn) {