org.apache.hadoop.mapreduce.lib.input

Class UncompressedSplitLineReader

java.lang.Object

org.apache.hadoop.util.LineReader

org.apache.hadoop.mapreduce.lib.input.SplitLineReader

org.apache.hadoop.mapreduce.lib.input.UncompressedSplitLineReader

All Implemented Interfaces:

java.io.Closeable, java.lang.AutoCloseable

@InterfaceAudience.Private
@InterfaceStability.Unstable
public class UncompressedSplitLineReader
extends SplitLineReader

SplitLineReader for uncompressed files. This class can split the file correctly even if the delimiter is multi-bytes.

Constructor Summary

Constructors

Constructor and Description
UncompressedSplitLineReader(org.apache.hadoop.fs.FSDataInputStream in, org.apache.hadoop.conf.Configuration conf, byte[] recordDelimiterBytes, long splitLength)

Method Summary

Methods

Modifier and Type	Method and Description
protected int	fillBuffer(java.io.InputStream in, byte[] buffer, boolean inDelimiter)
boolean	needAdditionalRecordAfterSplit()
int	readLine(org.apache.hadoop.io.Text str, int maxLineLength, int maxBytesToConsume)
protected void	unsetNeedAdditionalRecordAfterSplit()

Methods inherited from class org.apache.hadoop.util.LineReader

close, getBufferPosn, getBufferSize, readLine, readLine

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

UncompressedSplitLineReader

public UncompressedSplitLineReader(org.apache.hadoop.fs.FSDataInputStream in,
                           org.apache.hadoop.conf.Configuration conf,
                           byte[] recordDelimiterBytes,
                           long splitLength)
                            throws java.io.IOException

Throws:

java.io.IOException

Method Detail

fillBuffer

protected int fillBuffer(java.io.InputStream in,
             byte[] buffer,
             boolean inDelimiter)
                  throws java.io.IOException

Overrides:

fillBuffer in class org.apache.hadoop.util.LineReader

Throws:

java.io.IOException

readLine

public int readLine(org.apache.hadoop.io.Text str,
           int maxLineLength,
           int maxBytesToConsume)
             throws java.io.IOException

Overrides:

readLine in class org.apache.hadoop.util.LineReader

Throws:

java.io.IOException

needAdditionalRecordAfterSplit

public boolean needAdditionalRecordAfterSplit()

Overrides:

needAdditionalRecordAfterSplit in class SplitLineReader

unsetNeedAdditionalRecordAfterSplit

protected void unsetNeedAdditionalRecordAfterSplit()

Overrides:

unsetNeedAdditionalRecordAfterSplit in class org.apache.hadoop.util.LineReader