gguf : reject empty metadata keys (#24917)

diff --git a/ggml/src/gguf.cpp b/ggml/src/gguf.cpp
index 5e1986182515b3baadd3ab4c45c7e09038d0b64e..c3ffa1a13435bd531c259b6106a3a6763e4f2df9 100644 (file)
--- a/ggml/src/gguf.cpp
+++ b/ggml/src/gguf.cpp
@@ -557,6 +557,10 @@ static struct gguf_context * gguf_init_from_reader(const struct gguf_reader & gr
                 GGML_LOG_ERROR("%s: encountered bad_alloc error while reading key %" PRIi64 "\n", __func__, i);
                 ok = false;
             }
+            if (ok && key.empty()) {
+                GGML_LOG_ERROR("%s: key %" PRIi64 " is empty\n", __func__, i);
+                ok = false;
+            }
             for (size_t j = 0; ok && j < ctx->kv.size(); ++j) {
                 if (key == ctx->kv[j].key) {
                     GGML_LOG_ERROR("%s: duplicate key '%s' for tensors %zu and %" PRIi64 " \n", __func__, key.c_str(), j, i);

diff --git a/tests/test-gguf.cpp b/tests/test-gguf.cpp
index 1ae468fbd65f8f876e9cd644e83f4c7af98bd473..ddb1b4d94874f47ff372b81f64cf81c9d95ce211 100644 (file)
--- a/tests/test-gguf.cpp
+++ b/tests/test-gguf.cpp
@@ -26,6 +26,7 @@ enum handcrafted_file_type {
     HANDCRAFTED_HEADER_EMPTY               = 800,
 
     HANDCRAFTED_KV_BAD_KEY_SIZE            =  10 + offset_has_kv,
+    HANDCRAFTED_KV_EMPTY_KEY               =  15 + offset_has_kv,
     HANDCRAFTED_KV_BAD_TYPE                =  20 + offset_has_kv,
     // HANDCRAFTED_KV_BAD_VALUE_SIZE          =  30 + offset_has_kv, // removed because it can result in allocations > 1 TB (default sanitizer limit)
     HANDCRAFTED_KV_DUPLICATE_KEY           =  40 + offset_has_kv,
@@ -64,6 +65,7 @@ static std::string handcrafted_file_type_name(const enum handcrafted_file_type h
         case HANDCRAFTED_HEADER_EMPTY:               return "HEADER_EMPTY";
 
         case HANDCRAFTED_KV_BAD_KEY_SIZE:            return "KV_BAD_KEY_SIZE";
+        case HANDCRAFTED_KV_EMPTY_KEY:               return "KV_EMPTY_KEY";
         case HANDCRAFTED_KV_BAD_TYPE:                return "KV_BAD_TYPE";
         case HANDCRAFTED_KV_DUPLICATE_KEY:           return "KV_DUPLICATE_KEY";
         case HANDCRAFTED_KV_BAD_ALIGN:               return "KV_BAD_ALIGN";
@@ -284,7 +286,9 @@ static FILE * get_handcrafted_file(const unsigned int seed, const enum handcraft
         const enum gguf_type type     = gguf_type(hft == HANDCRAFTED_KV_BAD_TYPE ? GGUF_TYPE_COUNT : kv_types[i].first);
         const enum gguf_type type_arr = gguf_type(hft == HANDCRAFTED_KV_BAD_TYPE ? GGUF_TYPE_COUNT : kv_types[i].second);
 
-        const std::string key = "my_key_" + std::to_string((hft == HANDCRAFTED_KV_DUPLICATE_KEY ? i/2 : i));
+        const std::string key = hft == HANDCRAFTED_KV_EMPTY_KEY
+            ? ""
+            : "my_key_" + std::to_string((hft == HANDCRAFTED_KV_DUPLICATE_KEY ? i/2 : i));
 
         if (hft == HANDCRAFTED_KV_BAD_KEY_SIZE) {
             const uint64_t n = -1;
@@ -732,6 +736,7 @@ static std::pair<int, int> test_handcrafted_file(const unsigned int seed) {
         HANDCRAFTED_HEADER_EMPTY,
 
         HANDCRAFTED_KV_BAD_KEY_SIZE,
+        HANDCRAFTED_KV_EMPTY_KEY,
         HANDCRAFTED_KV_BAD_TYPE,
         HANDCRAFTED_KV_DUPLICATE_KEY,
         HANDCRAFTED_KV_BAD_ALIGN,