org.apache.hadoop.hive.ql.io.parquet.read

Class ParquetRecordReaderWrapper

java.lang.Object

org.apache.hadoop.hive.ql.io.parquet.read.ParquetRecordReaderWrapper

All Implemented Interfaces:

org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

public class ParquetRecordReaderWrapper
extends Object
implements org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

Field Summary

Fields

Modifier and Type	Field and Description
static org.apache.commons.logging.Log	LOG

Constructor Summary

Constructors

Constructor and Description
ParquetRecordReaderWrapper(parquet.hadoop.ParquetInputFormat<org.apache.hadoop.io.ArrayWritable> newInputFormat, org.apache.hadoop.mapred.InputSplit oldSplit, org.apache.hadoop.mapred.JobConf oldJobConf, org.apache.hadoop.mapred.Reporter reporter)
ParquetRecordReaderWrapper(parquet.hadoop.ParquetInputFormat<org.apache.hadoop.io.ArrayWritable> newInputFormat, org.apache.hadoop.mapred.InputSplit oldSplit, org.apache.hadoop.mapred.JobConf oldJobConf, org.apache.hadoop.mapred.Reporter reporter, ProjectionPusher pusher)

Method Summary

Methods

Modifier and Type	Method and Description
void	close()
Void	createKey()
org.apache.hadoop.io.ArrayWritable	createValue()
List<parquet.hadoop.metadata.BlockMetaData>	getFiltedBlocks()
long	getPos()
float	getProgress()
protected parquet.hadoop.ParquetInputSplit	getSplit(org.apache.hadoop.mapred.InputSplit oldSplit, org.apache.hadoop.mapred.JobConf conf) gets a ParquetInputSplit corresponding to a split given by Hive
boolean	next(Void key, org.apache.hadoop.io.ArrayWritable value)
parquet.filter2.compat.FilterCompat.Filter	setFilter(org.apache.hadoop.mapred.JobConf conf)

Methods inherited from class java.lang.Object

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

Field Detail

LOG

public static final org.apache.commons.logging.Log LOG

Constructor Detail

ParquetRecordReaderWrapper

public ParquetRecordReaderWrapper(parquet.hadoop.ParquetInputFormat<org.apache.hadoop.io.ArrayWritable> newInputFormat,
                          org.apache.hadoop.mapred.InputSplit oldSplit,
                          org.apache.hadoop.mapred.JobConf oldJobConf,
                          org.apache.hadoop.mapred.Reporter reporter)
                           throws IOException,
                                  InterruptedException

Throws:

IOException

InterruptedException

ParquetRecordReaderWrapper

public ParquetRecordReaderWrapper(parquet.hadoop.ParquetInputFormat<org.apache.hadoop.io.ArrayWritable> newInputFormat,
                          org.apache.hadoop.mapred.InputSplit oldSplit,
                          org.apache.hadoop.mapred.JobConf oldJobConf,
                          org.apache.hadoop.mapred.Reporter reporter,
                          ProjectionPusher pusher)
                           throws IOException,
                                  InterruptedException

Throws:

IOException

InterruptedException

Method Detail

setFilter

public parquet.filter2.compat.FilterCompat.Filter setFilter(org.apache.hadoop.mapred.JobConf conf)

close

public void close()
           throws IOException

Specified by:

close in interface org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

Throws:

IOException

createKey

public Void createKey()

Specified by:

createKey in interface org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

createValue

public org.apache.hadoop.io.ArrayWritable createValue()

Specified by:

createValue in interface org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

getPos

public long getPos()
            throws IOException

Specified by:

getPos in interface org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

Throws:

IOException

getProgress

public float getProgress()
                  throws IOException

Specified by:

getProgress in interface org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

Throws:

IOException

next

public boolean next(Void key,
           org.apache.hadoop.io.ArrayWritable value)
             throws IOException

Specified by:

next in interface org.apache.hadoop.mapred.RecordReader<Void,org.apache.hadoop.io.ArrayWritable>

Throws:

IOException

getSplit

protected parquet.hadoop.ParquetInputSplit getSplit(org.apache.hadoop.mapred.InputSplit oldSplit,
                                        org.apache.hadoop.mapred.JobConf conf)
                                             throws IOException

gets a ParquetInputSplit corresponding to a split given by Hive

Parameters:

oldSplit - The split given by Hive

conf - The JobConf of the Hive job

Returns:

a ParquetInputSplit corresponding to the oldSplit

Throws:

IOException - if the config cannot be enhanced or if the footer cannot be read from the file

getFiltedBlocks

public List<parquet.hadoop.metadata.BlockMetaData> getFiltedBlocks()