自定义InputFormat

package com.cn.demo_xwjhb;

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;

import java.io.IOException;

public class MyInputFormat extends FileInputFormat<NullWritable, BytesWritable> {
    /**
     * 目的:实现小文件的合并，合并成一个二进制文件
     * 返回值代表文件是否分割，因为要合并小文件，不分割
     */
    @Override
    protected boolean isSplitable(JobContext context, Path filename) {
        return false;
    }

    /**
     * 读取的时候主要使用此程序，需要返回重写的RecordReader
     * @param inputSplit    切片
     * @param taskAttemptContext     上下文
     * @return
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    public RecordReader<NullWritable, BytesWritable> createRecordReader(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        MyRecordReader reader = new MyRecordReader();
        reader.initialize(inputSplit,taskAttemptContext);
        return reader;
    }
}

package com.cn.demo_xwjhb;

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;

import java.io.IOException;

public class MyRecordReader extends RecordReader<NullWritable, BytesWritable> {
    private FileSplit fileSplit;
    private Configuration configuration;
    private BytesWritable value = new BytesWritable();
    private boolean processed = false;



    /**
     * 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，主要重写这个方法的逻辑
     *   通过getCurrentKey 和 getCurrentValue来返回上面构造好的key和value
     *
     */
    @Override
    public void initialize(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        this.fileSplit = (FileSplit) inputSplit;
        this.configuration = taskAttemptContext.getConfiguration();
    }

    /**
     * 获取K1 V1的逻辑
     * 定义一个数组，长度必须能够放下一整个切片
     * 利用IOUtils工具类的readFully   传入FSDataInputStream流   读入数据
     * 结束后关闭流
     * @return
     * @throws IOException
     */
    @Override
    public boolean nextKeyValue() throws IOException {
        if(!processed){
            byte[] contents = new byte[(int) fileSplit.getLength()];
            Path file = fileSplit.getPath();
            FileSystem fs = file.getFileSystem(configuration);
            FSDataInputStream in = null;

            try {
                in = fs.open(file);
                //IOUtils有两个，保持统一去使用即可
                IOUtils.readFully(in,contents,0,contents.length);
                value.set(contents,0,contents.length);
            } catch (IOException e) {
                e.printStackTrace();
            }finally {
                IOUtils.closeStream(in);
            }
            processed = true;
            return true;
        }
        return false;
    }

    /**
     * 返回k1
     */
    @Override
    public NullWritable getCurrentKey() throws IOException, InterruptedException {
        return NullWritable.get();
    }

    /**
     * 返回V1
     */
    @Override
    public BytesWritable getCurrentValue() throws IOException, InterruptedException {
        return value;
    }

    /**
     * 获取文件进度的东西，没什么用
     */
    @Override
    public float getProgress() throws IOException, InterruptedException {
        return processed?1.0f:0.0f;
    }

    @Override
    public void close() throws IOException {

    }
}

---------------------------------主程序二进制文件输出-------------------------

job.setOutputKeyClass(Text.class);
job.setOutputValueClass(BytesWritable.class);

job.setOutputFormatClass(SequenceFileOutputFormat.class);
SequenceFileOutputFormat.setOutputPath(job,new Path("file:///D:\\dsj\\baishi课件\\hadoop\\5、大数据离线第五天\\5、大数据离线第五天\\自定义inputformat_小文件合并\\output"));