Settings for write_parquet_chunked(). More...

#include <parquet.hpp>

Public Member Functions
	chunked_parquet_writer_options ()=default
	Default constructor. More...

sink_info const &	get_sink () const
	Returns sink info. More...

compression_type	get_compression () const
	Returns compression format used. More...

statistics_freq	get_stats_level () const
	Returns level of statistics requested in output file. More...

auto const &	get_metadata () const
	Returns metadata information. More...

std::vector< std::map< std::string, std::string > > const &	get_key_value_metadata () const
	Returns Key-Value footer metadata information. More...

bool	is_enabled_int96_timestamps () const
	Returns `true` if timestamps will be written as INT96. More...

auto	is_enabled_utc_timestamps () const
	Returns `true` if timestamps will be written as UTC. More...

auto	get_row_group_size_bytes () const
	Returns maximum row group size, in bytes. More...

auto	get_row_group_size_rows () const
	Returns maximum row group size, in rows. More...

auto	get_max_page_size_bytes () const
	Returns maximum uncompressed page size, in bytes. More...

auto	get_max_page_size_rows () const
	Returns maximum page size, in rows. More...

auto	get_column_index_truncate_length () const
	Returns maximum length of min or max values in column index, in bytes. More...

dictionary_policy	get_dictionary_policy () const
	Returns policy for dictionary use. More...

auto	get_max_dictionary_size () const
	Returns maximum dictionary size, in bytes. More...

auto	get_max_page_fragment_size () const
	Returns maximum page fragment size, in rows. More...

std::shared_ptr< writer_compression_statistics >	get_compression_statistics () const
	Returns a shared pointer to the user-provided compression statistics. More...

auto	is_enabled_write_v2_headers () const
	Returns `true` if V2 page headers should be written. More...

void	set_metadata (table_input_metadata metadata)
	Sets metadata. More...

void	set_key_value_metadata (std::vector< std::map< std::string, std::string >> metadata)
	Sets Key-Value footer metadata. More...

void	set_stats_level (statistics_freq sf)
	Sets the level of statistics in parquet_writer_options. More...

void	set_compression (compression_type compression)
	Sets compression type. More...

void	enable_int96_timestamps (bool req)
	Sets timestamp writing preferences. More...

void	enable_utc_timestamps (bool val)
	Sets preference for writing timestamps as UTC. Write timestamps as UTC if set to `true`. More...

void	set_row_group_size_bytes (size_t size_bytes)
	Sets the maximum row group size, in bytes. More...

void	set_row_group_size_rows (size_type size_rows)
	Sets the maximum row group size, in rows. More...

void	set_max_page_size_bytes (size_t size_bytes)
	Sets the maximum uncompressed page size, in bytes. More...

void	set_max_page_size_rows (size_type size_rows)
	Sets the maximum page size, in rows. More...

void	set_column_index_truncate_length (int32_t size_bytes)
	Sets the maximum length of min or max values in column index, in bytes. More...

void	set_dictionary_policy (dictionary_policy policy)
	Sets the policy for dictionary use. More...

void	set_max_dictionary_size (size_t size_bytes)
	Sets the maximum dictionary size, in bytes. More...

void	set_max_page_fragment_size (size_type size_rows)
	Sets the maximum page fragment size, in rows. More...

void	set_compression_statistics (std::shared_ptr< writer_compression_statistics > comp_stats)
	Sets the pointer to the output compression statistics. More...

void	enable_write_v2_headers (bool val)
	Sets preference for V2 page headers. Write V2 page headers if set to `true`. More...

Static Public Member Functions
static chunked_parquet_writer_options_builder	builder (sink_info const &sink)
	creates builder to build chunked_parquet_writer_options. More...

Detailed Description

Settings for write_parquet_chunked().

Definition at line 1197 of file parquet.hpp.

Constructor & Destructor Documentation

◆ chunked_parquet_writer_options()

cudf::io::chunked_parquet_writer_options::chunked_parquet_writer_options ( )

default

Default constructor.

This has been added since Cython requires a default constructor to create objects on stack.

Member Function Documentation

◆ builder()

static chunked_parquet_writer_options_builder cudf::io::chunked_parquet_writer_options::builder ( sink_info const & sink )

static

creates builder to build chunked_parquet_writer_options.

Parameters

sink	sink to use for writer output

Returns: Builder to build chunked_parquet_writer_options

◆ enable_int96_timestamps()

void cudf::io::chunked_parquet_writer_options::enable_int96_timestamps ( bool req )

inline

Sets timestamp writing preferences.

INT96 timestamps will be written if true and TIMESTAMP_MICROS will be written if false.

Parameters

req	Boolean value to enable/disable writing of INT96 timestamps

Definition at line 1422 of file parquet.hpp.

◆ enable_utc_timestamps()

void cudf::io::chunked_parquet_writer_options::enable_utc_timestamps ( bool val )

inline

Sets preference for writing timestamps as UTC. Write timestamps as UTC if set to true.

Parameters

val	Boolean value to enable/disable writing of timestamps as UTC.

Definition at line 1429 of file parquet.hpp.

◆ enable_write_v2_headers()

void cudf::io::chunked_parquet_writer_options::enable_write_v2_headers ( bool val )

inline

Sets preference for V2 page headers. Write V2 page headers if set to true.

Parameters

val	Boolean value to enable/disable writing of V2 page headers.

Definition at line 1502 of file parquet.hpp.

◆ get_column_index_truncate_length()

auto cudf::io::chunked_parquet_writer_options::get_column_index_truncate_length ( ) const

inline

Returns maximum length of min or max values in column index, in bytes.

Returns: length min/max will be truncated to

Definition at line 1347 of file parquet.hpp.

◆ get_compression()

compression_type cudf::io::chunked_parquet_writer_options::get_compression ( ) const

inline

Returns compression format used.

Returns: Compression format

Definition at line 1263 of file parquet.hpp.

◆ get_compression_statistics()

std::shared_ptr<writer_compression_statistics> cudf::io::chunked_parquet_writer_options::get_compression_statistics ( ) const

inline

Returns a shared pointer to the user-provided compression statistics.

Returns: Compression statistics

Definition at line 1375 of file parquet.hpp.

◆ get_dictionary_policy()

dictionary_policy cudf::io::chunked_parquet_writer_options::get_dictionary_policy ( ) const

inline

Returns policy for dictionary use.

Returns: policy for dictionary use

Definition at line 1354 of file parquet.hpp.

◆ get_key_value_metadata()

std::vector<std::map<std::string, std::string> > const& cudf::io::chunked_parquet_writer_options::get_key_value_metadata ( ) const

inline

Returns Key-Value footer metadata information.

Returns: Key-Value footer metadata information

Definition at line 1284 of file parquet.hpp.

◆ get_max_dictionary_size()

auto cudf::io::chunked_parquet_writer_options::get_max_dictionary_size ( ) const

inline

Returns maximum dictionary size, in bytes.

Returns: Maximum dictionary size, in bytes.

Definition at line 1361 of file parquet.hpp.

◆ get_max_page_fragment_size()

auto cudf::io::chunked_parquet_writer_options::get_max_page_fragment_size ( ) const

inline

Returns maximum page fragment size, in rows.

Returns: Maximum page fragment size, in rows.

Definition at line 1368 of file parquet.hpp.

◆ get_max_page_size_bytes()

auto cudf::io::chunked_parquet_writer_options::get_max_page_size_bytes ( ) const

inline

Returns maximum uncompressed page size, in bytes.

If set larger than the row group size, then this will return the row group size.

Returns: Maximum uncompressed page size, in bytes

Definition at line 1325 of file parquet.hpp.

◆ get_max_page_size_rows()

auto cudf::io::chunked_parquet_writer_options::get_max_page_size_rows ( ) const

inline

Returns maximum page size, in rows.

If set larger than the row group size, then this will return the row group size.

Returns: Maximum page size, in rows

Definition at line 1337 of file parquet.hpp.

◆ get_metadata()

auto const& cudf::io::chunked_parquet_writer_options::get_metadata ( ) const

inline

Returns metadata information.

Returns: Metadata information

Definition at line 1277 of file parquet.hpp.

◆ get_row_group_size_bytes()

auto cudf::io::chunked_parquet_writer_options::get_row_group_size_bytes ( ) const

inline

Returns maximum row group size, in bytes.

Returns: Maximum row group size, in bytes

Definition at line 1308 of file parquet.hpp.

◆ get_row_group_size_rows()

auto cudf::io::chunked_parquet_writer_options::get_row_group_size_rows ( ) const

inline

Returns maximum row group size, in rows.

Returns: Maximum row group size, in rows

Definition at line 1315 of file parquet.hpp.

◆ get_sink()

sink_info const& cudf::io::chunked_parquet_writer_options::get_sink ( ) const

inline

Returns sink info.

Returns: Sink info

Definition at line 1256 of file parquet.hpp.

◆ get_stats_level()

statistics_freq cudf::io::chunked_parquet_writer_options::get_stats_level ( ) const

inline

Returns level of statistics requested in output file.

Returns: Level of statistics requested in output file

Definition at line 1270 of file parquet.hpp.

◆ is_enabled_int96_timestamps()

bool cudf::io::chunked_parquet_writer_options::is_enabled_int96_timestamps ( ) const

inline

Returns true if timestamps will be written as INT96.

Returns: true if timestamps will be written as INT96

Definition at line 1294 of file parquet.hpp.

◆ is_enabled_utc_timestamps()

auto cudf::io::chunked_parquet_writer_options::is_enabled_utc_timestamps ( ) const

inline

Returns true if timestamps will be written as UTC.

Returns: true if timestamps will be written as UTC

Definition at line 1301 of file parquet.hpp.

◆ is_enabled_write_v2_headers()

auto cudf::io::chunked_parquet_writer_options::is_enabled_write_v2_headers ( ) const

inline

Returns true if V2 page headers should be written.

Returns: true if V2 page headers should be written.

Definition at line 1385 of file parquet.hpp.

◆ set_column_index_truncate_length()

void cudf::io::chunked_parquet_writer_options::set_column_index_truncate_length ( int32_t size_bytes )

Sets the maximum length of min or max values in column index, in bytes.

Parameters

size_bytes length min/max will be truncated to

◆ set_compression()

void cudf::io::chunked_parquet_writer_options::set_compression ( compression_type compression )

inline

Sets compression type.

Parameters

compression The compression type to use

Definition at line 1413 of file parquet.hpp.

◆ set_compression_statistics()

void cudf::io::chunked_parquet_writer_options::set_compression_statistics ( std::shared_ptr< writer_compression_statistics > comp_stats )

inline

Sets the pointer to the output compression statistics.

Parameters

comp_stats Pointer to compression statistics to be updated after writing

Definition at line 1492 of file parquet.hpp.

◆ set_dictionary_policy()

void cudf::io::chunked_parquet_writer_options::set_dictionary_policy ( dictionary_policy policy )

Sets the policy for dictionary use.

Parameters

policy Policy for dictionary use

◆ set_key_value_metadata()

void cudf::io::chunked_parquet_writer_options::set_key_value_metadata ( std::vector< std::map< std::string, std::string >> metadata )

Sets Key-Value footer metadata.

Parameters

metadata Key-Value footer metadata

◆ set_max_dictionary_size()

void cudf::io::chunked_parquet_writer_options::set_max_dictionary_size ( size_t size_bytes )

Sets the maximum dictionary size, in bytes.

Parameters

size_bytes Maximum dictionary size, in bytes

◆ set_max_page_fragment_size()

void cudf::io::chunked_parquet_writer_options::set_max_page_fragment_size ( size_type size_rows )

Sets the maximum page fragment size, in rows.

Parameters

size_rows Maximum page fragment size, in rows.

◆ set_max_page_size_bytes()

void cudf::io::chunked_parquet_writer_options::set_max_page_size_bytes ( size_t size_bytes )

Sets the maximum uncompressed page size, in bytes.

Parameters

size_bytes Maximum uncompressed page size, in bytes to set

◆ set_max_page_size_rows()

void cudf::io::chunked_parquet_writer_options::set_max_page_size_rows ( size_type size_rows )

Sets the maximum page size, in rows.

Parameters

size_rows The maximum page size, in rows to set

◆ set_metadata()

void cudf::io::chunked_parquet_writer_options::set_metadata ( table_input_metadata metadata )

inline

Sets metadata.

Parameters

metadata Associated metadata

Definition at line 1392 of file parquet.hpp.

◆ set_row_group_size_bytes()

void cudf::io::chunked_parquet_writer_options::set_row_group_size_bytes ( size_t size_bytes )

Sets the maximum row group size, in bytes.

Parameters

size_bytes Maximum row group size, in bytes to set

◆ set_row_group_size_rows()

void cudf::io::chunked_parquet_writer_options::set_row_group_size_rows ( size_type size_rows )

Sets the maximum row group size, in rows.

Parameters

size_rows The maximum row group size, in rows to set

◆ set_stats_level()

void cudf::io::chunked_parquet_writer_options::set_stats_level ( statistics_freq sf )

inline

Sets the level of statistics in parquet_writer_options.

Parameters

sf	Level of statistics requested in the output file

Definition at line 1406 of file parquet.hpp.

The documentation for this class was generated from the following file:

parquet.hpp

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ chunked_parquet_writer_options()

Member Function Documentation

◆ builder()

◆ enable_int96_timestamps()

◆ enable_utc_timestamps()

◆ enable_write_v2_headers()

◆ get_column_index_truncate_length()

◆ get_compression()

◆ get_compression_statistics()

◆ get_dictionary_policy()

◆ get_key_value_metadata()

◆ get_max_dictionary_size()

◆ get_max_page_fragment_size()

◆ get_max_page_size_bytes()

◆ get_max_page_size_rows()

◆ get_metadata()

◆ get_row_group_size_bytes()

◆ get_row_group_size_rows()

◆ get_sink()

◆ get_stats_level()

◆ is_enabled_int96_timestamps()

◆ is_enabled_utc_timestamps()

◆ is_enabled_write_v2_headers()

◆ set_column_index_truncate_length()

◆ set_compression()

◆ set_compression_statistics()

◆ set_dictionary_policy()

◆ set_key_value_metadata()

◆ set_max_dictionary_size()

◆ set_max_page_fragment_size()

◆ set_max_page_size_bytes()

◆ set_max_page_size_rows()

◆ set_metadata()

◆ set_row_group_size_bytes()

◆ set_row_group_size_rows()

◆ set_stats_level()