cudf::io::parquet Namespace Reference

Parquet I/O interfaces. More...

Classes
struct	file_header_s
	Struct that describes the Parquet file data header. More...
struct	file_ender_s
	Struct that describes the Parquet file data postscript. More...
struct	DecimalType
	Struct that describes the decimal logical type annotation. More...
struct	TimeUnit
	Time units for temporal logical types. More...
struct	TimeType
	Struct that describes the time logical type annotation. More...
struct	TimestampType
	Struct that describes the timestamp logical type annotation. More...
struct	IntType
	Struct that describes the integer logical type annotation. More...
struct	LogicalType
	Struct that describes the logical type annotation. More...
struct	ColumnOrder
	Union to specify the order used for the min_value and max_value fields for a column. More...
struct	SchemaElement
	Struct for describing an element/field in the Parquet format schema. More...
struct	Statistics
	Thrift-derived struct describing column chunk statistics. More...
struct	SizeStatistics
	Thrift-derived struct containing statistics used to estimate page and column chunk sizes. More...
struct	PageLocation
	Thrift-derived struct describing page location information stored in the offsets index. More...
struct	OffsetIndex
	Thrift-derived struct describing the offset index. More...
struct	ColumnIndex
	Thrift-derived struct describing the column index. More...
struct	PageEncodingStats
	Thrift-derived struct describing page encoding statistics. More...
struct	SortingColumn
	Thrift-derived struct describing column sort order. More...
struct	ColumnChunkMetaData
	Thrift-derived struct describing a column chunk. More...
struct	BloomFilterAlgorithm
	The algorithm used in bloom filter. More...
struct	BloomFilterHash
	The hash function used in Bloom filter. More...
struct	BloomFilterCompression
	The compression used in the bloom filter. More...
struct	BloomFilterHeader
	Bloom filter header struct. More...
struct	ColumnChunk
	Thrift-derived struct describing a chunk of data for a particular column. More...
struct	RowGroup
	Thrift-derived struct describing a group of row data. More...
struct	KeyValue
	Thrift-derived struct describing a key-value pair, for user metadata. More...
struct	FileMetaData
	Thrift-derived struct describing file-level metadata. More...
struct	DataPageHeader
	Thrift-derived struct describing the header for a data page. More...
struct	DataPageHeaderV2
	Thrift-derived struct describing the header for a V2 data page. More...
struct	DictionaryPageHeader
	Thrift-derived struct describing the header for a dictionary page. More...
struct	PageHeader
	Thrift-derived struct describing the page header. More...

Enumerations
enum class	TypeKind : int8_t {   UNDEFINED_TYPE = -1 , BOOLEAN = 0 , INT32 = 1 , INT64 = 2 ,   INT96 = 3 , FLOAT = 4 , DOUBLE = 5 , BYTE_ARRAY = 6 ,   FIXED_LEN_BYTE_ARRAY = 7 }
	Basic data types in Parquet, determines how data is physically stored.
enum class	Type : int8_t {   UNDEFINED = -1 , BOOLEAN = 0 , INT32 = 1 , INT64 = 2 ,   INT96 = 3 , FLOAT = 4 , DOUBLE = 5 , BYTE_ARRAY = 6 ,   FIXED_LEN_BYTE_ARRAY = 7 }
	Basic data types in Parquet, determines how data is physically stored.
enum class	ConvertedType : int8_t {   UNKNOWN = -1 , UTF8 = 0 , MAP = 1 , MAP_KEY_VALUE = 2 ,   LIST , ENUM = 4 , DECIMAL = 5 , DATE = 6 ,   TIME_MILLIS = 7 , TIME_MICROS = 8 , TIMESTAMP_MILLIS = 9 , TIMESTAMP_MICROS = 10 ,   UINT_8 = 11 , UINT_16 = 12 , UINT_32 = 13 , UINT_64 = 14 ,   INT_8 = 15 , INT_16 = 16 , INT_32 = 17 , INT_64 = 18 ,   JSON = 19 , BSON = 20 , INTERVAL = 21 , NA = 25 }
	High-level data types in Parquet, determines how data is logically interpreted.
enum class	Encoding : uint8_t {   PLAIN = 0 , GROUP_VAR_INT = 1 , PLAIN_DICTIONARY = 2 , RLE = 3 ,   BIT_PACKED = 4 , DELTA_BINARY_PACKED = 5 , DELTA_LENGTH_BYTE_ARRAY = 6 , DELTA_BYTE_ARRAY = 7 ,   RLE_DICTIONARY = 8 , BYTE_STREAM_SPLIT = 9 , NUM_ENCODINGS = 10 }
	Encoding types for the actual data stream.
enum class	Compression : uint8_t {   UNCOMPRESSED = 0 , SNAPPY = 1 , GZIP = 2 , LZO = 3 ,   BROTLI = 4 , LZ4 = 5 , ZSTD = 6 , LZ4_RAW = 7 }
	Compression codec used for compressed data pages.
enum class	FieldRepetitionType : int8_t { UNSPECIFIED = -1 , REQUIRED = 0 , OPTIONAL = 1 , REPEATED = 2 }
	Compression codec used for compressed data pages.
enum class	PageType : uint8_t { DATA_PAGE = 0 , INDEX_PAGE = 1 , DICTIONARY_PAGE = 2 , DATA_PAGE_V2 = 3 }
	Types of pages.
enum class	BoundaryOrder : uint8_t { UNORDERED = 0 , ASCENDING = 1 , DESCENDING = 2 }
	Enum to annotate whether lists of min/max elements inside ColumnIndex are ordered and if so, in which direction.
enum class	FieldType : uint8_t {   BOOLEAN_TRUE = 1 , BOOLEAN_FALSE = 2 , I8 = 3 , I16 = 4 ,   I32 = 5 , I64 = 6 , DOUBLE = 7 , BINARY = 8 ,   LIST = 9 , SET = 10 , MAP = 11 , STRUCT = 12 ,   UUID = 13 }
	Thrift compact protocol struct field types.

Detailed Description

Parquet I/O interfaces.