/**
* 字符截取 支持UTF8/GBK
* @param $string
* @param $length
* @param $dot
*/
function str_cut($string, $length, $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;
}今天在从drupal导入数据时,刚好用到它配合标题的strlen检测,发现总是有某条过不了,超字.但是看标题觉得奇怪.感觉应该没错.只是简单的再多预留字数,发现还是在这里卡住了.没办法拿那标题调试,再看一下实现,才发现原来当标题中使用了转义,刚好在它的实现中有对应的转义时.把整个转义当做一个字来算.却不是普通的英文来算.而标题这的strlen却是实打实的计算.搞得我超郁闷了.
