json: test (& simplify output of) empty schema

Makefile

@@ -862,7 +862,7 @@ tests/test-double-float: tests/test-double-float.cpp ggml.o $(OBJS)
 	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 
-tests/test-json-schema-to-grammar: tests/test-json-schema-to-grammar.cpp
+tests/test-json-schema-to-grammar: tests/test-json-schema-to-grammar.cpp examples/server/json-schema-to-grammar.cpp examples/server/json-schema-to-grammar.h
 	$(CXX) $(CXXFLAGS) -c $< -o $(call GET_OBJ_FILE, $<)
 	$(CXX) $(CXXFLAGS) $(filter-out %.h $<,$^) $(call GET_OBJ_FILE, $<) -o $@ $(LDFLAGS)
 

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

@@ -33,6 +33,7 @@ unordered_map<string, string> PRIMITIVE_RULES = {
                "      )* \"\\\"\" space"},
     {"null", "\"null\" space"}
 };
+vector<string> OBJECT_RULE_NAMES = {"object", "array", "string", "number", "boolean", "null"};
 
 unordered_map<string, string> DATE_RULES = {
     {"date", "[0-9] [0-9] [0-9] [0-9] \"-\" ( \"0\" [1-9] | \"1\" [0-2] ) \"-\" ( [0-2] [0-9] | \"3\" [0-1] )"},
@@ -663,10 +664,10 @@ public:
         } else if ((schema_type.is_null() || schema_type == "string") && schema.contains("pattern")) {
             return _visit_pattern(schema["pattern"], rule_name);
         } else if (schema.empty() || (schema.size() == 1 && schema_type == "object")) {
-            for (const auto& kv : PRIMITIVE_RULES) {
+            for (const auto& n : OBJECT_RULE_NAMES) {
-                _add_rule(kv.first, kv.second);
+                _add_rule(n, PRIMITIVE_RULES.at(n));
             }
-            return "object";
+            return _add_rule(rule_name, "object");
         } else if ((schema_type.is_null() || schema_type == "string") && regex_match(schema_format, regex("^uuid[1-5]?$"))) {
             return _add_rule(rule_name == "root" ? "root" : schema_format, PRIMITIVE_RULES.at("uuid"));
         } else if ((schema_type.is_null() || schema_type == "string") && DATE_RULES.find(schema_format) != DATE_RULES.end()) {

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

@@ -15,6 +15,7 @@ const PRIMITIVE_RULES = {
       )* "\\"" space`,
   null: '"null" space',
 };
+const OBJECT_RULE_NAMES = ['object', 'array', 'string', 'number', 'boolean', 'null'];
 
 // TODO: support "uri", "email" string formats
 const DATE_RULES = {
@@ -426,12 +427,11 @@ export class SchemaConverter {
         this._addRule(t, r);
       }
       return schemaFormat + '-string';
-    } else if (schemaType === 'object' && Object.keys(schema).length === 1 || schemaType === undefined && Object.keys(schema).length === 0) {
+    } else if ((schemaType === 'object' && Object.keys(schema).length === 1) || (Object.keys(schema).length === 0)) {
-      // This depends on all primitive types
+      for (const n of OBJECT_RULE_NAMES) {
-      for (const [t, r] of Object.entries(PRIMITIVE_RULES)) {
+        this._addRule(n, PRIMITIVE_RULES[n]);
-        this._addRule(t, r);
       }
-      return 'object';
+      return this._addRule(ruleName, 'object');
     } else {
       if (!(schemaType in PRIMITIVE_RULES)) {
         throw new Error(`Unrecognized schema: ${JSON.stringify(schema)}`);

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

@@ -68,7 +68,7 @@ static string read(const string& file) {
 }
 
 static void test_all(const string& lang, std::function<void(const TestCase&)> runner) {
-  cerr << "Testing JSON schema conversion (" << lang.c_str() << ")" << endl;
+  cerr << "#\n# Testing JSON schema conversion (" << lang.c_str() << ")\n#" << endl;
   auto test = [&](const TestCase& tc) {
     cerr << "- " << tc.name.c_str() << (tc.expected_status == FAILURE ? " (failure expected)" : "") << endl;
     runner(tc);
@@ -92,6 +92,25 @@ static void test_all(const string& lang, std::function<void(const TestCase&)> ru
     ""
   });
 
+  test({
+    SUCCESS,
+    "empty schema (object)",
+    "{}",
+    R"""(
+      array ::= "[" space ( value ("," space value)* )? "]" space
+      boolean ::= ("true" | "false") space
+      null ::= "null" space
+      number ::= ("-"? ([0-9] | [1-9] [0-9]*)) ("." [0-9]+)? ([eE] [-+]? [0-9]+)? space
+      object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
+      root ::= object
+      space ::= " "?
+      string ::=  "\"" (
+              [^"\\] |
+              "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
+            )* "\"" space
+    )"""
+  });
+
   test({
     SUCCESS,
     "exotic formats",