FlinkJob内部结构介绍_flink job

import org.apache.flink.api.common.functions.FlatMapFunction;

import org.apache.flink.api.java.tuple.Tuple2;

import org.apache.flink.streaming.api.datastream.DataStream;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

import org.apache.flink.util.Collector;

public class WordCountJob {

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

        // 创建执行环境

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 读取输入数据

        DataStream<String> input = env.readTextFile(args[0]);

        // 执行WordCount操作

        DataStream<Tuple2<String, Integer>> wordCounts = input

                .flatMap(new Tokenizer())

                .keyBy(0)

                .sum(1);

        // 输出结果到文件

        wordCounts.writeAsText(args[1]);

        // 执行作业

        env.execute("WordCountJob");

    }

    public static final class Tokenizer implements FlatMapFunction<String, Tuple2<String, Integer>> {

        @Override

        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) {

            // 将输入字符串按空格分割为单词

            String[] words = value.toLowerCase().split("\\s+");

            // 发射每个单词的计数为1

            for (String word : words) {

                if (word.length() > 0) {

                    out.collect(new Tuple2<>(word, 1));

                }

            }

        }

    }

}