From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: jmorganca <jmorganca@gmail.com>
Date: Tue, 8 Apr 2025 15:34:37 -0700
Subject: [PATCH] clip-unicode

fixes loading vision models in llama.cpp on windows
filesystems for paths that include wide characters
---
 examples/llava/clip.cpp | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
index 75970615..d57b4bd6 100644
--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -29,6 +29,19 @@
 #include <limits>
 #include <array>
 
+#if defined(_WIN32)
+#define WIN32_LEAN_AND_MEAN
+#ifndef NOMINMAX
+    #define NOMINMAX
+#endif
+#include <windows.h>
+#if __GLIBCXX__
+#include <cstdio>
+#include <ext/stdio_filebuf.h>
+#include <fcntl.h>
+#endif
+#endif
+
 struct clip_logger_state g_logger_state = {GGML_LOG_LEVEL_CONT, clip_log_callback_default, NULL};
 
 //#define CLIP_DEBUG_FUNCTIONS
@@ -1430,7 +1443,29 @@ struct clip_model_loader {
         {
             std::vector<uint8_t> read_buf;
 
+#ifdef _WIN32
+            int wlen = MultiByteToWideChar(CP_UTF8, 0, fname.c_str(), -1, NULL, 0);
+            if (!wlen) {
+                throw std::runtime_error(string_format("%s: failed to convert filename to wide string\n", __func__));
+            }
+            wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
+            wlen = MultiByteToWideChar(CP_UTF8, 0, fname.c_str(), -1, wbuf, wlen);
+            if (!wlen) {
+                free(wbuf);
+                throw std::runtime_error(string_format("%s: failed to convert filename to wide string\n", __func__));
+            }
+#if __GLIBCXX__
+            int fd = _wopen(wbuf, _O_RDONLY | _O_BINARY);
+            __gnu_cxx::stdio_filebuf<char> buffer(fd, std::ios_base::in);
+            std::istream fin(&buffer);
+#else // MSVC
+            // unused in our current build
+            auto fin = std::ifstream(wbuf, std::ios::binary);
+#endif
+            free(wbuf);
+#else
             auto fin = std::ifstream(fname, std::ios::binary);
+#endif
             if (!fin) {
                 throw std::runtime_error(string_format("%s: failed to open %s\n", __func__, fname.c_str()));
             }
@@ -1457,7 +1492,11 @@ struct clip_model_loader {
                     ggml_backend_tensor_set(cur, read_buf.data(), 0, num_bytes);
                 }
             }
+#if defined(_WIN32) && defined(__GLIBCXX__)
+            close(fd);
+#else
             fin.close();
+#endif
 
             LOG_DBG("%s: loaded %zu tensors from %s\n", __func__, tensors_to_load.size(), fname.c_str());
         }