Java之ES各种查询
引用：https://blog.csdn.net/diaojing1918/article/details/101348589?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.channel_param
| matchAllQuery | 匹配所有文档 |
|---|---|
| queryStringQuery | 基于Lucene的字段检索 |
| wildcardQuery | 通配符查询匹配多个字符，?匹配1个字符* |
| termQuery | 词条查询 |
| matchQuery | 字段查询 |
| idsQuery | 标识符查询 |
| fuzzyQuery | 文档相似度查询 |
| includeLower includeUpper | 范围查询 |
| boolQuery | 组合查询（复杂查询） |
| SortOrder | 排序查询 |
插入样例数据：
curl -XPOST http://hadoop01:9200/sanguo/dahan/_bulk -d '
{ "index": {}}
{ "studentNo" : 1, "name" : "刘备", "male" : "男", "age" : 24 , "birthday" : "1985-02-03" , "classNo" : 1 , "address" : "湖南省长沙市" , "isLeader" : true}
{ "index": {}}
{ "studentNo" : 2, "name" : "关羽", "male" : "男", "age" : 22 , "birthday" : "1987-08-23" , "classNo" : 2, "address" : "四川省成都市" , "isLeader" : false}
{ "index": {}}
{ "studentNo" : 3, "name" : "糜夫人", "male" : "女", "age" : 19 , "birthday" : "1990-06-12" , "classNo" : 1 , "address" : "上海市" , "isLeader" : false}
{ "index": {}}
{ "studentNo" : 4, "name" : "张飞", "male" : "男", "age" : 20 , "birthday" : "1989-07-30" , "classNo" : 3 , "address" : "北京市" , "isLeader" : false}
{ "index": {}}
{ "studentNo" : 5, "name" : "诸葛亮", "male" : "男", "age" : 18 , "birthday" : "1992-04-27" , "classNo" : 2 , "address" : "江苏省南京市" , "isLeader" : true}
{ "index": {}}
{ "studentNo" : 6, "name" : "孙尚香", "male" : "女", "age" : 16 , "birthday" : "1994-05-21" , "classNo" : 3 , "address" : "广东省深圳市" , "isLeader" : false}
{ "index": {}}
{ "studentNo" : 7, "name" : "马超", "male" : "男", "age" : 19 , "birthday" : "1991-10-20" , "classNo" : 1 , "address" : "黑龙江省哈尔滨市" , "isLeader" : false}
{ "index": {}}
{ "studentNo" : 8, "name" : "赵云", "male" : "男", "age" : 23 , "birthday" : "1986-10-26" , "classNo" : 2 , "address" : "浙江省杭州市" , "isLeader" : false}
'
1：查询所有
matchAllQuery()匹配所有文件
match_all查询是Elasticsearch中最简单的查询之一。它使我们能够匹配索引中的所有文件。
/**
*matchAllQuery()匹配所有文件
match_all查询是Elasticsearch中最简单的查询之一。它使我们能够匹配索引中的所有文件
* */
@Test
public void searchAll(){
SearchResponse searchResponse = client.prepareSearch("sanguo")
.setTypes("dahan").setQuery(QueryBuilders.matchAllQuery())
.get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
2：解析查询字符串
相比其他可用的查询，query_string查询支持全部的Apache Lucene查询语法
针对多字段的query_string查询
/**
* 相比其他可用的查询，query_string查询支持全部的Apache Lucene查询语法
针对多字段的query_string查询
* */
@Test
public void query_String(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.queryStringQuery("孙尚香")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
3：通配符查询（wildcardQuery）
*匹配多个字符，?匹配1个字符
注意：避免* 开始, 会检索大量内容造成效率缓慢
/**
* *匹配多个字符，?匹配1个字符
注意：避免* 开始, 会检索大量内容造成效率缓慢
* */
@Test
public void wildcardQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.wildcardQuery("address", "广东*")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
4：词条查询（termQuery）
词条查询是Elasticsearch中的一个简单查询。它仅匹配在给定字段中含有该词条的文档，而且是确切的、未经分析的词条
termQuery("key", obj) 完全匹配
termsQuery("key", obj1, obj2..)
一次匹配多个值，有一个值是正确的，就可以查询出数据
/**
* 词条查询是Elasticsearch中的一个简单查询。它仅匹配在给定字段中含有该词条的文档，而
且是确切的、未经分析的词条
termQuery("key", obj) 完全匹配
termsQuery("key", obj1, obj2..) 一次匹配多个值，只有有一个值是正确的，就可以查询出数据
* */
@Test
public void termQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.termsQuery("name", "张飞","刘备","关羽")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
5：字段匹配查询
match**查询把query参数中的值拿出来，加以分析，然后构建相应的查询**。使用match查询时，Elasticsearch将对一个字段选择合适的分析器，所以可以确定，传给match查询的词条将被建立索引时相同的分析器处理。
/**
* match query搜索的时候，首先会解析查询字符串，进行分词，然后查询，
而term query,输入的查询内容是什么，就会按照什么去查询，并不会解析查询内容，对它分词。
* */
@Test
public void MatchQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.matchQuery("address", " 上海")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
Matchquery 和termquery的区别：
match：匹配的时候，会将查询的关键字进行分词，然后根据分词后的结果进行查询。 term：直接使用关键字进行查询，不对关键字进行分词。
multiMatchQuery("text", "field1", "field2"..); 匹配多个字段
mutilMatchQuery：
/**
* multiMatchQuery（要搜索的值 ， 在哪些字段上）
* */
@Test
public void mutileMatchQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.multiMatchQuery("北京", "address","name")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
6：只查询ID（标识符查询）
标识符查询是一个简单的查询，仅用提供的标识符来过滤返回的文档。
/**
* 按照id进行查询，通过id返回我们想要的结果
* */
@Test
public void idsQuery() {
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.idsQuery().addIds("AWNkQSCJzU0_wTuf7egi")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
7：相似度查询
插入两条测试数据：
PUT /sanguo/dahan/123
{
"name": "曹操",
"male" : "男",
"age" : 40 ,
"birthday" : "1975-02-03" ,
"classNo" : 1 ,
"address" : "海淀区坐落于北京市" ,
"isLeader" : true
}
PUT /sanguo/dahan/234
{
"name": "董卓",
"male" : "男",
"age" : 35 ,
"birthday" : "1975-02-03" ,
"classNo" : 1 ,
"address" : "北京it程序员" ,
"isLeader" : true
}
fuzzy查询是模糊查询中的第三种类型，它基于编辑距离算法来匹配文档
/**
* 相似度查询：fuzzy查询是模糊查询中的第三种类型，它基于编辑距离算法来匹配文档
* */
@Test
public void fuzzyQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.fuzzyQuery("address", "北京市")).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
System.out.println("查询结果有：" + hits.getTotalHits() + "条");
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("得分："+next.getScore());
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("===============================================");
}
}
8：范围查询
范围查询使我们能够找到在某一字段值在某个范围里的文档，字段可以是数值型，也可以是
基于字符串的
includeLower(true)：包含上界
IncludeUpper(true)：包含下界
/**
范围查询使我们能够找到在某一字段值在某个范围里的文档，字段可以是数值型，也可以是
基于字符串的
includeLower(true)：包含上界
IncludeUpper(true)：包含下界
* */
@Test
public void rangeQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.rangeQuery("age").from(18).to(22)
.includeLower(true)
.includeUpper(false))
.get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("得分："+next.getScore());
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("age : "+ next.getSource().get("age"));
System.out.println("===============================================");
}
}
9：组合查询（复杂查询）
must(QueryBuilders) : AND mustNot(QueryBuilders): NOT should(QueryBuilders):OR
插入一条数据：
PUT /sanguo/dahan/345
{
"name": "貂蝉",
"male" : "女",
"age" : 16 ,
"birthday" : "2000-02-03" ,
"classNo" : 1 ,
"address" : "北京市女it程序员" ,
"isLeader" : true
}
/*
* 组合查询：
*
must(QueryBuilders) : AND
mustNot(QueryBuilders): NOT
should(QueryBuilders):OR
* */
@Test
public void boolQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.boolQuery()
.must(QueryBuilders.matchQuery("address", "程序员"))
.must(QueryBuilders.termQuery("male", "女"))).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("得分："+next.getScore());
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("studentNo : "+ next.getSource().get("studentNo"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("birthday : "+ next.getSource().get("birthday"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("age : "+ next.getSource().get("age"));
System.out.println("===============================================");
}
}
10：排序查询
/**
* ASC : 正序（从小到大）
* DESC: 倒序（从大到小）
* */
@Test
public void SortOrderQuery(){
SearchResponse searchResponse = client.prepareSearch("sanguo").setTypes("dahan")
.setQuery(QueryBuilders.matchAllQuery())
.addSort("age", SortOrder.ASC).get();
SearchHits hits = searchResponse.getHits(); // 获取命中次数，查询结果有多少对象
Iterator iterator = hits.iterator();
while (iterator.hasNext()) {
SearchHit next = iterator.next();
System.out.println("name : "+ next.getSource().get("name"));
System.out.println("male : "+ next.getSource().get("male"));
System.out.println("classNo : "+ next.getSource().get("classNo"));
System.out.println("address : "+ next.getSource().get("address"));
System.out.println("age : "+ next.getSource().get("age"));
System.out.println("===============================================");
}
}