+ * Cookies are stored like this: + * [domain][path][name] = array + * where array is: + * 0 => value, 1 => secure, 2 => expires + *+ * @var array + * @access private + */ + public $cookies = array(); + public $debug = false; + + /** + * Constructor + */ + function __construct() { + } + + protected function debug($msg, $file=null, $line=null) { + if ($this->debug) { + $mem = round(memory_get_usage()/1024, 2); + $memPeak = round(memory_get_peak_usage()/1024, 2); + echo '* ',$msg; + if (isset($file, $line)) echo " ($file line $line)"; + echo ' - mem used: ',$mem," (peak: $memPeak)\n"; + ob_flush(); + flush(); + } + } + + /** + * Get matching cookies + * + * Only use this method if you cannot use add_cookie_header(), for example, if you want to use + * this cookie jar class without using the request class. + * + * @param array $param associative array containing 'domain', 'path', 'secure' keys + * @return string + * @see add_cookie_header() + */ + public function getMatchingCookies($url) + { + if (($parts = @parse_url($url)) && isset($parts['scheme'], $parts['host'], $parts['path'])) { + $param['domain'] = $parts['host']; + $param['path'] = $parts['path']; + $param['secure'] = (strtolower($parts['scheme']) == 'https'); + unset($parts); + } else { + return false; + } + // RFC 2965 notes: + // If multiple cookies satisfy the criteria above, they are ordered in + // the Cookie header such that those with more specific Path attributes + // precede those with less specific. Ordering with respect to other + // attributes (e.g., Domain) is unspecified. + $domain = $param['domain']; + if (strpos($domain, '.') === false) $domain .= '.local'; + $request_path = $param['path']; + if ($request_path == '') $request_path = '/'; + $request_secure = $param['secure']; + $now = time(); + $matched_cookies = array(); + // domain - find matching domains + $this->debug('Finding matching domains for '.$domain, __FILE__, __LINE__); + while (strpos($domain, '.') !== false) { + if (isset($this->cookies[$domain])) { + $this->debug(' domain match found: '.$domain); + $cookies =& $this->cookies[$domain]; + } else { + $domain = $this->_reduce_domain($domain); + continue; + } + // paths - find matching paths starting from most specific + $this->debug(' - Finding matching paths for '.$request_path); + $paths = array_keys($cookies); + usort($paths, array($this, '_cmp_length')); + foreach ($paths as $path) { + // continue to next cookie if request path does not path-match cookie path + if (!$this->_path_match($request_path, $path)) continue; + // loop through cookie names + $this->debug(' path match found: '.$path); + foreach ($cookies[$path] as $name => $values) { + // if this cookie is secure but request isn't, continue to next cookie + if ($values[1] && !$request_secure) continue; + // if cookie is not a session cookie and has expired, continue to next cookie + if (is_int($values[2]) && ($values[2] < $now)) continue; + // cookie matches request + $this->debug(' cookie match: '.$name.'='.$values[0]); + $matched_cookies[] = $name.'='.$values[0]; + } + } + $domain = $this->_reduce_domain($domain); + } + // return cookies + return implode('; ', $matched_cookies); + } + + /** + * Parse Set-Cookie values. + * + * Only use this method if you cannot use extract_cookies(), for example, if you want to use + * this cookie jar class without using the response class. + * + * @param array $set_cookies array holding 1 or more "Set-Cookie" header values + * @param array $param associative array containing 'host', 'path' keys + * @return void + * @see extract_cookies() + */ + public function storeCookies($url, $set_cookies) + { + if (count($set_cookies) == 0) return; + $param = @parse_url($url); + if (!is_array($param) || !isset($param['host'])) return; + $request_host = $param['host']; + if (strpos($request_host, '.') === false) $request_host .= '.local'; + $request_path = @$param['path']; + if ($request_path == '') $request_path = '/'; + // + // loop through set-cookie headers + // + foreach ($set_cookies as $set_cookie) { + $this->debug('Parsing: '.$set_cookie); + // temporary cookie store (before adding to jar) + $tmp_cookie = array(); + $param = explode(';', $set_cookie); + // loop through params + for ($x=0; $x
', $data);
+ }
+ }
+
+ if ($type & (SIMPLEPIE_CONSTRUCT_HTML | SIMPLEPIE_CONSTRUCT_XHTML))
+ {
+ // Strip comments
+ if ($this->strip_comments)
+ {
+ $data = SimplePie_Misc::strip_comments($data);
+ }
+
+ // Strip out HTML tags and attributes that might cause various security problems.
+ // Based on recommendations by Mark Pilgrim at:
+ // http://diveintomark.org/archives/2003/06/12/how_to_consume_rss_safely
+ if ($this->strip_htmltags)
+ {
+ foreach ($this->strip_htmltags as $tag)
+ {
+ $pcre = "/<($tag)" . SIMPLEPIE_PCRE_HTML_ATTRIBUTE . "(>(.*)<\/$tag" . SIMPLEPIE_PCRE_HTML_ATTRIBUTE . '>|(\/)?>)/siU';
+ while (preg_match($pcre, $data))
+ {
+ $data = preg_replace_callback($pcre, array(&$this, 'do_strip_htmltags'), $data);
+ }
+ }
+ }
+
+ if ($this->strip_attributes)
+ {
+ foreach ($this->strip_attributes as $attrib)
+ {
+ $data = preg_replace('/(<[A-Za-z][^\x09\x0A\x0B\x0C\x0D\x20\x2F\x3E]*)' . SIMPLEPIE_PCRE_HTML_ATTRIBUTE . trim($attrib) . '(?:\s*=\s*(?:"(?:[^"]*)"|\'(?:[^\']*)\'|(?:[^\x09\x0A\x0B\x0C\x0D\x20\x22\x27\x3E][^\x09\x0A\x0B\x0C\x0D\x20\x3E]*)?))?' . SIMPLEPIE_PCRE_HTML_ATTRIBUTE . '>/', '\1\2\3>', $data);
+ }
+ }
+
+ // Replace relative URLs
+ $this->base = $base;
+ foreach ($this->replace_url_attributes as $element => $attributes)
+ {
+ $data = $this->replace_urls($data, $element, $attributes);
+ }
+
+ // If image handling (caching, etc.) is enabled, cache and rewrite all the image tags.
+ if (isset($this->image_handler) && ((string) $this->image_handler) !== '' && $this->enable_cache)
+ {
+ $images = SimplePie_Misc::get_element('img', $data);
+ foreach ($images as $img)
+ {
+ if (isset($img['attribs']['src']['data']))
+ {
+ $image_url = call_user_func($this->cache_name_function, $img['attribs']['src']['data']);
+ $cache = call_user_func(array($this->cache_class, 'create'), $this->cache_location, $image_url, 'spi');
+
+ if ($cache->load())
+ {
+ $img['attribs']['src']['data'] = $this->image_handler . $image_url;
+ $data = str_replace($img['full'], SimplePie_Misc::element_implode($img), $data);
+ }
+ else
+ {
+ $file = new $this->file_class($img['attribs']['src']['data'], $this->timeout, 5, array('X-FORWARDED-FOR' => $_SERVER['REMOTE_ADDR']), $this->useragent, $this->force_fsockopen);
+ $headers = $file->headers;
+
+ if ($file->success && ($file->method & SIMPLEPIE_FILE_SOURCE_REMOTE === 0 || ($file->status_code === 200 || $file->status_code > 206 && $file->status_code < 300)))
+ {
+ if ($cache->save(array('headers' => $file->headers, 'body' => $file->body)))
+ {
+ $img['attribs']['src']['data'] = $this->image_handler . $image_url;
+ $data = str_replace($img['full'], SimplePie_Misc::element_implode($img), $data);
+ }
+ else
+ {
+ trigger_error("$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);
+ }
+ }
+ }
+ }
+ }
+ }
+
+ // Having (possibly) taken stuff out, there may now be whitespace at the beginning/end of the data
+ $data = trim($data);
+ }
+
+ if ($type & SIMPLEPIE_CONSTRUCT_IRI)
+ {
+ $data = SimplePie_Misc::absolutize_url($data, $base);
+ }
+
+ if ($type & (SIMPLEPIE_CONSTRUCT_TEXT | SIMPLEPIE_CONSTRUCT_IRI))
+ {
+ $data = htmlspecialchars($data, ENT_COMPAT, 'UTF-8');
+ }
+
+ if ($this->output_encoding !== 'UTF-8')
+ {
+ $data = SimplePie_Misc::change_encoding($data, 'UTF-8', $this->output_encoding);
+ }
+ }
+ return $data;
+ }
+
+ public function replace_urls($data, $tag, $attributes)
+ {
+ if (!is_array($this->strip_htmltags) || !in_array($tag, $this->strip_htmltags))
+ {
+ $elements = SimplePie_Misc::get_element($tag, $data);
+ foreach ($elements as $element)
+ {
+ if (is_array($attributes))
+ {
+ foreach ($attributes as $attribute)
+ {
+ if (isset($element['attribs'][$attribute]['data']))
+ {
+ $element['attribs'][$attribute]['data'] = SimplePie_Misc::absolutize_url($element['attribs'][$attribute]['data'], $this->base);
+ $new_element = SimplePie_Misc::element_implode($element);
+ $data = str_replace($element['full'], $new_element, $data);
+ $element['full'] = $new_element;
+ }
+ }
+ }
+ elseif (isset($element['attribs'][$attributes]['data']))
+ {
+ $element['attribs'][$attributes]['data'] = SimplePie_Misc::absolutize_url($element['attribs'][$attributes]['data'], $this->base);
+ $data = str_replace($element['full'], SimplePie_Misc::element_implode($element), $data);
+ }
+ }
+ }
+ return $data;
+ }
+
+ public function do_strip_htmltags($match)
+ {
+ if ($this->encode_instead_of_strip)
+ {
+ if (isset($match[4]) && !in_array(strtolower($match[1]), array('script', 'style')))
+ {
+ $match[1] = htmlspecialchars($match[1], ENT_COMPAT, 'UTF-8');
+ $match[2] = htmlspecialchars($match[2], ENT_COMPAT, 'UTF-8');
+ return "<$match[1]$match[2]>$match[3]</$match[1]>";
+ }
+ else
+ {
+ return htmlspecialchars($match[0], ENT_COMPAT, 'UTF-8');
+ }
+ }
+ elseif (isset($match[4]) && !in_array(strtolower($match[1]), array('script', 'style')))
+ {
+ return $match[4];
+ }
+ else
+ {
+ return '';
+ }
+ }
+}
diff --git a/inc/3rdparty/simplepie/SimplePie/Source.php b/inc/3rdparty/simplepie/SimplePie/Source.php
new file mode 100644
index 0000000..a6605c1
--- /dev/null
+++ b/inc/3rdparty/simplepie/SimplePie/Source.php
@@ -0,0 +1,597 @@
+item = $item;
+ $this->data = $data;
+ }
+
+ public function __toString()
+ {
+ return md5(serialize($this->data));
+ }
+
+ public function get_source_tags($namespace, $tag)
+ {
+ if (isset($this->data['child'][$namespace][$tag]))
+ {
+ return $this->data['child'][$namespace][$tag];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_base($element = array())
+ {
+ return $this->item->get_base($element);
+ }
+
+ public function sanitize($data, $type, $base = '')
+ {
+ return $this->item->sanitize($data, $type, $base);
+ }
+
+ public function get_item()
+ {
+ return $this->item;
+ }
+
+ public function get_title()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SimplePie_Misc::atom_10_construct_type($return[0]['attribs']), $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SimplePie_Misc::atom_03_construct_type($return[0]['attribs']), $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_10, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_MAYBE_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_090, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_MAYBE_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_MAYBE_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_11, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_10, 'title'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_category($key = 0)
+ {
+ $categories = $this->get_categories();
+ if (isset($categories[$key]))
+ {
+ return $categories[$key];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_categories()
+ {
+ $categories = array();
+
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'category') as $category)
+ {
+ $term = null;
+ $scheme = null;
+ $label = null;
+ if (isset($category['attribs']['']['term']))
+ {
+ $term = $this->sanitize($category['attribs']['']['term'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if (isset($category['attribs']['']['scheme']))
+ {
+ $scheme = $this->sanitize($category['attribs']['']['scheme'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if (isset($category['attribs']['']['label']))
+ {
+ $label = $this->sanitize($category['attribs']['']['label'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ $categories[] = new $this->item->feed->category_class($term, $scheme, $label);
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'category') as $category)
+ {
+ // This is really the label, but keep this as the term also for BC.
+ // Label will also work on retrieving because that falls back to term.
+ $term = $this->sanitize($category['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ if (isset($category['attribs']['']['domain']))
+ {
+ $scheme = $this->sanitize($category['attribs']['']['domain'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ else
+ {
+ $scheme = null;
+ }
+ $categories[] = new $this->item->feed->category_class($term, $scheme, null);
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_11, 'subject') as $category)
+ {
+ $categories[] = new $this->item->feed->category_class($this->sanitize($category['data'], SIMPLEPIE_CONSTRUCT_TEXT), null, null);
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_10, 'subject') as $category)
+ {
+ $categories[] = new $this->item->feed->category_class($this->sanitize($category['data'], SIMPLEPIE_CONSTRUCT_TEXT), null, null);
+ }
+
+ if (!empty($categories))
+ {
+ return SimplePie_Misc::array_unique($categories);
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_author($key = 0)
+ {
+ $authors = $this->get_authors();
+ if (isset($authors[$key]))
+ {
+ return $authors[$key];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_authors()
+ {
+ $authors = array();
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'author') as $author)
+ {
+ $name = null;
+ $uri = null;
+ $email = null;
+ if (isset($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data']))
+ {
+ $name = $this->sanitize($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if (isset($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data']))
+ {
+ $uri = $this->sanitize($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]));
+ }
+ if (isset($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['email'][0]['data']))
+ {
+ $email = $this->sanitize($author['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['email'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if ($name !== null || $email !== null || $uri !== null)
+ {
+ $authors[] = new $this->item->feed->author_class($name, $uri, $email);
+ }
+ }
+ if ($author = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'author'))
+ {
+ $name = null;
+ $url = null;
+ $email = null;
+ if (isset($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['name'][0]['data']))
+ {
+ $name = $this->sanitize($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['name'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if (isset($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['url'][0]['data']))
+ {
+ $url = $this->sanitize($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['url'][0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['url'][0]));
+ }
+ if (isset($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['email'][0]['data']))
+ {
+ $email = $this->sanitize($author[0]['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['email'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if ($name !== null || $email !== null || $url !== null)
+ {
+ $authors[] = new $this->item->feed->author_class($name, $url, $email);
+ }
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_11, 'creator') as $author)
+ {
+ $authors[] = new $this->item->feed->author_class($this->sanitize($author['data'], SIMPLEPIE_CONSTRUCT_TEXT), null, null);
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_10, 'creator') as $author)
+ {
+ $authors[] = new $this->item->feed->author_class($this->sanitize($author['data'], SIMPLEPIE_CONSTRUCT_TEXT), null, null);
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_ITUNES, 'author') as $author)
+ {
+ $authors[] = new $this->item->feed->author_class($this->sanitize($author['data'], SIMPLEPIE_CONSTRUCT_TEXT), null, null);
+ }
+
+ if (!empty($authors))
+ {
+ return SimplePie_Misc::array_unique($authors);
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_contributor($key = 0)
+ {
+ $contributors = $this->get_contributors();
+ if (isset($contributors[$key]))
+ {
+ return $contributors[$key];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_contributors()
+ {
+ $contributors = array();
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'contributor') as $contributor)
+ {
+ $name = null;
+ $uri = null;
+ $email = null;
+ if (isset($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data']))
+ {
+ $name = $this->sanitize($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['name'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if (isset($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data']))
+ {
+ $uri = $this->sanitize($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['uri'][0]));
+ }
+ if (isset($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['email'][0]['data']))
+ {
+ $email = $this->sanitize($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_10]['email'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if ($name !== null || $email !== null || $uri !== null)
+ {
+ $contributors[] = new $this->item->feed->author_class($name, $uri, $email);
+ }
+ }
+ foreach ((array) $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'contributor') as $contributor)
+ {
+ $name = null;
+ $url = null;
+ $email = null;
+ if (isset($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['name'][0]['data']))
+ {
+ $name = $this->sanitize($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['name'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if (isset($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['url'][0]['data']))
+ {
+ $url = $this->sanitize($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['url'][0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['url'][0]));
+ }
+ if (isset($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['email'][0]['data']))
+ {
+ $email = $this->sanitize($contributor['child'][SIMPLEPIE_NAMESPACE_ATOM_03]['email'][0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ if ($name !== null || $email !== null || $url !== null)
+ {
+ $contributors[] = new $this->item->feed->author_class($name, $url, $email);
+ }
+ }
+
+ if (!empty($contributors))
+ {
+ return SimplePie_Misc::array_unique($contributors);
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_link($key = 0, $rel = 'alternate')
+ {
+ $links = $this->get_links($rel);
+ if (isset($links[$key]))
+ {
+ return $links[$key];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ /**
+ * Added for parity between the parent-level and the item/entry-level.
+ */
+ public function get_permalink()
+ {
+ return $this->get_link(0);
+ }
+
+ public function get_links($rel = 'alternate')
+ {
+ if (!isset($this->data['links']))
+ {
+ $this->data['links'] = array();
+ if ($links = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'link'))
+ {
+ foreach ($links as $link)
+ {
+ if (isset($link['attribs']['']['href']))
+ {
+ $link_rel = (isset($link['attribs']['']['rel'])) ? $link['attribs']['']['rel'] : 'alternate';
+ $this->data['links'][$link_rel][] = $this->sanitize($link['attribs']['']['href'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($link));
+ }
+ }
+ }
+ if ($links = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'link'))
+ {
+ foreach ($links as $link)
+ {
+ if (isset($link['attribs']['']['href']))
+ {
+ $link_rel = (isset($link['attribs']['']['rel'])) ? $link['attribs']['']['rel'] : 'alternate';
+ $this->data['links'][$link_rel][] = $this->sanitize($link['attribs']['']['href'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($link));
+
+ }
+ }
+ }
+ if ($links = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_10, 'link'))
+ {
+ $this->data['links']['alternate'][] = $this->sanitize($links[0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($links[0]));
+ }
+ if ($links = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_090, 'link'))
+ {
+ $this->data['links']['alternate'][] = $this->sanitize($links[0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($links[0]));
+ }
+ if ($links = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'link'))
+ {
+ $this->data['links']['alternate'][] = $this->sanitize($links[0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($links[0]));
+ }
+
+ $keys = array_keys($this->data['links']);
+ foreach ($keys as $key)
+ {
+ if (SimplePie_Misc::is_isegment_nz_nc($key))
+ {
+ if (isset($this->data['links'][SIMPLEPIE_IANA_LINK_RELATIONS_REGISTRY . $key]))
+ {
+ $this->data['links'][SIMPLEPIE_IANA_LINK_RELATIONS_REGISTRY . $key] = array_merge($this->data['links'][$key], $this->data['links'][SIMPLEPIE_IANA_LINK_RELATIONS_REGISTRY . $key]);
+ $this->data['links'][$key] =& $this->data['links'][SIMPLEPIE_IANA_LINK_RELATIONS_REGISTRY . $key];
+ }
+ else
+ {
+ $this->data['links'][SIMPLEPIE_IANA_LINK_RELATIONS_REGISTRY . $key] =& $this->data['links'][$key];
+ }
+ }
+ elseif (substr($key, 0, 41) === SIMPLEPIE_IANA_LINK_RELATIONS_REGISTRY)
+ {
+ $this->data['links'][substr($key, 41)] =& $this->data['links'][$key];
+ }
+ $this->data['links'][$key] = array_unique($this->data['links'][$key]);
+ }
+ }
+
+ if (isset($this->data['links'][$rel]))
+ {
+ return $this->data['links'][$rel];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_description()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'subtitle'))
+ {
+ return $this->sanitize($return[0]['data'], SimplePie_Misc::atom_10_construct_type($return[0]['attribs']), $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'tagline'))
+ {
+ return $this->sanitize($return[0]['data'], SimplePie_Misc::atom_03_construct_type($return[0]['attribs']), $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_10, 'description'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_MAYBE_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_090, 'description'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_MAYBE_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'description'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_MAYBE_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_11, 'description'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_10, 'description'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ITUNES, 'summary'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_HTML, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ITUNES, 'subtitle'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_HTML, $this->get_base($return[0]));
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_copyright()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'rights'))
+ {
+ return $this->sanitize($return[0]['data'], SimplePie_Misc::atom_10_construct_type($return[0]['attribs']), $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_03, 'copyright'))
+ {
+ return $this->sanitize($return[0]['data'], SimplePie_Misc::atom_03_construct_type($return[0]['attribs']), $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'copyright'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_11, 'rights'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_10, 'rights'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_language()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_RSS_20, 'language'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_11, 'language'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_DC_10, 'language'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ elseif (isset($this->data['xml_lang']))
+ {
+ return $this->sanitize($this->data['xml_lang'], SIMPLEPIE_CONSTRUCT_TEXT);
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_latitude()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_W3C_BASIC_GEO, 'lat'))
+ {
+ return (float) $return[0]['data'];
+ }
+ elseif (($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_GEORSS, 'point')) && preg_match('/^((?:-)?[0-9]+(?:\.[0-9]+)) ((?:-)?[0-9]+(?:\.[0-9]+))$/', trim($return[0]['data']), $match))
+ {
+ return (float) $match[1];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_longitude()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_W3C_BASIC_GEO, 'long'))
+ {
+ return (float) $return[0]['data'];
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_W3C_BASIC_GEO, 'lon'))
+ {
+ return (float) $return[0]['data'];
+ }
+ elseif (($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_GEORSS, 'point')) && preg_match('/^((?:-)?[0-9]+(?:\.[0-9]+)) ((?:-)?[0-9]+(?:\.[0-9]+))$/', trim($return[0]['data']), $match))
+ {
+ return (float) $match[2];
+ }
+ else
+ {
+ return null;
+ }
+ }
+
+ public function get_image_url()
+ {
+ if ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ITUNES, 'image'))
+ {
+ return $this->sanitize($return[0]['attribs']['']['href'], SIMPLEPIE_CONSTRUCT_IRI);
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'logo'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($return[0]));
+ }
+ elseif ($return = $this->get_source_tags(SIMPLEPIE_NAMESPACE_ATOM_10, 'icon'))
+ {
+ return $this->sanitize($return[0]['data'], SIMPLEPIE_CONSTRUCT_IRI, $this->get_base($return[0]));
+ }
+ else
+ {
+ return null;
+ }
+ }
+}
+
diff --git a/inc/3rdparty/simplepie/SimplePie/XML/Declaration/Parser.php b/inc/3rdparty/simplepie/SimplePie/XML/Declaration/Parser.php
new file mode 100644
index 0000000..b7ebc6f
--- /dev/null
+++ b/inc/3rdparty/simplepie/SimplePie/XML/Declaration/Parser.php
@@ -0,0 +1,362 @@
+data = $data;
+ $this->data_length = strlen($this->data);
+ }
+
+ /**
+ * Parse the input data
+ *
+ * @access public
+ * @return bool true on success, false on failure
+ */
+ public function parse()
+ {
+ while ($this->state && $this->state !== 'emit' && $this->has_data())
+ {
+ $state = $this->state;
+ $this->$state();
+ }
+ $this->data = '';
+ if ($this->state === 'emit')
+ {
+ return true;
+ }
+ else
+ {
+ $this->version = '';
+ $this->encoding = '';
+ $this->standalone = '';
+ return false;
+ }
+ }
+
+ /**
+ * Check whether there is data beyond the pointer
+ *
+ * @access private
+ * @return bool true if there is further data, false if not
+ */
+ public function has_data()
+ {
+ return (bool) ($this->position < $this->data_length);
+ }
+
+ /**
+ * Advance past any whitespace
+ *
+ * @return int Number of whitespace characters passed
+ */
+ public function skip_whitespace()
+ {
+ $whitespace = strspn($this->data, "\x09\x0A\x0D\x20", $this->position);
+ $this->position += $whitespace;
+ return $whitespace;
+ }
+
+ /**
+ * Read value
+ */
+ public function get_value()
+ {
+ $quote = substr($this->data, $this->position, 1);
+ if ($quote === '"' || $quote === "'")
+ {
+ $this->position++;
+ $len = strcspn($this->data, $quote, $this->position);
+ if ($this->has_data())
+ {
+ $value = substr($this->data, $this->position, $len);
+ $this->position += $len + 1;
+ return $value;
+ }
+ }
+ return false;
+ }
+
+ public function before_version_name()
+ {
+ if ($this->skip_whitespace())
+ {
+ $this->state = 'version_name';
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function version_name()
+ {
+ if (substr($this->data, $this->position, 7) === 'version')
+ {
+ $this->position += 7;
+ $this->skip_whitespace();
+ $this->state = 'version_equals';
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function version_equals()
+ {
+ if (substr($this->data, $this->position, 1) === '=')
+ {
+ $this->position++;
+ $this->skip_whitespace();
+ $this->state = 'version_value';
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function version_value()
+ {
+ if ($this->version = $this->get_value())
+ {
+ $this->skip_whitespace();
+ if ($this->has_data())
+ {
+ $this->state = 'encoding_name';
+ }
+ else
+ {
+ $this->state = 'emit';
+ }
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function encoding_name()
+ {
+ if (substr($this->data, $this->position, 8) === 'encoding')
+ {
+ $this->position += 8;
+ $this->skip_whitespace();
+ $this->state = 'encoding_equals';
+ }
+ else
+ {
+ $this->state = 'standalone_name';
+ }
+ }
+
+ public function encoding_equals()
+ {
+ if (substr($this->data, $this->position, 1) === '=')
+ {
+ $this->position++;
+ $this->skip_whitespace();
+ $this->state = 'encoding_value';
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function encoding_value()
+ {
+ if ($this->encoding = $this->get_value())
+ {
+ $this->skip_whitespace();
+ if ($this->has_data())
+ {
+ $this->state = 'standalone_name';
+ }
+ else
+ {
+ $this->state = 'emit';
+ }
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function standalone_name()
+ {
+ if (substr($this->data, $this->position, 10) === 'standalone')
+ {
+ $this->position += 10;
+ $this->skip_whitespace();
+ $this->state = 'standalone_equals';
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function standalone_equals()
+ {
+ if (substr($this->data, $this->position, 1) === '=')
+ {
+ $this->position++;
+ $this->skip_whitespace();
+ $this->state = 'standalone_value';
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+
+ public function standalone_value()
+ {
+ if ($standalone = $this->get_value())
+ {
+ switch ($standalone)
+ {
+ case 'yes':
+ $this->standalone = true;
+ break;
+
+ case 'no':
+ $this->standalone = false;
+ break;
+
+ default:
+ $this->state = false;
+ return;
+ }
+
+ $this->skip_whitespace();
+ if ($this->has_data())
+ {
+ $this->state = false;
+ }
+ else
+ {
+ $this->state = 'emit';
+ }
+ }
+ else
+ {
+ $this->state = false;
+ }
+ }
+}
diff --git a/inc/3rdparty/simplepie/SimplePie/gzdecode.php b/inc/3rdparty/simplepie/SimplePie/gzdecode.php
new file mode 100644
index 0000000..ddbd517
--- /dev/null
+++ b/inc/3rdparty/simplepie/SimplePie/gzdecode.php
@@ -0,0 +1,355 @@
+compressed_data = $data;
+ $this->compressed_size = strlen($data);
+ }
+
+ /**
+ * Decode the GZIP stream
+ *
+ * @access public
+ */
+ public function parse()
+ {
+ if ($this->compressed_size >= $this->min_compressed_size)
+ {
+ // Check ID1, ID2, and CM
+ if (substr($this->compressed_data, 0, 3) !== "\x1F\x8B\x08")
+ {
+ return false;
+ }
+
+ // Get the FLG (FLaGs)
+ $this->flags = ord($this->compressed_data[3]);
+
+ // FLG bits above (1 << 4) are reserved
+ if ($this->flags > 0x1F)
+ {
+ return false;
+ }
+
+ // Advance the pointer after the above
+ $this->position += 4;
+
+ // MTIME
+ $mtime = substr($this->compressed_data, $this->position, 4);
+ // Reverse the string if we're on a big-endian arch because l is the only signed long and is machine endianness
+ if (current(unpack('S', "\x00\x01")) === 1)
+ {
+ $mtime = strrev($mtime);
+ }
+ $this->MTIME = current(unpack('l', $mtime));
+ $this->position += 4;
+
+ // Get the XFL (eXtra FLags)
+ $this->XFL = ord($this->compressed_data[$this->position++]);
+
+ // Get the OS (Operating System)
+ $this->OS = ord($this->compressed_data[$this->position++]);
+
+ // Parse the FEXTRA
+ if ($this->flags & 4)
+ {
+ // Read subfield IDs
+ $this->SI1 = $this->compressed_data[$this->position++];
+ $this->SI2 = $this->compressed_data[$this->position++];
+
+ // SI2 set to zero is reserved for future use
+ if ($this->SI2 === "\x00")
+ {
+ return false;
+ }
+
+ // Get the length of the extra field
+ $len = current(unpack('v', substr($this->compressed_data, $this->position, 2)));
+ $this->position += 2;
+
+ // Check the length of the string is still valid
+ $this->min_compressed_size += $len + 4;
+ if ($this->compressed_size >= $this->min_compressed_size)
+ {
+ // Set the extra field to the given data
+ $this->extra_field = substr($this->compressed_data, $this->position, $len);
+ $this->position += $len;
+ }
+ else
+ {
+ return false;
+ }
+ }
+
+ // Parse the FNAME
+ if ($this->flags & 8)
+ {
+ // Get the length of the filename
+ $len = strcspn($this->compressed_data, "\x00", $this->position);
+
+ // Check the length of the string is still valid
+ $this->min_compressed_size += $len + 1;
+ if ($this->compressed_size >= $this->min_compressed_size)
+ {
+ // Set the original filename to the given string
+ $this->filename = substr($this->compressed_data, $this->position, $len);
+ $this->position += $len + 1;
+ }
+ else
+ {
+ return false;
+ }
+ }
+
+ // Parse the FCOMMENT
+ if ($this->flags & 16)
+ {
+ // Get the length of the comment
+ $len = strcspn($this->compressed_data, "\x00", $this->position);
+
+ // Check the length of the string is still valid
+ $this->min_compressed_size += $len + 1;
+ if ($this->compressed_size >= $this->min_compressed_size)
+ {
+ // Set the original comment to the given string
+ $this->comment = substr($this->compressed_data, $this->position, $len);
+ $this->position += $len + 1;
+ }
+ else
+ {
+ return false;
+ }
+ }
+
+ // Parse the FHCRC
+ if ($this->flags & 2)
+ {
+ // Check the length of the string is still valid
+ $this->min_compressed_size += $len + 2;
+ if ($this->compressed_size >= $this->min_compressed_size)
+ {
+ // Read the CRC
+ $crc = current(unpack('v', substr($this->compressed_data, $this->position, 2)));
+
+ // Check the CRC matches
+ if ((crc32(substr($this->compressed_data, 0, $this->position)) & 0xFFFF) === $crc)
+ {
+ $this->position += 2;
+ }
+ else
+ {
+ return false;
+ }
+ }
+ else
+ {
+ return false;
+ }
+ }
+
+ // Decompress the actual data
+ if (($this->data = gzinflate(substr($this->compressed_data, $this->position, -8))) === false)
+ {
+ return false;
+ }
+ else
+ {
+ $this->position = $this->compressed_size - 8;
+ }
+
+ // Check CRC of data
+ $crc = current(unpack('V', substr($this->compressed_data, $this->position, 4)));
+ $this->position += 4;
+ /*if (extension_loaded('hash') && sprintf('%u', current(unpack('V', hash('crc32b', $this->data)))) !== sprintf('%u', $crc))
+ {
+ return false;
+ }*/
+
+ // Check ISIZE of data
+ $isize = current(unpack('V', substr($this->compressed_data, $this->position, 4)));
+ $this->position += 4;
+ if (sprintf('%u', strlen($this->data) & 0xFFFFFFFF) !== sprintf('%u', $isize))
+ {
+ return false;
+ }
+
+ // Wow, against all odds, we've actually got a valid gzip string
+ return true;
+ }
+ else
+ {
+ return false;
+ }
+ }
+}
diff --git a/inc/3rdparty/simplepie/SimplePieAutoloader.php b/inc/3rdparty/simplepie/SimplePieAutoloader.php
new file mode 100644
index 0000000..b2654dc
--- /dev/null
+++ b/inc/3rdparty/simplepie/SimplePieAutoloader.php
@@ -0,0 +1,80 @@
+path = dirname(__FILE__);
+ }
+
+ /**
+ * Autoloader.
+ *
+ * @param string $class The name of the class to attempt to load.
+ */
+ public function autoload($class)
+ {
+ // see if this request should be handled by this autoloader
+ if (strpos($class, 'SimplePie') !== 0) {
+ return;
+ }
+
+ $filename = $this->path . DIRECTORY_SEPARATOR . str_replace('_', DIRECTORY_SEPARATOR, $class) . '.php';
+ include $filename;
+ }
+}
\ No newline at end of file
diff --git a/inc/3rdparty/site_config/README.txt b/inc/3rdparty/site_config/README.txt
new file mode 100644
index 0000000..0aff456
--- /dev/null
+++ b/inc/3rdparty/site_config/README.txt
@@ -0,0 +1,6 @@
+Full-Text RSS Site Patterns
+---------------------------
+
+Site patterns allow you to specify what should be extracted from specific sites.
+
+Please see http://help.fivefilters.org/customer/portal/articles/223153-site-patterns for more information.
\ No newline at end of file
diff --git a/inc/3rdparty/site_config/custom/inthepoche.com.txt b/inc/3rdparty/site_config/custom/inthepoche.com.txt
new file mode 100644
index 0000000..ede74b9
--- /dev/null
+++ b/inc/3rdparty/site_config/custom/inthepoche.com.txt
@@ -0,0 +1,7 @@
+title: //title
+body: //div[@class='post-content']
+
+prune: no
+tidy: no
+
+test_url: http://www.inthepoche.com/?post/poche-hosting
\ No newline at end of file
diff --git a/inc/3rdparty/site_config/index.php b/inc/3rdparty/site_config/index.php
new file mode 100644
index 0000000..a3d5f73
--- /dev/null
+++ b/inc/3rdparty/site_config/index.php
@@ -0,0 +1,3 @@
+
\ No newline at end of file
diff --git a/inc/3rdparty/site_config/standard/.wikipedia.org.txt b/inc/3rdparty/site_config/standard/.wikipedia.org.txt
new file mode 100644
index 0000000..8b98ae4
--- /dev/null
+++ b/inc/3rdparty/site_config/standard/.wikipedia.org.txt
@@ -0,0 +1,19 @@
+title: //h1[@id='firstHeading']
+body: //div[@id = 'bodyContent']
+strip_id_or_class: editsection
+#strip_id_or_class: toc
+strip_id_or_class: vertical-navbox
+strip: //table[@id='toc']
+strip: //div[@id='catlinks']
+strip: //div[@id='jump-to-nav']
+strip: //div[@class='thumbcaption']//div[@class='magnify']
+strip: //table[@class='navbox']
+strip: //table[contains(@class, 'infobox')]
+strip: //div[@class='dablink']
+strip: //div[@id='contentSub']
+strip: //table[contains(@class, 'metadata')]
+strip: //*[contains(@class, 'noprint')]
+strip: //span[@title='pronunciation:']
+prune: no
+tidy: no
+test_url: http://en.wikipedia.org/wiki/Christopher_Lloyd
\ No newline at end of file
diff --git a/inc/3rdparty/site_config/standard/index.php b/inc/3rdparty/site_config/standard/index.php
new file mode 100644
index 0000000..a3d5f73
--- /dev/null
+++ b/inc/3rdparty/site_config/standard/index.php
@@ -0,0 +1,3 @@
+
\ No newline at end of file
diff --git a/inc/3rdparty/site_config/standard/version.php b/inc/3rdparty/site_config/standard/version.php
new file mode 100644
index 0000000..e61807e
--- /dev/null
+++ b/inc/3rdparty/site_config/standard/version.php
@@ -0,0 +1,2 @@
+fetchContent()) {
- if ($this->store->add($url->getUrl(), $parametres_url['title'], $parametres_url['content'], $this->user->getId())) {
- Tools::logm('add link ' . $url->getUrl());
- $sequence = '';
- if (STORAGE == 'postgres') {
- $sequence = 'entries_id_seq';
- }
- $last_id = $this->store->getLastId($sequence);
- if (DOWNLOAD_PICTURES) {
- $content = filtre_picture($parametres_url['content'], $url->getUrl(), $last_id);
- Tools::logm('updating content article');
- $this->store->updateContent($last_id, $content, $this->user->getId());
- }
- if (!$import) {
- $this->messages->add('s', _('the link has been added successfully'));
- }
+ $content = $url->extract();
+
+ if ($this->store->add($url->getUrl(), $content['title'], $content['body'], $this->user->getId())) {
+ Tools::logm('add link ' . $url->getUrl());
+ $sequence = '';
+ if (STORAGE == 'postgres') {
+ $sequence = 'entries_id_seq';
}
- else {
- if (!$import) {
- $this->messages->add('e', _('error during insertion : the link wasn\'t added'));
- Tools::logm('error during insertion : the link wasn\'t added ' . $url->getUrl());
- }
+ $last_id = $this->store->getLastId($sequence);
+ if (DOWNLOAD_PICTURES) {
+ $content = filtre_picture($parametres_url['body'], $url->getUrl(), $last_id);
+ Tools::logm('updating content article');
+ $this->store->updateContent($last_id, $content, $this->user->getId());
+ }
+ if (!$import) {
+ $this->messages->add('s', _('the link has been added successfully'));
}
}
else {
if (!$import) {
- $this->messages->add('e', _('error during fetching content : the link wasn\'t added'));
- Tools::logm('error during content fetch ' . $url->getUrl());
+ $this->messages->add('e', _('error during insertion : the link wasn\'t added'));
+ Tools::logm('error during insertion : the link wasn\'t added ' . $url->getUrl());
}
}
+
if (!$import) {
Tools::redirect();
}
@@ -220,7 +215,6 @@ class Poche
}
break;
default:
- Tools::logm('action ' . $action . 'doesn\'t exist');
break;
}
}
diff --git a/inc/poche/Url.class.php b/inc/poche/Url.class.php
index d7ee911..5a89301 100644
--- a/inc/poche/Url.class.php
+++ b/inc/poche/Url.class.php
@@ -12,6 +12,45 @@ class Url
{
public $url;
+ private $fingerprints = array(
+ // Posterous
+ ' array('hostname'=>'fingerprint.posterous.com', 'head'=>true),
+ // Blogger
+ ' array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
+ ' array('hostname'=>'fingerprint.blogspot.com', 'head'=>true),
+ // WordPress (self-hosted and hosted)
+ '![\"$_name\"](\"$effective_url\")
";
+ } else {
+ $html = "Download $_name";
+ }
+ $title = $_name;
+ $do_content_extraction = false;
+ break;
+ }
+ }
+ }
+ unset($_mime, $_act, $_name, $match);
+ }
+ if ($do_content_extraction) {
+ $html = $response['body'];
+ // remove strange things
+ $html = str_replace('', '', $html);
+ $html = $this->convert_to_utf8($html, $response['headers']);
+
+ // check site config for single page URL - fetch it if found
+ if ($single_page_response = $this->getSinglePage($item, $html, $effective_url)) {
+ $html = $single_page_response['body'];
+ // remove strange things
+ $html = str_replace('', '', $html);
+ $html = $this->convert_to_utf8($html, $single_page_response['headers']);
+ $effective_url = $single_page_response['effective_url'];
+ unset($single_page_response);
+ }
+ $extract_result = $extractor->process($html, $effective_url);
+ $readability = $extractor->readability;
+ $content_block = ($extract_result) ? $extractor->getContent() : null;
+ }
+ }
+ if ($do_content_extraction) {
+ // if we failed to extract content...
+ if (!$extract_result) {
+ $html = $this->error_message;
+ // keep the original item description
+ $html .= $item->get_description();
+ } else {
+ $readability->clean($content_block, 'select');
+ if ($this->rewrite_relative_urls) $this->makeAbsolute($effective_url, $content_block);
+ if ($content_block->childNodes->length == 1 && $content_block->firstChild->nodeType === XML_ELEMENT_NODE) {
+ $html = $content_block->firstChild->innerHTML;
+ } else {
+ $html = $content_block->innerHTML;
+ }
+ // post-processing cleanup
+ $html = preg_replace('!]+)/i', $html_head, $match)) {
+ $encoding = trim($match[1]);
+ } elseif (preg_match_all('/]+)>/i', $html_head, $match)) {
+ foreach ($match[1] as $_test) {
+ if (preg_match('/charset=["\']?([^"\']+)/i', $_test, $_m)) {
+ $encoding = trim($_m[1]);
+ break;
+ }
+ }
}
}
-
- $parameters = array();
- if (isset($html) and strlen($html) > 0)
- {
- $readability = new Readability($html, $this->getUrl());
- $readability->convertLinksToFootnotes = CONVERT_LINKS_FOOTNOTES;
- $readability->revertForcedParagraphElements = REVERT_FORCED_PARAGRAPH_ELEMENTS;
-
- if($readability->init())
- {
- $content = $readability->articleContent->innerHTML;
- $parameters['title'] = ($readability->articleTitle->innerHTML != '' ? $readability->articleTitle->innerHTML : _('Untitled'));
- $parameters['content'] = $content;
-
- return $parameters;
+ if (isset($encoding)) $encoding = trim($encoding);
+ // trim is important here!
+ if (!$encoding || (strtolower($encoding) == 'iso-8859-1')) {
+ // replace MS Word smart qutoes
+ $trans = array();
+ $trans[chr(130)] = '‚'; // Single Low-9 Quotation Mark
+ $trans[chr(131)] = 'ƒ'; // Latin Small Letter F With Hook
+ $trans[chr(132)] = '„'; // Double Low-9 Quotation Mark
+ $trans[chr(133)] = '…'; // Horizontal Ellipsis
+ $trans[chr(134)] = '†'; // Dagger
+ $trans[chr(135)] = '‡'; // Double Dagger
+ $trans[chr(136)] = 'ˆ'; // Modifier Letter Circumflex Accent
+ $trans[chr(137)] = '‰'; // Per Mille Sign
+ $trans[chr(138)] = 'Š'; // Latin Capital Letter S With Caron
+ $trans[chr(139)] = '‹'; // Single Left-Pointing Angle Quotation Mark
+ $trans[chr(140)] = 'Œ'; // Latin Capital Ligature OE
+ $trans[chr(145)] = '‘'; // Left Single Quotation Mark
+ $trans[chr(146)] = '’'; // Right Single Quotation Mark
+ $trans[chr(147)] = '“'; // Left Double Quotation Mark
+ $trans[chr(148)] = '”'; // Right Double Quotation Mark
+ $trans[chr(149)] = '•'; // Bullet
+ $trans[chr(150)] = '–'; // En Dash
+ $trans[chr(151)] = '—'; // Em Dash
+ $trans[chr(152)] = '˜'; // Small Tilde
+ $trans[chr(153)] = '™'; // Trade Mark Sign
+ $trans[chr(154)] = 'š'; // Latin Small Letter S With Caron
+ $trans[chr(155)] = '›'; // Single Right-Pointing Angle Quotation Mark
+ $trans[chr(156)] = 'œ'; // Latin Small Ligature OE
+ $trans[chr(159)] = 'Ÿ'; // Latin Capital Letter Y With Diaeresis
+ $html = strtr($html, $trans);
+ }
+ if (!$encoding) {
+ $encoding = 'utf-8';
+ } else {
+ if (strtolower($encoding) != 'utf-8') {
+ $html = SimplePie_Misc::change_encoding($html, $encoding, 'utf-8');
+ /*
+ if (function_exists('iconv')) {
+ // iconv appears to handle certain character encodings better than mb_convert_encoding
+ $html = iconv($encoding, 'utf-8', $html);
+ } else {
+ $html = mb_convert_encoding($html, 'utf-8', $encoding);
+ }
+ */
}
}
}
- else {
- #$msg->add('e', _('error during url preparation : the link is not valid'));
- Tools::logm($this->getUrl() . ' is not a valid url');
- }
+ return $html;
+ }
- return FALSE;
+ private function makeAbsolute($base, $elem) {
+ $base = new SimplePie_IRI($base);
+ // remove '//' in URL path (used to prevent URLs from resolving properly)
+ // TODO: check if this is still the case
+ if (isset($base->path)) $base->path = preg_replace('!//+!', '/', $base->path);
+ foreach(array('a'=>'href', 'img'=>'src') as $tag => $attr) {
+ $elems = $elem->getElementsByTagName($tag);
+ for ($i = $elems->length-1; $i >= 0; $i--) {
+ $e = $elems->item($i);
+ //$e->parentNode->replaceChild($articleContent->ownerDocument->createTextNode($e->textContent), $e);
+ $this->makeAbsoluteAttr($base, $e, $attr);
+ }
+ if (strtolower($elem->tagName) == $tag) $this->makeAbsoluteAttr($base, $elem, $attr);
+ }
+ }
+
+ private function makeAbsoluteAttr($base, $e, $attr) {
+ if ($e->hasAttribute($attr)) {
+ // Trim leading and trailing white space. I don't really like this but
+ // unfortunately it does appear on some sites. e.g. 
+ $url = trim(str_replace('%20', ' ', $e->getAttribute($attr)));
+ $url = str_replace(' ', '%20', $url);
+ if (!preg_match('!https?://!i', $url)) {
+ if ($absolute = SimplePie_IRI::absolutize($base, $url)) {
+ $e->setAttribute($attr, $absolute);
+ }
+ }
+ }
+ }
+
+ private function makeAbsoluteStr($base, $url) {
+ $base = new SimplePie_IRI($base);
+ // remove '//' in URL path (causes URLs not to resolve properly)
+ if (isset($base->path)) $base->path = preg_replace('!//+!', '/', $base->path);
+ if (preg_match('!^https?://!i', $url)) {
+ // already absolute
+ return $url;
+ } else {
+ if ($absolute = SimplePie_IRI::absolutize($base, $url)) {
+ return $absolute;
+ }
+ return false;
+ }
+ }
+
+ // returns single page response, or false if not found
+ private function getSinglePage($item, $html, $url) {
+ global $http, $extractor;
+ $host = @parse_url($url, PHP_URL_HOST);
+ $site_config = SiteConfig::build($host);
+ if ($site_config === false) {
+ // check for fingerprints
+ if (!empty($extractor->fingerprints) && ($_fphost = $extractor->findHostUsingFingerprints($html))) {
+ $site_config = SiteConfig::build($_fphost);
+ }
+ if ($site_config === false) $site_config = new SiteConfig();
+ SiteConfig::add_to_cache($host, $site_config);
+ return false;
+ } else {
+ SiteConfig::add_to_cache($host, $site_config);
+ }
+ $splink = null;
+ if (!empty($site_config->single_page_link)) {
+ $splink = $site_config->single_page_link;
+ } elseif (!empty($site_config->single_page_link_in_feed)) {
+ // single page link xpath is targeted at feed
+ $splink = $site_config->single_page_link_in_feed;
+ // so let's replace HTML with feed item description
+ $html = $item->get_description();
+ }
+ if (isset($splink)) {
+ // Build DOM tree from HTML
+ $readability = new Readability($html, $url);
+ $xpath = new DOMXPath($readability->dom);
+ // Loop through single_page_link xpath expressions
+ $single_page_url = null;
+ foreach ($splink as $pattern) {
+ $elems = @$xpath->evaluate($pattern, $readability->dom);
+ if (is_string($elems)) {
+ $single_page_url = trim($elems);
+ break;
+ } elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+ foreach ($elems as $item) {
+ if ($item instanceof DOMElement && $item->hasAttribute('href')) {
+ $single_page_url = $item->getAttribute('href');
+ break;
+ } elseif ($item instanceof DOMAttr && $item->value) {
+ $single_page_url = $item->value;
+ break;
+ }
+ }
+ }
+ }
+ // If we've got URL, resolve against $url
+ if (isset($single_page_url) && ($single_page_url = $this->makeAbsoluteStr($url, $single_page_url))) {
+ // check it's not what we have already!
+ if ($single_page_url != $url) {
+ // it's not, so let's try to fetch it...
+ $_prev_ref = $http->referer;
+ $http->referer = $single_page_url;
+ if (($response = $http->get($single_page_url, true)) && $response['status_code'] < 300) {
+ $http->referer = $_prev_ref;
+ return $response;
+ }
+ $http->referer = $_prev_ref;
+ }
+ }
+ }
+ return false;
}
}
\ No newline at end of file
diff --git a/inc/poche/config.inc.php b/inc/poche/config.inc.php
index cb882cd..a191729 100755
--- a/inc/poche/config.inc.php
+++ b/inc/poche/config.inc.php
@@ -30,10 +30,25 @@ require_once __DIR__ . '/../../inc/3rdparty/simple_html_dom.php';
require_once __DIR__ . '/../../inc/3rdparty/paginator.php';
require_once __DIR__ . '/../../inc/3rdparty/Session.class.php';
+require_once __DIR__ . '/../../inc/3rdparty/simplepie/SimplePieAutoloader.php';
+require_once __DIR__ . '/../../inc/3rdparty/simplepie/SimplePie/Core.php';
+require_once __DIR__ . '/../../inc/3rdparty/content-extractor/ContentExtractor.php';
+require_once __DIR__ . '/../../inc/3rdparty/content-extractor/SiteConfig.php';
+require_once __DIR__ . '/../../inc/3rdparty/humble-http-agent/HumbleHttpAgent.php';
+require_once __DIR__ . '/../../inc/3rdparty/humble-http-agent/SimplePie_HumbleHttpAgent.php';
+require_once __DIR__ . '/../../inc/3rdparty/humble-http-agent/CookieJar.php';
+require_once __DIR__ . '/../../inc/3rdparty/feedwriter/FeedItem.php';
+require_once __DIR__ . '/../../inc/3rdparty/feedwriter/FeedWriter.php';
+require_once __DIR__ . '/../../inc/3rdparty/feedwriter/DummySingleItemFeed.php';
+
if (DOWNLOAD_PICTURES) {
require_once __DIR__ . '/../../inc/poche/pochePictures.php';
}
+if (!ini_get('date.timezone') || !@date_default_timezone_set(ini_get('date.timezone'))) {
+ date_default_timezone_set('UTC');
+}
+
$poche = new Poche();
#XSRF protection with token
// if (!empty($_POST)) {
diff --git a/inc/poche/define.inc.php b/inc/poche/define.inc.php
index 2d0a39e..3f66743 100644
--- a/inc/poche/define.inc.php
+++ b/inc/poche/define.inc.php
@@ -17,8 +17,6 @@ define ('STORAGE_PASSWORD', 'postgres'); # leave blank for sqlite
define ('MODE_DEMO', FALSE);
define ('DEBUG_POCHE', FALSE);
-define ('CONVERT_LINKS_FOOTNOTES', FALSE);
-define ('REVERT_FORCED_PARAGRAPH_ELEMENTS', FALSE);
define ('DOWNLOAD_PICTURES', FALSE);
define ('SHARE_TWITTER', TRUE);
define ('SHARE_MAIL', TRUE);
[\s\h\v]*
!u', '', $html); + } + } + } + + $title = ($extractor->getTitle() != '' ? $extractor->getTitle() : _('Untitled')); + $content = array ('title' => $title, 'body' => $html); + + return $content; } - public function fetchContent() + private function convert_to_utf8($html, $header=null) { - if ($this->isCorrect()) { - $this->clean(); - $html = Encoding::toUTF8(Tools::getFile($this->getUrl())); - - # if Tools::getFile() if not able to retrieve HTTPS content, try the same URL with HTTP protocol - if (!preg_match('!^https?://!i', $this->getUrl()) && (!isset($html) || strlen($html) <= 0)) { - $this->setUrl('http://' . $this->getUrl()); - $html = Encoding::toUTF8(Tools::getFile($this->getUrl())); + $encoding = null; + if ($html || $header) { + if (is_array($header)) $header = implode("\n", $header); + if (!$header || !preg_match_all('/^Content-Type:\s+([^;]+)(?:;\s*charset=["\']?([^;"\'\n]*))?/im', $header, $match, PREG_SET_ORDER)) { + // error parsing the response + } else { + $match = end($match); // get last matched element (in case of redirects) + if (isset($match[2])) $encoding = trim($match[2], "\"' \r\n\0\x0B\t"); } - - if (function_exists('tidy_parse_string')) { - $tidy = tidy_parse_string($html, array(), 'UTF8'); - $tidy->cleanRepair(); - - //Warning: tidy might fail so, ensure there is still a content - $body = $tidy->body(); - - //hasChildren does not seem to work, just check the string - //returned (and do not forget to clean the white spaces) - if (preg_replace('/\s+/', '', $body->value) !== "") { - $html = $tidy->value; + // TODO: check to see if encoding is supported (can we convert it?) + // If it's not, result will be empty string. + // For now we'll check for invalid encoding types returned by some sites, e.g. 'none' + // Problem URL: http://facta.co.jp/blog/archives/20111026001026.html + if (!$encoding || $encoding == 'none') { + // search for encoding in HTML - only look at the first 35000 characters + $html_head = substr($html, 0, 40000); + if (preg_match('/^<\?xml\s+version=(?:"[^"]*"|\'[^\']*\')\s+encoding=("[^"]*"|\'[^\']*\')/s', $html_head, $match)) { + $encoding = trim($match[1], '"\''); + } elseif (preg_match('/
+ $url = trim(str_replace('%20', ' ', $e->getAttribute($attr)));
+ $url = str_replace(' ', '%20', $url);
+ if (!preg_match('!https?://!i', $url)) {
+ if ($absolute = SimplePie_IRI::absolutize($base, $url)) {
+ $e->setAttribute($attr, $absolute);
+ }
+ }
+ }
+ }
+
+ private function makeAbsoluteStr($base, $url) {
+ $base = new SimplePie_IRI($base);
+ // remove '//' in URL path (causes URLs not to resolve properly)
+ if (isset($base->path)) $base->path = preg_replace('!//+!', '/', $base->path);
+ if (preg_match('!^https?://!i', $url)) {
+ // already absolute
+ return $url;
+ } else {
+ if ($absolute = SimplePie_IRI::absolutize($base, $url)) {
+ return $absolute;
+ }
+ return false;
+ }
+ }
+
+ // returns single page response, or false if not found
+ private function getSinglePage($item, $html, $url) {
+ global $http, $extractor;
+ $host = @parse_url($url, PHP_URL_HOST);
+ $site_config = SiteConfig::build($host);
+ if ($site_config === false) {
+ // check for fingerprints
+ if (!empty($extractor->fingerprints) && ($_fphost = $extractor->findHostUsingFingerprints($html))) {
+ $site_config = SiteConfig::build($_fphost);
+ }
+ if ($site_config === false) $site_config = new SiteConfig();
+ SiteConfig::add_to_cache($host, $site_config);
+ return false;
+ } else {
+ SiteConfig::add_to_cache($host, $site_config);
+ }
+ $splink = null;
+ if (!empty($site_config->single_page_link)) {
+ $splink = $site_config->single_page_link;
+ } elseif (!empty($site_config->single_page_link_in_feed)) {
+ // single page link xpath is targeted at feed
+ $splink = $site_config->single_page_link_in_feed;
+ // so let's replace HTML with feed item description
+ $html = $item->get_description();
+ }
+ if (isset($splink)) {
+ // Build DOM tree from HTML
+ $readability = new Readability($html, $url);
+ $xpath = new DOMXPath($readability->dom);
+ // Loop through single_page_link xpath expressions
+ $single_page_url = null;
+ foreach ($splink as $pattern) {
+ $elems = @$xpath->evaluate($pattern, $readability->dom);
+ if (is_string($elems)) {
+ $single_page_url = trim($elems);
+ break;
+ } elseif ($elems instanceof DOMNodeList && $elems->length > 0) {
+ foreach ($elems as $item) {
+ if ($item instanceof DOMElement && $item->hasAttribute('href')) {
+ $single_page_url = $item->getAttribute('href');
+ break;
+ } elseif ($item instanceof DOMAttr && $item->value) {
+ $single_page_url = $item->value;
+ break;
+ }
+ }
+ }
+ }
+ // If we've got URL, resolve against $url
+ if (isset($single_page_url) && ($single_page_url = $this->makeAbsoluteStr($url, $single_page_url))) {
+ // check it's not what we have already!
+ if ($single_page_url != $url) {
+ // it's not, so let's try to fetch it...
+ $_prev_ref = $http->referer;
+ $http->referer = $single_page_url;
+ if (($response = $http->get($single_page_url, true)) && $response['status_code'] < 300) {
+ $http->referer = $_prev_ref;
+ return $response;
+ }
+ $http->referer = $_prev_ref;
+ }
+ }
+ }
+ return false;
}
}
\ No newline at end of file
diff --git a/inc/poche/config.inc.php b/inc/poche/config.inc.php
index cb882cd..a191729 100755
--- a/inc/poche/config.inc.php
+++ b/inc/poche/config.inc.php
@@ -30,10 +30,25 @@ require_once __DIR__ . '/../../inc/3rdparty/simple_html_dom.php';
require_once __DIR__ . '/../../inc/3rdparty/paginator.php';
require_once __DIR__ . '/../../inc/3rdparty/Session.class.php';
+require_once __DIR__ . '/../../inc/3rdparty/simplepie/SimplePieAutoloader.php';
+require_once __DIR__ . '/../../inc/3rdparty/simplepie/SimplePie/Core.php';
+require_once __DIR__ . '/../../inc/3rdparty/content-extractor/ContentExtractor.php';
+require_once __DIR__ . '/../../inc/3rdparty/content-extractor/SiteConfig.php';
+require_once __DIR__ . '/../../inc/3rdparty/humble-http-agent/HumbleHttpAgent.php';
+require_once __DIR__ . '/../../inc/3rdparty/humble-http-agent/SimplePie_HumbleHttpAgent.php';
+require_once __DIR__ . '/../../inc/3rdparty/humble-http-agent/CookieJar.php';
+require_once __DIR__ . '/../../inc/3rdparty/feedwriter/FeedItem.php';
+require_once __DIR__ . '/../../inc/3rdparty/feedwriter/FeedWriter.php';
+require_once __DIR__ . '/../../inc/3rdparty/feedwriter/DummySingleItemFeed.php';
+
if (DOWNLOAD_PICTURES) {
require_once __DIR__ . '/../../inc/poche/pochePictures.php';
}
+if (!ini_get('date.timezone') || !@date_default_timezone_set(ini_get('date.timezone'))) {
+ date_default_timezone_set('UTC');
+}
+
$poche = new Poche();
#XSRF protection with token
// if (!empty($_POST)) {
diff --git a/inc/poche/define.inc.php b/inc/poche/define.inc.php
index 2d0a39e..3f66743 100644
--- a/inc/poche/define.inc.php
+++ b/inc/poche/define.inc.php
@@ -17,8 +17,6 @@ define ('STORAGE_PASSWORD', 'postgres'); # leave blank for sqlite
define ('MODE_DEMO', FALSE);
define ('DEBUG_POCHE', FALSE);
-define ('CONVERT_LINKS_FOOTNOTES', FALSE);
-define ('REVERT_FORCED_PARAGRAPH_ELEMENTS', FALSE);
define ('DOWNLOAD_PICTURES', FALSE);
define ('SHARE_TWITTER', TRUE);
define ('SHARE_MAIL', TRUE);