org.apache.iceberg.arrow.vectorized.parquet

Class VectorizedColumnIterator

java.lang.Object

org.apache.iceberg.parquet.BaseColumnIterator

org.apache.iceberg.arrow.vectorized.parquet.VectorizedColumnIterator

public class VectorizedColumnIterator
extends BaseColumnIterator

Vectorized version of the ColumnIterator that reads column values in data pages of a column in a row group in a batched fashion.

Field Summary

Fields inherited from class org.apache.iceberg.parquet.BaseColumnIterator

advanceNextPageCount, desc, dictionary, pageSource, triplesCount, triplesRead

Constructor Summary

Constructors

Constructor and Description
VectorizedColumnIterator(org.apache.parquet.column.ColumnDescriptor desc, java.lang.String writerVersion, boolean setArrowValidityVector)

Method Summary

Modifier and Type	Method and Description
void	nextBatchBoolean(org.apache.arrow.vector.FieldVector fieldVector, NullabilityHolder nullabilityHolder)
void	nextBatchDictionaryIds(org.apache.arrow.vector.IntVector vector, NullabilityHolder holder)
void	nextBatchDoubles(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder holder)
void	nextBatchFixedLengthDecimal(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder nullabilityHolder)
void	nextBatchFixedWidthBinary(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder nullabilityHolder)
void	nextBatchFloats(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder holder)
void	nextBatchIntBackedDecimal(org.apache.arrow.vector.FieldVector fieldVector, NullabilityHolder nullabilityHolder)
void	nextBatchIntegers(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder holder)
void	nextBatchLongBackedDecimal(org.apache.arrow.vector.FieldVector fieldVector, NullabilityHolder nullabilityHolder)
void	nextBatchLongs(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder holder)
void	nextBatchTimestampMillis(org.apache.arrow.vector.FieldVector fieldVector, int typeWidth, NullabilityHolder holder)
void	nextBatchVarWidthType(org.apache.arrow.vector.FieldVector fieldVector, NullabilityHolder nullabilityHolder)
protected BasePageIterator	pageIterator()
boolean	producesDictionaryEncodedVector()
void	setBatchSize(int batchSize)
org.apache.parquet.column.Dictionary	setRowGroupInfo(org.apache.parquet.column.page.PageReader store, boolean allPagesDictEncoded)

Methods inherited from class org.apache.iceberg.parquet.BaseColumnIterator

advance, hasNext, setPageSource

Methods inherited from class java.lang.Object

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

Constructor Detail

VectorizedColumnIterator

public VectorizedColumnIterator(org.apache.parquet.column.ColumnDescriptor desc,
                                java.lang.String writerVersion,
                                boolean setArrowValidityVector)

Method Detail

setBatchSize

public void setBatchSize(int batchSize)

setRowGroupInfo

public org.apache.parquet.column.Dictionary setRowGroupInfo(org.apache.parquet.column.page.PageReader store,
                                                            boolean allPagesDictEncoded)

nextBatchIntegers

public void nextBatchIntegers(org.apache.arrow.vector.FieldVector fieldVector,
                              int typeWidth,
                              NullabilityHolder holder)

nextBatchDictionaryIds

public void nextBatchDictionaryIds(org.apache.arrow.vector.IntVector vector,
                                   NullabilityHolder holder)

nextBatchLongs

public void nextBatchLongs(org.apache.arrow.vector.FieldVector fieldVector,
                           int typeWidth,
                           NullabilityHolder holder)

nextBatchTimestampMillis

public void nextBatchTimestampMillis(org.apache.arrow.vector.FieldVector fieldVector,
                                     int typeWidth,
                                     NullabilityHolder holder)

nextBatchFloats

public void nextBatchFloats(org.apache.arrow.vector.FieldVector fieldVector,
                            int typeWidth,
                            NullabilityHolder holder)

nextBatchDoubles

public void nextBatchDoubles(org.apache.arrow.vector.FieldVector fieldVector,
                             int typeWidth,
                             NullabilityHolder holder)

nextBatchIntBackedDecimal

public void nextBatchIntBackedDecimal(org.apache.arrow.vector.FieldVector fieldVector,
                                      NullabilityHolder nullabilityHolder)

nextBatchLongBackedDecimal

public void nextBatchLongBackedDecimal(org.apache.arrow.vector.FieldVector fieldVector,
                                       NullabilityHolder nullabilityHolder)

nextBatchFixedLengthDecimal

public void nextBatchFixedLengthDecimal(org.apache.arrow.vector.FieldVector fieldVector,
                                        int typeWidth,
                                        NullabilityHolder nullabilityHolder)

nextBatchVarWidthType

public void nextBatchVarWidthType(org.apache.arrow.vector.FieldVector fieldVector,
                                  NullabilityHolder nullabilityHolder)

nextBatchFixedWidthBinary

public void nextBatchFixedWidthBinary(org.apache.arrow.vector.FieldVector fieldVector,
                                      int typeWidth,
                                      NullabilityHolder nullabilityHolder)

nextBatchBoolean

public void nextBatchBoolean(org.apache.arrow.vector.FieldVector fieldVector,
                             NullabilityHolder nullabilityHolder)

pageIterator

protected BasePageIterator pageIterator()

Specified by:

pageIterator in class BaseColumnIterator

producesDictionaryEncodedVector

public boolean producesDictionaryEncodedVector()