php/src/gadgets/rewrite/GadgetRewriter.php

   1 <?php
   2 /**
   3  * Licensed to the Apache Software Foundation (ASF) under one
   4  * or more contributor license agreements.  See the NOTICE file
   5  * distributed with this work for additional information
   6  * regarding copyright ownership.  The ASF licenses this file
   7  * to you under the Apache License, Version 2.0 (the
   8  * "License"); you may not use this file except in compliance
   9  * with the License.  You may obtain a copy of the License at
  10  *
  11  *     http://www.apache.org/licenses/LICENSE-2.0
  12  *
  13  * Unless required by applicable law or agreed to in writing,
  14  * software distributed under the License is distributed on an
  15  * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
  16  * KIND, either express or implied.  See the License for the
  17  * specific language governing permissions and limitations
  18  * under the License.
  19  */
  20
  21 /**
  22  * The rewriter meta class, it checks the various gadget and configuration
  23  * settings, and calls the appropiate classes for the registered dom element
  24  * listeners
  25  */
  26 class GadgetRewriter {
  27   private $context;
  28   private $domObservers = array();
  29
  30   public function __construct(GadgetContext $context) {
  31     $this->context = $context;
  32   }
  33
  34   /**
  35    * Does the actual rewrite option scanning and performs the dom parsing
  36    *
  37    * @param string $content
  38    * @param Gadget $gadget
  39    */
  40   public function rewrite($content, Gadget &$gadget) {
  41     // Check to see if the gadget requested rewriting, or if rewriting is forced in the configuration
  42     if (is_array($gadget->gadgetSpec->rewrite) || Config::get('rewrite_by_default')) {
  43       require_once "src/gadgets/rewrite/ContentRewriter.php";
  44       $contentRewriter = new ContentRewriter($this->context, $gadget);
  45       $contentRewriter->register($this);
  46     }
  47
  48     // Are we configured to sanitize certain views? (if so the config should be an array of view names to sanitize, iaw: array('profile', 'home'))
  49     if (is_array(Config::get('sanitize_views'))) {
  50       require_once "src/gadgets/rewrite/SanitizeRewriter.php";
  51       $sanitizeRewriter = new SanitizeRewriter($this->context, $gadget);
  52       $sanitizeRewriter->register($this);
  53     }
  54
  55     // no observers registered, return the original content, otherwise parse the DOM tree and call the observers
  56     if (!count($this->domObservers)) {
  57       return $content;
  58     } else {
  59       libxml_use_internal_errors(true);
  60       $doc = new DOMDocument(null, 'utf-8');
  61       $doc->preserveWhiteSpace = false;
  62       $doc->formatOutput = false;
  63       $doc->strictErrorChecking = false;
  64       $doc->recover = false;
  65       if (! $doc->loadHtml($content)) {
  66         // parsing failed, return the unmodified content
  67         return $content;
  68       }
  69
  70       // find and parse all nodes in the dom document
  71       $rootNodes = $doc->getElementsByTagName('*');
  72       $this->parseNodes($rootNodes);
  73
  74       // DomDocument tries to make the document a valid html document, so added the html/body/head elements to it.. so lets strip them off before returning the content
  75       $html = $doc->saveHTML();
  76       $html = preg_replace('/^<!DOCTYPE.+?>/', '', str_replace(array('&amp;', '<head>', '</head>', '<html>', '</html>', '<body>', '</body>'), array('&', '', '', '', '', '', ''), $html));
  77
  78       // If the gadget specified the caja feature, cajole it
  79       if (in_array('caja', $gadget->features)) {
  80         //TODO : use the caja daemon to cajole the content (experimental patch is available and will be added soon)
  81       }
  82
  83       return $html;
  84     }
  85   }
  86
  87   /**
  88    * This function should be called from the DomRewriter implmentation class in the form of:
  89    * addObserver('img', $this, 'rewriteImage')
  90    *
  91    * @param string $tag
  92    * @param object instance $class
  93    * @param string $function
  94    */
  95   public function addObserver($tag, DomRewriter $class, $function) {
  96     // add the tag => function to call relationship to our $observers array
  97     $this->domObservers[] = array('tag' => $tag, 'class' => $class, 'function' => $function);
  98   }
  99
 100   /**
 101    * Parses the DOMNodeList $nodes and calls the registered rewriting function on nodes
 102    *
 103    * @param DOMNodeList $nodes
 104    */
 105   private function parseNodes(DOMNodeList &$nodes) {
 106     foreach ($nodes as $node) {
 107       $tagName = strtolower($node->tagName);
 108       foreach ($this->domObservers as $observer) {
 109         if ($observer['tag'] == $tagName) {
 110           $class = $observer['class'];
 111           $function = $observer['function'];
 112           $class->$function($node);
 113         }
 114       }
 115     }
 116   }
 117 }