Elasticsearch 之（43） Java API 实现 ES 的 增删改查、聚合分析
1、maven依赖
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>transport</artifactId>
<version>5.2.2</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>2.7</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.7</version>
</dependency>log4j2.properties
appender.console.type = Console appender.console.name = console appender.console.layout.type = PatternLayout rootLogger.level = info rootLogger.appenderRef.console.ref = console2、增删改查
package com.es.app;
import java.net.InetAddress;
import org.elasticsearch.action.delete.DeleteResponse;
import org.elasticsearch.action.get.GetResponse;
import org.elasticsearch.action.index.IndexResponse;
import org.elasticsearch.action.update.UpdateResponse;
import org.elasticsearch.client.transport.TransportClient;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.transport.InetSocketTransportAddress;
import org.elasticsearch.common.xcontent.XContentFactory;
import org.elasticsearch.transport.client.PreBuiltTransportClient;
/**
* 员工增删改查的应用程序
* @author Administrator
*
*/
public class EmployeeCRUDApp {
@SuppressWarnings({ "unchecked", "resource" })
public static void main(String[] args) throws Exception {
// 先构建client
Settings settings = Settings.builder()
.put("cluster.name", "elasticsearch")
.build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("localhost"), 9300));
// createEmployee(client);
// getEmployee(client);
// updateEmployee(client);
// deleteEmployee(client);
client.close();
}
/**
* 创建员工信息（创建一个document）
* @param client
*/
private static void createEmployee(TransportClient client) throws Exception {
IndexResponse response = client.prepareIndex("company", "employee", "1")
.setSource(XContentFactory.jsonBuilder()
.startObject()
.field("name", "jack")
.field("age", 27)
.field("position", "technique")
.field("country", "china")
.field("join_date", "2017-01-01")
.field("salary", 10000)
.endObject())
.get();
System.out.println(response.getResult());
}
/**
* 获取员工信息
* @param client
* @throws Exception
*/
private static void getEmployee(TransportClient client) throws Exception {
GetResponse response = client.prepareGet("company", "employee", "1").get();
System.out.println(response.getSourceAsString());
}
/**
* 修改员工信息
* @param client
* @throws Exception
*/
private static void updateEmployee(TransportClient client) throws Exception {
UpdateResponse response = client.prepareUpdate("company", "employee", "1")
.setDoc(XContentFactory.jsonBuilder()
.startObject()
.field("position", "technique manager")
.endObject())
.get();
System.out.println(response.getResult());
}
/**
* 删除 员工信息
* @param client
* @throws Exception
*/
private static void deleteEmployee(TransportClient client) throws Exception {
DeleteResponse response = client.prepareDelete("company", "employee", "1").get();
System.out.println(response.getResult());
}
}需求：
（1）搜索职位中包含technique的员工
（2）同时要求age在30到40岁之间
（3）分页查询，查找第一页
GET /company/employee/_search
{
"query": {
"bool": {
"must": [
{
"match": {
"position": "technique"
}
}
],
"filter": {
"range": {
"age": {
"gte": 30,
"lte": 40
}
}
}
}
},
"from": 0,
"size": 1
}
一边运行创建document，一边搜索什么都没搜索到？？？？
近实时！！！默认是1秒以后，写入es的数据，才能被搜索到。
package com.es.app;
import java.net.InetAddress;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.transport.TransportClient;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.transport.InetSocketTransportAddress;
import org.elasticsearch.common.xcontent.XContentFactory;
import org.elasticsearch.index.query.QueryBuilders;
import org.elasticsearch.search.SearchHit;
import org.elasticsearch.transport.client.PreBuiltTransportClient;
/**
* 员工搜索应用程序
* @author Administrator
*
*/
public class EmployeeSearchApp {
@SuppressWarnings({ "unchecked", "resource" })
public static void main(String[] args) throws Exception {
Settings settings = Settings.builder()
.put("cluster.name", "elasticsearch")
.build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("localhost"), 9300));
// prepareData(client);
executeSearch(client);
client.close();
}
/**
* 执行搜索操作
* @param client
*/
private static void executeSearch(TransportClient client) {
SearchResponse response = client.prepareSearch("company")
.setTypes("employee")
.setQuery(QueryBuilders.matchQuery("position", "technique"))
.setPostFilter(QueryBuilders.rangeQuery("age").from(30).to(40))
.setFrom(0).setSize(1)
.get();
SearchHit[] searchHits = response.getHits().getHits();
for(int i = 0; i < searchHits.length; i++) {
System.out.println(searchHits[i].getSourceAsString());
}
}
/**
* 准备数据
* @param client
*/
private static void prepareData(TransportClient client) throws Exception {
client.prepareIndex("company", "employee", "1")
.setSource(XContentFactory.jsonBuilder()
.startObject()
.field("name", "jack")
.field("age", 27)
.field("position", "technique software")
.field("country", "china")
.field("join_date", "2017-01-01")
.field("salary", 10000)
.endObject())
.get();
client.prepareIndex("company", "employee", "2")
.setSource(XContentFactory.jsonBuilder()
.startObject()
.field("name", "marry")
.field("age", 35)
.field("position", "technique manager")
.field("country", "china")
.field("join_date", "2017-01-01")
.field("salary", 12000)
.endObject())
.get();
client.prepareIndex("company", "employee", "3")
.setSource(XContentFactory.jsonBuilder()
.startObject()
.field("name", "tom")
.field("age", 32)
.field("position", "senior technique software")
.field("country", "china")
.field("join_date", "2016-01-01")
.field("salary", 11000)
.endObject())
.get();
client.prepareIndex("company", "employee", "4")
.setSource(XContentFactory.jsonBuilder()
.startObject()
.field("name", "jen")
.field("age", 25)
.field("position", "junior finance")
.field("country", "usa")
.field("join_date", "2016-01-01")
.field("salary", 7000)
.endObject())
.get();
client.prepareIndex("company", "employee", "5")
.setSource(XContentFactory.jsonBuilder()
.startObject()
.field("name", "mike")
.field("age", 37)
.field("position", "finance manager")
.field("country", "usa")
.field("join_date", "2015-01-01")
.field("salary", 15000)
.endObject())
.get();
}
}需求：
（1）首先按照country国家来进行分组
（2）然后在每个country分组内，再按照入职年限进行分组
（3）最后计算每个分组内的平均薪资
package com.es.app;
import java.net.InetAddress;
import java.util.Iterator;
import java.util.Map;
import org.elasticsearch.action.search.SearchResponse;
import org.elasticsearch.client.transport.TransportClient;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.transport.InetSocketTransportAddress;
import org.elasticsearch.search.aggregations.Aggregation;
import org.elasticsearch.search.aggregations.AggregationBuilders;
import org.elasticsearch.search.aggregations.bucket.histogram.DateHistogramInterval;
import org.elasticsearch.search.aggregations.bucket.histogram.Histogram;
import org.elasticsearch.search.aggregations.bucket.terms.StringTerms;
import org.elasticsearch.search.aggregations.bucket.terms.Terms.Bucket;
import org.elasticsearch.search.aggregations.metrics.avg.Avg;
import org.elasticsearch.transport.client.PreBuiltTransportClient;
/**
* 员工聚合分析应用程序
* @author Administrator
*
*/
public class EmployeeAggrApp {
@SuppressWarnings({ "unchecked", "resource" })
public static void main(String[] args) throws Exception {
Settings settings = Settings.builder()
.put("cluster.name", "elasticsearch")
.build();
TransportClient client = new PreBuiltTransportClient(settings)
.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName("localhost"), 9300));
SearchResponse searchResponse = client.prepareSearch("company")
.addAggregation(AggregationBuilders.terms("group_by_country").field("country")
.subAggregation(AggregationBuilders
.dateHistogram("group_by_join_date")
.field("join_date")
.dateHistogramInterval(DateHistogramInterval.YEAR)
.subAggregation(AggregationBuilders.avg("avg_salary").field("salary")))
)
.execute().actionGet();
Map<String, Aggregation> aggrMap = searchResponse.getAggregations().asMap();
StringTerms groupByCountry = (StringTerms) aggrMap.get("group_by_country");
Iterator<Bucket> groupByCountryBucketIterator = groupByCountry.getBuckets().iterator();
while(groupByCountryBucketIterator.hasNext()) {
Bucket groupByCountryBucket = groupByCountryBucketIterator.next();
System.out.println(groupByCountryBucket.getKey() + ":" + groupByCountryBucket.getDocCount());
Histogram groupByJoinDate = (Histogram) groupByCountryBucket.getAggregations().asMap().get("group_by_join_date");
Iterator<org.elasticsearch.search.aggregations.bucket.histogram.Histogram.Bucket> groupByJoinDateBucketIterator = groupByJoinDate.getBuckets().iterator();
while(groupByJoinDateBucketIterator.hasNext()) {
org.elasticsearch.search.aggregations.bucket.histogram.Histogram.Bucket groupByJoinDateBucket = groupByJoinDateBucketIterator.next();
System.out.println(groupByJoinDateBucket.getKey() + ":" +groupByJoinDateBucket.getDocCount());
Avg avg = (Avg) groupByJoinDateBucket.getAggregations().asMap().get("avg_salary");
System.out.println(avg.getValue());
}
}
client.close();
}
}正排索引没开启时候，会报错：
Exception in thread "main" Failed to execute phase [query], all shards failed; shardFailures {[yLv8gDZQQ5eMlHYMN0lKTg][company][0]: RemoteTransportException[[yLv8gDZ][127.0.0.1:9300][indices:data/read/search[phase/query]]]; nested: IllegalArgumentException[Fielddata is disabled on text fields by default. Set fielddata=true on [country] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory.]; }{[yLv8gDZQQ5eMlHYMN0lKTg][company][1]: RemoteTransportException[[yLv8gDZ][127.0.0.1:9300][indices:data/read/search[phase/query]]]; nested: IllegalArgumentException[Fielddata is disabled on text fields by default. Set fielddata=true on [country] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory.]; }{[yLv8gDZQQ5eMlHYMN0lKTg][company][2]: RemoteTransportException[[yLv8gDZ][127.0.0.1:9300][indices:data/read/search[phase/query]]]; nested: IllegalArgumentException[Fielddata is disabled on text fields by default. Set fielddata=true on [country] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory.]; }{[yLv8gDZQQ5eMlHYMN0lKTg][company][3]: RemoteTransportException[[yLv8gDZ][127.0.0.1:9300][indices:data/read/search[phase/query]]]; nested: IllegalArgumentException[Fielddata is disabled on text fields by default. Set fielddata=true on [country] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory.]; }{[yLv8gDZQQ5eMlHYMN0lKTg][company][4]: RemoteTransportException[[yLv8gDZ][127.0.0.1:9300][indices:data/read/search[phase/query]]]; nested: IllegalArgumentException[Fielddata is disabled on text fields by default. Set fielddata=true on [country] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory.]; }重新构建mappingGET /company/_mapping/employee
DELETE /company
PUT /company
{
"mappings": {
"employee": {
"properties": {
"age": {
"type": "long"
},
"country": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
},
"fielddata": true
},
"join_date": {
"type": "date"
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"position": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"salary": {
"type": "long"
}
}
}
}
}