学习笔记：Flink WordCount

批处理WordCount

构建Maven项目：

引入依赖：

    <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>

WordCount程序：

package wc;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

/**
 * 把文件中的单词进行分词，统计个数
 */
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 = "src/main/resources/word.txt";
        DataSet<String> inputDataSet = env.readTextFile(inputPath);

        // 对数据集进行处理，按空格分词展开，转换成（word，1）二元组进行统计
        DataSet<Tuple2<String, Integer>> resultSet = inputDataSet.flatMap(new MyFlatMapper())
                .groupBy(0)  // 按照第一个位置的word分组
                .sum(1);  // 讲第二个位置上的数据求和

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

    // 自定义MyFlatMapper类，实现FlatMapFunction接口：输入String，输出Tuple2<String, Integer>
    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer>> {
        @Override
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            // 按空格分词
            String[] words = value.split(" ");
            // 遍历所有word，包成二元组输出
            for(String word:words) {
                out.collect(new Tuple2<String, Integer>(word, 1));
            }
        }
    }
}

执行程序：

---

流处理WordCount

StreamWordCount程序：

package wc;

import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

/**
 * 流处理实现
 */
public class StreamWordCount {

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

        // 创建流处理执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 从文件中读取数据
        String inputPath = "src/main/resources/word.txt";
        DataStream<String> inputDataStream = env.readTextFile(inputPath);

        // 从Socket读取数据
        // DataStream<String> inputDataStream = env.socketTextStream("localhost",9999);

        // 基于数据流进行转换计算
        DataStream<Tuple2<String, Integer>> resultStream = inputDataStream.flatMap(new WordCount.MyFlatMapper())
                .keyBy(0)
                .sum(1);

        // 打印输出
        resultStream.print();

        // 执行任务
        env.execute();
    }
}

执行程序：

流式数据源测试：