记录一个简单的WordCount程序,以后当做模板用
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.*;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class WordCount extends Configured implements Tool{
enum Counter{
LINERSKIP;
}
public static class Map extends Mapper<LongWritable,Text,Text,IntWritable>
{
public void map(LongWritable key,Text value,Context context) throws IOException,InterruptedException
{
try{
String[] linesplit = value.toString().split(" ");
for(String str: linesplit)
context.write(new Text(str),new IntWritable(1));
}
catch(java.lang.ArrayIndexOutOfBoundsException e){
context.getCounter(Counter.LINERSKIP).increment(1);
return;
}
}
}
public static class Reduce extends Reducer<Text,IntWritable,Text,IntWritable>
{
public void reduce(Text key,Iterable<IntWritable> value,Context context) throws IOException,InterruptedException
{
int temp = 0;
for(IntWritable val : value)
{
temp += val.get();
}
context.write(key,new IntWritable(temp));
}
}
public int run(String[] args) throws Exception
{
Configuration conf = getConf();
Job job = new Job(conf,"WordCount");
job.setJarByClass(WordCount.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job,new Path(args[1]));
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.waitForCompletion(true);
return job.isSuccessful()?0:1;
}
public static void main(String[] args) throws Exception
{
int res = ToolRunner.run(new Configuration(), new WordCount(),args);
System.exit(res);
}
}