第十章 Flink专题之代码开发细节

• 业务需求：统计下列单词并打印输出

hadoop spark flink
hadoop spark flink
hadoop spark flink
hadoop spark flink
hadoop spark flink
hadoop spark flink

1、代码实现

package flink.demo;

import org.apache.flink.api.common.functions.FlatMapFunction;
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;
import org.apache.flink.util.Collector;

public class WordCount0 {
    public static void main(String[] args) throws Exception {
        // 1、创建执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        // 2、读取 文件数据 数据
        DataStreamSource<String> inputDataStream = env.readTextFile("H:\\flink_demo\\flink_test\\src\\main\\resources\\wordcount.txt");

        // 3、计算
        SingleOutputStreamOperator<Tuple2<String, Integer>> resultDataStream = inputDataStream.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String input, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] words = input.split(" ");
                for (String word : words) {
                    collector.collect(new Tuple2<>(word, 1));
                }
            }
        }).keyBy(0)
                .sum(1);

        // 4、输出
        resultDataStream.print();

        // 5、启动 env
        env.execute();
    }
}

• 运行结果

2、优化点一 - 使用面向对象

• 优化点：把数据看成对象，遇到字段较多的数据操作比较方便

2.1、自定义对象数据结构

public class WordAndCount {

    private String word;
    private int count;

    public WordAndCount() {
    }

    public WordAndCount(String word, int count) {
        this.word = word;
        this.count = count;
    }

    public String getWord() {
        return word;
    }

    public void setWord(String word) {
        this.word = word;
    }

    public int getCount() {
        return count;
    }

    public void setCount(int count) {
        this.count = count;
    }

    @Override
    public String toString() {
        return "WordAndCount{" +
                "word='" + word + '\'' +
                ", count=" + count +
                '}';
    }
}

2.2、main方法实现业务逻辑

public class WordCount {
    public static void main(String[] args) throws Exception {
        // 1、创建执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        // 2、读取数据
        DataStreamSource<String> inputDataStream = env.readTextFile("H:\\flink_demo\\flink_test\\src\\main\\resources\\wordcount.txt");

        // 3、扁平化 + 分组 + sum
        SingleOutputStreamOperator<WordAndCount> resultData = inputDataStream.flatMap(new FlatMapFunction<String, WordAndCount>() {
            @Override
            public void flatMap(String line, Collector<WordAndCount> out) throws Exception {
                String[] fields = line.split(" ");
                for (String word : fields) {
                    out.collect(new WordAndCount(word, 1));
                }
            }
        }).keyBy("word").sum("count");

        resultData.print();

        // 4、启动 env
        env.execute();
    }
}

• 运行结果

3、优化点二 - 抽取业务功能

• 优化：业务逻辑核心算子单独实现，代码便于阅读

3.1、自定义对象的数据结构

public class WordAndCount {

    private String word;
    private int count;

    public WordAndCount() {
    }

    public WordAndCount(String word, int count) {
        this.word = word;
        this.count = count;
    }

    public String getWord() {
        return word;
    }

    public void setWord(String word) {
        this.word = word;
    }

    public int getCount() {
        return count;
    }

    public void setCount(int count) {
        this.count = count;
    }

    @Override
    public String toString() {
        return "WordAndCount{" +
                "word='" + word + '\'' +
                ", count=" + count +
                '}';
    }
}

3.2、抽取业务逻辑

public static class SplitLine implements FlatMapFunction<String,WordAndCount>{

    @Override
    public void flatMap(String line, Collector<WordAndCount> out) throws Exception {
        String[] fields = line.split(" ");
        for (String word : fields) {
            out.collect(new WordAndCount(word, 1));
        }
    }
}

3.3、main方法实现

public static void main(String[] args) throws Exception {
    // 1、创建执行环境
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.setParallelism(1);
    // 2、读取数据
    DataStreamSource<String> inputDataStream = env.readTextFile("H:\\flink_demo\\flink_test\\src\\main\\resources\\wordcount.txt");

    // 3、扁平化 + 分组 + sum
    SingleOutputStreamOperator<WordAndCount> resultData = inputDataStream.flatMap(new SplitLine()).keyBy("word").sum("count");

    // 4、打印输出
    resultData.print();

    // 5、启动 env
    env.execute();
}

• 运行结果

4、优化点三 - 数据源传参

• 优化点：flink建议如果程序中需要传入参数，使用它提供的ParameterTool。

4.1、自定义对象的数据结构

public class WordAndCount {

    private String word;
    private int count;

    public WordAndCount() {
    }

    public WordAndCount(String word, int count) {
        this.word = word;
        this.count = count;
    }

    public String getWord() {
        return word;
    }

    public void setWord(String word) {
        this.word = word;
    }

    public int getCount() {
        return count;
    }

    public void setCount(int count) {
        this.count = count;
    }

    @Override
    public String toString() {
        return "WordAndCount{" +
                "word='" + word + '\'' +
                ", count=" + count +
                '}';
    }
}

4.2、抽取业务逻辑

public static class SplitLine implements FlatMapFunction<String,WordAndCount>{

    @Override
    public void flatMap(String line, Collector<WordAndCount> out) throws Exception {
        String[] fields = line.split(" ");
        for (String word : fields) {
            out.collect(new WordAndCount(word, 1));
        }
    }
}

4.3、main方法实现自定义参数传递

public static void main(String[] args) throws Exception {
    // 1、创建执行环境
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.setParallelism(1);
    // 2、读取数据
    //flink提供的工具类，获取传递的参数
    ParameterTool parameterTool = ParameterTool.fromArgs(args);
    String path = parameterTool.get("path");
    DataStreamSource<String> dataStream = env.readTextFile(path);

    // 3、扁平化 + 分组 + sum
    SingleOutputStreamOperator<WordAndCount> resultData = dataStream.flatMap(new SplitLine()).keyBy("word").sum("count");

    // 4、打印输出
    resultData.print();

    // 5、启动 env
    env.execute();
}

• 参数传递

• 运行结果

5、生产环境最佳代码实践

5.1、pom文件配置

<project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xmlns="http://maven.apache.org/POM/4.0.0"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0modelVersion>

    <groupId>org.examplegroupId>
    <artifactId>flinkdemoartifactId>
    <version>1.0-SNAPSHOTversion>

    <properties>
        <java.version>1.8java.version>
        <scala.version>2.11scala.version>
        <flink.version>1.9.3flink.version>
        <parquet.version>1.10.0parquet.version>
        <hadoop.version>2.7.3hadoop.version>
        <fastjson.version>1.2.72fastjson.version>
        <redis.version>2.9.0redis.version>
        <mysql.version>5.1.35mysql.version>
        <log4j.version>1.2.17log4j.version>
        <slf4j.version>1.7.7slf4j.version>
        <maven.compiler.source>1.8maven.compiler.source>
        <maven.compiler.target>1.8maven.compiler.target>
        <maven.compiler.compilerVersion>1.8maven.compiler.compilerVersion>
        <project.build.sourceEncoding>UTF-8project.build.sourceEncoding>
        <project.build.scope>compileproject.build.scope>
        
        <mainClass>com.hainiu.DrivermainClass>
    properties>

    <dependencies>
        <dependency>
            <groupId>org.slf4jgroupId>
            <artifactId>slf4j-log4j12artifactId>
            <version>${slf4j.version}version>
            <scope>${project.build.scope}scope>
        dependency>

        <dependency>
            <groupId>log4jgroupId>
            <artifactId>log4jartifactId>
            <version>${log4j.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-clientartifactId>
            <version>${hadoop.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-hadoop-compatibility_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-javaartifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-streaming-java_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-scala_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-streaming-scala_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-runtime-web_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-statebackend-rocksdb_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-hbase_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-connector-elasticsearch5_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-connector-kafka-0.10_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-connector-filesystem_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>mysqlgroupId>
            <artifactId>mysql-connector-javaartifactId>
            <version>${mysql.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>redis.clientsgroupId>
            <artifactId>jedisartifactId>
            <version>${redis.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>org.apache.parquetgroupId>
            <artifactId>parquet-avroartifactId>
            <version>${parquet.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        <dependency>
            <groupId>org.apache.parquetgroupId>
            <artifactId>parquet-hadoopartifactId>
            <version>${parquet.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        <dependency>
            <groupId>org.apache.flinkgroupId>
            <artifactId>flink-parquet_${scala.version}artifactId>
            <version>${flink.version}version>
            <scope>${project.build.scope}scope>
        dependency>
        
        <dependency>
            <groupId>com.alibabagroupId>
            <artifactId>fastjsonartifactId>
            <version>${fastjson.version}version>
            <scope>${project.build.scope}scope>
        dependency>
    dependencies>

    <build>
        <resources>
            <resource>
                <directory>src/main/resourcesdirectory>
            resource>
        resources>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-assembly-pluginartifactId>
                <configuration>
                    <descriptors>
                        <descriptor>src/assembly/assembly.xmldescriptor>
                    descriptors>
                    <archive>
                        <manifest>
                            <mainClass>${mainClass}mainClass>
                        manifest>
                    archive>
                configuration>
                <executions>
                    <execution>
                        <id>make-assemblyid>
                        <phase>packagephase>
                        <goals>
                            <goal>singlegoal>
                        goals>
                    execution>
                executions>
            plugin>
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-surefire-pluginartifactId>
                <version>2.12version>
                <configuration>
                    <skip>trueskip>
                    <forkMode>onceforkMode>
                    <excludes>
                        <exclude>**/**exclude>
                    excludes>
                configuration>
            plugin>
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-compiler-pluginartifactId>
                <version>3.1version>
                <configuration>
                    <source>${java.version}source>
                    <target>${java.version}target>
                    <encoding>${project.build.sourceEncoding}encoding>
                configuration>
            plugin>
        plugins>
    build>

project>

5.2、自定义对象的数据结构

package flink.demo;

public class WordAndCount {

    private String word;
    private int count;

    public WordAndCount() {
    }

    public WordAndCount(String word, int count) {
        this.word = word;
        this.count = count;
    }

    public String getWord() {
        return word;
    }

    public void setWord(String word) {
        this.word = word;
    }

    public int getCount() {
        return count;
    }

    public void setCount(int count) {
        this.count = count;
    }

    @Override
    public String toString() {
        return "WordAndCount{" +
                "word='" + word + '\'' +
                ", count=" + count +
                '}';
    }
}

5.3、入口类实现

package flink.demo;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class WordCount {
    public static void main(String[] args) throws Exception {
        // 1、创建执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        // 2、读取数据
        //flink提供的工具类，获取传递的参数
        ParameterTool parameterTool = ParameterTool.fromArgs(args);
        String path = parameterTool.get("path");
        DataStreamSource<String> dataStream = env.readTextFile(path);

        // 3、扁平化 + 分组 + sum
        SingleOutputStreamOperator<WordAndCount> resultData = dataStream.flatMap(new SplitLine()).keyBy("word").sum("count");

        // 4、打印输出
        resultData.print();

        // 5、启动 env
        env.execute();
    }

    // 业务逻辑抽离：核心算子单独实现
    public static class SplitLine implements FlatMapFunction<String,WordAndCount>{

        @Override
        public void flatMap(String line, Collector<WordAndCount> out) throws Exception {
            String[] fields = line.split(" ");
            for (String word : fields) {
                out.collect(new WordAndCount(word, 1));
            }
        }
    }
}

5.4、代码目录结构