关于hadoop的自定义输入格式:
之前在网上找过很多教程,但是大多数都是在不支持分片的前提下进行自定义输入。本文实现了一种在能够分片的基础上支持自定义输入格式的方法。
先贴代码:
import java.io.IOException;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
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.fs.Seekable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CodecPool;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.io.compress.Decompressor;
import org.apache.hadoop.io.compress.SplitCompressionInputStream;
import org.apache.hadoop.io.compress.SplittableCompressionCodec;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.map