Flink 分布式缓存 代码

DistributeCacheTest.java

package com.xxxxx.flink.batch;

import org.apache.commons.io.FileUtils;
import org.apache.flink.api.common.functions.RichMapFunction;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.MapOperator;
import org.apache.flink.configuration.Configuration;

import java.io.File;
import java.util.List;

/**
 * 分布式缓存
 */
public class DistributeCacheTest {

    public static void main(String[] args) throws Exception {
        ExecutionEnvironment environment = ExecutionEnvironment.getExecutionEnvironment();

        //当前项目路径.
        String project_path =System.getProperty("user.dir");

        //可以是本地文件或hdfs文件，hdfs文件路径则以hdfs://开头
        environment.registerCachedFile("file:///" + project_path + "/data/textfile", "myfile");

        DataSource<String> elements = environment.fromElements("hadoop", "flink", "spark", "hbase");

        MapOperator<String, String> map = elements.map(new RichMapFunction<String, String>() {

            @Override
            public void open(Configuration parameters) throws Exception {
                //在worker端获取缓存文件
                File myfile = getRuntimeContext().getDistributedCache().getFile("myfile");
                //读取缓存文件
                List<String> list = FileUtils.readLines(myfile);

                for (String line : list) {
                    System.out.println("[" + line + "]");
                }
            }

            @Override
            public String map(String value) throws Exception {

                return value;
            }
        });

        map.print();
    }
}