Files
ik_llama.cpp/examples/gbnf-validator/gbnf-validator.cpp
firecoperana 1cad1ec1cc Update grammar (#1023)
* grammar : fix JSON Schema for string regex with top-level alt. (#9903)

Prior to this commit, using a JSON Schema containing a string
with `pattern` regular expression that uses top-level alternation
(e.g. `"pattern": "^A|B|C|D$"`) would result in invalid JSON
output from the constrained sampling grammar, because it
ended up creating a grammar rule like this for the string:

```
thing ::= "\"" "A" | "B" | "C" | "D" "\"" space
```

Note that this rule will only match a starting quote for the "A" case,
and will only match an ending quote for the "D" case,
so this rule will always produce invalid JSON when used for sampling
(that is, the JSON will always be lacking the starting quote,
the ending quote, or both).

This was fixed in a simple way by adding parentheses to the
generated rule (for all string pattern rules, to keep it simple),
such that the new generated rule looks like this (correct):

```
thing ::= "\"" ("A" | "B" | "C" | "D") "\"" space
```

* grammars : add English-only grammar (#10612)

* grammar : handle maxItems == 0 in JSON schema (#13117)

Co-authored-by: Richard Lyons <frob@cloudstaff.com>

* grammar-parser : fix possible null-deref (#9004)

Fixes: https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=70680

Signed-off-by: David Korczynski <david@adalogics.com>

* llama : fix typo in llama-grammar.h [no ci] (#11816)

* * server: fix "--grammar-file" parameter (#12285)

* common : use std::string_view now that we target c++17 (#14319)

* json : support `enum` values within `allOf` (#15830)

* grammar : use int64_t to avoid int overflows in int schema to grammar conversion logic (#16626)

* grammar : support array references in json schema (#16792)

* grammar : support array references in json schema

* Update json-schema-to-grammar.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* grammar : improve regex when naming ref derived rules

* grammar : replace non-conformant definitions array with anyOf test case

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
# Conflicts:
#	tests/test-json-schema-to-grammar.cpp

* merge fix

* llama : minor grammar refactor (#10897)

* llama: fix error on bad grammar (#12628)

* grammar : fix integer overflow (#17381)

* Fix DoS / integer overflow

* Remove optional, use INT64_MAX instead as placeholder value (it's technically -1, so it fits :)

* White space

* Actually, since it's unsigned, use UINT64_MAX
# Conflicts:
#	src/llama-grammar.cpp

* grammar: fix regression caused by #17381 (#17412)

* grammar: fix regression caused by #17381

* more readable
# Conflicts:
#	src/llama-grammar.cpp

* Merge Fix

* Fix warnings

---------

Signed-off-by: David Korczynski <david@adalogics.com>
Co-authored-by: Joe Eli McIlvain <joe.eli.mac@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: frob <rick+github@frob.com.au>
Co-authored-by: Richard Lyons <frob@cloudstaff.com>
Co-authored-by: DavidKorczynski <david@adalogics.com>
Co-authored-by: Daniel Bevenius <daniel.bevenius@gmail.com>
Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Aldehir Rojas <hello@alde.dev>
Co-authored-by: Olivier Chafik <olivier.chafik@gmail.com>
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-11-30 18:45:38 +01:00

130 lines
4.0 KiB
C++

#define LLAMA_API_INTERNAL
#include "grammar-parser.h"
#include "ggml.h"
#include "llama.h"
#include "unicode.h"
#include <cstdio>
#include <cstdlib>
#include <sstream>
#include <fstream>
#include <string>
#include <vector>
static bool llama_sample_grammar_string(struct llama_grammar * grammar, const std::string & input_str, size_t & error_pos, std::string & error_msg) {
const auto cpts = unicode_cpts_from_utf8(input_str);
auto& cur_stacks = llama_grammar_get_stacks(grammar);
size_t pos = 0;
for (const auto& cpt : cpts) {
llama_grammar_accept(grammar, cpt);
if (cur_stacks.empty()) {
error_pos = pos;
error_msg = "Unexpected character '" + unicode_cpt_to_utf8(cpt) + "'";
return false;
}
++pos;
}
for (const auto & stack : cur_stacks) {
if (stack.empty()) {
return true;
}
}
error_pos = pos;
error_msg = "Unexpected end of input";
return false;
}
static void print_error_message(const std::string & input_str, size_t error_pos, const std::string & error_msg) {
fprintf(stdout, "Input string is invalid according to the grammar.\n");
fprintf(stdout, "Error: %s at position %zu\n", error_msg.c_str(), error_pos);
fprintf(stdout, "\n");
fprintf(stdout, "Input string:\n");
fprintf(stdout, "%s", input_str.substr(0, error_pos).c_str());
if (error_pos < input_str.size()) {
fprintf(stdout, "\033[1;31m%c", input_str[error_pos]);
if (error_pos+1 < input_str.size()) {
fprintf(stdout, "\033[0;31m%s", input_str.substr(error_pos+1).c_str());
}
fprintf(stdout, "\033[0m\n");
}
}
int main(int argc, char** argv) {
if (argc != 3) {
fprintf(stdout, "Usage: %s <grammar_filename> <input_filename>\n", argv[0]);
return 1;
}
const std::string grammar_filename = argv[1];
const std::string input_filename = argv[2];
// Read the GBNF grammar file
FILE* grammar_file = fopen(grammar_filename.c_str(), "r");
if (!grammar_file) {
fprintf(stdout, "Failed to open grammar file: %s\n", grammar_filename.c_str());
return 1;
}
std::string grammar_str;
{
std::ifstream grammar_file(grammar_filename);
GGML_ASSERT(grammar_file.is_open() && "Failed to open grammar file");
std::stringstream buffer;
buffer << grammar_file.rdbuf();
grammar_str = buffer.str();
}
// Parse the GBNF grammar
auto parsed_grammar = grammar_parser::parse(grammar_str.c_str());
// will be empty (default) if there are parse errors
if (parsed_grammar.rules.empty()) {
fprintf(stdout, "%s: failed to parse grammar\n", __func__);
return 1;
}
// Ensure that there is a "root" node.
if (parsed_grammar.symbol_ids.find("root") == parsed_grammar.symbol_ids.end()) {
fprintf(stdout, "%s: grammar does not contain a 'root' symbol\n", __func__);
return 1;
}
std::vector<const llama_grammar_element *> grammar_rules(parsed_grammar.c_rules());
// Create the LLAMA grammar
auto grammar = llama_grammar_init(
grammar_rules.data(),
grammar_rules.size(), parsed_grammar.symbol_ids.at("root"));
if (grammar == nullptr) {
throw std::runtime_error("Failed to initialize llama_grammar");
}
// Read the input file
std::string input_str;
{
std::ifstream input_file(input_filename);
GGML_ASSERT(input_file.is_open() && "Failed to open input file");
std::stringstream buffer;
buffer << input_file.rdbuf();
input_str = buffer.str();
}
// Validate the input string against the grammar
size_t error_pos;
std::string error_msg;
bool is_valid = llama_sample_grammar_string(grammar, input_str, error_pos, error_msg);
if (is_valid) {
fprintf(stdout, "Input string is valid according to the grammar.\n");
} else {
print_error_message(input_str, error_pos, error_msg);
}
// Clean up
llama_grammar_free(grammar);
return 0;
}