mapreduce作业接受序列化文件（SequenceFile）作为文件输入的WordCount程序

MapReduce作业接受序列化文件的输入时，可通过配置job的输入文件格式实现，具体见代码：

package hadoop;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
//import org.apache.hadoop.mapred.Task.CombinerRunner;
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.SequenceFileAsTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WCseq {
	
	public static class Map extends Mapper<Text, Text, Text, IntWritable>{
		
		//private Writable Key = (Writable)ReflectionUtils.newInstance(reader.getKeyClass(), conf);
				
		@Override         //注意key为Text类型
		protected void map(Text key, Text value, Context context)
				throws IOException, InterruptedException {
			
			System.out.println("key:" + key.toString() + "    " + "value:" + value );
			
			String [] input = value.toString().split(" ");
			for(String s : input){
				context.write(new Text(s), new IntWritable(1));
			}
			
		}
		
	}
	
	public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable>{
		@Override
		protected void reduce(Text key, Iterable<IntWritable> values, Context context)
				throws IOException, InterruptedException {
			
			int sum = 0;
			for (IntWritable val : values) {
				sum += val.get();
			}
			context.write(key, new IntWritable(sum));
			
		}
	}
	
	
	private static Path inputPath = new Path("/user/root/in-seqf/seq1");
	private static Path outputPath = new Path("out-seqf");
	
	public static void main(String[] args) throws Exception {
	    Configuration conf = new Configuration();
	    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        Job job = new Job(conf, "WCseq");
        job.setJarByClass(WCseq.class);
        
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
                //主要通过该设置实现
		job.setInputFormatClass(SequenceFileAsTextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);
		
        FileInputFormat.addInputPath(job, inputPath);
        FileSystem fs = FileSystem.get(conf);
        fs.delete(outputPath, true);
        FileOutputFormat.setOutputPath(job, outputPath);
        
        System.exit(job.waitForCompletion(true) ? 0 : 1);
	  }
}

经测试发现，map作业接受key的值为行号，map程序接受的key、value如下：

key:0    value:hello world
key:1    value:bye world
key:2    value:hello hadoop
key:3    value:bye hadoop
key:4    value:hello world
key:5    value:bye world
key:6    value:hello hadoop
key:7    value:bye hadoop
key:8    value:hello world
key:9    value:bye world
key:10    value:hello hadoop
key:11    value:bye hadoop
key:12    value:hello world