public abstract class BaseVectorizedColumnReader extends Object implements org.apache.flink.formats.parquet.vector.reader.ColumnReader<org.apache.flink.table.data.columnar.vector.writable.WritableColumnVector>
ColumnReader. part of the code is referred from Apache Hive and Apache Parquet.| Modifier and Type | Class and Description |
|---|---|
protected static class |
BaseVectorizedColumnReader.NullIntIterator
return zero.
|
protected static class |
BaseVectorizedColumnReader.RLEIntIterator
read ints from
RunLengthBitPackingHybridDecoder. |
protected static class |
BaseVectorizedColumnReader.ValuesReaderIntIterator
read ints from
ValuesReader. |
| Modifier and Type | Field and Description |
|---|---|
protected ParquetDataColumnReader |
dataColumn |
protected int |
definitionLevel |
protected org.apache.hudi.table.format.cow.vector.reader.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 boolean |
isCurrentPageDictionaryEncoded
If true, the current page is dictionary encoded.
|
protected boolean |
isUtcTimestamp |
protected org.apache.flink.table.types.logical.LogicalType |
logicalType |
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.hudi.table.format.cow.vector.reader.BaseVectorizedColumnReader.IntIterator |
repetitionLevelColumn
Repetition/Definition/Value readers.
|
protected org.apache.parquet.schema.Type |
type |
protected long |
valuesRead
Total number of values read.
|
| Constructor and Description |
|---|
BaseVectorizedColumnReader(org.apache.parquet.column.ColumnDescriptor descriptor,
org.apache.parquet.column.page.PageReader pageReader,
boolean isUtcTimestamp,
org.apache.parquet.schema.Type parquetType,
org.apache.flink.table.types.logical.LogicalType logicalType) |
| Modifier and Type | Method and Description |
|---|---|
protected void |
readPage() |
protected void |
readRepetitionAndDefinitionLevels() |
protected boolean isUtcTimestamp
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.hudi.table.format.cow.vector.reader.BaseVectorizedColumnReader.IntIterator repetitionLevelColumn
protected org.apache.hudi.table.format.cow.vector.reader.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 org.apache.flink.table.types.logical.LogicalType logicalType
public BaseVectorizedColumnReader(org.apache.parquet.column.ColumnDescriptor descriptor,
org.apache.parquet.column.page.PageReader pageReader,
boolean isUtcTimestamp,
org.apache.parquet.schema.Type parquetType,
org.apache.flink.table.types.logical.LogicalType logicalType)
throws IOException
IOExceptionprotected void readRepetitionAndDefinitionLevels()
protected void readPage()
throws IOException
IOExceptionCopyright © 2023 The Apache Software Foundation. All rights reserved.