spark hello world

idea 中建立maven工程依赖如下

<?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>
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <jdk.version>1.8</jdk.version>
    </properties>
    <groupId>com.asa.lab.spark</groupId>
    <artifactId>spark-admin</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.3.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>2.3.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-source-plugin</artifactId>
                <version>2.1.2</version>
                <executions>
                    <execution>
                        <id>attach-sources</id>
                        <phase>verify</phase>
                        <goals>
                            <goal>jar-no-fork</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.3</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

hello world

public class RDDTest {

    public static void main(String[] args) {
        SparkConf conf = new SparkConf();

        conf.setAppName("WordCounter")//
                .setMaster("local");

        String fileName = "/log4j.properties";

        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaRDD<String> lines = sc.textFile(fileName, 1);

        JavaRDD<String> words = lines
                .flatMap(new FlatMapFunction<String, String>() {
                    private static final long serialVersionUID = 1L;

                    // 以前的版本好像是Iterable而不是Iterator
                    @Override
                    public Iterator<String> call(String line) throws Exception {
                        return Arrays.asList(line.split(" ")).iterator();
                    }
                });

        JavaPairRDD<String, Integer> pairs = words
                .mapToPair(new PairFunction<String, String, Integer>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Tuple2<String, Integer> call(String word)
                            throws Exception {
                        return new Tuple2<String, Integer>(word, 1);
                    }
                });

        JavaPairRDD<String, Integer> result = pairs.reduceByKey(
                new Function2<Integer, Integer, Integer>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Integer call(Integer e, Integer acc)
                            throws Exception {
                        return e + acc;
                    }
                }, 1);

        result.map(
                new Function<Tuple2<String, Integer>, Tuple2<String, Integer>>() {

                    private static final long serialVersionUID = 1L;

                    @Override
                    public Tuple2<String, Integer> call(
                            Tuple2<String, Integer> v1) throws Exception {
                        return new Tuple2<>(v1._1, v1._2);
                    }
                })//
                .sortBy(new Function<Tuple2<String, Integer>, Integer>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public Integer call(Tuple2<String, Integer> v1)
                            throws Exception {
                        return v1._2;
                    }
                }, false, 1)//
                .foreach(new VoidFunction<Tuple2<String, Integer>>() {
                    private static final long serialVersionUID = 1L;

                    @Override
                    public void call(Tuple2<String, Integer> e)
                            throws Exception {
                        System.out.println("【" + e._1 + "】出现了" + e._2 + "次");
                    }
                });
        sc.close();
    }
}
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值