<?php
/*
- * Laconica - a distributed open-source microblogging tool
- * Copyright (C) 2008, 2009, Control Yourself, Inc.
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 2008, 2009, StatusNet, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
$language = common_language();
// So we don't have to make people install the gettext locales
$locale_set = common_init_locale($language);
- bindtextdomain("laconica", common_config('site','locale_path'));
- bind_textdomain_codeset("laconica", "UTF-8");
- textdomain("laconica");
+ bindtextdomain("statusnet", common_config('site','locale_path'));
+ bind_textdomain_codeset("statusnet", "UTF-8");
+ textdomain("statusnet");
setlocale(LC_CTYPE, 'C');
if(!$locale_set) {
- common_log(LOG_INFO,'Language requested:'.$language.' - locale could not be set:',__FILE__);
+ common_log(LOG_INFO, 'Language requested:' . $language . ' - locale could not be set. Perhaps that system locale is not installed.', __FILE__);
}
}
$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('/(^|\"\;|\'|\(|\[|\{|\s+)#([\pL\pN_\-\.]{1,64})/e', "'\\1#'.common_tag_link('\\2')", $r);
// XXX: machine tags
return $r;
}
function common_replace_urls_callback($text, $callback, $notice_id = null) {
// Start off with a regex
$regex = '#'.
- '(?:^|[\s\(\)\[\]\{\}]+)('.
- '(?:'. //Known protocols
- '(?:'.
- '(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://'.
- '|'.
- '(?:mailto|aim|tel|xmpp):'.
- ')[^\s\(\)\[\]\{\}]+'.
+ '(?:^|[\s\(\)\[\]\{\}\\\'\\\";]+)(?![\@\!\#])'.
+ '('.
+ '(?:'.
+ '(?:'. //Known protocols
+ '(?:'.
+ '(?:(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://)'.
+ '|'.
+ '(?:(?: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
+ '\[?(?:(?:(?:[0-9A-Fa-f]{1,4}:){7}(?:(?:[0-9A-Fa-f]{1,4})|:))|(?:(?:[0-9A-Fa-f]{1,4}:){6}(?::|(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})|(?::[0-9A-Fa-f]{1,4})))|(?:(?:[0-9A-Fa-f]{1,4}:){5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){4}(?::[0-9A-Fa-f]{1,4}){0,1}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){3}(?::[0-9A-Fa-f]{1,4}){0,2}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){2}(?::[0-9A-Fa-f]{1,4}){0,3}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:)(?::[0-9A-Fa-f]{1,4}){0,4}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?::(?::[0-9A-Fa-f]{1,4}){0,5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})))\]?(?<!:)'.
+ ')|(?:'. //DNS
+ '(?:[\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\-\_])'.
')'.
- '|(?:(?: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-f]{1,4}:){1,1}(?::[0-9a-f]{1,4}){1,6}|'.
- '(?:[0-9a-f]{1,4}:){1,2}(?::[0-9a-f]{1,4}){1,5}|'.
- '(?:[0-9a-f]{1,4}:){1,3}(?::[0-9a-f]{1,4}){1,4}|'.
- '(?:[0-9a-f]{1,4}:){1,4}(?::[0-9a-f]{1,4}){1,3}|'.
- '(?:[0-9a-f]{1,4}:){1,5}(?::[0-9a-f]{1,4}){1,2}|'.
- '(?:[0-9a-f]{1,4}:){1,6}(?::[0-9a-f]{1,4}){1,1}|'.
- '(?:(?:[0-9a-f]{1,4}:){1,7}|:):|'.
- ':(?::[0-9a-f]{1,4}){1,7}|'.
- '(?:(?:(?:[0-9a-f]{1,4}:){6})(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|'.
- '(?:(?:[0-9a-f]{1,4}:){5}[0-9a-f]{1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|'.
- '(?:[0-9a-f]{1,4}:){5}:[0-9a-f]{1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
- '(?:[0-9a-f]{1,4}:){1,1}(?::[0-9a-f]{1,4}){1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
- '(?:[0-9a-f]{1,4}:){1,2}(?::[0-9a-f]{1,4}){1,3}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
- '(?:[0-9a-f]{1,4}:){1,3}(?::[0-9a-f]{1,4}){1,2}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
- '(?:[0-9a-f]{1,4}:){1,4}(?::[0-9a-f]{1,4}){1,1}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
- '(?:(?:[0-9a-f]{1,4}:){1,5}|:):(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
- ':(?::[0-9a-f]{1,4}){1,5}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}'.
- ')|(?:'. //DNS
- '\S+\.(?:museum|travel|onion|local|[a-z]{2,4})'.
- ')'.
- '([^\s\(\)\[\]\{\}]*)'.
+ '(?:'.
+ '(?:\:\d+)?'. //:port
+ '(?:/[\pN\pL$\[\]\,\!\(\)\.\:\-\_\+\/\=\&\;\%\~\*\$\+\'\"@]*)?'. // /path
+ '(?:\?[\pN\pL\$\[\]\,\!\(\)\.\:\-\_\+\/\=\&\;\%\~\*\$\+\'\"@\/]*)?'. // ?query string
+ '(?:\#[\pN\pL$\[\]\,\!\(\)\.\:\-\_\+\/\=\&\;\%\~\*\$\+\'\"\@/\?\#]*)?'. // #fragment
+ ')(?<![\?\.\,\#\,])'.
')'.
- '#ix';
- return preg_replace_callback($regex, curry(callback_helper,$callback,$notice_id) ,$text);
+ '#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[1];
+ $left = strpos($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(array($url,$notice_id)) );
}
- return $left . $result . $right;
+ return substr($matches[0],0,$left) . $result . substr($matches[0],$right);
}
function curry($fn) {
array_shift($args);
$id = uniqid('_partial');
$GLOBALS[$id] = array($fn, $args);
- return create_function(
- '',
- '
- $args = func_get_args();
- return call_user_func_array(
- $GLOBALS["'.$id.'"][0],
- array_merge(
- $args,
- $GLOBALS["'.$id.'"][1]));
- ');
+ return create_function('',
+ '$args = func_get_args(); '.
+ 'return call_user_func_array('.
+ '$GLOBALS["'.$id.'"][0],'.
+ 'array_merge('.
+ '$args,'.
+ '$GLOBALS["'.$id.'"][1]));');
}
function common_linkify($url) {
// functions
$url = htmlspecialchars_decode($url);
- if(strpos($url, '@')!==false && strpos($url, ':')===false){
+ if(strpos($url, '@') !== false && strpos($url, ':') === false) {
//url is an email address without the mailto: protocol
return XMLStringer::estring('a', array('href' => "mailto:$url", 'rel' => 'external'), $url);
}
$attachment_id = null;
$has_thumb = false;
- // Check to see whether there's a filename associated with this URL.
- // If there is, it's an upload and qualifies as an attachment
+ // Check to see whether this is a known "attachment" URL.
- $localfile = File::staticGet('url', $longurl);
+ $f = File::staticGet('url', $longurl);
- if (!empty($localfile)) {
- if (isset($localfile->filename)) {
- $is_attachment = true;
- $attachment_id = $localfile->id;
- }
+ if (empty($f)) {
+ // XXX: this writes to the database. :<
+ $f = File::processNew($longurl);
}
- // if this URL is an attachment, then we set class='attachment' and id='attahcment-ID'
- // where ID is the id of the attachment for the given URL.
- //
- // we need a better test telling what can be shown as an attachment
- // we're currently picking up oembeds only.
- // I think the best option is another file_view table in the db
- // and associated dbobject.
-
- $query = "select file_oembed.file_id as file_id from file join file_oembed on file.id = file_oembed.file_id where file.url='$longurl'";
- $file = new File;
- $file->query($query);
- $file->fetch();
-
- if (!empty($file->file_id)) {
- $is_attachment = true;
- $attachment_id = $file->file_id;
-
- $query = "select file_thumbnail.file_id as file_id from file join file_thumbnail on file.id = file_thumbnail.file_id where file.url='$longurl'";
- $file2 = new File;
- $file2->query($query);
- $file2->fetch();
-
- if (!empty($file2)) {
- $has_thumb = true;
+ if (!empty($f)) {
+ if ($f->isEnclosure()) {
+ $is_attachment = true;
+ $attachment_id = $f->id;
+ } else {
+ $foe = File_oembed::staticGet('file_id', $f->id);
+ if (!empty($foe)) {
+ // if it has OEmbed info, it's an attachment, too
+ $is_attachment = true;
+ $attachment_id = $f->id;
+
+ $thumb = File_thumbnail::staticGet('file_id', $f->id);
+ if (!empty($thumb)) {
+ $has_thumb = true;
+ }
+ }
}
}
$base_key = common_keyize(common_config('site', 'name'));
}
- return 'laconica:' . $base_key . ':' . $extra;
+ return 'statusnet:' . $base_key . ':' . $extra;
}
function common_keyize($str)
$curlh = curl_init();
curl_setopt($curlh, CURLOPT_CONNECTTIMEOUT, 20); // # seconds to wait
- curl_setopt($curlh, CURLOPT_USERAGENT, 'Laconica');
+ curl_setopt($curlh, CURLOPT_USERAGENT, 'StatusNet');
curl_setopt($curlh, CURLOPT_RETURNTRANSFER, true);
switch($svc) {