LIMA
Libre Multilingual Analyzer — C++ API
Loading...
Searching...
No Matches
deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder > Class Template Reference

#include </home/runner/work/lima/lima/deeplima/libs/tasks/segmentation/train/char_dict_builder.h>

Public Member Functions

 DictionaryBuilderImpl (const std::vector< impl::ngram_descr_t > &ngram_descr)
 
uint64_t get_num_features () const
 
DictsHolder process (const std::string &text, uint32_t min_ipm, uint64_t &char_counter)
 
void process (const std::wstring &text, uint32_t min_ipm)
 

Protected Member Functions

void read_string (const std::string &text, uint64_t &char_counter, std::vector< std::unordered_map< uint64_t, uint64_t > > &temp_dicts)
 
void handle_timepoint (uint64_t &char_counter, std::vector< std::unordered_map< uint64_t, uint64_t > > &temp_dicts)
 

Static Protected Member Functions

static float ipm (uint64_t count, uint64_t total)
 

Protected Attributes

InputEncoder m_input_encoder
 
uint64_t m_unk
 

Detailed Description

template<class InputEncoder>
class deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >

Definition at line 26 of file char_dict_builder.h.

Constructor & Destructor Documentation

◆ DictionaryBuilderImpl()

template<class InputEncoder >
deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::DictionaryBuilderImpl ( const std::vector< impl::ngram_descr_t > &  ngram_descr)
inline

Definition at line 29 of file char_dict_builder.h.

Member Function Documentation

◆ get_num_features()

template<class InputEncoder >
uint64_t deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::get_num_features ( ) const
inline

Definition at line 36 of file char_dict_builder.h.

◆ handle_timepoint()

template<class InputEncoder >
void deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::handle_timepoint ( uint64_t &  char_counter,
std::vector< std::unordered_map< uint64_t, uint64_t > > &  temp_dicts 
)
inlineprotected

Definition at line 149 of file char_dict_builder.h.

◆ ipm()

template<class InputEncoder >
static float deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::ipm ( uint64_t  count,
uint64_t  total 
)
inlinestaticprotected

Definition at line 109 of file char_dict_builder.h.

◆ process() [1/2]

template<class InputEncoder >
DictsHolder deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::process ( const std::string &  text,
uint32_t  min_ipm,
uint64_t &  char_counter 
)
inline

Definition at line 42 of file char_dict_builder.h.

◆ process() [2/2]

template<class InputEncoder >
void deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::process ( const std::wstring &  text,
uint32_t  min_ipm 
)
inline

Definition at line 76 of file char_dict_builder.h.

◆ read_string()

template<class InputEncoder >
void deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::read_string ( const std::string &  text,
uint64_t &  char_counter,
std::vector< std::unordered_map< uint64_t, uint64_t > > &  temp_dicts 
)
inlineprotected

Definition at line 114 of file char_dict_builder.h.

Member Data Documentation

◆ m_input_encoder

template<class InputEncoder >
InputEncoder deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::m_input_encoder
protected

Definition at line 175 of file char_dict_builder.h.

◆ m_unk

template<class InputEncoder >
uint64_t deeplima::segmentation::train::DictionaryBuilderImpl< InputEncoder >::m_unk
protected

Definition at line 176 of file char_dict_builder.h.


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