[PHP] - 中文字符串截取(UTF-8与非UTF-8)

时间:2022-09-21 07:47:15

来源:http://zhidao.baidu.com/question/282309749.html

function cutstr ($string, $length, $dot = '...', $charset = 'utf-8') {

//功能:按长度截取字符串
//$string, $length, $dot,$charset
//字符串,要取长度,截断符,编码



if (strlen($string) <= $length) {
return $string;
}

$string = str_replace(array('&', '"', '<', '>'), array('&', '"', '<', '>'), $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++;
$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);

} else {
for ($i = 0; $i < $length; $i++) {
$strcut .= ord($string[$i]) > 127 ? $string[$i] . $string[++ $i] : $string[$i];
}
}
$strcut = str_replace(array('&', '"', '<', '>'), array('&', '"', '<', '>'), $strcut);

return $strcut . $dot;
}



$str = "我们要截取的字符串";
echo cutstr($str, 15, "...", 'utf-8');