json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum (#7797)
* 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
GitHub
parent
dd047b476c
commit
84631fe150
6 changed files with 1150 additions and 3 deletions
|
|
@ -24,6 +24,201 @@ function _buildRepetition(itemRule, minItems, maxItems, opts={}) {
|
|||
return minItems === 0 ? `(${result})?` : result;
|
||||
}
|
||||
|
||||
function _generateMinMaxInt(minValue, maxValue, out, decimalsLeft = 16, topLevel = true) {
|
||||
const hasMin = minValue !== null;
|
||||
const hasMax = maxValue !== null;
|
||||
|
||||
function digitRange(fromChar, toChar) {
|
||||
out.push("[");
|
||||
if (fromChar === toChar) {
|
||||
out.push(fromChar);
|
||||
} else {
|
||||
out.push(fromChar);
|
||||
out.push("-");
|
||||
out.push(toChar);
|
||||
}
|
||||
out.push("]");
|
||||
}
|
||||
|
||||
function moreDigits(minDigits, maxDigits) {
|
||||
out.push("[0-9]");
|
||||
if (minDigits === maxDigits && minDigits === 1) {
|
||||
return;
|
||||
}
|
||||
out.push("{");
|
||||
out.push(minDigits.toString());
|
||||
if (maxDigits !== minDigits) {
|
||||
out.push(",");
|
||||
if (maxDigits !== Number.MAX_SAFE_INTEGER) {
|
||||
out.push(maxDigits.toString());
|
||||
}
|
||||
}
|
||||
out.push("}");
|
||||
}
|
||||
|
||||
function uniformRange(fromStr, toStr) {
|
||||
let i = 0;
|
||||
while (i < fromStr.length && fromStr[i] === toStr[i]) {
|
||||
i++;
|
||||
}
|
||||
if (i > 0) {
|
||||
out.push("\"");
|
||||
out.push(fromStr.slice(0, i));
|
||||
out.push("\"");
|
||||
}
|
||||
if (i < fromStr.length) {
|
||||
if (i > 0) {
|
||||
out.push(" ");
|
||||
}
|
||||
const subLen = fromStr.length - i - 1;
|
||||
if (subLen > 0) {
|
||||
const fromSub = fromStr.slice(i + 1);
|
||||
const toSub = toStr.slice(i + 1);
|
||||
const subZeros = "0".repeat(subLen);
|
||||
const subNines = "9".repeat(subLen);
|
||||
|
||||
let toReached = false;
|
||||
out.push("(");
|
||||
if (fromSub === subZeros) {
|
||||
digitRange(fromStr[i], String.fromCharCode(toStr.charCodeAt(i) - 1));
|
||||
out.push(" ");
|
||||
moreDigits(subLen, subLen);
|
||||
} else {
|
||||
out.push("[");
|
||||
out.push(fromStr[i]);
|
||||
out.push("] ");
|
||||
out.push("(");
|
||||
uniformRange(fromSub, subNines);
|
||||
out.push(")");
|
||||
if (fromStr.charCodeAt(i) < toStr.charCodeAt(i) - 1) {
|
||||
out.push(" | ");
|
||||
if (toSub === subNines) {
|
||||
digitRange(String.fromCharCode(fromStr.charCodeAt(i) + 1), toStr[i]);
|
||||
toReached = true;
|
||||
} else {
|
||||
digitRange(String.fromCharCode(fromStr.charCodeAt(i) + 1), String.fromCharCode(toStr.charCodeAt(i) - 1));
|
||||
}
|
||||
out.push(" ");
|
||||
moreDigits(subLen, subLen);
|
||||
}
|
||||
}
|
||||
if (!toReached) {
|
||||
out.push(" | ");
|
||||
digitRange(toStr[i], toStr[i]);
|
||||
out.push(" ");
|
||||
uniformRange(subZeros, toSub);
|
||||
}
|
||||
out.push(")");
|
||||
} else {
|
||||
out.push("[");
|
||||
out.push(fromStr[i]);
|
||||
out.push("-");
|
||||
out.push(toStr[i]);
|
||||
out.push("]");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (hasMin && hasMax) {
|
||||
if (minValue < 0 && maxValue < 0) {
|
||||
out.push("\"-\" (");
|
||||
_generateMinMaxInt(-maxValue, -minValue, out, decimalsLeft, true);
|
||||
out.push(")");
|
||||
return;
|
||||
}
|
||||
|
||||
if (minValue < 0) {
|
||||
out.push("\"-\" (");
|
||||
_generateMinMaxInt(0, -minValue, out, decimalsLeft, true);
|
||||
out.push(") | ");
|
||||
minValue = 0;
|
||||
}
|
||||
|
||||
let minS = minValue.toString();
|
||||
const maxS = maxValue.toString();
|
||||
const minDigits = minS.length;
|
||||
const maxDigits = maxS.length;
|
||||
|
||||
for (let digits = minDigits; digits < maxDigits; digits++) {
|
||||
uniformRange(minS, "9".repeat(digits));
|
||||
minS = "1" + "0".repeat(digits);
|
||||
out.push(" | ");
|
||||
}
|
||||
uniformRange(minS, maxS);
|
||||
return;
|
||||
}
|
||||
|
||||
const lessDecimals = Math.max(decimalsLeft - 1, 1);
|
||||
|
||||
if (hasMin) {
|
||||
if (minValue < 0) {
|
||||
out.push("\"-\" (");
|
||||
_generateMinMaxInt(null, -minValue, out, decimalsLeft, false);
|
||||
out.push(") | [0] | [1-9] ");
|
||||
moreDigits(0, decimalsLeft - 1);
|
||||
} else if (minValue === 0) {
|
||||
if (topLevel) {
|
||||
out.push("[0] | [1-9] ");
|
||||
moreDigits(0, lessDecimals);
|
||||
} else {
|
||||
moreDigits(1, decimalsLeft);
|
||||
}
|
||||
} else if (minValue <= 9) {
|
||||
const c = minValue.toString();
|
||||
const range_start = topLevel ? '1' : '0';
|
||||
if (c > range_start) {
|
||||
digitRange(range_start, String.fromCharCode(c.charCodeAt(0) - 1));
|
||||
out.push(" ");
|
||||
moreDigits(1, lessDecimals);
|
||||
out.push(" | ");
|
||||
}
|
||||
digitRange(c, "9");
|
||||
out.push(" ");
|
||||
moreDigits(0, lessDecimals);
|
||||
} else {
|
||||
const minS = minValue.toString();
|
||||
const length = minS.length;
|
||||
const c = minS[0];
|
||||
|
||||
if (c > "1") {
|
||||
digitRange(topLevel ? "1" : "0", String.fromCharCode(c.charCodeAt(0) - 1));
|
||||
out.push(" ");
|
||||
moreDigits(length, lessDecimals);
|
||||
out.push(" | ");
|
||||
}
|
||||
digitRange(c, c);
|
||||
out.push(" (");
|
||||
_generateMinMaxInt(parseInt(minS.slice(1)), null, out, lessDecimals, false);
|
||||
out.push(")");
|
||||
if (c < "9") {
|
||||
out.push(" | ");
|
||||
digitRange(String.fromCharCode(c.charCodeAt(0) + 1), "9");
|
||||
out.push(" ");
|
||||
moreDigits(length - 1, lessDecimals);
|
||||
}
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
if (hasMax) {
|
||||
if (maxValue >= 0) {
|
||||
if (topLevel) {
|
||||
out.push("\"-\" [1-9] ");
|
||||
moreDigits(0, lessDecimals);
|
||||
out.push(" | ");
|
||||
}
|
||||
_generateMinMaxInt(0, maxValue, out, decimalsLeft, true);
|
||||
} else {
|
||||
out.push("\"-\" (");
|
||||
_generateMinMaxInt(-maxValue, null, out, decimalsLeft, false);
|
||||
out.push(")");
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
throw new Error("At least one of minValue or maxValue must be set");
|
||||
}
|
||||
|
||||
class BuiltinRule {
|
||||
constructor(content, deps) {
|
||||
this.content = content;
|
||||
|
|
@ -435,6 +630,24 @@ export class SchemaConverter {
|
|||
const minLen = schema.minLength || 0;
|
||||
const maxLen = schema.maxLength;
|
||||
return this._addRule(ruleName, '"\\\"" ' + _buildRepetition(charRuleName, minLen, maxLen) + ' "\\\"" space');
|
||||
} else if (schemaType === 'integer' && ('minimum' in schema || 'exclusiveMinimum' in schema || 'maximum' in schema || 'exclusiveMaximum' in schema)) {
|
||||
let minValue = null;
|
||||
let maxValue = null;
|
||||
if ('minimum' in schema) {
|
||||
minValue = schema.minimum;
|
||||
} else if ('exclusiveMinimum' in schema) {
|
||||
minValue = schema.exclusiveMinimum + 1;
|
||||
}
|
||||
if ('maximum' in schema) {
|
||||
maxValue = schema.maximum;
|
||||
} else if ('exclusiveMaximum' in schema) {
|
||||
maxValue = schema.exclusiveMaximum - 1;
|
||||
}
|
||||
|
||||
const out = ["("];
|
||||
_generateMinMaxInt(minValue, maxValue, out);
|
||||
out.push(") space");
|
||||
return this._addRule(ruleName, out.join(''));
|
||||
} else if ((schemaType === 'object') || (Object.keys(schema).length === 0)) {
|
||||
return this._addRule(ruleName, this._addPrimitive('object', PRIMITIVE_RULES['object']));
|
||||
} else {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue