Flink-02 上手

搭建maven工程 FlinkTutorial
pom文件

<?xml version="1.0" encoding="UTF-8"?>

4.0.0
com.atguigu.flink
FlinkTutorial
1.0-SNAPSHOT

<dependencies>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-java</artifactId>
        <version>1.10.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-streaming-java_2.12</artifactId>
        <version>1.10.1</version>
    </dependency>
</dependencies>

批处理 wordcount
src/main/java/com.atguigu.wc/WordCount.java

public class WordCount {
    public static void main(String[] args) throws Exception {

        // 创建执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // 从文件中读取数据
        String inputPath = "hello.txt";
        DataSet<String> inputDataSet = env.readTextFile(inputPath);

        // 空格分词打散之后，对单词进行groupby分组，然后用sum进行聚合
        DataSet<Tuple2<String, Integer>> wordCountDataSet =
                inputDataSet.flatMap(new MyFlatMapper())
                .groupBy(0)
                .sum(1);

        // 打印输出
        wordCountDataSet.print();
    }

    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer>> {
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            String[] words = value.split(" ");
            for (String word : words) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }
}

流处理 wordcount
src/main/scala/com.atguigu.wc/StreamWordCount.java

public class StreamWordCount {
    public static void main(String[] args) throws Exception{
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        ParameterTool parameterTool = ParameterTool.fromArgs(args);
        String host = parameterTool.get("host");
        int port = parameterTool.getInt("port");

        DataStream<String> inputDataStream = env.socketTextStream(host, port);

        DataStream<Tuple2<String, Integer>> wordCountDataStream = inputDataStream
                .flatMap( new WordCount.MyFlatMapper())
                .keyBy(0)
                .sum(1);
        wordCountDataStream.print().setParallelism(1);

        env.execute();
    }
}

测试——在linux系统中用netcat命令进行发送测试。

nc -lk  7777