一、Flink 框架介绍
- 数据精准一次性处理(Exactly-Once)
- 乱序数据,迟到数据
- 低延迟,高吞吐,准确性
- 容错性
二、框架集成
2.1创建 Maven 项目
依赖
<?xml version="1.0" encoding="UTF-8"?>
<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/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.lun.es</groupId>
<artifactId>flink-elasticsearch</artifactId>
<version>1.0</version>
<properties>
<maven.compiler.source>8</maven.compiler.source>
<maven.compiler.target>8</maven.compiler.target>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-scala_2.12</artifactId>
<version>1.12.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-scala_2.12</artifactId>
<version>1.12.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_2.12</artifactId>
<version>1.12.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-elasticsearch7_2.11</artifactId>
<version>1.12.0</version>
</dependency>
<!-- jackson -->
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
<version>2.11.1</version>
</dependency>
</dependencies>
</project>
功能实现文章来源:https://www.toymoban.com/news/detail-702036.html
package com.xmx.es;
import org.apache.flink.api.common.functions.RuntimeContext;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.elasticsearch.ElasticsearchSinkFunction;
import org.apache.flink.streaming.connectors.elasticsearch.RequestIndexer;
import org.apache.flink.streaming.connectors.elasticsearch7.ElasticsearchSink;
import org.apache.http.HttpHost;
import org.elasticsearch.action.index.IndexRequest;
import org.elasticsearch.client.Requests;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
public class FlinkElasticsearchSinkTest {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
DataStreamSource<String> source = env.socketTextStream("localhost", 9999);
List<HttpHost> httpHosts = new ArrayList<>();
httpHosts.add(new HttpHost("127.0.0.1", 9200, "http"));
//httpHosts.add(new HttpHost("10.2.3.1", 9200, "http"));
// use a ElasticsearchSink.Builder to create an ElasticsearchSink
ElasticsearchSink.Builder<String> esSinkBuilder = new ElasticsearchSink.Builder<>(httpHosts,
new ElasticsearchSinkFunction<String>() {
public IndexRequest createIndexRequest(String element) {
Map<String, String> json = new HashMap<>();
json.put("data", element);
return Requests.indexRequest()
.index("my-index")
//.type("my-type")
.source(json);
}
@Override
public void process(String element, RuntimeContext ctx, RequestIndexer indexer) {
indexer.add(createIndexRequest(element));
}
}
);
// configuration for the bulk requests; this instructs the sink to emit after every element, otherwise they would be buffered
esSinkBuilder.setBulkFlushMaxActions(1);
// provide a RestClientFactory for custom configuration on the internally createdREST client
// esSinkBuilder.setRestClientFactory(
// restClientBuilder -> {
// restClientBuilder.setDefaultHeaders(...)
// restClientBuilder.setMaxRetryTimeoutMillis(...)
// restClientBuilder.setPathPrefix(...)
// restClientBuilder.setHttpClientConfigCallback(...)
// }
// );
source.addSink(esSinkBuilder.build());
env.execute("flink-es");
}
}
文章来源地址https://www.toymoban.com/news/detail-702036.html
到了这里,关于Elasticsearch 集成--Flink 框架集成的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!