This is a complex token for an index. More...

#include <linguisticProcessing/common/BagOfWords/bowComplexToken.h>

Inheritance diagram for Lima::Common::BagOfWords::BoWComplexToken:

Classes
class	Part
	This class represents a part of a ComplexToken : it is composed of a pointer on the actual part (a BoWToken), and a boolean that says if the BoWToken is also in the global list (the BoWText) or not. More...

Public Member Functions
	BoWComplexToken ()

	BoWComplexToken (const Lima::LimaString &lemma, const LinguisticCode category, const uint64_t position, const uint64_t length)

	BoWComplexToken (const Lima::LimaString &lemma, const LinguisticCode category, const uint64_t position, const uint64_t length, std::deque< boost::shared_ptr< Lima::Common::BagOfWords::BoWToken > > &parts, const uint64_t head)
	a constructor to build a simple, independent complex token (parts are simple tokens, not listed elsewhere in a BoWText)

virtual	~BoWComplexToken ()

virtual void	clear () override

virtual Lima::LimaString	getLemma (void) const override

virtual Lima::LimaString	getInflectedForm (void) const override

BoWComplexToken &	operator= (const BoWComplexToken &)

bool	operator== (const BoWComplexToken &)

uint64_t	size (void) const override
	size is the number of parts in the token

std::deque< Part > &	getParts (void)

const std::deque< Part > &	getParts (void) const

std::deque< Part >::iterator	getPartsIterator (void)

const std::deque< Part >::const_iterator	getPartsIterator (void) const

boost::shared_ptr< BoWToken >	addPart (boost::shared_ptr< BoWToken > tok, const bool isHead=false)
	add a part in the list of parts of the complex token.

boost::shared_ptr< BoWToken >	addPart (boost::shared_ptr< BoWRelation > rel, boost::shared_ptr< BoWToken > tok, const bool isHead=false)
	add a part in the list of parts of the complex token.

uint64_t	getHead () const
	add a part in the list of parts of the complex token.

void	setHead (const uint64_t)

virtual BoWType	getType () const override=0

std::string	getUTF8StringParts (const Common::PropertyCode::PropertyManager *macroManager=0) const

std::string	getstdstringParts () const

virtual Common::Misc::PositionLengthList	getPositionLengthList () const override
	get the list of (position,length) couples of the elements of the token (if several)

void	addToPosition (const uint64_t offset) override
	add the offset to the positions of the token and of each of its parts (recusrively)

virtual std::set< uint64_t >	getVertices () const override
	returns the vertices of all its parts

Public Member Functions inherited from Lima::Common::BagOfWords::BoWToken
	BoWToken (const Lima::LimaString &lemma, const LinguisticCode category, const uint64_t position, const uint64_t length)

	BoWToken (const Lima::LimaString &str, const uint64_t position=0, const uint64_t length=0)

	BoWToken (const BoWToken &tok)

	BoWToken ()

virtual	~BoWToken ()

virtual BoWToken *	clone () const override

LinguisticCode	getCategory (void) const

uint64_t	getPosition (void) const override

uint64_t	getLength (void) const override

void	setLemma (const Lima::LimaString &lemma)

void	setInflectedForm (const Lima::LimaString &inflectedForm)

void	setCategory (LinguisticCode c)

void	setPosition (const uint64_t pos) override

void	setLength (const uint64_t len) override

virtual Lima::LimaString	getString (void) const override

uint64_t	getVertex () const

void	setVertex (uint64_t vertex)

virtual std::string	getOutputUTF8String (const Common::PropertyCode::PropertyManager *macroManager=0) const override
	get a string of the BoWToken for output function

virtual std::string	getIdUTF8String () const override
	function used to identify a bowtoken in a text (used in BowDumper)

bool	operator== (const BoWToken &) const
	redefine equality

bool	operator!= (const BoWToken &) const
	redefine inequality as negation of equality.

Public Member Functions inherited from Lima::Common::BagOfWords::AbstractBoWElement
	AbstractBoWElement ()

virtual	~AbstractBoWElement ()

Protected Member Functions
	BoWComplexToken (BoWComplexTokenPrivate &d)

Protected Member Functions inherited from Lima::Common::BagOfWords::BoWToken
	BoWToken (BoWTokenPrivate &d)

BoWToken &	operator= (const BoWToken &tok)

bool	operator== (const BoWToken &tok)

Friends
class	BoWComplexTokenPrivate

Additional Inherited Members
Static Public Member Functions inherited from Lima::Common::BagOfWords::BoWToken
static void	setInternalSeparator (const LimaChar c)

static void	setCompoundSeparator (const LimaChar c)

static LimaChar	getInternalSeparator ()

static LimaChar	getCompoundSeparator ()

static void	setUseOnlyLemma (const bool b)

static bool	getUseOnlyLemma ()

Protected Attributes inherited from Lima::Common::BagOfWords::BoWToken
BoWTokenPrivate *	m_d

Detailed Description

This is a complex token for an index.

It is made of a collection of BoWTokens's, one of which is the head of the token.

Author: Romaric Besancon

Definition at line 42 of file bowComplexToken.h.

Constructor & Destructor Documentation

◆ BoWComplexToken() [1/4]

Lima::Common::BagOfWords::BoWComplexToken::BoWComplexToken ( )

Definition at line 95 of file bowComplexToken.cpp.

◆ BoWComplexToken() [2/4]

Lima::Common::BagOfWords::BoWComplexToken::BoWComplexToken	(	const Lima::LimaString &	lemma,
		const LinguisticCode	category,
		const uint64_t	position,
		const uint64_t	length
	)

◆ BoWComplexToken() [3/4]

Lima::Common::BagOfWords::BoWComplexToken::BoWComplexToken	(	const Lima::LimaString &	lemma,
		const LinguisticCode	category,
		const uint64_t	position,
		const uint64_t	length,
		std::deque< boost::shared_ptr< Lima::Common::BagOfWords::BoWToken > > &	parts,
		const uint64_t	head
	)

a constructor to build a simple, independent complex token (parts are simple tokens, not listed elsewhere in a BoWText)

Parameters

lemma	the lemma of the complex token
category	the category of the complex token
position	the position of the complex token
length	the length of the complex token
parts	a deque containing the simple tokens forming the parts of the complex token
int	head the index of the head token in the preceding list

Returns

◆ ~BoWComplexToken()

Lima::Common::BagOfWords::BoWComplexToken::~BoWComplexToken ( )

virtual

Definition at line 140 of file bowComplexToken.cpp.

◆ BoWComplexToken() [4/4]

Lima::Common::BagOfWords::BoWComplexToken::BoWComplexToken ( BoWComplexTokenPrivate & d )

protected

Definition at line 136 of file bowComplexToken.cpp.

Member Function Documentation

◆ addPart() [1/2]

boost::shared_ptr< BoWToken > Lima::Common::BagOfWords::BoWComplexToken::addPart	(	boost::shared_ptr< BoWRelation >	rel,
		boost::shared_ptr< BoWToken >	tok,
		const bool	isHead = `false`
	)

add a part in the list of parts of the complex token.

Have to specify if the token forming the part exists as a proper token or only as a part: in the first case, the pointer is added in the part list, in the second case, a pointer on a copy of the token is added in the list.

Parameters

rel	a pointer on the BoWRelation linking the part to add to the head or the other parts
tok	a pointer on the BoWToken forming the part to add
isInList	a boolean indicating, if true, that the BoWToken pointed has an existence outside of the part list
isHead	a boolean indicating that the BoWToken a

Definition at line 257 of file bowComplexToken.cpp.

◆ addPart() [2/2]

boost::shared_ptr< BoWToken > Lima::Common::BagOfWords::BoWComplexToken::addPart	(	boost::shared_ptr< BoWToken >	tok,
		const bool	isHead = `false`
	)

add a part in the list of parts of the complex token.

Have to specify if the token forming the part exists as a proper token or only as a part: in the first case, the pointer is added in the part list, in the second case, a pointer on a copy of the token is added in the list.

Parameters

tok	a pointer on the BoWToken forming the part to add
isInList	a boolean indicating, if true, that the BoWToken pointed has an existence outside of the part list
isHead	a boolean indicating that the BoWToken a

Definition at line 250 of file bowComplexToken.cpp.

◆ addToPosition()

void Lima::Common::BagOfWords::BoWComplexToken::addToPosition ( const uint64_t offset )

overridevirtual

add the offset to the positions of the token and of each of its parts (recusrively)

Parameters

offset the offset to add to all positions

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Definition at line 367 of file bowComplexToken.cpp.

◆ clear()

void Lima::Common::BagOfWords::BoWComplexToken::clear ( )

overridevirtual

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Definition at line 280 of file bowComplexToken.cpp.

◆ getHead()

uint64_t Lima::Common::BagOfWords::BoWComplexToken::getHead ( ) const

add a part in the list of parts of the complex token.

A pointer on a copy of tok is added in the list.

Parameters

tok	a pointer on the BoWToken forming the part to be copied and added
isHead	a boolean indicating that the BoWToken is the head of the complex token it is part of add a part in the list of parts of the complex token. A pointer on a copy of tok is added in the list.
rel	a pointer on the BoWRelation linking the part to copy and add to the head or the other parts
tok	a pointer on the BoWToken forming the part to be copied and added
isHead	a boolean indicating that the BoWToken is the head of the complex token it is part of

Definition at line 210 of file bowComplexToken.cpp.

◆ getInflectedForm()

LimaString Lima::Common::BagOfWords::BoWComplexToken::getInflectedForm ( void ) const

overridevirtual

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Definition at line 317 of file bowComplexToken.cpp.

◆ getLemma()

LimaString Lima::Common::BagOfWords::BoWComplexToken::getLemma ( void ) const

overridevirtual

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Definition at line 299 of file bowComplexToken.cpp.

◆ getParts() [1/2]

std::deque< BoWComplexToken::Part > & Lima::Common::BagOfWords::BoWComplexToken::getParts ( void )

Definition at line 187 of file bowComplexToken.cpp.

◆ getParts() [2/2]

const std::deque< BoWComplexToken::Part > & Lima::Common::BagOfWords::BoWComplexToken::getParts ( void ) const

Definition at line 193 of file bowComplexToken.cpp.

◆ getPartsIterator() [1/2]

std::deque< BoWComplexToken::Part >::iterator Lima::Common::BagOfWords::BoWComplexToken::getPartsIterator ( void )

Definition at line 199 of file bowComplexToken.cpp.

◆ getPartsIterator() [2/2]

const std::deque< BoWComplexToken::Part >::const_iterator Lima::Common::BagOfWords::BoWComplexToken::getPartsIterator ( void ) const

Definition at line 205 of file bowComplexToken.cpp.

◆ getPositionLengthList()

Common::Misc::PositionLengthList Lima::Common::BagOfWords::BoWComplexToken::getPositionLengthList ( ) const

overridevirtual

get the list of (position,length) couples of the elements of the token (if several)

Returns

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Definition at line 352 of file bowComplexToken.cpp.

◆ getstdstringParts()

std::string Lima::Common::BagOfWords::BoWComplexToken::getstdstringParts ( ) const

Definition at line 402 of file bowComplexToken.cpp.

◆ getType()

virtual BoWType Lima::Common::BagOfWords::BoWComplexToken::getType ( ) const

overridepure virtual

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Implemented in Lima::Common::BagOfWords::BoWNamedEntity, and Lima::Common::BagOfWords::BoWTerm.

◆ getUTF8StringParts()

std::string Lima::Common::BagOfWords::BoWComplexToken::getUTF8StringParts ( const Common::PropertyCode::PropertyManager * macroManager = 0 ) const

Definition at line 379 of file bowComplexToken.cpp.

◆ getVertices()

std::set< uint64_t > Lima::Common::BagOfWords::BoWComplexToken::getVertices ( ) const

overridevirtual

returns the vertices of all its parts

Returns: the vertices of all its parts

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Reimplemented in Lima::Common::BagOfWords::BoWNamedEntity.

Definition at line 420 of file bowComplexToken.cpp.

◆ operator=()

BoWComplexToken & Lima::Common::BagOfWords::BoWComplexToken::operator= ( const BoWComplexToken & t )

Definition at line 146 of file bowComplexToken.cpp.

◆ operator==()

bool Lima::Common::BagOfWords::BoWComplexToken::operator== ( const BoWComplexToken & t )

Definition at line 155 of file bowComplexToken.cpp.

◆ setHead()

void Lima::Common::BagOfWords::BoWComplexToken::setHead ( const uint64_t i )

Definition at line 215 of file bowComplexToken.cpp.

◆ size()

uint64_t Lima::Common::BagOfWords::BoWComplexToken::size ( void ) const

overridevirtual

size is the number of parts in the token

Reimplemented from Lima::Common::BagOfWords::BoWToken.

Definition at line 337 of file bowComplexToken.cpp.

Friends And Related Symbol Documentation

◆ BoWComplexTokenPrivate

friend class BoWComplexTokenPrivate

friend

Definition at line 44 of file bowComplexToken.h.

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

lima_linguisticprocessing/src/linguisticProcessing/common/BagOfWords/bowComplexToken.h
lima_linguisticprocessing/src/linguisticProcessing/common/BagOfWords/bowComplexToken.cpp

Classes

Public Member Functions

Protected Member Functions

Friends

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ BoWComplexToken() [1/4]

◆ BoWComplexToken() [2/4]

◆ BoWComplexToken() [3/4]

◆ ~BoWComplexToken()

◆ BoWComplexToken() [4/4]

Member Function Documentation

◆ addPart() [1/2]

◆ addPart() [2/2]

◆ addToPosition()

◆ clear()

◆ getHead()

◆ getInflectedForm()

◆ getLemma()

◆ getParts() [1/2]

◆ getParts() [2/2]

◆ getPartsIterator() [1/2]

◆ getPartsIterator() [2/2]

◆ getPositionLengthList()

◆ getstdstringParts()

◆ getType()

◆ getUTF8StringParts()

◆ getVertices()

◆ operator=()

◆ operator==()

◆ setHead()

◆ size()

Friends And Related Symbol Documentation

◆ BoWComplexTokenPrivate