flink 一、wordCount入门示例

1、Java版本batch wordcount

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.FlatMapOperator;
import org.apache.flink.api.java.operators.MapOperator;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;


public class flinkWordCountBatchJava {
    public static void main(String[] args) throws Exception {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSource<String> dataSource = env.readTextFile("F://word.txt");
        FlatMapOperator<String, String> flatMapString = dataSource.flatMap(new FlatMapFunction<String, String>() {

            public void flatMap(String s, Collector<String> collector) {
                String[] words = s.split(" ");
                for (String word : words) {
                    collector.collect(word);
                }
            }
        });
        MapOperator<String, Tuple2<String,Long>> mapTuple = flatMapString.map(new MapFunction<String, Tuple2<String,Long>>() {
            public Tuple2<String, Long> map(String s){
                return new Tuple2<String, Long>(s, 1L);
            }
        });
        AggregateOperator<Tuple2<String,Long>> sum = mapTuple.groupBy(0).sum(1);
        sum.print();
    }
}

2、Java版本 stream wordcount

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class flinkWordCountStreamJava {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> dataStreamSource = env.socketTextStream("192.168.169.128", 9000, "\n");
        SingleOutputStreamOperator<Tuple2<String, Integer>> tuple2SingleOutputStreamOperator = dataStreamSource.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
                for (String s1 : s.split(" ")) {
                    collector.collect(new Tuple2<String, Integer>(s1, 1));
                }
            }
        });
        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = tuple2SingleOutputStreamOperator.keyBy(0).sum(1);
        sum.print();
        env.execute();
    }
}

3、Scala版本batch

import org.apache.flink.api.scala.ExecutionEnvironment

object flinkWordCountBatch {
  def main(args: Array[String]): Unit = {
    // 加载环境
    val env = ExecutionEnvironment.getExecutionEnvironment
    // 指定读取文件
    val fileSource = env.readTextFile("F://word.txt")
    import org.apache.flink.api.scala._
    fileSource.flatMap(_.split(" "))
      .map((_,1))
      .groupBy(0)
      .sum(1)
      .print()
  }
}

4、scala版本stream

import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment

object flinkWordCountStream {
  def main(args: Array[String]): Unit = {
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    val socketSource = env.socketTextStream("192.168.169.128",9000,'\n')
    import org.apache.flink.api.scala._
    socketSource.flatMap(_.split(" "))
      .map((_,1))
      .keyBy(0)
      .sum(1)
      .print()
    env.execute()
  }
}