LIMA
Libre Multilingual Analyzer — C++ API
Loading...
Searching...
No Matches
Lima::LinguisticProcessing::FlatTokenizer::CharChart Class Reference

#include <linguisticProcessing/core/FlatTokenizer/CharChart.h>

Inheritance diagram for Lima::LinguisticProcessing::FlatTokenizer::CharChart:
Lima::LinguisticProcessing::AbstractResource Lima::LinguisticProcessing::AbstractResourceBase Lima::InitializableObject< AbstractResource, ResourceInitializationParameters >

Public Member Functions

 CharChart ()
 
virtual ~CharChart ()
 
void init (Common::XMLConfigurationFiles::GroupConfigurationStructure &, Manager *) override
 
const std::vector< CharClass * > & classes () const
 
const std::vector< Char * > & chars () const
 
std::vector< CharClass * > & classes ()
 
std::vector< Char * > & chars ()
 
const CharClass * charClass (const Lima::LimaChar &c) const
 Gets the Class of the specified character.
 
const CharClass * charClass (const LimaChar &c1, const LimaChar &c2) const
 
Lima::LimaChar maj (const Lima::LimaChar &c) const
 Gets the upper case corresponding to the specified character.
 
Lima::LimaChar min (const Lima::LimaChar &c) const
 Gets the lower case corresponding to the specified character.
 
LimaString unmarkWithMapping (const LimaString &str, std::vector< unsigned char > &mapping) const
 
Lima::LimaChar unmark (const Lima::LimaChar &c) const
 Gets the unmark character corresponding to the specified character.
 
LimaString unmark (const LimaString &str) const
 
Lima::LimaString unmarkByString (const Lima::LimaChar &c) const
 Gets the unmark string corresponding to the specified character.
 
Lima::LimaString toLower (const Lima::LimaString &src) const
 Converts src to its lowercase equivalent.
 
const CharClass * classNamed (const Lima::LimaString &name) const
 
bool loadFromFile (const std::string &fileName)
 
const std::map< LimaChar, std::map< LimaChar, Char * > > & surrogates () const
 
std::map< LimaChar, std::map< LimaChar, Char * > > & surrogates ()
 
- Public Member Functions inherited from Lima::LinguisticProcessing::AbstractResource
 AbstractResource (QObject *parent=0)
 
virtual ~AbstractResource ()
 
 AbstractResource (const AbstractResource &)
 
virtual void init (Common::XMLConfigurationFiles::GroupConfigurationStructure &unitConfiguration, Manager *manager) override=0
 initialize with parameters from configuration file.
 
- Public Member Functions inherited from Lima::LinguisticProcessing::AbstractResourceBase
 AbstractResourceBase (QObject *parent=0)
 
virtual ~AbstractResourceBase ()
 
 AbstractResourceBase (const AbstractResourceBase &)
 
QString getResourceFileName (const QString &paramName)
 
- Public Member Functions inherited from Lima::InitializableObject< AbstractResource, ResourceInitializationParameters >
 InitializableObject ()
 
 InitializableObject (const InitializableObject &object)
 
InitializableObject & operator= (const InitializableObject &object)
 
virtual ~InitializableObject ()
 
const std::string & getId () const
 get the object id
 
void setId (const std::string &id)
 set the object id
 

Additional Inherited Members

- Public Types inherited from Lima::InitializableObject< AbstractResource, ResourceInitializationParameters >
typedef InitializableObjectManager< AbstractResource, ResourceInitializationParameters > Manager
 Manager is the type of the Manager associated to the initializableObject.
 
typedef InitializableObjectFactory< AbstractResource > Factory
 Factory is the type of the Factory associated to the initializableObject.
 
- Signals inherited from Lima::LinguisticProcessing::AbstractResourceBase
void resourceFileChanged (const QString &path)
 Signal triggered whenever one of the registered files changes on disk.
 
- Protected Member Functions inherited from Lima::LinguisticProcessing::AbstractResourceBase
LimaFileSystemWatcher & resourceFileWatcher ()
 Accessor to the file watcher used to register resource files to be watched for changes.
 
- Protected Attributes inherited from Lima::LinguisticProcessing::AbstractResourceBase
AbstractResourceBasePrivate * m_d
 
- Protected Attributes inherited from Lima::InitializableObject< AbstractResource, ResourceInitializationParameters >
std::string m_id
 

Detailed Description

Definition at line 31 of file CharChart.h.

Constructor & Destructor Documentation

◆ CharChart()

Lima::LinguisticProcessing::FlatTokenizer::CharChart::CharChart ( )
explicit

Definition at line 46 of file CharChart.cpp.

◆ ~CharChart()

Lima::LinguisticProcessing::FlatTokenizer::CharChart::~CharChart ( )
virtual

Definition at line 119 of file CharChart.cpp.

Member Function Documentation

◆ charClass() [1/2]

const CharClass * Lima::LinguisticProcessing::FlatTokenizer::CharChart::charClass ( const Lima::LimaChar &  c) const

Gets the Class of the specified character.

If specified character was not defined, try to use the mapping with Qt Unicode categories and if this fails too, class named unknwn is returned.

Definition at line 162 of file CharChart.cpp.

◆ charClass() [2/2]

const CharClass * Lima::LinguisticProcessing::FlatTokenizer::CharChart::charClass ( const LimaChar &  c1,
const LimaChar &  c2 
) const

Definition at line 189 of file CharChart.cpp.

◆ chars() [1/2]

std::vector< Char * > & Lima::LinguisticProcessing::FlatTokenizer::CharChart::chars ( )
inline

Definition at line 45 of file CharChart.h.

◆ chars() [2/2]

const std::vector< Char * > & Lima::LinguisticProcessing::FlatTokenizer::CharChart::chars ( ) const
inline

Definition at line 43 of file CharChart.h.

◆ classes() [1/2]

std::vector< CharClass * > & Lima::LinguisticProcessing::FlatTokenizer::CharChart::classes ( )
inline

Definition at line 44 of file CharChart.h.

◆ classes() [2/2]

const std::vector< CharClass * > & Lima::LinguisticProcessing::FlatTokenizer::CharChart::classes ( ) const
inline

Definition at line 42 of file CharChart.h.

◆ classNamed()

const CharClass * Lima::LinguisticProcessing::FlatTokenizer::CharChart::classNamed ( const Lima::LimaString &  name) const

Definition at line 356 of file CharChart.cpp.

◆ init()

void Lima::LinguisticProcessing::FlatTokenizer::CharChart::init ( Common::XMLConfigurationFiles::GroupConfigurationStructure &  unitConfiguration,
Manager *  manager 
)
override

Definition at line 136 of file CharChart.cpp.

◆ loadFromFile()

bool Lima::LinguisticProcessing::FlatTokenizer::CharChart::loadFromFile ( const std::string &  fileName)

@ERROR DOES NOT COMPILE UNDER WINDOWS

Definition at line 380 of file CharChart.cpp.

◆ maj()

LimaChar Lima::LinguisticProcessing::FlatTokenizer::CharChart::maj ( const Lima::LimaChar &  c) const

Gets the upper case corresponding to the specified character.

If specified character was not defined, InvalidCharException is raised.

Definition at line 212 of file CharChart.cpp.

◆ min()

LimaChar Lima::LinguisticProcessing::FlatTokenizer::CharChart::min ( const Lima::LimaChar &  c) const

Gets the lower case corresponding to the specified character.

If specified character was not defined, InvalidCharException is raised.

Definition at line 219 of file CharChart.cpp.

◆ surrogates() [1/2]

std::map< LimaChar, std::map< LimaChar, Char * > > & Lima::LinguisticProcessing::FlatTokenizer::CharChart::surrogates ( )
inline

Definition at line 89 of file CharChart.h.

◆ surrogates() [2/2]

const std::map< LimaChar, std::map< LimaChar, Char * > > & Lima::LinguisticProcessing::FlatTokenizer::CharChart::surrogates ( ) const
inline

Definition at line 88 of file CharChart.h.

◆ toLower()

LimaString Lima::LinguisticProcessing::FlatTokenizer::CharChart::toLower ( const Lima::LimaString &  src) const

Converts src to its lowercase equivalent.

Definition at line 347 of file CharChart.cpp.

◆ unmark() [1/2]

LimaChar Lima::LinguisticProcessing::FlatTokenizer::CharChart::unmark ( const Lima::LimaChar &  c) const

Gets the unmark character corresponding to the specified character.

First take the lowercase version before unmarking. If specified character was not defined, InvalidCharException is raised. If unmark replacement is less or more than one character, 0 is returned. In that case, replacement by string must be called

Definition at line 227 of file CharChart.cpp.

◆ unmark() [2/2]

LimaString Lima::LinguisticProcessing::FlatTokenizer::CharChart::unmark ( const LimaString &  str) const

Definition at line 282 of file CharChart.cpp.

◆ unmarkByString()

LimaString Lima::LinguisticProcessing::FlatTokenizer::CharChart::unmarkByString ( const Lima::LimaChar &  c) const

Gets the unmark string corresponding to the specified character.

If specified character was not defined, InvalidCharException is raised. Null string, one, two and more characters string can be returned.

Definition at line 251 of file CharChart.cpp.

◆ unmarkWithMapping()

LimaString Lima::LinguisticProcessing::FlatTokenizer::CharChart::unmarkWithMapping ( const LimaString &  str,
std::vector< unsigned char > &  mapping 
) const

Definition at line 313 of file CharChart.cpp.


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