flink-01 wordcount

<?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>com.learn</groupId>
    <artifactId>Flink17Learn</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java</artifactId>
            <version>1.17.1</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients</artifactId>
            <version>1.17.1</version>
            <scope>provided</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.2.4</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <artifactSet>
                                <excludes>
                                    <exclude>com.google.code.findbugs:jsr305</exclude>
                                    <exclude>org.slf4j:*</exclude>
                                    <exclude>log4j:*</exclude>
                                </excludes>
                            </artifactSet>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers combine.children="append">
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"></transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

import org.apache.flink.api.common.functions.FlatMapFunction;
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 WordCountBatchDemo {
    public static void main(String[] args) throws Exception {
        // TODO 1.创建执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        // TODO 2.读取数据
        DataSource<String> lineDS = env.readTextFile("input/words.txt");
        // TODO 3.切分、转换
        FlatMapOperator<String, Tuple2<String, Integer>> wordAndOne = lineDS.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String line, Collector<Tuple2<String, Integer>> out) throws Exception {
                String[] words = line.split(" ");
                for (String word : words) {
                    out.collect(Tuple2.of(word, 1));
                }
            }
        });
        // TODO 4.按照word进行分组
        UnsortedGrouping<Tuple2<String, Integer>> wordAndOneGroupBy = wordAndOne.groupBy(0);
        // TODO 5.各分组内聚合
        AggregateOperator<Tuple2<String, Integer>> sum = wordAndOneGroupBy.sum(1);
        // TODO 6.输出
        sum.print();
    }
}

package com.learn.wc;

import org.apache.flink.api.common.functions.FlatMapFunction;
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.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

public class WordCountStreamDemo {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> socketDS = env.socketTextStream("hadoop101", 7777);
        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = socketDS.flatMap((FlatMapFunction<String, Tuple2<String, Integer>>) (value, out) -> {
            String[] words = value.split(" ");
            for (String word : words) {
                out.collect(Tuple2.of(word, 1));
            }
        }).returns(Types.TUPLE(Types.STRING, Types.INT))
                .keyBy(value -> value.f0)
                .sum(1);
        sum.print();
        env.execute();
    }
}