LIMA
Libre Multilingual Analyzer — C++ API
Loading...
Searching...
No Matches
utf8_reader.h File Reference
#include <cassert>
#include <limits>
#include <stdexcept>
#include <string.h>
#include <unicode/uchar.h>
#include <unicode/uscript.h>

Go to the source code of this file.

Classes

class  deeplima::segmentation::impl::Utf8Reader< TBufferType, NUM_CHANNELS, BYTES_BUFFER_SIZE >
 

Namespaces

namespace  deeplima
 
namespace  deeplima::segmentation
 
namespace  deeplima::segmentation::impl
 

Macros

#define UTF8_DECODER_CHAR_HISTORY_MASK   0x7FFFFFFFFFFFFFFFull
 

Enumerations

enum  deeplima::segmentation::impl::uc_channel_t : uint8_t {
  deeplima::segmentation::impl::channel_char = 0 , deeplima::segmentation::impl::channel_type = 1 , deeplima::segmentation::impl::channel_len = 2 , deeplima::segmentation::impl::channel_script_change = 3 ,
  deeplima::segmentation::impl::max_channel_value
}
 

Variables

const uint8_t deeplima::segmentation::impl::bits_per_position_table []
 

Macro Definition Documentation

◆ UTF8_DECODER_CHAR_HISTORY_MASK

#define UTF8_DECODER_CHAR_HISTORY_MASK   0x7FFFFFFFFFFFFFFFull

Definition at line 24 of file utf8_reader.h.