【对比】PHP检测提交的段落是否有重复行，哪一种更好？解决办法

【对比】PHP检测提交的段落是否有重复行，哪一种更好？
写的两个函数，对比提交的文本段落里面重复的有无，发现一些问题：
（1）in_array()检测中文有的时候会有问题，明明存在却提示不存在，长文本的时候概率更高
（2）有时候短段落重复3~4次是允许的，但是如果用similar_text作对比就导致只要有一次重复就拒绝用户提交了。如何改进才更好
（3）还有没有更好的方法，求~

function hasSimilarText($string)

{

    $lineArr = explode("\n",$string);

    $arrStr = $arrLen = array();

    foreach($lineArr as $k => $v)

    {

        $arrLen[] = strlen($v);

        $arrStr[] = $v;

    }



    foreach($arrStr as $k1 => $v1)

    {

        foreach($arrStr as $k2 => $v2)

        {

            if($k1 == $k2) continue;

            if($arrLen[$k2] < 30 || abs($arrLen[$k2] - $arrLen[$k1]) > 100) continue;

            similar_text($v1, $v2, $pct);

            if($pct > 90) return true;

        }

    }

    return false;

}





/* 重复段落检测 */

function hasRepeatLine($string)

{

    $string = str_replace(array("\t"," ","@","#","。","，",".",","),'',$string);

    //$string = str_replace("\r","\n",$string);

    $lineArr = explode("\n",$string);

    $countShort = $countMiddle = $countLong = 0;

    $arr = array();



    foreach($lineArr as $lineString)

    {

        $length = strlen( $lineString );

        if($length < 1) continue;

        if(in_array($lineString,$arr))

        {

            if($length < 13)

            {

                $countShort++;

                if($countShort > 4) return true;//5次

            } elseif($length>12 && $length < 51) {

                $countMiddle++;

                if($countMiddle > 3) return true; //4次

            } elseif($length>50 && $length < 101) {

                $countLong++;

                if($countLong > 2) return true; //3次