json: basic support for reserved names {number:{number:{root:number}}}

examples/json-schema-to-grammar.py

@@ -35,6 +35,8 @@ DATE_RULES = {
     'date-time-string': '"\\"" date-time "\\"" space',
 }
 
+RESERVED_NAMES = set(["root", *PRIMITIVE_RULES.keys(), *DATE_RULES.keys()])
+
 INVALID_RULE_CHARS_RE = re.compile(r'[^a-zA-Z0-9-]+')
 GRAMMAR_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"]')
 GRAMMAR_RANGE_LITERAL_ESCAPE_RE = re.compile(r'[\r\n"\]\-\\]')
@@ -300,7 +302,7 @@ class SchemaConverter:
     def visit(self, schema, name):
         schema_type = schema.get('type')
         schema_format = schema.get('format')
-        rule_name = name or 'root'
+        rule_name = name + '-' if name in RESERVED_NAMES else name or 'root'
 
         if (ref := schema.get('$ref')) is not None:
             return self._add_rule(rule_name, self._resolve_ref(ref))

examples/server/json-schema-to-grammar.cpp

@@ -43,6 +43,16 @@ unordered_map<string, string> DATE_RULES = {
     {"date-time-string", "\"\\\"\" date-time \"\\\"\" space"}
 };
 
+static bool is_reserved_name(const string& name) {
+    static std::unordered_set<std::string> RESERVED_NAMES;
+    if (RESERVED_NAMES.empty()) {
+        RESERVED_NAMES.insert("root");
+        for (const auto &p : PRIMITIVE_RULES) RESERVED_NAMES.insert(p.first);
+        for (const auto &p : DATE_RULES) RESERVED_NAMES.insert(p.first);
+    }
+    return RESERVED_NAMES.find(name) != RESERVED_NAMES.end();
+}
+
 regex INVALID_RULE_CHARS_RE("[^a-zA-Z0-9-]+");
 regex GRAMMAR_LITERAL_ESCAPE_RE("[\r\n\"]");
 regex GRAMMAR_RANGE_LITERAL_ESCAPE_RE("[\r\n\"\\]\\-\\\\]");
@@ -523,7 +533,7 @@ public:
     string visit(const json& schema, const string& name) {
         json schema_type = schema.contains("type") ? schema["type"] : json();
         string schema_format = schema.contains("format") ? schema["format"].get<string>() : "";
-        string rule_name = name.empty() ? "root" : name;
+        string rule_name = is_reserved_name(name) ? name + "-" : name.empty() ? "root" : name;
 
         if (schema.contains("$ref")) {
             return _add_rule(rule_name, _resolve_ref(schema["$ref"]));

examples/server/public/json-schema-to-grammar.mjs

@@ -26,6 +26,8 @@ const DATE_RULES = {
     'date-time-string': '"\\"" date-time "\\"" space',
 };
 
+const RESERVED_NAMES = {'root': true, ...PRIMITIVE_RULES, ...DATE_RULES};
+
 const INVALID_RULE_CHARS_RE = /[^\dA-Za-z-]+/g;
 const GRAMMAR_LITERAL_ESCAPE_RE = /[\n\r"]/g;
 const GRAMMAR_RANGE_LITERAL_ESCAPE_RE = /[\n\r"\]\-\\]/g;
@@ -326,7 +328,7 @@ export class SchemaConverter {
   visit(schema, name) {
     const schemaType = schema.type;
     const schemaFormat = schema.format;
-    const ruleName = name || 'root';
+    const ruleName = name in RESERVED_NAMES ? name + '-' : name == '' ? 'root' : name;
 
     const ref = schema.$ref;
     if (ref !== undefined) {

tests/test-json-schema-to-grammar.cpp

@@ -259,10 +259,61 @@ int main() {
     )"""
   });
 
+  run_all({
+    "object w/ required props",
+    R"""({
+      "type": "object",
+      "properties": {
+        "a": {
+          "type": "string"
+        },
+        "b": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "a",
+        "b"
+      ],
+      "additionalProperties": false,
+      "definitions": {}
+    })""",
+    R"""(
+      a-kv ::= "\"a\"" space ":" space string
+      b-kv ::= "\"b\"" space ":" space string
+      root ::= "{" space a-kv "," space b-kv "}" space
+      space ::= " "?
+      string ::=  "\"" (
+              [^"\\] |
+              "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
+            )* "\"" space
+    )"""
+  });
+
+  run_all({
+    "1 optional",
+    R"""({
+      "properties": {
+        "a": {
+          "type": "string"
+        }
+      },
+      "additionalProperties": false
+    })""",
+    R"""(
+      a-kv ::= "\"a\"" space ":" space string
+      root ::= "{" space  (a-kv )? "}" space
+      space ::= " "?
+      string ::=  "\"" (
+              [^"\\] |
+              "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
+            )* "\"" space
+    )"""
+  });
+
   run_all({
     "optionals",
     R"""({
-      "$schema": "http://json-schema.org/draft-07/schema#",
       "type": "object",
       "properties": {
         "a": {
@@ -333,7 +384,6 @@ int main() {
   run_all({
     "top-level $ref",
     R"""({
-      "$schema": "http://json-schema.org/draft-07/schema#",
       "$ref": "#/definitions/MyType",
       "definitions": {
         "MyType": {
@@ -362,4 +412,48 @@ int main() {
     )"""
   });
 
+  run_all({
+    "conflicting names",
+    R"""({
+      "type": "object",
+      "properties": {
+        "number": {
+          "type": "object",
+          "properties": {
+            "number": {
+              "type": "object",
+              "properties": {
+                "root": {
+                  "type": "number"
+                }
+              },
+              "required": [
+                "root"
+              ],
+              "additionalProperties": false
+            }
+          },
+          "required": [
+            "number"
+          ],
+          "additionalProperties": false
+        }
+      },
+      "required": [
+        "number"
+      ],
+      "additionalProperties": false,
+      "definitions": {}
+    })""",
+    R"""(
+      number ::= ("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? space
+      number- ::= "{" space number-number-kv "}" space
+      number-kv ::= "\"number\"" space ":" space number-
+      number-number ::= "{" space number-number-root-kv "}" space
+      number-number-kv ::= "\"number\"" space ":" space number-number
+      number-number-root-kv ::= "\"root\"" space ":" space number
+      root ::= "{" space number-kv "}" space
+      space ::= " "?
+    )"""
+  });
 }