Abstract base class which provides CSV parsing logic. More...

#include <basic_csv_parser.hpp>

Inherited by csv::internals::MmapParser, and csv::internals::StreamParser< TStream >.

Public Member Functions
	IBasicCSVParser (const CSVFormat &, const ColNamesPtr &)

	IBasicCSVParser (const ParseFlagMap &parse_flags, const WhitespaceMap &ws_flags)

bool	eof ()
	Whether or not we have reached the end of source.

ResolvedFormat	get_resolved_format ()

virtual void	next (size_t bytes)=0
	Parse the next block of data.

void	end_feed ()
	Indicate the last block of data has been parsed.

CONSTEXPR_17 ParseFlags	parse_flag (const char ch) const noexcept

CONSTEXPR_17 ParseFlags	compound_parse_flag (const char ch) const noexcept

CONSTEXPR bool	utf8_bom () const
	Whether or not this CSV has a UTF-8 byte order mark.

void	set_output (RowCollection &rows)

Protected Member Functions
virtual std::string &	get_csv_head ()=0

CONSTEXPR bool	no_chunk () const
	Whether or not source needs to be read in chunks.

size_t	parse ()
	Parse the current chunk of data and return the completed-row prefix length.

void	reset_data_ptr ()
	Create a new RawCSVDataPtr for a new chunk of data.

void	resolve_format_from_head (const CSVFormat &format)

Protected Attributes
Current Parser State
CSVRow	current_row_

RawCSVDataPtr	data_ptr_ = nullptr

ColNamesPtr	col_names_ = nullptr

RawCSVFieldList *	fields_ = nullptr

int	field_start_ = UNINITIALIZED_FIELD

size_t	field_length_ = 0

SentinelVecs	simd_sentinels_
	Precomputed SIMD broadcast vectors for find_next_non_special.

ParseFlagMap	parse_flags_
	An array where the (i + 128)th slot gives the ParseFlags for ASCII character i.

Current Stream/File State
bool	eof_ = false

ResolvedFormat	format

size_t	source_size_ = 0
	The size of the incoming CSV.

Detailed Description

Abstract base class which provides CSV parsing logic.

Concrete implementations may customize this logic across different input sources, such as memory mapped files, stringstreams, etc...

Definition at line 177 of file basic_csv_parser.hpp.

Constructor & Destructor Documentation

◆ IBasicCSVParser() [1/2]

csv::internals::IBasicCSVParser::IBasicCSVParser	(	const CSVFormat &	source_format,
		const ColNamesPtr &	col_names
	)

Definition at line 49 of file basic_csv_parser.cpp.

◆ IBasicCSVParser() [2/2]

csv::internals::IBasicCSVParser::IBasicCSVParser	(	const ParseFlagMap &	parse_flags,
		const WhitespaceMap &	ws_flags
	)

inline

Definition at line 181 of file basic_csv_parser.hpp.

◆ ~IBasicCSVParser()

virtual csv::internals::IBasicCSVParser::~IBasicCSVParser ( )

inlinevirtual

Definition at line 190 of file basic_csv_parser.hpp.

Member Function Documentation

◆ compound_parse_flag()

CONSTEXPR_17 ParseFlags csv::internals::IBasicCSVParser::compound_parse_flag ( const char ch ) const

inlinenoexcept

Definition at line 207 of file basic_csv_parser.hpp.

◆ end_feed()

void csv::internals::IBasicCSVParser::end_feed ( )

Indicate the last block of data has been parsed.

Definition at line 107 of file basic_csv_parser.cpp.

◆ eof()

bool csv::internals::IBasicCSVParser::eof ( )

inline

Whether or not we have reached the end of source.

Definition at line 193 of file basic_csv_parser.hpp.

◆ get_resolved_format()

ResolvedFormat csv::internals::IBasicCSVParser::get_resolved_format ( )

inline

Definition at line 195 of file basic_csv_parser.hpp.

◆ next()

virtual void csv::internals::IBasicCSVParser::next ( size_t bytes )

pure virtual

Parse the next block of data.

Implemented in csv::internals::MmapParser, and csv::internals::StreamParser< TStream >.

◆ no_chunk()

CONSTEXPR bool csv::internals::IBasicCSVParser::no_chunk ( ) const

inlineprotected

Whether or not source needs to be read in chunks.

Definition at line 246 of file basic_csv_parser.hpp.

◆ parse()

size_t csv::internals::IBasicCSVParser::parse ( )

protected

Parse the current chunk of data and return the completed-row prefix length.

Parse the current chunk and return the number of bytes belonging to complete rows.

Definition at line 171 of file basic_csv_parser.cpp.

◆ parse_flag()

CONSTEXPR_17 ParseFlags csv::internals::IBasicCSVParser::parse_flag ( const char ch ) const

inlinenoexcept

Definition at line 203 of file basic_csv_parser.hpp.

◆ reset_data_ptr()

void csv::internals::IBasicCSVParser::reset_data_ptr ( )

protected

Create a new RawCSVDataPtr for a new chunk of data.

Definition at line 269 of file basic_csv_parser.cpp.

◆ resolve_format_from_head()

void csv::internals::IBasicCSVParser::resolve_format_from_head ( const CSVFormat & format )

protected

Definition at line 62 of file basic_csv_parser.cpp.

◆ set_output()

void csv::internals::IBasicCSVParser::set_output ( RowCollection & rows )

inline

Definition at line 214 of file basic_csv_parser.hpp.

◆ utf8_bom()

CONSTEXPR bool csv::internals::IBasicCSVParser::utf8_bom ( ) const

inline

Whether or not this CSV has a UTF-8 byte order mark.

Definition at line 212 of file basic_csv_parser.hpp.

Member Data Documentation

◆ col_names_

ColNamesPtr csv::internals::IBasicCSVParser::col_names_ = nullptr

protected

Definition at line 221 of file basic_csv_parser.hpp.

◆ current_row_

CSVRow csv::internals::IBasicCSVParser::current_row_

protected

Definition at line 219 of file basic_csv_parser.hpp.

◆ data_ptr_

RawCSVDataPtr csv::internals::IBasicCSVParser::data_ptr_ = nullptr

protected

Definition at line 220 of file basic_csv_parser.hpp.

◆ eof_

bool csv::internals::IBasicCSVParser::eof_ = false

protected

Definition at line 235 of file basic_csv_parser.hpp.

◆ field_length_

size_t csv::internals::IBasicCSVParser::field_length_ = 0

protected

Definition at line 224 of file basic_csv_parser.hpp.

◆ field_start_

int csv::internals::IBasicCSVParser::field_start_ = UNINITIALIZED_FIELD

protected

Definition at line 223 of file basic_csv_parser.hpp.

◆ fields_

RawCSVFieldList* csv::internals::IBasicCSVParser::fields_ = nullptr

protected

Definition at line 222 of file basic_csv_parser.hpp.

◆ format

ResolvedFormat csv::internals::IBasicCSVParser::format

protected

Definition at line 237 of file basic_csv_parser.hpp.

◆ parse_flags_

ParseFlagMap csv::internals::IBasicCSVParser::parse_flags_

protected

An array where the (i + 128)th slot gives the ParseFlags for ASCII character i.

Definition at line 230 of file basic_csv_parser.hpp.

◆ simd_sentinels_

SentinelVecs csv::internals::IBasicCSVParser::simd_sentinels_

protected

Precomputed SIMD broadcast vectors for find_next_non_special.

Definition at line 227 of file basic_csv_parser.hpp.

◆ source_size_

size_t csv::internals::IBasicCSVParser::source_size_ = 0

protected

The size of the incoming CSV.

Definition at line 240 of file basic_csv_parser.hpp.

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

include/internal/basic_csv_parser.hpp
include/internal/basic_csv_parser.cpp

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Constructor & Destructor Documentation

◆ IBasicCSVParser() [1/2]

◆ IBasicCSVParser() [2/2]

◆ ~IBasicCSVParser()

Member Function Documentation

◆ compound_parse_flag()

◆ end_feed()

◆ eof()

◆ get_resolved_format()

◆ next()

◆ no_chunk()

◆ parse()

◆ parse_flag()

◆ reset_data_ptr()

◆ resolve_format_from_head()

◆ set_output()

◆ utf8_bom()

Member Data Documentation

◆ col_names_

◆ current_row_

◆ data_ptr_

◆ eof_

◆ field_length_

◆ field_start_

◆ fields_

◆ format

◆ parse_flags_

◆ simd_sentinels_

◆ source_size_