java调用spark+hdfs计算的一个小demo

最近在入门spark+hadoop，伪分布式安装，部署推荐这几个地址，不错。这边顺手记录一下自己用到的两个小程序。

推荐教程

http://www.powerxing.com/install-hadoop/
http://blog.csdn.net/yeruby/article/details/41042713
http://blog.csdn.net/tongxinzhazha/article/details/54346311

maven配置

<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>4.0.0modelVersion>
    <groupId>com.landigroupId>
    <artifactId>testsparkartifactId>
    <version>0.0.1-SNAPSHOTversion>
    <name>testsparkname>
    <description>testsparkdescription>
    <properties>
        <jdk.version>1.8jdk.version>
        <spark.version>2.1.0spark.version>
        <hadoop.version>2.6.5hadoop.version>
    properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-core_2.10artifactId>
            <version>${spark.version}version>
        dependency>
        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-clientartifactId>
            <version>${hadoop.version}version>
        dependency>

        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-commonartifactId>
            <version>${hadoop.version}version>
        dependency>

        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-hdfsartifactId>
            <version>${hadoop.version}version>
        dependency>
    dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-compiler-pluginartifactId>
                <version>3.1version>
                <configuration>
                    <source>${jdk.version}source>
                    <target>${jdk.version}target>
                configuration>
            plugin>
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-assembly-pluginartifactId>
                <version>2.4version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependenciesdescriptorRef>
                    descriptorRefs>
                    <archive>
                        <manifest>
                          <addClasspath>trueaddClasspath>
                          <mainClass>com.landi.testspark.TestSparkmainClass>
                        manifest>
                      archive>
                configuration>
            plugin>
        plugins>
    build>

project>

spark统计单词数demo

package com.landi.testspark;

import java.util.Arrays;

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;

import scala.Tuple2;


public class TestSpark {

    public static void main(String[] args) {
        //设置spark master节点地址，app名以及部署方式
         SparkConf conf = new SparkConf()
         .setMaster(args[1])
         .setAppName(args[3]);
         JavaSparkContext sc = new JavaSparkContext(conf);
         //连接hdfs地址，读取输入内容，并分割处理
        JavaRDD textFile = sc.textFile("hdfs://localhost:9070/user/root/input/*").flatMap(s -> Arrays.asList(s.split("\\s")).iterator());

JavaPairRDD result = textFile
                .filter((String s) -> {
                        Boolean flag = false;
                        if(s.indexOf("")!=-1){
                            flag = true;
                        }else if(s.indexOf("")!=-1){
                            flag = true;
                        }else if(s.indexOf("")!=-1){
                            flag = true;
                        }
                        return flag;})
                .mapToPair(word -> new Tuple2<>(word, 1))
                .reduceByKey((a, b) -> a + b);              
        result.saveAsTextFile("hdfs://localhost:9070/user/root/output2");
//  
    }

}

打包，上传到服务器。
执行前清空一下hdfs

执行

bin/spark-submit testspark-0.0.1-SNAPSHOT-jar-with-dependencies.jar 
--master spark://localhost:7077 
--name reduce 
--num-executors 10

读取hdfs并打印

package com.landi.testspark;

import java.io.IOException;
import java.io.InputStream;
import java.net.URI;
import java.net.URISyntaxException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class LoadFromHdfs {

    public static void main(String[] argvs) {
        String uri = "hdfs://localhost:9070/user/root/output2/";
        Configuration conf = new Configuration();
        //出现无法识别hdsf的问题可以加上以下两句
        conf.set("fs.hdfs.impl", "org.apache.hadoop.hdfs.DistributedFileSystem");
        conf.set("fs.file.impl", "org.apache.hadoop.fs.LocalFileSystem");
        try {
            FileSystem fs = FileSystem.get(new URI(uri), conf);
            Path path = new Path(uri);
            FileStatus status[] = fs.listStatus(path);
            for (int i = 0; i < status.length; i++) {
                String pathname =status[i].getPath().toString();
                System.out.println(pathname);
                System.out.println("==========");
                FileStatus tmp = status[i];
                if(tmp.isFile()&&tmp.getLen()>0){//判断文件大小
                    InputStream  in = fs.open(tmp.getPath());
                    StringBuffer sb = new StringBuffer("");
                    byte[] b = new byte[1];
                    while (in.read(b) != -1) {
                        // 字符串拼接
                        sb.append(new String(b));
                    }
                    System.out.println(sb.toString());
                    System.out.println("==========");
                    in.close();
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        } catch (URISyntaxException e) {
            e.printStackTrace();
        }
    }

}

打包上传服务器，执行java -jar LoadFromHdfs 。