Elasticsearch Java API简介
1、创建项目
创建Maven项目添加依赖,依赖版本与ES服务版本一致:
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.dameng.log</groupId>
<artifactId>restLog</artifactId>
<packaging>war</packaging>
<version>1.0-SNAPSHOT</version>
<name>restLog Maven Webapp</name>
<url>http://maven.apache.org</url>
<repositories>
<repository>
<id>elasticsearch-releases</id>
<url>https://artifacts.elastic.co/maven</url>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>false</enabled>
</snapshots>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.elasticsearch.client</groupId>
<artifactId>x-pack-transport</artifactId>
<version>5.4.1</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.8.2</version>
</dependency>
</dependencies>
<build>
<finalName>restLog</finalName>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
</plugins>
</build>
</project>
值得注意的是,如果ES安装了x-pack插件,在链接ES服务时需要使用 PreBuiltXPackTransportClient ,该类在x-pack-transport包中,这个包在Maven的公共库里是没有的,需要添加ES的库。
2、ES基本配置与连接
2.1、基本配置
ES有两种连接方式: Connecting a Client to a Coordinating Only Node 和 Transport Client ,本文使用的是后者,基本配置内容如下:
# Elasticsearch configuration
# ES的集群名称
cluster.name = elasticsearch
# 是否发现集群中的其他节点
client.transport.sniff = true
# 如果安装的x-pack插件,此处填写ES的用户名和密码
xpack.security.user = elastic:changeme
# 链接ES节点地址
transportAddress = localhost:9300
# 默认时区,用于查询时的日期比较
default.timeZone = Asia/Shanghai
# 默认返回页大小
default.size = 100
# 默认返回起始位置
default.from = 0
2.2、建立连接
建立client的代码如下:
package com.dameng.es;
import org.elasticsearch.client.transport.TransportClient;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.transport.InetSocketTransportAddress;
import org.elasticsearch.transport.client.PreBuiltTransportClient;
import org.elasticsearch.xpack.client.PreBuiltXPackTransportClient;
import java.io.IOException;
import java.io.InputStream;
import java.net.InetAddress;
import java.util.*;
/**
* Created by lion on 2017/7/24.
*/
public class ESUtil {
private static volatile TransportClient client = null;
private static String timeZone = "";
public static String getDefaultTimeZone() {
return timeZone;
}
public static String getDefaultSize() {
try {
return ESUtil.getProperties().getProperty("default.size", "100");
} catch (IOException e) {
e.printStackTrace();
}
return "100";
}
public static String getDefaultFrom() {
try {
return ESUtil.getProperties().getProperty("default.from", "0");
} catch (IOException e) {
e.printStackTrace();
}
return "0";
}
private ESUtil () {
}
/**
* 读取配置文件
* @return
* @throws IOException
*/
private static Properties getProperties() throws IOException {
try (InputStream inputStream = ESUtil.class.getClassLoader().getResourceAsStream("ES.properties")) {
Properties properties = new Properties();
properties.load(inputStream);
return properties;
}
}
/**
* 获取ES客户端,单例实现
* @return
*/
public static TransportClient getClient() throws Exception {
if (ESUtil.client == null) {
Properties properties = ESUtil.getProperties();
Settings.Builder builder = Settings.builder();
builder.put("cluster.name", properties.getProperty("properties"));
builder.put("client.transport.sniff", properties.getProperty("client.transport.sniff"));
builder.put("xpack.security.user", properties.getProperty("xpack.security.user"));
Settings settings = builder.build();
if (settings.isEmpty()) {
throw new Exception("ES设置项未设置.");
}
if (settings.get("xpack.security.user") == null || settings.get("xpack.security.user").equals("")) {
ESUtil.client = new PreBuiltTransportClient(settings);
} else {
ESUtil.client = new PreBuiltXPackTransportClient(settings);
}
String transportAddress = properties.getProperty("transportAddress");
if (transportAddress == null || transportAddress.equals("")) {
throw new Exception("ES集群地址未设置.");
}
String[] address = transportAddress.split(",");
for (int i = 0; i < address.length; i++) {
String hoseName = address[i].split(":")[0];
int port = Integer.parseInt(address[i].split(":")[1]);
ESUtil.client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName(hoseName), port));
}
ESUtil.timeZone = properties.getProperty("default.timeZone", "Asia/Shanghai");
}
return ESUtil.client;
}
}
3、API代码事例
3.1、查询
3.1.1、查询全部内容
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.2、设置索引
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setIndices("file*").get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.3、设置类型
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setIndices("file*").setTypes("BIZZ").get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.4、设置翻页
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setFrom(0).setSize(100).get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.5、字段过滤
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.termQuery("level", "BIZZ")).get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.6、通配符查询
通配符支持 * 和 ? 两个, * 表示任意多个字符, ? 表示单个字符:
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.wildcardQuery("level", "I*")).get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.7、多条件查询
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
ExistsQueryBuilder existsQueryBuilder = QueryBuilders.existsQuery("offset");
TermQueryBuilder termQueryBuilder = QueryBuilders.termQuery("level", "BIZZ");
BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery().must(existsQueryBuilder).must(termQueryBuilder);
SearchResponse searchResponse = client.prepareSearch().setQuery(boolQueryBuilder).get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.8、范围查询
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
ExistsQueryBuilder existsQueryBuilder = QueryBuilders.existsQuery("offset");
RangeQueryBuilder rangeQueryBuilder = QueryBuilders.rangeQuery("offset").gte(0).lt(134166220);
BoolQueryBuilder boolQueryBuilder = QueryBuilders.boolQuery().must(existsQueryBuilder).must(rangeQueryBuilder);
SearchResponse searchResponse = client.prepareSearch().setQuery(boolQueryBuilder).get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.1.9、时间查询
对于时间范围查询,需要注意时区的问题。ES默认使用的UTC时区,在日起比较时需要设置为当前时区。还有一点需要注意:ES默认的时间格式是ISO8601。
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.rangeQuery("@timestamp").timeZone(ESUtil.getDefaultTimeZone()).gt("2017-07-25T16:30")).get();
SearchHits hits = searchResponse.getHits();
System.out.println(hits.totalHits);
if (hits.getTotalHits() > 0) {
for (SearchHit hit : hits) {
System.out.println(hit.getSourceAsString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.2、统计
3.2.1、简单分组统计
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.existsQuery("level")).addAggregation(AggregationBuilders.terms("by_level").field("level")).get();
StringTerms by_level = searchResponse.getAggregations().get("by_level");
List<Terms.Bucket> buckets = by_level.getBuckets();
for (Terms.Bucket bucket : buckets) {
System.out.println(bucket.getKey() + ":" + bucket.getDocCount());
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.2.2、时间频度统计
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.existsQuery("level")).addAggregation(AggregationBuilders.dateHistogram("by_day").field("@timestamp").dateHistogramInterval(DateHistogramInterval.DAY)).get();
InternalDateHistogram by_day = searchResponse.getAggregations().get("by_day");
List<InternalDateHistogram.Bucket> buckets = by_day.getBuckets();
for (InternalDateHistogram.Bucket bucket : buckets) {
DateFormat df = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'");
df.setTimeZone(TimeZone.getTimeZone("Asia/shanghai"));
System.out.println(new SimpleDateFormat("yyyy-MM-dd").format(df.parse(bucket.getKeyAsString())) + ":" + bucket.getDocCount());
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.2.3、多维度分组统计
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.existsQuery("level")).addAggregation(
AggregationBuilders.dateHistogram("by_day").field("@timestamp").dateHistogramInterval(DateHistogramInterval.DAY).subAggregation(
AggregationBuilders.terms("by_level").field("level")
)
).get();
InternalDateHistogram by_day = searchResponse.getAggregations().get("by_day");
List<InternalDateHistogram.Bucket> buckets = by_day.getBuckets();
for (InternalDateHistogram.Bucket bucket : buckets) {
DateFormat df = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'");
df.setTimeZone(TimeZone.getTimeZone("Asia/shanghai"));
System.out.println(new SimpleDateFormat("yyyy-MM-dd").format(df.parse(bucket.getKeyAsString())) + ":" + bucket.getDocCount());
InternalTerms by_level = bucket.getAggregations().get("by_level");
List<Terms.Bucket> buckets_level = by_level.getBuckets();
for (Terms.Bucket bucket_level : buckets_level) {
System.out.println("\t" + bucket_level.getKey() + ":" + bucket_level.getDocCount());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
3.2.4、聚合函数
public static void main(String[] args) {
try {
TransportClient client = ESUtil.getClient();
SearchResponse searchResponse = client.prepareSearch().setQuery(QueryBuilders.existsQuery("offset")).addAggregation(
AggregationBuilders.dateHistogram("by_day").field("@timestamp").dateHistogramInterval(DateHistogramInterval.DAY).subAggregation(
AggregationBuilders.max("max_offset").field("offset")
)
).get();
InternalDateHistogram by_day = searchResponse.getAggregations().get("by_day");
List<InternalDateHistogram.Bucket> buckets = by_day.getBuckets();
for (InternalDateHistogram.Bucket bucket : buckets) {
DateFormat df = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'");
df.setTimeZone(TimeZone.getTimeZone("Asia/shanghai"));
System.out.println(new SimpleDateFormat("yyyy-MM-dd").format(df.parse(bucket.getKeyAsString())) + ":" + bucket.getDocCount());
InternalMax max_offset = bucket.getAggregations().get("max_offset");
System.out.println("\t" + max_offset.getName() + ":" + max_offset.getValue());
}
} catch (Exception e) {
e.printStackTrace();
}
}
4、注意事项
- x-pack插件需要用到x-pack-transport依赖,x-pack并非开源(收费)软件,该依赖在Maven公共库中没有;
- 日起过滤时注意时区设置;
5、参考资料:
- 官方文档:https://www.elastic.co/guide/en/elasticsearch/client/java-api/current/index.html
- ES 2.3.3 JAVA api说明文档:https://www.blog-china.cn/template/documentHtml/1484101683485.html#title_9
- ES java api 基本搜索部分详解:http://blog.youkuaiyun.com/molong1208/article/details/50512149
6、补充:将任意Aggregations转换为JSON的例子
以下代码算是一个思路,将多层嵌套的统计结果转换成json格式的字符串,调用方法类似这样:"{\"result\": [" + this.analysisAggregations(searchResponse.getAggregations()) + "]}";
private String analysisAggregations (Aggregations aggregations) {
StringBuffer sb = new StringBuffer();
for (Aggregation aggregation : aggregations.asList()) {
if (aggregation instanceof StringTerms) {
for (Terms.Bucket bucket : ((StringTerms) aggregation).getBuckets()) {
String result = analysisAggregations(bucket.getAggregations());
if (result == null || result.equals("")) {
result = String.valueOf(bucket.getDocCount());
}
if (result.indexOf(",") != -1) {
sb.append(",{\"").append(bucket.getKeyAsString()).append("\":[").append(result).append("]}");
} else {
sb.append(",{\"").append(bucket.getKeyAsString()).append("\":").append(result).append("}");
}
}
}
if (aggregation instanceof InternalDateHistogram) {
for (InternalDateHistogram.Bucket bucket : ((InternalDateHistogram) aggregation).getBuckets()) {
String result = analysisAggregations(bucket.getAggregations());
if (result == null || result.equals("")) {
result = String.valueOf(bucket.getDocCount());
}
if (result.indexOf(",") != -1) {
sb.append(",{\"").append(bucket.getKeyAsString()).append("\":[").append(result).append("]}");
} else {
sb.append(",{\"").append(bucket.getKeyAsString()).append("\":").append(result).append("}");
}
}
}
if (aggregation instanceof InternalNumericMetricsAggregation.SingleValue) {
sb.append(",{\"").append(aggregation.getName()).append("\":\"").append(((InternalNumericMetricsAggregation.SingleValue) aggregation).getValueAsString()).append("\"}");
}
}
if (sb.length() == 0) {
return "";
}
return sb.substring(1);
}
本文介绍如何通过Java API操作Elasticsearch,包括创建项目、配置连接、执行查询及统计等常见操作,并提供多个代码示例。
6691

被折叠的 条评论
为什么被折叠?



