- Patch #212130 by Damien Tournoud, grendzy: decode_entities() should support all (X)HTML entities.

1 files changed, 13 insertions, 16 deletions

diff --git a/includes/unicode.inc b/includes/unicode.inc
index d9b81f062..f25f472d2 100644
--- a/includes/unicode.inc
+++ b/includes/unicode.inc
@@ -323,33 +323,30 @@ function _mime_header_decode($matches) {
  *   array('<', '&', '"'). This affects both named and numerical entities.
  */
 function decode_entities($text, $exclude = array()) {
-  static $table;
-  // We store named entities in a table for quick processing.
-  if (!isset($table)) {
-    // Get all named HTML entities.
-    $table = array_flip(get_html_translation_table(HTML_ENTITIES));
-    // PHP gives us ISO-8859-1 data, we need UTF-8.
-    $table = array_map('utf8_encode', $table);
-    // Add apostrophe (XML)
-    $table['&apos;'] = "'";
-  }
-  $newtable = array_diff($table, $exclude);
+  static $html_entities;
+  if (!isset($html_entities)) {
+    include DRUPAL_ROOT . '/includes/unicode.entities.inc';
+  }
+
+  // Flip the exclude list so that we can do quick lookups later.
+  $exclude = array_flip($exclude);
 
   // Use a regexp to select all entities in one pass, to avoid decoding 
   // double-escaped entities twice. The PREG_REPLACE_EVAL modifier 'e' is
   // being used to allow for a callback (see 
   // http://php.net/manual/en/reference.pcre.pattern.modifiers).
-  return preg_replace('/&(#x?)?([A-Za-z0-9]+);/e', '_decode_entities("$1", "$2", "$0", $newtable, $exclude)', $text);
+  return preg_replace('/&(#x?)?([A-Za-z0-9]+);/e', '_decode_entities("$1", "$2", "$0", $html_entities, $exclude)', $text);
 }
 
 /**
  * Helper function for decode_entities
  */
-function _decode_entities($prefix, $codepoint, $original, &$table, &$exclude) {
+function _decode_entities($prefix, $codepoint, $original, &$html_entities, &$exclude) {
   // Named entity
   if (!$prefix) {
-    if (isset($table[$original])) {
-      return $table[$original];
+    // A named entity not in the exclude list.
+    if (isset($html_entities[$original]) && !isset($exclude[$html_entities[$original]])) {
+      return $html_entities[$original];
     }
     else {
       return $original;
@@ -383,7 +380,7 @@ function _decode_entities($prefix, $codepoint, $original, &$table, &$exclude) {
          . chr(0x80 | ( $codepoint        & 0x3F));
   }
   // Check for excluded characters
-  if (in_array($str, $exclude)) {
+  if (isset($exclude[$str])) {
     return $original;
   }
   else {