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);
119 * Check if this URL is a redirect and return redir info.
120 * If a File record is present for this URL, it is not considered a redirect.
121 * If a File_redirection record is present for this URL, the recorded target is returned.
123 * If no File or File_redirect record is present, the URL is hit and any
124 * redirects are followed, up to 10 levels or until a protected URL is
127 * @param string $in_url
128 * @return mixed one of:
129 * string - target URL, if this is a direct link or a known redirect
130 * array - redirect info if this is an *unknown* redirect:
131 * associative array with the following elements:
132 * code: HTTP status code
133 * redirects: count of redirects followed
134 * url: URL string of final target
135 * type (optional): MIME type from Content-Type header
136 * size (optional): byte size from Content-Length header
137 * time (optional): timestamp from Last-Modified header
139 function where($in_url) {
140 $ret = File_redirection::_redirectWhere_imp($in_url);
145 * Shorten a URL with the current user's configured shortening
146 * options, if applicable.
148 * If it cannot be shortened or the "short" URL is longer than the
149 * original, the original is returned.
151 * If the referenced item has not been seen before, embedding data
154 * @param string $long_url
157 function makeShort($long_url) {
159 $canon = File_redirection::_canonUrl($long_url);
161 $short_url = File_redirection::_userMakeShort($canon);
163 // Did we get one? Is it shorter?
164 if (!empty($short_url) && mb_strlen($short_url) < mb_strlen($long_url)) {
171 function _userMakeShort($long_url) {
172 $short_url = common_shorten_url($long_url);
173 if (!empty($short_url) && $short_url != $long_url) {
174 $short_url = (string)$short_url;
176 $file = File::staticGet('url', $long_url);
178 // Check if the target URL is itself a redirect...
179 $redir_data = File_redirection::where($long_url);
180 if (is_array($redir_data)) {
181 // We haven't seen the target URL before.
182 // Save file and embedding data about it!
183 $file = File::saveNew($redir_data, $long_url);
184 $file_id = $file->id;
185 if (!empty($redir_data['oembed']['json'])) {
186 File_oembed::saveNew($redir_data['oembed']['json'], $file_id);
188 } else if (is_string($redir_data)) {
189 // The file is a known redirect target.
190 $file = File::staticGet('url', $redir_data);
191 $file_id = $file->id;
194 $file_id = $file->id;
196 $file_redir = File_redirection::staticGet('url', $short_url);
197 if (empty($file_redir)) {
198 $file_redir = new File_redirection;
199 $file_redir->url = $short_url;
200 $file_redir->file_id = $file_id;
201 $file_redir->insert();
208 function _canonUrl($in_url, $default_scheme = 'http://') {
209 if (empty($in_url)) return false;
211 $p = parse_url($out_url);
212 if (empty($p['host']) || empty($p['scheme'])) {
213 list($scheme) = explode(':', $in_url, 2);
217 $out_url = str_replace('.-()', '', $out_url);
224 // don't touch anything
228 $out_url = $default_scheme . ltrim($out_url, '/');
229 $p = parse_url($out_url);
230 if (empty($p['scheme'])) return false;
235 if (('ftp' == $p['scheme']) || ('ftps' == $p['scheme']) || ('http' == $p['scheme']) || ('https' == $p['scheme'])) {
236 if (empty($p['host'])) return false;
237 if (empty($p['path'])) {
245 function saveNew($data, $file_id, $url) {
246 $file_redir = new File_redirection;
247 $file_redir->url = $url;
248 $file_redir->file_id = $file_id;
249 $file_redir->redirections = intval($data['redirects']);
250 $file_redir->httpcode = intval($data['code']);
251 $file_redir->insert();