Input arguments to the read_json interface. More...

#include <json.hpp>

Public Types
using	dtype_variant = std::variant< std::vector< data_type >, std::map< std::string, data_type >, std::map< std::string, schema_element >, schema_element >
	Variant type holding dtypes information for the columns.

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

source_info const &	get_source () const
	Returns source info. More...

dtype_variant const &	get_dtypes () const
	Returns data types of the columns. More...

compression_type	get_compression () const
	Returns compression format of the source. More...

size_t	get_byte_range_offset () const
	Returns number of bytes to skip from source start. More...

size_t	get_byte_range_size () const
	Returns number of bytes to read. More...

size_t	get_byte_range_size_with_padding () const
	Returns number of bytes to read with padding. More...

size_t	get_byte_range_padding () const
	Returns number of bytes to pad when reading. More...

char	get_delimiter () const
	Returns delimiter separating records in JSON lines. More...

bool	is_enabled_lines () const
	Whether to read the file as a json object per line. More...

bool	is_enabled_mixed_types_as_string () const
	Whether to parse mixed types as a string column. More...

bool	is_enabled_prune_columns () const
	Whether to prune columns on read, selected based on the set_dtypes option. More...

bool	is_enabled_experimental () const
	Whether to enable experimental features. More...

bool	is_enabled_dayfirst () const
	Whether to parse dates as DD/MM versus MM/DD. More...

bool	is_enabled_keep_quotes () const
	Whether the reader should keep quotes of string values. More...

bool	is_enabled_normalize_single_quotes () const
	Whether the reader should normalize single quotes around strings. More...

bool	is_enabled_normalize_whitespace () const
	Whether the reader should normalize unquoted whitespace characters. More...

json_recovery_mode_t	recovery_mode () const
	Queries the JSON reader's behavior on invalid JSON lines. More...

bool	is_strict_validation () const
	Whether json validation should be enforced strictly or not. More...

bool	is_allowed_numeric_leading_zeros () const
	Whether leading zeros are allowed in numeric values. More...

bool	is_allowed_nonnumeric_numbers () const
	Whether unquoted number values should be allowed NaN, +INF, -INF, +Infinity, Infinity, and -Infinity. More...

bool	is_allowed_unquoted_control_chars () const
	Whether in a quoted string should characters greater than or equal to 0 and less than 32 be allowed without some form of escaping. More...

std::vector< std::string > const &	get_na_values () const
	Returns additional values to recognize as null values. More...

void	set_dtypes (std::vector< data_type > types)
	Set data types for columns to be read. More...

void	set_dtypes (std::map< std::string, data_type > types)
	Set data types for columns to be read. More...

void	set_dtypes (std::map< std::string, schema_element > types)
	Set data types for a potentially nested column hierarchy. More...

void	set_dtypes (schema_element types)
	Set data types for a potentially nested column hierarchy. More...

void	set_compression (compression_type comp_type)
	Set the compression type. More...

void	set_byte_range_offset (size_t offset)
	Set number of bytes to skip from source start. More...

void	set_byte_range_size (size_t size)
	Set number of bytes to read. More...

void	set_delimiter (char delimiter)
	Set delimiter separating records in JSON lines. More...

void	enable_lines (bool val)
	Set whether to read the file as a json object per line. More...

void	enable_mixed_types_as_string (bool val)
	Set whether to parse mixed types as a string column. Also enables forcing to read a struct as string column using schema. More...

void	enable_prune_columns (bool val)
	Set whether to prune columns on read, selected based on the set_dtypes option. More...

void	enable_experimental (bool val)
	Set whether to enable experimental features. More...

void	enable_dayfirst (bool val)
	Set whether to parse dates as DD/MM versus MM/DD. More...

void	enable_keep_quotes (bool val)
	Set whether the reader should keep quotes of string values. More...

void	enable_normalize_single_quotes (bool val)
	Set whether the reader should enable normalization of single quotes around strings. More...

void	enable_normalize_whitespace (bool val)
	Set whether the reader should enable normalization of unquoted whitespace. More...

void	set_recovery_mode (json_recovery_mode_t val)
	Specifies the JSON reader's behavior on invalid JSON lines. More...

void	set_strict_validation (bool val)
	Set whether strict validation is enabled or not. More...

void	allow_numeric_leading_zeros (bool val)
	Set whether leading zeros are allowed in numeric values. Strict validation must be enabled for this to work. More...

void	allow_nonnumeric_numbers (bool val)
	Set whether unquoted number values should be allowed NaN, +INF, -INF, +Infinity, Infinity, and -Infinity. Strict validation must be enabled for this to work. More...

void	allow_unquoted_control_chars (bool val)
	Set whether in a quoted string should characters greater than or equal to 0 and less than 32 be allowed without some form of escaping. Strict validation must be enabled for this to work. More...

void	set_na_values (std::vector< std::string > vals)
	Sets additional values to recognize as null values. More...

Static Public Member Functions
static json_reader_options_builder	builder (source_info src)
	create json_reader_options_builder which will build json_reader_options. More...

Detailed Description

Input arguments to the read_json interface.

Available parameters are closely patterned after PANDAS' read_json API. Not all parameters are supported. If the matching PANDAS' parameter has a default value of None, then a default value of -1 or 0 may be used as the equivalent.

Parameters in PANDAS that are unavailable or in cudf:

Name	Description
`orient`	currently fixed-format
`typ`	data is always returned as a cudf::table
`convert_axes`	use column functions for axes operations instead
`convert_dates`	dates are detected automatically
`keep_default_dates`	dates are detected automatically
`numpy`	data is always returned as a cudf::table
`precise_float`	there is only one converter
`date_unit`	only millisecond units are supported
`encoding`	only ASCII-encoded data is supported
`chunksize`	use `byte_range_xxx` for chunking instead

Definition at line 95 of file io/json.hpp.

Constructor & Destructor Documentation

◆ json_reader_options()

cudf::io::json_reader_options::json_reader_options ( )

default

Default constructor.

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

Member Function Documentation

◆ allow_nonnumeric_numbers()

void cudf::io::json_reader_options::allow_nonnumeric_numbers ( bool val )

inline

Set whether unquoted number values should be allowed NaN, +INF, -INF, +Infinity, Infinity, and -Infinity. Strict validation must be enabled for this to work.

Exceptions

cudf::logic_error if strict_validation is not enabled before setting this option.

Parameters

val	Boolean value to indicate whether leading zeros are allowed in numeric values

Definition at line 558 of file io/json.hpp.

◆ allow_numeric_leading_zeros()

void cudf::io::json_reader_options::allow_numeric_leading_zeros ( bool val )

inline

Set whether leading zeros are allowed in numeric values. Strict validation must be enabled for this to work.

Exceptions

cudf::logic_error if strict_validation is not enabled before setting this option.

Parameters

val	Boolean value to indicate whether leading zeros are allowed in numeric values

Definition at line 544 of file io/json.hpp.

◆ allow_unquoted_control_chars()

void cudf::io::json_reader_options::allow_unquoted_control_chars ( bool val )

inline

Set whether in a quoted string should characters greater than or equal to 0 and less than 32 be allowed without some form of escaping. Strict validation must be enabled for this to work.

Exceptions

cudf::logic_error if strict_validation is not enabled before setting this option.

Parameters

val	true to indicate whether unquoted control chars are allowed.

Definition at line 573 of file io/json.hpp.

◆ builder()

static json_reader_options_builder cudf::io::json_reader_options::builder ( source_info src )

static

create json_reader_options_builder which will build json_reader_options.

Parameters

src	source information used to read json file

Returns: builder to build the options

◆ enable_dayfirst()

void cudf::io::json_reader_options::enable_dayfirst ( bool val )

inline

Set whether to parse dates as DD/MM versus MM/DD.

Parameters

val	Boolean value to enable/disable day first parsing format

Definition at line 496 of file io/json.hpp.

◆ enable_experimental()

void cudf::io::json_reader_options::enable_experimental ( bool val )

inline

Set whether to enable experimental features.

When set to true, experimental features, such as the new column tree construction, utf-8 matching of field names will be enabled.

Parameters

val	Boolean value to enable/disable experimental features

Definition at line 489 of file io/json.hpp.

◆ enable_keep_quotes()

void cudf::io::json_reader_options::enable_keep_quotes ( bool val )

inline

Set whether the reader should keep quotes of string values.

Parameters

val	Boolean value to indicate whether the reader should keep quotes of string values

Definition at line 504 of file io/json.hpp.

◆ enable_lines()

void cudf::io::json_reader_options::enable_lines ( bool val )

inline

Set whether to read the file as a json object per line.

Parameters

val	Boolean value to enable/disable the option to read each line as a json object

Definition at line 460 of file io/json.hpp.

◆ enable_mixed_types_as_string()

void cudf::io::json_reader_options::enable_mixed_types_as_string ( bool val )

inline

Set whether to parse mixed types as a string column. Also enables forcing to read a struct as string column using schema.

Parameters

val	Boolean value to enable/disable parsing mixed types as a string column

Definition at line 468 of file io/json.hpp.

◆ enable_normalize_single_quotes()

void cudf::io::json_reader_options::enable_normalize_single_quotes ( bool val )

inline

Set whether the reader should enable normalization of single quotes around strings.

Parameters

val	Boolean value to indicate whether the reader should normalize single quotes around strings

Definition at line 512 of file io/json.hpp.

◆ enable_normalize_whitespace()

void cudf::io::json_reader_options::enable_normalize_whitespace ( bool val )

inline

Set whether the reader should enable normalization of unquoted whitespace.

Parameters

val	Boolean value to indicate whether the reader should normalize unquoted whitespace characters i.e. tabs and spaces

Definition at line 520 of file io/json.hpp.

◆ enable_prune_columns()

void cudf::io::json_reader_options::enable_prune_columns ( bool val )

inline

Set whether to prune columns on read, selected based on the set_dtypes option.

When set as true, if the reader options include set_dtypes, then the reader will only return those columns which are mentioned in set_dtypes. If false, then all columns are returned, independent of the set_dtypes setting.

Parameters

val	Boolean value to enable/disable column pruning

Definition at line 479 of file io/json.hpp.

◆ get_byte_range_offset()

size_t cudf::io::json_reader_options::get_byte_range_offset ( ) const

inline

Returns number of bytes to skip from source start.

Returns: Number of bytes to skip from source start

Definition at line 206 of file io/json.hpp.

◆ get_byte_range_padding()

size_t cudf::io::json_reader_options::get_byte_range_padding ( ) const

inline

Returns number of bytes to pad when reading.

Returns: Number of bytes to pad

Definition at line 234 of file io/json.hpp.

◆ get_byte_range_size()

size_t cudf::io::json_reader_options::get_byte_range_size ( ) const

inline

Returns number of bytes to read.

Returns: Number of bytes to read

Definition at line 213 of file io/json.hpp.

◆ get_byte_range_size_with_padding()

size_t cudf::io::json_reader_options::get_byte_range_size_with_padding ( ) const

inline

Returns number of bytes to read with padding.

Returns: Number of bytes to read with padding

Definition at line 220 of file io/json.hpp.

◆ get_compression()

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

inline

Returns compression format of the source.

Returns: Compression format of the source

Definition at line 199 of file io/json.hpp.

◆ get_delimiter()

char cudf::io::json_reader_options::get_delimiter ( ) const

inline

Returns delimiter separating records in JSON lines.

Returns: Delimiter separating records in JSON lines

Definition at line 260 of file io/json.hpp.

◆ get_dtypes()

dtype_variant const& cudf::io::json_reader_options::get_dtypes ( ) const

inline

Returns data types of the columns.

Returns: Data types of the columns

Definition at line 192 of file io/json.hpp.

◆ get_na_values()

std::vector<std::string> const& cudf::io::json_reader_options::get_na_values ( ) const

inline

Returns additional values to recognize as null values.

Returns: Additional values to recognize as null values

Definition at line 379 of file io/json.hpp.

◆ get_source()

source_info const& cudf::io::json_reader_options::get_source ( ) const

inline

Returns source info.

Returns: Source info

Definition at line 185 of file io/json.hpp.

◆ is_allowed_nonnumeric_numbers()

bool cudf::io::json_reader_options::is_allowed_nonnumeric_numbers ( ) const

inline

Whether unquoted number values should be allowed NaN, +INF, -INF, +Infinity, Infinity, and -Infinity.

Note: : This validation is enforced only if strict validation is enabled.

Returns: true if leading zeros are allowed in numeric values

Definition at line 359 of file io/json.hpp.

◆ is_allowed_numeric_leading_zeros()

bool cudf::io::json_reader_options::is_allowed_numeric_leading_zeros ( ) const

inline

Whether leading zeros are allowed in numeric values.

Note: : This validation is enforced only if strict validation is enabled.

Returns: true if leading zeros are allowed in numeric values

Definition at line 346 of file io/json.hpp.

◆ is_allowed_unquoted_control_chars()

bool cudf::io::json_reader_options::is_allowed_unquoted_control_chars ( ) const

inline

Whether in a quoted string should characters greater than or equal to 0 and less than 32 be allowed without some form of escaping.

Note: : This validation is enforced only if strict validation is enabled.

Returns: true if unquoted control chars are allowed.

Definition at line 369 of file io/json.hpp.

◆ is_enabled_dayfirst()

bool cudf::io::json_reader_options::is_enabled_dayfirst ( ) const

inline

Whether to parse dates as DD/MM versus MM/DD.

Returns: true if dates are parsed as DD/MM, false if MM/DD

Definition at line 302 of file io/json.hpp.

◆ is_enabled_experimental()

bool cudf::io::json_reader_options::is_enabled_experimental ( ) const

inline

Whether to enable experimental features.

When set to true, experimental features, such as the new column tree construction, utf-8 matching of field names will be enabled.

Returns: true if experimental features are enabled

Definition at line 295 of file io/json.hpp.

◆ is_enabled_keep_quotes()

bool cudf::io::json_reader_options::is_enabled_keep_quotes ( ) const

inline

Whether the reader should keep quotes of string values.

Returns: true if the reader should keep quotes, false otherwise

Definition at line 309 of file io/json.hpp.

◆ is_enabled_lines()

bool cudf::io::json_reader_options::is_enabled_lines ( ) const

inline

Whether to read the file as a json object per line.

Returns: true if reading the file as a json object per line

Definition at line 267 of file io/json.hpp.

◆ is_enabled_mixed_types_as_string()

bool cudf::io::json_reader_options::is_enabled_mixed_types_as_string ( ) const

inline

Whether to parse mixed types as a string column.

Returns: true if mixed types are parsed as a string column

Definition at line 274 of file io/json.hpp.

◆ is_enabled_normalize_single_quotes()

bool cudf::io::json_reader_options::is_enabled_normalize_single_quotes ( ) const

inline

Whether the reader should normalize single quotes around strings.

Returns: true if the reader should normalize single quotes, false otherwise

Definition at line 316 of file io/json.hpp.

◆ is_enabled_normalize_whitespace()

bool cudf::io::json_reader_options::is_enabled_normalize_whitespace ( ) const

inline

Whether the reader should normalize unquoted whitespace characters.

Returns: true if the reader should normalize whitespace, false otherwise

Definition at line 323 of file io/json.hpp.

◆ is_enabled_prune_columns()

bool cudf::io::json_reader_options::is_enabled_prune_columns ( ) const

inline

Whether to prune columns on read, selected based on the set_dtypes option.

When set as true, if the reader options include set_dtypes, then the reader will only return those columns which are mentioned in set_dtypes. If false, then all columns are returned, independent of the set_dtypes setting.

Returns: True if column pruning is enabled

Definition at line 286 of file io/json.hpp.

◆ is_strict_validation()

bool cudf::io::json_reader_options::is_strict_validation ( ) const

inline

Whether json validation should be enforced strictly or not.

Returns: true if it should be.

Definition at line 337 of file io/json.hpp.

◆ recovery_mode()

json_recovery_mode_t cudf::io::json_reader_options::recovery_mode ( ) const

inline

Queries the JSON reader's behavior on invalid JSON lines.

Returns: An enum that specifies the JSON reader's behavior on invalid JSON lines.

Definition at line 330 of file io/json.hpp.

◆ set_byte_range_offset()

void cudf::io::json_reader_options::set_byte_range_offset ( size_t offset )

inline

Set number of bytes to skip from source start.

Parameters

offset Number of bytes of offset

Definition at line 422 of file io/json.hpp.

◆ set_byte_range_size()

void cudf::io::json_reader_options::set_byte_range_size ( size_t size )

inline

Set number of bytes to read.

Parameters

size	Number of bytes to read

Definition at line 429 of file io/json.hpp.

◆ set_compression()

void cudf::io::json_reader_options::set_compression ( compression_type comp_type )

inline

Set the compression type.

Parameters

comp_type The compression type used

Definition at line 415 of file io/json.hpp.

◆ set_delimiter()

void cudf::io::json_reader_options::set_delimiter ( char delimiter )

inline

Set delimiter separating records in JSON lines.

Parameters

delimiter Delimiter separating records in JSON lines

Definition at line 436 of file io/json.hpp.

◆ set_dtypes() [1/4]

void cudf::io::json_reader_options::set_dtypes ( schema_element types )

Set data types for a potentially nested column hierarchy.

Parameters

types schema element with column names and column order to support arbitrary nesting of data types

◆ set_dtypes() [2/4]

void cudf::io::json_reader_options::set_dtypes ( std::map< std::string, data_type > types )

inline

Set data types for columns to be read.

Parameters

types Vector dtypes in string format

Definition at line 393 of file io/json.hpp.

◆ set_dtypes() [3/4]

void cudf::io::json_reader_options::set_dtypes ( std::map< std::string, schema_element > types )

inline

Set data types for a potentially nested column hierarchy.

Parameters

types Map of column names to schema_element to support arbitrary nesting of data types

Definition at line 400 of file io/json.hpp.

◆ set_dtypes() [4/4]

void cudf::io::json_reader_options::set_dtypes ( std::vector< data_type > types )

inline

Set data types for columns to be read.

Parameters

types Vector of dtypes

Definition at line 386 of file io/json.hpp.

◆ set_na_values()

void cudf::io::json_reader_options::set_na_values ( std::vector< std::string > vals )

inline

Sets additional values to recognize as null values.

Parameters

vals	Vector of values to be considered to be null

Definition at line 584 of file io/json.hpp.

◆ set_recovery_mode()

void cudf::io::json_reader_options::set_recovery_mode ( json_recovery_mode_t val )

inline

Specifies the JSON reader's behavior on invalid JSON lines.

Parameters

val	An enum value to indicate the JSON reader's behavior on invalid JSON lines.

Definition at line 527 of file io/json.hpp.

◆ set_strict_validation()

void cudf::io::json_reader_options::set_strict_validation ( bool val )

inline

Set whether strict validation is enabled or not.

Parameters

val	Boolean value to indicate whether strict validation is enabled.

Definition at line 534 of file io/json.hpp.

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

io/json.hpp

Public Types

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ json_reader_options()

Member Function Documentation

◆ allow_nonnumeric_numbers()

◆ allow_numeric_leading_zeros()

◆ allow_unquoted_control_chars()

◆ builder()

◆ enable_dayfirst()

◆ enable_experimental()

◆ enable_keep_quotes()

◆ enable_lines()

◆ enable_mixed_types_as_string()

◆ enable_normalize_single_quotes()

◆ enable_normalize_whitespace()

◆ enable_prune_columns()

◆ get_byte_range_offset()

◆ get_byte_range_padding()

◆ get_byte_range_size()

◆ get_byte_range_size_with_padding()

◆ get_compression()

◆ get_delimiter()

◆ get_dtypes()

◆ get_na_values()

◆ get_source()

◆ is_allowed_nonnumeric_numbers()

◆ is_allowed_numeric_leading_zeros()

◆ is_allowed_unquoted_control_chars()

◆ is_enabled_dayfirst()

◆ is_enabled_experimental()

◆ is_enabled_keep_quotes()

◆ is_enabled_lines()

◆ is_enabled_mixed_types_as_string()

◆ is_enabled_normalize_single_quotes()

◆ is_enabled_normalize_whitespace()

◆ is_enabled_prune_columns()

◆ is_strict_validation()

◆ recovery_mode()

◆ set_byte_range_offset()

◆ set_byte_range_size()

◆ set_compression()

◆ set_delimiter()

◆ set_dtypes() [1/4]

◆ set_dtypes() [2/4]

◆ set_dtypes() [3/4]

◆ set_dtypes() [4/4]

◆ set_na_values()

◆ set_recovery_mode()

◆ set_strict_validation()