diff options
| -rw-r--r-- | includes/common.inc | 14 |
1 files changed, 12 insertions, 2 deletions
diff --git a/includes/common.inc b/includes/common.inc index bae9c2554..0fc380eef 100644 --- a/includes/common.inc +++ b/includes/common.inc @@ -1710,7 +1710,7 @@ function drupal_map_assoc($array, $function = NULL) { * be used instead of xml_parser_create(), because PHP's XML parser doesn't check * the input encoding itself. * - * This is also where unsupported encodings should be converted. + * This is also where unsupported encodings will be converted. * Callers should take this into account: $data might have been changed after * the call. * @@ -1720,8 +1720,18 @@ function drupal_map_assoc($array, $function = NULL) { * An XML parser object. */ function drupal_xml_parser_create(&$data) { + // Default XML encoding is UTF-8 $encoding = 'utf-8'; - if (ereg('^<\?xml[^>]+encoding="([^"]+)"', $data, $match)) { + $bom = false; + + // Check for UTF-8 byte order mark (PHP5's XML parser doesn't handle it). + if (!strncmp($data, "\xEF\xBB\xBF", 3)) { + $bom = true; + $data = substr($data, 3); + } + + // Check for an encoding declaration in the XML prolog if no BOM was found. + if (!$bom && ereg('^<\?xml[^>]+encoding="([^"]+)"', $data, $match)) { $encoding = $match[1]; } |