重写RecordReader和InputFormat实现单个文件不分片，整个分片作为一条记录处理。（倒排索引）

这是MapReduce功能代码：

package org.edu.bupt.xiaoye.hadooptest;

import java.io.IOException;
import java.net.URI;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;
import java.util.Set;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MyInverseIndex {
	public static final String INPUT_PATH = "hdfs://10.103.240.160:9000/usr/hadoop/MyInverseIndex_in";
	public static final String OUTPUT_PATH = "hdfs://10.103.240.160:9000/usr/hadoop/MyInverseIndex_out";

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		final FileSystem fileSystem = FileSystem.get(new URI(INPUT_PATH), conf);
		final Path outPath = new Path(OUTPUT_PATH);
		if (fileSystem.exists(outPath)) {
			fileSystem.delete(outPath, true);
		}
		conf.set("hadoop.job.user","hadoop");
		conf.set("mapred.job.tracker", "10.103.240.160:9001");
		
		final Job job = new Job(conf, MyInverseIndex.class.getSimpleName());
		FileInputFormat.setInputPaths(job, INPUT_PATH);
		job.setJarByClass(MyInverseIndex.class);
		job.setMapperClass(MyMapper.class);
		job.setReducerClass(MyReduce.class);
		job.setInputFormatClass(WholeFileInputFormat.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		job.setNumReduceTasks(1);//设置个数为1
		FileOutputFormat.setOutputPath(job, outPath);
		job.waitForCompletion(true);
		
	}

	/**
	 * 只适用于文档中只出现一行 （可以一次读取整个文档）
	 * 
	 * @author hadoop
	 * 
	 */
	public static class MyMapper extends Mapper<NullWritable, BytesWritable, Text, Text> {
		Map<String, Integer> map = new HashMap();

		@Override
		public  void map(NullWritable key, BytesWritable value, Context context)
				throws IOException, InterruptedException {
			String line = new String(value.getBytes(), "utf-8").trim();
			String[] words = line.split(" ");
			for (String s : words) {
				if (map.containsKey(s)) {
					map.put(s, map.get(s) + 1);
				} else {
					map.put(s, 1);
				}
			}
			Set<String> keys = map.keySet();
			for (Iterator it = keys.iterator(); it.hasNext();) {
				String s = (String) it.next();
				context.write(new Text(s),
						new Text(((FileSplit) context.getInputSplit()).getPath().getName().toString() + ":" + map.get(s)));
			}
			map.clear();
		}
	}

	public static class MyReduce extends Reducer<Text, Text, Text, Text> {		
		private Text result = new Text();
		// 实现reduce函数
		public void reduce(Text key, Iterable<Text> values, Context context)
		throws IOException, InterruptedException {
			StringBuffer fileList = new StringBuffer();
			for(Text value : values){
				fileList.append(value.toString()+";");
			}
			result.set(fileList.toString());
			context.write(key, result);
		}
	}
		
}
package