vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

unicode : category support via std::regex

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-28 13:42:00 +03:00
parent 581c4a0239
commit b97add52a4
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
4 changed files with 172 additions and 99 deletions
Download patch file Download diff file Expand all files Collapse all files

1
unicode-data.h
View file

@ -16,5 +16,4 @@ 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;
extern const std::map<std::string, std::wstring> unicode_regex_equivalent_wregex;
extern const std::set<std::string> unicode_regex_with_custom_preprocessor;