Ported ListDiff to DOMDocument

Ported ListDiff to DOMDocument

Author: SavageTiger

README.md

@@ -199,8 +199,8 @@ php-htmldiff is available under [GNU General Public License, version 2][gnu]. Se
 * Performance improvements (we have 1 benchmark test, we should probably get more)
     * Algorithm improvements - trimming alike text at start and ends, store nested diff results in memory to re-use (like we do w/ caching)
     * Benchmark using DOMDocument vs. alternatives vs. string parsing
+    * Consider not using string parsing for HtmlDiff in order to avoid having to create many DOMDocument instances in ListDiff and TableDiff
 * Benchmarking
-* Look into removing dependency on php-simple-html-dom-parser library - possibly find alternative or no library at all. Consider how this affects performance.
 * Refactoring (but... tests first)
     * Overall design/architecture improvements
     * API improvements so a new HtmlDiff isn't required for each new diff (especially so that configuration can be re-used)

composer.json

@@ -21,7 +21,8 @@
     "require": {
         "php": ">=7.3",
         "ezyang/htmlpurifier": "^4.7",
-        "kub-at/php-simple-html-dom-parser": "^1.7"
+        "ext-dom": "*",
+        "ext-mbstring": "*"
     },
     "require-dev": {
         "phpunit/phpunit": "~9.0",

lib/Caxy/HtmlDiff/AbstractDiff.php

@@ -3,6 +3,8 @@
 namespace Caxy\HtmlDiff;
 
 use Caxy\HtmlDiff\Util\MbStringUtil;
+use HTMLPurifier;
+use HTMLPurifier_Config;
 
 /**
  * Class AbstractDiff.
@@ -66,12 +68,12 @@ abstract class AbstractDiff
     protected $diffCaches = array();
 
     /**
-     * @var \HTMLPurifier|null
+     * @var HTMLPurifier|null
      */
     protected $purifier;
 
     /**
-     * @var \HTMLPurifier_Config|null
+     * @var HTMLPurifier_Config|null
      */
     protected $purifierConfig = null;
 
@@ -129,7 +131,7 @@ public function initPurifier($defaultPurifierSerializerCache = null)
         if (null !== $this->purifierConfig) {
             $HTMLPurifierConfig  = $this->purifierConfig;
         } else {
-            $HTMLPurifierConfig = \HTMLPurifier_Config::createDefault();
+            $HTMLPurifierConfig = HTMLPurifier_Config::createDefault();
         }
 
         // Cache.SerializerPath defaults to Null and sets
@@ -144,7 +146,7 @@ public function initPurifier($defaultPurifierSerializerCache = null)
         // created by the web/php user (www-user, php-fpm, etc.)
         $HTMLPurifierConfig->set('Cache.SerializerPermissions', 0777);
 
-        $this->purifier = new \HTMLPurifier($HTMLPurifierConfig);
+        $this->purifier = new HTMLPurifier($HTMLPurifierConfig);
     }
 
     /**
@@ -373,33 +375,13 @@ public function isGroupDiffs()
     }
 
     /**
-     * @param \HTMLPurifier_Config $config
+     * @param HTMLPurifier_Config $config
      */
-    public function setHTMLPurifierConfig(\HTMLPurifier_Config $config)
+    public function setHTMLPurifierConfig(HTMLPurifier_Config $config)
     {
         $this->purifierConfig = $config;
     }
 
-    /**
-     * @param string $tag
-     *
-     * @return string
-     */
-    protected function getOpeningTag($tag)
-    {
-        return '/<'.$tag.'[^>]*/i';
-    }
-
-    /**
-     * @param string $tag
-     *
-     * @return string
-     */
-    protected function getClosingTag($tag)
-    {
-        return '</'.$tag.'>';
-    }
-
     /**
      * @param string $html
      *

lib/Caxy/HtmlDiff/HtmlDiff.php

@@ -291,6 +291,7 @@ protected function processInsertOperation($operation, $cssClass)
                 }
             }
         }
+
         $this->insertTag('ins', $cssClass, $text);
     }
 
@@ -544,8 +545,7 @@ protected function insertTag($tag, $cssClass, &$words)
             $specialCaseTagInjectionIsBefore = false;
 
             if (count($nonTags) !== 0) {
-                $text = $this->wrapText(implode('', $nonTags), $tag, $cssClass);
-                $this->content .= $text;
+                $this->content .= $this->wrapText(implode('', $nonTags), $tag, $cssClass);
             } else {
                 $firstOrDefault = false;
                 foreach ($this->config->getSpecialCaseOpeningTags() as $x) {
@@ -615,15 +615,12 @@ protected function checkCondition($word, $condition)
         return $condition == 'tag' ? $this->isTag($word) : !$this->isTag($word);
     }
 
-    /**
-     * @param string $text
-     * @param string $tagName
-     * @param string $cssClass
-     *
-     * @return string
-     */
-    protected function wrapText($text, $tagName, $cssClass)
+    protected function wrapText(string $text, string $tagName, string $cssClass) : string
     {
+        if (trim($text) === '') {
+            return '';
+        }
+
         return sprintf('<%1$s class="%2$s">%3$s</%1$s>', $tagName, $cssClass, $text);
     }