Skip to content

Fix non-ASCII path handling in common argument parser on Windows #16611

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+38 −0
Open

Fix non-ASCII path handling in common argument parser on Windows #16611

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cdd8931
Added handling for non-ASCII arguments on Windows
kuguma Oct 16, 2025
7ae5e44
Follow naming rules
kuguma Oct 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 38 additions & 0 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
# define NOMINMAX
#endif
#include <windows.h>
#include <shellapi.h>
#endif

#define JSON_ASSERT GGML_ASSERT
Expand Down Expand Up @@ -1626,7 +1627,44 @@ static void add_rpc_devices(const std::string & servers) {
}
}

#ifdef _WIN32
struct utf8_argv {
std::vector<std::string> buf;
std::vector<char*> ptrs;
};

static utf8_argv make_utf8_argv() {
utf8_argv out;
int wargc = 0;
LPWSTR* wargv = CommandLineToArgvW(GetCommandLineW(), &wargc);
if (!wargv) return out;

out.buf.reserve(wargc);
for (int i = 0; i < wargc; ++i) {
int n = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS, wargv[i], -1, nullptr, 0, nullptr, nullptr);
if (n <= 0) { out.buf.emplace_back(); continue; }
auto& s = out.buf.emplace_back();
s.resize(static_cast<size_t>(n - 1));
(void)WideCharToMultiByte(CP_UTF8, 0, wargv[i], -1, s.data(), n, nullptr, nullptr);
}
LocalFree(wargv);

out.ptrs.reserve(out.buf.size() + 1);
for (auto& s : out.buf) out.ptrs.push_back(s.data());
out.ptrs.push_back(nullptr);
return out;
}
#endif

Comment on lines +1630 to +1658
Copy link
Member

@ggerganov ggerganov Oct 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
#ifdef _WIN32
struct utf8_argv {
std::vector<std::string> buf;
std::vector<char*> ptrs;
};
static utf8_argv make_utf8_argv() {
utf8_argv out;
int wargc = 0;
LPWSTR* wargv = CommandLineToArgvW(GetCommandLineW(), &wargc);
if (!wargv) return out;
out.buf.reserve(wargc);
for (int i = 0; i < wargc; ++i) {
int n = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS, wargv[i], -1, nullptr, 0, nullptr, nullptr);
if (n <= 0) { out.buf.emplace_back(); continue; }
auto& s = out.buf.emplace_back();
s.resize(static_cast<size_t>(n - 1));
(void)WideCharToMultiByte(CP_UTF8, 0, wargv[i], -1, s.data(), n, nullptr, nullptr);
}
LocalFree(wargv);
out.ptrs.reserve(out.buf.size() + 1);
for (auto& s : out.buf) out.ptrs.push_back(s.data());
out.ptrs.push_back(nullptr);
return out;
}
#endif
#ifdef _WIN32
struct utf8_argv {
std::vector<std::string> buf;
std::vector<char *> ptrs;
};
static utf8_argv make_utf8_argv() {
utf8_argv out;
int wargc = 0;
LPWSTR * wargv = CommandLineToArgvW(GetCommandLineW(), &wargc);
if (!wargv) return out;
out.buf.reserve(wargc);
for (int i = 0; i < wargc; ++i) {
int n = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS, wargv[i], -1, nullptr, 0, nullptr, nullptr);
if (n <= 0) { out.buf.emplace_back(); continue; }
auto & s = out.buf.emplace_back();
s.resize(static_cast<size_t>(n - 1));
(void)WideCharToMultiByte(CP_UTF8, 0, wargv[i], -1, s.data(), n, nullptr, nullptr);
}
LocalFree(wargv);
out.ptrs.reserve(out.buf.size() + 1);
for (auto & s : out.buf) out.ptrs.push_back(s.data());
out.ptrs.push_back(nullptr);
return out;
}
#endif

Copy link
Author

@kuguma kuguma Oct 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I checked the line endings of the code committed to the repository just in case, and they appear to be LF, consistent with the rest of the files.

bool common_params_parse(int argc, char ** argv, common_params & params, llama_example ex, void(*print_usage)(int, char **)) {
#ifdef _WIN32
auto utf8 = make_utf8_argv();
if (!utf8.ptrs.empty()) {
argc = static_cast<int>(utf8.buf.size());
argv = utf8.ptrs.data();
}
#endif

auto ctx_arg = common_params_parser_init(params, ex, print_usage);
const common_params params_org = ctx_arg.params; // the example can modify the default params

Expand Down
Loading