分布式搜索Elasticsearch——QueryBuilders.matchPhrasePrefixQuery

注：该文项目基础为分布式搜索Elasticsearch——项目过程（一）和分布式搜索Elasticsearch——项目过程（二），项目骨架可至这里下载。

ES源代码中对matchPhrasePrefixQuery的描述如下所示：

/**
* Creates a match query with type "PHRASE_PREFIX" for the provided field name and text.
*
* @param name The field name.
* @param text The query text (to be analyzed).
*/
public static MatchQueryBuilder matchPhrasePrefixQuery(String name, Object text) {
return new MatchQueryBuilder(name, text).type(MatchQueryBuilder.Type.PHRASE_PREFIX);
}

如果你调用matchPhrasePrefixQuery时，text为中文，那么，很大可能是一种状况：你会发现，matchPhraseQuery和matchPhrasePrefixQuery没有任何差别。而当text为英文时，差别就显现出来了：matchPhraseQuery的text是一个英文单词，而matchPhrasePrefixQuery的text则无这一约束，你可以从一个英文单词中抽几个连接在一起的字母进行查询。

示例代码如下所示：

/**
* @author Geloin
*/
package com.gsoft.gsearch.util;

import java.util.UUID;

import junit.framework.Assert;

import org.elasticsearch.action.bulk.BulkRequestBuilder;
import org.elasticsearch.action.bulk.BulkResponse;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.index.query.QueryBuilder;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.search.SearchHits;
import org.junit.Test;

import com.gsoft.gsearch.BaseTest;
import com.gsoft.gsearch.entity.Person;

/**
* 以短语形式查询，查询时关键字不会被分词，而是直接以一个字符串的形式查询
*
* @author Geloin
*
*/
public class MatchPhrasePrefixQueryTest extends BaseTest {

@Test
public void matchPhrasePrefixQuery() {
try {

// 创建索引
BulkRequestBuilder builder = client.prepareBulk();

for (int i = 0; i < 2; i++) {
Person p = new Person();
p.setId(UUID.randomUUID().toString());
p.setAge(20);
p.setIsStudent(false);
p.setSex("男");
p.setName("Zhangsan wang");

String source = ElasticSearchUtil.BeanToJson(p);

IndexRequest request = client.prepareIndex().setIndex(index)
.setType(type).setId(p.getId()).setSource(source)
.request();

builder.add(request);
}

BulkResponse bResponse = builder.execute().actionGet();
if (bResponse.hasFailures()) {
Assert.fail("创建索引出错！");
}

// 检索
QueryBuilder qb = QueryBuilders.matchPhraseQuery("name", "wa");

SearchResponse searchResponse = client.prepareSearch(index)
.setTypes(type).setQuery(qb).setFrom(0).setSize(12)
.execute().actionGet();

SearchHits hits = searchResponse.getHits();
if (null == hits || hits.totalHits() == 0) {
log.error("使用matchPhraseQuery(\"name\", \"wa\")没有查询到任何结果！");
} else {
for (SearchHit hit : hits) {
String json = hit.getSourceAsString();

Person newPerson = mapper.readValue(json, Person.class);
System.out.println("name\t\t" + newPerson.getName());
System.out.println("sex\t\t" + newPerson.getSex());
System.out.println("age\t\t" + newPerson.getAge());
System.out.println("isStudent\t\t"
+ newPerson.getIsStudent());
}
}

System.out.println("===================================================");

// 检索
QueryBuilder qb1 = QueryBuilders.matchPhrasePrefixQuery("name", "wa");

SearchResponse searchResponse1 = client.prepareSearch(index)
.setTypes(type).setQuery(qb1).setFrom(0).setSize(20)
.execute().actionGet();

SearchHits hits1 = searchResponse1.getHits();

if (null == hits1 || hits1.totalHits() == 0) {
log.error("使用matchPhrasePrefixQuery(\"name\", \"wa\")没有查询到任何结果！");
return;
} else {
for (SearchHit hit : hits1) {
String json = hit.getSourceAsString();

Person newPerson = mapper.readValue(json, Person.class);
System.out.println("name\t\t" + newPerson.getName());
System.out.println("sex\t\t" + newPerson.getSex());
System.out.println("age\t\t" + newPerson.getAge());
System.out.println("isStudent\t\t"
+ newPerson.getIsStudent());
}
}

} catch (Exception e) {
e.printStackTrace();
} finally {
if (null != client) {
client.close();
}
if (null != node) {
node.close();
}
}
}
}

你会发现，使用matchPhraseQuery并未查询出结果，而matchPhrasePrefixQuery查询出的，则是我们需要的结果。