public final class ParquetTypeUtils extends Object
| Modifier and Type | Method and Description |
|---|---|
static List<String> |
columnPathFromSubfield(Subfield subfield) |
static Optional<Type> |
createDecimalType(RichColumnDescriptor descriptor) |
static org.apache.parquet.io.ColumnIO |
getArrayElementColumn(org.apache.parquet.io.ColumnIO columnIO) |
static org.apache.parquet.io.MessageColumnIO |
getColumnIO(org.apache.parquet.schema.MessageType fileSchema,
org.apache.parquet.schema.MessageType requestedSchema) |
static List<org.apache.parquet.io.PrimitiveColumnIO> |
getColumns(org.apache.parquet.schema.MessageType fileSchema,
org.apache.parquet.schema.MessageType requestedSchema) |
static Optional<RichColumnDescriptor> |
getDescriptor(List<org.apache.parquet.io.PrimitiveColumnIO> columns,
List<String> path) |
static Map<List<String>,RichColumnDescriptor> |
getDescriptors(org.apache.parquet.schema.MessageType fileSchema,
org.apache.parquet.schema.MessageType requestedSchema) |
static int |
getFieldIndex(org.apache.parquet.schema.MessageType fileSchema,
String name) |
static org.apache.parquet.io.GroupColumnIO |
getMapKeyValueColumn(org.apache.parquet.io.GroupColumnIO groupColumnIO) |
static ParquetEncoding |
getParquetEncoding(org.apache.parquet.column.Encoding encoding) |
static org.apache.parquet.schema.Type |
getParquetTypeByName(String columnName,
org.apache.parquet.schema.GroupType messageType) |
static long |
getShortDecimalValue(byte[] bytes) |
static Optional<org.apache.parquet.schema.Type> |
getSubfieldType(org.apache.parquet.schema.GroupType baseType,
String rootName,
List<String> nestedColumnPath) |
static boolean |
isTimeStampMicrosType(org.apache.parquet.column.ColumnDescriptor descriptor) |
static boolean |
isValueNull(boolean required,
int definitionLevel,
int maxDefinitionLevel)
For optional fields:
definitionLevel == maxDefinitionLevel => Value is defined
definitionLevel == maxDefinitionLevel - 1 => Value is null
definitionLevel < maxDefinitionLevel - 1 => Value does not exist, because one of its optional parent fields is null
|
static org.apache.parquet.io.ColumnIO |
lookupColumnByName(org.apache.parquet.io.GroupColumnIO groupColumnIO,
String columnName)
Parquet column names are case-sensitive unlike Hive, which converts all column names to lowercase.
|
static List<String> |
nestedColumnPath(Subfield subfield) |
static String |
pushdownColumnNameForSubfield(Subfield subfield) |
public static List<org.apache.parquet.io.PrimitiveColumnIO> getColumns(org.apache.parquet.schema.MessageType fileSchema, org.apache.parquet.schema.MessageType requestedSchema)
public static org.apache.parquet.io.MessageColumnIO getColumnIO(org.apache.parquet.schema.MessageType fileSchema,
org.apache.parquet.schema.MessageType requestedSchema)
public static org.apache.parquet.io.GroupColumnIO getMapKeyValueColumn(org.apache.parquet.io.GroupColumnIO groupColumnIO)
public static org.apache.parquet.io.ColumnIO getArrayElementColumn(org.apache.parquet.io.ColumnIO columnIO)
public static Map<List<String>,RichColumnDescriptor> getDescriptors(org.apache.parquet.schema.MessageType fileSchema, org.apache.parquet.schema.MessageType requestedSchema)
public static Optional<RichColumnDescriptor> getDescriptor(List<org.apache.parquet.io.PrimitiveColumnIO> columns, List<String> path)
public static int getFieldIndex(org.apache.parquet.schema.MessageType fileSchema,
String name)
public static ParquetEncoding getParquetEncoding(org.apache.parquet.column.Encoding encoding)
public static org.apache.parquet.schema.Type getParquetTypeByName(String columnName, org.apache.parquet.schema.GroupType messageType)
public static org.apache.parquet.io.ColumnIO lookupColumnByName(org.apache.parquet.io.GroupColumnIO groupColumnIO,
String columnName)
public static Optional<Type> createDecimalType(RichColumnDescriptor descriptor)
public static boolean isValueNull(boolean required,
int definitionLevel,
int maxDefinitionLevel)
public static long getShortDecimalValue(byte[] bytes)
public static Optional<org.apache.parquet.schema.Type> getSubfieldType(org.apache.parquet.schema.GroupType baseType, String rootName, List<String> nestedColumnPath)
public static boolean isTimeStampMicrosType(org.apache.parquet.column.ColumnDescriptor descriptor)
Copyright © 2012–2022. All rights reserved.