public abstract class BaseVectorizedColumnReader extends Object implements VectorizedColumnReader
Modifier and Type | Class and Description |
---|---|
protected static class |
BaseVectorizedColumnReader.NullIntIterator |
protected static class |
BaseVectorizedColumnReader.RLEIntIterator |
protected static class |
BaseVectorizedColumnReader.ValuesReaderIntIterator |
Modifier and Type | Field and Description |
---|---|
protected ParquetDataColumnReader |
dataColumn |
protected int |
definitionLevel |
protected org.apache.hadoop.hive.ql.io.parquet.vector.BaseVectorizedColumnReader.IntIterator |
definitionLevelColumn |
protected org.apache.parquet.column.ColumnDescriptor |
descriptor |
protected ParquetDataColumnReader |
dictionary
The dictionary, if this column has dictionary encoding.
|
protected long |
endOfPageValueCount
value that indicates the end of the current page.
|
protected TypeInfo |
hiveType |
protected boolean |
isCurrentPageDictionaryEncoded
If true, the current page is dictionary encoded.
|
protected int |
maxDefLevel
Maximum definition level for this column.
|
protected org.apache.parquet.column.page.PageReader |
pageReader |
protected int |
pageValueCount
Total values in the current page.
|
protected int |
repetitionLevel |
protected org.apache.hadoop.hive.ql.io.parquet.vector.BaseVectorizedColumnReader.IntIterator |
repetitionLevelColumn
Repetition/Definition/Value readers.
|
protected boolean |
skipTimestampConversion |
protected org.apache.parquet.schema.Type |
type |
protected long |
valuesRead
Total number of values read.
|
protected ZoneId |
writerTimezone |
Constructor and Description |
---|
BaseVectorizedColumnReader()
Used for VectorizedDummyColumnReader.
|
BaseVectorizedColumnReader(org.apache.parquet.column.ColumnDescriptor descriptor,
org.apache.parquet.column.page.PageReader pageReader,
boolean skipTimestampConversion,
ZoneId writerTimezone,
org.apache.parquet.schema.Type parquetType,
TypeInfo hiveType) |
Modifier and Type | Method and Description |
---|---|
protected void |
decimalTypeCheck(org.apache.parquet.schema.Type type)
Check the underlying Parquet file is able to parse as Hive Decimal type.
|
protected void |
readPage() |
protected void |
readRepetitionAndDefinitionLevels() |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
readBatch
protected boolean skipTimestampConversion
protected ZoneId writerTimezone
protected long valuesRead
protected long endOfPageValueCount
protected final ParquetDataColumnReader dictionary
protected boolean isCurrentPageDictionaryEncoded
protected final int maxDefLevel
protected int definitionLevel
protected int repetitionLevel
protected org.apache.hadoop.hive.ql.io.parquet.vector.BaseVectorizedColumnReader.IntIterator repetitionLevelColumn
protected org.apache.hadoop.hive.ql.io.parquet.vector.BaseVectorizedColumnReader.IntIterator definitionLevelColumn
protected ParquetDataColumnReader dataColumn
protected int pageValueCount
protected final org.apache.parquet.column.page.PageReader pageReader
protected final org.apache.parquet.column.ColumnDescriptor descriptor
protected final org.apache.parquet.schema.Type type
protected final TypeInfo hiveType
public BaseVectorizedColumnReader()
public BaseVectorizedColumnReader(org.apache.parquet.column.ColumnDescriptor descriptor, org.apache.parquet.column.page.PageReader pageReader, boolean skipTimestampConversion, ZoneId writerTimezone, org.apache.parquet.schema.Type parquetType, TypeInfo hiveType) throws IOException
IOException
protected void readRepetitionAndDefinitionLevels()
protected void readPage() throws IOException
IOException
protected void decimalTypeCheck(org.apache.parquet.schema.Type type)
type
- Copyright © 2019 The Apache Software Foundation. All rights reserved.