vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum (#7797)

Browse source 
* json: support minimum for positive integer values

* json: fix min 0

* json: min + max integer constraints

* json: handle negative min / max integer bounds

* json: fix missing paren min/max bug

* json: proper paren fix

* json: integration test for schemas

* json: fix bounds tests

* Update json-schema-to-grammar.cpp

* json: fix negative max

* json: fix negative min (w/ more than 1 digit)

* Update test-grammar-integration.cpp

* json: nit: move string rules together

* json: port min/max integer support to Python & JS

* nit: move + rename _build_min_max_int

* fix min in [1, 9]

* Update test-grammar-integration.cpp

* add C++11-compatible replacement for std::string_view

* add min/max constrained int field to pydantic json schema example

* fix merge

* json: add integration tests for min/max bounds

* reshuffle/merge min/max integ test cases

* nits / cleanups

* defensive code against string out of bounds (apparently different behaviour of libstdc++ vs. clang's libc++, can't read final NULL char w/ former)
This commit is contained in:
Olivier Chafik 2024-06-25 20:06:20 +01:00 • committed by GitHub
parent dd047b476c
commit 84631fe150
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 1150 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

246
common/json-schema-to-grammar.cpp
View file

@ -40,6 +40,233 @@ static std::string build_repetition(const std::string & item_rule, int min_items
return result;
}
/* Minimalistic replacement for std::string_view, which is only available from C++17 onwards */
class string_view {
const std::string & _str;
const size_t _start;
const size_t _end;
public:
string_view(const std::string & str, size_t start = 0, size_t end = std::string::npos) : _str(str), _start(start), _end(end == std::string::npos ? str.length() : end) {}
size_t size() const {
return _end - _start;
}
size_t length() const {
return size();
}
operator std::string() const {
return str();
}
std::string str() const {
return _str.substr(_start, _end - _start);
}
string_view substr(size_t pos, size_t len = std::string::npos) const {
return string_view(_str, _start + pos, len == std::string::npos ? _end : _start + pos + len);
}
char operator[](size_t pos) const {
auto index = _start + pos;
if (index >= _end) {
throw std::out_of_range("string_view index out of range");
}
return _str[_start + pos];
}
bool operator==(const string_view & other) const {
std::string this_str = *this;
std::string other_str = other;
return this_str == other_str;
}
};
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();
auto digit_range = [&](char from, char to) {
out << "[";
if (from == to) {
out << from;
} else {
out << from << "-" << to;
}
out << "]";
};
auto more_digits = [&](int min_digits, int max_digits) {
out << "[0-9]";
if (min_digits == max_digits && min_digits == 1) {
return;
}
out << "{";
out << min_digits;
if (max_digits != min_digits) {
out << ",";
if (max_digits != std::numeric_limits<int>::max()) {
out << max_digits;
}
}
out << "}";
};
std::function<void(const string_view &, const string_view &)> uniform_range =
[&](const string_view & from, const string_view & to) {
size_t i = 0;
while (i < from.length() && i < to.length() && from[i] == to[i]) {
i++;
}
if (i > 0) {
out << "\"" << from.substr(0, i).str() << "\"";
}
if (i < from.length() && i < to.length()) {
if (i > 0) {
out << " ";
}
auto sub_len = from.length() - i - 1;
if (sub_len > 0) {
auto from_sub = from.substr(i + 1);
auto to_sub = to.substr(i + 1);
auto sub_zeros = repeat("0", sub_len);
auto sub_nines = repeat("9", sub_len);
auto to_reached = false;
out << "(";
if (from_sub == sub_zeros) {
digit_range(from[i], to[i] - 1);
out << " ";
more_digits(sub_len, sub_len);
} else {
out << "[" << from[i] << "] ";
out << "(";
uniform_range(from_sub, sub_nines);
out << ")";
if (from[i] < to[i] - 1) {
out << " | ";
if (to_sub == sub_nines) {
digit_range(from[i] + 1, to[i]);
to_reached = true;
} else {
digit_range(from[i] + 1, to[i] - 1);
}
out << " ";
more_digits(sub_len, sub_len);
}
}
if (!to_reached) {
out << " | ";
digit_range(to[i], to[i]);
out << " ";
uniform_range(sub_zeros, to_sub);
}
out << ")";
} else {
out << "[" << from[i] << "-" << to[i] << "]";
}
}
};
if (has_min && has_max) {
if (min_value < 0 && max_value < 0) {
out << "\"-\" (";
_build_min_max_int(-max_value, -min_value, out, decimals_left, /* top_level= */ true);
out << ")";
return;
}
if (min_value < 0) {
out << "\"-\" (";
_build_min_max_int(0, -min_value, out, decimals_left, /* top_level= */ true);
out << ") | ";
min_value = 0;
}
auto min_s = std::to_string(min_value);
auto max_s = std::to_string(max_value);
auto min_digits = min_s.length();
auto max_digits = max_s.length();
for (auto digits = min_digits; digits < max_digits; digits++) {
uniform_range(min_s, repeat("9", digits));
min_s = "1" + repeat("0", digits);
out << " | ";
}
uniform_range(min_s, max_s);
return;
}
auto less_decimals = std::max(decimals_left - 1, 1);
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);
out << ") | [0] | [1-9] ";
more_digits(0, decimals_left - 1);
} else if (min_value == 0) {
if (top_level) {
out << "[0] | [1-9] ";
more_digits(0, less_decimals);
} else {
more_digits(1, decimals_left);
}
} else if (min_value <= 9) {
char c = '0' + min_value;
auto range_start = top_level ? '1' : '0';
if (c > range_start) {
digit_range(range_start, c - 1);
out << " ";
more_digits(1, less_decimals);
out << " | ";
}
digit_range(c, '9');
out << " ";
more_digits(0, less_decimals);
} else {
auto min_s = std::to_string(min_value);
auto len = min_s.length();
auto c = min_s[0];
if (c > '1') {
digit_range(top_level ? '1' : '0', c - 1);
out << " ";
more_digits(len, less_decimals);
out << " | ";
}
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);
out << ")";
if (c < '9') {
out << " | ";
digit_range(c + 1, '9');
out << " ";
more_digits(len - 1, less_decimals);
}
}
return;
}
if (has_max) {
if (max_value >= 0) {
if (top_level) {
out << "\"-\" [1-9] ";
more_digits(0, less_decimals);
out << " | ";
}
_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);
out << ")";
}
return;
}
throw std::runtime_error("At least one of min_value or max_value must be set");
}
const std::string SPACE_RULE = "| \" \" | \"\\n\" [ \\t]{0,20}";
struct BuiltinRule {
@ -160,7 +387,6 @@ static std::string format_literal(const std::string & literal) {
return "\"" + escaped + "\"";
}
class SchemaConverter {
private:
std::function<json(const std::string &)> _fetch_json;
@ -686,6 +912,24 @@ public:
int min_len = schema.contains("minLength") ? schema["minLength"].get<int>() : 0;
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();
if (schema.contains("minimum")) {
min_value = schema["minimum"].get<int>();
} else if (schema.contains("exclusiveMinimum")) {
min_value = schema["exclusiveMinimum"].get<int>() + 1;
}
if (schema.contains("maximum")) {
max_value = schema["maximum"].get<int>();
} else if (schema.contains("exclusiveMaximum")) {
max_value = schema["exclusiveMaximum"].get<int>() - 1;
}
std::stringstream out;
out << "(";
_build_min_max_int(min_value, max_value, out);
out << ") space";
return _add_rule(rule_name, out.str());
} else if (schema.empty() || schema_type == "object") {
return _add_rule(rule_name, _add_primitive("object", PRIMITIVE_RULES.at("object")));
} else {