This class contains the representation of an element of the bag of words. More...

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

Inheritance diagram for Lima::Common::BagOfWords::BoWToken:

Public Member Functions
	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 void	clear () override

virtual BoWToken *	clone () const override

virtual Lima::LimaString	getLemma (void) const

virtual Lima::LimaString	getInflectedForm (void) const

LinguisticCode	getCategory (void) const

uint64_t	getPosition (void) const override

uint64_t	getLength (void) const override

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

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

virtual BoWType	getType () const override

uint64_t	getVertex () const

void	setVertex (uint64_t vertex)

virtual std::set< uint64_t >	getVertices () const override
	returns a singleton made of the value of the getVertex function.

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.

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

virtual void	addToPosition (const uint64_t offset)
	add the offset to the position of the token

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

virtual	~AbstractBoWElement ()

Static Public Member Functions
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 Member Functions
	BoWToken (BoWTokenPrivate &d)

BoWToken &	operator= (const BoWToken &tok)

bool	operator== (const BoWToken &tok)

Protected Attributes
BoWTokenPrivate *	m_d

Friends
class	BoWTokenPrivate

LIMA_BOW_EXPORT std::ostream &	operator<< (std::ostream &, const BoWToken &)

LIMA_BOW_EXPORT QDebug &	operator<< (QDebug &, const BoWToken &)

LIMA_BOW_EXPORT std::ostream &	operator<< (std::ostream &os, const Common::Misc::PositionLengthList &p)

LIMA_BOW_EXPORT QDebug &	operator<< (QDebug &os, const Common::Misc::PositionLengthList &p)

LIMA_BOW_EXPORT std::ostream &	operator<< (std::ostream &os, const std::map< BoWToken *, uint64_t > &refMap)
	only for debug

LIMA_BOW_EXPORT QDebug &	operator<< (QDebug &os, const std::map< BoWToken *, uint64_t > &refMap)

Detailed Description

This class contains the representation of an element of the bag of words.

This element is characterized by a normalized form, a grammatical category, its position and length. It can be a simple word, a multiterm or a named entity.

Definition at line 45 of file bowToken.h.

Constructor & Destructor Documentation

◆ BoWToken() [1/5]

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

◆ BoWToken() [2/5]

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

◆ BoWToken() [3/5]

Lima::Common::BagOfWords::BoWToken::BoWToken ( const BoWToken & tok )

Definition at line 204 of file bowToken.cpp.

◆ BoWToken() [4/5]

Lima::Common::BagOfWords::BoWToken::BoWToken ( )

Definition at line 182 of file bowToken.cpp.

◆ ~BoWToken()

Lima::Common::BagOfWords::BoWToken::~BoWToken ( )

virtual

Definition at line 274 of file bowToken.cpp.

◆ BoWToken() [5/5]

Lima::Common::BagOfWords::BoWToken::BoWToken ( BoWTokenPrivate & d )

protected

Definition at line 173 of file bowToken.cpp.

Member Function Documentation

◆ addToPosition()

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

virtual

add the offset to the position of the token

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 326 of file bowToken.cpp.

◆ clear()

virtual void Lima::Common::BagOfWords::BoWToken::clear ( )

inlineoverridevirtual

Reimplemented from Lima::Common::BagOfWords::AbstractBoWElement.

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 62 of file bowToken.h.

◆ clone()

BoWToken * Lima::Common::BagOfWords::BoWToken::clone ( ) const

overridevirtual

Implements Lima::Common::BagOfWords::AbstractBoWElement.

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

Definition at line 255 of file bowToken.cpp.

◆ getCategory()

LinguisticCode Lima::Common::BagOfWords::BoWToken::getCategory ( void ) const

Definition at line 285 of file bowToken.cpp.

◆ getCompoundSeparator()

LimaChar Lima::Common::BagOfWords::BoWToken::getCompoundSeparator ( )

static

Definition at line 321 of file bowToken.cpp.

◆ getIdUTF8String()

std::string Lima::Common::BagOfWords::BoWToken::getIdUTF8String ( void ) const

overridevirtual

function used to identify a bowtoken in a text (used in BowDumper)

Implements Lima::Common::BagOfWords::AbstractBoWElement.

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

Definition at line 446 of file bowToken.cpp.

◆ getInflectedForm()

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

virtual

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 284 of file bowToken.cpp.

◆ getInternalSeparator()

LimaChar Lima::Common::BagOfWords::BoWToken::getInternalSeparator ( )

static

Definition at line 317 of file bowToken.cpp.

◆ getLemma()

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

virtual

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 283 of file bowToken.cpp.

◆ getLength()

uint64_t Lima::Common::BagOfWords::BoWToken::getLength ( void ) const

overridevirtual

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Definition at line 287 of file bowToken.cpp.

◆ getOutputUTF8String()

std::string Lima::Common::BagOfWords::BoWToken::getOutputUTF8String ( const Common::PropertyCode::PropertyManager * macroManager = 0 ) const

overridevirtual

get a string of the BoWToken for output function

Parameters

macroAccessor if not null, will output the human readable form of the macrocategory. otherwise output the integer code

Implements Lima::Common::BagOfWords::AbstractBoWElement.

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

Definition at line 430 of file bowToken.cpp.

◆ getPosition()

uint64_t Lima::Common::BagOfWords::BoWToken::getPosition ( void ) const

overridevirtual

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Definition at line 286 of file bowToken.cpp.

◆ getPositionLengthList()

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

virtual

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

Returns

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 382 of file bowToken.cpp.

◆ getString()

LimaString Lima::Common::BagOfWords::BoWToken::getString ( void ) const

overridevirtual

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Definition at line 332 of file bowToken.cpp.

◆ getType()

BoWType Lima::Common::BagOfWords::BoWToken::getType ( ) const

overridevirtual

Reimplemented from Lima::Common::BagOfWords::AbstractBoWElement.

Reimplemented in Lima::Common::BagOfWords::BoWNamedEntity, Lima::Common::BagOfWords::BoWTerm, and Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 299 of file bowToken.cpp.

◆ getUseOnlyLemma()

bool Lima::Common::BagOfWords::BoWToken::getUseOnlyLemma ( )

static

Definition at line 305 of file bowToken.cpp.

◆ getVertex()

uint64_t Lima::Common::BagOfWords::BoWToken::getVertex ( ) const

Definition at line 301 of file bowToken.cpp.

◆ getVertices()

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

overridevirtual

returns a singleton made of the value of the getVertex function.

Subclasses like BoWComplexToken reimplement this method to return the set of vertices of all their parts.

Returns: a singleton made of the value of the getVertex function

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken, and Lima::Common::BagOfWords::BoWNamedEntity.

Definition at line 454 of file bowToken.cpp.

◆ operator!=()

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

redefine inequality as negation of equality.

Author: Benoit Mathieu

Definition at line 407 of file bowToken.cpp.

◆ operator=()

BoWToken & Lima::Common::BagOfWords::BoWToken::operator= ( const BoWToken & tok )

protected

Definition at line 213 of file bowToken.cpp.

◆ operator==() [1/2]

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

redefine equality

Author

Benoit Mathieu return true if :

objects have the same BowType
objects have the same category
objects have the same lemma
if objects are of BoWNamedEntity type, objects have the same NamedEntityType.

Definition at line 394 of file bowToken.cpp.

◆ operator==() [2/2]

bool Lima::Common::BagOfWords::BoWToken::operator== ( const BoWToken & tok )

protected

Definition at line 223 of file bowToken.cpp.

◆ setCategory()

void Lima::Common::BagOfWords::BoWToken::setCategory ( LinguisticCode c )

Definition at line 295 of file bowToken.cpp.

◆ setCompoundSeparator()

void Lima::Common::BagOfWords::BoWToken::setCompoundSeparator ( const LimaChar c )

static

Definition at line 312 of file bowToken.cpp.

◆ setInflectedForm()

void Lima::Common::BagOfWords::BoWToken::setInflectedForm ( const Lima::LimaString & inflectedForm )

Definition at line 293 of file bowToken.cpp.

◆ setInternalSeparator()

void Lima::Common::BagOfWords::BoWToken::setInternalSeparator ( const LimaChar c )

static

Definition at line 308 of file bowToken.cpp.

◆ setLemma()

void Lima::Common::BagOfWords::BoWToken::setLemma ( const Lima::LimaString & lemma )

Definition at line 292 of file bowToken.cpp.

◆ setLength()

void Lima::Common::BagOfWords::BoWToken::setLength ( const uint64_t len )

overridevirtual

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Definition at line 297 of file bowToken.cpp.

◆ setPosition()

void Lima::Common::BagOfWords::BoWToken::setPosition ( const uint64_t pos )

overridevirtual

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Definition at line 296 of file bowToken.cpp.

◆ setUseOnlyLemma()

void Lima::Common::BagOfWords::BoWToken::setUseOnlyLemma ( const bool b )

static

Definition at line 304 of file bowToken.cpp.

◆ setVertex()

void Lima::Common::BagOfWords::BoWToken::setVertex ( uint64_t vertex )

Definition at line 302 of file bowToken.cpp.

◆ size()

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

overridevirtual

size of the BoWToken is the number of parts in the token

Implements Lima::Common::BagOfWords::AbstractBoWElement.

Reimplemented in Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 290 of file bowToken.cpp.

Friends And Related Symbol Documentation

◆ BoWTokenPrivate

friend class BoWTokenPrivate

friend

Definition at line 47 of file bowToken.h.

◆ operator<< [1/6]

LIMA_BOW_EXPORT QDebug & operator<<	(	QDebug &	os,
		const BoWToken &	tok
	)

friend

Definition at line 423 of file bowToken.cpp.

◆ operator<< [2/6]

LIMA_BOW_EXPORT QDebug & operator<<	(	QDebug &	os,
		const Common::Misc::PositionLengthList &	p
	)

friend

Definition at line 56 of file positionLengthList.cpp.

◆ operator<< [3/6]

LIMA_BOW_EXPORT QDebug & operator<<	(	QDebug &	os,
		const std::map< BoWToken *, uint64_t > &	refMap
	)

friend

◆ operator<< [4/6]

LIMA_BOW_EXPORT std::ostream & operator<<	(	std::ostream &	os,
		const BoWToken &	tok
	)

friend

Definition at line 416 of file bowToken.cpp.

◆ operator<< [5/6]

LIMA_BOW_EXPORT std::ostream & operator<<	(	std::ostream &	os,
		const Common::Misc::PositionLengthList &	p
	)

friend

Definition at line 39 of file positionLengthList.cpp.

◆ operator<< [6/6]

LIMA_BOW_EXPORT std::ostream & operator<<	(	std::ostream &	os,
		const std::map< BoWToken *, uint64_t > &	refMap
	)

friend

only for debug

Member Data Documentation

◆ m_d

BoWTokenPrivate* Lima::Common::BagOfWords::BoWToken::m_d

protected

Definition at line 166 of file bowToken.h.

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

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

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Friends

Detailed Description

Constructor & Destructor Documentation

◆ BoWToken() [1/5]

◆ BoWToken() [2/5]

◆ BoWToken() [3/5]

◆ BoWToken() [4/5]

◆ ~BoWToken()

◆ BoWToken() [5/5]

Member Function Documentation

◆ addToPosition()

◆ clear()

◆ clone()

◆ getCategory()

◆ getCompoundSeparator()

◆ getIdUTF8String()

◆ getInflectedForm()

◆ getInternalSeparator()

◆ getLemma()

◆ getLength()

◆ getOutputUTF8String()

◆ getPosition()

◆ getPositionLengthList()

◆ getString()

◆ getType()

◆ getUseOnlyLemma()

◆ getVertex()

◆ getVertices()

◆ operator!=()

◆ operator=()

◆ operator==() [1/2]

◆ operator==() [2/2]

◆ setCategory()

◆ setCompoundSeparator()

◆ setInflectedForm()

◆ setInternalSeparator()

◆ setLemma()

◆ setLength()

◆ setPosition()

◆ setUseOnlyLemma()

◆ setVertex()

◆ size()

Friends And Related Symbol Documentation

◆ BoWTokenPrivate

◆ operator<< [1/6]

◆ operator<< [2/6]

◆ operator<< [3/6]

◆ operator<< [4/6]

◆ operator<< [5/6]

◆ operator<< [6/6]

Member Data Documentation

◆ m_d