llama.cpp/unicode-data.h
Jared Van Bortel 32c8486e1f
wpm : portable unicode tolower (#6305)
Also use C locale for ispunct/isspace, and split unicode-data.cpp from unicode.cpp.
2024-03-26 17:46:21 -04:00

17 lines
782 B
C++

#pragma once
#include <cstdint>
#include <map>
#include <utility>
#include <vector>
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_digit;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_letter;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_whitespace;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_accent_mark;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_punctuation;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_symbol;
extern const std::vector<std::pair<uint32_t, uint32_t>> unicode_ranges_control;
extern const std::multimap<uint32_t, uint32_t> unicode_map_nfd;
extern const std::map<char32_t, char32_t> unicode_map_lowercase;