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
拼音分词器
下载
要实现根据字母做补全，就必须对文档按照拼音分词，GitHub上有拼音分词插件
解压
解压到一个文件夹中去
上传
上传到服务器中，elasticsearch的plugin目录
重启
重启elasticsearch
docker restart es
测试
POST /_analyze
{
"text": "如家酒店还不错",
"analyzer": "pinyin"
}
返回拼音
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
自定义分词器
PUT /myanalyzer
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "ik_max_word",
"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": {
"name": {
"type": "text",
"analyzer": "my_analyzer",
"search_analyzer": "ik_smart"
}
}
}
}
- analyzer自定义分词器
- my_analyzer分词器名称
- filter自定义tokenizer filter
- py过滤器名称
- filter.type过滤器类型，这里是pinyin
- name分词的字段
测试
POST /myanalyzer/_analyze
{
"text": ["华美达酒店还不错"],
"analyzer": "my_analyzer"
}
结果
自动补全查询
创建索引库
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"
}
}
}
}
HotelDoc实体
java
import lombok.Data;
import lombok.NoArgsConstructor;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
@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);
}
}
}导入数据
java
@Test
void testBulkRequest() throws IOException {
// 批量查询酒店数据
List<Hotel> hotels = hotelService.list();
// 1.创建Request
BulkRequest request = new BulkRequest();
// 2.准备参数，添加多个新增的Request
for (Hotel hotel : hotels) {
// 2.1.转换为文档类型HotelDoc
HotelDoc hotelDoc = new HotelDoc(hotel);
// 2.2.创建新增文档的Request对象
request.add(new IndexRequest("hotel")
.id(hotelDoc.getId().toString())
.source(JSON.toJSONString(hotelDoc), XContentType.JSON));
}
// 3.发送请求
client.bulk(request, RequestOptions.DEFAULT);
}controller类
java
import cn.itcast.hotel.pojo.PageResult;
import cn.itcast.hotel.pojo.RequestParams;
import cn.itcast.hotel.service.IHotelService;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.*;
import java.util.List;
import java.util.Map;
@RestController
@RequestMapping("/hotel")
public class HotelController {
@Autowired
private IHotelService hotelService;
// 搜索酒店数据
@GetMapping("suggestion")
public List<String> getSuggestions(@RequestParam("key") String prefix) {
return hotelService.getSuggestions(prefix);
}
}service类
java
import cn.itcast.hotel.mapper.HotelMapper;
import cn.itcast.hotel.pojo.Hotel;
import cn.itcast.hotel.pojo.HotelDoc;
import cn.itcast.hotel.pojo.PageResult;
import cn.itcast.hotel.pojo.RequestParams;
import cn.itcast.hotel.service.IHotelService;
import com.alibaba.fastjson.JSON;
import com.baomidou.mybatisplus.extension.service.impl.ServiceImpl;
import org.elasticsearch.action.search.SearchRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.RequestOptions;
import org.elasticsearch.client.RestHighLevelClient;
import org.elasticsearch.common.geo.GeoPoint;
import org.elasticsearch.common.unit.DistanceUnit;
import org.elasticsearch.index.query.BoolQueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.index.query.functionscore.FunctionScoreQueryBuilder;
import org.elasticsearch.index.query.functionscore.ScoreFunctionBuilders;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.Aggregations;
import org.elasticsearch.search.aggregations.bucket.terms.Terms;
import org.elasticsearch.search.sort.SortBuilders;
import org.elasticsearch.search.sort.SortOrder;
import org.elasticsearch.search.suggest.Suggest;
import org.elasticsearch.search.suggest.SuggestBuilder;
import org.elasticsearch.search.suggest.SuggestBuilders;
import org.elasticsearch.search.suggest.completion.CompletionSuggestion;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.stereotype.Service;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
@Service
public class HotelService extends ServiceImpl<HotelMapper, Hotel> implements IHotelService {
@Autowired
private RestHighLevelClient client;
@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);
}
}
}测试
