Scott Reynen编写了一个将UTF-8转换为Unipre的函数。我在PHP文档中发现了它。
function utf8_to_unipre( $str ) { $unipre = array(); $values = array(); $lookingFor = 1; for ($i = 0; $i < strlen( $str ); $i++ ) { $thisValue = ord( $str[ $i ] ); if ( $thisValue < ord('A') ) { // exclude 0-9 if ($thisValue >= ord('0') && $thisValue <= ord('9')) { // number $unipre[] = chr($thisValue); } else { $unipre[] = '%'.dechex($thisValue); } } else { if ( $thisValue < 128) $unipre[] = $str[ $i ]; else { if ( count( $values ) == 0 ) $lookingFor = ( $thisValue < 224 ) ? 2 : 3; $values[] = $thisValue; if ( count( $values ) == $lookingFor ) { $number = ( $lookingFor == 3 ) ? ( ( $values[0] % 16 ) * 4096 ) + ( ( $values[1] % 64 ) * 64 ) + ( $values[2] % 64 ): ( ( $values[0] % 32 ) * 64 ) + ( $values[1] % 64 ); $number = dechex($number); $unipre[] = (strlen($number)==3)?"%u0".$number:"%u".$number; $values = array(); $lookingFor = 1; } // if } // if } } // for return implode("",$unipre);} // utf8_to_unipre
