3 * StatusNet - the distributed open-source microblogging tool
4 * Copyright (C) 2008, 2009, StatusNet, Inc.
6 * This program is free software: you can redistribute it and/or modify
7 * it under the terms of the GNU Affero General Public License as published by
8 * the Free Software Foundation, either version 3 of the License, or
9 * (at your option) any later version.
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU Affero General Public License for more details.
16 * You should have received a copy of the GNU Affero General Public License
17 * along with this program. If not, see <http://www.gnu.org/licenses/>.
20 if (!defined('STATUSNET') && !defined('LACONICA')) { exit(1); }
22 require_once INSTALLDIR.'/classes/Memcached_DataObject.php';
23 require_once INSTALLDIR.'/classes/File.php';
24 require_once INSTALLDIR.'/classes/File_oembed.php';
26 define('USER_AGENT', 'StatusNet user agent / file probe');
29 * Table Definition for file_redirection
32 class File_redirection extends Memcached_DataObject
35 /* the code below is auto generated do not remove the above tag */
37 public $__table = 'file_redirection'; // table name
38 public $url; // varchar(255) primary_key not_null
39 public $file_id; // int(4)
40 public $redirections; // int(4)
41 public $httpcode; // int(4)
42 public $modified; // timestamp() not_null default_CURRENT_TIMESTAMP
45 function staticGet($k,$v=NULL) { return Memcached_DataObject::staticGet('File_redirection',$k,$v); }
47 /* the code above is auto generated do not remove the tag below */
50 static function _commonHttp($url, $redirs) {
51 $request = new HTTPClient($url);
52 $request->setConfig(array(
53 'connect_timeout' => 10, // # seconds to wait
54 'max_redirs' => $redirs, // # max number of http redirections to follow
55 'follow_redirects' => true, // Follow redirects
56 'store_body' => false, // We won't need body content here.
61 function _redirectWhere_imp($short_url, $redirs = 10, $protected = false) {
62 if ($redirs < 0) return false;
64 // let's see if we know this...
65 $a = File::staticGet('url', $short_url);
68 // this is a direct link to $a->url
71 $b = File_redirection::staticGet('url', $short_url);
73 // this is a redirect to $b->file_id
74 $a = File::staticGet('id', $b->file_id);
79 if(strpos($short_url,'://') === false){
83 $request = self::_commonHttp($short_url, $redirs);
84 // Don't include body in output
85 $request->setMethod(HTTP_Request2::METHOD_HEAD);
86 $response = $request->send();
88 if (405 == $response->getStatus()) {
89 // Server doesn't support HEAD method? Can this really happen?
90 // We'll try again as a GET and ignore the response data.
91 $request = self::_commonHttp($short_url, $redirs);
92 $response = $request->send();
94 } catch (Exception $e) {
95 // Invalid URL or failure to reach server
99 if ($response->getRedirectCount() && File::isProtected($response->getUrl())) {
100 // Bump back up the redirect chain until we find a non-protected URL
101 return self::_redirectWhere_imp($short_url, $response->getRedirectCount() - 1, true);
104 $ret = array('code' => $response->getStatus()
105 , 'redirects' => $response->getRedirectCount()
106 , 'url' => $response->getUrl());
108 $type = $response->getHeader('Content-Type');
109 if ($type) $ret['type'] = $type;
110 if ($protected) $ret['protected'] = true;
111 $size = $response->getHeader('Content-Length'); // @fixme bytes?
112 if ($size) $ret['size'] = $size;
113 $time = $response->getHeader('Last-Modified');
114 if ($time) $ret['time'] = strtotime($time);
118 function where($in_url) {
119 $ret = File_redirection::_redirectWhere_imp($in_url);
123 function makeShort($long_url) {
125 $canon = File_redirection::_canonUrl($long_url);
127 $short_url = File_redirection::_userMakeShort($canon);
129 // Did we get one? Is it shorter?
130 if (!empty($short_url) && mb_strlen($short_url) < mb_strlen($long_url)) {
137 function _userMakeShort($long_url) {
138 $short_url = common_shorten_url($long_url);
139 if (!empty($short_url) && $short_url != $long_url) {
140 $short_url = (string)$short_url;
142 $file = File::staticGet('url', $long_url);
144 $redir_data = File_redirection::where($long_url);
145 $file = File::saveNew($redir_data, $long_url);
146 $file_id = $file->id;
147 if (!empty($redir_data['oembed']['json'])) {
148 File_oembed::saveNew($redir_data['oembed']['json'], $file_id);
151 $file_id = $file->id;
153 $file_redir = File_redirection::staticGet('url', $short_url);
154 if (empty($file_redir)) {
155 $file_redir = new File_redirection;
156 $file_redir->url = $short_url;
157 $file_redir->file_id = $file_id;
158 $file_redir->insert();
165 function _canonUrl($in_url, $default_scheme = 'http://') {
166 if (empty($in_url)) return false;
168 $p = parse_url($out_url);
169 if (empty($p['host']) || empty($p['scheme'])) {
170 list($scheme) = explode(':', $in_url, 2);
174 $out_url = str_replace('.-()', '', $out_url);
181 // don't touch anything
185 $out_url = $default_scheme . ltrim($out_url, '/');
186 $p = parse_url($out_url);
187 if (empty($p['scheme'])) return false;
192 if (('ftp' == $p['scheme']) || ('ftps' == $p['scheme']) || ('http' == $p['scheme']) || ('https' == $p['scheme'])) {
193 if (empty($p['host'])) return false;
194 if (empty($p['path'])) {
202 function saveNew($data, $file_id, $url) {
203 $file_redir = new File_redirection;
204 $file_redir->url = $url;
205 $file_redir->file_id = $file_id;
206 $file_redir->redirections = intval($data['redirects']);
207 $file_redir->httpcode = intval($data['code']);
208 $file_redir->insert();