11-ES的自动补全

自动补全

在搜索框输入字符时，我们应该提示出与该字符有关的搜索项，因为需要根据拼音字母来推断，因此要用到拼音分词功能。

拼音分词器

要实现根据字母做补全，就必须对文档按照拼音分词。在GitHub上恰好有elasticsearch的拼音分词插件。地址：https://github.com/medcl/elasticsearch-analysis-pinyin

安装方式可以参考IK分词器的安装方式：https://editor.csdn.net/md/?articleId=122899932

测试拼音分词器

POST /_analyze
{
  "text": "谁把爷电动车骑走了？",
  "analyzer": "pinyin"
}

结果：

{
  "tokens" : [
    {
      "token" : "shui",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "sbyddcqzl",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 0
    },
    {
      "token" : "ba",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 1
    },
    {
      "token" : "ye",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 2
    },
    {
      "token" : "dian",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 3
    },
    {
      "token" : "dong",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 4
    },
    {
      "token" : "che",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 5
    },
    {
      "token" : "qi",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 6
    },
    {
      "token" : "zou",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 7
    },
    {
      "token" : "le",
      "start_offset" : 0,
      "end_offset" : 0,
      "type" : "word",
      "position" : 8
    }
  ]
}

自定义分词器

默认的拼音分词器会将每个汉字单独分为拼音，而我们希望的是每个词条形成一组拼音，需要对拼音分词器做个性化定制，形成自定义分词器。

elasticsearch中分词器（analyzer）的组成包含三部分：

• character filters：在tokenizer（分词器）之前对文本进行处理。例如删除字符、替换字符
• tokenizer：将文本按照一定的规则切割成词条（term）。例如keyword，就是不分词；还有ik_smart
• tokenizer filter：将tokenizer输出的词条做进一步处理。例如大小写转换、同义词处理、拼音处理等

文档分词时会依次由这三部分来处理文档。

声明自定义分词器：

PUT /test
{
  "settings": {
    "analysis": {
      "analyzer": {	//自定义分词器
        "my_analyer":{	//分词器名称
          "tokenizer": "ik_max_word",
          "filter": "py"
        }
      },
      "filter": {	//自定义tokenizer filter
        "py":{	//过滤器名称
          "type":"pinyin",	//过滤器类型
          "keep_full_pinyin":false,
          "keep_joined_full_pinyin":true,
          "keep_original":true,
          "limit_first_letter_length":16,
          "remove_duplicated_term":true,
          "none_chinese_pinyin_tokenize":false
        }
      }
    }
  },"mappings": {
    "properties": {
      "name":{
        "type": "text",
        "analyzer": "my_analyer",
        "search_analyzer": "ik_smart"
      }
    }
  }
}

测试自定义分词器

POST /test/_analyze
{
  "text": ["谁把爷电动车骑走了"],
  "analyzer": "my_analyer"
}

结果：

{
  "tokens" : [
    {
      "token" : "谁",
      "start_offset" : 0,
      "end_offset" : 1,
      "type" : "CN_CHAR",
      "position" : 0
    },
    {
      "token" : "shui",
      "start_offset" : 0,
      "end_offset" : 1,
      "type" : "CN_CHAR",
      "position" : 0
    },
    {
      "token" : "s",
      "start_offset" : 0,
      "end_offset" : 1,
      "type" : "CN_CHAR",
      "position" : 0
    },
    {
      "token" : "把",
      "start_offset" : 1,
      "end_offset" : 2,
      "type" : "CN_CHAR",
      "position" : 1
    },
    {
      "token" : "ba",
      "start_offset" : 1,
      "end_offset" : 2,
      "type" : "CN_CHAR",
      "position" : 1
    },
    {
      "token" : "b",
      "start_offset" : 1,
      "end_offset" : 2,
      "type" : "CN_CHAR",
      "position" : 1
    },
    {
      "token" : "爷",
      "start_offset" : 2,
      "end_offset" : 3,
      "type" : "CN_CHAR",
      "position" : 2
    },
    {
      "token" : "ye",
      "start_offset" : 2,
      "end_offset" : 3,
      "type" : "CN_CHAR",
      "position" : 2
    },
    {
      "token" : "y",
      "start_offset" : 2,
      "end_offset" : 3,
      "type" : "CN_CHAR",
      "position" : 2
    },
    {
      "token" : "电动车",
      "start_offset" : 3,
      "end_offset" : 6,
      "type" : "CN_WORD",
      "position" : 3
    },
    {
      "token" : "diandongche",
      "start_offset" : 3,
      "end_offset" : 6,
      "type" : "CN_WORD",
      "position" : 3
    },
    {
      "token" : "ddc",
      "start_offset" : 3,
      "end_offset" : 6,
      "type" : "CN_WORD",
      "position" : 3
    },
    {
      "token" : "电动",
      "start_offset" : 3,
      "end_offset" : 5,
      "type" : "CN_WORD",
      "position" : 4
    },
    {
      "token" : "diandong",
      "start_offset" : 3,
      "end_offset" : 5,
      "type" : "CN_WORD",
      "position" : 4
    },
    {
      "token" : "dd",
      "start_offset" : 3,
      "end_offset" : 5,
      "type" : "CN_WORD",
      "position" : 4
    },
    {
      "token" : "车骑",
      "start_offset" : 5,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 5
    },
    {
      "token" : "cheqi",
      "start_offset" : 5,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 5
    },
    {
      "token" : "cq",
      "start_offset" : 5,
      "end_offset" : 7,
      "type" : "CN_WORD",
      "position" : 5
    },
    {
      "token" : "骑走",
      "start_offset" : 6,
      "end_offset" : 8,
      "type" : "CN_WORD",
      "position" : 6
    },
    {
      "token" : "qizou",
      "start_offset" : 6,
      "end_offset" : 8,
      "type" : "CN_WORD",
      "position" : 6
    },
    {
      "token" : "qz",
      "start_offset" : 6,
      "end_offset" : 8,
      "type" : "CN_WORD",
      "position" : 6
    },
    {
      "token" : "走了",
      "start_offset" : 7,
      "end_offset" : 9,
      "type" : "CN_WORD",
      "position" : 7
    },
    {
      "token" : "zoule",
      "start_offset" : 7,
      "end_offset" : 9,
      "type" : "CN_WORD",
      "position" : 7
    },
    {
      "token" : "zl",
      "start_offset" : 7,
      "end_offset" : 9,
      "type" : "CN_WORD",
      "position" : 7
    }
  ]
}

自动补全查询

elasticsearch提供了Completion Suggester查询来实现自动补全功能。这个查询会匹配以用户输入内容开头的词条并返回。为了提高补全查询的效率，对于文档中字段的类型有一些约束：

• 参与补全查询的字段必须是completion类型。

• 字段的内容一般是用来补全的多个词条形成的数组。

比如，一个这样的索引库：

PUT test1
{
  "mappings": {"properties": {
    "title":{
      "type": "completion"
    }
  }}
}

然后插入下面的数据：

// 示例数据
POST test/_doc
{
  "title": ["Sony", "WH-1000XM3"]
}
POST test/_doc
{
  "title": ["SK-II", "PITERA"]
}
POST test/_doc
{
  "title": ["Nintendo", "switch"]
}

查询的DSL语句如下：

GET test1/_search
{
  "suggest": {
    "title_suggest": {
      "text": "s",	//关键字
      "completion":{
        "field":"title",//补全查询的字段
        "skip_duplicates":true,//跳过重复的
        "size":10	//获取前10条结果
      }
    }
  }
}

示例

实体类：

@Data
@NoArgsConstructor
public class HotelDoc {
    private Long id;
    private String name;
    private String address;
    private Integer price;
    private Integer score;
    private String brand;
    private String city;
    private String starName;
    private String business;
    private String location;
    private String pic;
    private Object distance;
    private Boolean isAD;
    private List<String> suggestion;

    public HotelDoc(Hotel hotel) {
        this.id = hotel.getId();
        this.name = hotel.getName();
        this.address = hotel.getAddress();
        this.price = hotel.getPrice();
        this.score = hotel.getScore();
        this.brand = hotel.getBrand();
        this.city = hotel.getCity();
        this.starName = hotel.getStarName();
        this.business = hotel.getBusiness();
        this.location = hotel.getLatitude() + ", " + hotel.getLongitude();
        this.pic = hotel.getPic();
        // 组装suggestion
        if(this.business.contains("/")){
            // business有多个值，需要切割
            String[] arr = this.business.split("/");
            // 添加元素
            this.suggestion = new ArrayList<>();
            this.suggestion.add(this.brand);
            Collections.addAll(this.suggestion, arr);
        }else {
            this.suggestion = Arrays.asList(this.brand, this.business);
        }
    }
}

实现自动补全查询的方法：

@Override
public List<String> getSuggestions(String prefix) {
    try {
        // 1.准备Request
        SearchRequest request = new SearchRequest("hotel");
        // 2.准备DSL
        request.source().suggest(new SuggestBuilder().addSuggestion(
            "suggestions",
            SuggestBuilders.completionSuggestion("suggestion")
            .prefix(prefix)
            .skipDuplicates(true)
            .size(10)
        ));
        // 3.发起请求
        SearchResponse response = client.search(request, RequestOptions.DEFAULT);
        // 4.解析结果
        Suggest suggest = response.getSuggest();
        // 4.1.根据补全查询名称，获取补全结果
        CompletionSuggestion suggestions = suggest.getSuggestion("suggestions");
        // 4.2.获取options
        List<CompletionSuggestion.Entry.Option> options = suggestions.getOptions();
        // 4.3.遍历
        List<String> list = new ArrayList<>(options.size());
        for (CompletionSuggestion.Entry.Option option : options) {
            String text = option.getText().toString();
            list.add(text);
        }
        return list;
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}