mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
83796e62bc
* llama : refactor unicode stuff ggml-ci * unicode : names * make : fix c++ compiler * unicode : names * unicode : straighten tables * zig : fix build * unicode : put nfd normalization behind API ggml-ci * swift : fix build * unicode : add BOM * unicode : add <cstdint> ggml-ci * unicode : pass as cpts as const ref
27 lines
770 B
C++
27 lines
770 B
C++
#pragma once
|
|
|
|
#include <cstdint>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#define CODEPOINT_TYPE_UNIDENTIFIED 0
|
|
#define CODEPOINT_TYPE_DIGIT 1
|
|
#define CODEPOINT_TYPE_LETTER 2
|
|
#define CODEPOINT_TYPE_WHITESPACE 3
|
|
#define CODEPOINT_TYPE_ACCENT_MARK 4
|
|
#define CODEPOINT_TYPE_PUNCTUATION 5
|
|
#define CODEPOINT_TYPE_SYMBOL 6
|
|
#define CODEPOINT_TYPE_CONTROL 7
|
|
|
|
std::string unicode_cpt_to_utf8(uint32_t cp);
|
|
std::vector<uint32_t> unicode_cpts_from_utf8(const std::string & utf8);
|
|
|
|
std::vector<uint32_t> unicode_cpts_normalize_nfd(const std::vector<uint32_t> & cpts);
|
|
|
|
int unicode_cpt_type(uint32_t cp);
|
|
int unicode_cpt_type(const std::string & utf8);
|
|
|
|
std::string unicode_byte_to_utf8(uint8_t byte);
|
|
uint8_t unicode_utf8_to_byte(const std::string & utf8);
|
|
|