MapReduce-myInputFormat

MainTest.java

package MyinputFormat;

import java.io.IOException;
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.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.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;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


/**
 * @author carssun 2018年3月19日下午6:41:39
 *自定义outputformat
 */
public class MainTest extends Configured implements Tool {
	public static void main(String[] args) throws Exception {
		int exitCode = ToolRunner.run(new MainTest(), args);
		System.exit(exitCode);
		
	}
	
	private static Text filename;
	public static class MyInMapper extends Mapper<NullWritable, Text, Text, Text>{
		
		@Override
		protected void setup(Mapper<NullWritable, Text, Text, Text>.Context context)
				throws IOException, InterruptedException {
			InputSplit split=context.getInputSplit();
			Path filePath=((FileSplit)split).getPath();
			filename=new Text(filePath.toString());//记得试一下换成getNames
			
		}

		@Override
		protected void map(NullWritable key, Text value, Mapper<NullWritable, Text, Text, Text>.Context context)
				throws IOException, InterruptedException {
			context.write(filename, value);
			System.err.println("读了一次");
		}
		
	}
	//reduce原样输出即可
	public static class MyInReducer extends Reducer<Text, Text, Text, NullWritable>{
		@Override
		protected void reduce(Text key, Iterable<Text> value, Context context)
				throws IOException, InterruptedException {
			context.write(value.iterator().next(),NullWritable.get());//不用循环 一个key只对应一个value
		}
		
	}
	@Override
	public int run(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);
		job.setJarByClass(MainTest.class);
		
		job.setMapperClass(MyInMapper.class);
		job.setReducerClass(MyInReducer.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(NullWritable.class);
		Path inputPath=new Path("D:/result/small");
		Path outputPath=new Path("D:/result/small/output");
		FileInputFormat.setInputPaths(job, inputPath);
		FileOutputFormat.setOutputPath(job,outputPath);
		job.setNumReduceTasks(0);
		
		job.setInputFormatClass(WholeInputFormat.class);
		
		FileSystem fs=FileSystem.get(conf);
		if(fs.exists(outputPath)){
			fs.delete(outputPath,true);
		}
		int status = job.waitForCompletion(true) ? 0 : 1;
		return status;
	}
}

MyReaderRecorder

package MyinputFormat;

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.IOUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
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;

/**
 * @author lhx 2018年3月19日下午8:37:16
 *
 */
public class MyReaderRecorder extends RecordReader<NullWritable, Text>{
	//四个成员变量
	private Configuration conf=null;//配置
	private FileSplit split=null;//文件切片
	private boolean process=false;//记录进度
	private Text value=new Text();
	@Override
	public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
		conf=context.getConfiguration();
		this.split=(FileSplit)split;
	}
	// nextKeyValue()方法是RecordReader最重要的方法，也就是RecordReader读取文件的读取逻辑所在地
	// 所以我们要自定义RecordReader，就需要重写nextKeyValue()的实现
	@Override
	public boolean nextKeyValue() throws IOException, InterruptedException {
		if(!process){
			//创建缓冲区
			byte[] contents=new byte[(int)split.getLength()];//文件的确可能超过int最大值
			//这里的强转也是迫不得已 如果超过int最大值 就可以不考虑整个文件一起切
			FileSystem fs=FileSystem.get(conf);
			Path filePath=split.getPath();//通过filesplit切片获取文件路劲
			FSDataInputStream inputStream=fs.open(filePath);//hdfs文件读流
			//读取文件
			IOUtils.readFully(inputStream, contents, 0, contents.length);
			//把文件内容都读取到缓缓冲区后 再把内容写到value
			value.set(contents,0,contents.length);
			IOUtils.closeStream(inputStream);//关闭输入流
			process=true;//进度完成
			return true;
		}
		return false;
	}

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

	@Override
	public Text getCurrentValue() throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		return value;
	}

	@Override
	public float getProgress() throws IOException, InterruptedException {
		// TODO Auto-generated method stub
		return process?0f:1f;//进度 要不就是100%要不就是0%
	}

	@Override
	public void close() throws IOException {
		// do nothing
		
	}

}

WholeInputFormat

package MyinputFormat;

import java.io.IOException;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
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 WholeInputFormat extends FileInputFormat<NullWritable, Text>{
	
	

	@Override
	protected boolean isSplitable(JobContext context, Path filename) {//设置成不可再切分
		return false;
	}

	@Override
	public RecordReader<NullWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context)
			throws IOException, InterruptedException {
		MyReaderRecorder reader=new MyReaderRecorder();
		reader.initialize(split, context);
		return reader;
	}
	
	
	
	

}