MapReduce打jar包上传hdfs运行

MapReduce打jar包上传hdfs运行

上传原数据文件到hdfs

hdfs dfs -mkdir /datas/
hdfs dfs -put data1.txt /datas/

pom.xml

<?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>

    <groupId>org.example</groupId>
    <artifactId>wdDemo</artifactId>
    <version>1.0-SNAPSHOT</version>


    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
    <dependencies>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-client</artifactId>
            <version>2.6.0-mr1-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-common</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-hdfs</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.Hadoop</groupId>
            <artifactId>Hadoop-mapreduce-client-core</artifactId>
            <version>2.6.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
        </dependency>
    </dependencies>
    <build>
        <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>
                </configuration>
            </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>
                            <minimizeJar>true</minimizeJar>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

        </plugins>
    </build>

</project>

MapReduce源码

map代码

package test;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class test1Map extends Mapper<LongWritable, Text, Text, NullWritable> {
    int index = 0;
    Text k = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行
        String line = value.toString();
        //剔除标题
        if (line.startsWith("酒店")) {
            return;
        }
        String[] data = line.split(",");
        String str = "";
        if (data.length < 7) {
            return;
        }
        for (int i = 0; i < data.length; i++) {
            str += data[i] + ",";
        }
        str = str.substring(0, str.length() - 1);
        k.set(str);
        context.write(k, NullWritable.get());
    }
}

Reduce代码

package test;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class test1Reduce extends Reducer<Text, NullWritable,Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

Driver代码

package test;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class test1Driver{
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
//        conf.set("hadoop.tmp.dir","D:\\file\\hdfs_temp");
        Job job = Job.getInstance(conf);
        job.setJarByClass(test1Driver.class);
        job.setMapperClass(test1Map.class);
        job.setReducerClass(test1Reduce.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        Path p = setPath(job);
        p.getFileSystem(conf).delete(p,true);
        Boolean result = job.waitForCompletion(true);
        System.out.println(result);
        System.exit(result?0:1);
    }
    private static Path setPath(Job job) throws IOException {
        //在本地运行的路径
//        Path inpath = new Path("D:\\file\\source\\data1.txt");
//        Path outpath = new Path("D:\\file\\output");
        //打jar包到HDFS上运行输出在HDFS上的配置，注意hdfs的ip地址和对应的端口号
        //hdfs getconf -confKey fs.default.name查看hdfs端口号
        Path inpath = new Path("hdfs://192.168.1.66:9000/datas");
        //MapReduce程序的输入如果是一个目录，则会计算目录下所有文件
        //如果指定某文件，则只计算这个文件。
        //这里就是输入一个目录，就会计算目录下所有文件，也就是上传的那个文件。
        Path outpath = new Path("hdfs://192.168.1.66:9000/datas_out");
        //输出的文件目录不能存在
        FileInputFormat.addInputPath(job,inpath);
        FileOutputFormat.setOutputPath(job,outpath);
        return outpath;
    }
}

打jar包

名字短的体积比较大，里面包括了运行所需要的所有jar包

名字长的体积小，里面只有核心程序。不包括运行所需要的jar包

所以，使用体积比较大的，复制，粘贴到桌面，改名为test.jar

把它先上传到服务器里，然后再上传到hdfs里

上传hdfs

hadoop dfs -put test.jar /

在hdfs上运行jar

hadoop jar test.jar test.test1Driver