note 48955 added to function.mb-detect-encoding

Sometimes mb_detect_string is not what you need. When using pdflib for example you want to VERIFY the correctness of utf-8. mb_detect_encoding reports some iso-8859-1 encoded text as utf-8. To verify utf 8 use the following: // // utf8 encoding validation developed based on Wikipedia entry at: // http://en.wikipedia.org/wiki/UTF-8 // // Implemented as a recursive descent parser based on a simple state machine // copyright 2005 Maarten Meijer // // This cries out for a C-implementation to be included in PHP core // function valid_1byte($char) { if(!is_int($char)) return false; return ($char & 0x80) == 0x00; } function valid_2byte($char) { if(!is_int($char)) return false; return ($char & 0xE0) == 0xC0; } function valid_3byte($char) { if(!is_int($char)) return false; return ($char & 0xF0) == 0xE0; } function valid_4byte($char) { if(!is_int($char)) return false; return ($char & 0xF8) == 0xF0; } function valid_nextbyte($char) { if(!is_int($char)) return false; return ($char & 0xC0) == 0x80; } function valid_utf8($string) { $len = strlen($string); $i = 0; while( $i < $len ) { $char = ord(substr($string, $i++, 1)); if(valid_1byte($char)) { // continue continue; } else if(valid_2byte($char)) { // check 1 byte if(!valid_nextbyte(ord(substr($string, $i++, 1)))) return false; } else if(valid_3byte($char)) { // check 2 bytes if(!valid_nextbyte(ord(substr($string, $i++, 1)))) return false; if(!valid_nextbyte(ord(substr($string, $i++, 1)))) return false; } else if(valid_4byte($char)) { // check 3 bytes if(!valid_nextbyte(ord(substr($string, $i++, 1)))) return false; if(!valid_nextbyte(ord(substr($string, $i++, 1)))) return false; if(!valid_nextbyte(ord(substr($string, $i++, 1)))) return false; } // goto next char } return true; // done } for a drawing of the statemachine see: http://www.xs4all.nl/~mjmeijer/unicode.png and http://www.xs4all.nl/~mjmeijer/unicode2.png ---- Manual Page -- http://www.php.net/manual/en/function.mb-detect-encoding.php Edit -- http://master.php.net/manage/user-notes.php?action=edit+48955 Delete -- http://master.php.net/manage/user-notes.php?action=delete+48955&report=yes Reason: bad code -- http://master.php.net/manage/user-notes.php?action=delete+48955&report=yes&reason=bad+code Reason: spam -- http://master.php.net/manage/user-notes.php?action=delete+48955&report=yes&reason=spam Reason: useless example -- http://master.php.net/manage/user-notes.php?action=delete+48955&report=yes&reason=useless+example Reason: contains commercial links -- http://master.php.net/manage/user-notes.php?action=delete+48955&report=yes&reason=contains+commercial+links Reason: useless note -- http://master.php.net/manage/user-notes.php?action=delete+48955&report=yes&reason=useless+note Reject -- http://master.php.net/manage/user-notes.php?action=reject+48955&report=yes Search -- http://master.php.net/manage/user-notes.php