中文分词 - php逐个汉字遍历字符串

<code class="lang-php">function str_split_unicode($str, $l = 0) {
if ($l > 0) {
$ret = array();
$len = mb_strlen($str, "UTF-8");
for ($i = 0; $i < $len; $i += $l) {
$ret[] = mb_substr($str, $i, $l, "UTF-8");
}
return $ret;
}
return preg_split("//u", $str, -1, PREG_SPLIT_NO_EMPTY);
}
$s = '中华人民abc共和\x01国'; 

print_r(str_split_unicode($s));
Array
(
    [0] => 中
    [1] => 华
    [2] => 人
    [3] => 民
    [4] => a
    [5] => b
    [6] => c
    [7] => 共
    [8] => 和
    [9] => \
    [10] => x
    [11] => 0
    [12] => 1
    [13] => 国
)
</code>

<code class="lang-php"><br> $cind = 0;
 $arr_cont = array();
 for ($i = 0; $i < strlen($tempaddtext); $i++) {
            if (strlen(substr($tempaddtext, $cind, 1)) > 0) {
                if (ord(substr($tempaddtext, $cind, 1)) < 192) { //如果为英文则取1个字节
                    if (substr($tempaddtext, $cind, 1) != " ") {
                        array_push($arr_cont, substr($tempaddtext, $cind, 1));
                    }
                    $cind++;
                } elseif(ord(substr($tempaddtext, $cind, 1)) < 224) {
                    array_push($arr_cont, substr($tempaddtext, $cind, 2));
                    $cind+=2;
                } else {
                    array_push($arr_cont, substr($tempaddtext, $cind, 3));
                    $cind+=3;
                }
            }
        }

         print_r($arr_cont);
</code>