Helper function for decode_entities

File

drupal-6.x/includes/unicode.inc, line 355

Code

function _decode_entities($prefix, $codepoint, $original, &$html_entities, &$exclude) {
  // Named entity
  if (!$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);
  }
  else if ($codepoint < 0x800) {
    $str = chr(0xC0 | ($codepoint >> 6))
      . chr(0x80 | ($codepoint & 0x3F));
  }
  else if ($codepoint < 0x10000) {
    $str = chr(0xE0 | ($codepoint >> 12))
      . chr(0x80 | (($codepoint >> 6) & 0x3F))
      . chr(0x80 | ($codepoint & 0x3F));
  }
  else if ($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;
  }
}