学步园

package com.ccse.hadoop.cmd;

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

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

import com.ccse.hadoop.outputformat.MySelfOutputFormatApp;

/**
 * 命令行运行MapReduce
 * @author woshiccna
 *
 */
public class WordCountApp extends Configured implements Tool {

	public static String INPUT_PATH = null;
	public static String OUTPUT_PATH = null;
	
	public static void main(String[] args) throws Exception {
		ToolRunner.run(new Configuration(), new WordCountApp(), args);
	}
	
	public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
		private Text word = new Text();
		private LongWritable writable = new LongWritable(1);
		@Override
		protected void map(LongWritable key, Text value,
				Mapper<LongWritable, Text, Text, LongWritable>.Context context)
				throws IOException, InterruptedException {
			if (value != null) {
				String line = value.toString();
				StringTokenizer tokenizer = new StringTokenizer(line);
				while (tokenizer.hasMoreTokens()) {
					word.set(tokenizer.nextToken());
					context.write(word, writable);
				}
			}
		}
	}
	
	public static class MyReducer 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 sum = 0; 
			for (LongWritable value : values) {
				sum += value.get();
			}
			context.write(key, new LongWritable(sum));
		}
	}

	@Override
	public int run(String[] args) throws Exception {
		INPUT_PATH = args[0];
		OUTPUT_PATH = args[1];		
		Configuration conf = new Configuration();
		FileSystem fileSystem = FileSystem.get(new URI(OUTPUT_PATH), conf);
		fileSystem.delete(new Path(OUTPUT_PATH), true);
		
		Job job = new Job(conf, MySelfOutputFormatApp.class.getSimpleName());
		job.setJarByClass(MySelfOutputFormatApp.class);
		
		FileInputFormat.setInputPaths(job, new Path(INPUT_PATH));
		job.setMapperClass(MyMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(LongWritable.class);
		
		job.setReducerClass(MyReducer.class);
	    job.setOutputKeyClass(Text.class);
	    job.setOutputValueClass(LongWritable.class);
	    FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH));
	    
	    job.waitForCompletion(true);
		return 0;
	}

}

使用命令 hadoop jar jar.jar com.ccse.hadoop.cmd.WordCountApp hdfs://chaoren1:9000/mapinput hdfs://chaoren1:9000/mapoutput来执行MapReduce程序