手把手教你做关键词匹配项目（搜索引擎）---- 第十九天

<?php

class Splitter {

    /**
     * 获取类目下分词的词组数据,按字符串长度比较排序
     * @param $cid
     * @return array
     */
    public static function getWordSegmentation($cid){

        $ret = array();
        $sql = "select word from category_linklist where cid=‘$cid‘";
        $words = DB::makeArray($sql);
        foreach($words as $strWords){
            $words = explode(",",$strWords);

            foreach($words as $word){
               if(self::isPhrase($word)){
                    $ret[] = $word;
                }
            }
        }

        usort($ret,function($a,$b){
            (strlen($a)>strlen($b))?1:-1;
        });

        return $ret;
    }

    /**
     * 检测是否为词组
     * @param $word
     * @return bool
     */
    public static function isPhrase($word){
        if(preg_match(‘/^[\x{4E00}-\x{9FA5}]+$/u‘, $word) && strlen($word) <= 3){
            return false;
        }

        if(strlen($word)<=1){
            return false;
        }
        return true;
    }


    /**
     * 把关键词拆分成词组或者单词
     * @param $keyword
     * @param $cid
     * @return array
     */
    public static function split($keyword,$cid){

        $splitWords = array();
        $splitSegmentation = self::getWordSegmentation($cid);
        $remainKeyword = $keyword;

        foreach($splitSegmentation as $phrase){

            if(count(explode($phrase,$remainKeyword))>1){
                $splitWords[] = $phrase;
                $remainKeyword = str_replace($phrase,"::",$remainKeyword);
            }
        }

        $remainKeywords = explode("::",$remainKeyword);
        $splitWords = array_merge($splitWords,$remainKeywords);

        $keywordScores = array();
        foreach($splitWords as $splitWord){

            $keywordScore = new KeywordScore();
            $keywordScore->splitWord = $splitWord;
            $keywordScore->weight = self::calculateWeight($splitWord,$keyword);
            $keywordScores[] = $keywordScore;
        }

        return $keywordScores;

    }

    /**
     * @desc 计算UTF8字符串权重
     * @param string $splitWord
     * @param string $word
     * @return float
     */
    public static function calculateWeight($splitWord, $word)
    {
        return ROUND(strlen($splitWord) / strlen($word), 3);
    }

}


class KeywordScore {

    public $splitWord;
    public $weight;

}