flink 1.11.2 学习笔记(1)-wordCount

一、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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.cnblogs.yjmyzz</groupId>
    <artifactId>spring-boot-demo</artifactId>
    <version>0.0.1-SNAPSHOT</version>

    <properties>
        <java.version>1.8</java.version>
        <flink.version>1.11.2</flink.version>
    </properties>

    <dependencies>

        <!--lombok可选-->
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.12</version>
        </dependency>

        <!-- spring应用最小依赖-可选 -->
        <dependency>
            <groupId>org.springframework</groupId>
            <artifactId>spring-context</artifactId>
            <version>5.2.4.RELEASE</version>
        </dependency>

        <!-- flink -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-core</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-test-utils-junit</artifactId>
            <version>${flink.version}</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>

            <!-- Scala Compiler -->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>4.4.0</version>
                <executions>
                    <!-- Run scala compiler in the process-resources phase, so that dependencies on
                        scala classes can be resolved later in the (Java) compile phase -->
                    <execution>
                        <id>scala-compile-first</id>
                        <phase>process-resources</phase>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <jvmArgs>
                        <jvmArg>-Xms128m</jvmArg>
                        <jvmArg>-Xmx512m</jvmArg>
                    </jvmArgs>
                </configuration>
            </plugin>

        </plugins>
    </build>

</project>

二、WordCount(批处理版本)

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;

/**
 * WordCount批处理版本
 */
public class BatchWordCount {

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

        // 1 设置环境
        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // 2. 定义数据
        String wordFilePath = "/Users/jimmy/Downloads/word.txt";
        DataSet<String> text = env.readTextFile(wordFilePath);

        // 3. 处理逻辑
        DataSet<Tuple2<String, Integer>> counts =

                text.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
                    @Override
                    public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
                        //将每行按word拆分
                        String[] tokens = value.toLowerCase().split("\W+");

                        //收集(类似:map-reduce思路)
                        for (String token : tokens) {
                            if (token.length() > 0) {
                                out.collect(new Tuple2<>(token, 1));
                            }
                        }
                    }
                })
                        //按Tuple2里的第0项，即：word分组
                        .groupBy(0)
                        //然后对Tuple2里的第1项求合
                        .sum(1);

        // 4. 打印结果
        counts.print();

    }
}

注：数据文件/Users/jimmy/Downloads/word.txt的位置，大家可根据实际情况调整，该文件的内容类似：

hello java
hello flink

　　

三、WordCount(流式处理版本)

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

public class StreamWordCount {

    public static void main(String[] args) throws Exception {
        // 1 设置环境
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 2. 定义数据
        DataStream<String> text = env.socketTextStream("127.0.0.1", 9999);

        // 3. 处理逻辑
        DataStream<Tuple2<String, Integer>> counts =

                text.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
                    @Override
                    public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
                        //将每行按word拆分
                        String[] tokens = value.toLowerCase().split("\b+");

                        //收集(类似:map-reduce思路)
                        for (String token : tokens) {
                            if (token.trim().length() > 0) {
                                out.collect(new Tuple2<>(token.trim(), 1));
                            }
                        }
                    }
                })
                        //按Tuple2里的第0项，即：word分组
                        .keyBy(value -> value.f0)
                        //然后对Tuple2里的第1项求合
                        .sum(1);

        // 4. 打印结果
        counts.print();

        // execute program
        env.execute("Streaming WordCount");

    }
}

注：运行前，先在终端命令行输入nc -l 9999，开启一个tcp server作为流式处理的数据源，然后再运行上面的代码，然后命令行输入一些文本，即可看到输出