Classes | Namespaces | Enumerations
parquet_schema.hpp File Reference

Parquet footer schema structs. More...

#include <cudf/types.hpp>
#include <cuda/std/optional>
#include <cstdint>
#include <optional>
#include <string>
#include <vector>

Go to the source code of this file.

Classes

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

Namespaces

 cudf
 cuDF interfaces
 
 cudf::io
 IO interfaces.
 

Enumerations

enum class  cudf::io::parquet::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  cudf::io::parquet::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  cudf::io::parquet::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  cudf::io::parquet::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  cudf::io::parquet::FieldRepetitionType : int8_t { UNSPECIFIED = -1 , REQUIRED = 0 , OPTIONAL = 1 , REPEATED = 2 }
 Compression codec used for compressed data pages.
 
enum class  cudf::io::parquet::PageType : uint8_t { DATA_PAGE = 0 , INDEX_PAGE = 1 , DICTIONARY_PAGE = 2 , DATA_PAGE_V2 = 3 }
 Types of pages.
 
enum class  cudf::io::parquet::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  cudf::io::parquet::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 footer schema structs.

Definition in file parquet_schema.hpp.