diff --git a/base.php b/base.php index b2c0c98..a1b7e7c 100644 --- a/base.php +++ b/base.php @@ -28,19 +28,6 @@ function xml2xhtml($xml) { '), $xml); } -function is_utf8($string) { -return preg_match('%^(?: -[\x09\x0A\x0D\x20-\x7E] # ASCII -| [\xC2-\xDF][\x80-\xBF] # non-overlong 2-byte -| \xE0[\xA0-\xBF][\x80-\xBF] # excluding overlongs -| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # straight 3-byte -| \xED[\x80-\x9F][\x80-\xBF] # excluding surrogates -| \xF0[\x90-\xBF][\x80-\xBF]{2} # planes 1-3 -| [\xF1-\xF3][\x80-\xBF]{3} # planes 4-15 -| \xF4[\x80-\x8F][\x80-\xBF]{2} # plane 16 -)*$%xs', $string); -} - function display_xml_error($error) { $return .= str_repeat('-', $error->column) . "^\n"; @@ -81,7 +68,6 @@ function are_libxml_errors_ok () function html2xhtml ($html) { $doc = new DOMDocument(); libxml_use_internal_errors(true); - if (is_utf8($html)) { $doc->loadHTML('
' . $html . ''); // Load the HTML $output = $doc->saveXML($doc->documentElement); // Transform to an Ansi xml stream @@ -89,16 +75,6 @@ function html2xhtml ($html) { if (preg_match ('#(.*)#ms', $output, $matches)) { $output = $matches [1]; // Remove } - } else { - $doc->loadHTML($html); // Load the HTML - $output = $doc->saveXML($doc->documentElement); // Transform to an Ansi xml stream - $output = xml2xhtml($output); - $output = xml2xhtml($output); - if (preg_match ('#(.*)#ms', $output, $matches)) { - $output = $matches [1]; // Remove - } - } - /* // In case of error with summary, use it to debug $errors = libxml_get_errors(); @@ -110,7 +86,7 @@ function html2xhtml ($html) { if (!are_libxml_errors_ok ()) $output = "HTML code not valid."; - + libxml_use_internal_errors(false); return $output; }