php中高性能中文字符串截取函數分享

這是用了phpwind裡面的一個字符串截取函數，他支持gbk,gbk2312,utf-8等多種編碼的字符截取，也很好高效的支持中文字符串的處理。  代碼如下 復制代碼

function substrs($content,$length,$add='Y'){
if (strlen($content)>$length) {
if ($GLOBALS['db_charset']!='utf-8') {
$retstr = '';
for ($i=0;$i<$length-2;$i++) {
$retstr .= ord($content[$i]) > 127 ? $content[$i].$content[++$i] : $content[$i];
}
return $retstr.($add=='Y' ? ' ..' : '');
}
return utf8_trim(substr($content,0,$length)).($add=='Y' ? ' ..' : '');
}
return $content;
}
function utf8_trim($str) {
$hex = '';
$len = strlen($str)-1;
for ($i=$len;$i>=0;$i-=1) {
$ch = ord($str[$i]);
$hex .= " $ch";
if (($ch & 128)==0 || ($ch & 192)==192) {
return substr($str,0,$i);
}
}
return $str.$hex;
}

function cutstr($string, $length, $dot = ' ...') {
global $charset;
if(strlen($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;
}