common : use fs::path for cache dirs (#29595)

- Avoid useless string conversions on Windows.
- No need for BSD or emscripten special cases.

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

common/arg.cpp

@@ -351,7 +351,7 @@ static bool parse_bool_value(const std::string & value) {
 static std::string get_default_local_path(const std::string & url) {
     auto f = string_split<std::string>(url, '#').front();
     f = string_split<std::string>(f, '?').front();
-    return fs_get_cache_file(string_split<std::string>(f, '/').back());
+    return fs_path_to_utf8(fs_get_cache_file(string_split<std::string>(f, '/').back()));
 }
 
 static bool spec_types_is_default(const common_params & params) {

common/common.cpp

@@ -49,7 +49,7 @@
 #include <unistd.h>
 #endif
 
-#if defined(__linux__)
+#if !defined(_WIN32) && !defined(__APPLE__)
 #include <sys/types.h>
 #include <pwd.h>
 #endif
@@ -912,13 +912,6 @@ std::string fs_path_to_utf8(const std::filesystem::path & path) {
     return std::string(value.begin(), value.end());
 }
 
-// returns true if successful, false otherwise
-bool fs_create_directory_with_parents(const std::string & path) {
-    std::error_code ec;
-    std::filesystem::create_directories(std::filesystem::u8path(path), ec);
-    return !ec;
-}
-
 bool fs_is_directory(const std::string & path) {
     std::filesystem::path dir(path);
     return std::filesystem::exists(dir) && std::filesystem::is_directory(dir);
@@ -952,58 +945,41 @@ std::filesystem::path common_get_path_from_env(const std::string & name) {
 #endif
 }
 
-std::string fs_get_cache_directory() {
-    std::string cache_directory = "";
-    auto ensure_trailing_slash = [](std::string p) {
-        // Make sure to add trailing slash
-        if (p.empty() || p.back() != DIRECTORY_SEPARATOR) {
-            p += DIRECTORY_SEPARATOR;
-        }
-        return p;
-    };
-    cache_directory = common_get_env("LLAMA_CACHE");
+std::filesystem::path fs_get_cache_directory() {
+    std::filesystem::path cache_directory = common_get_path_from_env("LLAMA_CACHE");
+    if (!cache_directory.empty()) {
+        return cache_directory;
+    }
+
+#if defined(_WIN32)
+    cache_directory = common_get_path_from_env("LOCALAPPDATA");
     if (cache_directory.empty()) {
-#if defined(__linux__) || defined(__FreeBSD__) || defined(_AIX) || \
-        defined(__OpenBSD__) || defined(__NetBSD__)
-        const std::string xdg_cache_home = common_get_env("XDG_CACHE_HOME");
-        const std::string home           = common_get_env("HOME");
-        if (!xdg_cache_home.empty()) {
-            cache_directory = xdg_cache_home;
-        } else if (!home.empty()) {
-            cache_directory = home + "/.cache/";
+        throw std::runtime_error("Failed to find %LOCALAPPDATA% directory");
+    }
+#elif defined(__APPLE__)
+    cache_directory = common_get_path_from_env("HOME");
+    if (cache_directory.empty()) {
+        throw std::runtime_error("Failed to find $HOME directory");
+    }
+    cache_directory /= "Library/Caches";
+#else
+    cache_directory = common_get_path_from_env("XDG_CACHE_HOME");
+    if (cache_directory.empty()) {
+        cache_directory = common_get_path_from_env("HOME");
+        if (!cache_directory.empty()) {
+            cache_directory /= ".cache";
         } else {
-#if defined(__linux__)
             /* no $HOME is defined, fallback to getpwuid */
-            struct passwd *pw = getpwuid(getuid());
-            if ((!pw) || (!pw->pw_dir)) {
+            const struct passwd * pw = getpwuid(getuid());
+            if (!pw || !pw->pw_dir || !*pw->pw_dir) {
                 throw std::runtime_error("Failed to find $HOME directory");
             }
-
-            cache_directory = std::string(pw->pw_dir) + std::string("/.cache/");
-#else /* defined(__linux__) */
-            throw std::runtime_error("Failed to find $HOME directory");
-#endif /* defined(__linux__) */
+            cache_directory = pw->pw_dir;
+            cache_directory /= ".cache";
         }
-#elif defined(__APPLE__)
-        cache_directory = common_get_env("HOME");
-        if (cache_directory.empty()) {
-            throw std::runtime_error("Failed to find $HOME directory");
-        }
-        cache_directory += "/Library/Caches/";
-#elif defined(_WIN32)
-        cache_directory = common_get_env("LOCALAPPDATA");
-        if (cache_directory.empty()) {
-            throw std::runtime_error("Failed to find %LOCALAPPDATA% directory");
-        }
-#elif defined(__EMSCRIPTEN__)
-        GGML_ABORT("not implemented on this platform");
-#else
-#  error Unknown architecture
-#endif
-        cache_directory = ensure_trailing_slash(cache_directory);
-        cache_directory += "llama.cpp";
     }
-    return ensure_trailing_slash(cache_directory);
+#endif
+    return cache_directory / "llama.cpp";
 }
 
 std::string fs_get_config_directory() {
@@ -1051,14 +1027,15 @@ std::string fs_get_config_directory() {
     return ensure_trailing_slash(config_directory);
 }
 
-std::string fs_get_cache_file(const std::string & filename) {
+std::filesystem::path fs_get_cache_file(const std::string & filename) {
     GGML_ASSERT(filename.find(DIRECTORY_SEPARATOR) == std::string::npos);
-    std::string cache_directory = fs_get_cache_directory();
-    const bool success = fs_create_directory_with_parents(cache_directory);
-    if (!success) {
-        throw std::runtime_error("failed to create cache directory: " + cache_directory);
+    const std::filesystem::path cache_directory = fs_get_cache_directory();
+    std::error_code ec;
+    std::filesystem::create_directories(cache_directory, ec);
+    if (ec) {
+        throw std::runtime_error("failed to create cache directory: " + fs_path_to_utf8(cache_directory));
     }
-    return cache_directory + filename;
+    return cache_directory / std::filesystem::u8path(filename);
 }
 
 std::vector<common_file_info> fs_list(const std::string & path, bool include_directories) {

common/common.h

@@ -912,11 +912,10 @@ std::filesystem::path common_get_path_from_env(const std::string & name);
 //
 
 bool fs_validate_filename(const std::string & filename, bool allow_subdirs = false);
-bool fs_create_directory_with_parents(const std::string & path);
 bool fs_is_directory(const std::string & path);
 
-std::string fs_get_cache_directory();
-std::string fs_get_cache_file(const std::string & filename);
+std::filesystem::path fs_get_cache_directory();
+std::filesystem::path fs_get_cache_file(const std::string & filename);
 std::string fs_get_config_directory();
 
 struct common_file_info {

common/download.cpp

@@ -943,7 +943,7 @@ std::string common_docker_resolve_model(const std::string & docker) {
         std::string model_filename = repo;
         std::replace(model_filename.begin(), model_filename.end(), '/', '_');
         model_filename += "_" + tag + ".gguf";
-        std::string local_path = fs_get_cache_file(model_filename);
+        std::string local_path = fs_path_to_utf8(fs_get_cache_file(model_filename));
 
         const std::string blob_url = url_prefix + "/blobs/" + gguf_digest;
         common_download_opts opts;

tests/gguf-model-data.cpp

@@ -371,8 +371,8 @@ static std::optional<gguf_remote_model> gguf_parse_meta(const std::vector<char>
 }
 
 // cache handling for local download
-static std::string get_default_cache_dir() {
-    return fs_get_cache_directory() + "gguf-headers/";
+static std::filesystem::path get_default_cache_dir() {
+    return fs_get_cache_directory() / "gguf-headers";
 }
 
 static std::string sanitize_for_path(const std::string & s) {
@@ -385,7 +385,7 @@ static std::string sanitize_for_path(const std::string & s) {
     return out;
 }
 
-static bool read_file(const std::string & path, std::vector<char> & out) {
+static bool read_file(const std::filesystem::path & path, std::vector<char> & out) {
     std::ifstream f(path, std::ios::binary | std::ios::ate);
     if (!f.good()) {
         return false;
@@ -400,7 +400,7 @@ static bool read_file(const std::string & path, std::vector<char> & out) {
     return f.good();
 }
 
-static bool write_file(const std::string & path, const std::vector<char> & data) {
+static bool write_file(const std::filesystem::path & path, const std::vector<char> & data) {
     std::ofstream f(path, std::ios::binary | std::ios::trunc);
     if (!f.good()) {
         return false;
@@ -516,7 +516,7 @@ static std::string detect_gguf_filename(const std::string & repo, const std::str
 static std::optional<gguf_remote_model> fetch_and_parse(
         const std::string & repo,
         const std::string & filename,
-        const std::string & cache_path,
+        const std::filesystem::path & cache_path,
         bool verbose) {
     std::string url = "https://huggingface.co/" + repo + "/resolve/main/" + filename;
 
@@ -564,19 +564,19 @@ static std::optional<gguf_remote_model> fetch_and_parse(
     return std::nullopt;
 }
 
-static std::string get_cache_file_path(const std::string& cdir, const std::string& repo_part, const std::string& filename) {
+static std::filesystem::path get_cache_file_path(const std::filesystem::path & cdir, const std::string & repo_part, const std::string & filename) {
     std::string fname_part = sanitize_for_path(filename);
-    return cdir + "/" + repo_part + "--" + fname_part + ".partial";
+    return cdir / std::filesystem::u8path(repo_part + "--" + fname_part + ".partial");
 }
 
 // Try cache first, then fetch and parse a single GGUF shard.
 static std::optional<gguf_remote_model> fetch_or_cached(
         const std::string & repo,
         const std::string & filename,
-        const std::string & cdir,
+        const std::filesystem::path & cdir,
         const std::string & repo_part,
         bool verbose) {
-    std::string cache_path = get_cache_file_path(cdir, repo_part, filename);
+    std::filesystem::path cache_path = get_cache_file_path(cdir, repo_part, filename);
 
     {
         std::vector<char> cached;
@@ -584,14 +584,15 @@ static std::optional<gguf_remote_model> fetch_or_cached(
             auto result = gguf_parse_meta(cached);
             if (result.has_value()) {
                 if (verbose) {
-                    fprintf(stderr, "gguf_fetch: loaded from cache: %s\n", cache_path.c_str());
+                    fprintf(stderr, "gguf_fetch: loaded from cache: %s\n", fs_path_to_utf8(cache_path).c_str());
                 }
                 return result;
             }
         }
     }
 
-    fs_create_directory_with_parents(cdir);
+    std::error_code ec;
+    std::filesystem::create_directories(cdir, ec);
     return fetch_and_parse(repo, filename, cache_path, verbose);
 }
 
@@ -600,7 +601,7 @@ std::optional<gguf_remote_model> gguf_fetch_model_meta(
         const std::string & quant,
         const std::string & cache_dir,
         bool verbose) {
-    std::string cdir = cache_dir.empty() ? get_default_cache_dir() : cache_dir;
+    const std::filesystem::path cdir = cache_dir.empty() ? get_default_cache_dir() : std::filesystem::u8path(cache_dir);
     std::string repo_part = sanitize_for_path(repo);
 
     std::string split_prefix;
@@ -661,7 +662,7 @@ gguf_context_ptr gguf_fetch_gguf_ctx(
         const std::string & quant,
         const std::string & cache_dir,
         bool verbose) {
-    std::string cdir = cache_dir.empty() ? get_default_cache_dir() : cache_dir;
+    const std::filesystem::path cdir = cache_dir.empty() ? get_default_cache_dir() : std::filesystem::u8path(cache_dir);
     std::string repo_part = sanitize_for_path(repo);
 
     std::string split_prefix;
@@ -679,12 +680,12 @@ gguf_context_ptr gguf_fetch_gguf_ctx(
 
     auto & model = model_opt.value();
 
-    const std::string cache_path = get_cache_file_path(cdir, repo_part, filename);
+    const std::filesystem::path cache_path = get_cache_file_path(cdir, repo_part, filename);
 
     ggml_context_ptr ggml_ctx_ptr;
     ggml_context * ggml_ctx{};
     gguf_init_params params{true, &ggml_ctx};
-    gguf_context_ptr ctx{gguf_init_from_file(cache_path.c_str(), params)};
+    gguf_context_ptr ctx{gguf_init_from_file(fs_path_to_utf8(cache_path).c_str(), params)};
     ggml_ctx_ptr.reset(ggml_ctx);
 
     if (ctx == nullptr) {
@@ -718,11 +719,11 @@ gguf_context_ptr gguf_fetch_gguf_ctx(
             }
 
             // Load tensors from shard and add to main gguf_context
-            const std::string shard_path = get_cache_file_path(cdir, repo_part, shard_name);
+            const std::filesystem::path shard_path = get_cache_file_path(cdir, repo_part, shard_name);
             ggml_context_ptr shard_ggml_ctx_ptr;
             ggml_context * shard_ggml_ctx{};
             gguf_init_params shard_params{true, &shard_ggml_ctx};
-            gguf_context_ptr shard_ctx{gguf_init_from_file(shard_path.c_str(), shard_params)};
+            gguf_context_ptr shard_ctx{gguf_init_from_file(fs_path_to_utf8(shard_path).c_str(), shard_params)};
             shard_ggml_ctx_ptr.reset(shard_ggml_ctx);
 
             if (shard_ctx == nullptr) {

tools/rpc/rpc-server.cpp

@@ -2,12 +2,10 @@
 #include "ggml-rpc.h"
 #ifdef _WIN32
 #  define NOMINMAX
-#  define DIRECTORY_SEPARATOR '\\'
 #  include <windows.h>
 #  include <fcntl.h>
 #  include <io.h>
 #else
-#  define DIRECTORY_SEPARATOR '/'
 #  include <unistd.h>
 #endif
 #include <algorithm>
@@ -20,64 +18,68 @@
 #include <thread>
 #include <vector>
 
-#if defined(__linux__)
+#if !defined(_WIN32) && !defined(__APPLE__)
 #include <sys/types.h>
 #include <pwd.h>
 #endif
 
-// NOTE: this is copied from common.cpp to avoid linking with libcommon
-// returns true if successful, false otherwise
-static bool fs_create_directory_with_parents(const std::string & path) {
-    std::error_code ec;
-    std::filesystem::create_directories(std::filesystem::u8path(path), ec);
-    return !ec;
+
+static std::string fs_path_to_utf8(const std::filesystem::path & path) {
+    const auto value = path.u8string();
+    return std::string(value.begin(), value.end());
+}
+
+// common_get_path_from_env() is adapted to avoid utf8_to_wstring
+static std::filesystem::path common_get_path_from_env(const std::string & name) {
+#ifdef _WIN32
+    std::wstring wname;
+    for (const char * p = name.c_str(); *p; ++p) {
+        wname.push_back((wchar_t)*p);
+    }
+    const wchar_t * wvalue = _wgetenv(wname.c_str());
+    return wvalue ? std::filesystem::path(wvalue) : std::filesystem::path();
+#else
+    const char * value = std::getenv(name.c_str());
+    return value ? std::filesystem::path(value) : std::filesystem::path();
+#endif
 }
 
 // NOTE: this is copied from common.cpp to avoid linking with libcommon
-static std::string fs_get_cache_directory() {
-    std::string cache_directory = "";
-    auto ensure_trailing_slash = [](std::string p) {
-        // Make sure to add trailing slash
-        if (p.back() != DIRECTORY_SEPARATOR) {
-            p += DIRECTORY_SEPARATOR;
-        }
-        return p;
-    };
-    if (getenv("LLAMA_CACHE")) {
-        cache_directory = std::getenv("LLAMA_CACHE");
-    } else {
-#if defined(__linux__) || defined(__FreeBSD__) || defined(_AIX) || \
-    defined(__OpenBSD__) || defined(__NetBSD__)
-        if (std::getenv("XDG_CACHE_HOME")) {
-            cache_directory = std::getenv("XDG_CACHE_HOME");
-        } else if (std::getenv("HOME")) {
-            cache_directory = std::getenv("HOME") + std::string("/.cache/");
+static std::filesystem::path fs_get_cache_directory() {
+    std::filesystem::path cache_directory = common_get_path_from_env("LLAMA_CACHE");
+    if (!cache_directory.empty()) {
+        return cache_directory;
+    }
+
+#if defined(_WIN32)
+    cache_directory = common_get_path_from_env("LOCALAPPDATA");
+    if (cache_directory.empty()) {
+        throw std::runtime_error("Failed to find %LOCALAPPDATA% directory");
+    }
+#elif defined(__APPLE__)
+    cache_directory = common_get_path_from_env("HOME");
+    if (cache_directory.empty()) {
+        throw std::runtime_error("Failed to find $HOME directory");
+    }
+    cache_directory /= "Library/Caches";
+#else
+    cache_directory = common_get_path_from_env("XDG_CACHE_HOME");
+    if (cache_directory.empty()) {
+        cache_directory = common_get_path_from_env("HOME");
+        if (!cache_directory.empty()) {
+            cache_directory /= ".cache";
         } else {
-#if defined(__linux__)
             /* no $HOME is defined, fallback to getpwuid */
-            struct passwd *pw = getpwuid(getuid());
-            if ((!pw) || (!pw->pw_dir)) {
+            const struct passwd * pw = getpwuid(getuid());
+            if (!pw || !pw->pw_dir || !*pw->pw_dir) {
                 throw std::runtime_error("Failed to find $HOME directory");
             }
-
-            cache_directory = std::string(pw->pw_dir) + std::string("/.cache/");
-#else /* defined(__linux__) */
-            throw std::runtime_error("Failed to find $HOME directory");
-#endif /* defined(__linux__) */
+            cache_directory = pw->pw_dir;
+            cache_directory /= ".cache";
         }
-#elif defined(__APPLE__)
-        cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
-#elif defined(_WIN32)
-        cache_directory = std::getenv("LOCALAPPDATA");
-#elif defined(__EMSCRIPTEN__)
-        GGML_ABORT("not implemented on this platform");
-#else
-#  error Unknown architecture
-#endif
-        cache_directory = ensure_trailing_slash(cache_directory);
-        cache_directory += "llama.cpp";
     }
-    return ensure_trailing_slash(cache_directory);
+#endif
+    return cache_directory / "llama.cpp";
 }
 
 struct rpc_server_params {
@@ -229,11 +231,14 @@ int main(int argc, char * argv[]) {
     const char * cache_dir = nullptr;
     std::string cache_dir_str;
     if (params.use_cache) {
-        cache_dir_str = fs_get_cache_directory() + "rpc" + DIRECTORY_SEPARATOR;
-        if (!fs_create_directory_with_parents(cache_dir_str)) {
-            fprintf(stderr, "Failed to create cache directory: %s\n", cache_dir_str.c_str());
+        const std::filesystem::path cache_dir_path = fs_get_cache_directory() / "rpc";
+        std::error_code ec;
+        std::filesystem::create_directories(cache_dir_path, ec);
+        if (ec) {
+            fprintf(stderr, "Failed to create cache directory: %s\n", fs_path_to_utf8(cache_dir_path).c_str());
             return 1;
         }
+        cache_dir_str = fs_path_to_utf8(cache_dir_path);
         cache_dir = cache_dir_str.c_str();
     }