PHP Chinese support function PHP Chinese interception string function PHP Chinese string flip

/**
 * Convert a string containing full-width numeric characters, letters, spaces or '%+-()' characters into corresponding half-width characters
 *
 * @access public
 * @param string $str String to be converted
 *
 * @return string $str processed string
*/
function make_semiangle($str)
{
    $arr = array('０' => '0', '１' => '1', '２' => '2', '３' => '3', '４' => '4',
    '５' => '5', '６' => '6', '７' => '7', '８' => '8', '９' => '9',
    'Ａ' => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D', 'Ｅ' => 'E',
    'Ｆ' => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J',
    'Ｋ' => 'K', 'Ｌ' => 'L', 'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O',
    'Ｐ' => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T',
    'Ｕ' => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y',
    'Ｚ' => 'Z', 'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd',
    'ｅ' => 'e', 'ｆ' => 'f', 'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i',
    'ｊ' => 'j', 'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n',
    'ｏ' => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's',
    'ｔ' => 't', 'ｕ' => 'u', 'ｖ' => 'v', 'ｗ' => 'w', 'ｘ' => 'x',
    'ｙ' => 'y', 'ｚ' => 'z',
    '（' => '(', '）' => ')', '〔' => '[', '〕' => ']', '【' => '[',
    '】' => ']', '〖' => '[', '〗' => ']', '“' => '[', '”' => ']',
    '‘' => '[', '’' => ']', '｛' => '{', '｝' => '}', '《' => '<',
    '》' => '>',
    '％' => '%', '＋' => '+', '—' => '-', '－' => '-', '～' => '-',
    '：' => ':', '。' => '.', '、' => ',', '，' => '.', '、' => '.',
    '；' => ',', '？' => '?', '！' => '!', '…' => '-', '‖' => '|',
    '”' => '"', '’' => '`', '‘' => '`', '｜' => '|', '〃' => '"',
    '　' => ' ','＄'=>'$','＠'=>'@','＃'=>'#','＾'=>'^','＆'=>'&','＊'=>'*');

    return strtr($str, $arr);
}

例2，php中文截取字符串

/*
Utf-8、gb2312都支持的汉字截取函数
cut_str(字符串, 截取长度, 开始长度, 编码);
编码默认为 utf-8
开始长度默认为 0
* edit: bbs.it-home.org
*/
function cut_str($string, $sublen, $start = 0, $code = 'UTF-8') {
    if ($code == 'UTF-8') {
        $pa = "/[x01-x7f]|[xc2-xdf][x80-xbf]|xe0[xa0-xbf][x80-xbf]|[xe1-xef][x80-xbf][x80-xbf]|xf0[x90-xbf][x80-xbf][x80-xbf]|[xf1-xf7][x80-xbf][x80-xbf][x80-xbf]/";
        preg_match_all ( $pa, $string, $t_string );
        if (count ( $t_string [0] ) - $start > $sublen)
            return join ( '', array_slice ( $t_string [0], $start, $sublen ) ) . "...";
        return join ( '', array_slice ( $t_string [0], $start, $sublen ) );
    } else {
        $start = $start * 2;
        $sublen = $sublen * 2;
        $strlen = strlen ( $string );
        $tmpstr = '';
        for($i = 0; $i < $strlen; $i ++) {
            if ($i >= $start && $i < ($start + $sublen)) {
                if (ord ( substr ( $string, $i, 1 ) ) > 129) {
                    $tmpstr .= substr ( $string, $i, 2 );
                } else {
                    $tmpstr .= substr ( $string, $i, 1 );
                }
            }
            if (ord ( substr ( $string, $i, 1 ) ) > 129)
                $i ++;
        }
        if (strlen ( $tmpstr ) < $strlen)
            $tmpstr .= "...";
        return $tmpstr;
    }
}
$str = "abcd需要截取的字符串";
echo cut_str ( $str, 1, 0, 'gb2312' );
?>

例3，字符串的载取

/**
 * 字符截取 支持UTF8/GBK
 * @param $string
 * @param $length
 * @param $dot
 */
function str_cut($string, $length, $charset = 'utf-8', $dot = '...') {
    $strlen = strlen($string);
    if($strlen <= $length) return $string;
    $string = str_replace(array(' ',' ', '&', '"', ''', '“', '”', '—', '<', '>', '·', '…'), array('∵',' ', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), $string);
    $strcut = '';
    if(strtolower($charset) == 'utf-8') {
        $length = intval($length-strlen($dot)-$length/3);
        $n = $tn = $noc = 0;
        while($n < strlen($string)) {
            $t = ord($string[$n]);
            if($t == 9 || $t == 10 || (32 <= $t && $t <= 126)) {
                $tn = 1; $n++; $noc++;
            } elseif(194 <= $t && $t <= 223) {
                $tn = 2; $n += 2; $noc += 2;
            } elseif(224 <= $t && $t <= 239) {
                $tn = 3; $n += 3; $noc += 2;
            } elseif(240 <= $t && $t <= 247) {
                $tn = 4; $n += 4; $noc += 2;
            } elseif(248 <= $t && $t <= 251) {
                $tn = 5; $n += 5; $noc += 2;
            } elseif($t == 252 || $t == 253) {
                $tn = 6; $n += 6; $noc += 2;
            } else {
                $n++;
            }
            if($noc >= $length) {
                break;
            }
        }
        if($noc > $length) {
            $n -= $tn;
        }
        $strcut = substr($string, 0, $n);
        $strcut = str_replace(array('∵', '&', '"', "'", '“', '”', '—', '<', '>', '·', '…'), array(' ', '&', '"', ''', '“', '”', '—', '<', '>', '·', '…'), $strcut);
    } else {
        $dotlen = strlen($dot);
        $maxi = $length - $dotlen - 1;
        $current_str = '';
        $search_arr = array('&',' ', '"', "'", '“', '”', '—', '<', '>', '·', '…','∵');
        $replace_arr = array('&',' ', '"', ''', '“', '”', '—', '<', '>', '·', '…',' ');
        $search_flip = array_flip($search_arr);
        for ($i = 0; $i < $maxi; $i++) {
            $current_str = ord($string[$i]) > 127 ? $string[$i].$string[++$i] : $string[$i];
            if (in_array($current_str, $search_arr)) {
                $key = $search_flip[$current_str];
                $current_str = str_replace($search_arr[$key], $replace_arr[$key], $current_str);
            }
            $strcut .= $current_str;
        }
    }
    return $strcut.$dot;
}

例4，PHP中文字符串翻转 翻转一个字符串可以使用strrev()函数即可。 但有时需要处理是字符串是含中文的，这样用strrev就会出现乱码。 这里自定义一个函数来处理含中文的字符。

/**
* 中文字符串翻转
* by bbs.it-home.org
*/
function cstrrev($str)
{
    $len = strlen($str);
    for($i = 0; $i < $len; $i++)
    {
        $char = $str{0};
        if(ord($char) > 127)
        {
            $i++;
            if($i < $len)
            {
                $arr[] = substr($str, 0, 2);
                $str = substr($str, 2);
            }
        }
        else
        {
            $arr[] = $char;
            $str = substr($str, 1);
        }
    }
    return join(array_reverse($arr));
}
#使用方法：
$str = '中文.look!';
echo cstrrev($str);
#结果输出：!kool.文中

附5，

function str_replace_cn($needle, $str, $haystack, $charset = "utf-8"){
        $re['utf-8']   = "/[x01-x7f]|[xc2-xdf][x80-xbf]|[xe0-xef][x80-xbf]{2}|[xf0-xff][x80-xbf]{3}/";
        $re['gb2312'] = "/[x01-x7f]|[xb0-xf7][xa0-xfe]/";
        $re['gbk']    = "/[x01-x7f]|[x81-xfe][x40-xfe]/";
        $re['big5']   = "/[x01-x7f]|[x81-xfe]([x40-x7e]|xa1-xfe])/";

        preg_match_all($re[$charset], $haystack, $match_haystack);
        preg_match_all($re[$charset], $needle, $match_needle);

        for($i = 0; $i < count($match_needle); $i ++){
            if(!in_array($match_needle[0][$i], $match_haystack[0]))return $haystack;//无匹配
        }

        $match_haystack = $match_haystack[0];
        $match_needle = $match_needle[0];

        for($i = 0; $i < count($match_haystack); $i ++){
            if($match_haystack[$i] == "")continue;
            if($match_haystack[$i] == $match_needle[0]){
                if(count($match_needle) == 1){//如果只一个字符
                    $match_haystack[$i] = $str;
                }else{
                    $flag = true;
                    for($j = 1; $j < count($match_needle); $j ++){
                        if($match_haystack[$i + $j] != $match_needle[$j]){
                            $flag = false;
                            break;
                        }
                    }
                    if($flag){//匹配
                        $match_haystack[$i] = $str;
                        for($j = 1; $j < count($match_needle); $j ++){
                            $match_haystack[$i + $j] = "";
                        }
                    }
                }
            }
        }
        return implode("", $match_haystack);
    }