Skip to content

gguf : reject empty metadata key names during parsing #22410

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

Closed
rxho wants to merge 1 commit into from
+25 −2
Closed

gguf : reject empty metadata key names during parsing #22410

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 4 additions & 0 deletions ggml/src/gguf.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -508,6 +508,10 @@ struct gguf_context * gguf_init_from_file_ptr(FILE * file, struct gguf_init_para
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: empty key name at KV pair %" PRIi64 "\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);
Expand Down
23 changes: 21 additions & 2 deletions tests/test-gguf.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,9 @@ enum handcrafted_file_type {
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,
HANDCRAFTED_KV_EMPTY_KEY = 45 + offset_has_kv,
HANDCRAFTED_KV_EMPTY_KEY_ONLY_FIRST = 46 + offset_has_kv,
HANDCRAFTED_KV_EMPTY_KEY_ONLY_MID = 47 + offset_has_kv,
HANDCRAFTED_KV_BAD_ALIGN = 50 + offset_has_kv,
HANDCRAFTED_KV_SUCCESS = 800 + offset_has_kv,

Expand Down Expand Up @@ -66,6 +69,9 @@ static std::string handcrafted_file_type_name(const enum handcrafted_file_type h
case HANDCRAFTED_KV_BAD_KEY_SIZE: return "KV_BAD_KEY_SIZE";
case HANDCRAFTED_KV_BAD_TYPE: return "KV_BAD_TYPE";
case HANDCRAFTED_KV_DUPLICATE_KEY: return "KV_DUPLICATE_KEY";
case HANDCRAFTED_KV_EMPTY_KEY: return "KV_EMPTY_KEY";
case HANDCRAFTED_KV_EMPTY_KEY_ONLY_FIRST: return "KV_EMPTY_KEY_ONLY_FIRST";
case HANDCRAFTED_KV_EMPTY_KEY_ONLY_MID: return "KV_EMPTY_KEY_ONLY_MID";
case HANDCRAFTED_KV_BAD_ALIGN: return "KV_BAD_ALIGN";
case HANDCRAFTED_KV_SUCCESS: return "KV_RANDOM_KV";

Expand Down Expand Up @@ -250,14 +256,24 @@ static FILE * get_handcrafted_file(const unsigned int seed, const enum handcraft

const std::string key = "my_key_" + std::to_string((hft == HANDCRAFTED_KV_DUPLICATE_KEY ? i/2 : i));

if (hft == HANDCRAFTED_KV_BAD_KEY_SIZE) {
const bool empty_key_this_iter =
hft == HANDCRAFTED_KV_EMPTY_KEY ||
(hft == HANDCRAFTED_KV_EMPTY_KEY_ONLY_FIRST && i == 0) ||
(hft == HANDCRAFTED_KV_EMPTY_KEY_ONLY_MID && i == int(kv_types.size()) / 2);

if (empty_key_this_iter) {
const uint64_t n = 0;
helper_write(file, n);
} else if (hft == HANDCRAFTED_KV_BAD_KEY_SIZE) {
const uint64_t n = -1;
helper_write(file, n);
} else {
const uint64_t n = key.length();
helper_write(file, n);
}
helper_write(file, key.data(), key.length());
if (!empty_key_this_iter) {
helper_write(file, key.data(), key.length());
}

{
const int32_t type32 = int32_t(type);
Expand Down Expand Up @@ -698,6 +714,9 @@ static std::pair<int, int> test_handcrafted_file(const unsigned int seed) {
HANDCRAFTED_KV_BAD_KEY_SIZE,
HANDCRAFTED_KV_BAD_TYPE,
HANDCRAFTED_KV_DUPLICATE_KEY,
HANDCRAFTED_KV_EMPTY_KEY,
HANDCRAFTED_KV_EMPTY_KEY_ONLY_FIRST,
HANDCRAFTED_KV_EMPTY_KEY_ONLY_MID,
HANDCRAFTED_KV_BAD_ALIGN,
HANDCRAFTED_KV_SUCCESS,

Expand Down