Merge pull request 'schemagen: reject absent additionalProperties' (#58) from weaselbot/weaseljson:weaselbot/issue-55 into main

Reviewed-on: #58

contrib/schemagen/README.md

@@ -60,8 +60,9 @@ into the result, so it is non-movable.
 ## Not supported (rejected at generation time, no fallback)
 
 `oneOf` / `anyOf` / `allOf` / `not` / `if`-`then`-`else`,
-`patternProperties`, `additionalProperties` with a schema (typed map),
+`patternProperties`, `additionalProperties` absent or set to `true`,
-`additionalProperties: true`, `prefixItems` (tuples), `const`,
+`additionalProperties` with a schema (typed map), `prefixItems` (tuples),
+`const`,
 `dependentSchemas`/`dependentRequired`, union `type` lists other than
 `["T", "null"]`, non-string enums, and remote (`$ref` to other documents).
 

contrib/schemagen/example.schema.json

@@ -56,6 +56,7 @@
       "type": "array",
       "items": {
         "type": "object",
+        "additionalProperties": false,
         "required": [
           "name"
         ],

contrib/schemagen/test_schemagen.py

@@ -32,6 +32,7 @@ class SchemagenEnumTest(unittest.TestCase):
     def test_colliding_enum_values_deduplicate(self):
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"role": {"enum": ["foo-bar", "foo_bar"]}},
         }
         rc, stdout, stderr = self.run_schemagen(schema)
@@ -45,6 +46,7 @@ class SchemagenEnumTest(unittest.TestCase):
     def test_distinct_enum_values_generate(self):
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"role": {"enum": ["admin", "user", "guest"]}},
         }
         rc, stdout, stderr = self.run_schemagen(schema)
@@ -80,7 +82,7 @@ class SchemagenKeywordTest(unittest.TestCase):
             "module",
             "import",
         ]
-        schema = {"type": "object", "properties": {}}
+        schema = {"type": "object", "additionalProperties": False, "properties": {}}
         for kw in keywords:
             schema["properties"][kw] = {"type": "string"}
         rc, stdout, stderr = self.run_schemagen(schema)
@@ -164,11 +166,18 @@ class SchemagenCollisionTest(unittest.TestCase):
     def test_kind_enum_does_not_duplicate_arr0(self):
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {
                 "arr": {"type": "array", "items": {"type": "string"}},
                 "obj": {"$ref": "#/$defs/Arr0"},
             },
-            "$defs": {"Arr0": {"type": "object", "properties": {}}},
+            "$defs": {
+                "Arr0": {
+                    "type": "object",
+                    "additionalProperties": False,
+                    "properties": {},
+                }
+            },
         }
         out = self.generate_and_compile(schema)
         self.assertIn("struct Arr0", out)
@@ -183,7 +192,13 @@ class SchemagenCollisionTest(unittest.TestCase):
         schema = {
             "type": "array",
             "items": {"$ref": "#/$defs/Skip"},
-            "$defs": {"Skip": {"type": "object", "properties": {}}},
+            "$defs": {
+                "Skip": {
+                    "type": "object",
+                    "additionalProperties": False,
+                    "properties": {},
+                }
+            },
         }
         out = self.generate_and_compile(schema)
         self.assertIn("struct Skip", out)
@@ -199,6 +214,7 @@ class SchemagenCollisionTest(unittest.TestCase):
         """Regression test for issue #17: enum and array $defs must be reused."""
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {
                 "role1": {"$ref": "#/$defs/Role"},
                 "role2": {"$ref": "#/$defs/Role"},
@@ -252,17 +268,14 @@ class SchemagenAdditionalPropertiesTest(unittest.TestCase):
         self.assertNotEqual(rc, 0)
         self.assertIn("additionalProperties: true is not supported", stderr)
 
-    def test_additional_properties_absent_defaults_to_strict(self):
+    def test_additional_properties_absent_rejected(self):
         schema = {
             "type": "object",
             "properties": {"name": {"type": "string"}},
         }
         rc, stdout, stderr = self.run_schemagen(schema)
-        self.assertEqual(rc, 0, msg=stderr)
+        self.assertNotEqual(rc, 0)
-        # The generated parser should reject unknown keys. Verify the key-matching
+        self.assertIn("additionalProperties is required for object schemas", stderr)
-        # helper returns -1 for an unknown key and cbKeyData rejects it.
-        self.assertIn("int matchKey(Kind k, std::string_view key) const {", stdout)
-        self.assertNotIn("bool isStrict(Kind k) const", stdout)
 
     def test_additional_properties_false_accepted(self):
         schema = {
@@ -310,6 +323,7 @@ class SchemagenCyclicArrayTest(unittest.TestCase):
     def test_object_field_to_self_referential_array_rejected(self):
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"items": {"$ref": "#/$defs/Items"}},
             "$defs": {
                 "Items": {
@@ -326,6 +340,7 @@ class SchemagenCyclicArrayTest(unittest.TestCase):
     def test_chain_of_array_refs_rejected(self):
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"x": {"$ref": "#/$defs/A"}},
             "$defs": {
                 "A": {"type": "array", "items": {"$ref": "#/$defs/B"}},
@@ -339,6 +354,7 @@ class SchemagenCyclicArrayTest(unittest.TestCase):
     def test_non_recursive_array_refs_still_allowed(self):
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"roles": {"$ref": "#/$defs/Roles"}},
             "$defs": {
                 "Role": {"enum": ["admin", "user"]},
@@ -439,10 +455,12 @@ class SchemagenCyclicNullableObjectTest(unittest.TestCase):
             self.skipTest("C++ compiler not available")
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"self": {"$ref": "#/$defs/Self"}},
             "$defs": {
                 "Self": {
                     "type": ["object", "null"],
+                    "additionalProperties": False,
                     "properties": {"self": {"$ref": "#/$defs/Self"}},
                 }
             },
@@ -592,6 +610,13 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
             ("123.0", "WeaselJson_OK", 123),
             ("9e18", "WeaselJson_OK", 9000000000000000000),
             ("10e18", "WeaselJson_REJECT", 0),
+            # Issue #56: zero written with a negative exponent must be accepted.
+            ("0e-1", "WeaselJson_OK", 0),
+            ("0e-2", "WeaselJson_OK", 0),
+            ("0.0e-2", "WeaselJson_OK", 0),
+            ("-0e-2", "WeaselJson_OK", 0),
+            ("0e-20", "WeaselJson_OK", 0),
+            ("0.000e-5", "WeaselJson_OK", 0),
         ]
         cases_src = self._build_cases_array("root", cases)
         harness = textwrap.dedent(
@@ -634,6 +659,9 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
             ('{"age":2.0}', "WeaselJson_OK", 2),
             ('{"age":0.0001e4}', "WeaselJson_OK", 1),
             ('{"age":0.001}', "WeaselJson_REJECT", 0),
+            # Issue #56: zero written with a negative exponent must be accepted.
+            ('{"age":0e-2}', "WeaselJson_OK", 0),
+            ('{"age":-0e-20}', "WeaselJson_OK", 0),
             (
                 '{"age":-9223372036854775808.0}',
                 "WeaselJson_OK",
@@ -670,6 +698,7 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
         )
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {"age": {"type": "integer"}},
             "required": ["age"],
         }
@@ -785,14 +814,22 @@ class SchemagenStringEscapeTest(unittest.TestCase):
 
     def test_newline_in_property_key(self):
         """A JSON key containing a newline must become a valid C++ literal."""
-        schema = {"type": "object", "properties": {"a\nb": {"type": "string"}}}
+        schema = {
+            "type": "object",
+            "additionalProperties": False,
+            "properties": {"a\nb": {"type": "string"}},
+        }
         out = self.generate_and_compile(schema)
         self.assertIn('// "a\\nb"', out)
         self.assertIn('if (key == "a\\nb") return 0;', out)
 
     def test_newline_in_enum_value(self):
         """An enum value containing a newline must become a valid C++ literal."""
-        schema = {"type": "object", "properties": {"x": {"enum": ["a\nb"]}}}
+        schema = {
+            "type": "object",
+            "additionalProperties": False,
+            "properties": {"x": {"enum": ["a\nb"]}},
+        }
         out = self.generate_and_compile(schema)
         self.assertIn('static constexpr const char *X_names[] = { "a\\nb" };', out)
 
@@ -800,6 +837,7 @@ class SchemagenStringEscapeTest(unittest.TestCase):
         """Mixed control characters in an enum value must be escaped."""
         schema = {
             "type": "object",
+            "additionalProperties": False,
             "properties": {
                 "x": {"enum": ["x\ny\rz\tw\vq\x00\x01"]},
             },
@@ -812,7 +850,11 @@ class SchemagenStringEscapeTest(unittest.TestCase):
 
     def test_backslash_and_quote_still_escaped(self):
         """Existing escaping for backslash and double quote must remain correct."""
-        schema = {"type": "object", "properties": {'a"b\\c': {"type": "string"}}}
+        schema = {
+            "type": "object",
+            "additionalProperties": False,
+            "properties": {'a"b\\c': {"type": "string"}},
+        }
         out = self.generate_and_compile(schema)
         self.assertIn('// "a\\"b\\\\c"', out)
         self.assertIn('if (key == "a\\"b\\\\c") return 0;', out)

contrib/schemagen/weaseljson_schemagen.py

@@ -417,7 +417,13 @@ class Builder:
         tobj = TObj(name)
         if defname is not None:
             self._building[defname] = (tobj, nullable)
-        ap = node.get("additionalProperties", False)
+        ap = node.get("additionalProperties", None)
+        if ap is None:
+            raise GenError(
+                "additionalProperties is required for object schemas; set it "
+                "explicitly to false to reject unknown keys (absent "
+                "additionalProperties is not supported)"
+            )
         if ap is True:
             raise GenError("additionalProperties: true is not supported")
         if isinstance(ap, dict):
@@ -1058,10 +1064,10 @@ private:
       ++trim;
     }}
     int64_t finalExp = exp - fracDigits + trim;
-    if (finalExp < 0) return false;
     size_t leadingZeros = 0;
     while (leadingZeros < digits.size() && digits[leadingZeros] == '0') ++leadingZeros;
     if (leadingZeros == digits.size()) {{ out = 0; return true; }}
+    if (finalExp < 0) return false;
     if (leadingZeros > 0) digits.erase(0, leadingZeros);
 
     constexpr uint64_t kMaxNeg = 9223372036854775808ULL;

include/weaseljson.h

@@ -38,6 +38,8 @@ enum WeaselJsonStatus {
   WeaselJson_REJECT,
   /** json is too deeply nested */
   WeaselJson_OVERFLOW,
+  /** Tried to call parse on a null parser */
+  WeaselJson_NULL,
 };
 
 typedef struct WeaselJsonParser WeaselJsonParser;
@@ -65,7 +67,7 @@ void WeaselJsonParser_destroy(WeaselJsonParser *parser);
 /** Incrementally parse `len` more bytes starting at `buf`. `buf` may be
  * modified. Call with `len` 0 to indicate end of data. `buf` may be null if
  * `len` is 0. `len` must not be negative; a negative length is treated as a
- * rejected input. */
+ * rejected input. Returns WeaselJson_NULL if parser is null */
 WeaselJsonStatus WeaselJsonParser_parse(WeaselJsonParser *parser, char *buf,
                                         int len);
 

src/lib.cpp

@@ -46,6 +46,9 @@ WeaselJsonParser_destroy(WeaselJsonParser *parser) {
 
 __attribute__((visibility("default"))) WeaselJsonStatus
 WeaselJsonParser_parse(WeaselJsonParser *parser, char *buf, int len) {
+  if (parser == nullptr) [[unlikely]] {
+    return WeaselJson_NULL;
+  }
   return ((Parser3 *)parser)->parse(buf, len);
 }
 }

src/parser3.h

@@ -139,8 +139,7 @@ struct Parser3 {
     stackPtr = stack();
     std::ignore = push({N_VALUE, N_WHITESPACE, T_EOF});
     inKey = false;
-    rejected = false;
+    terminalStatus = WeaselJson_OK;
-    overflowed = false;
     utf8Codepoint = 0;
     utf16Surrogate = 0;
     minCodepoint = 0;
@@ -163,8 +162,7 @@ struct Parser3 {
   NumDfa numDfa;
   Utf8Dfa strDfa;
   bool inKey = false;
-  bool rejected = false;
+  WeaselJsonStatus terminalStatus = WeaselJson_OK;
-  bool overflowed = false;
 
 #ifndef HAS_MUSTTAIL
   char *stashBufForTrampoline;
@@ -652,7 +650,7 @@ inline PRESERVE_NONE ContinuationStatus n_string2(Parser3 *self, char *buf,
             self->writeBuf[0] = (0b00000111 & codepoint) | 0b11110000;
             self->writeBuf += 4;
           }
-        } else if (0xdc00 <= codepoint && codepoint <= 0xdfff) {
+        } else if (0xdc00 <= codepoint && codepoint <= 0xdfff) [[unlikely]] {
           return WeaselJson_REJECT;
         } else {
           if (!(self->flags & WeaselJsonRaw)) {
@@ -1072,16 +1070,12 @@ constexpr inline struct ContinuationTable {
 inline WeaselJsonStatus Parser3::parse(char *buf, int len) {
   this->dataBegin = this->writeBuf = buf;
 
-  if (this->rejected) [[unlikely]] {
+  if (this->terminalStatus != WeaselJson_OK) [[unlikely]] {
-    return WeaselJson_REJECT;
+    return this->terminalStatus;
-  }
-
-  if (this->overflowed) [[unlikely]] {
-    return WeaselJson_OVERFLOW;
   }
 
   if (len < 0) [[unlikely]] {
-    this->rejected = true;
+    this->terminalStatus = WeaselJson_REJECT;
     return WeaselJson_REJECT;
   }
 
@@ -1091,10 +1085,8 @@ inline WeaselJsonStatus Parser3::parse(char *buf, int len) {
   // range.
   ContinuationStatus status =
       symbolTables.continuations[top()](this, buf, buf + len);
-  if (status == WeaselJson_REJECT) {
+  if (status > WeaselJson_AGAIN) {
-    this->rejected = true;
+    this->terminalStatus = WeaselJsonStatus(status);
-  } else if (status == WeaselJson_OVERFLOW) {
-    this->overflowed = true;
   }
   return WeaselJsonStatus(status);
 #else
@@ -1103,10 +1095,8 @@ inline WeaselJsonStatus Parser3::parse(char *buf, int len) {
   while ((result = symbolTables.continuations[top()](
               this, stashBufForTrampoline, buf + len)) == kBounce)
     ;
-  if (result == WeaselJson_REJECT) {
+  if (result > WeaselJson_AGAIN) {
-    this->rejected = true;
+    this->terminalStatus = WeaselJsonStatus(result);
-  } else if (result == WeaselJson_OVERFLOW) {
-    this->overflowed = true;
   }
   return WeaselJsonStatus(result);
 #endif

src/test.cpp

@@ -330,6 +330,10 @@ TEST_CASE("parse rejects negative length") {
   WeaselJsonParser_destroy(parser);
 }
 
+TEST_CASE("Calling parse with nullptr doesn't crash") {
+  REQUIRE(WeaselJsonParser_parse(nullptr, nullptr, 0) == WeaselJson_NULL);
+}
+
 TEST_CASE("streaming") { testStreaming(json); }
 
 TEST_CASE("reset clears inKey and transient state") {

src/validate.cpp

@@ -33,6 +33,9 @@ int main(int argc, char **argv) {
     case WeaselJson_REJECT:
     case WeaselJson_OVERFLOW:
       return 1;
+    case WeaselJson_NULL:
+      fprintf(stderr, "parse called with a null parser\n");
+      return 1;
     }
     if (l == 0) {
       return 1;

weaseljson.py

@@ -30,6 +30,7 @@ class WeaselJsonStatus(enum.Enum):
     AGAIN = 1
     REJECT = 2
     OVERFLOW = 3
+    NULL = 4
 
 
 class WeaselJsonCallbacksBase: