aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-09-19 19:13:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix for windows utf-8 input (#840)

Browse source 
Use UTF-16 as input on Windows, since UTF-8 does not work and reads multibyte characters as zeros
This commit is contained in:
Tomáš Pazdiora 2023-04-08 17:49:39 +02:00 committed by GitHub
parent f2d1c47294
commit aaf3b23deb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 28 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
examples/common.cpp
View file

@ -16,12 +16,19 @@
#endif
#if defined (_WIN32)
#include <fcntl.h>
#include <io.h>
#pragma comment(lib,"kernel32.lib")
extern "C" __declspec(dllimport) void* __stdcall GetStdHandle(unsigned long nStdHandle);
extern "C" __declspec(dllimport) int __stdcall GetConsoleMode(void* hConsoleHandle, unsigned long* lpMode);
extern "C" __declspec(dllimport) int __stdcall SetConsoleMode(void* hConsoleHandle, unsigned long dwMode);
extern "C" __declspec(dllimport) int __stdcall SetConsoleCP(unsigned int wCodePageID);
extern "C" __declspec(dllimport) int __stdcall SetConsoleOutputCP(unsigned int wCodePageID);
extern "C" __declspec(dllimport) int __stdcall WideCharToMultiByte(unsigned int CodePage, unsigned long dwFlags,
const wchar_t * lpWideCharStr, int cchWideChar,
char * lpMultiByteStr, int cbMultiByte,
const char * lpDefaultChar, bool * lpUsedDefaultChar);
#define CP_UTF8 65001
#endif
bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
@ -307,12 +314,20 @@ void win32_console_init(bool enable_color) {
SetConsoleMode(hConOut, dwMode | 0x4); // ENABLE_VIRTUAL_TERMINAL_PROCESSING (0x4)
}
// Set console output codepage to UTF8
SetConsoleOutputCP(65001); // CP_UTF8
SetConsoleOutputCP(CP_UTF8);
}
void* hConIn = GetStdHandle((unsigned long)-10); // STD_INPUT_HANDLE (-10)
if (hConIn && hConIn != (void*)-1 && GetConsoleMode(hConIn, &dwMode)) {
// Set console input codepage to UTF8
SetConsoleCP(65001); // CP_UTF8
// Set console input codepage to UTF16
_setmode(_fileno(stdin), _O_WTEXT);
}
}
// Convert a wide Unicode string to an UTF8 string
void win32_utf8_encode(const std::wstring & wstr, std::string & str) {
int size_needed = WideCharToMultiByte(CP_UTF8, 0, &wstr[0], (int)wstr.size(), NULL, 0, NULL, NULL);
std::string strTo(size_needed, 0);
WideCharToMultiByte(CP_UTF8, 0, &wstr[0], (int)wstr.size(), &strTo[0], size_needed, NULL, NULL);
str = strTo;
}
#endif

1
examples/common.h
View file

@ -92,4 +92,5 @@ void set_console_color(console_state & con_st, console_color_t color);
#if defined (_WIN32)
void win32_console_init(bool enable_color);
void win32_utf8_encode(const std::wstring & wstr, std::string & str);
#endif

9
examples/main/main.cpp
View file

@ -386,10 +386,19 @@ int main(int argc, char ** argv) {
std::string line;
bool another_line = true;
do {
#if defined(_WIN32)
std::wstring wline;
if (!std::getline(std::wcin, wline)) {
// input stream is bad or EOF received
return 0;
}
win32_utf8_encode(wline, line);
#else
if (!std::getline(std::cin, line)) {
// input stream is bad or EOF received
return 0;
}
#endif
if (line.empty() || line.back() != '\\') {
another_line = false;
} else {