org.apache.flink.formats.parquet.vector

Class ParquetSplitReaderUtil

java.lang.Object

org.apache.flink.formats.parquet.vector.ParquetSplitReaderUtil

public class ParquetSplitReaderUtil
extends Object

Util for generating ParquetColumnarRowSplitReader.

Constructor Summary

Constructors

Constructor and Description
ParquetSplitReaderUtil()

Method Summary

Modifier and Type	Method and Description
static ColumnReader	createColumnReader(boolean isUtcTimestamp, LogicalType fieldType, org.apache.parquet.schema.Type type, List<org.apache.parquet.column.ColumnDescriptor> columnDescriptors, org.apache.parquet.column.page.PageReadStore pages, int depth)
static ColumnVector	createVectorFromConstant(LogicalType type, Object value, int batchSize)
static WritableColumnVector	createWritableColumnVector(int batchSize, LogicalType fieldType, org.apache.parquet.schema.Type type, List<org.apache.parquet.column.ColumnDescriptor> columnDescriptors, int depth)
static ParquetColumnarRowSplitReader	genPartColumnarRowReader(boolean utcTimestamp, boolean caseSensitive, org.apache.hadoop.conf.Configuration conf, String[] fullFieldNames, DataType[] fullFieldTypes, Map<String,Object> partitionSpec, int[] selectedFields, int batchSize, Path path, long splitStart, long splitLength) Util for generating partitioned ParquetColumnarRowSplitReader.

Methods inherited from class java.lang.Object

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

Constructor Detail

ParquetSplitReaderUtil

public ParquetSplitReaderUtil()

Method Detail

genPartColumnarRowReader

public static ParquetColumnarRowSplitReader genPartColumnarRowReader(boolean utcTimestamp,
                                                                     boolean caseSensitive,
                                                                     org.apache.hadoop.conf.Configuration conf,
                                                                     String[] fullFieldNames,
                                                                     DataType[] fullFieldTypes,
                                                                     Map<String,Object> partitionSpec,
                                                                     int[] selectedFields,
                                                                     int batchSize,
                                                                     Path path,
                                                                     long splitStart,
                                                                     long splitLength)
                                                              throws IOException

Util for generating partitioned ParquetColumnarRowSplitReader.

Throws:

IOException

createVectorFromConstant

public static ColumnVector createVectorFromConstant(LogicalType type,
                                                    Object value,
                                                    int batchSize)

createColumnReader

public static ColumnReader createColumnReader(boolean isUtcTimestamp,
                                              LogicalType fieldType,
                                              org.apache.parquet.schema.Type type,
                                              List<org.apache.parquet.column.ColumnDescriptor> columnDescriptors,
                                              org.apache.parquet.column.page.PageReadStore pages,
                                              int depth)
                                       throws IOException

Throws:

IOException

createWritableColumnVector

public static WritableColumnVector createWritableColumnVector(int batchSize,
                                                              LogicalType fieldType,
                                                              org.apache.parquet.schema.Type type,
                                                              List<org.apache.parquet.column.ColumnDescriptor> columnDescriptors,
                                                              int depth)