* @see utf8_deaccent() * @package utf8 * @subpackage ascii */ $GLOBALS['UTF8_LOWER_ACCENTS'] = array( 'à ' => 'a', 'ô' => 'o', 'ÄÂ?' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'Å¡' => 's', 'Æ¡' => 'o', 'ß' => 'ss', 'ă' => 'a', 'Ã…â„¢' => 'r', 'È›' => 't', 'ň' => 'n', 'ÄÂ?' => 'a', 'Ä·' => 'k', 'Ã…Â?' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'á¹—' => 'p', 'ó' => 'o', 'ú' => 'u', 'Ä›' => 'e', 'é' => 'e', 'ç' => 'c', 'áºÂ?' => 'w', 'Ä‹' => 'c', 'õ' => 'o', 'ṡ' => 's', 'ø' => 'o', 'Ä£' => 'g', 'ŧ' => 't', 'È™' => 's', 'Ä—' => 'e', 'ĉ' => 'c', 'Å›' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'Ä™' => 'e', 'ŵ' => 'w', 'ṫ' => 't', 'Å«' => 'u', 'ÄÂ?' => 'c', 'ö' => 'oe', 'è' => 'e', 'Å·' => 'y', 'Ä…' => 'a', 'Å‚' => 'l', 'ų' => 'u', 'ů' => 'u', 'ÅŸ' => 's', 'ÄŸ' => 'g', 'ļ' => 'l', 'Æ’' => 'f', 'ž' => 'z', 'ẃ' => 'w', 'ḃ' => 'b', 'Ã¥' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'Ã…Â¥' => 't', 'Å—' => 'r', 'ä' => 'ae', 'í' => 'i', 'Å•' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o', 'Ä“' => 'e', 'ñ' => 'n', 'Å„' => 'n', 'Ä¥' => 'h', 'ÄÂ?' => 'g', 'Ä‘' => 'd', 'ĵ' => 'j', 'ÿ' => 'y', 'Å©' => 'u', 'Å­' => 'u', 'Æ°' => 'u', 'Å£' => 't', 'ý' => 'y', 'Å‘' => 'o', 'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'Ä«' => 'i', 'ã' => 'a', 'Ä¡' => 'g', 'á¹Â?' => 'm', 'Ã…Â?' => 'o', 'Ä©' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a', 'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', ); //--------------------------------------------------------------- /** * UTF-8 lookup table for upper case accented letters * This lookuptable defines replacements for accented characters from the ASCII-7 * range. This are upper case letters only. * @author Andreas Gohr * @see utf8_deaccent() * @package utf8 * @subpackage ascii */ $GLOBALS['UTF8_UPPER_ACCENTS'] = array( 'à ' => 'A', 'ô' => 'O', 'ÄÂ?' => 'D', 'ḟ' => 'F', 'ë' => 'E', 'Å¡' => 'S', 'Æ¡' => 'O', 'ß' => 'Ss', 'ă' => 'A', 'Ã…â„¢' => 'R', 'È›' => 'T', 'ň' => 'N', 'ÄÂ?' => 'A', 'Ä·' => 'K', 'Ã…Â?' => 'S', 'ỳ' => 'Y', 'ņ' => 'N', 'ĺ' => 'L', 'ħ' => 'H', 'á¹—' => 'P', 'ó' => 'O', 'ú' => 'U', 'Ä›' => 'E', 'é' => 'E', 'ç' => 'C', 'áºÂ?' => 'W', 'Ä‹' => 'C', 'õ' => 'O', 'ṡ' => 'S', 'ø' => 'O', 'Ä£' => 'G', 'ŧ' => 'T', 'È™' => 'S', 'Ä—' => 'E', 'ĉ' => 'C', 'Å›' => 'S', 'î' => 'I', 'ű' => 'U', 'ć' => 'C', 'Ä™' => 'E', 'ŵ' => 'W', 'ṫ' => 'T', 'Å«' => 'U', 'ÄÂ?' => 'C', 'ö' => 'Oe', 'è' => 'E', 'Å·' => 'Y', 'Ä…' => 'A', 'Å‚' => 'L', 'ų' => 'U', 'ů' => 'U', 'ÅŸ' => 'S', 'ÄŸ' => 'G', 'ļ' => 'L', 'Æ’' => 'F', 'ž' => 'Z', 'ẃ' => 'W', 'ḃ' => 'B', 'Ã¥' => 'A', 'ì' => 'I', 'ï' => 'I', 'ḋ' => 'D', 'Ã…Â¥' => 'T', 'Å—' => 'R', 'ä' => 'Ae', 'í' => 'I', 'Å•' => 'R', 'ê' => 'E', 'ü' => 'Ue', 'ò' => 'O', 'Ä“' => 'E', 'ñ' => 'N', 'Å„' => 'N', 'Ä¥' => 'H', 'ÄÂ?' => 'G', 'Ä‘' => 'D', 'ĵ' => 'J', 'ÿ' => 'Y', 'Å©' => 'U', 'Å­' => 'U', 'Æ°' => 'U', 'Å£' => 'T', 'ý' => 'Y', 'Å‘' => 'O', 'â' => 'A', 'ľ' => 'L', 'ẅ' => 'W', 'ż' => 'Z', 'Ä«' => 'I', 'ã' => 'A', 'Ä¡' => 'G', 'á¹Â?' => 'M', 'Ã…Â?' => 'O', 'Ä©' => 'I', 'ù' => 'U', 'į' => 'I', 'ź' => 'Z', 'á' => 'A', 'û' => 'U', 'Þ' => 'Th', 'ÃÂ?' => 'Dh', 'Æ' => 'Ae', ); //-------------------------------------------------------------------- /** * Tests whether a string contains only 7bit ASCII bytes. * You might use this to conditionally check whether a string * needs handling as UTF-8 or not, potentially offering performance * benefits by using the native PHP equivalent if it's just ASCII e.g.; * * * * * * @param string * @return boolean TRUE if it's all ASCII * @package utf8 * @subpackage ascii * @see utf8_is_ascii_ctrl */ function utf8_is_ascii($str) { if ( strlen($str) > 0 ) { // Search for any bytes which are outside the ASCII range... return (preg_match('/[^\x00-\x7F]/',$str) !== 1); } return FALSE; } //-------------------------------------------------------------------- /** * Tests whether a string contains only 7bit ASCII bytes with device * control codes omitted. The device control codes can be found on the * second table here: http://www.w3schools.com/tags/ref_ascii.asp * * @param string * @return boolean TRUE if it's all ASCII without device control codes * @package utf8 * @subpackage ascii * @see utf8_is_ascii */ function utf8_is_ascii_ctrl($str) { if ( strlen($str) > 0 ) { // Search for any bytes which are outside the ASCII range, // or are device control codes return (preg_match('/[^\x09\x0A\x0D\x20-\x7E]/',$str) !== 1); } return FALSE; } //-------------------------------------------------------------------- /** * Strip out all non-7bit ASCII bytes * If you need to transmit a string to system which you know can only * support 7bit ASCII, you could use this function. * @param string * @return string with non ASCII bytes removed * @package utf8 * @subpackage ascii * @see utf8_strip_non_ascii_ctrl */ function utf8_strip_non_ascii($str) { ob_start(); while ( preg_match( '/^([\x00-\x7F]+)|([^\x00-\x7F]+)/S', $str, $matches) ) { if ( !isset($matches[2]) ) { echo $matches[0]; } $str = substr($str, strlen($matches[0])); } $result = ob_get_contents(); ob_end_clean(); return $result; } //-------------------------------------------------------------------- /** * Strip out all non 7bit ASCII bytes and ASCII device control codes. * For a list of ASCII device control codes see the 2nd table here: * http://www.w3schools.com/tags/ref_ascii.asp * * @param string * @return boolean TRUE if it's all ASCII * @package utf8 * @subpackage ascii */ function utf8_strip_non_ascii_ctrl($str) { ob_start(); while ( preg_match( '/^([\x09\x0A\x0D\x20-\x7E]+)|([^\x09\x0A\x0D\x20-\x7E]+)/S', $str, $matches) ) { if ( !isset($matches[2]) ) { echo $matches[0]; } $str = substr($str, strlen($matches[0])); } $result = ob_get_contents(); ob_end_clean(); return $result; } //--------------------------------------------------------------- /** * Replace accented UTF-8 characters by unaccented ASCII-7 "equivalents". * The purpose of this function is to replace characters commonly found in Latin * alphabets with something more or less equivalent from the ASCII range. This can * be useful for converting a UTF-8 to something ready for a filename, for example. * Following the use of this function, you would probably also pass the string * through utf8_strip_non_ascii to clean out any other non-ASCII chars * Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1) * letters. Default is to deaccent both cases ($case = 0) * @param string UTF-8 string * @param int (optional) -1 lowercase only, +1 uppercase only, 1 both cases * @param string UTF-8 with accented characters replaced by ASCII chars * @return string accented chars replaced with ascii equivalents * @author Andreas Gohr * @package utf8 * @subpackage ascii */ function utf8_accents_to_ascii( $str, $case=0 ){ if($case <= 0){ global $UTF8_LOWER_ACCENTS; $string = str_replace( array_keys($UTF8_LOWER_ACCENTS), array_values($UTF8_LOWER_ACCENTS), $str ); } if($case >= 0){ global $UTF8_UPPER_ACCENTS; $string = str_replace( array_keys($UTF8_UPPER_ACCENTS), array_values($UTF8_UPPER_ACCENTS), $str ); } return $str; }