想要在windows上以本地模式运行hadoop就必须要在windows上配置好hadoop的本地运行环境。我们需要下载编译好的hadoop二进制包。
下载地址如下:
链接:http://pan.baidu.com/s/1skE4fQt 密码:or48
下载完成后配置windows环境变量:
HADOOP_HOME=C:\Program Files (x86)\hadoop-2.6.0
PATH=%PATH%:%HADOOP_HOME%\bin
map:
package cn.hadoop.mr;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;
public class WCMapper extends Mapper<LongWritable, Text, Text, LongWritable>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
String line = value.toString();
String[] words = StringUtils.split(line,' ');
for(String word : words) {
context.write(new Text(word), new LongWritable(1));
}
}
}
reduce:
package cn.hadoop.mr;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class WCReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key, Iterable<LongWritable> values,
Reducer<Text, LongWritable, Text, LongWritable>.Context context) throws IOException, InterruptedException {
long count = 0;
for(LongWritable value : values) {
count += value.get();
}
context.write(key, new LongWritable(count));
}
}
run:
package cn.hadoop.mr;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;
public class WCRunner {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job wcjob = Job.getInstance(conf);
wcjob.setJarByClass(WCRunner.class);
wcjob.setMapperClass(WCMapper.class);
wcjob.setReducerClass(WCReducer.class);
wcjob.setOutputKeyClass(Text.class);
wcjob.setOutputValueClass(LongWritable.class);
wcjob.setMapOutputKeyClass(Text.class);
wcjob.setMapOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(wcjob, "E:/wc/inputdata/");
FileOutputFormat.setOutputPath(wcjob, new Path("E:/wc/output/"));
wcjob.waitForCompletion(true);
}
}
缺少jar包的话就把C:\Program Files (x86)\had