LIMA
Libre Multilingual Analyzer — C++ API
Loading...
Searching...
No Matches
Lima::Common::BagOfWords::BoWTerm Class Reference

This is a complex token used to represent a multiword term. More...

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

Inheritance diagram for Lima::Common::BagOfWords::BoWTerm:
Lima::Common::BagOfWords::BoWComplexToken Lima::Common::BagOfWords::BoWToken Lima::Common::BagOfWords::AbstractBoWElement

Public Member Functions

 BoWTerm ()
 
 BoWTerm (const BoWTerm &)
 
 BoWTerm (const Lima::LimaString &lemma, const LinguisticCode category, const uint64_t position, const uint64_t length)
 
 BoWTerm (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)
 
virtual ~BoWTerm ()
 
virtual BoWTerm * clone () const override
 
BoWTerm & operator= (const BoWTerm &)
 
virtual BoWType getType () const override
 
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 (void) const override
 function used to identify a bowtoken in a text (used in BowDumper)
 
- Public Member Functions inherited from Lima::Common::BagOfWords::BoWComplexToken
 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)
 
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 ()
 
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)
 
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

 BoWTerm (BoWTermPrivate &)
 
- Protected Member Functions inherited from Lima::Common::BagOfWords::BoWComplexToken
 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)
 

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 used to represent a multiword term.

Author
Gael de Chalendar

Definition at line 35 of file bowTerm.h.

Constructor & Destructor Documentation

◆ BoWTerm() [1/5]

Lima::Common::BagOfWords::BoWTerm::BoWTerm ( )

Definition at line 36 of file bowTerm.cpp.

◆ BoWTerm() [2/5]

Lima::Common::BagOfWords::BoWTerm::BoWTerm ( const BoWTerm &  t)

Definition at line 40 of file bowTerm.cpp.

◆ BoWTerm() [3/5]

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

Definition at line 51 of file bowTerm.cpp.

◆ BoWTerm() [4/5]

Lima::Common::BagOfWords::BoWTerm::BoWTerm ( 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 
)

◆ ~BoWTerm()

Lima::Common::BagOfWords::BoWTerm::~BoWTerm ( )
virtual

Definition at line 83 of file bowTerm.cpp.

◆ BoWTerm() [5/5]

Lima::Common::BagOfWords::BoWTerm::BoWTerm ( BoWTermPrivate &  d)
protected

Definition at line 45 of file bowTerm.cpp.

Member Function Documentation

◆ clone()

BoWTerm * Lima::Common::BagOfWords::BoWTerm::clone ( ) const
overridevirtual

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

Definition at line 94 of file bowTerm.cpp.

◆ getIdUTF8String()

std::string Lima::Common::BagOfWords::BoWTerm::getIdUTF8String ( void  ) const
overridevirtual

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

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

Definition at line 109 of file bowTerm.cpp.

◆ getOutputUTF8String()

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

get a string of the BoWToken for output function

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

Definition at line 103 of file bowTerm.cpp.

◆ getType()

virtual BoWType Lima::Common::BagOfWords::BoWTerm::getType ( ) const
inlineoverridevirtual

Implements Lima::Common::BagOfWords::BoWComplexToken.

Definition at line 60 of file bowTerm.h.

◆ operator=()

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

Definition at line 88 of file bowTerm.cpp.


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