Flink DataSet API和DataStream API 对于WordCount的演示

---

准备工作

pom依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.chad</groupId>
    <artifactId>guigu_learning_flink</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>8</source>
                    <target>8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <properties>
        <flink.version>1.14.2</flink.version>
        <java.version>1.8</java.version>
        <scala.binary.version>2.12</scala.binary.version>
        <slf4j.version>1.7.30</slf4j.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <!-- 日志管理 -->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.0</version>
        </dependency>
    </dependencies>
</project>

创建word.txt
在项目下创建input目录，并创建word.txt文件

Flink DataSet API

创建java类BatchWordCount

package org.chad.wordcount;

import org.apache.flink.api.common.typeinfo.Types;
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.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;


public class BatchWordCount {
    public static void main(String[] args) throws Exception {
        //1. 创建执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        //2. 读取数据源,从文件中读取
        final DataSource<String> fileDS = env.readTextFile("input/word.txt");

        //3. 转换算子操作环节，将数据转换为二元组
        FlatMapOperator<String, Tuple2<String, Long>> wordAndOne = fileDS.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
            //3. 将一行文本进行拆分，将每个单词转换为二元组输出
            String[] words = line.split(" ");
            for (String word : words) {
                out.collect(Tuple2.of(word, 1L));
            }

        }).returns(Types.TUPLE(Types.STRING, Types.LONG));

        //4. 按照word进行分组
        UnsortedGrouping<Tuple2<String, Long>> wordAndOneGroup = wordAndOne.groupBy(0);

        //5. 分组内进行聚合统计
        AggregateOperator<Tuple2<String, Long>> wordAndOneSum = wordAndOneGroup.sum(1);

        //6. 对结果打印输出
        wordAndOneSum.print();

    }
}

补充说明:
以上方式为dataset api 官放在1.12之后已经将其视为软弃用状态，使用批流一体的方式，怎么运行批处理,只需要在执行任务时，

$ bin/flink run -Dexecution.runtime-mode=BATCH BatchWordCount.jar

运行结果

Flink DataStream API

创建java类BoundedStreamWordCount

package org.chad.wordcount;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
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.util.Collector;

public class BoundedStreamWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> ds = env.readTextFile("input/word.txt");
        SingleOutputStreamOperator<Tuple2<String, Long>> wordAndOne = ds.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
            String[] words = line.split(" ");
            for (String word : words) {
                out.collect(Tuple2.of(word, 1L));
            }
        }).returns(Types.TUPLE(Types.STRING, Types.LONG));

        KeyedStream<Tuple2<String, Long>, String> tuple2StringKeyedStream = wordAndOne.keyBy(data -> data.f0);

        SingleOutputStreamOperator<Tuple2<String, Long>> sum = tuple2StringKeyedStream.sum(1);

        sum.print();

        env.execute("流处理");
    }
}

因为是流处理，所以最后一定要加上env.execute(), 去执行以下它

它的运行结果

结论

• 我们可以看到DataStream API的形式输出的结果是一条一条的去相加的，并且每一行前面会有一个进程号
• 批处理是一下子全部输出的
• 既然后续DataSet API会弃用我们就只要掌握DataStream API就可以了，只需要在后续提交任务的时候，提交模式改为BATCH 就可以了。