Safe Haskell	Safe-Inferred
Language	Haskell2010

Hydra.Langs.Parquet.Format

Description

A model for the Parquet format. Based on the Thrift-based specification at: | https://github.com/apache/parquet-format/blob/master/src/main/thrift/parquet.thrift

Synopsis

data Type
- = TypeBoolean
- | TypeInt32
- | TypeInt64
- | TypeFloat
- | TypeDouble
- | TypeByteArray
- | TypeFixedLenByteArray
_Type :: Name
_Type_boolean :: Name
_Type_int32 :: Name
_Type_int64 :: Name
_Type_float :: Name
_Type_double :: Name
_Type_byteArray :: Name
_Type_fixedLenByteArray :: Name
data FieldRepetitionType
- = FieldRepetitionTypeRequired
- | FieldRepetitionTypeOptional
- | FieldRepetitionTypeRepeated
_FieldRepetitionType :: Name
_FieldRepetitionType_required :: Name
_FieldRepetitionType_optional :: Name
_FieldRepetitionType_repeated :: Name
data Statistics = Statistics {
- statisticsNullCount :: Maybe Integer
- statisticsDistinctCount :: Maybe Integer
- statisticsMaxValue :: Maybe String
- statisticsMinValue :: Maybe String
}
_Statistics :: Name
_Statistics_nullCount :: Name
_Statistics_distinctCount :: Name
_Statistics_maxValue :: Name
_Statistics_minValue :: Name
data DecimalType = DecimalType {
- decimalTypeScale :: Int
- decimalTypePrecision :: Int
}
_DecimalType :: Name
_DecimalType_scale :: Name
_DecimalType_precision :: Name
data TimeUnit
- = TimeUnitMillis
- | TimeUnitMicros
- | TimeUnitNanos
_TimeUnit :: Name
_TimeUnit_millis :: Name
_TimeUnit_micros :: Name
_TimeUnit_nanos :: Name
data TimestampType = TimestampType {
- timestampTypeIsAdjustedToUtc :: Bool
- timestampTypeUnit :: TimeUnit
}
_TimestampType :: Name
_TimestampType_isAdjustedToUtc :: Name
_TimestampType_unit :: Name
data TimeType = TimeType {
- timeTypeIsAdjustedToUtc :: Bool
- timeTypeUnit :: TimeUnit
}
_TimeType :: Name
_TimeType_isAdjustedToUtc :: Name
_TimeType_unit :: Name
data IntType = IntType {
- intTypeBitWidth :: Int16
- intTypeIsSigned :: Bool
}
_IntType :: Name
_IntType_bitWidth :: Name
_IntType_isSigned :: Name
data LogicalType
- = LogicalTypeString
- | LogicalTypeMap
- | LogicalTypeList
- | LogicalTypeEnum
- | LogicalTypeDecimal DecimalType
- | LogicalTypeDate
- | LogicalTypeTime TimeType
- | LogicalTypeTimestamp TimestampType
- | LogicalTypeInteger IntType
- | LogicalTypeUnknown
- | LogicalTypeJson
- | LogicalTypeBson
- | LogicalTypeUuid
_LogicalType :: Name
_LogicalType_string :: Name
_LogicalType_map :: Name
_LogicalType_list :: Name
_LogicalType_enum :: Name
_LogicalType_decimal :: Name
_LogicalType_date :: Name
_LogicalType_time :: Name
_LogicalType_timestamp :: Name
_LogicalType_integer :: Name
_LogicalType_unknown :: Name
_LogicalType_json :: Name
_LogicalType_bson :: Name
_LogicalType_uuid :: Name
data SchemaElement = SchemaElement {
- schemaElementType :: Maybe Type
- schemaElementTypeLength :: Maybe Int
- schemaElementRepetitionType :: Maybe FieldRepetitionType
- schemaElementName :: String
- schemaElementNumChildren :: Maybe Int
- schemaElementFieldId :: Maybe Int
- schemaElementLogicalType :: Maybe LogicalType
}
_SchemaElement :: Name
_SchemaElement_type :: Name
_SchemaElement_typeLength :: Name
_SchemaElement_repetitionType :: Name
_SchemaElement_name :: Name
_SchemaElement_numChildren :: Name
_SchemaElement_fieldId :: Name
_SchemaElement_logicalType :: Name
data Encoding
- = EncodingPlain
- | EncodingRle
- | EncodingBitPacked
- | EncodingDeltaBinaryPacked
- | EncodingDeltaLengthByteArray
- | EncodingDeltaByteArray
- | EncodingRleDictionary
- | EncodingByteStreamSplit
_Encoding :: Name
_Encoding_plain :: Name
_Encoding_rle :: Name
_Encoding_bitPacked :: Name
_Encoding_deltaBinaryPacked :: Name
_Encoding_deltaLengthByteArray :: Name
_Encoding_deltaByteArray :: Name
_Encoding_rleDictionary :: Name
_Encoding_byteStreamSplit :: Name
data CompressionCodec
- = CompressionCodecUncompressed
- | CompressionCodecSnappy
- | CompressionCodecGzip
- | CompressionCodecLzo
- | CompressionCodecBrotli
- | CompressionCodecZstd
- | CompressionCodecLz4Raw
_CompressionCodec :: Name
_CompressionCodec_uncompressed :: Name
_CompressionCodec_snappy :: Name
_CompressionCodec_gzip :: Name
_CompressionCodec_lzo :: Name
_CompressionCodec_brotli :: Name
_CompressionCodec_zstd :: Name
_CompressionCodec_lz4Raw :: Name
data PageType
- = PageTypeDataPage
- | PageTypeIndexPage
- | PageTypeDictionaryPage
- | PageTypeDataPageV2
_PageType :: Name
_PageType_dataPage :: Name
_PageType_indexPage :: Name
_PageType_dictionaryPage :: Name
_PageType_dataPageV2 :: Name
data BoundaryOrder
- = BoundaryOrderUnordered
- | BoundaryOrderAscending
- | BoundaryOrderDescending
_BoundaryOrder :: Name
_BoundaryOrder_unordered :: Name
_BoundaryOrder_ascending :: Name
_BoundaryOrder_descending :: Name
data DataPageHeader = DataPageHeader {
- dataPageHeaderNumValues :: Int
- dataPageHeaderEncoding :: Encoding
- dataPageHeaderDefinitionLevelEncoding :: Encoding
- dataPageHeaderRepetitionLevelEncoding :: Encoding
- dataPageHeaderStatistics :: Maybe Statistics
}
_DataPageHeader :: Name
_DataPageHeader_numValues :: Name
_DataPageHeader_encoding :: Name
_DataPageHeader_definitionLevelEncoding :: Name
_DataPageHeader_repetitionLevelEncoding :: Name
_DataPageHeader_statistics :: Name
data IndexPageHeader = IndexPageHeader {
}
_IndexPageHeader :: Name
data DictionaryPageHeader = DictionaryPageHeader {
- dictionaryPageHeaderNumValues :: Int
- dictionaryPageHeaderEncoding :: Encoding
- dictionaryPageHeaderIsSorted :: Maybe Bool
}
_DictionaryPageHeader :: Name
_DictionaryPageHeader_numValues :: Name
_DictionaryPageHeader_encoding :: Name
_DictionaryPageHeader_isSorted :: Name
data DataPageHeaderV2 = DataPageHeaderV2 {
- dataPageHeaderV2NumValues :: Int
- dataPageHeaderV2NumNulls :: Int
- dataPageHeaderV2NumRows :: Int
- dataPageHeaderV2Encoding :: Encoding
- dataPageHeaderV2DefinitionLevelsByteLength :: Int
- dataPageHeaderV2RepetitionLevelsByteLength :: Int
- dataPageHeaderV2IsCompressed :: Maybe Bool
- dataPageHeaderV2Statistics :: Maybe Statistics
}
_DataPageHeaderV2 :: Name
_DataPageHeaderV2_numValues :: Name
_DataPageHeaderV2_numNulls :: Name
_DataPageHeaderV2_numRows :: Name
_DataPageHeaderV2_encoding :: Name
_DataPageHeaderV2_definitionLevelsByteLength :: Name
_DataPageHeaderV2_repetitionLevelsByteLength :: Name
_DataPageHeaderV2_isCompressed :: Name
_DataPageHeaderV2_statistics :: Name
data BloomFilterAlgorithm = BloomFilterAlgorithmBlock
_BloomFilterAlgorithm :: Name
_BloomFilterAlgorithm_block :: Name
data BloomFilterHash = BloomFilterHashXxhash
_BloomFilterHash :: Name
_BloomFilterHash_xxhash :: Name
data BloomFilterCompression = BloomFilterCompressionUncompressed
_BloomFilterCompression :: Name
_BloomFilterCompression_uncompressed :: Name
data BloomFilterHeader = BloomFilterHeader {
- bloomFilterHeaderNumBytes :: Int
- bloomFilterHeaderAlgorithm :: BloomFilterAlgorithm
- bloomFilterHeaderHash :: BloomFilterHash
- bloomFilterHeaderCompression :: BloomFilterCompression
}
_BloomFilterHeader :: Name
_BloomFilterHeader_numBytes :: Name
_BloomFilterHeader_algorithm :: Name
_BloomFilterHeader_hash :: Name
_BloomFilterHeader_compression :: Name
data PageHeader = PageHeader {
- pageHeaderType :: PageType
- pageHeaderUncompressedPageSize :: Int
- pageHeaderCompressedPageSize :: Int
- pageHeaderCrc :: Maybe Int
- pageHeaderDataPageHeader :: Maybe DataPageHeader
- pageHeaderIndexPageHeader :: Maybe IndexPageHeader
- pageHeaderDictionaryPageHeader :: Maybe DictionaryPageHeader
- pageHeaderDataPageHeaderV2 :: Maybe DataPageHeaderV2
}
_PageHeader :: Name
_PageHeader_type :: Name
_PageHeader_uncompressedPageSize :: Name
_PageHeader_compressedPageSize :: Name
_PageHeader_crc :: Name
_PageHeader_dataPageHeader :: Name
_PageHeader_indexPageHeader :: Name
_PageHeader_dictionaryPageHeader :: Name
_PageHeader_dataPageHeaderV2 :: Name
data KeyValue = KeyValue {
- keyValueKey :: String
- keyValueValue :: Maybe String
}
_KeyValue :: Name
_KeyValue_key :: Name
_KeyValue_value :: Name
data SortingColumn = SortingColumn {
- sortingColumnColumnIdx :: Int
- sortingColumnDescending :: Bool
- sortingColumnNullsFirst :: Bool
}
_SortingColumn :: Name
_SortingColumn_columnIdx :: Name
_SortingColumn_descending :: Name
_SortingColumn_nullsFirst :: Name
data PageEncodingStats = PageEncodingStats {
- pageEncodingStatsPageType :: PageType
- pageEncodingStatsEncoding :: Encoding
- pageEncodingStatsCount :: Int
}
_PageEncodingStats :: Name
_PageEncodingStats_pageType :: Name
_PageEncodingStats_encoding :: Name
_PageEncodingStats_count :: Name
data ColumnMetaData = ColumnMetaData {
- columnMetaDataType :: Type
- columnMetaDataEncodings :: [Encoding]
- columnMetaDataPathInSchema :: [String]
- columnMetaDataCodec :: CompressionCodec
- columnMetaDataNumValues :: Int64
- columnMetaDataTotalUncompressedSize :: Int64
- columnMetaDataTotalCompressedSize :: Int64
- columnMetaDataKeyValueMetadata :: Maybe [KeyValue]
- columnMetaDataDataPageOffset :: Int64
- columnMetaDataIndexPageOffset :: Maybe Int64
- columnMetaDataDictionaryPageOffset :: Maybe Int64
- columnMetaDataStatistics :: Maybe Statistics
- columnMetaDataEncodingStats :: Maybe [PageEncodingStats]
- columnMetaDataBloomFilterOffset :: Maybe Int64
}
_ColumnMetaData :: Name
_ColumnMetaData_type :: Name
_ColumnMetaData_encodings :: Name
_ColumnMetaData_pathInSchema :: Name
_ColumnMetaData_codec :: Name
_ColumnMetaData_numValues :: Name
_ColumnMetaData_totalUncompressedSize :: Name
_ColumnMetaData_totalCompressedSize :: Name
_ColumnMetaData_keyValueMetadata :: Name
_ColumnMetaData_dataPageOffset :: Name
_ColumnMetaData_indexPageOffset :: Name
_ColumnMetaData_dictionaryPageOffset :: Name
_ColumnMetaData_statistics :: Name
_ColumnMetaData_encodingStats :: Name
_ColumnMetaData_bloomFilterOffset :: Name
data EncryptionWithFooterKey = EncryptionWithFooterKey {
}
_EncryptionWithFooterKey :: Name
data EncryptionWithColumnKey = EncryptionWithColumnKey {
- encryptionWithColumnKeyPathInSchema :: [String]
- encryptionWithColumnKeyKeyMetadata :: Maybe String
}
_EncryptionWithColumnKey :: Name
_EncryptionWithColumnKey_pathInSchema :: Name
_EncryptionWithColumnKey_keyMetadata :: Name
data ColumnCryptoMetaData
- = ColumnCryptoMetaDataEncryptionWithFooterKey EncryptionWithFooterKey
- | ColumnCryptoMetaDataEncryptionWithColumnKey EncryptionWithColumnKey
_ColumnCryptoMetaData :: Name
_ColumnCryptoMetaData_encryptionWithFooterKey :: Name
_ColumnCryptoMetaData_encryptionWithColumnKey :: Name
data ColumnChunk = ColumnChunk {
- columnChunkFilePath :: Maybe String
- columnChunkFileOffset :: Int64
- columnChunkMetaData :: Maybe ColumnMetaData
- columnChunkOffsetIndexOffset :: Maybe Int64
- columnChunkOffsetIndexLength :: Maybe Int
- columnChunkColumnIndexOffset :: Maybe Int64
- columnChunkColumnIndexLength :: Maybe Int
- columnChunkCryptoMetadata :: Maybe ColumnCryptoMetaData
- columnChunkEncryptedColumnMetadata :: Maybe String
}
_ColumnChunk :: Name
_ColumnChunk_filePath :: Name
_ColumnChunk_fileOffset :: Name
_ColumnChunk_metaData :: Name
_ColumnChunk_offsetIndexOffset :: Name
_ColumnChunk_offsetIndexLength :: Name
_ColumnChunk_columnIndexOffset :: Name
_ColumnChunk_columnIndexLength :: Name
_ColumnChunk_cryptoMetadata :: Name
_ColumnChunk_encryptedColumnMetadata :: Name
data RowGroup = RowGroup {
- rowGroupColumns :: [ColumnChunk]
- rowGroupTotalByteSize :: Int64
- rowGroupNumRows :: Int64
- rowGroupSortingColumns :: Maybe [SortingColumn]
- rowGroupFileOffset :: Maybe Int64
- rowGroupTotalCompressedSize :: Maybe Int64
- rowGroupOrdinal :: Maybe Int16
}
_RowGroup :: Name
_RowGroup_columns :: Name
_RowGroup_totalByteSize :: Name
_RowGroup_numRows :: Name
_RowGroup_sortingColumns :: Name
_RowGroup_fileOffset :: Name
_RowGroup_totalCompressedSize :: Name
_RowGroup_ordinal :: Name
data ColumnOrder = ColumnOrderTypeOrder
_ColumnOrder :: Name
_ColumnOrder_typeOrder :: Name
data PageLocation = PageLocation {
- pageLocationOffset :: Int64
- pageLocationCompressedPageSize :: Int
- pageLocationFirstRowIndex :: Int64
}
_PageLocation :: Name
_PageLocation_offset :: Name
_PageLocation_compressedPageSize :: Name
_PageLocation_firstRowIndex :: Name
data OffsetIndex = OffsetIndex {
- offsetIndexPageLocations :: [PageLocation]
}
_OffsetIndex :: Name
_OffsetIndex_pageLocations :: Name
data ColumnIndex = ColumnIndex {
- columnIndexNullPages :: [Bool]
- columnIndexMinValues :: [String]
- columnIndexMaxValues :: [String]
- columnIndexBoundaryOrder :: BoundaryOrder
- columnIndexNullCounts :: Maybe [Int64]
}
_ColumnIndex :: Name
_ColumnIndex_nullPages :: Name
_ColumnIndex_minValues :: Name
_ColumnIndex_maxValues :: Name
_ColumnIndex_boundaryOrder :: Name
_ColumnIndex_nullCounts :: Name
data AesGcmV1 = AesGcmV1 {
- aesGcmV1AadPrefix :: Maybe String
- aesGcmV1AadFileUnique :: Maybe String
- aesGcmV1SupplyAadPrefix :: Maybe Bool
}
_AesGcmV1 :: Name
_AesGcmV1_aadPrefix :: Name
_AesGcmV1_aadFileUnique :: Name
_AesGcmV1_supplyAadPrefix :: Name
data AesGcmCtrV1 = AesGcmCtrV1 {
- aesGcmCtrV1AadPrefix :: Maybe String
- aesGcmCtrV1AadFileUnique :: Maybe String
- aesGcmCtrV1SupplyAadPrefix :: Maybe Bool
}
_AesGcmCtrV1 :: Name
_AesGcmCtrV1_aadPrefix :: Name
_AesGcmCtrV1_aadFileUnique :: Name
_AesGcmCtrV1_supplyAadPrefix :: Name
data EncryptionAlgorithm
- = EncryptionAlgorithmAesGcmV1 AesGcmV1
- | EncryptionAlgorithmAesGcmCtrV1 AesGcmCtrV1
_EncryptionAlgorithm :: Name
_EncryptionAlgorithm_aesGcmV1 :: Name
_EncryptionAlgorithm_aesGcmCtrV1 :: Name
data FileMetaData = FileMetaData {
- fileMetaDataVersion :: Int
- fileMetaDataSchema :: [SchemaElement]
- fileMetaDataNumRows :: Int64
- fileMetaDataRowGroups :: [RowGroup]
- fileMetaDataKeyValueMetadata :: Maybe [KeyValue]
- fileMetaDataCreatedBy :: Maybe String
- fileMetaDataColumnOrders :: Maybe [ColumnOrder]
- fileMetaDataEncryptionAlgorithm :: Maybe EncryptionAlgorithm
- fileMetaDataFooterSigningKeyMetadata :: Maybe String
}
_FileMetaData :: Name
_FileMetaData_version :: Name
_FileMetaData_schema :: Name
_FileMetaData_numRows :: Name
_FileMetaData_rowGroups :: Name
_FileMetaData_keyValueMetadata :: Name
_FileMetaData_createdBy :: Name
_FileMetaData_columnOrders :: Name
_FileMetaData_encryptionAlgorithm :: Name
_FileMetaData_footerSigningKeyMetadata :: Name
data FileCryptoMetaData = FileCryptoMetaData {
- fileCryptoMetaDataEncryptionAlgorithm :: EncryptionAlgorithm
- fileCryptoMetaDataKeyMetadata :: Maybe String
}
_FileCryptoMetaData :: Name
_FileCryptoMetaData_encryptionAlgorithm :: Name
_FileCryptoMetaData_keyMetadata :: Name

Documentation

data Type Source #

Types supported by Parquet. These types are intended to be used in combination with the encodings to control the on disk storage format. For example INT16 is not included as a type since a good encoding of INT32 would handle this.

Constructors

TypeBoolean
TypeInt32
TypeInt64
TypeFloat
TypeDouble
TypeByteArray
TypeFixedLenByteArray

Instances

Instances details

Read Type Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS Type # readList :: ReadS [Type] # readPrec :: ReadPrec Type # readListPrec :: ReadPrec [Type] #
Show Type Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> Type -> ShowS # show :: Type -> String # showList :: [Type] -> ShowS #
Eq Type Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: Type -> Type -> Bool # (/=) :: Type -> Type -> Bool #
Ord Type Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: Type -> Type -> Ordering # (<) :: Type -> Type -> Bool # (<=) :: Type -> Type -> Bool # (>) :: Type -> Type -> Bool # (>=) :: Type -> Type -> Bool # max :: Type -> Type -> Type # min :: Type -> Type -> Type #

_Type :: Name Source #

_Type_boolean :: Name Source #

_Type_int32 :: Name Source #

_Type_int64 :: Name Source #

_Type_float :: Name Source #

_Type_double :: Name Source #

_Type_byteArray :: Name Source #

_Type_fixedLenByteArray :: Name Source #

data FieldRepetitionType Source #

Representation of Schemas

Constructors

FieldRepetitionTypeRequired	This field is required (can not be null) and each record has exactly 1 value.
FieldRepetitionTypeOptional	The field is optional (can be null) and each record has 0 or 1 values.
FieldRepetitionTypeRepeated	The field is repeated and can contain 0 or more values

Instances

Instances details

Read FieldRepetitionType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS FieldRepetitionType # readList :: ReadS [FieldRepetitionType] # readPrec :: ReadPrec FieldRepetitionType # readListPrec :: ReadPrec [FieldRepetitionType] #
Show FieldRepetitionType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> FieldRepetitionType -> ShowS # show :: FieldRepetitionType -> String # showList :: [FieldRepetitionType] -> ShowS #
Eq FieldRepetitionType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: FieldRepetitionType -> FieldRepetitionType -> Bool # (/=) :: FieldRepetitionType -> FieldRepetitionType -> Bool #
Ord FieldRepetitionType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: FieldRepetitionType -> FieldRepetitionType -> Ordering # (<) :: FieldRepetitionType -> FieldRepetitionType -> Bool # (<=) :: FieldRepetitionType -> FieldRepetitionType -> Bool # (>) :: FieldRepetitionType -> FieldRepetitionType -> Bool # (>=) :: FieldRepetitionType -> FieldRepetitionType -> Bool # max :: FieldRepetitionType -> FieldRepetitionType -> FieldRepetitionType # min :: FieldRepetitionType -> FieldRepetitionType -> FieldRepetitionType #

_FieldRepetitionType :: Name Source #

_FieldRepetitionType_required :: Name Source #

_FieldRepetitionType_optional :: Name Source #

_FieldRepetitionType_repeated :: Name Source #

data Statistics Source #

Statistics per row group and per page. All fields are optional.

Constructors

Statistics

Fields

statisticsNullCount :: Maybe Integer
statisticsDistinctCount :: Maybe Integer
statisticsMaxValue :: Maybe String
Max value for the column, determined by its ColumnOrder. Values are encoded using PLAIN encoding, except that variable-length byte arrays do not include a length prefix.
statisticsMinValue :: Maybe String
Max value for the column, determined by its ColumnOrder. Values are encoded using PLAIN encoding, except that variable-length byte arrays do not include a length prefix.

Instances

Instances details

Read Statistics Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS Statistics # readList :: ReadS [Statistics] # readPrec :: ReadPrec Statistics # readListPrec :: ReadPrec [Statistics] #
Show Statistics Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> Statistics -> ShowS # show :: Statistics -> String # showList :: [Statistics] -> ShowS #
Eq Statistics Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: Statistics -> Statistics -> Bool # (/=) :: Statistics -> Statistics -> Bool #
Ord Statistics Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: Statistics -> Statistics -> Ordering # (<) :: Statistics -> Statistics -> Bool # (<=) :: Statistics -> Statistics -> Bool # (>) :: Statistics -> Statistics -> Bool # (>=) :: Statistics -> Statistics -> Bool # max :: Statistics -> Statistics -> Statistics # min :: Statistics -> Statistics -> Statistics #

_Statistics :: Name Source #

_Statistics_nullCount :: Name Source #

_Statistics_distinctCount :: Name Source #

_Statistics_maxValue :: Name Source #

_Statistics_minValue :: Name Source #

data DecimalType Source #

Decimal logical type annotation. To maintain forward-compatibility in v1, implementations using this logical type must also set scale and precision on the annotated SchemaElement. Allowed for physical types: INT32, INT64, FIXED, and BINARY

Constructors

DecimalType
Fields decimalTypeScale :: Int decimalTypePrecision :: Int

Instances

Instances details

Read DecimalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS DecimalType # readList :: ReadS [DecimalType] # readPrec :: ReadPrec DecimalType # readListPrec :: ReadPrec [DecimalType] #
Show DecimalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> DecimalType -> ShowS # show :: DecimalType -> String # showList :: [DecimalType] -> ShowS #
Eq DecimalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: DecimalType -> DecimalType -> Bool # (/=) :: DecimalType -> DecimalType -> Bool #
Ord DecimalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: DecimalType -> DecimalType -> Ordering # (<) :: DecimalType -> DecimalType -> Bool # (<=) :: DecimalType -> DecimalType -> Bool # (>) :: DecimalType -> DecimalType -> Bool # (>=) :: DecimalType -> DecimalType -> Bool # max :: DecimalType -> DecimalType -> DecimalType # min :: DecimalType -> DecimalType -> DecimalType #

_DecimalType :: Name Source #

_DecimalType_scale :: Name Source #

_DecimalType_precision :: Name Source #

data TimeUnit Source #

Constructors

TimeUnitMillis
TimeUnitMicros
TimeUnitNanos

Instances

Instances details

Read TimeUnit Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS TimeUnit # readList :: ReadS [TimeUnit] # readPrec :: ReadPrec TimeUnit # readListPrec :: ReadPrec [TimeUnit] #
Show TimeUnit Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> TimeUnit -> ShowS # show :: TimeUnit -> String # showList :: [TimeUnit] -> ShowS #
Eq TimeUnit Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: TimeUnit -> TimeUnit -> Bool # (/=) :: TimeUnit -> TimeUnit -> Bool #
Ord TimeUnit Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: TimeUnit -> TimeUnit -> Ordering # (<) :: TimeUnit -> TimeUnit -> Bool # (<=) :: TimeUnit -> TimeUnit -> Bool # (>) :: TimeUnit -> TimeUnit -> Bool # (>=) :: TimeUnit -> TimeUnit -> Bool # max :: TimeUnit -> TimeUnit -> TimeUnit # min :: TimeUnit -> TimeUnit -> TimeUnit #

_TimeUnit :: Name Source #

_TimeUnit_millis :: Name Source #

_TimeUnit_micros :: Name Source #

_TimeUnit_nanos :: Name Source #

data TimestampType Source #

Timestamp logical type annotation. Allowed for physical types: INT64

Constructors

TimestampType
Fields timestampTypeIsAdjustedToUtc :: Bool timestampTypeUnit :: TimeUnit

Instances

Instances details

Read TimestampType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS TimestampType # readList :: ReadS [TimestampType] # readPrec :: ReadPrec TimestampType # readListPrec :: ReadPrec [TimestampType] #
Show TimestampType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> TimestampType -> ShowS # show :: TimestampType -> String # showList :: [TimestampType] -> ShowS #
Eq TimestampType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: TimestampType -> TimestampType -> Bool # (/=) :: TimestampType -> TimestampType -> Bool #
Ord TimestampType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: TimestampType -> TimestampType -> Ordering # (<) :: TimestampType -> TimestampType -> Bool # (<=) :: TimestampType -> TimestampType -> Bool # (>) :: TimestampType -> TimestampType -> Bool # (>=) :: TimestampType -> TimestampType -> Bool # max :: TimestampType -> TimestampType -> TimestampType # min :: TimestampType -> TimestampType -> TimestampType #

_TimestampType :: Name Source #

_TimestampType_isAdjustedToUtc :: Name Source #

_TimestampType_unit :: Name Source #

data TimeType Source #

Time logical type annotation. Allowed for physical types: INT32 (millis), INT64 (micros, nanos)

Constructors

TimeType
Fields timeTypeIsAdjustedToUtc :: Bool timeTypeUnit :: TimeUnit

Instances

Instances details

Read TimeType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS TimeType # readList :: ReadS [TimeType] # readPrec :: ReadPrec TimeType # readListPrec :: ReadPrec [TimeType] #
Show TimeType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> TimeType -> ShowS # show :: TimeType -> String # showList :: [TimeType] -> ShowS #
Eq TimeType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: TimeType -> TimeType -> Bool # (/=) :: TimeType -> TimeType -> Bool #
Ord TimeType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: TimeType -> TimeType -> Ordering # (<) :: TimeType -> TimeType -> Bool # (<=) :: TimeType -> TimeType -> Bool # (>) :: TimeType -> TimeType -> Bool # (>=) :: TimeType -> TimeType -> Bool # max :: TimeType -> TimeType -> TimeType # min :: TimeType -> TimeType -> TimeType #

_TimeType :: Name Source #

_TimeType_isAdjustedToUtc :: Name Source #

_TimeType_unit :: Name Source #

data IntType Source #

Integer logical type annotation. bitWidth must be 8, 16, 32, or 64. Allowed for physical types: INT32, INT64

Constructors

IntType
Fields intTypeBitWidth :: Int16 intTypeIsSigned :: Bool

Instances

Instances details

Read IntType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS IntType # readList :: ReadS [IntType] # readPrec :: ReadPrec IntType # readListPrec :: ReadPrec [IntType] #
Show IntType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> IntType -> ShowS # show :: IntType -> String # showList :: [IntType] -> ShowS #
Eq IntType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: IntType -> IntType -> Bool # (/=) :: IntType -> IntType -> Bool #
Ord IntType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: IntType -> IntType -> Ordering # (<) :: IntType -> IntType -> Bool # (<=) :: IntType -> IntType -> Bool # (>) :: IntType -> IntType -> Bool # (>=) :: IntType -> IntType -> Bool # max :: IntType -> IntType -> IntType # min :: IntType -> IntType -> IntType #

_IntType :: Name Source #

_IntType_bitWidth :: Name Source #

_IntType_isSigned :: Name Source #

data LogicalType Source #

LogicalType annotations to replace ConvertedType. To maintain compatibility, implementations using LogicalType for a SchemaElement aust also set the corresponding ConvertedType (if any) from the following table.

Constructors

LogicalTypeString	use ConvertedType UTF8
LogicalTypeMap	use ConvertedType MAP
LogicalTypeList	use ConvertedType LIST
LogicalTypeEnum	use ConvertedType ENUM
LogicalTypeDecimal DecimalType	use ConvertedType DECIMAL + SchemaElement.{scale, precision}
LogicalTypeDate	use ConvertedType DATE
LogicalTypeTime TimeType	use ConvertedType TIME_MICROS for TIME(isAdjustedToUTC = , unit = MICROS). use ConvertedType TIME_MILLIS for TIME(isAdjustedToUTC = , unit = MILLIS)
LogicalTypeTimestamp TimestampType	use ConvertedType TIMESTAMP_MICROS for TIMESTAMP(isAdjustedToUTC = , unit = MICROS). use ConvertedType TIMESTAMP_MILLIS for TIMESTAMP(isAdjustedToUTC = , unit = MILLIS)
LogicalTypeInteger IntType	use ConvertedType INT_* or UINT_*
LogicalTypeUnknown	no compatible ConvertedType
LogicalTypeJson	use ConvertedType JSON
LogicalTypeBson	use ConvertedType BSON
LogicalTypeUuid	no compatible ConvertedType

Instances

Instances details

Read LogicalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS LogicalType # readList :: ReadS [LogicalType] # readPrec :: ReadPrec LogicalType # readListPrec :: ReadPrec [LogicalType] #
Show LogicalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> LogicalType -> ShowS # show :: LogicalType -> String # showList :: [LogicalType] -> ShowS #
Eq LogicalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: LogicalType -> LogicalType -> Bool # (/=) :: LogicalType -> LogicalType -> Bool #
Ord LogicalType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: LogicalType -> LogicalType -> Ordering # (<) :: LogicalType -> LogicalType -> Bool # (<=) :: LogicalType -> LogicalType -> Bool # (>) :: LogicalType -> LogicalType -> Bool # (>=) :: LogicalType -> LogicalType -> Bool # max :: LogicalType -> LogicalType -> LogicalType # min :: LogicalType -> LogicalType -> LogicalType #

_LogicalType :: Name Source #

_LogicalType_string :: Name Source #

_LogicalType_map :: Name Source #

_LogicalType_list :: Name Source #

_LogicalType_enum :: Name Source #

_LogicalType_decimal :: Name Source #

_LogicalType_date :: Name Source #

_LogicalType_time :: Name Source #

_LogicalType_timestamp :: Name Source #

_LogicalType_integer :: Name Source #

_LogicalType_unknown :: Name Source #

_LogicalType_json :: Name Source #

_LogicalType_bson :: Name Source #

_LogicalType_uuid :: Name Source #

data SchemaElement Source #

Represents a element inside a schema definition. | - if it is a group (inner node) then type is undefined and num_children is defined | - if it is a primitive type (leaf) then type is defined and num_children is undefined | the nodes are listed in depth first traversal order.

Constructors

SchemaElement

Fields

schemaElementType :: Maybe Type
Data type for this field. Not set if the current element is a non-leaf node
schemaElementTypeLength :: Maybe Int
If type is FIXED_LEN_BYTE_ARRAY, this is the byte length of the values. Otherwise, if specified, this is the maximum bit length to store any of the values. (e.g. a low cardinality INT col could have this set to 3). Note that this is in the schema, and therefore fixed for the entire file.
schemaElementRepetitionType :: Maybe FieldRepetitionType
repetition of the field. The root of the schema does not have a repetition_type. All other nodes must have one
schemaElementName :: String
Name of the field in the schema
schemaElementNumChildren :: Maybe Int
Nested fields. Since thrift does not support nested fields, the nesting is flattened to a single list by a depth-first traversal. The children count is used to construct the nested relationship. This field is not set when the element is a primitive type
schemaElementFieldId :: Maybe Int
When the original schema supports field ids, this will save the original field id in the parquet schema
schemaElementLogicalType :: Maybe LogicalType
The logical type of this SchemaElement. LogicalType replaces ConvertedType, but ConvertedType is still required for some logical types to ensure forward-compatibility in format v1.

Instances

Instances details

Read SchemaElement Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS SchemaElement # readList :: ReadS [SchemaElement] # readPrec :: ReadPrec SchemaElement # readListPrec :: ReadPrec [SchemaElement] #
Show SchemaElement Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> SchemaElement -> ShowS # show :: SchemaElement -> String # showList :: [SchemaElement] -> ShowS #
Eq SchemaElement Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: SchemaElement -> SchemaElement -> Bool # (/=) :: SchemaElement -> SchemaElement -> Bool #
Ord SchemaElement Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: SchemaElement -> SchemaElement -> Ordering # (<) :: SchemaElement -> SchemaElement -> Bool # (<=) :: SchemaElement -> SchemaElement -> Bool # (>) :: SchemaElement -> SchemaElement -> Bool # (>=) :: SchemaElement -> SchemaElement -> Bool # max :: SchemaElement -> SchemaElement -> SchemaElement # min :: SchemaElement -> SchemaElement -> SchemaElement #

_SchemaElement :: Name Source #

_SchemaElement_type :: Name Source #

_SchemaElement_typeLength :: Name Source #

_SchemaElement_repetitionType :: Name Source #

_SchemaElement_name :: Name Source #

_SchemaElement_numChildren :: Name Source #

_SchemaElement_fieldId :: Name Source #

_SchemaElement_logicalType :: Name Source #

data Encoding Source #

Encodings supported by Parquet. Not all encodings are valid for all types. These enums are also used to specify the encoding of definition and repetition levels. See the accompanying doc for the details of the more complicated encodings.

Constructors

EncodingPlain	Default encoding. \| BOOLEAN - 1 bit per value. 0 is false; 1 is true. \| INT32 - 4 bytes per value. Stored as little-endian. \| INT64 - 8 bytes per value. Stored as little-endian. \| FLOAT - 4 bytes per value. IEEE. Stored as little-endian. \| DOUBLE - 8 bytes per value. IEEE. Stored as little-endian. \| BYTE_ARRAY - 4 byte length stored as little endian, followed by bytes. \| FIXED_LEN_BYTE_ARRAY - Just the bytes.
EncodingRle	Group packed run length encoding. Usable for definition/repetition levels encoding and Booleans (on one bit: 0 is false; 1 is true.)
EncodingBitPacked	Bit packed encoding. This can only be used if the data has a known max width. Usable for definition/repetition levels encoding.
EncodingDeltaBinaryPacked	Delta encoding for integers. This can be used for int columns and works best on sorted data
EncodingDeltaLengthByteArray	Encoding for byte arrays to separate the length values and the data. The lengths are encoded using DELTA_BINARY_PACKED
EncodingDeltaByteArray	Incremental-encoded byte array. Prefix lengths are encoded using DELTA_BINARY_PACKED. Suffixes are stored as delta length byte arrays.
EncodingRleDictionary	Dictionary encoding: the ids are encoded using the RLE encoding
EncodingByteStreamSplit	Encoding for floating-point data. K byte-streams are created where K is the size in bytes of the data type. The individual bytes of an FP value are scattered to the corresponding stream and the streams are concatenated. This itself does not reduce the size of the data but can lead to better compression afterwards.

Instances

Instances details

Read Encoding Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS Encoding # readList :: ReadS [Encoding] # readPrec :: ReadPrec Encoding # readListPrec :: ReadPrec [Encoding] #
Show Encoding Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> Encoding -> ShowS # show :: Encoding -> String # showList :: [Encoding] -> ShowS #
Eq Encoding Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: Encoding -> Encoding -> Bool # (/=) :: Encoding -> Encoding -> Bool #
Ord Encoding Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: Encoding -> Encoding -> Ordering # (<) :: Encoding -> Encoding -> Bool # (<=) :: Encoding -> Encoding -> Bool # (>) :: Encoding -> Encoding -> Bool # (>=) :: Encoding -> Encoding -> Bool # max :: Encoding -> Encoding -> Encoding # min :: Encoding -> Encoding -> Encoding #

_Encoding :: Name Source #

_Encoding_plain :: Name Source #

_Encoding_rle :: Name Source #

_Encoding_bitPacked :: Name Source #

_Encoding_deltaBinaryPacked :: Name Source #

_Encoding_deltaLengthByteArray :: Name Source #

_Encoding_deltaByteArray :: Name Source #

_Encoding_rleDictionary :: Name Source #

_Encoding_byteStreamSplit :: Name Source #

data CompressionCodec Source #

Supported compression algorithms. Codecs added in format version X.Y can be read by readers based on X.Y and later. Codec support may vary between readers based on the format version and libraries available at runtime. See Compression.md for a detailed specification of these algorithms.

Constructors

CompressionCodecUncompressed
CompressionCodecSnappy
CompressionCodecGzip
CompressionCodecLzo
CompressionCodecBrotli	Added in 2.4
CompressionCodecZstd	Added in 2.4
CompressionCodecLz4Raw	Added in 2.9

Instances

Instances details

Read CompressionCodec Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS CompressionCodec # readList :: ReadS [CompressionCodec] # readPrec :: ReadPrec CompressionCodec # readListPrec :: ReadPrec [CompressionCodec] #
Show CompressionCodec Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> CompressionCodec -> ShowS # show :: CompressionCodec -> String # showList :: [CompressionCodec] -> ShowS #
Eq CompressionCodec Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: CompressionCodec -> CompressionCodec -> Bool # (/=) :: CompressionCodec -> CompressionCodec -> Bool #
Ord CompressionCodec Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: CompressionCodec -> CompressionCodec -> Ordering # (<) :: CompressionCodec -> CompressionCodec -> Bool # (<=) :: CompressionCodec -> CompressionCodec -> Bool # (>) :: CompressionCodec -> CompressionCodec -> Bool # (>=) :: CompressionCodec -> CompressionCodec -> Bool # max :: CompressionCodec -> CompressionCodec -> CompressionCodec # min :: CompressionCodec -> CompressionCodec -> CompressionCodec #

_CompressionCodec :: Name Source #

_CompressionCodec_uncompressed :: Name Source #

_CompressionCodec_snappy :: Name Source #

_CompressionCodec_gzip :: Name Source #

_CompressionCodec_lzo :: Name Source #

_CompressionCodec_brotli :: Name Source #

_CompressionCodec_zstd :: Name Source #

_CompressionCodec_lz4Raw :: Name Source #

data PageType Source #

Constructors

PageTypeDataPage
PageTypeIndexPage
PageTypeDictionaryPage
PageTypeDataPageV2

Instances

Instances details

Read PageType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS PageType # readList :: ReadS [PageType] # readPrec :: ReadPrec PageType # readListPrec :: ReadPrec [PageType] #
Show PageType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> PageType -> ShowS # show :: PageType -> String # showList :: [PageType] -> ShowS #
Eq PageType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: PageType -> PageType -> Bool # (/=) :: PageType -> PageType -> Bool #
Ord PageType Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: PageType -> PageType -> Ordering # (<) :: PageType -> PageType -> Bool # (<=) :: PageType -> PageType -> Bool # (>) :: PageType -> PageType -> Bool # (>=) :: PageType -> PageType -> Bool # max :: PageType -> PageType -> PageType # min :: PageType -> PageType -> PageType #

_PageType :: Name Source #

_PageType_dataPage :: Name Source #

_PageType_indexPage :: Name Source #

_PageType_dictionaryPage :: Name Source #

_PageType_dataPageV2 :: Name Source #

data BoundaryOrder Source #

Enum to annotate whether lists of min/max elements inside ColumnIndex are ordered and if so, in which direction.

Constructors

BoundaryOrderUnordered
BoundaryOrderAscending
BoundaryOrderDescending

Instances

Instances details

Read BoundaryOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS BoundaryOrder # readList :: ReadS [BoundaryOrder] # readPrec :: ReadPrec BoundaryOrder # readListPrec :: ReadPrec [BoundaryOrder] #
Show BoundaryOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> BoundaryOrder -> ShowS # show :: BoundaryOrder -> String # showList :: [BoundaryOrder] -> ShowS #
Eq BoundaryOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: BoundaryOrder -> BoundaryOrder -> Bool # (/=) :: BoundaryOrder -> BoundaryOrder -> Bool #
Ord BoundaryOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: BoundaryOrder -> BoundaryOrder -> Ordering # (<) :: BoundaryOrder -> BoundaryOrder -> Bool # (<=) :: BoundaryOrder -> BoundaryOrder -> Bool # (>) :: BoundaryOrder -> BoundaryOrder -> Bool # (>=) :: BoundaryOrder -> BoundaryOrder -> Bool # max :: BoundaryOrder -> BoundaryOrder -> BoundaryOrder # min :: BoundaryOrder -> BoundaryOrder -> BoundaryOrder #

_BoundaryOrder :: Name Source #

_BoundaryOrder_unordered :: Name Source #

_BoundaryOrder_ascending :: Name Source #

_BoundaryOrder_descending :: Name Source #

data DataPageHeader Source #

Data page header

Constructors

DataPageHeader

Fields

dataPageHeaderNumValues :: Int
Number of values, including NULLs, in this data page.
dataPageHeaderEncoding :: Encoding
Encoding used for this data page
dataPageHeaderDefinitionLevelEncoding :: Encoding
Encoding used for definition levels
dataPageHeaderRepetitionLevelEncoding :: Encoding
Encoding used for repetition levels
dataPageHeaderStatistics :: Maybe Statistics
Optional statistics for the data in this page

Instances

Instances details

Read DataPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS DataPageHeader # readList :: ReadS [DataPageHeader] # readPrec :: ReadPrec DataPageHeader # readListPrec :: ReadPrec [DataPageHeader] #
Show DataPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> DataPageHeader -> ShowS # show :: DataPageHeader -> String # showList :: [DataPageHeader] -> ShowS #
Eq DataPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: DataPageHeader -> DataPageHeader -> Bool # (/=) :: DataPageHeader -> DataPageHeader -> Bool #
Ord DataPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: DataPageHeader -> DataPageHeader -> Ordering # (<) :: DataPageHeader -> DataPageHeader -> Bool # (<=) :: DataPageHeader -> DataPageHeader -> Bool # (>) :: DataPageHeader -> DataPageHeader -> Bool # (>=) :: DataPageHeader -> DataPageHeader -> Bool # max :: DataPageHeader -> DataPageHeader -> DataPageHeader # min :: DataPageHeader -> DataPageHeader -> DataPageHeader #

_DataPageHeader :: Name Source #

_DataPageHeader_numValues :: Name Source #

_DataPageHeader_encoding :: Name Source #

_DataPageHeader_definitionLevelEncoding :: Name Source #

_DataPageHeader_repetitionLevelEncoding :: Name Source #

_DataPageHeader_statistics :: Name Source #

data IndexPageHeader Source #

Constructors

IndexPageHeader

Instances

Instances details

Read IndexPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS IndexPageHeader # readList :: ReadS [IndexPageHeader] # readPrec :: ReadPrec IndexPageHeader # readListPrec :: ReadPrec [IndexPageHeader] #
Show IndexPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> IndexPageHeader -> ShowS # show :: IndexPageHeader -> String # showList :: [IndexPageHeader] -> ShowS #
Eq IndexPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: IndexPageHeader -> IndexPageHeader -> Bool # (/=) :: IndexPageHeader -> IndexPageHeader -> Bool #
Ord IndexPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: IndexPageHeader -> IndexPageHeader -> Ordering # (<) :: IndexPageHeader -> IndexPageHeader -> Bool # (<=) :: IndexPageHeader -> IndexPageHeader -> Bool # (>) :: IndexPageHeader -> IndexPageHeader -> Bool # (>=) :: IndexPageHeader -> IndexPageHeader -> Bool # max :: IndexPageHeader -> IndexPageHeader -> IndexPageHeader # min :: IndexPageHeader -> IndexPageHeader -> IndexPageHeader #

_IndexPageHeader :: Name Source #

data DictionaryPageHeader Source #

The dictionary page must be placed at the first position of the column chunk if it is partly or completely dictionary encoded. At most one dictionary page can be placed in a column chunk.

Constructors

DictionaryPageHeader
Fields dictionaryPageHeaderNumValues :: Int Number of values in the dictionary dictionaryPageHeaderEncoding :: Encoding Encoding using this dictionary page dictionaryPageHeaderIsSorted :: Maybe Bool If true, the entries in the dictionary are sorted in ascending order

Instances

Instances details

Read DictionaryPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS DictionaryPageHeader # readList :: ReadS [DictionaryPageHeader] # readPrec :: ReadPrec DictionaryPageHeader # readListPrec :: ReadPrec [DictionaryPageHeader] #
Show DictionaryPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> DictionaryPageHeader -> ShowS # show :: DictionaryPageHeader -> String # showList :: [DictionaryPageHeader] -> ShowS #
Eq DictionaryPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: DictionaryPageHeader -> DictionaryPageHeader -> Bool # (/=) :: DictionaryPageHeader -> DictionaryPageHeader -> Bool #
Ord DictionaryPageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: DictionaryPageHeader -> DictionaryPageHeader -> Ordering # (<) :: DictionaryPageHeader -> DictionaryPageHeader -> Bool # (<=) :: DictionaryPageHeader -> DictionaryPageHeader -> Bool # (>) :: DictionaryPageHeader -> DictionaryPageHeader -> Bool # (>=) :: DictionaryPageHeader -> DictionaryPageHeader -> Bool # max :: DictionaryPageHeader -> DictionaryPageHeader -> DictionaryPageHeader # min :: DictionaryPageHeader -> DictionaryPageHeader -> DictionaryPageHeader #

_DictionaryPageHeader :: Name Source #

_DictionaryPageHeader_numValues :: Name Source #

_DictionaryPageHeader_encoding :: Name Source #

_DictionaryPageHeader_isSorted :: Name Source #

data DataPageHeaderV2 Source #

New page format allowing reading levels without decompressing the data Repetition and definition levels are uncompressed The remaining section containing the data is compressed if is_compressed is true

Constructors

DataPageHeaderV2

Fields

dataPageHeaderV2NumValues :: Int
Number of values, including NULLs, in this data page.
dataPageHeaderV2NumNulls :: Int
Number of NULL values, in this data page. Number of non-null = num_values - num_nulls which is also the number of values in the data section
dataPageHeaderV2NumRows :: Int
Number of rows in this data page. which means pages change on record boundaries (r = 0)
dataPageHeaderV2Encoding :: Encoding
Encoding used for data in this page
dataPageHeaderV2DefinitionLevelsByteLength :: Int
length of the definition levels
dataPageHeaderV2RepetitionLevelsByteLength :: Int
length of the repetition levels
dataPageHeaderV2IsCompressed :: Maybe Bool
whether the values are compressed. Which means the section of the page between definition_levels_byte_length + repetition_levels_byte_length + 1 and compressed_page_size (included) is compressed with the compression_codec. If missing it is considered compressed
dataPageHeaderV2Statistics :: Maybe Statistics
optional statistics for the data in this page

Instances

Instances details

Read DataPageHeaderV2 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS DataPageHeaderV2 # readList :: ReadS [DataPageHeaderV2] # readPrec :: ReadPrec DataPageHeaderV2 # readListPrec :: ReadPrec [DataPageHeaderV2] #
Show DataPageHeaderV2 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> DataPageHeaderV2 -> ShowS # show :: DataPageHeaderV2 -> String # showList :: [DataPageHeaderV2] -> ShowS #
Eq DataPageHeaderV2 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: DataPageHeaderV2 -> DataPageHeaderV2 -> Bool # (/=) :: DataPageHeaderV2 -> DataPageHeaderV2 -> Bool #
Ord DataPageHeaderV2 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: DataPageHeaderV2 -> DataPageHeaderV2 -> Ordering # (<) :: DataPageHeaderV2 -> DataPageHeaderV2 -> Bool # (<=) :: DataPageHeaderV2 -> DataPageHeaderV2 -> Bool # (>) :: DataPageHeaderV2 -> DataPageHeaderV2 -> Bool # (>=) :: DataPageHeaderV2 -> DataPageHeaderV2 -> Bool # max :: DataPageHeaderV2 -> DataPageHeaderV2 -> DataPageHeaderV2 # min :: DataPageHeaderV2 -> DataPageHeaderV2 -> DataPageHeaderV2 #

_DataPageHeaderV2 :: Name Source #

_DataPageHeaderV2_numValues :: Name Source #

_DataPageHeaderV2_numNulls :: Name Source #

_DataPageHeaderV2_numRows :: Name Source #

_DataPageHeaderV2_encoding :: Name Source #

_DataPageHeaderV2_definitionLevelsByteLength :: Name Source #

_DataPageHeaderV2_repetitionLevelsByteLength :: Name Source #

_DataPageHeaderV2_isCompressed :: Name Source #

_DataPageHeaderV2_statistics :: Name Source #

data BloomFilterAlgorithm Source #

The algorithm used in Bloom filter.

Constructors

BloomFilterAlgorithmBlock

Block-based Bloom filter.

Instances

Instances details

Read BloomFilterAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS BloomFilterAlgorithm # readList :: ReadS [BloomFilterAlgorithm] # readPrec :: ReadPrec BloomFilterAlgorithm # readListPrec :: ReadPrec [BloomFilterAlgorithm] #
Show BloomFilterAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> BloomFilterAlgorithm -> ShowS # show :: BloomFilterAlgorithm -> String # showList :: [BloomFilterAlgorithm] -> ShowS #
Eq BloomFilterAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Bool # (/=) :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Bool #
Ord BloomFilterAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Ordering # (<) :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Bool # (<=) :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Bool # (>) :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Bool # (>=) :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> Bool # max :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> BloomFilterAlgorithm # min :: BloomFilterAlgorithm -> BloomFilterAlgorithm -> BloomFilterAlgorithm #

_BloomFilterAlgorithm :: Name Source #

_BloomFilterAlgorithm_block :: Name Source #

data BloomFilterHash Source #

The hash function used in Bloom filter. This function takes the hash of a column value using plain encoding.

Constructors

BloomFilterHashXxhash

xxHash Strategy.

Instances

Instances details

Read BloomFilterHash Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS BloomFilterHash # readList :: ReadS [BloomFilterHash] # readPrec :: ReadPrec BloomFilterHash # readListPrec :: ReadPrec [BloomFilterHash] #
Show BloomFilterHash Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> BloomFilterHash -> ShowS # show :: BloomFilterHash -> String # showList :: [BloomFilterHash] -> ShowS #
Eq BloomFilterHash Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: BloomFilterHash -> BloomFilterHash -> Bool # (/=) :: BloomFilterHash -> BloomFilterHash -> Bool #
Ord BloomFilterHash Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: BloomFilterHash -> BloomFilterHash -> Ordering # (<) :: BloomFilterHash -> BloomFilterHash -> Bool # (<=) :: BloomFilterHash -> BloomFilterHash -> Bool # (>) :: BloomFilterHash -> BloomFilterHash -> Bool # (>=) :: BloomFilterHash -> BloomFilterHash -> Bool # max :: BloomFilterHash -> BloomFilterHash -> BloomFilterHash # min :: BloomFilterHash -> BloomFilterHash -> BloomFilterHash #

_BloomFilterHash :: Name Source #

_BloomFilterHash_xxhash :: Name Source #

data BloomFilterCompression Source #

The compression used in the Bloom filter.

Constructors

BloomFilterCompressionUncompressed

Instances

Instances details

Read BloomFilterCompression Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS BloomFilterCompression # readList :: ReadS [BloomFilterCompression] # readPrec :: ReadPrec BloomFilterCompression # readListPrec :: ReadPrec [BloomFilterCompression] #
Show BloomFilterCompression Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> BloomFilterCompression -> ShowS # show :: BloomFilterCompression -> String # showList :: [BloomFilterCompression] -> ShowS #
Eq BloomFilterCompression Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: BloomFilterCompression -> BloomFilterCompression -> Bool # (/=) :: BloomFilterCompression -> BloomFilterCompression -> Bool #
Ord BloomFilterCompression Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: BloomFilterCompression -> BloomFilterCompression -> Ordering # (<) :: BloomFilterCompression -> BloomFilterCompression -> Bool # (<=) :: BloomFilterCompression -> BloomFilterCompression -> Bool # (>) :: BloomFilterCompression -> BloomFilterCompression -> Bool # (>=) :: BloomFilterCompression -> BloomFilterCompression -> Bool # max :: BloomFilterCompression -> BloomFilterCompression -> BloomFilterCompression # min :: BloomFilterCompression -> BloomFilterCompression -> BloomFilterCompression #

_BloomFilterCompression :: Name Source #

_BloomFilterCompression_uncompressed :: Name Source #

data BloomFilterHeader Source #

Bloom filter header is stored at beginning of Bloom filter data of each column and followed by its bitset.

Constructors

BloomFilterHeader
Fields bloomFilterHeaderNumBytes :: Int The size of bitset in bytes bloomFilterHeaderAlgorithm :: BloomFilterAlgorithm The algorithm for setting bits. bloomFilterHeaderHash :: BloomFilterHash The hash function used for Bloom filter. bloomFilterHeaderCompression :: BloomFilterCompression The compression used in the Bloom filter

Instances

Instances details

Read BloomFilterHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS BloomFilterHeader # readList :: ReadS [BloomFilterHeader] # readPrec :: ReadPrec BloomFilterHeader # readListPrec :: ReadPrec [BloomFilterHeader] #
Show BloomFilterHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> BloomFilterHeader -> ShowS # show :: BloomFilterHeader -> String # showList :: [BloomFilterHeader] -> ShowS #
Eq BloomFilterHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: BloomFilterHeader -> BloomFilterHeader -> Bool # (/=) :: BloomFilterHeader -> BloomFilterHeader -> Bool #
Ord BloomFilterHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: BloomFilterHeader -> BloomFilterHeader -> Ordering # (<) :: BloomFilterHeader -> BloomFilterHeader -> Bool # (<=) :: BloomFilterHeader -> BloomFilterHeader -> Bool # (>) :: BloomFilterHeader -> BloomFilterHeader -> Bool # (>=) :: BloomFilterHeader -> BloomFilterHeader -> Bool # max :: BloomFilterHeader -> BloomFilterHeader -> BloomFilterHeader # min :: BloomFilterHeader -> BloomFilterHeader -> BloomFilterHeader #

_BloomFilterHeader :: Name Source #

_BloomFilterHeader_numBytes :: Name Source #

_BloomFilterHeader_algorithm :: Name Source #

_BloomFilterHeader_hash :: Name Source #

_BloomFilterHeader_compression :: Name Source #

data PageHeader Source #

Constructors

PageHeader

Fields

pageHeaderType :: PageType
the type of the page: indicates which of the *_header fields is set
pageHeaderUncompressedPageSize :: Int
Uncompressed page size in bytes (not including this header)
pageHeaderCompressedPageSize :: Int
Compressed (and potentially encrypted) page size in bytes, not including this header
pageHeaderCrc :: Maybe Int
The 32bit CRC for the page, to be be calculated as follows: | - Using the standard CRC32 algorithm | - On the data only, i.e. this header should not be included. Data | hereby refers to the concatenation of the repetition levels, the | definition levels and the column value, in this exact order. | - On the encoded versions of the repetition levels, definition levels and | column values | - On the compressed versions of the repetition levels, definition levels | and column values where possible; | - For v1 data pages, the repetition levels, definition levels and column | values are always compressed together. If a compression scheme is | specified, the CRC shall be calculated on the compressed version of | this concatenation. If no compression scheme is specified, the CRC | shall be calculated on the uncompressed version of this concatenation. | - For v2 data pages, the repetition levels and definition levels are | handled separately from the data and are never compressed (only | encoded). If a compression scheme is specified, the CRC shall be | calculated on the concatenation of the uncompressed repetition levels, | uncompressed definition levels and the compressed column values. | If no compression scheme is specified, the CRC shall be calculated on | the uncompressed concatenation. | - In encrypted columns, CRC is calculated after page encryption; the | encryption itself is performed after page compression (if compressed) | If enabled, this allows for disabling checksumming in HDFS if only a few pages need to be read.
pageHeaderDataPageHeader :: Maybe DataPageHeader
pageHeaderIndexPageHeader :: Maybe IndexPageHeader
pageHeaderDictionaryPageHeader :: Maybe DictionaryPageHeader
pageHeaderDataPageHeaderV2 :: Maybe DataPageHeaderV2

Instances

Instances details

Read PageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS PageHeader # readList :: ReadS [PageHeader] # readPrec :: ReadPrec PageHeader # readListPrec :: ReadPrec [PageHeader] #
Show PageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> PageHeader -> ShowS # show :: PageHeader -> String # showList :: [PageHeader] -> ShowS #
Eq PageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: PageHeader -> PageHeader -> Bool # (/=) :: PageHeader -> PageHeader -> Bool #
Ord PageHeader Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: PageHeader -> PageHeader -> Ordering # (<) :: PageHeader -> PageHeader -> Bool # (<=) :: PageHeader -> PageHeader -> Bool # (>) :: PageHeader -> PageHeader -> Bool # (>=) :: PageHeader -> PageHeader -> Bool # max :: PageHeader -> PageHeader -> PageHeader # min :: PageHeader -> PageHeader -> PageHeader #

_PageHeader :: Name Source #

_PageHeader_type :: Name Source #

_PageHeader_uncompressedPageSize :: Name Source #

_PageHeader_compressedPageSize :: Name Source #

_PageHeader_crc :: Name Source #

_PageHeader_dataPageHeader :: Name Source #

_PageHeader_indexPageHeader :: Name Source #

_PageHeader_dictionaryPageHeader :: Name Source #

_PageHeader_dataPageHeaderV2 :: Name Source #

data KeyValue Source #

Wrapper struct to store key values

Constructors

KeyValue
Fields keyValueKey :: String keyValueValue :: Maybe String

Instances

Instances details

Read KeyValue Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS KeyValue # readList :: ReadS [KeyValue] # readPrec :: ReadPrec KeyValue # readListPrec :: ReadPrec [KeyValue] #
Show KeyValue Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> KeyValue -> ShowS # show :: KeyValue -> String # showList :: [KeyValue] -> ShowS #
Eq KeyValue Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: KeyValue -> KeyValue -> Bool # (/=) :: KeyValue -> KeyValue -> Bool #
Ord KeyValue Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: KeyValue -> KeyValue -> Ordering # (<) :: KeyValue -> KeyValue -> Bool # (<=) :: KeyValue -> KeyValue -> Bool # (>) :: KeyValue -> KeyValue -> Bool # (>=) :: KeyValue -> KeyValue -> Bool # max :: KeyValue -> KeyValue -> KeyValue # min :: KeyValue -> KeyValue -> KeyValue #

_KeyValue :: Name Source #

_KeyValue_key :: Name Source #

_KeyValue_value :: Name Source #

data SortingColumn Source #

Wrapper struct to specify sort order

Constructors

SortingColumn
Fields sortingColumnColumnIdx :: Int The column index (in this row group) sortingColumnDescending :: Bool If true, indicates this column is sorted in descending order. sortingColumnNullsFirst :: Bool If true, nulls will come before non-null values, otherwise, nulls go at the end.

Instances

Instances details

Read SortingColumn Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS SortingColumn # readList :: ReadS [SortingColumn] # readPrec :: ReadPrec SortingColumn # readListPrec :: ReadPrec [SortingColumn] #
Show SortingColumn Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> SortingColumn -> ShowS # show :: SortingColumn -> String # showList :: [SortingColumn] -> ShowS #
Eq SortingColumn Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: SortingColumn -> SortingColumn -> Bool # (/=) :: SortingColumn -> SortingColumn -> Bool #
Ord SortingColumn Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: SortingColumn -> SortingColumn -> Ordering # (<) :: SortingColumn -> SortingColumn -> Bool # (<=) :: SortingColumn -> SortingColumn -> Bool # (>) :: SortingColumn -> SortingColumn -> Bool # (>=) :: SortingColumn -> SortingColumn -> Bool # max :: SortingColumn -> SortingColumn -> SortingColumn # min :: SortingColumn -> SortingColumn -> SortingColumn #

_SortingColumn :: Name Source #

_SortingColumn_columnIdx :: Name Source #

_SortingColumn_descending :: Name Source #

_SortingColumn_nullsFirst :: Name Source #

data PageEncodingStats Source #

statistics of a given page type and encoding

Constructors

PageEncodingStats
Fields pageEncodingStatsPageType :: PageType the page type (datadic...) pageEncodingStatsEncoding :: Encoding encoding of the page pageEncodingStatsCount :: Int number of pages of this type with this encoding

Instances

Instances details

Read PageEncodingStats Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS PageEncodingStats # readList :: ReadS [PageEncodingStats] # readPrec :: ReadPrec PageEncodingStats # readListPrec :: ReadPrec [PageEncodingStats] #
Show PageEncodingStats Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> PageEncodingStats -> ShowS # show :: PageEncodingStats -> String # showList :: [PageEncodingStats] -> ShowS #
Eq PageEncodingStats Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: PageEncodingStats -> PageEncodingStats -> Bool # (/=) :: PageEncodingStats -> PageEncodingStats -> Bool #
Ord PageEncodingStats Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: PageEncodingStats -> PageEncodingStats -> Ordering # (<) :: PageEncodingStats -> PageEncodingStats -> Bool # (<=) :: PageEncodingStats -> PageEncodingStats -> Bool # (>) :: PageEncodingStats -> PageEncodingStats -> Bool # (>=) :: PageEncodingStats -> PageEncodingStats -> Bool # max :: PageEncodingStats -> PageEncodingStats -> PageEncodingStats # min :: PageEncodingStats -> PageEncodingStats -> PageEncodingStats #

_PageEncodingStats :: Name Source #

_PageEncodingStats_pageType :: Name Source #

_PageEncodingStats_encoding :: Name Source #

_PageEncodingStats_count :: Name Source #

data ColumnMetaData Source #

Description for column metadata

Constructors

ColumnMetaData

Fields

columnMetaDataType :: Type
Type of this column
columnMetaDataEncodings :: [Encoding]
Set of all encodings used for this column. The purpose is to validate whether we can decode those pages.
columnMetaDataPathInSchema :: [String]
Path in schema
columnMetaDataCodec :: CompressionCodec
Compression codec
columnMetaDataNumValues :: Int64
Number of values in this column
columnMetaDataTotalUncompressedSize :: Int64
total byte size of all uncompressed pages in this column chunk (including the headers)
columnMetaDataTotalCompressedSize :: Int64
total byte size of all compressed, and potentially encrypted, pages in this column chunk (including the headers)
columnMetaDataKeyValueMetadata :: Maybe [KeyValue]
Optional key/value metadata
columnMetaDataDataPageOffset :: Int64
Byte offset from beginning of file to first data page
columnMetaDataIndexPageOffset :: Maybe Int64
Byte offset from beginning of file to root index page
columnMetaDataDictionaryPageOffset :: Maybe Int64
Byte offset from the beginning of file to first (only) dictionary page
columnMetaDataStatistics :: Maybe Statistics
optional statistics for this column chunk
columnMetaDataEncodingStats :: Maybe [PageEncodingStats]
Set of all encodings used for pages in this column chunk. This information can be used to determine if all data pages are dictionary encoded for example
columnMetaDataBloomFilterOffset :: Maybe Int64
Byte offset from beginning of file to Bloom filter data.

Instances

Instances details

Read ColumnMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS ColumnMetaData # readList :: ReadS [ColumnMetaData] # readPrec :: ReadPrec ColumnMetaData # readListPrec :: ReadPrec [ColumnMetaData] #
Show ColumnMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> ColumnMetaData -> ShowS # show :: ColumnMetaData -> String # showList :: [ColumnMetaData] -> ShowS #
Eq ColumnMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: ColumnMetaData -> ColumnMetaData -> Bool # (/=) :: ColumnMetaData -> ColumnMetaData -> Bool #
Ord ColumnMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: ColumnMetaData -> ColumnMetaData -> Ordering # (<) :: ColumnMetaData -> ColumnMetaData -> Bool # (<=) :: ColumnMetaData -> ColumnMetaData -> Bool # (>) :: ColumnMetaData -> ColumnMetaData -> Bool # (>=) :: ColumnMetaData -> ColumnMetaData -> Bool # max :: ColumnMetaData -> ColumnMetaData -> ColumnMetaData # min :: ColumnMetaData -> ColumnMetaData -> ColumnMetaData #

_ColumnMetaData :: Name Source #

_ColumnMetaData_type :: Name Source #

_ColumnMetaData_encodings :: Name Source #

_ColumnMetaData_pathInSchema :: Name Source #

_ColumnMetaData_codec :: Name Source #

_ColumnMetaData_numValues :: Name Source #

_ColumnMetaData_totalUncompressedSize :: Name Source #

_ColumnMetaData_totalCompressedSize :: Name Source #

_ColumnMetaData_keyValueMetadata :: Name Source #

_ColumnMetaData_dataPageOffset :: Name Source #

_ColumnMetaData_indexPageOffset :: Name Source #

_ColumnMetaData_dictionaryPageOffset :: Name Source #

_ColumnMetaData_statistics :: Name Source #

_ColumnMetaData_encodingStats :: Name Source #

_ColumnMetaData_bloomFilterOffset :: Name Source #

data EncryptionWithFooterKey Source #

Constructors

EncryptionWithFooterKey

Instances

Instances details

Read EncryptionWithFooterKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS EncryptionWithFooterKey # readList :: ReadS [EncryptionWithFooterKey] # readPrec :: ReadPrec EncryptionWithFooterKey # readListPrec :: ReadPrec [EncryptionWithFooterKey] #
Show EncryptionWithFooterKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> EncryptionWithFooterKey -> ShowS # show :: EncryptionWithFooterKey -> String # showList :: [EncryptionWithFooterKey] -> ShowS #
Eq EncryptionWithFooterKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Bool # (/=) :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Bool #
Ord EncryptionWithFooterKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Ordering # (<) :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Bool # (<=) :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Bool # (>) :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Bool # (>=) :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> Bool # max :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> EncryptionWithFooterKey # min :: EncryptionWithFooterKey -> EncryptionWithFooterKey -> EncryptionWithFooterKey #

_EncryptionWithFooterKey :: Name Source #

data EncryptionWithColumnKey Source #

Constructors

EncryptionWithColumnKey
Fields encryptionWithColumnKeyPathInSchema :: [String] Column path in schema encryptionWithColumnKeyKeyMetadata :: Maybe String Retrieval metadata of column encryption key

Instances

Instances details

Read EncryptionWithColumnKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS EncryptionWithColumnKey # readList :: ReadS [EncryptionWithColumnKey] # readPrec :: ReadPrec EncryptionWithColumnKey # readListPrec :: ReadPrec [EncryptionWithColumnKey] #
Show EncryptionWithColumnKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> EncryptionWithColumnKey -> ShowS # show :: EncryptionWithColumnKey -> String # showList :: [EncryptionWithColumnKey] -> ShowS #
Eq EncryptionWithColumnKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Bool # (/=) :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Bool #
Ord EncryptionWithColumnKey Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Ordering # (<) :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Bool # (<=) :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Bool # (>) :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Bool # (>=) :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> Bool # max :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> EncryptionWithColumnKey # min :: EncryptionWithColumnKey -> EncryptionWithColumnKey -> EncryptionWithColumnKey #

_EncryptionWithColumnKey :: Name Source #

_EncryptionWithColumnKey_pathInSchema :: Name Source #

_EncryptionWithColumnKey_keyMetadata :: Name Source #

data ColumnCryptoMetaData Source #

Constructors

ColumnCryptoMetaDataEncryptionWithFooterKey EncryptionWithFooterKey
ColumnCryptoMetaDataEncryptionWithColumnKey EncryptionWithColumnKey

Instances

Instances details

Read ColumnCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS ColumnCryptoMetaData # readList :: ReadS [ColumnCryptoMetaData] # readPrec :: ReadPrec ColumnCryptoMetaData # readListPrec :: ReadPrec [ColumnCryptoMetaData] #
Show ColumnCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> ColumnCryptoMetaData -> ShowS # show :: ColumnCryptoMetaData -> String # showList :: [ColumnCryptoMetaData] -> ShowS #
Eq ColumnCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Bool # (/=) :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Bool #
Ord ColumnCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Ordering # (<) :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Bool # (<=) :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Bool # (>) :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Bool # (>=) :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> Bool # max :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> ColumnCryptoMetaData # min :: ColumnCryptoMetaData -> ColumnCryptoMetaData -> ColumnCryptoMetaData #

_ColumnCryptoMetaData :: Name Source #

_ColumnCryptoMetaData_encryptionWithFooterKey :: Name Source #

_ColumnCryptoMetaData_encryptionWithColumnKey :: Name Source #

data ColumnChunk Source #

Constructors

ColumnChunk

Fields

columnChunkFilePath :: Maybe String
File where column data is stored. If not set, assumed to be same file as metadata. This path is relative to the current file.
columnChunkFileOffset :: Int64
Byte offset in file_path to the ColumnMetaData
columnChunkMetaData :: Maybe ColumnMetaData
Column metadata for this chunk. This is the same content as what is at file_path/file_offset. Having it here has it replicated in the file metadata.
columnChunkOffsetIndexOffset :: Maybe Int64
File offset of ColumnChunk's OffsetIndex
columnChunkOffsetIndexLength :: Maybe Int
Size of ColumnChunk's OffsetIndex, in bytes
columnChunkColumnIndexOffset :: Maybe Int64
File offset of ColumnChunk's ColumnIndex
columnChunkColumnIndexLength :: Maybe Int
Size of ColumnChunk's ColumnIndex, in bytes
columnChunkCryptoMetadata :: Maybe ColumnCryptoMetaData
Crypto metadata of encrypted columns
columnChunkEncryptedColumnMetadata :: Maybe String
Encrypted column metadata for this chunk

Instances

Instances details

Read ColumnChunk Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS ColumnChunk # readList :: ReadS [ColumnChunk] # readPrec :: ReadPrec ColumnChunk # readListPrec :: ReadPrec [ColumnChunk] #
Show ColumnChunk Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> ColumnChunk -> ShowS # show :: ColumnChunk -> String # showList :: [ColumnChunk] -> ShowS #
Eq ColumnChunk Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: ColumnChunk -> ColumnChunk -> Bool # (/=) :: ColumnChunk -> ColumnChunk -> Bool #
Ord ColumnChunk Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: ColumnChunk -> ColumnChunk -> Ordering # (<) :: ColumnChunk -> ColumnChunk -> Bool # (<=) :: ColumnChunk -> ColumnChunk -> Bool # (>) :: ColumnChunk -> ColumnChunk -> Bool # (>=) :: ColumnChunk -> ColumnChunk -> Bool # max :: ColumnChunk -> ColumnChunk -> ColumnChunk # min :: ColumnChunk -> ColumnChunk -> ColumnChunk #

_ColumnChunk :: Name Source #

_ColumnChunk_filePath :: Name Source #

_ColumnChunk_fileOffset :: Name Source #

_ColumnChunk_metaData :: Name Source #

_ColumnChunk_offsetIndexOffset :: Name Source #

_ColumnChunk_offsetIndexLength :: Name Source #

_ColumnChunk_columnIndexOffset :: Name Source #

_ColumnChunk_columnIndexLength :: Name Source #

_ColumnChunk_cryptoMetadata :: Name Source #

_ColumnChunk_encryptedColumnMetadata :: Name Source #

data RowGroup Source #

Constructors

RowGroup

Fields

rowGroupColumns :: [ColumnChunk]
Metadata for each column chunk in this row group. This list must have the same order as the SchemaElement list in FileMetaData.
rowGroupTotalByteSize :: Int64
Total byte size of all the uncompressed column data in this row group
rowGroupNumRows :: Int64
Number of rows in this row group
rowGroupSortingColumns :: Maybe [SortingColumn]
If set, specifies a sort ordering of the rows in this RowGroup. The sorting columns can be a subset of all the columns.
rowGroupFileOffset :: Maybe Int64
Byte offset from beginning of file to first page (data or dictionary) in this row group
rowGroupTotalCompressedSize :: Maybe Int64
Total byte size of all compressed (and potentially encrypted) column data in this row group
rowGroupOrdinal :: Maybe Int16
Row group ordinal in the file

Instances

Instances details

Read RowGroup Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS RowGroup # readList :: ReadS [RowGroup] # readPrec :: ReadPrec RowGroup # readListPrec :: ReadPrec [RowGroup] #
Show RowGroup Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> RowGroup -> ShowS # show :: RowGroup -> String # showList :: [RowGroup] -> ShowS #
Eq RowGroup Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: RowGroup -> RowGroup -> Bool # (/=) :: RowGroup -> RowGroup -> Bool #
Ord RowGroup Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: RowGroup -> RowGroup -> Ordering # (<) :: RowGroup -> RowGroup -> Bool # (<=) :: RowGroup -> RowGroup -> Bool # (>) :: RowGroup -> RowGroup -> Bool # (>=) :: RowGroup -> RowGroup -> Bool # max :: RowGroup -> RowGroup -> RowGroup # min :: RowGroup -> RowGroup -> RowGroup #

_RowGroup :: Name Source #

_RowGroup_columns :: Name Source #

_RowGroup_totalByteSize :: Name Source #

_RowGroup_numRows :: Name Source #

_RowGroup_sortingColumns :: Name Source #

_RowGroup_fileOffset :: Name Source #

_RowGroup_totalCompressedSize :: Name Source #

_RowGroup_ordinal :: Name Source #

data ColumnOrder Source #

Union to specify the order used for the min_value and max_value fields for a column. This union takes the role of an enhanced enum that allows rich elements (which will be needed for a collation-based ordering in the future). Possible values are: | * TypeDefinedOrder - the column uses the order defined by its logical or physical type (if there is no logical type). | If the reader does not support the value of this union, min and max stats for this column should be ignored.

Constructors

ColumnOrderTypeOrder

Instances

Instances details

Read ColumnOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS ColumnOrder # readList :: ReadS [ColumnOrder] # readPrec :: ReadPrec ColumnOrder # readListPrec :: ReadPrec [ColumnOrder] #
Show ColumnOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> ColumnOrder -> ShowS # show :: ColumnOrder -> String # showList :: [ColumnOrder] -> ShowS #
Eq ColumnOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: ColumnOrder -> ColumnOrder -> Bool # (/=) :: ColumnOrder -> ColumnOrder -> Bool #
Ord ColumnOrder Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: ColumnOrder -> ColumnOrder -> Ordering # (<) :: ColumnOrder -> ColumnOrder -> Bool # (<=) :: ColumnOrder -> ColumnOrder -> Bool # (>) :: ColumnOrder -> ColumnOrder -> Bool # (>=) :: ColumnOrder -> ColumnOrder -> Bool # max :: ColumnOrder -> ColumnOrder -> ColumnOrder # min :: ColumnOrder -> ColumnOrder -> ColumnOrder #

_ColumnOrder :: Name Source #

_ColumnOrder_typeOrder :: Name Source #

data PageLocation Source #

Constructors

PageLocation
Fields pageLocationOffset :: Int64 Offset of the page in the file pageLocationCompressedPageSize :: Int Size of the page, including header. Sum of compressed_page_size and header length pageLocationFirstRowIndex :: Int64 Index within the RowGroup of the first row of the page; this means pages change on record boundaries (r = 0).

Instances

Instances details

Read PageLocation Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS PageLocation # readList :: ReadS [PageLocation] # readPrec :: ReadPrec PageLocation # readListPrec :: ReadPrec [PageLocation] #
Show PageLocation Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> PageLocation -> ShowS # show :: PageLocation -> String # showList :: [PageLocation] -> ShowS #
Eq PageLocation Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: PageLocation -> PageLocation -> Bool # (/=) :: PageLocation -> PageLocation -> Bool #
Ord PageLocation Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: PageLocation -> PageLocation -> Ordering # (<) :: PageLocation -> PageLocation -> Bool # (<=) :: PageLocation -> PageLocation -> Bool # (>) :: PageLocation -> PageLocation -> Bool # (>=) :: PageLocation -> PageLocation -> Bool # max :: PageLocation -> PageLocation -> PageLocation # min :: PageLocation -> PageLocation -> PageLocation #

_PageLocation :: Name Source #

_PageLocation_offset :: Name Source #

_PageLocation_compressedPageSize :: Name Source #

_PageLocation_firstRowIndex :: Name Source #

data OffsetIndex Source #

Constructors

OffsetIndex
Fields offsetIndexPageLocations :: [PageLocation] PageLocations, ordered by increasing PageLocation.offset. It is required that page_locations[i].first_row_index < page_locations[i+1].first_row_index.

Instances

Instances details

Read OffsetIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS OffsetIndex # readList :: ReadS [OffsetIndex] # readPrec :: ReadPrec OffsetIndex # readListPrec :: ReadPrec [OffsetIndex] #
Show OffsetIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> OffsetIndex -> ShowS # show :: OffsetIndex -> String # showList :: [OffsetIndex] -> ShowS #
Eq OffsetIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: OffsetIndex -> OffsetIndex -> Bool # (/=) :: OffsetIndex -> OffsetIndex -> Bool #
Ord OffsetIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: OffsetIndex -> OffsetIndex -> Ordering # (<) :: OffsetIndex -> OffsetIndex -> Bool # (<=) :: OffsetIndex -> OffsetIndex -> Bool # (>) :: OffsetIndex -> OffsetIndex -> Bool # (>=) :: OffsetIndex -> OffsetIndex -> Bool # max :: OffsetIndex -> OffsetIndex -> OffsetIndex # min :: OffsetIndex -> OffsetIndex -> OffsetIndex #

_OffsetIndex :: Name Source #

_OffsetIndex_pageLocations :: Name Source #

data ColumnIndex Source #

Description for ColumnIndex. Each array-field[i] refers to the page at OffsetIndex.page_locations[i]

Constructors

ColumnIndex

Fields

columnIndexNullPages :: [Bool]
A list of Boolean values to determine the validity of the corresponding min and max values. If true, a page contains only null values, and writers have to set the corresponding entries in min_values and max_values to byte[0], so that all lists have the same length. If false, the corresponding entries in min_values and max_values must be valid.
columnIndexMinValues :: [String]
minValues and maxValues are lists containing lower and upper bounds for the values of each page determined by the ColumnOrder of the column. These may be the actual minimum and maximum values found on a page, but can also be (more compact) values that do not exist on a page. For example, instead of storing "Blart Versenwald III", a writer may set min_values[i]=B, max_values[i]=C. Such more compact values must still be valid values within the column's logical type. Readers must make sure that list entries are populated before using them by inspecting null_pages.
columnIndexMaxValues :: [String]
columnIndexBoundaryOrder :: BoundaryOrder
Stores whether both min_values and max_values are orderd and if so, in which direction. This allows readers to perform binary searches in both lists. Readers cannot assume that max_values[i] <= min_values[i+1], even if the lists are ordered.
columnIndexNullCounts :: Maybe [Int64]
A list containing the number of null values for each page

Instances

Instances details

Read ColumnIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS ColumnIndex # readList :: ReadS [ColumnIndex] # readPrec :: ReadPrec ColumnIndex # readListPrec :: ReadPrec [ColumnIndex] #
Show ColumnIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> ColumnIndex -> ShowS # show :: ColumnIndex -> String # showList :: [ColumnIndex] -> ShowS #
Eq ColumnIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: ColumnIndex -> ColumnIndex -> Bool # (/=) :: ColumnIndex -> ColumnIndex -> Bool #
Ord ColumnIndex Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: ColumnIndex -> ColumnIndex -> Ordering # (<) :: ColumnIndex -> ColumnIndex -> Bool # (<=) :: ColumnIndex -> ColumnIndex -> Bool # (>) :: ColumnIndex -> ColumnIndex -> Bool # (>=) :: ColumnIndex -> ColumnIndex -> Bool # max :: ColumnIndex -> ColumnIndex -> ColumnIndex # min :: ColumnIndex -> ColumnIndex -> ColumnIndex #

_ColumnIndex :: Name Source #

_ColumnIndex_nullPages :: Name Source #

_ColumnIndex_minValues :: Name Source #

_ColumnIndex_maxValues :: Name Source #

_ColumnIndex_boundaryOrder :: Name Source #

_ColumnIndex_nullCounts :: Name Source #

data AesGcmV1 Source #

Constructors

AesGcmV1
Fields aesGcmV1AadPrefix :: Maybe String AAD prefix aesGcmV1AadFileUnique :: Maybe String Unique file identifier part of AAD suffix aesGcmV1SupplyAadPrefix :: Maybe Bool In files encrypted with AAD prefix without storing it, readers must supply the prefix

Instances

Instances details

Read AesGcmV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS AesGcmV1 # readList :: ReadS [AesGcmV1] # readPrec :: ReadPrec AesGcmV1 # readListPrec :: ReadPrec [AesGcmV1] #
Show AesGcmV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> AesGcmV1 -> ShowS # show :: AesGcmV1 -> String # showList :: [AesGcmV1] -> ShowS #
Eq AesGcmV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: AesGcmV1 -> AesGcmV1 -> Bool # (/=) :: AesGcmV1 -> AesGcmV1 -> Bool #
Ord AesGcmV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: AesGcmV1 -> AesGcmV1 -> Ordering # (<) :: AesGcmV1 -> AesGcmV1 -> Bool # (<=) :: AesGcmV1 -> AesGcmV1 -> Bool # (>) :: AesGcmV1 -> AesGcmV1 -> Bool # (>=) :: AesGcmV1 -> AesGcmV1 -> Bool # max :: AesGcmV1 -> AesGcmV1 -> AesGcmV1 # min :: AesGcmV1 -> AesGcmV1 -> AesGcmV1 #

_AesGcmV1 :: Name Source #

_AesGcmV1_aadPrefix :: Name Source #

_AesGcmV1_aadFileUnique :: Name Source #

_AesGcmV1_supplyAadPrefix :: Name Source #

data AesGcmCtrV1 Source #

Constructors

AesGcmCtrV1
Fields aesGcmCtrV1AadPrefix :: Maybe String AAD prefix aesGcmCtrV1AadFileUnique :: Maybe String Unique file identifier part of AAD suffix aesGcmCtrV1SupplyAadPrefix :: Maybe Bool In files encrypted with AAD prefix without storing it, readers must supply the prefix

Instances

Instances details

Read AesGcmCtrV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS AesGcmCtrV1 # readList :: ReadS [AesGcmCtrV1] # readPrec :: ReadPrec AesGcmCtrV1 # readListPrec :: ReadPrec [AesGcmCtrV1] #
Show AesGcmCtrV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> AesGcmCtrV1 -> ShowS # show :: AesGcmCtrV1 -> String # showList :: [AesGcmCtrV1] -> ShowS #
Eq AesGcmCtrV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: AesGcmCtrV1 -> AesGcmCtrV1 -> Bool # (/=) :: AesGcmCtrV1 -> AesGcmCtrV1 -> Bool #
Ord AesGcmCtrV1 Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: AesGcmCtrV1 -> AesGcmCtrV1 -> Ordering # (<) :: AesGcmCtrV1 -> AesGcmCtrV1 -> Bool # (<=) :: AesGcmCtrV1 -> AesGcmCtrV1 -> Bool # (>) :: AesGcmCtrV1 -> AesGcmCtrV1 -> Bool # (>=) :: AesGcmCtrV1 -> AesGcmCtrV1 -> Bool # max :: AesGcmCtrV1 -> AesGcmCtrV1 -> AesGcmCtrV1 # min :: AesGcmCtrV1 -> AesGcmCtrV1 -> AesGcmCtrV1 #

_AesGcmCtrV1 :: Name Source #

_AesGcmCtrV1_aadPrefix :: Name Source #

_AesGcmCtrV1_aadFileUnique :: Name Source #

_AesGcmCtrV1_supplyAadPrefix :: Name Source #

data EncryptionAlgorithm Source #

Constructors

EncryptionAlgorithmAesGcmV1 AesGcmV1
EncryptionAlgorithmAesGcmCtrV1 AesGcmCtrV1

Instances

Instances details

Read EncryptionAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS EncryptionAlgorithm # readList :: ReadS [EncryptionAlgorithm] # readPrec :: ReadPrec EncryptionAlgorithm # readListPrec :: ReadPrec [EncryptionAlgorithm] #
Show EncryptionAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> EncryptionAlgorithm -> ShowS # show :: EncryptionAlgorithm -> String # showList :: [EncryptionAlgorithm] -> ShowS #
Eq EncryptionAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: EncryptionAlgorithm -> EncryptionAlgorithm -> Bool # (/=) :: EncryptionAlgorithm -> EncryptionAlgorithm -> Bool #
Ord EncryptionAlgorithm Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: EncryptionAlgorithm -> EncryptionAlgorithm -> Ordering # (<) :: EncryptionAlgorithm -> EncryptionAlgorithm -> Bool # (<=) :: EncryptionAlgorithm -> EncryptionAlgorithm -> Bool # (>) :: EncryptionAlgorithm -> EncryptionAlgorithm -> Bool # (>=) :: EncryptionAlgorithm -> EncryptionAlgorithm -> Bool # max :: EncryptionAlgorithm -> EncryptionAlgorithm -> EncryptionAlgorithm # min :: EncryptionAlgorithm -> EncryptionAlgorithm -> EncryptionAlgorithm #

_EncryptionAlgorithm :: Name Source #

_EncryptionAlgorithm_aesGcmV1 :: Name Source #

_EncryptionAlgorithm_aesGcmCtrV1 :: Name Source #

data FileMetaData Source #

Description for file metadata

Constructors

FileMetaData

Fields

fileMetaDataVersion :: Int
Version of this file
fileMetaDataSchema :: [SchemaElement]
Parquet schema for this file. This schema contains metadata for all the columns. The schema is represented as a tree with a single root. The nodes of the tree are flattened to a list by doing a depth-first traversal. The column metadata contains the path in the schema for that column which can be used to map columns to nodes in the schema. The first element is the root
fileMetaDataNumRows :: Int64
Number of rows in this file
fileMetaDataRowGroups :: [RowGroup]
Row groups in this file
fileMetaDataKeyValueMetadata :: Maybe [KeyValue]
Optional key/value metadata
fileMetaDataCreatedBy :: Maybe String
String for application that wrote this file. This should be in the format Application version Version (build Build Hash). e.g. impala version 1.0 (build 6cf94d29b2b7115df4de2c06e2ab4326d721eb55)
fileMetaDataColumnOrders :: Maybe [ColumnOrder]
Sort order used for the min_value and max_value fields in the Statistics objects and the min_values and max_values fields in the ColumnIndex objects of each column in this file. Sort orders are listed in the order matching the columns in the schema. The indexes are not necessary the same though, because only leaf nodes of the schema are represented in the list of sort orders. | Without column_orders, the meaning of the min_value and max_value fields in the Statistics object and the ColumnIndex object is undefined. To ensure well-defined behaviour, if these fields are written to a Parquet file, column_orders must be written as well. | The obsolete min and max fields in the Statistics object are always sorted by signed comparison regardless of column_orders.
fileMetaDataEncryptionAlgorithm :: Maybe EncryptionAlgorithm
Encryption algorithm. This field is set only in encrypted files with plaintext footer. Files with encrypted footer store algorithm id in FileCryptoMetaData structure.
fileMetaDataFooterSigningKeyMetadata :: Maybe String
Retrieval metadata of key used for signing the footer. Used only in encrypted files with plaintext footer.

Instances

Instances details

Read FileMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS FileMetaData # readList :: ReadS [FileMetaData] # readPrec :: ReadPrec FileMetaData # readListPrec :: ReadPrec [FileMetaData] #
Show FileMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> FileMetaData -> ShowS # show :: FileMetaData -> String # showList :: [FileMetaData] -> ShowS #
Eq FileMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: FileMetaData -> FileMetaData -> Bool # (/=) :: FileMetaData -> FileMetaData -> Bool #
Ord FileMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: FileMetaData -> FileMetaData -> Ordering # (<) :: FileMetaData -> FileMetaData -> Bool # (<=) :: FileMetaData -> FileMetaData -> Bool # (>) :: FileMetaData -> FileMetaData -> Bool # (>=) :: FileMetaData -> FileMetaData -> Bool # max :: FileMetaData -> FileMetaData -> FileMetaData # min :: FileMetaData -> FileMetaData -> FileMetaData #

_FileMetaData :: Name Source #

_FileMetaData_version :: Name Source #

_FileMetaData_schema :: Name Source #

_FileMetaData_numRows :: Name Source #

_FileMetaData_rowGroups :: Name Source #

_FileMetaData_keyValueMetadata :: Name Source #

_FileMetaData_createdBy :: Name Source #

_FileMetaData_columnOrders :: Name Source #

_FileMetaData_encryptionAlgorithm :: Name Source #

_FileMetaData_footerSigningKeyMetadata :: Name Source #

data FileCryptoMetaData Source #

Crypto metadata for files with encrypted footer

Constructors

FileCryptoMetaData
Fields fileCryptoMetaDataEncryptionAlgorithm :: EncryptionAlgorithm Encryption algorithm. This field is only used for files with encrypted footer. Files with plaintext footer store algorithm id inside footer (FileMetaData structure). fileCryptoMetaDataKeyMetadata :: Maybe String Retrieval metadata of key used for encryption of footer, and (possibly) columns

Instances

Instances details

Read FileCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods readsPrec :: Int -> ReadS FileCryptoMetaData # readList :: ReadS [FileCryptoMetaData] # readPrec :: ReadPrec FileCryptoMetaData # readListPrec :: ReadPrec [FileCryptoMetaData] #
Show FileCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods showsPrec :: Int -> FileCryptoMetaData -> ShowS # show :: FileCryptoMetaData -> String # showList :: [FileCryptoMetaData] -> ShowS #
Eq FileCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods (==) :: FileCryptoMetaData -> FileCryptoMetaData -> Bool # (/=) :: FileCryptoMetaData -> FileCryptoMetaData -> Bool #
Ord FileCryptoMetaData Source #
Instance details Defined in Hydra.Langs.Parquet.Format Methods compare :: FileCryptoMetaData -> FileCryptoMetaData -> Ordering # (<) :: FileCryptoMetaData -> FileCryptoMetaData -> Bool # (<=) :: FileCryptoMetaData -> FileCryptoMetaData -> Bool # (>) :: FileCryptoMetaData -> FileCryptoMetaData -> Bool # (>=) :: FileCryptoMetaData -> FileCryptoMetaData -> Bool # max :: FileCryptoMetaData -> FileCryptoMetaData -> FileCryptoMetaData # min :: FileCryptoMetaData -> FileCryptoMetaData -> FileCryptoMetaData #

_FileCryptoMetaData :: Name Source #

_FileCryptoMetaData_encryptionAlgorithm :: Name Source #

_FileCryptoMetaData_keyMetadata :: Name Source #