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

unicode : shot in the dark to fix tests on Windows

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-26 14:57:12 +03:00
parent 4907e41aa7
commit e8c206be61
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
unicode.cpp
View file

@ -203,8 +203,14 @@ static inline std::wstring unicode_wstring_from_utf8(const std::string & s) {
} }
static inline std::string unicode_wstring_to_utf8(const std::wstring & ws) { static inline std::string unicode_wstring_to_utf8(const std::wstring & ws) {
#if defined(_WIN32)
// code to convert from utf32/utf16 to utf8
std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>, wchar_t> converter;
return converter.to_bytes(ws);
#else
std::wstring_convert<std::codecvt_utf8<wchar_t>> conv; std::wstring_convert<std::codecvt_utf8<wchar_t>> conv;
return conv.to_bytes(ws); return conv.to_bytes(ws);
#endif
} }
static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) { static std::vector<std::string> unicode_byte_encoding_process(const std::vector<std::string> & bpe_words) {