Flink入门系列4----DataStream API编程

1. 使用mvn创建一个flink-quick-start项目，自定义gav和包名

mvn archetype:generate -DarchetypeGroupId=org.apache.flink -DarchetypeArtifactId=flink-quickstart-java -DarchetypeVersion=1.8.0

2. 创建完成后使用windows命令查看所有文件

E:\git_projects>dir /s/b flink-quickstart

3. 使用idea打开项目，在pom中添加以下依赖

		<dependency>
			<groupId>org.apache.flinkgroupId>
			<artifactId>flink-clients_2.11artifactId>
			<version>${flink.version}version>
		dependency>
		<dependency>
			<groupId>org.apache.flinkgroupId>
			<artifactId>flink-connector-wikiedits_2.11artifactId>
			<version>${flink.version}version>
		dependency>

4. 新建WikipediaAnalysis类，完整版代码如下，点击运行即可：

package com.xicheng;

import org.apache.flink.api.common.functions.FoldFunction;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.streaming.connectors.wikiedits.WikipediaEditEvent;
import org.apache.flink.streaming.connectors.wikiedits.WikipediaEditsSource;

public class WikipediaAnalysis {

    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment see = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStream<WikipediaEditEvent> edits = see.addSource(new WikipediaEditsSource());

        KeyedStream<WikipediaEditEvent, String> keyedEdits = edits.keyBy(new KeySelector<WikipediaEditEvent, String>() {
            @Override
            public String getKey(WikipediaEditEvent wikipediaEditEvent) throws Exception {
                return wikipediaEditEvent.getUser();
            }
        });

        SingleOutputStreamOperator<Tuple2<String, Long>> result = keyedEdits.timeWindow(Time.seconds(5))
                .fold(new Tuple2<>("", 0L), new FoldFunction<WikipediaEditEvent, Tuple2<String, Long>>() {
                    @Override
                    public Tuple2<String, Long> fold(Tuple2<String, Long> tuple2, WikipediaEditEvent o) throws Exception {
                        tuple2.f0 = o.getUser();
                        tuple2.f1 += o.getByteDiff();
                        return tuple2;
                    }
                });
        result.print();
        see.execute();
    }
}

参考文档：https://ci.apache.org/projects/flink/flink-docs-release-1.8/tutorials/datastream_api.html#writing-a-flink-program