php: 中国語に従った文字列のカット関数メソッド

php: 中国語に従った文字列カット関数メソッド

    define(CHARSET, 'UTF-8'); // 系统默认编码

    /**
     * 根据中文裁减字符串
     * @param $string - 字符串
     * @param $length - 长度
     * @param $doc - 缩略后缀
     * @return 返回带省略号被裁减好的字符串
     */
    function cutstr( $string, $length, $dot = '...' ) {
        if ( strlen( $string ) <= $length ) {
            return $string;
        }
        $pre = chr( 1 );
        $end = chr( 1 );
        $string = str_replace( array( '&', '"', '<', '>' ), array( $pre . '&' . $end, $pre . '"' . $end, $pre . '<' . $end, $pre . '>' . $end ), $string );
        $strcut = '';
        if ( strtolower( CHARSET ) == 'utf-8' ) {
            $n = $tn = $noc = 0;
            while ( $n < strlen( $string ) ) {
                $t = ord( $string[$n] );
                if ( $t == 9 || $t == 10 || (32 <= $t && $t <= 126) ) {
                    $tn = 1;
                    $n&#43;&#43;;
                    $noc&#43;&#43;;
                } elseif ( 194 <= $t && $t <= 223 ) {
                    $tn = 2;
                    $n &#43;= 2;
                    $noc &#43;= 2;
                } elseif ( 224 <= $t && $t <= 239 ) {
                    $tn = 3;
                    $n &#43;= 3;
                    $noc &#43;= 2;
                } elseif ( 240 <= $t && $t <= 247 ) {
                    $tn = 4;
                    $n &#43;= 4;
                    $noc &#43;= 2;
                } elseif ( 248 <= $t && $t <= 251 ) {
                    $tn = 5;
                    $n &#43;= 5;
                    $noc &#43;= 2;
                } elseif ( $t == 252 || $t == 253 ) {
                    $tn = 6;
                    $n &#43;= 6;
                    $noc &#43;= 2;
                } else {
                    $n&#43;&#43;;
                }
                if ( $noc >= $length ) {
                    break;
                }
            }
            if ( $noc > $length ) {
                $n -= $tn;
            }
            $strcut = substr( $string, 0, $n );
        } else {
            for ( $i = 0; $i < $length; $i&#43;&#43; ) {
                $strcut .= ord( $string[$i] ) > 127 ? $string[$i] . $string[++$i] : $string[$i];
            }
        }
        $strcut = str_replace( array( $pre . '&' . $end, $pre . '"' . $end, $pre . '<' . $end, $pre . '>' . $end ), array( '&', '"', '<', '>' ), $strcut );
        $pos = strrpos( $strcut, chr( 1 ) );
        if ( $pos !== false ) {
            $strcut = substr( $strcut, 0, $pos );
        }
        return $strcut . $dot;
    }