使用inputFormat实现合并多个小文件为一个大文件

测试数据

did.txt

did_1,1
did_2,1
did_3,1

pid.txt

pid_1,1
pid_2,1
pid_3,1

order.txt

order_1,1
order_2,1
order_3,1

代码

package cn.feizhou.combinefile;

import java.io.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

public class WholeFileInputFormat extends FileInputFormat<NullWritable, BytesWritable>{

	@Override
	//是否分割文件
	 //设置每个小文件不可分片,保证一个小文件生成一个key-value键值对
	protected boolean isSplitable(JobContext context, Path file) {
		return false;
	}

	@Override
	//读取整个文件
	public RecordReader<NullWritable, BytesWritable> createRecordReader(
			InputSplit split, TaskAttemptContext context) throws IOException,	InterruptedException {
		
		WholeFileRecordReader reader = new WholeFileRecordReader();
		reader.initialize(split, context);
		return reader;
	}

}
------------------------------
package cn.feizhou.combinefile;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

/**
 * 改写RecordReader，实现一次读取一个完整文件封装为KV
 * RecordReader的核心工作逻辑：
 * 通过nextKeyValue()方法去读取数据构造将返回的key   value
 * 通过getCurrentKey 和 getCurrentValue来返回上面构造好的key和value
 * 
 * 
 * @author
 *
 */
class WholeFileRecordReader extends RecordReader<NullWritable, BytesWritable> {
	private FileSplit fileSplit;
	private Configuration conf;
	private BytesWritable value = new BytesWritable();
	private boolean processed = false;

	@Override
	public void initialize(InputSplit split, TaskAttemptContext context)
			throws IOException, InterruptedException {
		this.fileSplit = (FileSplit) split;
		this.conf = context.getConfiguration();
	}

	@Override
	public boolean nextKeyValue() throws IOException, InterruptedException {
		if (!processed) {
			byte[] contents = new byte[(int) fileSplit.getLength()];
			Path file = fileSplit.getPath();
			FileSystem fs = file.getFileSystem(conf);
			FSDataInputStream in = null;
			try {
				in = fs.open(file);
				IOUtils.readFully(in, contents, 0, contents.length);
				value.set(contents, 0, contents.length);
			} finally {
				IOUtils.closeStream(in);
			}
			processed = true;
			return true;
		}
		return false;
	}

	
	
	
	@Override
	public NullWritable getCurrentKey() throws IOException,
			InterruptedException {
		return NullWritable.get();
	}

	@Override
	public BytesWritable getCurrentValue() throws IOException,
			InterruptedException {
		return value;
	}

	/**
	 * 返回当前进度
	 */
	@Override
	public float getProgress() throws IOException {
		return processed ? 1.0f : 0.0f;
	}

	@Override
	public void close() throws IOException {
	}
}
------------------------------
package cn.feizhou.combinefile;


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.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class SmallFilesToSequenceFileConverter extends Configured implements Tool {
	static class SequenceFileMapper extends
			Mapper<NullWritable, BytesWritable, Text, BytesWritable> {
		private Text filenameKey;

		@Override
		protected void setup(Context context) throws IOException,
				InterruptedException {
			InputSplit split = context.getInputSplit();
			Path path = ((FileSplit) split).getPath();
			filenameKey = new Text(path.toString());
		}

		@Override
		protected void map(NullWritable key, BytesWritable value,
				Context context) throws IOException, InterruptedException {
			context.write(filenameKey, value);
		}
	}

	@Override
	public int run(String[] args) throws Exception {
		Configuration conf = new Configuration();

		Job job = Job.getInstance(conf,"combine small files to sequencefile");
		job.setJarByClass(SmallFilesToSequenceFileConverter.class);
		
		job.setInputFormatClass(WholeFileInputFormat.class);
//		在输出时使用SequenceFileOutPutFormat输出合并文件
		job.setOutputFormatClass(SequenceFileOutputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(BytesWritable.class);
		job.setMapperClass(SequenceFileMapper.class);
		
		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		return job.waitForCompletion(true) ? 0 : 1;
	}

	public static void main(String[] args) throws Exception {
		args=new String[]{"H:/test/","H:/out/"};
		int exitCode = ToolRunner.run(new SmallFilesToSequenceFileConverter(),args);
		System.exit(exitCode);
		
	}
}

测试结果