配置 ubuntu14.04 伪分布式 hadoop1.04
wordcount入门程序, 摘自hadoop基础教程
import java.io.*;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCount {
//map操作
public static class WordCountMapper 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{
String[] words = value.toString().split(" ");
for(String str:words) {
word.set(str);
context.write(word, one);
}
}
}
//reduce操作
public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException{
int total = 0;
for(IntWritable val : values) {
total++;
}
context.write(key, new IntWritable(total));
}
}
public static void main(String[] args) {
try{
//创建Configuration对象,用于设置其他选项
Configuration conf = new Configuration();
//创建作业对象
Job job = new Job(conf, "WordCount");
//设置作业jarfile中主类名字
job.setJarByClass(WordCount.class);
//设置mapper类
job.setMapperClass(WordCountMapper.class);
//设置reduce类
job.setReducerClass(WordCountReducer.class);
//设置输出的类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//设置输入和输出文件路径
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//等待程序退出
System.exit(job.waitForCompletion(true)?0:1);
}catch(Exception e) {
//system.out.println("出错");
}
}
}