SparkStreaming实战案例

1、单词计数

pom.xml配置：

<properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.1</spark.version>
        <hadoop.version>2.7.5</hadoop.version>
        <encoding>UTF-8</encoding>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${
   scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${
   spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
            <version>${
   spark.version}</version>
        </dependency>
    </dependencies>

    <build>
        <pluginManagement>
            <plugins>
                <plugin>
                    <groupId>net.alchim31.maven</groupId>
                    <artifactId>scala-maven-plugin</artifactId>
                    <version>3.2.2</version>
                </plugin>
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-compiler-plugin</artifactId>
                    <version>3.5.1</version>
                </plugin>
            </plugins>
        </pluginManagement>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <phase>process-resources</phase>
                        <goals>
                            <goal>add-source</goal>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <phase>process-test-resources</phase>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <executions>
                    <execution>
                        <phase>compile</phase>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

1.1 scala版本

object WordCount {
   
  def main(args: Array[String]): Unit = {
   
    //步骤一：初始化程序入口
    val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
    val ssc = new StreamingContext(conf, Seconds(1))
    //步骤二：获取数据流
    val lines = ssc.socketTextStream("localhost", 9999)
    //步骤三：数据处理
    val words = lines.flatMap(_.split(" "))
    val pairs = words.map(word => (word, 1))
    val wordCounts = pairs.reduceByKey(_ + _)
   //步骤四： 数据输出
    wordCounts.print()
    //步骤五：启动任务
    ssc.start()
    ssc.awaitTermination()
    ssc.stop()

  }

}

1.2 java版本

/**
 * 单词统计
 */
public class WordCount {
   
    public static void main(String[] args)  throws  Exception{
   
        //步骤一：初始化程序入口
        SparkConf conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount");
        JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(1));
        //步骤二：获取数据源
        JavaReceiverInputDStream<String> lines = jssc.socketTextStream("10.148.15.10", 9999);
        //步骤三：数据处理
        JavaDStream<String> words = lines.flatMap(x -> Arrays.asList(x.split(" ")).iterator());
        JavaPairDStream<String, Integer> pairs = words.mapToPair(s -> new Tuple2<>(s, 1));
        JavaPairDStream<String, Integer> wordCounts = pairs.reduceByKey((i1, i2) -> i1 + i2);
        //步骤四：数据输出
        wordCounts.print();
        //步骤五：启动程序
        jssc.start();
        jssc.awaitTermination();
        jssc.stop();

    }
}

1.3 HDFS 数据源

/**
  * HDFS 数据源
  */
object WordCountForHDFSSource {
   
  def main(args: Array[String]): Unit = {
   
    //步骤一：初始化程序入口
    val conf = new SparkConf().setMaster("local[2]").setAppName("NetworkWordCount")
    val ssc = new StreamingContext(conf, Seconds(1))
    //步骤二：获取数据流
    val lines = ssc.textFileStream("/tmp");
    //步骤三：数据处理
    val words = lines.flatMap(_.split(" "))
    val pairs = words.map(word => (word, 1))
    val wordCounts = pairs.reduceByKey(_ + _)
    //步骤四： 数据输出
    wordCounts.print()
    //步骤五：启动任务
    ssc.start()
    ssc.awaitTermination()
    ssc.stop()

  }

}

1.4 自定义数据源

/**
  * 自定义一个Receiver，这个Receiver从socket中接收数据
  * 接收过来的数据解析成以 \n 分隔开的text
    使用方式：nc -lk 9999
  */
object CustomReceiver {
   
  def main(args