手把手教你做关键词匹配项目（搜索引擎）---- 第二十天，教你做第二十天

客串：屌丝的坑人表单神器、数据库那点事儿

面向对象升华：面向对象的认识----新生的初识、面向对象的番外----思想的梦游篇（1）、面向对象的认识---如何找出类

负载均衡：负载均衡----概念认识篇、负载均衡----实现配置篇（Nginx）

吐槽：有人反馈了这样的一个信息，说该文章越到最后越难看懂，跟不上节奏，也有的人说小帅帅的能力怎么飙的那么快，是不是我比较蠢。也有的直接看文字，不看代码，代码太难懂了。

其实我这几天也一直在思考这个问题，所以没办法就去开展了一些面向对象的课程，希望对那些跟不上的有些帮助。其实说真的，读者不反馈的话，我只好按照我认为的小帅帅去开展课程了。

第二十天

起点：手把手教你做关键词匹配项目（搜索引擎）---- 第一天

回顾：手把手教你做关键词匹配项目（搜索引擎）---- 第十九天

话说小帅帅为了解决那个分词算法写出了初版，他拿给于老大看的时候，被要求重写了。

原因有以下几点：

1. 如何测试，测试数据呢？

2. Splitter是不是做了太多事情?

3. 连衣裙xxl裙连衣裙这种有重复词组怎么办？

小帅帅拿着这些问题，开始重构。

首先他发现了这点，中文、英文和中英文的判断，以及长度的计算，他把这个写成了类：

<?<span>php

</span><span>class</span><span> UTF8 {

    </span><span>/*</span><span>*
     * 检测是否utf8
     * @param $char
     * @return bool
     </span><span>*/</span>
    <span>public</span> <span>static</span> <span>function</span> is(<span>$char</span><span>){
        </span><span>return</span> (<span>preg_match</span>("/^([".<span>chr</span>(228)."-".<span>chr</span>(233)."]{1}[".<span>chr</span>(128)."-".<span>chr</span>(191)."]{1}[".<span>chr</span>(128)."-".<span>chr</span>(191)."]{1}){1}/",<span>$char</span>) ||
            <span>preg_match</span>("/([".<span>chr</span>(228)."-".<span>chr</span>(233)."]{1}[".<span>chr</span>(128)."-".<span>chr</span>(191)."]{1}[".<span>chr</span>(128)."-".<span>chr</span>(191)."]{1}){1}$/",<span>$char</span>) ||
            <span>preg_match</span>("/([".<span>chr</span>(228)."-".<span>chr</span>(233)."]{1}[".<span>chr</span>(128)."-".<span>chr</span>(191)."]{1}[".<span>chr</span>(128)."-".<span>chr</span>(191)."]{1}){2,}/",<span>$char</span><span>));
    }

    </span><span>/*</span><span>*
     * 计算utf8字的个数
     * @param $char
     * @return float|int
     </span><span>*/</span>
    <span>public</span> <span>static</span> <span>function</span> length(<span>$char</span><span>) {

        </span><span>if</span>(self::is(<span>$char</span><span>))
            </span><span>return</span> <span>ceil</span>(<span>strlen</span>(<span>$char</span>)/3<span>);
        </span><span>return</span> <span>strlen</span>(<span>$char</span><span>);
    }

    </span><span>/*</span><span>*
     * 检测是否为词组
     * @param $word
     * @return bool
     </span><span>*/</span>
    <span>public</span> <span>static</span> <span>function</span> isPhrase(<span>$word</span><span>){

        </span><span>if</span>(self::length(<span>$word</span>)<=1<span>)
            </span><span>return</span> <span>false</span><span>;
        </span><span>return</span> <span>true</span><span>;
    }

}</span>

登入後複製

小帅帅又考虑到词典的来源有可能来自多个地方，比如我给的测试数据，这样不就是可以解决于老大说到无法测试的问题了，小帅帅把词典的来源抽成了个类，类如下：

<?<span>php

</span><span>class</span><span> DBSegmentation {

    </span><span>public</span> <span>$cid</span><span>;

    </span><span>/*</span><span>*
     * 获取类目下分词的词组数据
     * @return array
     </span><span>*/</span>
    <span>public</span> <span>function</span><span> transferDictionary(){
        </span><span>$ret</span> = <span>array</span><span>();
        </span><span>$sql</span> = "select word from category_linklist where cid='<span>$this</span>->cid'"<span>;
        </span><span>$words</span> = DB::makeArray(<span>$sql</span><span>);
        </span><span>foreach</span>(<span>$words</span> <span>as</span> <span>$strWords</span><span>){
            </span><span>$words</span> = <span>explode</span>(",",<span>$strWords</span><span>);

            </span><span>foreach</span>(<span>$words</span> <span>as</span> <span>$word</span><span>){
                </span><span>if</span>(UTF8::isPhrase(<span>$word</span><span>)){
                    </span><span>$ret</span>[] = <span>$word</span><span>;
                }
            }
        }
        </span><span>return</span> <span>$ret</span><span>;
    }
} 

</span><span>class</span><span> TestSegmentation {
    
    </span><span>public</span> <span>function</span><span> transferDictionary(){
        </span><span>$words</span> = <span>array</span><span>(
            </span>"连衣裙,连衣",
            "XXL,xxl,加大,加大码",
            "X码,中码",
            "外套,衣,衣服,外衣,上衣",
            "女款,女士,女生,女性"<span>
        );

        </span><span>$ret</span> = <span>array</span><span>();
        </span><span>foreach</span>(<span>$words</span> <span>as</span> <span>$strWords</span><span>){
            </span><span>$words</span> = <span>explode</span>(",",<span>$strWords</span><span>);

            </span><span>foreach</span>(<span>$words</span> <span>as</span> <span>$word</span><span>){
                </span><span>if</span>(UTF8::isPhrase(<span>$word</span><span>)){
                    </span><span>$ret</span>[] = <span>$word</span><span>;
                }
            }
        }
        </span><span>return</span> <span>$ret</span><span>;

    }
}</span>

登入後複製

那么Splitter 就专心分词把，代码如下：

<span>class</span><span> Splitter {

    </span><span>public</span> <span>$keyword</span><span>;
    </span><span>private</span> <span>$dictionary</span> = <span>array</span><span>();

    </span><span>public</span> <span>function</span> setDictionary(<span>$dictionary</span> = <span>array</span><span>()){

        </span><span>usort</span>(<span>$dictionary</span>,<span>function</span>(<span>$a</span>,<span>$b</span><span>){
            </span><span>return</span> (UTF8::length(<span>$a</span>)>UTF8::length(<span>$b</span>))?1:-1<span>;
        });

        </span><span>$this</span>->dictionary = <span>$dictionary</span><span>;
    }

    </span><span>public</span> <span>function</span><span> getDictionary(){
        </span><span>return</span> <span>$this</span>-><span>dictionary;
    }

    </span><span>/*</span><span>*
     * 把关键词拆分成词组或者单词
     * @return KeywordEntity $keywordEntity
     </span><span>*/</span>
    <span>public</span> <span>function</span> <span>split</span><span>(){

        </span><span>$remainKeyword</span> = <span>$this</span>-><span>keyword;

        </span><span>$keywordEntity</span> = <span>new</span> KeywordEntity(<span>$this</span>-><span>keyword);

        </span><span>foreach</span>(<span>$this</span>->dictionary <span>as</span> <span>$phrase</span><span>){

            </span><span>$matchTimes</span> = <span>preg_match_all</span>("/<span>$phrase</span>/",<span>$remainKeyword</span>,<span>$matches</span><span>);
            </span><span>if</span>(<span>$matchTimes</span>>0<span>){
                </span><span>$keywordEntity</span>->addElement(<span>$phrase</span>,<span>$matchTimes</span><span>);

                </span><span>$remainKeyword</span> = <span>str_replace</span>(<span>$phrase</span>,"::",<span>$remainKeyword</span><span>);
            }
        }

        </span><span>$remainKeywords</span> = <span>explode</span>("::",<span>$remainKeyword</span><span>);
        </span><span>foreach</span>(<span>$remainKeywords</span> <span>as</span> <span>$splitWord</span><span>){

            </span><span>if</span>(!<span>empty</span>(<span>$splitWord</span><span>)){
                </span><span>$keywordEntity</span>->addElement(<span>$splitWord</span><span>);
            }
        }

        </span><span>return</span> <span>$keywordEntity</span><span>;

    }

}


</span><span>class</span><span> KeywordEntity {

    </span><span>public</span> <span>$keyword</span><span>;
    </span><span>public</span> <span>$elements</span> = <span>array</span><span>();

    </span><span>public</span> <span>function</span> __construct(<span>$keyword</span><span>){
        </span><span>$this</span>->keyword = <span>$keyword</span><span>;
    }

    </span><span>public</span> <span>function</span> addElement(<span>$word</span>,<span>$times</span>=1<span>){

        </span><span>if</span>(<span>isset</span>(<span>$this</span>->elements[<span>$word</span><span>])){
            </span><span>$this</span>->elements[<span>$word</span>]->times += <span>$times</span><span>;
        }</span><span>else</span>
            <span>$this</span>->elements[] = <span>new</span> KeywordElement(<span>$word</span>,<span>$times</span><span>);
    }

    </span><span>/*</span><span>*
     * @desc 计算UTF8字符串权重
     * @param string $word
     * @return float
     </span><span>*/</span>
    <span>public</span> <span>function</span> calculateWeight(<span>$word</span><span>)
    {
        </span><span>$element</span> = <span>$this</span>->elements[<span>$word</span><span>];
        </span><span>return</span> <span>ROUND</span>(<span>strlen</span>(<span>$element</span>->word)*<span>$element</span>->times / <span>strlen</span>(<span>$this</span>->keyword), 3<span>);
    }
}


</span><span>class</span><span> KeywordElement {
    </span><span>public</span> <span>$word</span><span>;
    </span><span>public</span> <span>$times</span><span>;

    </span><span>public</span> <span>function</span> __construct(<span>$word</span>,<span>$times</span><span>){
        </span><span>$this</span>->word = <span>$word</span><span>;
        </span><span>$this</span>->times = <span>$times</span><span>;
    }
}</span>

登入後複製

他把算权重的也丢给了一个类专门去处理。

小帅帅写完之后，也顺手写了测试实例：

<?<span>php

</span><span>$segmentation</span> = <span>new</span><span> TestSegmentation();

</span><span>$splitter</span> = <span>new</span><span> Splitter();
</span><span>$splitter</span>->setDictionary(<span>$segmentation</span>-><span>transferDictionary());
</span><span>$splitter</span>->keyword = "连衣裙xxl裙连衣裙"<span>;
</span><span>$keywordEntity</span> = <span>$splitter</span>-><span>split</span><span>();

</span><span>var_dump</span>(<span>$keywordEntity</span>);

登入後複製

这样就算你的算法怎么改，它也能从容面对了。

小帅帅理解了这个，当你觉得类做的事情太多的时候，可以考虑下单一职责原则。

单一职责原则：一个类，只有一个引起它变化的原因。应该只有一个职责。每一个职责都是变化的一个轴线，如果一个类有一个以上的职责，这些职责就耦合在了一起。这会导致脆弱的设计。当一个职责发生变化时，可能会影响其它的职责。另外，多个职责耦合在一起，会影响复用性。例如：要实现逻辑和界面的分离。【来自百度百科】

当于老大提到是不是有其他分词算法的时候，我们能不能拿来用，小帅帅很高兴，因为现在它的代码是多么美好。

小帅帅如何玩转第三方分词扩展，请继续关注下回分解：手把手教你做关键词匹配项目（搜索引擎）---- 第二十一天