Writers

Files
file	csv.hpp
file	io/json.hpp
file	orc.hpp
file	parquet.hpp

Classes
class	cudf::io::csv_writer_options
	Settings to use for write_csv(). More...
class	cudf::io::csv_writer_options_builder
	Builder to build options for writer_csv() More...
class	cudf::io::experimental::cudftable_writer_options
	Settings for write_cudftable(). More...
class	cudf::io::experimental::cudftable_writer_options_builder
	Class to build cudftable_writer_options. More...
class	cudf::io::json_writer_options
	Settings to use for write_json(). More...
class	cudf::io::json_writer_options_builder
	Builder to build options for writer_json() More...
class	cudf::io::orc_writer_options
	Settings to use for write_orc(). More...
class	cudf::io::orc_writer_options_builder
	Builds settings to use for write_orc(). More...
class	cudf::io::chunked_orc_writer_options
	Settings to use for write_orc_chunked(). More...
class	cudf::io::chunked_orc_writer_options_builder
	Builds settings to use for write_orc_chunked(). More...
class	cudf::io::orc_chunked_writer
	Chunked orc writer class writes an ORC file in a chunked/stream form. More...
struct	cudf::io::sorting_column
	Struct used to describe column sorting metadata. More...
class	cudf::io::parquet_writer_options_base
	Base settings for write_parquet() and chunked_parquet_writer. More...
class	cudf::io::parquet_writer_options_builder_base< BuilderT, OptionsT >
	Base class for Parquet options builders. More...
class	cudf::io::parquet_writer_options
	Settings for write_parquet(). More...
class	cudf::io::parquet_writer_options_builder
	Class to build parquet_writer_options. More...
class	cudf::io::chunked_parquet_writer_options
	Settings for chunked_parquet_writer. More...
class	cudf::io::chunked_parquet_writer_options_builder
	Class to build chunked_parquet_writer_options. More...
class	cudf::io::chunked_parquet_writer
	chunked parquet writer class to handle options and write tables in chunks. More...

Functions
void	cudf::io::write_csv (csv_writer_options const &options, rmm::cuda_stream_view stream=cudf::get_default_stream())
	Writes a set of columns to CSV format. More...
constexpr bool	cudf::io::is_supported_write_csv (data_type type)
	Checks if a cudf::data_type is supported for CSV writing. More...
void	cudf::io::experimental::write_cudftable (cudftable_writer_options const &options, rmm::cuda_stream_view stream=cudf::get_default_stream())
	Write a table using the CudfTable binary format. More...
void	cudf::io::write_json (json_writer_options const &options, rmm::cuda_stream_view stream=cudf::get_default_stream())
	Writes a set of columns to JSON format. More...
constexpr bool	cudf::io::is_supported_write_json (data_type type)
	Checks if a cudf::data_type is supported for JSON writing. More...
void	cudf::io::write_orc (orc_writer_options const &options, rmm::cuda_stream_view stream=cudf::get_default_stream())
	Writes a set of columns to ORC format. More...
std::unique_ptr< std::vector< uint8_t > >	cudf::io::write_parquet (parquet_writer_options const &options, rmm::cuda_stream_view stream=cudf::get_default_stream())
	Writes a set of columns to parquet format. More...
std::unique_ptr< std::vector< uint8_t > >	cudf::io::merge_row_group_metadata (std::vector< std::unique_ptr< std::vector< uint8_t >>> const &metadata_list)
	Merges multiple raw metadata blobs that were previously created by write_parquet into a single metadata blob. More...

Detailed Description

Function Documentation

is_supported_write_csv()

constexpr bool cudf::io::is_supported_write_csv ( data_type  type )

constexpr

Checks if a cudf::data_type is supported for CSV writing.

Parameters

type	The data_type to check.

Returns

true if the type is supported for CSV writing, false otherwise.

Definition at line 1772 of file csv.hpp.

is_supported_write_json()

constexpr bool cudf::io::is_supported_write_json ( data_type  type )

constexpr

Checks if a cudf::data_type is supported for JSON writing.

Parameters

type	The data_type to check.

Returns

true if the type is supported for JSON writing, false otherwise.

Definition at line 1352 of file io/json.hpp.

merge_row_group_metadata()

std::unique_ptr<std::vector<uint8_t> > cudf::io::merge_row_group_metadata

(

std::vector< std::unique_ptr< std::vector< uint8_t >>> const &

metadata_list

)

Merges multiple raw metadata blobs that were previously created by write_parquet into a single metadata blob.

Parameters

[in]

metadata_list

List of input file metadata

Returns

A parquet-compatible blob that contains the data for all row groups in the list

write_csv()

void cudf::io::write_csv	(	csv_writer_options const &	options,
		rmm::cuda_stream_view	stream = cudf::get_default_stream()
	)

Writes a set of columns to CSV format.

The following code snippet demonstrates how to write columns to a file:

auto destination = cudf::io::sink_info("dataset.csv");
auto options     = cudf::io::csv_writer_options(destination, table->view())
  .na_rep(na)
  .include_header(include_header)
  .rows_per_chunk(rows_per_chunk);
 
cudf::io::write_csv(options);

Parameters

options	Settings for controlling writing behavior
stream	CUDA stream used for device memory operations and kernel launches

write_cudftable()

void cudf::io::experimental::write_cudftable	(	cudftable_writer_options const &	options,
		rmm::cuda_stream_view	stream = cudf::get_default_stream()
	)

Write a table using the CudfTable binary format.

This function uses cudf::pack to serialize a table into a contiguous format, then writes it to the specified sink with a simple header containing metadata and data lengths.

Parameters

options	Options specifying the sink and table to write
stream	CUDA stream used for device memory operations and kernel launches

write_json()

void cudf::io::write_json	(	json_writer_options const &	options,
		rmm::cuda_stream_view	stream = cudf::get_default_stream()
	)

Writes a set of columns to JSON format.

The following code snippet demonstrates how to write columns to a file:

auto destination = cudf::io::sink_info("dataset.json");
auto options     = cudf::io::json_writer_options(destination, table->view())
  .na_rep(na)
  .lines(lines)
  .rows_per_chunk(rows_per_chunk);
 
cudf::io::write_json(options);

Parameters

options	Settings for controlling writing behavior
stream	CUDA stream used for device memory operations and kernel launches

write_orc()

void cudf::io::write_orc	(	orc_writer_options const &	options,
		rmm::cuda_stream_view	stream = cudf::get_default_stream()
	)

Writes a set of columns to ORC format.

The following code snippet demonstrates how to write columns to a file:

auto destination = cudf::io::sink_info("dataset.orc");
auto options     = cudf::io::orc_writer_options::builder(destination, table->view());
cudf::io::write_orc(options);

Note

If an exception is thrown during encoding or compression, no data is written to the sink.

Parameters

options	Settings for controlling reading behavior
stream	CUDA stream used for device memory operations and kernel launches

write_parquet()

std::unique_ptr<std::vector<uint8_t> > cudf::io::write_parquet	(	parquet_writer_options const &	options,
		rmm::cuda_stream_view	stream = cudf::get_default_stream()
	)

Writes a set of columns to parquet format.

The following code snippet demonstrates how to write columns to a file:

auto destination = cudf::io::sink_info("dataset.parquet");
auto options     = cudf::io::parquet_writer_options::builder(destination, table->view());
cudf::io::write_parquet(options);

Note

If an exception is thrown during encoding or compression, no data is written to the sink.

Parameters

options	Settings for controlling writing behavior
stream	CUDA stream used for device memory operations and kernel launches

Returns

A parquet-compatible blob that contains the file metadata (parquet FileMetadata thrift message).