eclipse通过maven进行打包并且对hdfs上的文件进行wordcount

在eclipse中配置自己的maven仓库

1.安装maven(用于管理仓库,jar包的管理)

-1.解压maven安装包
-2.把maven添加到环境变量/etc/profile
-3.添加maven目录下的conf/setting.xml文件到~/.m2文件夹下

2.安装eclipse

-1.解压eclipse安装文件
-2.执行eclipse.inst文件
-3.按步骤操作

3.在eclipse中配置自己的maven仓库

1.window>>perfoemence>>maven>>installations(添加使用的maven目录,步骤1.1)
add>>选择1.1中的路径
2.window>>perfoemence>>maven>>User settings(选择本地仓库的配置文件,步骤1.3)
Uesr Settings>>选择1.3中的文件

4.新建maven的项目

-new>>maven project>>创建一个简单的项目>>next>>next>>Group Id:域名倒置>>Artfact Id:项目名>>finish
-修改pom.xml文件


junit
junit
3.8.1
test

org.apache.hadoop hadoop-hdfs 2.5.0 org.apache.hadoop hadoop-client 2.5.1 org.apache.hadoop hadoop-common 2.5.0

编写一个小程序进行Test

在src/main/java下新建hadoop_test类
package hadoop_test;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class ConfTest extends Configured implements Tool{

public int run(String[] arg0) throws Exception {
	// TODO Auto-generated method stub
	Configuration conf =getConf();
	return 0;
}
		
public static void main(String[] args) throws Exception {
	System.out.println("hello world!!!");
	int status = ToolRunner.run(new ConfTest(), args);
	System.exit(status);
}

}

打包,在终端进入该Java Project的pom.xml所在文件夹,执行mvn install clean,在target文件夹中可以找到一个jar包(hadoop_test-0.0.1-SNAPSHOT.jar),若是jarhadoop jar hadoop_test-0.0.1-SNAPSHOT.jar hadoop_test/ConfTest 指令执行输出hello world则该基本上成功了。同时也可测试下系统自带的wordcount类,具体方法是$ ./bin/$ hadoop jar $HADOOP_PREFIX/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.2.0.jar wordcount input output

最后写程序读取hdfs上的文件进行mapreduce并将结果传回hdfs

类:package hadoop_test;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool{
static class WordCountMapper
extends Mapper<LongWritable, Text, Text, IntWritable>{
// 统计使用变量
private final static IntWritable one=
new IntWritable(1);
// 单词变量
private Text word=new Text();

	/**
	 * key:当前读取行的偏移量
	 * value:当前读取的行
	 * context:map方法执行时上下文
	 */
	@Override
	protected void map(LongWritable key, Text value, Context context)
			throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		StringTokenizer words=
				new StringTokenizer(value.toString(), " ");
		
		while(words.hasMoreTokens()){
			word.set(words.nextToken());
			context.write(word, one);
		}
	}
}

static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
	private IntWritable counter = new IntWritable();
	/**
	 * key:待统计的word
	 * values:待统计word的所有统计标识
	 * context:reduce方法执行时的上下文
	 */
	@Override
	protected void reduce(Text key, 
			Iterable<IntWritable> values,
			Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		int count=0;
		for(IntWritable one:values){
			count+=one.get();
		}
		counter.set(count);
		context.write(key, counter);
	}
}

// @Override
public int run(String[] args) throws Exception {
//获得程序运行时的配置信息
Configuration conf=getConf();
String inputPath=conf.get("input");
String outputPath=conf.get("output");

	//构建新的作业
	Job job = Job.getInstance(conf, "Word Frequence Count");
	job.setJarByClass(WordCount.class);
	
	//给job设置mapper类及map方法输出的键值类型
	job.setMapperClass(WordCountMapper.class);
	job.setMapOutputKeyClass(Text.class);
	job.setMapOutputValueClass(IntWritable.class);
	
	//给job设置reducer类及reduce方法输出的键值类型
	job.setReducerClass(WordCountReducer.class);
	job.setOutputKeyClass(Text.class);
	job.setOutputValueClass(IntWritable.class);
	
	//设置数据的读取方式(文本文件)及结果的输出方式(文本文件)
	job.setInputFormatClass(TextInputFormat.class);
	job.setOutputFormatClass(TextOutputFormat.class);

	//设置输入和输出目录
	TextInputFormat.addInputPath(job, new Path(inputPath));
	TextOutputFormat.setOutputPath(job, new Path(outputPath));
	
	
	//将作业提交集群执行	
	return job.waitForCompletion(true)?0:1;
}


public static void main(String[] args) throws Exception{
	int status = ToolRunner.run(new WordCount(), args);
	System.exit(status);
}

}

执行hadoop jar hadoop_test-0.0.1-SNAPSHOT.jar hadoop_test/WordCount -Dinput=hdfs:/usr/hadoop/maven* -Doutput=hdfs:/usr/hadoop/maven1指令(注意此时的文件路径和/usr/local区分开)
好了,到这里基本上我们的环境就搭建成功了,还有些细节的这几天会慢慢补充的。

参考地址:maven配置部分:https://www.cnblogs.com/cenzhongman/p/7093672.html 侵删

posted @ 2017-12-06 21:15  周景白炎  阅读(759)  评论(0编辑  收藏  举报