分布式搜索Elasticsearch——QueryBuilders.matchPhraseQuery

ES源代码中对matchPhraseQuery的描述如下所示：

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

        先看示例：

/** * @author Geloin */package com.geloin.esample.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.geloin.esample.BaseTest;import com.geloin.esample.entity.Person;/** * @author Geloin *  */public class MatchPhraseQueryTest extends BaseTest {@Testpublic void matchPhraseQuery() {try {// 创建索引BulkRequestBuilder builder = client.prepareBulk();for (int i = 0; i < 5; i++) {Person p = new Person();p.setId(UUID.randomUUID().toString());p.setAge(20);p.setIsStudent(false);p.setSex("男");p.setName("小别克听老别克讲别克的故事");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", "小别克老");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\"小别克老\"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());}}// 检索QueryBuilder qb1 = QueryBuilders.matchPhraseQuery("name", "小别克听");SearchResponse searchResponse1 = client.prepareSearch(index).setTypes(type).setQuery(qb1).setFrom(0).setSize(12).execute().actionGet();SearchHits hits1 = searchResponse1.getHits();if (null == hits1 || hits1.totalHits() == 0) {log.error("使用\"小别克听\"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());}}Thread.sleep(1000000);} catch (Exception e) {e.printStackTrace();}}}

        你会发现，使用“小别克老”没有查询出任何结果，而使用“小别克听”则查询出了我们需要的结果，这便是matchPhraseQuery和matchQuery等的区别，在使用matchQuery等时，即使你传入的是“小别克老”，在执行查询时，“小别克老”会被分词器分词，例如paoding解析成“小别/别克/老”，而使用matchPhraseQuery时，“小别克老”并不会被分词器分词，而是直接以一个短语的形式查询，而如果你在创建索引所使用的field的value中没有这么一个短语（顺序无差，且连接在一起），那么将查询不出任何结果。