function _testXPath($xpath_expression)
{
if (!class_exists('DOMDocument') || !class_exists('DOMXPath')) {
if (function_exists('domxml_open_mem')) {
$dom = domxml_open_mem($this->_response);
if (!$dom) {
$this->fail('Error parsing doc');
return false;
}
var_dump($dom);
$xpath = $dom->xpath_init();
var_dump($xpath);
$ctx = $dom->xpath_new_context();
var_dump($xpath_expression);
$result = $ctx->xpath_eval($xpath_expression);
var_dump($result);
$return = new stdClass();
$return->length = count($result->nodeset);
return $return;
}
$this->fail('No xpath support built in');
return false;
} else {
if (extension_loaded('domxml')) {
$this->fail('Please disable the domxml extension. Only php5 builtin domxml is supported');
return false;
}
}
$dom = new DOMDocument();
$dom->loadHtml($this->_response);
$xpath = new DOMXPath($dom);
$node = $xpath->query($xpath_expression);
return $node;
}
function process(&$article)
{
$owner_uid = $article["owner_uid"];
if (strpos($article["guid"], "bunicomic.com") !== FALSE || strpos($article["guid"], "buttersafe.com") !== FALSE || strpos($article["guid"], "whompcomic.com") !== FALSE || strpos($article["guid"], "extrafabulouscomics.com") !== FALSE || strpos($article["guid"], "happyjar.com") !== FALSE || strpos($article["guid"], "csectioncomics.com") !== FALSE) {
if (strpos($article["plugin_data"], "af_comics,{$owner_uid}:") === FALSE) {
// lol at people who block clients by user agent
// oh noes my ad revenue Q_Q
$res = fetch_file_contents($article["link"], false, false, false, false, false, 0, "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)");
$doc = new DOMDocument();
@$doc->loadHTML($res);
$basenode = false;
if ($doc) {
$xpath = new DOMXPath($doc);
$basenode = $xpath->query('//div[@id="comic"]')->item(0);
if ($basenode) {
$article["content"] = $doc->saveXML($basenode);
$article["plugin_data"] = "af_comics,{$owner_uid}:" . $article["plugin_data"];
}
}
} else {
if (isset($article["stored"]["content"])) {
$article["content"] = $article["stored"]["content"];
}
}
return true;
}
return false;
}
/**
* Constructs a new object object from DOM Document.
*
* @param DomDocument $dom the ReST fragment for this object
*/
public function __construct(DomDocument $dom)
{
$xpath = new DOMXPath($dom);
$result = $xpath->query('//result/weblog');
if ($result->length == 1) {
$this->_weblog = new Zend_Service_Technorati_Weblog($result->item(0));
} else {
// follow the same behavior of blogPostTags
// and raise an Exception if the URL is not a valid weblog
throw new Zend_Service_Technorati_Exception(
"Your URL is not a recognized Technorati weblog");
}
$result = $xpath->query('//result/url/text()');
if ($result->length == 1) {
try {
// fetched URL often doens't include schema
// and this issue causes the following line to fail
$this->_url = Zend_Service_Technorati_Utils::normalizeUriHttp($result->item(0)->data);
} catch(Zend_Service_Technorati_Exception $e) {
if ($this->getWeblog() instanceof Zend_Service_Technorati_Weblog) {
$this->_url = $this->getWeblog()->getUrl();
}
}
}
$result = $xpath->query('//result/inboundblogs/text()');
if ($result->length == 1) $this->_inboundBlogs = (int) $result->item(0)->data;
$result = $xpath->query('//result/inboundlinks/text()');
if ($result->length == 1) $this->_inboundLinks = (int) $result->item(0)->data;
}
function generate()
{
parent::generate();
$xpath = new DOMXPath($this->_doc);
$this->appendLine('<?php');
$this->appendLine('require_once("KalturaClientBase.php");');
$this->appendLine('');
// enumes
$enumNodes = $xpath->query("/xml/enums/enum");
foreach ($enumNodes as $enumNode) {
$this->writeEnum($enumNode);
}
// classes
$classNodes = $xpath->query("/xml/classes/class");
foreach ($classNodes as $classNode) {
$this->writeClass($classNode);
}
$serviceNodes = $xpath->query("/xml/services/service");
foreach ($serviceNodes as $serviceNode) {
$this->writeService($serviceNode);
}
$this->appendLine();
$this->writeMainClient($serviceNodes);
$this->appendLine();
$this->addFile("KalturaClient.php", $this->getTextBlock());
}
/**
* Constructs a new object from DOM Element.
*
* @param DomElement $dom the ReST fragment for this object
*/
public function __construct(DomElement $dom)
{
$xpath = new DOMXPath($dom->ownerDocument);
$result = $xpath->query('./firstname/text()', $dom);
if ($result->length == 1) {
$this->setFirstName($result->item(0)->data);
}
$result = $xpath->query('./lastname/text()', $dom);
if ($result->length == 1) {
$this->setLastName($result->item(0)->data);
}
$result = $xpath->query('./username/text()', $dom);
if ($result->length == 1) {
$this->setUsername($result->item(0)->data);
}
$result = $xpath->query('./description/text()', $dom);
if ($result->length == 1) {
$this->setDescription($result->item(0)->data);
}
$result = $xpath->query('./bio/text()', $dom);
if ($result->length == 1) {
$this->setBio($result->item(0)->data);
}
$result = $xpath->query('./thumbnailpicture/text()', $dom);
if ($result->length == 1) {
$this->setThumbnailPicture($result->item(0)->data);
}
}
function parseResinImprFile($file_path)
{
global $hostDict;
$doc = new DOMDocument();
@$doc->loadHTMLFile($file_path);
$query = "//table[1]/tr[@class != 'first']/td[position() < 3]";
$xpath = new DOMXPath($doc);
$entries = $xpath->query($query);
$index = 0;
$key = "";
$value = "";
foreach ($entries as $entry) {
if ($index % 2 == 0) {
$key = $entry->nodeValue;
} else {
$value = $entry->nodeValue;
}
if ($index != 0 and $index % 2 == 1) {
if ($key == "AD_EXCHANGE.bidResult") {
# 还不能区分bid 和 bidResult, 所以加到一起
$key = "AD_EXCHANGE.bid";
}
if (array_key_exists($key, $hostDict) && !in_array($value, $hostDict[$key])) {
array_push($hostDict[$key], $value);
}
}
$index++;
}
}
/**
* Convert dom node tree to array
*
* @param \DOMDocument $source
* @return array
* @throws \InvalidArgumentException
*/
public function convert($source)
{
$output = [];
$xpath = new \DOMXPath($source);
$indexers = $xpath->evaluate('/config/indexer');
/** @var $typeNode \DOMNode */
foreach ($indexers as $indexerNode) {
$data = [];
$indexerId = $this->getAttributeValue($indexerNode, 'id');
$data['indexer_id'] = $indexerId;
$data['primary'] = $this->getAttributeValue($indexerNode, 'primary');
$data['view_id'] = $this->getAttributeValue($indexerNode, 'view_id');
$data['action_class'] = $this->getAttributeValue($indexerNode, 'class');
$data['title'] = '';
$data['description'] = '';
/** @var $childNode \DOMNode */
foreach ($indexerNode->childNodes as $childNode) {
if ($childNode->nodeType != XML_ELEMENT_NODE) {
continue;
}
/** @var $childNode \DOMElement */
$data = $this->convertChild($childNode, $data);
}
$output[$indexerId] = $data;
}
return $output;
}
/**
* Unserializes the property.
*
* This static method should return a an instance of this object.
*
* @param \DOMElement $prop
* @param array $propertyMap
* @return DAV\IProperty
*/
static function unserialize(\DOMElement $prop, array $propertyMap)
{
$xpath = new \DOMXPath($prop->ownerDocument);
$xpath->registerNamespace('d', 'urn:DAV');
// Finding the 'response' element
$xResponses = $xpath->evaluate('d:response', $prop);
$result = [];
for ($jj = 0; $jj < $xResponses->length; $jj++) {
$xResponse = $xResponses->item($jj);
// Parsing 'href'
$href = Href::unserialize($xResponse, $propertyMap);
$properties = [];
// Parsing 'status' in 'd:response'
$responseStatus = $xpath->evaluate('string(d:status)', $xResponse);
if ($responseStatus) {
list(, $responseStatus, ) = explode(' ', $responseStatus, 3);
}
// Parsing 'propstat'
$xPropstat = $xpath->query('d:propstat', $xResponse);
for ($ii = 0; $ii < $xPropstat->length; $ii++) {
// Parsing 'status'
$status = $xpath->evaluate('string(d:status)', $xPropstat->item($ii));
list(, $statusCode, ) = explode(' ', $status, 3);
$usedPropertyMap = $statusCode == '200' ? $propertyMap : [];
// Parsing 'prop'
$properties[$statusCode] = DAV\XMLUtil::parseProperties($xPropstat->item($ii), $usedPropertyMap);
}
$result[] = new Response($href->getHref(), $properties, $responseStatus ? $responseStatus : null);
}
return new self($result);
}
public static function parse($html, $url)
{
$recipe = RecipeParser_Parser_MicrodataSchema::parse($html, $url);
// Turn off libxml errors to prevent mismatched tag warnings.
libxml_use_internal_errors(true);
$doc = new DOMDocument();
$html = mb_convert_encoding($html, 'HTML-ENTITIES', "UTF-8");
$doc->loadHTML('<?xml encoding="UTF-8">' . $html);
$xpath = new DOMXPath($doc);
// Photo -- skip logo if it was used in place of photo
if (strpos($recipe->photo_url, "FDC_Logo_vertical.png") !== false || strpos($recipe->photo_url, "FDC_share-logo.png") !== false) {
$recipe->photo_url = '';
}
if ($recipe->photo_url) {
$recipe->photo_url = str_replace("/thumbs/", "/large/", $recipe->photo_url);
}
// Yield
$yield = '';
$nodes = $xpath->query('//*[@class="yield"]');
// Find as 'yield'
if ($nodes->length) {
$line = $nodes->item(0)->nodeValue;
$line = RecipeParser_Text::formatYield($line);
$recipe->yield = $line;
// Or as number of 'servings'
} else {
$nodes = $xpath->query('//*[@class="servings"]//*[@class="value"]');
if ($nodes->length) {
$line = $nodes->item(0)->nodeValue;
$line = RecipeParser_Text::formatYield($line);
$recipe->yield = $line;
}
}
return $recipe;
}
/**
* addEntriesFromFeed adds all the entries from a zotero api feed to the collection
* @param $feed either a DOMDocument or string xml of the feed
*/
public function addEntriesFromFeed($feed)
{
if (is_string($feed)) {
$dom = new DOMDocument();
//cleanup GET param separators in the links in the feed
$feed = str_replace('&', '&', $feed);
$dom->loadXML($feed);
} else {
if (get_class($feed) == 'DOMDocument') {
$dom = $feed;
//$newFeedNode = $dom->importNode($feed, true);
//$dom->appendChild($newFeedNode);
} else {
throw new Exception('Entry must be either an XML string or an ATOM feed DOMNode');
}
}
$xpath = new DOMXPath($dom);
$xpath->registerNamespace('zxfer', 'http://zotero.org/ns/transfer');
$xpath->registerNamespace('atom', 'http://www.w3.org/2005/Atom');
$entryNodes = $xpath->query('//atom:entry');
for ($i = 0; $i < $entryNodes->length; $i++) {
$newEntry = new phpZoteroEntry($entryNodes->item($i));
$this->entries[$newEntry->itemUri] = $newEntry;
}
}
/**
* load all app files for given path and build.xml document
*
* @param string $path app base path
* @param DOMDocument $build build.xml
* @return boolean
*/
private function _doBuild($path, DOMDocument $build)
{
$Classes = Classes::get();
$x = new DOMXPath($build);
$app = $x->query('/build/app');
if ($app->length != 1) {
throw new PException('App error!');
}
$app = $app->item(0);
if (!$app->hasAttribute('name')) {
throw new PException('App name error!');
}
$this->_apps[$app->getAttribute('name')] = $build;
$files = $x->query('/build/files/file');
foreach ($files as $file) {
if ($file->hasAttribute('class')) {
$Classes->addClass($file->getAttribute('class'), $path . $file->nodeValue);
continue;
}
if ($file->hasAttribute('include')) {
if (!file_exists($path . $file->nodeValue)) {
continue;
}
$this->_includes[] = $path . $file->nodeValue;
continue;
}
}
return true;
}
/**
* Handle a node
*
* Handle / transform a given node, and return the result of the
* conversion.
*
* @param ezcDocumentElementVisitorConverter $converter
* @param DOMElement $node
* @param mixed $root
* @return mixed
*/
public function handle(ezcDocumentElementVisitorConverter $converter, DOMElement $node, $root)
{
$quote = $root->ownerDocument->createElement('blockquote');
// Locate optional attribution elements, and transform them below the
// recursive quote visiting.
$xpath = new DOMXPath($node->ownerDocument);
$attributionNodes = $xpath->query('*[local-name() = "attribution"]', $node);
$attributions = array();
foreach ($attributionNodes as $attribution) {
$attributions[] = $attribution->cloneNode(true);
$attribution->parentNode->removeChild($attribution);
}
// Recursively decorate blockquote, after all attribution nodes are
// removed
$quote = $converter->visitChildren($node, $quote);
$root->appendChild($quote);
// Append attribution nodes, if any
foreach ($attributions as $attribution) {
$div = $root->ownerDocument->createElement('div');
$div->setAttribute('class', 'attribution');
$quote->appendChild($div);
$cite = $root->ownerDocument->createElement('cite', htmlspecialchars($attribution->textContent));
$div->appendChild($cite);
}
return $root;
}
/**
* @param \DOMNode $node
* @param string $selector
* @return \DOMNodeList
*/
public function findAll($node, $selector)
{
$domXPath = new \DOMXPath($node->ownerDocument);
$converter = new CssSelectorConverter();
$xpath = $converter->toXPath($selector);
return $domXPath->query($xpath, $node);
}
public function apply(KalturaRelatedFilter $filter, KalturaObject $parentObject)
{
$filterProperty = $this->filterProperty;
$parentProperty = $this->parentProperty;
KalturaLog::debug("Mapping XPath {$parentProperty} to " . get_class($filter) . "::{$filterProperty}");
if (!$parentObject instanceof KalturaMetadata) {
throw new KalturaAPIException(KalturaErrors::INVALID_OBJECT_TYPE, get_class($parentObject));
}
if (!property_exists($filter, $filterProperty)) {
throw new KalturaAPIException(KalturaErrors::PROPERTY_IS_NOT_DEFINED, $filterProperty, get_class($filter));
}
$xml = $parentObject->xml;
$doc = new KDOMDocument();
$doc->loadXML($xml);
$xpath = new DOMXPath($doc);
$metadataElements = $xpath->query($parentProperty);
if ($metadataElements->length == 1) {
$filter->{$filterProperty} = $metadataElements->item(0)->nodeValue;
} elseif ($metadataElements->length > 1) {
$values = array();
foreach ($metadataElements as $element) {
$values[] = $element->nodeValue;
}
$filter->{$filterProperty} = implode(',', $values);
} elseif (!$this->allowNull) {
return false;
}
return true;
}
public function patch($version, \DOMDocument $domct, \DOMDocument $domth, Connection $connbas, \unicode $unicode)
{
if ($version == "") {
$th = $domth->documentElement;
$ct = $domct->documentElement;
$th->setAttribute("id", "0");
$xp = new DOMXPath($domth);
$te = $xp->query("/thesaurus/te");
if ($te->length > 0) {
$te0 = $te->item(0);
$th->setAttribute("nextid", $te0->getAttribute("nextid"));
$te = $xp->query("te", $te0);
$te1 = [];
for ($i = 0; $i < $te->length; $i++) {
$te1[] = $te->item($i);
}
foreach ($te1 as $tei) {
$th->appendChild($tei);
$this->fixThesaurus2($domth, $tei, 0, $unicode);
}
$te0->parentNode->removeChild($te0);
}
$ct->setAttribute("version", $version = "2.0.0");
$th->setAttribute("version", "2.0.0");
$th->setAttribute("creation_date", $now = date("YmdHis"));
$th->setAttribute("modification_date", $now);
$version = "2.0.0";
}
return $version;
}
/**
* Returns array, containing detailed results for any Google search.
*
* @access private
* @param string $query String, containing the search query.
* @param string $tld String, containing the desired Google top level domain.
* @return array Returns array, containing the keys 'URL', 'Title' and 'Description'.
*/
public static function googleArray($query)
{
$result = array();
$pages = 1;
$delay = 0;
for ($start = 0; $start < $pages; $start++) {
$url = 'http://www.google.' . GOOGLE_TLD . '/custom?q=' . $query . '&filter=0' . '&num=100' . ($start == 0 ? '' : '&start=' . $start . '00');
$str = SEOstats::cURL($url);
if (preg_match("#answer=86640#i", $str)) {
$e = 'Please read: http://www.google.com/support/websearch/' . 'bin/answer.py?&answer=86640&hl=en';
throw new SEOstatsException($e);
} else {
$html = new DOMDocument();
@$html->loadHtml($str);
$xpath = new DOMXPath($html);
$links = $xpath->query("//div[@class='g']//a");
$descs = $xpath->query("//td[@class='j']//div[@class='std']");
$i = 0;
foreach ($links as $link) {
if (!preg_match('#cache#si', $link->textContent) && !preg_match('#similar#si', $link->textContent)) {
$result[] = array('url' => $link->getAttribute('href'), 'title' => utf8_decode($link->textContent), 'descr' => utf8_decode($descs->item($i)->textContent));
$i++;
}
}
if (preg_match('#<div id="nn"><\\/div>#i', $str) || preg_match('#<div id=nn><\\/div>#i', $str)) {
$pages += 1;
$delay += 200000;
usleep($delay);
} else {
$pages -= 1;
}
}
}
return $result;
}
/**
* Exclude some html parts by class inside content wrapped with TYPO3SEARCH_begin and TYPO3SEARCH_end
* markers.
*
* @param string $indexableContent HTML markup
* @return string HTML
*/
public function excludeContentByClass($indexableContent)
{
if (empty(trim($indexableContent))) {
return html_entity_decode($indexableContent);
}
$excludeClasses = $this->getConfiguration()->getIndexQueuePagesExcludeContentByClassArray();
if (count($excludeClasses) === 0) {
return html_entity_decode($indexableContent);
}
$isInContent = Util::containsOneOfTheStrings($indexableContent, $excludeClasses);
if (!$isInContent) {
return html_entity_decode($indexableContent);
}
$doc = new \DOMDocument('1.0', 'UTF-8');
libxml_use_internal_errors(true);
$doc->loadHTML('<?xml version="1.0" encoding="UTF-8"?>' . PHP_EOL . $indexableContent);
$xpath = new \DOMXPath($doc);
foreach ($excludeClasses as $excludePart) {
$elements = $xpath->query("//*[contains(@class,'" . $excludePart . "')]");
if (count($elements) == 0) {
continue;
}
foreach ($elements as $element) {
$element->parentNode->removeChild($element);
}
}
$html = $doc->saveHTML($doc->documentElement->parentNode);
// remove XML-Preamble, newlines and doctype
$html = preg_replace('/(<\\?xml[^>]+\\?>|\\r?\\n|<!DOCTYPE.+?>)/imS', '', $html);
$html = str_replace(array('<html>', '</html>', '<body>', '</body>'), array('', '', '', ''), $html);
return $html;
}
function ConsultarCEP($cep)
{
$url = 'http://www.buscacep.correios.com.br/sistemas/buscacep/resultadoBuscaCepEndereco.cfm';
$fields = array('relaxation' => urlencode(intval($cep)), 'tipoCEP' => urlencode('ALL'), 'semelhante' => urlencode('N'));
$fields_string = '';
foreach ($fields as $key => $value) {
$fields_string .= $key . '=' . $value . '&';
}
rtrim($fields_string, '&');
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_POST, count($fields));
curl_setopt($ch, CURLOPT_POSTFIELDS, $fields_string);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE);
$result = utf8_decode(curl_exec($ch));
curl_close($ch);
$doc = new DOMDocument();
$doc->preserveWhiteSpace = false;
$doc->strictErrorChecking = false;
$doc->recover = true;
$doc->loadHTML(mb_convert_encoding($result, 'HTML-ENTITIES', 'UTF-8'));
$xpath = new DOMXPath($doc);
$query = "//table[@class='tmptabela']//td";
$entries = $xpath->query($query);
$uf = explode('/', $entries->item(2)->nodeValue)[1];
$cidade = explode('/', $entries->item(2)->nodeValue)[0];
$bairro = substr($entries->item(1)->nodeValue, 0, -2);
$logradouro = substr($entries->item(0)->nodeValue, 0, -2);
$return = array('uf' => trim($uf), 'cidade' => trim($cidade), 'bairro' => trim($bairro), 'logradouro' => trim($logradouro));
if (!empty($return)) {
return $return;
} else {
return false;
}
}
protected function parseSpecificContributions(&$contribNode)
{
parent::parseSpecificContributions($contribNode);
if ($contribNode->nodeName != "actions") {
return;
}
$actionXpath = new DOMXPath($contribNode->ownerDocument);
if (!isset($this->options["FTP_LOGIN_SCREEN"]) || $this->options["FTP_LOGIN_SCREEN"] != "TRUE" || $this->options["FTP_LOGIN_SCREEN"] === false) {
// Remove "ftp_login" && "ftp_set_data" actions
$nodeList = $actionXpath->query('action[@name="dynamic_login"]', $contribNode);
if (!$nodeList->length) {
return;
}
unset($this->actions["dynamic_login"]);
$contribNode->removeChild($nodeList->item(0));
$nodeList = $actionXpath->query('action[@name="ftp_set_data"]', $contribNode);
if (!$nodeList->length) {
return;
}
unset($this->actions["ftp_set_data"]);
$contribNode->removeChild($node = $nodeList->item(0));
} else {
// Replace "login" by "dynamic_login"
$loginList = $actionXpath->query('action[@name="login"]', $contribNode);
if ($loginList->length && $loginList->item(0)->getAttribute("auth_ftp_impl") == null) {
$contribNode->removeChild($loginList->item(0));
}
$dynaLoginList = $actionXpath->query('action[@name="dynamic_login"]', $contribNode);
if ($dynaLoginList->length) {
$dynaLoginList->item(0)->setAttribute("name", "login");
$dynaLoginList->item(0)->setAttribute("auth_ftp_impl", "true");
}
}
}
/**
* Find all return tags that contain 'self' or '$this' and replace those
* terms for the name of the current class' type.
*
* @param \DOMDocument $xml Structure source to apply behaviour onto.
*
* @return \DOMDocument
*/
public function process(\DOMDocument $xml)
{
$this->log('Linking to license URLs in @license tags');
$licenseMap = array('#^\\s*(GPL|GNU General Public License)((\\s?v?|version)?2)\\s*$#i' => 'http://opensource.org/licenses/GPL-2.0', '#^\\s*(GPL|GNU General Public License)((\\s?v?|version)?3?)\\s*$#i' => 'http://opensource.org/licenses/GPL-3.0', '#^\\s*(LGPL|GNU (Lesser|Library) (General Public License|GPL))' . '((\\s?v?|version)?2(\\.1)?)\\s*$#i' => 'http://opensource.org/licenses/LGPL-2.1', '#^\\s*(LGPL|GNU (Lesser|Library) (General Public License|GPL))' . '((\\s?v?|version)?3?)\\s*$#i' => 'http://opensource.org/licenses/LGPL-3.0', '#^\\s*((new |revised |modified |three-clause |3-clause )BSD' . '( License)?)\\s*$#i' => 'http://opensource.org/licenses/BSD-3-Clause', '#^\\s*((simplified |two-clause |2-clause |Free)BSD)( License)?\\s*$#i' => 'http://opensource.org/licenses/BSD-2-Clause', '#^\\s*MIT( License)?\\s*$#i' => 'http://opensource.org/licenses/MIT');
$xpath = new \DOMXPath($xml);
$nodes = $xpath->query('//tag[@name="license"]/@description');
/** @var \DOMElement $node */
foreach ($nodes as $node) {
$license = $node->nodeValue;
// FIXME: migrate to '#^' . PHPDOC::LINK_REGEX . '(\s+(?P<text>.+))
// ?$#u' once that const exists
if (preg_match('#^(?i)\\b(?P<url>(?:https?://|www\\d{0,3}[.]|[a-z0-9.\\-]+[.]' . '[a-z]{2,4}/)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))+' . '(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|' . '[^\\s`!()\\[\\]{};:\'".,<>?«»“”‘’]))(\\s+(?P<text>.+))?$#u', $license, $matches)) {
if (!isset($matches['text']) || !$matches['text']) {
// set text to URL if not present
$matches['text'] = $matches['url'];
}
$node->parentNode->setAttribute('link', $matches['url']);
$node->nodeValue = $matches['text'];
// bail out early
continue;
}
// check map if any license matches
foreach ($licenseMap as $regex => $url) {
if (preg_match($regex, $license, $matches)) {
$node->parentNode->setAttribute('link', $url);
// we're done here
break;
}
}
}
return $xml;
}
function hook_article_filter($article)
{
$owner_uid = $article["owner_uid"];
if (strpos($article["guid"], "dilbert.com") !== FALSE) {
if (strpos($article["plugin_data"], "dilbert,{$owner_uid}:") === FALSE) {
$doc = new DOMDocument();
@$doc->loadHTML(fetch_file_contents($article["link"]));
$basenode = false;
if ($doc) {
$xpath = new DOMXPath($doc);
$entries = $xpath->query('(//img[@src])');
// we might also check for img[@class='strip'] I guess...
$matches = array();
foreach ($entries as $entry) {
if (preg_match("/dyn\\/str_strip\\/.*zoom\\.gif\$/", $entry->getAttribute("src"), $matches)) {
$entry->setAttribute("src", rewrite_relative_url("http://dilbert.com/", $matches[0]));
$basenode = $entry;
break;
}
}
if ($basenode) {
$article["content"] = $doc->saveXML($basenode);
$article["plugin_data"] = "dilbert,{$owner_uid}:" . $article["plugin_data"];
}
}
} else {
if (isset($article["stored"]["content"])) {
$article["content"] = $article["stored"]["content"];
}
}
}
return $article;
}
function xsl_transform($filename, $xslname = null)
{
// Get the original XML document
$xml = new DOMDocument();
$xml->load($filename);
if ($xslname == null) {
// extract bound stylesheet from embedded link
$xp = new DOMXPath($xml);
// use xpath to get the directive
$pi = $xp->evaluate('/processing-instruction("xml-stylesheet")')->item(0);
// extract the "data" part of it
$data = $pi->data;
// find out where the href starts
$start = strpos($data, 'href=');
// and extract the stylesheet name
$xslname = XML_FOLDER . substr($data, $start + 6, -1);
}
// load the XSL stylesheet
$xsl = new DOMDocument();
$xsl->load($xslname);
// prime the transform engine
$xslt = new XSLTProcessor();
$xslt->importStyleSheet($xsl);
// and away we go!
return $xslt->transformToXml($xml);
}
/**
* Constructs a new object object from DOM Document.
*
* @param DomDocument $dom the ReST fragment for this object
*/
public function __construct(DomDocument $dom)
{
$xpath = new DOMXPath($dom);
/**
* @see Zend_Service_Technorati_Author
*/
require_once 'Zend/Service/Technorati/Author.php';
$result = $xpath->query('//result');
if ($result->length == 1) {
$this->_author = new Zend_Service_Technorati_Author($result->item(0));
}
/**
* @see Zend_Service_Technorati_Weblog
*/
require_once 'Zend/Service/Technorati/Weblog.php';
$result = $xpath->query('//item/weblog');
if ($result->length >= 1) {
foreach ($result as $weblog) {
$this->_weblogs[] = new Zend_Service_Technorati_Weblog($weblog);
}
}
}
public function getNames($ids, &$names) {
$result = false;
$names = array();
$onlinePlayers = 0;
$params = array();
$params["version"] = "2";
$params["ids"] = implode(",", $ids);
if ($this->request("/eve/CharacterName.xml.aspx", $params)) {
$domPath = new DOMXPath($this->document);
$nodes = $domPath->query("descendant::rowset[@name='characters']/row");
foreach ($nodes as $node) {
$id = $node->getAttribute("characterID");
$name = $node->getAttribute("name");
$names[$id] = $name;
}
if (count($ids) == count($names))
$result = true;
}
return $result;
}
public function process(array $documents, &$context)
{
$document = $documents[self::URL_MEDIA];
$dom = self::getDOM($document);
$xpath = new DOMXPath($dom);
Database::delete('mediarelation', ['media_id' => $context->media->id]);
$data = [];
foreach ($xpath->query('//table[@class=\'anime_detail_related_anime\']/tr') as $node) {
$typeMal = strtolower(Strings::removeSpaces($node->childNodes[0]->textContent));
$type = Strings::makeEnum($typeMal, ['adaptation' => MediaRelation::Adaptation, 'alternative setting' => MediaRelation::AlternativeSetting, 'alternative version' => MediaRelation::AlternativeVersion, 'character' => MediaRelation::Character, 'full story' => MediaRelation::FullStory, 'other' => MediaRelation::Other, 'parent story' => MediaRelation::ParentStory, 'prequel' => MediaRelation::Prequel, 'sequel' => MediaRelation::Sequel, 'side story' => MediaRelation::SideStory, 'spin-off' => MediaRelation::SpinOff, 'summary' => MediaRelation::Summary], null);
if ($type === null) {
throw new BadProcessorDocumentException($document, 'unknown relation type: ' . $typeMal);
}
$links = $node->childNodes[1]->getElementsByTagName('a');
foreach ($links as $link) {
$link = $link->getAttribute('href');
if (preg_match('#^/(anime|manga)/([0-9]+)/#', $link, $matches)) {
$idMal = Strings::makeInteger($matches[2]);
if ($matches[1] === 'anime') {
$media = Media::Anime;
} elseif ($matches[1] === 'manga') {
$media = Media::Manga;
}
$data[] = ['media_id' => $context->media->id, 'mal_id' => $idMal, 'media' => $media, 'type' => $type];
}
}
}
Database::insert('mediarelation', $data);
$context->relationData = $data;
}
function addTrustedClient($ip, $desc, $appId)
{
$requestURI = $this->PIDS_SERVICE_BASE_URI . 'addClient';
$requestURI .= "?ip=" . $ip . "&desc=" . $desc;
$requestURI .= strlen($appId) == 40 ? "&appId=" . $appId : '';
$response = file_get_contents($requestURI);
$result_array = array();
if (!$response) {
$result_array['errorMessages'] = "Error whilst attempting to fetch from URI: " . $this->PIDS_SERVICE_BASE_URI;
} else {
$responseDOMDoc = new DOMDocument();
$result = $responseDOMDoc->loadXML($response);
if ($result) {
$messageType = strtoupper($responseDOMDoc->getElementsByTagName("response")->item(0)->getAttribute("type"));
if ($messageType == 'SUCCESS') {
$xPath = new DOMXPath($responseDOMDoc);
$nodeList = $xPath->query("//property[@name='appId']");
$appId = $nodeList->item(0)->getAttribute("value");
if (strlen($appId) == 40) {
$result_array['app_id'] = $appId;
} else {
$result_array['errorMessages'] = "Could not extract appId. Status of request unknown.<br/>";
}
} elseif ($messageType == 'FAILURE') {
foreach ($responseDOMDoc->getElementsByTagName("response")->item(0)->getElementsByTagName("message") as $message) {
$result_array['errorMessages'] = $message->nodeValue . "<br/>";
}
}
} else {
$result_array['errorMessages'] = "Error whilst attempting to load XML response. Response could not be parsed.";
}
}
return $result_array;
}
protected function describeAnalysis(Analysis $analysis, array $options = array())
{
$output = $options['output'];
$xml = new \DOMDocument('1.0', 'UTF-8');
$xpath = new \DOMXPath($xml);
$xml->formatOutput = true;
$xml->preserveWhiteSpace = true;
$pmd = $xml->createElement('pmd');
$pmd->setAttribute('timestamp', $analysis->getEndAt()->format('c'));
$xml->appendChild($pmd);
foreach ($analysis->getViolations() as $violation) {
/**
* @var $violation \SensioLabs\Insight\Sdk\Model\Violation
*/
$filename = $violation->getResource();
$nodes = $xpath->query(sprintf('//file[@name="%s"]', $filename));
if ($nodes->length > 0) {
$node = $nodes->item(0);
} else {
$node = $xml->createElement('file');
$node->setAttribute('name', $filename);
$pmd->appendChild($node);
}
$violationNode = $xml->createElement('violation', $violation->getMessage());
$node->appendChild($violationNode);
$violationNode->setAttribute('beginline', $violation->getLine());
$violationNode->setAttribute('endline', $violation->getLine());
$violationNode->setAttribute('rule', $violation->getTitle());
$violationNode->setAttribute('ruleset', $violation->getCategory());
$violationNode->setAttribute('priority', $this->getPriority($violation));
}
$output->writeln($xml->saveXML());
}
/**
* get rendered menu and adds drop down markup
*
* @param string $html rendered navigation
* @param string $class css class to check for adding drop down
*
* @return string
*/
public function __invoke($html, $class = 'toplevel', $toggle = false)
{
$domDoc = new \DOMDocument('1.0', 'utf-8');
$domDoc->loadXML('<?xml version="1.0" encoding="utf-8"?>' . $html);
$xpath = new \DOMXPath($domDoc);
foreach ($xpath->query('//a[starts-with(@class, "' . $class . '")]') as $item) {
$result = $xpath->query('../ul', $item);
if ($result->length === 1) {
$ul = $result->item(0);
$ul->setAttribute('class', 'dropdown-menu');
$li = $item->parentNode;
$li->setAttribute('id', substr($item->getAttribute('href'), 1));
if (($existingClass = $li->getAttribute('class')) !== '') {
$li->setAttribute('class', $existingClass . ' dropdown');
} else {
$li->setAttribute('class', 'dropdown');
}
if ($toggle) {
$item->setAttribute('data-toggle', 'dropdown');
}
if (($existingClass = $item->getAttribute('class')) !== '') {
$item->setAttribute('class', $item->getAttribute('class') . ' dropdown-toggle');
} else {
$item->setAttribute('class', 'dropdown-toggle');
}
$space = $domDoc->createTextNode(' ');
$item->appendChild($space);
$caret = $domDoc->createElement('b', '');
$caret->setAttribute('class', 'caret');
$item->appendChild($caret);
}
}
return $domDoc->saveXML($xpath->query('/ul')->item(0), LIBXML_NOEMPTYTAG);
}
/**
* Filter XHtml document
*
* Filter for the document, which may modify / restructure a document and
* assign semantic information bits to the elements in the tree.
*
* @param DOMDocument $document
* @return DOMDocument
*/
public function filter(DOMDocument $document)
{
$xpath = new DOMXPath($document);
// Find all tables
$tables = $xpath->query('//*[local-name() = "table"]');
foreach ($tables as $table) {
// Ignore tables, which again contain tables, as these most
// probably contain the website content somehow.
if ($xpath->query('.//*[local-name() = "table"]', $table)->length > 0) {
continue;
}
// Extract all cells from the table and check what they contain
$cells = $xpath->query('.//*[local-name() = "td"] | .//*[local-name() = "th"]', $table);
$cellCount = $cells->length;
$cellContentCount = 0;
foreach ($cells as $cell) {
$cellContentCount += (int) $this->cellHasContent($cell);
}
// Completely remove table, if it does not meet the configured
// expectations
if ($cellContentCount / $cellCount < $this->threshold) {
$table->parentNode->removeChild($table);
continue;
}
// Tables with only one column are most probably also used only for
// layout. We remove them, too.
if ($xpath->query('.//*[local-name() = "tr"]', $table)->length >= $cellCount) {
$table->parentNode->removeChild($table);
continue;
}
}
}
function hook_article_filter($article)
{
if (strpos($article["link"], "titanic-magazin.de") !== FALSE) {
$doc = new DOMDocument();
@$doc->loadHTML(mb_convert_encoding(fetch_file_contents($article["link"]), 'HTML-ENTITIES', "UTF-8"));
$basenode = false;
if ($doc) {
$xpath = new DOMXPath($doc);
// first remove advertisement + tracking stuff
$stuff = $xpath->query('(//script)|(//noscript)|(//form)|(//a[@name="form"])|(//p)|(//a[@href="newsticker.html"])');
foreach ($stuff as $removethis) {
if ($removethis->localName === "p") {
if ($removethis->textContent == "bezahlte Anzeige") {
$removethis->parentNode->removeChild($removethis);
}
} else {
$removethis->parentNode->removeChild($removethis);
}
}
// now get the (cleaned) article
$entries = $xpath->query('(//div[@class="tt_news-bodytext"])');
foreach ($entries as $entry) {
$basenode = $entry;
break;
}
if ($basenode) {
$article["content"] = $doc->saveXML($basenode);
}
}
}
return $article;
}