Fixes #70

mmikkel · Oct 21, 2024 · d482cf2 · d482cf2
1 parent dcd459a
commit d482cf2
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 4 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,7 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/) and this p
 ## Unreleased
 ### Fixed 
 - Fixed an issue where the `retconAutoAlt` filter didn't work as intended [#71](https://github.com/mmikkel/Retcon-Craft/issues/71)
+- Fixed an issue where Retcon would convert UTF-8 non-breaking spaces to HTML entities, preventing filters like `retconRemoveEmpty` from working correctly in all cases [#70](https://github.com/mmikkel/Retcon-Craft/issues/70)
 
 ## 3.2.0 - 2024-06-28
 ### Improved  

diff --git a/src/library/RetconDom.php b/src/library/RetconDom.php
@@ -43,16 +43,16 @@ class RetconDom
      */
     public function __construct($html)
     {
-        $html = (string)$html;
-        $libxmlUseInternalErrors = \libxml_use_internal_errors(true);
-        $content = \mb_convert_encoding($html, 'HTML-ENTITIES', Craft::$app->getView()->getTwig()->getCharset());
+        $html = str_replace("\xc2\xa0", ' ', (string)$html); // Make sure UTF-8 non-breaking spaces are replaced with regular spaces
+        $libxmlUseInternalErrors = libxml_use_internal_errors(true);
+        $content = mb_convert_encoding($html, 'HTML-ENTITIES', Craft::$app->getView()->getTwig()->getCharset());
         $this->doc = new \DOMDocument();
         $this->doc->loadHTML("<html><retcon>$content</retcon></html>", LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
         $this->crawler = new Crawler($this->doc);
         $this->html5 = new HTML5([
             'encode_entities' => false,
         ]);
-        \libxml_use_internal_errors($libxmlUseInternalErrors);
+        libxml_use_internal_errors($libxmlUseInternalErrors);
     }
 
     /**