- Patch #878408 by pwolanin, Damien Tournoud: replace decode_entities() with...

- Patch #878408 by pwolanin, Damien Tournoud: replace decode_entities() with built-in html_entity_decode().

includes/unicode.inc

@@ -422,94 +422,12 @@ function _mime_header_decode($matches) {
  *
  * @param $text
  *   The text to decode entities in.
- * @param $exclude
- *   An array of characters which should not be decoded. For example,
- *   array('<', '&', '"'). This affects both named and numerical entities.
  *
  * @return
  *   The input $text, with all HTML entities decoded once.
  */
-function decode_entities($text, $exclude = array()) {
-  // Flip the exclude list so that we can do quick lookups later.
-  $exclude = array_flip($exclude);
-
-  // Prepare the callback function.
-  _decode_entities(NULL, $exclude);
-
-  // Use a regexp to select all entities in one pass, to avoid decoding
-  // double-escaped entities twice.
-  return preg_replace_callback('/&(#x?)?([A-Za-z0-9]+);/', '_decode_entities', $text);
-}
-
-/**
- * Helper function for decode_entities
- *
- * @param $matches
- *   An array of matches found by preg_replace_callback(). Elements 0, 1, and 2
- *   of $matches must be the original entity, its prefix, and its codepoint.
- * @param $set_exclude
- *   An array of entities that should be excluded from decoding. This should
- *   only be set during a preparatory call before preg_replace_callback().
- *
- * @return
- *   The decoded entity for a given match, or the original encoded entity if
- *   the entity is in the list of excluded entities.
- */
-function _decode_entities($matches = NULL, $set_exclude = NULL) {
-  static $html_entities, $exclude;
-  if (!isset($html_entities)) {
-    include DRUPAL_ROOT . '/includes/unicode.entities.inc';
-  }
-  if (isset($set_exclude)) {
-    // This is a preparatory call.
-    $exclude = $set_exclude;
-    return;
-  }
-  list($original, $prefix, $codepoint) = $matches;
-  // Named entity
-  if (!$prefix) {
-    // A named entity not in the exclude list.
-    if (isset($html_entities[$original]) && !isset($exclude[$html_entities[$original]])) {
-      return $html_entities[$original];
-    }
-    else {
-      return $original;
-    }
-  }
-  // Hexadecimal numerical entity
-  if ($prefix == '#x') {
-    $codepoint = base_convert($codepoint, 16, 10);
-  }
-  // Decimal numerical entity (strip leading zeros to avoid PHP octal notation)
-  else {
-    $codepoint = preg_replace('/^0+/', '', $codepoint);
-  }
-  // Encode codepoint as UTF-8 bytes
-  if ($codepoint < 0x80) {
-    $str = chr($codepoint);
-  }
-  elseif ($codepoint < 0x800) {
-    $str = chr(0xC0 | ($codepoint >> 6))
-         . chr(0x80 | ($codepoint & 0x3F));
-  }
-  elseif ($codepoint < 0x10000) {
-    $str = chr(0xE0 | ( $codepoint >> 12))
-         . chr(0x80 | (($codepoint >> 6) & 0x3F))
-         . chr(0x80 | ( $codepoint       & 0x3F));
-  }
-  elseif ($codepoint < 0x200000) {
-    $str = chr(0xF0 | ( $codepoint >> 18))
-         . chr(0x80 | (($codepoint >> 12) & 0x3F))
-         . chr(0x80 | (($codepoint >> 6)  & 0x3F))
-         . chr(0x80 | ( $codepoint        & 0x3F));
-  }
-  // Check for excluded characters
-  if (isset($exclude[$str])) {
-    return $original;
-  }
-  else {
-    return $str;
-  }
+function decode_entities($text) {
+  return html_entity_decode($text, ENT_QUOTES, 'UTF-8');
 }
 
 /**

modules/simpletest/tests/unicode.test

@@ -218,36 +218,6 @@ class UnicodeUnitTest extends DrupalWebTestCase {
     }
   }
 
-  function testDecodeEntitiesExclusion() {
-    $testcase = array(
-      'Drupal' => 'Drupal',
-      '<script>' => '<script>',
-      '&lt;script&gt;' => '&lt;script>',
-      '&#60;script&#62;' => '&#60;script>',
-      '&amp;lt;script&amp;gt;' => '&amp;lt;script&amp;gt;',
-      '"' => '"',
-      '&#34;' => '&#34;',
-      '&amp;#34;' => '&amp;#34;',
-      '&quot;' => '&quot;',
-      '&amp;quot;' => '&amp;quot;',
-      "'" => "'",
-      '&#39;' => "'",
-      '&amp;#39;' => '&amp;#39;',
-      '©' => '©',
-      '&copy;' => '©',
-      '&#169;' => '©',
-      '→' => '→',
-      '&#8594;' => '→',
-      '➼' => '➼',
-      '&#10172;' => '➼',
-      '&euro;' => '€',
-    );
-    $exclude = array('<', '&', '"');
-    foreach ($testcase as $input => $output) {
-      $this->assertIdentical(decode_entities($input, $exclude), $output, t('Make sure the decoded entity of %input, excluding %excludes, is %output', array('%input' => $input, '%excludes' => implode(',', $exclude), '%output' => $output)));
-    }
-  }
-
   /**
    * Tests truncate_utf8().
    */