1、创建一个maven工程
2、POM文件
<?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>com.sogou</groupId>
<artifactId>teemo-dc-etl</artifactId>
<version>1.0.0</version>
<packaging>jar</packaging>
<name>teemo-dc-etl</name>
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<mahout.version>0.5</mahout.version>
<mahout.groupid>org.apache.mahout</mahout.groupid>
<spring.version>3.0.6.RELEASE</spring.version>
</properties>
<repositories>
<repository>
<id>maven-ali</id>
<url>http://maven.twttr.com/</url>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>true</enabled>
<updatePolicy>always</updatePolicy>
<checksumPolicy>fail</checksumPolicy>
</snapshots>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>3.8.1</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.5.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.5.1</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.5.0</version>
</dependency>
<dependency>
<groupId>com.hadoop.gplcompression</groupId>
<artifactId>hadoop-lzo</artifactId>
<version>0.4.19</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-yarn-common</artifactId>
<version>2.5.2</version>
</dependency>
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.4</version>
</dependency>
</dependencies>
<build>
<plugins>
<!--
bind the maven-assembly-plugin to the package phase
this will create a jar file without the storm dependencies
suitable for deployment to a cluster.
-->
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<archive>
<manifest>
<mainClass></mainClass>
</manifest>
</archive>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase> <!-- packaging phase -->
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.6</source>
<target>1.6</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.14.1</version>
<configuration>
<argLine>-Xmx2048m</argLine>
</configuration>
</plugin>
</plugins>
</build>
</project>
这里有个lzo包，需要增加twiter的资源库
3、mapreduce文件写法
package com.sogou.teemo.test;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.StringTokenizer;
public class WordCount {
/* Mapper */
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
@Override
public void map(Object key, Text value, Context context) throws IOException, InterruptedException{
StringTokenizer itr = new StringTokenizer(value.toString());
while(itr.hasMoreTokens()){
word.set(itr.nextToken());
context.write(word, one);
}
}
}
/* Reducer */
public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable>{
private IntWritable result = new IntWritable();
@Override
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException,InterruptedException{
int sum = 0;
for(IntWritable val : values){
sum += val.get();
}
result.set(sum);
context.write(key,result);
}
}
/* 启动 MapReduce Job */
public static void main(String[] args) throws Exception{
System.setProperty("hadoop.home.dir","D:/hadoop-2.6.5" );
Configuration conf = new Configuration();
/*if(args.length != 2){
System.err.println("Usage: wordcount <int> <out>");
System.exit(2);
}*/
String arg1 = "input";
String arg2 = "output";
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job,new Path(arg1));
FileOutputFormat.setOutputPath(job,new Path(arg2));
System.exit(job.waitForCompletion(true)?0:1);
}
}
内容来源于网络如有侵权请私信删除
- 还没有人评论，欢迎说说您的想法！
客服
