这里提供一款支持中文汉字与英文混合在一起的截取功能,包括对html标签等进来处理,下面我们来看看这款截取函数吧.
中英文字符串截取函数(包括html),实例代码如下:
function get_word($string, $length, $dot = '..',$charset='gbk') {
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];
}
}
return $strcut.$dot;
}
$str = "欢迎 visit 简明 nowamagic";
$str_result = get_word($str, 12);
echo $str_result;
