【Spark】使用java語言開發spark程序

目錄

• 步驟
• 一、創建maven工程，導入jar包
• 二、開發代碼

---

步驟

一、創建maven工程，導入jar包

<properties>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.0</spark.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.5</version>
        </dependency>
    </dependencies>
    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                    <!-- <verbal>true</verbal>-->
                </configuration>
            </plugin>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.0</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.1</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>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

二、開發代碼

/** * java代碼實現spark的WordCount */
public class WordCountJava {
    public static void main(String[] args) {
        //todo:1、構建sparkconf,設置配置信息
        SparkConf sparkConf = new SparkConf().setAppName("WordCount_Java").setMaster("local[2]");
        //todo:2、構建java版的sparkContext
        JavaSparkContext sc = new JavaSparkContext(sparkConf);
        //todo:3、讀取數據文件
        JavaRDD<String> dataRDD = sc.textFile("d:/data/words1.txt");
        //todo:4、對每一行單詞進行切分
        JavaRDD<String> wordsRDD = dataRDD.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String s) throws Exception {
                String[] words = s.split(" ");
                return Arrays.asList(words).iterator();
            }
        });
        //todo:5、給每個單詞計為 1
        // Spark為包含鍵值對類型的RDD提供了一些專有的操作。這些RDD被稱為PairRDD。
        // mapToPair函數會對一個RDD中的每個元素調用f函數，其中原來RDD中的每一個元素都是T類型的，
        // 調用f函數后會進行一定的操作把每個元素都轉換成一個<K2,V2>類型的對象,其中Tuple2為多元組
        JavaPairRDD<String, Integer> wordAndOnePairRDD = wordsRDD.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String word) throws Exception {
                return new Tuple2<String,Integer>(word, 1);
            }
        });

        //todo:6、相同單詞出現的次數累加
        JavaPairRDD<String, Integer> resultJavaPairRDD = wordAndOnePairRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        //todo:7、反轉順序
        JavaPairRDD<Integer, String> reverseJavaPairRDD = resultJavaPairRDD.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple) throws Exception {
                return new Tuple2<Integer, String>(tuple._2, tuple._1);
            }
        });

        //todo:8、把每個單詞出現的次數作為key，進行排序，並且在通過mapToPair進行反轉順序后輸出
        JavaPairRDD<String, Integer> sortJavaPairRDD = reverseJavaPairRDD.sortByKey(false).mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tuple) throws Exception {

                return  new Tuple2<String, Integer>(tuple._2,tuple._1);
                //或者使用tuple.swap() 實現位置互換，生成新的tuple;
            }
        });
        //todo:執行輸出
        System.out.println(sortJavaPairRDD.collect());
        //todo:關閉sparkcontext
        sc.stop();
    }
}