LIMA
Libre Multilingual Analyzer — C++ API
Loading...
Searching...
No Matches
Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate Class Reference
Inheritance diagram for Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate:
Lima::LinguisticProcessing::DeepTokenizerBase Lima::LinguisticProcessing::ConfigurationHelper

Classes

struct  TPrimitiveToken
 

Public Member Functions

 RnnTokenizerPrivate ()
 
virtual ~RnnTokenizerPrivate ()
 
void init (GroupConfigurationStructure &unitConfiguration)
 
void tokenize (const QString &text, std::vector< std::vector< TPrimitiveToken > > &sentences)
 
- Public Member Functions inherited from Lima::LinguisticProcessing::DeepTokenizerBase
 DeepTokenizerBase ()
 
virtual ~DeepTokenizerBase ()
 
 DeepTokenizerBase (const DeepTokenizerBase &)
 
DeepTokenizerBase & operator= (const DeepTokenizerBase &)
 
virtual void computeDefaultStatus (LinguisticAnalysisStructure::TStatus &curSettings)
 
virtual void computeDefaultStatus (LinguisticAnalysisStructure::Token &token)
 

Protected Member Functions

void append_new_word (std::vector< TPrimitiveToken > &current_sentence, const QString &current_token, int current_token_offset) const
 
- Protected Member Functions inherited from Lima::LinguisticProcessing::ConfigurationHelper
 ConfigurationHelper (const std::string &processUnitName, const std::string &loggingCategory)
 
void getStringParameter (Common::XMLConfigurationFiles::GroupConfigurationStructure &unitConfiguration, const std::string &name, std::string &value, int flags=Flags::REQUIRED, std::string default_value="")
 
std::string getStringParameter (Common::XMLConfigurationFiles::GroupConfigurationStructure &unitConfiguration, const std::string &name, int flags=Flags::REQUIRED, std::string default_value="")
 
void getIntParameter (Common::XMLConfigurationFiles::GroupConfigurationStructure &unitConfiguration, const std::string &name, int &value, int flags=Flags::REQUIRED, int default_value=0)
 
int getIntParameter (Common::XMLConfigurationFiles::GroupConfigurationStructure &unitConfiguration, const std::string &name, int flags=Flags::REQUIRED, int default_value=0)
 
bool isInitLazy ()
 

Protected Attributes

MediaId m_language
 
FsaStringsPool * m_stringsPool
 
LinguisticGraphVertex m_currentVx
 
QString m_data
 
size_t m_max_seq_len
 
std::map< QString, std::vector< QString > > m_trrules
 
bool m_ignoreEOL
 
std::shared_ptr< segmentation::impl::SegmentationImpl > m_segm
 
std::function< void()> m_load_fn
 
bool m_loaded
 

Additional Inherited Members

- Protected Types inherited from Lima::LinguisticProcessing::ConfigurationHelper
enum  Flags { REQUIRED = 0x1 , NOT_EMPTY = 0x2 , NOT_ZERO = 0x2 }
 

Detailed Description

Definition at line 62 of file RnnTokenizer.cpp.

Constructor & Destructor Documentation

◆ RnnTokenizerPrivate()

Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::RnnTokenizerPrivate ( )

Definition at line 109 of file RnnTokenizer.cpp.

◆ ~RnnTokenizerPrivate()

Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::~RnnTokenizerPrivate ( )
virtual

Definition at line 119 of file RnnTokenizer.cpp.

Member Function Documentation

◆ append_new_word()

void Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::append_new_word ( std::vector< TPrimitiveToken > &  current_sentence,
const QString &  current_token,
int  current_token_offset 
) const
protected

Definition at line 289 of file RnnTokenizer.cpp.

◆ init()

void Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::init ( GroupConfigurationStructure &  unitConfiguration)

Definition at line 237 of file RnnTokenizer.cpp.

◆ tokenize()

void Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::tokenize ( const QString &  text,
std::vector< std::vector< TPrimitiveToken > > &  sentences 
)

Definition at line 317 of file RnnTokenizer.cpp.

Member Data Documentation

◆ m_currentVx

LinguisticGraphVertex Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_currentVx
protected

Definition at line 93 of file RnnTokenizer.cpp.

◆ m_data

QString Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_data
protected

Definition at line 94 of file RnnTokenizer.cpp.

◆ m_ignoreEOL

bool Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_ignoreEOL
protected

Definition at line 101 of file RnnTokenizer.cpp.

◆ m_language

MediaId Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_language
protected

Definition at line 91 of file RnnTokenizer.cpp.

◆ m_load_fn

std::function<void()> Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_load_fn
protected

Definition at line 105 of file RnnTokenizer.cpp.

◆ m_loaded

bool Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_loaded
protected

Definition at line 106 of file RnnTokenizer.cpp.

◆ m_max_seq_len

size_t Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_max_seq_len
protected

Definition at line 96 of file RnnTokenizer.cpp.

◆ m_segm

std::shared_ptr<segmentation::impl::SegmentationImpl> Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_segm
protected

Definition at line 103 of file RnnTokenizer.cpp.

◆ m_stringsPool

FsaStringsPool* Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_stringsPool
protected

Definition at line 92 of file RnnTokenizer.cpp.

◆ m_trrules

std::map<QString, std::vector<QString> > Lima::LinguisticProcessing::DeepLimaUnits::RnnTokenizer::RnnTokenizerPrivate::m_trrules
protected

Definition at line 98 of file RnnTokenizer.cpp.


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