org.apache.hadoop.hive.ql.io

Class BatchToRowReader<StructType,UnionType>

java.lang.Object

org.apache.hadoop.hive.ql.io.BatchToRowReader<StructType,UnionType>

All Implemented Interfaces:

Closeable, AutoCloseable, org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

Direct Known Subclasses:

OrcOiBatchToRowReader

public abstract class BatchToRowReader<StructType,UnionType>
extends Object
implements org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

A record reader wrapper that converts VRB reader into an OI-based reader. Due to the fact that changing table OIs in the plan after compilation is nearly impossible, this is made an abstract class where type-specific implementations can plug in certain details, so that the data produced after wrapping a vectorized reader would conform to the original OIs.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	BatchToRowReader.VirtualColumnHandler Wrapper class to map a virtual column to a handler defined by subclasses of BatchToRowReader.

Field Summary

Fields

Modifier and Type	Field and Description
protected static org.slf4j.Logger	LOG
protected List<BatchToRowReader.VirtualColumnHandler>	virtualColumnHandlers

Constructor Summary

Constructors

Constructor and Description
BatchToRowReader(org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,VectorizedRowBatch> vrbReader, VectorizedRowBatchCtx vrbCtx, List<Integer> includedCols)

Method Summary

Modifier and Type	Method and Description
void	close()
org.apache.hadoop.io.NullWritable	createKey()
protected abstract StructType	createStructObject(Object previous, List<TypeInfo> childrenTypes)
protected abstract UnionType	createUnionObject(List<TypeInfo> childrenTypes, Object previous)
Object	createValue()
long	getPos()
float	getProgress()
protected abstract Object	getStructCol(StructType structObj, int i)
protected abstract int	getStructLength(StructType structObj)
protected abstract Object	getUnionField(UnionType unionObj)
boolean	next(org.apache.hadoop.io.NullWritable key, Object previous)
static org.apache.hadoop.io.BytesWritable	nextBinary(ColumnVector vector, int row, Object previous)
static org.apache.hadoop.io.BooleanWritable	nextBoolean(ColumnVector vector, int row, Object previous)
static ByteWritable	nextByte(ColumnVector vector, int row, Object previous)
static HiveCharWritable	nextChar(ColumnVector vector, int row, int size, Object previous)
static DateWritableV2	nextDate(ColumnVector vector, int row, Object previous)
static HiveDecimalWritable	nextDecimal(ColumnVector vector, int row, Object previous)
static DoubleWritable	nextDouble(ColumnVector vector, int row, Object previous)
static org.apache.hadoop.io.FloatWritable	nextFloat(ColumnVector vector, int row, Object previous)
static org.apache.hadoop.io.IntWritable	nextInt(ColumnVector vector, int row, Object previous)
static org.apache.hadoop.io.LongWritable	nextLong(ColumnVector vector, int row, Object previous)
static ShortWritable	nextShort(ColumnVector vector, int row, Object previous)
static org.apache.hadoop.io.Text	nextString(ColumnVector vector, int row, Object previous)
StructType	nextStruct(ColumnVector vector, int row, StructTypeInfo schema, Object previous)
static TimestampWritableV2	nextTimestamp(ColumnVector vector, int row, Object previous)
static HiveVarcharWritable	nextVarchar(ColumnVector vector, int row, int size, Object previous)
protected abstract List<BatchToRowReader.VirtualColumnHandler>	requestedVirtualColumns()
protected abstract void	setStructCol(StructType structObj, int i, Object value)
protected abstract void	setUnion(UnionType unionObj, byte tag, Object object)

Methods inherited from class java.lang.Object

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

Field Detail

LOG

protected static final org.slf4j.Logger LOG

virtualColumnHandlers

protected List<BatchToRowReader.VirtualColumnHandler> virtualColumnHandlers

Constructor Detail

BatchToRowReader

public BatchToRowReader(org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,VectorizedRowBatch> vrbReader,
                        VectorizedRowBatchCtx vrbCtx,
                        List<Integer> includedCols)

Method Detail

requestedVirtualColumns

protected abstract List<BatchToRowReader.VirtualColumnHandler> requestedVirtualColumns()

createStructObject

protected abstract StructType createStructObject(Object previous,
                                                 List<TypeInfo> childrenTypes)

setStructCol

protected abstract void setStructCol(StructType structObj,
                                     int i,
                                     Object value)

getStructCol

protected abstract Object getStructCol(StructType structObj,
                                       int i)

getStructLength

protected abstract int getStructLength(StructType structObj)

createUnionObject

protected abstract UnionType createUnionObject(List<TypeInfo> childrenTypes,
                                               Object previous)

setUnion

protected abstract void setUnion(UnionType unionObj,
                                 byte tag,
                                 Object object)

getUnionField

protected abstract Object getUnionField(UnionType unionObj)

createKey

public org.apache.hadoop.io.NullWritable createKey()

Specified by:

createKey in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

createValue

public Object createValue()

Specified by:

createValue in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

getPos

public long getPos()
            throws IOException

Specified by:

getPos in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

Throws:

IOException

getProgress

public float getProgress()
                  throws IOException

Specified by:

getProgress in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

Throws:

IOException

next

public boolean next(org.apache.hadoop.io.NullWritable key,
                    Object previous)
             throws IOException

Specified by:

next in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

Throws:

IOException

close

public void close()
           throws IOException

Specified by:

close in interface Closeable

Specified by:

close in interface AutoCloseable

Specified by:

close in interface org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.NullWritable,Object>

Throws:

IOException

nextBoolean

public static org.apache.hadoop.io.BooleanWritable nextBoolean(ColumnVector vector,
                                                               int row,
                                                               Object previous)

nextByte

public static ByteWritable nextByte(ColumnVector vector,
                                    int row,
                                    Object previous)

nextShort

public static ShortWritable nextShort(ColumnVector vector,
                                      int row,
                                      Object previous)

nextInt

public static org.apache.hadoop.io.IntWritable nextInt(ColumnVector vector,
                                                       int row,
                                                       Object previous)

nextLong

public static org.apache.hadoop.io.LongWritable nextLong(ColumnVector vector,
                                                         int row,
                                                         Object previous)

nextFloat

public static org.apache.hadoop.io.FloatWritable nextFloat(ColumnVector vector,
                                                           int row,
                                                           Object previous)

nextDouble

public static DoubleWritable nextDouble(ColumnVector vector,
                                        int row,
                                        Object previous)

nextString

public static org.apache.hadoop.io.Text nextString(ColumnVector vector,
                                                   int row,
                                                   Object previous)

nextChar

public static HiveCharWritable nextChar(ColumnVector vector,
                                        int row,
                                        int size,
                                        Object previous)

nextVarchar

public static HiveVarcharWritable nextVarchar(ColumnVector vector,
                                              int row,
                                              int size,
                                              Object previous)

nextBinary

public static org.apache.hadoop.io.BytesWritable nextBinary(ColumnVector vector,
                                                            int row,
                                                            Object previous)

nextDecimal

public static HiveDecimalWritable nextDecimal(ColumnVector vector,
                                              int row,
                                              Object previous)

nextDate

public static DateWritableV2 nextDate(ColumnVector vector,
                                      int row,
                                      Object previous)

nextTimestamp

public static TimestampWritableV2 nextTimestamp(ColumnVector vector,
                                                int row,
                                                Object previous)

nextStruct

public StructType nextStruct(ColumnVector vector,
                             int row,
                             StructTypeInfo schema,
                             Object previous)