json: support non-string const / enums

common/json-schema-to-grammar.cpp

@@ -124,7 +124,7 @@ static std::string replacePattern(const std::string & input, const std::regex &
 }
 
 static std::string format_literal(const std::string & literal) {
-    std::string escaped = replacePattern(json(literal).dump(), GRAMMAR_LITERAL_ESCAPE_RE, [&](const std::smatch & match) {
+    std::string escaped = replacePattern(literal, GRAMMAR_LITERAL_ESCAPE_RE, [&](const std::smatch & match) {
         char c = match.str()[0];
         return GRAMMAR_LITERAL_ESCAPES.at(c);
     });
@@ -413,7 +413,7 @@ private:
             std::string prop_rule_name = visit(prop_schema, name + (name.empty() ? "" : "-") + prop_name);
             prop_kv_rule_names[prop_name] = _add_rule(
                 name + (name.empty() ? "" : "-") + prop_name + "-kv",
-                format_literal(prop_name) + " space \":\" space " + prop_rule_name
+                format_literal(json(prop_name).dump()) + " space \":\" space " + prop_rule_name
             );
             if (required.find(prop_name) != required.end()) {
                 required_props.push_back(prop_name);
@@ -557,11 +557,7 @@ public:
     }
 
     std::string _generate_constant_rule(const json & value) {
-        if (!value.is_string()) {
-            _errors.push_back("Only std::string constants are supported, got " + value.dump());
-            return "";
-        }
-        return format_literal(value.get<std::string>());
+        return format_literal(value.dump());
     }
 
     std::string visit(const json & schema, const std::string & name) {

examples/json-schema-to-grammar.py

@@ -61,7 +61,7 @@ class SchemaConverter:
 
     def _format_literal(self, literal):
         escaped = GRAMMAR_LITERAL_ESCAPE_RE.sub(
-            lambda m: GRAMMAR_LITERAL_ESCAPES.get(m.group(0)), json.dumps(literal)
+            lambda m: GRAMMAR_LITERAL_ESCAPES.get(m.group(0)), literal
         )
         return f'"{escaped}"'
 
@@ -308,8 +308,7 @@ class SchemaConverter:
         return ref_name
 
     def _generate_constant_rule(self, value):
-        assert isinstance(value, str), f'Only string constants are supported, got {value}'
-        return self._format_literal(value)
+        return self._format_literal(json.dumps(value))
 
     def visit(self, schema, name):
         schema_type = schema.get('type')
@@ -428,7 +427,7 @@ class SchemaConverter:
             prop_rule_name = self.visit(prop_schema, f'{name}{"-" if name else ""}{prop_name}')
             prop_kv_rule_names[prop_name] = self._add_rule(
                 f'{name}{"-" if name else ""}{prop_name}-kv',
-                fr'{self._format_literal(prop_name)} space ":" space {prop_rule_name}'
+                fr'{self._format_literal(json.dumps(prop_name))} space ":" space {prop_rule_name}'
             )
         required_props = [k for k in sorted_props if k in required]
         optional_props = [k for k in sorted_props if k not in required]

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

@@ -48,7 +48,7 @@ export class SchemaConverter {
   }
 
   _formatLiteral(literal) {
-    const escaped = JSON.stringify(literal).replace(
+    const escaped = literal.replace(
       GRAMMAR_LITERAL_ESCAPE_RE,
       m => GRAMMAR_LITERAL_ESCAPES[m]
     );
@@ -327,10 +327,7 @@ export class SchemaConverter {
   }
 
   _generateConstantRule(value) {
-    if (typeof value !== 'string') {
-      throw new Error('Only string constants are supported, got ' + JSON.stringify(value));
-    }
-    return this._formatLiteral(value);
+    return this._formatLiteral(JSON.stringify(value));
   }
 
   visit(schema, name) {
@@ -346,9 +343,6 @@ export class SchemaConverter {
     } else if (Array.isArray(schemaType)) {
       return this._addRule(ruleName, this._generateUnionRule(name, schemaType.map(t => ({ type: t }))));
     } else if ('const' in schema) {
-      if (typeof schema.const !== 'string') {
-        throw new Error('Only string constants are supported, got ' + JSON.stringify(schema.const));
-      }
       return this._addRule(ruleName, this._generateConstantRule(schema.const));
     } else if ('enum' in schema) {
       const rule = schema.enum.map(v => this._generateConstantRule(v)).join(' | ');
@@ -457,7 +451,7 @@ export class SchemaConverter {
       const propRuleName = this.visit(propSchema, `${name ?? ''}${name ? '-' : ''}${propName}`);
       propKvRuleNames[propName] = this._addRule(
         `${name ?? ''}${name ? '-' : ''}${propName}-kv`,
-        `${this._formatLiteral(propName)} space ":" space ${propRuleName}`
+        `${this._formatLiteral(JSON.stringify(propName))} space ":" space ${propRuleName}`
       );
     }
     const requiredProps = sortedProps.filter(k => required.has(k));

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

@@ -193,21 +193,27 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
     });
 
     test({
-        FAILURE,
+        SUCCESS,
         "non-string const",
         R"""({
             "const": 123
         })""",
-        ""
+        R"""(
+            root ::= "123"
+            space ::= " "?
+        )"""
     });
 
     test({
-        FAILURE,
+        SUCCESS,
         "non-string enum",
         R"""({
-            "enum": [123]
+            "enum": ["red", "amber", "green", null, 42, ["foo"]]
         })""",
-        ""
+        R"""(
+            root ::= "\"red\"" | "\"amber\"" | "\"green\"" | "null" | "42" | "[\"foo\"]"
+            space ::= " "?
+        )"""
     });
 
     test({