Flink-有界流处理方法DataStream API

pom.xml

<?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.spoon</groupId>
    <artifactId>FlinkStream</artifactId>
    <version>1.0-SNAPSHOT</version>
    <properties>
        <flink.version>1.13.0</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>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.22</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.0</version>
        </dependency>
    </dependencies>

</project>

log4j.properties

# 级别，名称
log4j.rootLogger = error, stdout
#日志输出到控制台
log4j.appender.stdout = org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout = org.apache.log4j.PatternLayout
# 日志格式
log4j.appender.console.layout.ConversionPattern =%-4r [%t] %-5p %c %x - %m%n

words.txt

hello java
hello flink
hello world

package wc;
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 {
        //1.创建流式执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //2.读取文件
        DataStreamSource<String> lineDataStreamSource = env.readTextFile("input/words.txt");
        //3.转换计算
        SingleOutputStreamOperator<Tuple2<String, Long>> wordAndOneTuple = lineDataStreamSource.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));

        //4.分组
        KeyedStream<Tuple2<String, Long>, String> wordAndOneKeyedStream = wordAndOneTuple.keyBy(data -> data.f0);
        //5.求和
        SingleOutputStreamOperator<Tuple2<String, Long>> sum = wordAndOneKeyedStream.sum(1);
        //6.打印
        sum.print();
        //7.启动执行
        env.execute();

    }
}

运行结果

2> (java,1)
3> (hello,1)
7> (flink,1)
3> (hello,2)
3> (hello,3)
5> (world,1)

并不是按照顺序输出,因为程序用多线程模拟flink集群
2> (java,1) 2是并行子任务编号-代表本地的哪个线程来执行输出统计结果的任务对应flink占据的那个并行的资源，在flink里最小的资源单位叫做任务槽task slot