最近在入門spark+hadoop，偽分散式安裝，部署推薦這幾個地址，不錯。這邊順手記錄一下自己用到的兩個小程式。

推薦教程

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>4.0.0</modelVersion
 
>
    <groupId>com.landi</groupId>
    <artifactId>testspark</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>testspark</name>
    <description>testspark</description>
    <properties>
        <jdk.version>1.8</jdk.version
 
>
        <spark.version>2.1.0</spark.version>
        <hadoop.version>2.6.5</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId
 
>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.1</version>
                <configuration>
                    <source>${jdk.version}</source>
                    <target>${jdk.version}</target>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>2.4</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                          <addClasspath>true</addClasspath>
                          <mainClass>com.landi.testspark.TestSpark</mainClass>
                        </manifest>
                      </archive>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

spark統計單詞數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) {
        //設定spark master節點地址，app名以及部署方式
         SparkConf conf = new SparkConf()
         .setMaster(args[1])
         .setAppName(args[3]);
         JavaSparkContext sc = new JavaSparkContext(conf);
         //連線hdfs地址，讀取輸入內容，並分割處理
        JavaRDD<String> textFile = sc.textFile("hdfs://localhost:9070/user/root/input/*").flatMap(s -> Arrays.asList(s.split("\\s")).iterator());

JavaPairRDD<String, Integer> result = textFile
                .filter((String s) -> {
                        Boolean flag = false;
                        if(s.indexOf("<name>")!=-1){
                            flag = true;
                        }else if(s.indexOf("<property>")!=-1){
                            flag = true;
                        }else if(s.indexOf("<IF>")!=-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，上傳到伺服器。
執行前清空一下hdfs

執行

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

讀取hdfs並列印

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();
        //出現無法識別hdsf的問題可以加上以下兩句
        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){//判斷檔案大小
                    InputStream  in = fs.open(tmp.getPath());
                    StringBuffer sb = new StringBuffer("");
                    byte[] b = new byte[1];
                    while (in.read(b) != -1) {
                        // 字串拼接
                        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();
        }
    }

}

打包上傳伺服器，執行java -jar LoadFromHdfs 。