准备工具
- Eclipse(本人使用的是4.4.2)
- hadoop-eclipse-plugin-2.6.0(eclipse插件)
- hadoop-common-2.2.0-bin-master(windows下远程调用hadoop使用)
工具链接: http://pan.baidu.com/s/1i474ko1 密码: naph
配置步骤
- 将插件hadoop-eclipse-plugin-2.6.0.jar放入到Eclipse安装目录plugins文件夹下并重启Eclipse;
- 将hadoop-common-2.2.0-bin-master.zip解压到合适文件夹中,并将解压的目录配置到环境变量中,主要配置变量参照如下;
- HADOOP_HOME=E:\develop_tools\hadoop-common-2.2.0-bin-master
- PATH=%PATH%;E:\develop_tools\hadoop-common-2.2.0-bin-master\bin
- 打开Eclipse选择windows->show view->other打开mapreduce tools视图
- 点击右上方添加按钮进行hadoop相关位置配置,根据实际情况填写
- 如果填写正确可在Project Explorer中DFS Locations查看hdfs文档结构
- 运行WordCount程序验证,附上代码。
package com.doolin;
import java.io.IOException;
import java.util.StringTokenizer;
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 org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
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);
}
}
}
public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();
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);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}