public class FlinkStreamingTopDomain {
    public static void main(String[] args) throws Exception{
        // 獲取流處理運行環(huán)境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 獲取kafkaConsumer
        FlinkKafkaConsumer<String> kafkaConsumer = FlinkUtil.getKafkaConsumer("ahl_test1", "console-consumer-72096");
        // 從當前消費組下標開始讀取
        kafkaConsumer.setStartFromEarliest();
        DataStreamSource text = env.addSource(kafkaConsumer);

        // 算子
        DataStream<Tuple2<String,String>> windowCount = text.flatMap(new FlatMap())
                .keyBy(0).reduce(new Reduce());
        //把數(shù)據(jù)打印到控制臺
        windowCount.print()
                .setParallelism(16);//使用16個并行度
        //注意：因為flink是懶加載的，所以必須調用execute方法，上面的代碼才會執(zhí)行
        env.execute("streaming topDomain calculate");
    }
}

FlatMap
DataStream → DataStream
Takes one element and produces zero, one, or more elements. A flatmap function that splits sentences to words:
dataStream.flatMap(new FlatMapFunction<String, String>() {
    @Override
    public void flatMap(String value, Collector<String> out)
        throws Exception {
        for(String word: value.split(" ")){
            out.collect(word);
        }
    }
});

    // FlatMap分割域名，并輸出二元組<頂級域名，域名>
    public static class FlatMap implements FlatMapFunction<String, Tuple2<String,String>> {
        @Override
        public void flatMap(String s, Collector<Tuple2<String, String>> out) throws Exception {
            String[] values = s.split("\\^");   // 按字符^分割
            if(values.length - 1 < 2) {
                return;
            }
            String domain = values[2];
            out.collect(new Tuple2<String,String>(ToolUtil.getTopDomain(domain),domain));
        }
    }

KeyBy
DataStream → KeyedStream
    
Logically partitions a stream into disjoint partitions. All records with the same key are assigned to the same partition. Internally, keyBy() is implemented with hash partitioning. There are different ways to specify keys.

This transformation returns a KeyedStream, which is, among other things, required to use keyed state.

dataStream.keyBy(value -> value.getSomeKey()) // Key by field "someKey"
dataStream.keyBy(value -> value.f0) // Key by the first element of a Tuple

Attention：A type cannot be a key if:
    1.it is a POJO type but does not override the hashCode() method and relies on the Object.hashCode() implementation.
    2.it is an array of any type.   

Reduce
KeyedStream → DataStream
A "rolling" reduce on a keyed data stream. Combines the current element with the last reduced value and emits the new value.
A reduce function that creates a stream of partial sums:
keyedStream.reduce(new ReduceFunction<Integer>() {
    @Override
    public Integer reduce(Integer value1, Integer value2)
    throws Exception {
        return value1 + value2;
    }
});

    // 拼接同一分區(qū)下的ip
    public static class Reduce implements ReduceFunction<Tuple2<String,String>>{
        @Override
        public Tuple2<String,String> reduce(Tuple2 t1, Tuple2 t2) throws Exception {
            String[] domains = t1.f1.toString().split("\\^");
            if(domains.length == 10){
                return t1;
            }
            t1.f1 = t1.f1.toString() + "^" + t2.f1.toString();
            System.out.println(t1.f1 );
            return t1;
        }
   }

//        int port;
//        try {
//            ParameterTool parameterTool = ParameterTool.fromArgs(args);
//            port = parameterTool.getInt("port");
//        } catch (Exception e){
//            System.out.println("沒有指定port參數(shù)，使用默認值1112");
//            port = 1112;
//        }

        // 連接socket獲取輸入數(shù)據(jù)
//        DataStreamSource<String> text = env.socketTextStream("192.168.3.221",port);

kafka-topics.sh --create --zookeeper IP1:2181 IP2:2181... --replication-factor 2 --partitions 16 --topic ahl_test

java -jar $jar包路徑  $topic $path

/kafka-console-producer.sh --broker-list slave3:9092 --topic ahl_test1

<plugins>
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<executions>
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<!--							<createDependencyReducedPom>false</createDependencyReducedPom>-->
							<artifactSet>
								<excludes>
									<exclude>com.google.code.findbugs:jsr305</exclude>
									<exclude>org.slf4j:*</exclude>
									<exclude>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>com.ncs.flink.streaming.FlinkStreamingTopDomain</mainClass>
								</transformer>
							</transformers>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>

/home/soft/flink-1.12.0//bin/flink run -c com.ncs.flink.streaming.FlinkStreamingDomainJob /home/ahl/flink/situation-mapred-flink-0.0.1-SNAPSHOT.jar