Flink java wordcount案例（批处理、流处理）

基本思路：

1. 首先构造pom.xml
2. 构造数据源，把数据都写在文件中
3. 批处理：使用import org.apache.flink.api.java.DataSet;读取数据
4. 流处理：使用import org.apache.flink.streaming.api.datastream.DataStream;读取数据

首先新建一个maven项目：

1.pom.xml

<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.myorg.quickstart</groupId>
    <artifactId>quickstart</artifactId>
    <version>0.1</version>
    <packaging>jar</packaging>

    <name>Flink Quickstart Job</name>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <flink.version>1.13.2</flink.version>
        <target.java.version>1.8</target.java.version>
        <scala.binary.version>2.11</scala.binary.version>
        <maven.compiler.source>${target.java.version}</maven.compiler.source>
        <maven.compiler.target>${target.java.version}</maven.compiler.target>
        <log4j.version>2.12.1</log4j.version>
    </properties>

    <repositories>
        <repository>
            <id>apache.snapshots</id>
            <name>Apache Development Snapshot Repository</name>
            <url>https://repository.apache.org/content/repositories/snapshots/</url>
            <releases>
                <enabled>false</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
        </repository>
    </repositories>

    <dependencies>
        <!-- Apache Flink dependencies -->
        <!-- These dependencies are provided, because they should not be packaged into the JAR file. -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>compile</scope>
        </dependency>

        <!-- Add connector dependencies here. They must be in the default scope (compile). -->

        <!-- Example:

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        -->

        <!-- Add logging framework, to produce console output when running in the IDE. -->
        <!-- These dependencies are excluded from the application JAR by default. -->
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-slf4j-impl</artifactId>
            <version>${log4j.version}</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-api</artifactId>
            <version>${log4j.version}</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>${log4j.version}</version>
            <scope>runtime</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>

            <!-- Java Compiler -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.1</version>
                <configuration>
                    <source>${target.java.version}</source>
                    <target>${target.java.version}</target>
                </configuration>
            </plugin>

            <!-- We use the maven-shade plugin to create a fat jar that contains all necessary dependencies. -->
            <!-- Change the value of <mainClass>...</mainClass> if your program entry point changes. -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.1</version>
                <executions>
                    <!-- Run shade goal on package phase -->
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <artifactSet>
                                <excludes>
                                    <exclude>org.apache.flink:force-shading</exclude>
                                    <exclude>com.google.code.findbugs:jsr305</exclude>
                                    <exclude>org.slf4j:*</exclude>
                                    <exclude>org.apache.logging.log4j:*</exclude>
                                </excludes>
                            </artifactSet>
                            <filters>
                                <filter>
                                    <!-- Do not copy the signatures in the META-INF folder.
                                    Otherwise, this might cause SecurityExceptions when using the JAR. -->
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>org.myorg.quickstart.StreamingJob</mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>

        <pluginManagement>
            <plugins>

                <!-- This improves the out-of-the-box experience in Eclipse by resolving some warnings. -->
                <plugin>
                    <groupId>org.eclipse.m2e</groupId>
                    <artifactId>lifecycle-mapping</artifactId>
                    <version>1.0.0</version>
                    <configuration>
                        <lifecycleMappingMetadata>
                            <pluginExecutions>
                                <pluginExecution>
                                    <pluginExecutionFilter>
                                        <groupId>org.apache.maven.plugins</groupId>
                                        <artifactId>maven-shade-plugin</artifactId>
                                        <versionRange>[3.1.1,)</versionRange>
                                        <goals>
                                            <goal>shade</goal>
                                        </goals>
                                    </pluginExecutionFilter>
                                    <action>
                                        <ignore/>
                                    </action>
                                </pluginExecution>
                                <pluginExecution>
                                    <pluginExecutionFilter>
                                        <groupId>org.apache.maven.plugins</groupId>
                                        <artifactId>maven-compiler-plugin</artifactId>
                                        <versionRange>[3.1,)</versionRange>
                                        <goals>
                                            <goal>testCompile</goal>
                                            <goal>compile</goal>
                                        </goals>
                                    </pluginExecutionFilter>
                                    <action>
                                        <ignore/>
                                    </action>
                                </pluginExecution>
                            </pluginExecutions>
                        </lifecycleMappingMetadata>
                    </configuration>
                </plugin>
            </plugins>
        </pluginManagement>
    </build>
</project>

2.数据源

在resources文件夹下新建hello.txt文件，写入：

hello world
hello flink
hello spark
When we have shuffled off this mortal coil
When we have shuffled off this mortal coil
ack

3. 批处理代码

package mytest;

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;

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

        // 2.从文件中读取数据
        DataSet<String> inputDataSet = env.readTextFile("src/main/resources/hello.txt");

        // 3.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);    // 将第二个位置上的数据求和
        resultSet.print();
    }

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

4. 流处理代码

package mytest;

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

public class StreamWordCount {
    public static void main(String[] args) throws Exception {
        // 创建流处理执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(4); //单机模拟分布式的4台机器

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

        // 基于数据流进行转换计算
        DataStream<Tuple2<String, Integer>> resultStream =
                inputDataStream.flatMap(new WordCount.MyFlatMapper())
                        .keyBy(tuple -> tuple.f0)
                        .sum(1);
        // 打印
        resultStream.print();
        // 执行任务
        env.execute();
    }
}