diff options
| author | 2017-02-15 14:14:03 +0100 | |
|---|---|---|
| committer | 2017-02-15 14:14:03 +0100 | |
| commit | 5a1bb1393b4496eb35a2ffb3cc63d41c9dc1e2e5 (patch) | |
| tree | 67028e45792c575c25c92616633f64cc7a4a13eb /lib/SimplePie | |
| parent | 7e949d50320317b5c3b5a2da2bdaf324e794b2f7 (diff) | |
| parent | 5f637bd816b7323885bfe1751a1724ee59a822f6 (diff) | |
Merge remote-tracking branch 'FreshRSS/master'
Diffstat (limited to 'lib/SimplePie')
| -rw-r--r-- | lib/SimplePie/SimplePie.php | 214 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Cache/File.php | 12 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Content/Type/Sniffer.php | 15 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Decode/HTML/Entities.php | 1 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/File.php | 24 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Item.php | 43 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Locator.php | 2 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Misc.php | 20 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Parse/Date.php | 5 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Parser.php | 2 | ||||
| -rwxr-xr-x | lib/SimplePie/SimplePie/Registry.php | 4 | ||||
| -rw-r--r-- | lib/SimplePie/SimplePie/Sanitize.php | 80 |
12 files changed, 314 insertions, 108 deletions
diff --git a/lib/SimplePie/SimplePie.php b/lib/SimplePie/SimplePie.php index d7aaeb0c5..0f2fdbb87 100644 --- a/lib/SimplePie/SimplePie.php +++ b/lib/SimplePie/SimplePie.php @@ -75,6 +75,12 @@ define('SIMPLEPIE_USERAGENT', SIMPLEPIE_NAME . '/' . SIMPLEPIE_VERSION . ' (Feed define('SIMPLEPIE_LINKBACK', '<a href="' . SIMPLEPIE_URL . '" title="' . SIMPLEPIE_NAME . ' ' . SIMPLEPIE_VERSION . '">' . SIMPLEPIE_NAME . '</a>'); /** + * Use syslog to report HTTP requests done by SimplePie. + * @see SimplePie::set_syslog() + */ +define('SIMPLEPIE_SYSLOG', true); //FreshRSS + +/** * No Autodiscovery * @see SimplePie::set_autodiscovery_level() */ @@ -446,6 +452,13 @@ class SimplePie public $feed_url; /** + * @var string Original feed URL, or new feed URL iff HTTP 301 Moved Permanently + * @see SimplePie::subscribe_url() + * @access private + */ + public $permanent_url = null; + + /** * @var object Instance of SimplePie_File to use as a feed * @see SimplePie::set_file() * @access private @@ -467,6 +480,13 @@ class SimplePie public $timeout = 10; /** + * @var array Custom curl options + * @see SimplePie::set_curl_options() + * @access private + */ + public $curl_options = array(); + + /** * @var bool Forces fsockopen() to be used for remote files instead * of cURL, even if a new enough version is installed * @see SimplePie::force_fsockopen() @@ -616,6 +636,12 @@ class SimplePie public $strip_htmltags = array('base', 'blink', 'body', 'doctype', 'embed', 'font', 'form', 'frame', 'frameset', 'html', 'iframe', 'input', 'marquee', 'meta', 'noscript', 'object', 'param', 'script', 'style'); /** + * Use syslog to report HTTP requests done by SimplePie. + * @see SimplePie::set_syslog() + */ + public $syslog_enabled = SIMPLEPIE_SYSLOG; + + /** * The SimplePie class contains feed level data and options * * To use SimplePie, create the SimplePie object with no parameters. You can @@ -735,6 +761,7 @@ class SimplePie else { $this->feed_url = $this->registry->call('Misc', 'fix_protocol', array($url, 1)); + $this->permanent_url = $this->feed_url; } } @@ -749,6 +776,7 @@ class SimplePie if ($file instanceof SimplePie_File) { $this->feed_url = $file->url; + $this->permanent_url = $this->feed_url; $this->file =& $file; return true; } @@ -786,6 +814,19 @@ class SimplePie { $this->timeout = (int) $timeout; } + + /** + * Set custom curl options + * + * This allows you to change default curl options + * + * @since 1.0 Beta 3 + * @param array $curl_options Curl options to add to default settings + */ + public function set_curl_options(array $curl_options = array()) + { + $this->curl_options = $curl_options; + } /** * Force SimplePie to use fsockopen() instead of cURL @@ -1082,6 +1123,7 @@ class SimplePie $this->strip_attributes(false); $this->add_attributes(false); $this->set_image_handler(false); + $this->set_https_domains(array()); } } @@ -1127,7 +1169,7 @@ class SimplePie $this->sanitize->strip_attributes($attribs); } - public function add_attributes($attribs = '') + public function add_attributes($attribs = '') //FreshRSS { if ($attribs === '') { @@ -1137,6 +1179,14 @@ class SimplePie } /** + * Use syslog to report HTTP requests done by SimplePie. + */ + public function set_syslog($value = SIMPLEPIE_SYSLOG) //FreshRSS + { + $this->syslog_enabled = $value == true; + } + + /** * Set the output encoding * * Allows you to override SimplePie's output to match that of your webpage. @@ -1185,6 +1235,19 @@ class SimplePie } /** + * Set the list of domains for which force HTTPS. + * @see SimplePie_Sanitize::set_https_domains() + * FreshRSS + */ + public function set_https_domains($domains = array()) + { + if (is_array($domains)) + { + $this->sanitize->set_https_domains($domains); + } + } + + /** * Set the handler to enable the display of cached images. * * @param str $page Web-accessible path to the handler_image.php file. @@ -1222,7 +1285,8 @@ class SimplePie $this->enable_exceptions = $enable; } - function cleanMd5($rss) { //FreshRSS + function cleanMd5($rss) + { return md5(preg_replace(array('#<(lastBuildDate|pubDate|updated|feedDate|dc:date|slash:comments)>[^<]+</\\1>#', '#<!--.+?-->#s'), '', $rss)); } @@ -1240,6 +1304,7 @@ class SimplePie // Check absolute bare minimum requirements. if (!extension_loaded('xml') || !extension_loaded('pcre')) { + $this->error = 'XML or PCRE extensions not loaded!'; return false; } // Then check the xml extension is sane (i.e., libxml 2.7.x issue on PHP < 5.2.9 and libxml 2.7.0 to 2.7.2 on any version) if we don't have xmlreader. @@ -1267,7 +1332,7 @@ class SimplePie // Pass whatever was set with config options over to the sanitizer. // Pass the classes in for legacy support; new classes should use the registry instead $this->sanitize->pass_cache_data($this->cache, $this->cache_location, $this->cache_name_function, $this->registry->get_class('Cache')); - $this->sanitize->pass_file_data($this->registry->get_class('File'), $this->timeout, $this->useragent, $this->force_fsockopen); + $this->sanitize->pass_file_data($this->registry->get_class('File'), $this->timeout, $this->useragent, $this->force_fsockopen, $this->curl_options); if (!empty($this->multifeed_url)) { @@ -1312,7 +1377,7 @@ class SimplePie // Fetch the data via SimplePie_File into $this->raw_data if (($fetched = $this->fetch_data($cache)) === true) { - return $this->data['mtime']; //FreshRSS + return $this->data['mtime']; } elseif ($fetched === false) { return false; @@ -1320,7 +1385,8 @@ class SimplePie list($headers, $sniffed) = $fetched; - if (isset($this->data['md5'])) { //FreshRSS + if (isset($this->data['md5'])) + { $md5 = $this->data['md5']; } } @@ -1331,7 +1397,7 @@ class SimplePie // First check to see if input has been overridden. if ($this->input_encoding !== false) { - $encodings[] = strtoupper($this->input_encoding); //FreshRSS + $encodings[] = strtoupper($this->input_encoding); } $application_types = array('application/xml', 'application/xml-dtd', 'application/xml-external-parsed-entity'); @@ -1355,7 +1421,7 @@ class SimplePie { if (isset($headers['content-type']) && preg_match('/;\x20?charset=([^;]*)/i', $headers['content-type'], $charset)) { - $encodings[] = strtoupper($charset[1]); //FreshRSS + $encodings[] = strtoupper($charset[1]); } else { @@ -1404,8 +1470,8 @@ class SimplePie $this->data['headers'] = $headers; } $this->data['build'] = SIMPLEPIE_BUILD; - $this->data['mtime'] = time(); //FreshRSS - $this->data['md5'] = empty($md5) ? $this->cleanMd5($this->raw_data) : $md5; //FreshRSS + $this->data['mtime'] = time(); + $this->data['md5'] = empty($md5) ? $this->cleanMd5($this->raw_data) : $md5; // Cache the file if caching is enabled if ($cache && !$cache->save($this)) @@ -1420,7 +1486,7 @@ class SimplePie if (isset($parser)) { // We have an error, just set SimplePie_Misc::error to it and quit - $this->error = sprintf('This XML document is invalid, likely due to invalid characters. XML error: %s at line %d, column %d', $parser->get_error_string(), $parser->get_current_line(), $parser->get_current_column()); + $this->error = sprintf('This XML document is invalid, likely due to invalid characters. XML error: %s at line %d, column %d, encoding %s, URL: %s', $parser->get_error_string(), $parser->get_current_line(), $parser->get_current_column(), $encoding, $this->feed_url); } else { @@ -1446,7 +1512,12 @@ class SimplePie { // Load the Cache $this->data = $cache->load(); - if (!empty($this->data)) + if ($cache->mtime() + $this->cache_duration > time()) + { + $this->raw_data = false; + return true; // If the cache is still valid, just return true + } + elseif (!empty($this->data)) { // If the cache is for an outdated build of SimplePie if (!isset($this->data['build']) || $this->data['build'] !== SIMPLEPIE_BUILD) @@ -1478,63 +1549,58 @@ class SimplePie } } // Check if the cache has been updated - elseif ($cache->mtime() + $this->cache_duration < time()) + else { - // If we have last-modified and/or etag set - //if (isset($this->data['headers']['last-modified']) || isset($this->data['headers']['etag'])) //FreshRSS removed + $headers = array( + 'Accept' => 'application/atom+xml, application/rss+xml, application/rdf+xml;q=0.9, application/xml;q=0.8, text/xml;q=0.8, text/html;q=0.7, unknown/unknown;q=0.1, application/unknown;q=0.1, */*;q=0.1', + ); + if (isset($this->data['headers']['last-modified'])) { - $headers = array( - 'Accept' => 'application/atom+xml, application/rss+xml, application/rdf+xml;q=0.9, application/xml;q=0.8, text/xml;q=0.8, text/html;q=0.7, unknown/unknown;q=0.1, application/unknown;q=0.1, */*;q=0.1', - ); - if (isset($this->data['headers']['last-modified'])) - { - $headers['if-modified-since'] = $this->data['headers']['last-modified']; - } - if (isset($this->data['headers']['etag'])) - { - $headers['if-none-match'] = $this->data['headers']['etag']; - } + $headers['if-modified-since'] = $this->data['headers']['last-modified']; + } + if (isset($this->data['headers']['etag'])) + { + $headers['if-none-match'] = $this->data['headers']['etag']; + } - $file = $this->registry->create('File', array($this->feed_url, $this->timeout, 5, $headers, $this->useragent, $this->force_fsockopen)); //FreshRSS + $file = $this->registry->create('File', array($this->feed_url, $this->timeout, 5, $headers, $this->useragent, $this->force_fsockopen, $this->curl_options)); - if ($file->success) + if ($file->success) + { + if ($file->status_code === 304) { - if ($file->status_code === 304) - { - $cache->touch(); - return true; - } + $cache->touch(); + return true; } - else + } + else + { + $cache->touch(); + $this->error = $file->error; + return !empty($this->data); + } + + $md5 = $this->cleanMd5($file->body); + if ($this->data['md5'] === $md5) { + if ($this->syslog_enabled) { - $this->error = $file->error; //FreshRSS - return !empty($this->data); //FreshRSS - //unset($file); //FreshRSS removed + syslog(LOG_DEBUG, 'SimplePie MD5 cache match for ' . SimplePie_Misc::url_remove_credentials($this->feed_url)); } - } - { //FreshRSS - $md5 = $this->cleanMd5($file->body); - if ($this->data['md5'] === $md5) { - syslog(LOG_DEBUG, 'SimplePie MD5 cache match for ' . $this->feed_url); - $cache->touch(); - return true; //Content unchanged even though server did not send a 304 - } else { - syslog(LOG_DEBUG, 'SimplePie MD5 cache no match for ' . $this->feed_url); - $this->data['md5'] = $md5; + $cache->touch(); + return true; //Content unchanged even though server did not send a 304 + } else { + if ($this->syslog_enabled) + { + syslog(LOG_DEBUG, 'SimplePie MD5 cache no match for ' . SimplePie_Misc::url_remove_credentials($this->feed_url)); } + $this->data['md5'] = $md5; } } - // If the cache is still valid, just return true - else - { - $this->raw_data = false; - return true; - } } - // If the cache is empty, delete it + // If the cache is empty else { - $cache->unlink(); + $cache->touch(); //To keep the date/time of the last tentative update $this->data = array(); } } @@ -1550,7 +1616,7 @@ class SimplePie $headers = array( 'Accept' => 'application/atom+xml, application/rss+xml, application/rdf+xml;q=0.9, application/xml;q=0.8, text/xml;q=0.8, text/html;q=0.7, unknown/unknown;q=0.1, application/unknown;q=0.1, */*;q=0.1', ); - $file = $this->registry->create('File', array($this->feed_url, $this->timeout, 5, $headers, $this->useragent, $this->force_fsockopen)); + $file = $this->registry->create('File', array($this->feed_url, $this->timeout, 5, $headers, $this->useragent, $this->force_fsockopen, $this->curl_options)); } } // If the file connection has an error, set SimplePie::error to that and quit @@ -1567,13 +1633,15 @@ class SimplePie if (!$locate->is_feed($file)) { + $copyStatusCode = $file->status_code; + $copyContentType = $file->headers['content-type']; // We need to unset this so that if SimplePie::set_file() has been called that object is untouched unset($file); try { if (!($file = $locate->find($this->autodiscovery, $this->all_discovered_feeds))) { - $this->error = "A feed could not be found at $this->feed_url. A feed with an invalid mime type may fall victim to this error, or " . SIMPLEPIE_NAME . " was unable to auto-discover it.. Use force_feed() if you are certain this URL is a real feed."; + $this->error = "A feed could not be found at `$this->feed_url`; the status code is `$copyStatusCode` and content-type is `$copyContentType`"; $this->registry->call('Misc', 'error', array($this->error, E_USER_NOTICE, __FILE__, __LINE__)); return false; } @@ -1588,8 +1656,8 @@ class SimplePie if ($cache) { $this->data = array('url' => $this->feed_url, 'feed_url' => $file->url, 'build' => SIMPLEPIE_BUILD); - $this->data['mtime'] = time(); //FreshRSS - $this->data['md5'] = empty($md5) ? $this->cleanMd5($file->body) : $md5; //FreshRSS + $this->data['mtime'] = time(); + $this->data['md5'] = empty($md5) ? $this->cleanMd5($file->body) : $md5; if (!$cache->save($this)) { trigger_error("$this->cache_location is not writeable. Make sure you've set the correct relative or absolute path, and that the location is server-writable.", E_USER_WARNING); @@ -1601,8 +1669,9 @@ class SimplePie $locate = null; } + $file->body = trim($file->body); $this->raw_data = $file->body; - + $this->permanent_url = $file->permanent_url; $headers = $file->headers; $sniffer = $this->registry->create('Content_Type_Sniffer', array(&$file)); $sniffed = $sniffer->get_type(); @@ -1788,26 +1857,39 @@ class SimplePie /** * Get the URL for the feed + * + * When the 'permanent' mode is enabled, returns the original feed URL, + * except in the case of an `HTTP 301 Moved Permanently` status response, + * in which case the location of the first redirection is returned. * - * May or may not be different from the URL passed to {@see set_feed_url()}, + * When the 'permanent' mode is disabled (default), + * may or may not be different from the URL passed to {@see set_feed_url()}, * depending on whether auto-discovery was used. * * @since Preview Release (previously called `get_feed_url()` since SimplePie 0.8.) - * @todo If we have a perm redirect we should return the new URL - * @todo When we make the above change, let's support <itunes:new-feed-url> as well + * @todo Support <itunes:new-feed-url> * @todo Also, |atom:link|@rel=self + * @param bool $permanent Permanent mode to return only the original URL or the first redirection + * iff it is a 301 redirection * @return string|null */ - public function subscribe_url() + public function subscribe_url($permanent = false) { - if ($this->feed_url !== null) + if ($permanent) { - return $this->sanitize($this->feed_url, SIMPLEPIE_CONSTRUCT_IRI); + if ($this->permanent_url !== null) + { + return $this->sanitize($this->permanent_url, SIMPLEPIE_CONSTRUCT_IRI); + } } else { - return null; + if ($this->feed_url !== null) + { + return $this->sanitize($this->feed_url, SIMPLEPIE_CONSTRUCT_IRI); + } } + return null; } /** diff --git a/lib/SimplePie/SimplePie/Cache/File.php b/lib/SimplePie/SimplePie/Cache/File.php index 3b163545b..72e75a4b6 100644 --- a/lib/SimplePie/SimplePie/Cache/File.php +++ b/lib/SimplePie/SimplePie/Cache/File.php @@ -136,11 +136,7 @@ class SimplePie_Cache_File implements SimplePie_Cache_Base */ public function mtime() { - if (file_exists($this->name)) - { - return filemtime($this->name); - } - return false; + return @filemtime($this->name); } /** @@ -150,11 +146,7 @@ class SimplePie_Cache_File implements SimplePie_Cache_Base */ public function touch() { - if (file_exists($this->name)) - { - return touch($this->name); - } - return false; + return @touch($this->name); } /** diff --git a/lib/SimplePie/SimplePie/Content/Type/Sniffer.php b/lib/SimplePie/SimplePie/Content/Type/Sniffer.php index a32f47f59..ec0bf0952 100644 --- a/lib/SimplePie/SimplePie/Content/Type/Sniffer.php +++ b/lib/SimplePie/SimplePie/Content/Type/Sniffer.php @@ -109,9 +109,7 @@ class SimplePie_Content_Type_Sniffer { return $this->unknown(); } - elseif (substr($official, -4) === '+xml' - || $official === 'text/xml' - || $official === 'application/xml') + elseif (substr($official, -4) === '+xml') { return $official; } @@ -126,7 +124,9 @@ class SimplePie_Content_Type_Sniffer return $official; } } - elseif ($official === 'text/html') + elseif ($official === 'text/html' + || $official === 'text/xml' + || $official === 'application/xml') { return $this->feed_or_html(); } @@ -256,7 +256,12 @@ class SimplePie_Content_Type_Sniffer public function feed_or_html() { $len = strlen($this->file->body); - $pos = strspn($this->file->body, "\x09\x0A\x0D\x20"); + $pos = 0; + if (isset($this->file->body[2]) && $this->file->body[0] === "\xEF" && + $this->file->body[1] === "\xBB" && $this->file->body[2] === "\xBF") { + $pos += 3; //UTF-8 BOM + } + $pos += strspn($this->file->body, "\x09\x0A\x0D\x20", $pos); while ($pos < $len) { diff --git a/lib/SimplePie/SimplePie/Decode/HTML/Entities.php b/lib/SimplePie/SimplePie/Decode/HTML/Entities.php index cde06c884..46b3a1dff 100644 --- a/lib/SimplePie/SimplePie/Decode/HTML/Entities.php +++ b/lib/SimplePie/SimplePie/Decode/HTML/Entities.php @@ -169,7 +169,6 @@ class SimplePie_Decode_HTML_Entities case "\x09": case "\x0A": case "\x0B": - case "\x0B": case "\x0C": case "\x20": case "\x3C": diff --git a/lib/SimplePie/SimplePie/File.php b/lib/SimplePie/SimplePie/File.php index faf5dd1f1..45994d102 100644 --- a/lib/SimplePie/SimplePie/File.php +++ b/lib/SimplePie/SimplePie/File.php @@ -64,8 +64,9 @@ class SimplePie_File var $redirects = 0; var $error; var $method = SIMPLEPIE_FILE_SOURCE_NONE; + var $permanent_url; //FreshRSS - public function __construct($url, $timeout = 10, $redirects = 5, $headers = null, $useragent = null, $force_fsockopen = false) + public function __construct($url, $timeout = 10, $redirects = 5, $headers = null, $useragent = null, $force_fsockopen = false, $curl_options = array(), $syslog_enabled = SIMPLEPIE_SYSLOG) { if (class_exists('idna_convert')) { @@ -74,10 +75,14 @@ class SimplePie_File $url = SimplePie_Misc::compress_parse_url($parsed['scheme'], $idn->encode($parsed['authority']), $parsed['path'], $parsed['query'], $parsed['fragment']); } $this->url = $url; + $this->permanent_url = $url; $this->useragent = $useragent; if (preg_match('/^http(s)?:\/\//i', $url)) { - syslog(LOG_INFO, 'SimplePie GET ' . $url); //FreshRSS + if ($syslog_enabled) + { + syslog(LOG_INFO, 'SimplePie GET ' . SimplePie_Misc::url_remove_credentials($url)); //FreshRSS + } if ($useragent === null) { $useragent = ini_get('user_agent'); @@ -108,12 +113,15 @@ class SimplePie_File curl_setopt($fp, CURLOPT_REFERER, $url); curl_setopt($fp, CURLOPT_USERAGENT, $useragent); curl_setopt($fp, CURLOPT_HTTPHEADER, $headers2); - curl_setopt($fp, CURLOPT_SSL_VERIFYPEER, false); //FreshRSS if (!ini_get('open_basedir') && !ini_get('safe_mode') && version_compare(SimplePie_Misc::get_curl_version(), '7.15.2', '>=')) { curl_setopt($fp, CURLOPT_FOLLOWLOCATION, 1); curl_setopt($fp, CURLOPT_MAXREDIRS, $redirects); } + foreach ($curl_options as $curl_param => $curl_value) + { + curl_setopt($fp, $curl_param, $curl_value); + } $this->headers = curl_exec($fp); if (curl_errno($fp) === 23 || curl_errno($fp) === 61) @@ -142,7 +150,10 @@ class SimplePie_File { $this->redirects++; $location = SimplePie_Misc::absolutize_url($this->headers['location'], $url); - return $this->__construct($location, $timeout, $redirects, $headers, $useragent, $force_fsockopen); + $previousStatusCode = $this->status_code; + $this->__construct($location, $timeout, $redirects, $headers, $useragent, $force_fsockopen); + $this->permanent_url = ($previousStatusCode == 301) ? $location : $url; + return; } } } @@ -224,7 +235,10 @@ class SimplePie_File { $this->redirects++; $location = SimplePie_Misc::absolutize_url($this->headers['location'], $url); - return $this->__construct($location, $timeout, $redirects, $headers, $useragent, $force_fsockopen); + $previousStatusCode = $this->status_code; + $this->__construct($location, $timeout, $redirects, $headers, $useragent, $force_fsockopen); + $this->permanent_url = ($previousStatusCode == 301) ? $location : $url; //FreshRSS + return; } if (isset($this->headers['content-encoding'])) { diff --git a/lib/SimplePie/SimplePie/Item.php b/lib/SimplePie/SimplePie/Item.php index 7bd96c15f..19ba7c8f4 100644 --- a/lib/SimplePie/SimplePie/Item.php +++ b/lib/SimplePie/SimplePie/Item.php @@ -406,6 +406,30 @@ class SimplePie_Item return null; } } + + /** + * Get the media:thumbnail of the item + * + * Uses `<media:thumbnail>` + * + * + * @return array|null + */ + public function get_thumbnail() + { + if (!isset($this->data['thumbnail'])) + { + if ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_MEDIARSS, 'thumbnail')) + { + $this->data['thumbnail'] = $return[0]['attribs']['']; + } + else + { + $this->data['thumbnail'] = null; + } + } + return $this->data['thumbnail']; + } /** * Get a category for the item @@ -738,31 +762,31 @@ class SimplePie_Item { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'updated')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'pubDate')) { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'issued')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_DC_11, 'date')) { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'created')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_DC_10, 'date')) { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'modified')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'updated')) { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'pubDate')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'issued')) { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_DC_11, 'date')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'created')) { $this->data['date']['raw'] = $return[0]['data']; } - elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_DC_10, 'date')) + elseif ($return = $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'modified')) { $this->data['date']['raw'] = $return[0]['data']; } @@ -2733,7 +2757,9 @@ class SimplePie_Item { foreach ($content['child'][SIMPLEPIE_NAMESPACE_MEDIARSS]['thumbnail'] as $thumbnail) { - $thumbnails[] = $this->sanitize($thumbnail['attribs']['']['url'], SIMPLEPIE_CONSTRUCT_IRI); + if (isset($thumbnail['attribs']['']['url'])) { + $thumbnails[] = $this->sanitize($thumbnail['attribs']['']['url'], SIMPLEPIE_CONSTRUCT_IRI); + } } if (is_array($thumbnails)) { @@ -2851,6 +2877,7 @@ class SimplePie_Item $width = null; $url = $this->sanitize($enclosure[0]['attribs']['']['url'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($enclosure[0])); + $url = $this->feed->sanitize->https_url($url); //FreshRSS if (isset($enclosure[0]['attribs']['']['type'])) { $type = $this->sanitize($enclosure[0]['attribs']['']['type'], SIMPLEPIE_CONSTRUCT_TEXT); diff --git a/lib/SimplePie/SimplePie/Locator.php b/lib/SimplePie/SimplePie/Locator.php index 90ee7a302..ba4a843b0 100644 --- a/lib/SimplePie/SimplePie/Locator.php +++ b/lib/SimplePie/SimplePie/Locator.php @@ -148,7 +148,7 @@ class SimplePie_Locator { $sniffer = $this->registry->create('Content_Type_Sniffer', array($file)); $sniffed = $sniffer->get_type(); - if (in_array($sniffed, array('application/rss+xml', 'application/rdf+xml', 'text/rdf', 'application/atom+xml', 'text/xml', 'application/xml'))) + if (in_array($sniffed, array('application/rss+xml', 'application/rdf+xml', 'text/rdf', 'application/atom+xml', 'text/xml', 'application/xml', 'application/x-rss+xml'))) { return true; } diff --git a/lib/SimplePie/SimplePie/Misc.php b/lib/SimplePie/SimplePie/Misc.php index 5a263a2e5..2d154cbcb 100644 --- a/lib/SimplePie/SimplePie/Misc.php +++ b/lib/SimplePie/SimplePie/Misc.php @@ -79,9 +79,9 @@ class SimplePie_Misc public static function absolutize_url($relative, $base) { - if (substr($relative, 0, 2) === '//') //FreshRSS: disable absolutize_url for "//www.example.net" which will pick HTTP or HTTPS automatically - { - return $relative; + if (substr($relative, 0, 2) === '//') + {//Protocol-relative URLs "//www.example.net" + return 'https:' . $relative; } $iri = SimplePie_IRI::absolutize(new SimplePie_IRI($base), $relative); if ($iri === false) @@ -128,7 +128,7 @@ class SimplePie_Misc { $attribs[$j][2] = $attribs[$j][1]; } - $return[$i]['attribs'][strtolower($attribs[$j][1])]['data'] = SimplePie_Misc::entities_decode(end($attribs[$j]), 'UTF-8'); //FreshRSS + $return[$i]['attribs'][strtolower($attribs[$j][1])]['data'] = SimplePie_Misc::entities_decode(end($attribs[$j]), 'UTF-8'); } } } @@ -142,7 +142,7 @@ class SimplePie_Misc foreach ($element['attribs'] as $key => $value) { $key = strtolower($key); - $full .= " $key=\"" . htmlspecialchars($value['data'], ENT_COMPAT, 'UTF-8') . '"'; //FreshRSS + $full .= " $key=\"" . htmlspecialchars($value['data'], ENT_COMPAT, 'UTF-8') . '"'; } if ($element['self_closing']) { @@ -2240,5 +2240,15 @@ function embed_wmedia(width, height, link) { { // No-op } + + /** + * Sanitize a URL by removing HTTP credentials. + * @param $url the URL to sanitize. + * @return the same URL without HTTP credentials. + */ + public static function url_remove_credentials($url) //FreshRSS + { + return preg_replace('#^(https?://)[^/:@]+:[^/:@]+@#i', '$1', $url); + } } diff --git a/lib/SimplePie/SimplePie/Parse/Date.php b/lib/SimplePie/SimplePie/Parse/Date.php index ef800f125..50bb5cffa 100644 --- a/lib/SimplePie/SimplePie/Parse/Date.php +++ b/lib/SimplePie/SimplePie/Parse/Date.php @@ -173,7 +173,7 @@ class SimplePie_Parse_Date 'aug' => 8, 'august' => 8, 'sep' => 9, - 'september' => 8, + 'september' => 9, 'oct' => 10, 'october' => 10, 'nov' => 11, @@ -332,6 +332,7 @@ class SimplePie_Parse_Date 'CDT' => -18000, 'CEDT' => 7200, 'CET' => 3600, + 'CEST' => 7200, 'CGST' => -7200, 'CGT' => -10800, 'CHADT' => 49500, @@ -720,7 +721,7 @@ class SimplePie_Parse_Date { $output .= substr($string, $position, $pos - $position); $position = $pos + 1; - if ($string[$pos - 1] !== '\\') + if ($pos === 0 || $string[$pos - 1] !== '\\') { $depth++; while ($depth && $position < $length) diff --git a/lib/SimplePie/SimplePie/Parser.php b/lib/SimplePie/SimplePie/Parser.php index 9300b4ba9..7fb7bd9be 100644 --- a/lib/SimplePie/SimplePie/Parser.php +++ b/lib/SimplePie/SimplePie/Parser.php @@ -142,7 +142,7 @@ class SimplePie_Parser $dom = new DOMDocument(); $dom->recover = true; $dom->strictErrorChecking = false; - $dom->loadXML($data); + @$dom->loadXML($data); $this->encoding = $encoding = $dom->encoding = 'UTF-8'; $data2 = $dom->saveXML(); if (function_exists('mb_convert_encoding')) diff --git a/lib/SimplePie/SimplePie/Registry.php b/lib/SimplePie/SimplePie/Registry.php index bd9c1f535..dac55e34e 100755 --- a/lib/SimplePie/SimplePie/Registry.php +++ b/lib/SimplePie/SimplePie/Registry.php @@ -113,7 +113,7 @@ class SimplePie_Registry */ public function register($type, $class, $legacy = false) { - if (!is_subclass_of($class, $this->default[$type])) + if (!@is_subclass_of($class, $this->default[$type])) { return false; } @@ -222,4 +222,4 @@ class SimplePie_Registry $result = call_user_func_array(array($class, $method), $parameters); return $result; } -}
\ No newline at end of file +} diff --git a/lib/SimplePie/SimplePie/Sanitize.php b/lib/SimplePie/SimplePie/Sanitize.php index 168a5e2e8..bdc601100 100644 --- a/lib/SimplePie/SimplePie/Sanitize.php +++ b/lib/SimplePie/SimplePie/Sanitize.php @@ -73,6 +73,15 @@ class SimplePie_Sanitize var $force_fsockopen = false; var $replace_url_attributes = null; + /** + * List of domains for which force HTTPS. + * @see SimplePie_Sanitize::set_https_domains() + * Array is tree split at DNS levels. Example: + * array('biz' => true, 'com' => array('example' => true), 'net' => array('example') => array('www' => true)) + * FreshRSS + */ + var $https_domains = array('com' => array('dailymotion' => true, 'youtube' => true)); + public function __construct() { // Set defaults @@ -242,6 +251,71 @@ class SimplePie_Sanitize $this->replace_url_attributes = (array) $element_attribute; } + /** + * Set the list of domains for which force HTTPS. + * @see SimplePie_Misc::https_url() + * Example array('biz', 'example.com', 'example.org', 'www.example.net'); + * FreshRSS + */ + public function set_https_domains($domains) + { + $this->https_domains = array(); + foreach ($domains as $domain) + { + $domain = trim($domain, ". \t\n\r\0\x0B"); + $segments = array_reverse(explode('.', $domain)); + $node =& $this->https_domains; + foreach ($segments as $segment) + {//Build a tree + if ($node === true) + { + break; + } + if (!isset($node[$segment])) + { + $node[$segment] = array(); + } + $node =& $node[$segment]; + } + $node = true; + } + } + + /** + * Check if the domain is in the list of forced HTTPS + * FreshRSS + */ + protected function is_https_domain($domain) + { + $domain = trim($domain, '. '); + $segments = array_reverse(explode('.', $domain)); + $node =& $this->https_domains; + foreach ($segments as $segment) + {//Explore the tree + if (isset($node[$segment])) + { + $node =& $node[$segment]; + } + else + { + break; + } + } + return $node === true; + } + + /** + * Force HTTPS for selected Web sites + * FreshRSS + */ + public function https_url($url) + { + return (strtolower(substr($url, 0, 7)) === 'http://') && + $this->is_https_domain(parse_url($url, PHP_URL_HOST)) ? + substr_replace($url, 's', 4, 0) : //Add the 's' to HTTPS + $url; + } + public function sanitize($data, $type, $base = '') { $data = trim($data); @@ -249,6 +323,7 @@ class SimplePie_Sanitize { if ($type & SIMPLEPIE_CONSTRUCT_MAYBE_HTML) { + $data = htmlspecialchars_decode($data, ENT_QUOTES); if (preg_match('/(&(#(x[0-9a-fA-F]+|[0-9]+)|[a-zA-Z0-9]+)|<\/[A-Za-z][^\x09\x0A\x0B\x0C\x0D\x20\x2F\x3E]*' . SIMPLEPIE_PCRE_HTML_ATTRIBUTE . '>)/', $data)) { $type |= SIMPLEPIE_CONSTRUCT_HTML; @@ -279,7 +354,7 @@ class SimplePie_Sanitize $document->loadHTML($data); restore_error_handler(); - $xpath = new DOMXPath($document); //FreshRSS + $xpath = new DOMXPath($document); // Strip comments if ($this->strip_comments) @@ -450,7 +525,8 @@ class SimplePie_Sanitize if ($element->hasAttribute($attribute)) { $value = $this->registry->call('Misc', 'absolutize_url', array($element->getAttribute($attribute), $this->base)); - if ($value !== false) + $value = $this->https_url($value); //FreshRSS + if ($value) { $element->setAttribute($attribute, $value); } |
