ES搜索补全建议一

作者: rainbowz | 来源:发表于2021-12-13 00:41 被阅读0次

当用户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，如图

image.png

elasticsearch提供了Completion Suggesttion查询实现自动补全。为了提高补全查询的效率，对于文档字段的类型有限制

参与补全查询的字段必须是completetion类型
字段的内容一般是用来补全的多个字条组成的数组

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

插入下面数据

// 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

// 自动补全查询
GET /test/_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
        }
      }
  }
}

搜索补全结果

实现酒店搜索框的自动补全

1修改hotel索引的索引库结构，设置自定义拼音分词器
2修改索引库需要被自定义分词字段那么/all
3索引库添加一个新字段suggestion，类型为completetion类型，使用我们自己自定义分词器
4给HotelDoc类添加suggestestion字段，内容包含brand、business
5重新导入数据到hotel库

酒店索引映射结构

PUT /hotel
{
  "settings": {
    "analysis": {
      "analyzer": {
        "text_anlyzer": {
          "tokenizer": "ik_max_word",
          "filter": "py"
        },
        "completion_analyzer": {
          "tokenizer": "keyword",
          "filter": "py"
        }
      },
      "filter": {
        "py": {
          "type": "pinyin",
          "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": {
      "id":{
        "type": "keyword"
      },
      "name":{
        "type": "text",
        "analyzer": "text_anlyzer",
        "search_analyzer": "ik_smart",
        "copy_to": "all"
      },
      "address":{
        "type": "keyword",
        "index": false
      },
      "price":{
        "type": "integer"
      },
      "score":{
        "type": "integer"
      },
      "brand":{
        "type": "keyword",
        "copy_to": "all"
      },
      "city":{
        "type": "keyword"
      },
      "starName":{
        "type": "keyword"
      },
      "business":{
        "type": "keyword",
        "copy_to": "all"
      },
      "location":{
        "type": "geo_point"
      },
      "pic":{
        "type": "keyword",
        "index": false
      },
      "all":{
        "type": "text",
        "analyzer": "text_anlyzer",
        "search_analyzer": "ik_smart"
      },
      "suggestion":{
          "type": "completion",
          "analyzer": "completion_analyzer"
      }
    }
  }
}

JAVA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();

        // 判断商圈是否包含/
        if (this.business.contains("/")) {
            // 需要切割
            String[] arr = this.business.split("/");
            this.suggestion = new ArrayList<>();
            this.suggestion.add(this.brand);
            Collections.addAll(this.suggestion, arr);
        } else {
            this.suggestion = Arrays.asList(this.brand, this.business);
        }

    }
}

重新导入数据,编写DSL语句