mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
grammar : use int64_t to avoid int overflows in int schema to grammar conversion logic (#16626)
This commit is contained in:
@@ -41,9 +41,9 @@ static std::string build_repetition(const std::string & item_rule, int min_items
|
||||
return result;
|
||||
}
|
||||
|
||||
static void _build_min_max_int(int min_value, int max_value, std::stringstream & out, int decimals_left = 16, bool top_level = true) {
|
||||
auto has_min = min_value != std::numeric_limits<int>::min();
|
||||
auto has_max = max_value != std::numeric_limits<int>::max();
|
||||
static void _build_min_max_int(int64_t min_value, int64_t max_value, std::stringstream & out, int decimals_left = 16, bool top_level = true) {
|
||||
auto has_min = min_value != std::numeric_limits<int64_t>::min();
|
||||
auto has_max = max_value != std::numeric_limits<int64_t>::max();
|
||||
|
||||
auto digit_range = [&](char from, char to) {
|
||||
out << "[";
|
||||
@@ -159,7 +159,7 @@ static void _build_min_max_int(int min_value, int max_value, std::stringstream &
|
||||
if (has_min) {
|
||||
if (min_value < 0) {
|
||||
out << "\"-\" (";
|
||||
_build_min_max_int(std::numeric_limits<int>::min(), -min_value, out, decimals_left, /* top_level= */ false);
|
||||
_build_min_max_int(std::numeric_limits<int64_t>::min(), -min_value, out, decimals_left, /* top_level= */ false);
|
||||
out << ") | [0] | [1-9] ";
|
||||
more_digits(0, decimals_left - 1);
|
||||
} else if (min_value == 0) {
|
||||
@@ -194,7 +194,7 @@ static void _build_min_max_int(int min_value, int max_value, std::stringstream &
|
||||
}
|
||||
digit_range(c, c);
|
||||
out << " (";
|
||||
_build_min_max_int(std::stoi(min_s.substr(1)), std::numeric_limits<int>::max(), out, less_decimals, /* top_level= */ false);
|
||||
_build_min_max_int(std::stoll(min_s.substr(1)), std::numeric_limits<int64_t>::max(), out, less_decimals, /* top_level= */ false);
|
||||
out << ")";
|
||||
if (c < '9') {
|
||||
out << " | ";
|
||||
@@ -216,7 +216,7 @@ static void _build_min_max_int(int min_value, int max_value, std::stringstream &
|
||||
_build_min_max_int(0, max_value, out, decimals_left, /* top_level= */ true);
|
||||
} else {
|
||||
out << "\"-\" (";
|
||||
_build_min_max_int(-max_value, std::numeric_limits<int>::max(), out, decimals_left, /* top_level= */ false);
|
||||
_build_min_max_int(-max_value, std::numeric_limits<int64_t>::max(), out, decimals_left, /* top_level= */ false);
|
||||
out << ")";
|
||||
}
|
||||
return;
|
||||
@@ -925,17 +925,17 @@ public:
|
||||
int max_len = schema.contains("maxLength") ? schema["maxLength"].get<int>() : std::numeric_limits<int>::max();
|
||||
return _add_rule(rule_name, "\"\\\"\" " + build_repetition(char_rule, min_len, max_len) + " \"\\\"\" space");
|
||||
} else if (schema_type == "integer" && (schema.contains("minimum") || schema.contains("exclusiveMinimum") || schema.contains("maximum") || schema.contains("exclusiveMaximum"))) {
|
||||
int min_value = std::numeric_limits<int>::min();
|
||||
int max_value = std::numeric_limits<int>::max();
|
||||
int64_t min_value = std::numeric_limits<int64_t>::min();
|
||||
int64_t max_value = std::numeric_limits<int64_t>::max();
|
||||
if (schema.contains("minimum")) {
|
||||
min_value = schema["minimum"].get<int>();
|
||||
min_value = schema["minimum"].get<int64_t>();
|
||||
} else if (schema.contains("exclusiveMinimum")) {
|
||||
min_value = schema["exclusiveMinimum"].get<int>() + 1;
|
||||
min_value = schema["exclusiveMinimum"].get<int64_t>() + 1;
|
||||
}
|
||||
if (schema.contains("maximum")) {
|
||||
max_value = schema["maximum"].get<int>();
|
||||
max_value = schema["maximum"].get<int64_t>();
|
||||
} else if (schema.contains("exclusiveMaximum")) {
|
||||
max_value = schema["exclusiveMaximum"].get<int>() - 1;
|
||||
max_value = schema["exclusiveMaximum"].get<int64_t>() - 1;
|
||||
}
|
||||
std::stringstream out;
|
||||
out << "(";
|
||||
|
||||
@@ -301,6 +301,30 @@ static void test_simple_grammar() {
|
||||
"0123",
|
||||
}
|
||||
);
|
||||
test_schema(
|
||||
"min 1 max 900719925474091",
|
||||
// Schema
|
||||
R"""({
|
||||
"type": "integer",
|
||||
"exclusiveMinimum": 0,
|
||||
"maximum": 900719925474091
|
||||
})""",
|
||||
// Passing strings
|
||||
{
|
||||
"1",
|
||||
"2",
|
||||
"10",
|
||||
"900719925474090",
|
||||
"900719925474091",
|
||||
},
|
||||
// Failing strings
|
||||
{
|
||||
"0",
|
||||
"01",
|
||||
"900719925474092",
|
||||
"9007199254740910",
|
||||
}
|
||||
);
|
||||
test_schema(
|
||||
"min -1 max 1",
|
||||
R"""({
|
||||
|
||||
Reference in New Issue
Block a user