Fix schemagen integer parser rejecting zero with negative exponents

Move the zero-detection check in the generated parseJsonInt64 before the
finalExp < 0 guard. Previously, valid JSON numbers whose mathematical
value is 0 but written with a large negative exponent (e.g. 0e-2,
0.0e-2, -0e-2, 0e-20) were rejected because the negative-finalExp early
return ran before the all-zero-digits branch could set out = 0. Non-zero
values with negative exponents are still correctly rejected.

Closes #56

contrib/schemagen/test_schemagen.py

@@ -353,6 +353,132 @@ class SchemagenCyclicArrayTest(unittest.TestCase):
         self.assertIn("std::optional<std::vector<Role>> roles;", stdout)
 
 
+class SchemagenCyclicNullableObjectTest(unittest.TestCase):
+    """Regression tests for issue #14: nullable cyclic $ref targets."""
+
+    def setUp(self):
+        self.repo_root = os.path.dirname(
+            os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+        )
+        self.include_dir = os.path.join(self.repo_root, "include")
+        self.lib_src = os.path.join(self.repo_root, "src", "lib.cpp")
+        self.compiler = shutil.which("c++")
+
+    def _compile_harness(self, tmpdir, schema, harness):
+        schema_path = os.path.join(tmpdir, "schema.json")
+        with open(schema_path, "w") as fp:
+            json.dump(schema, fp)
+        header_path = os.path.join(tmpdir, "gen.h")
+        result = subprocess.run(
+            [
+                sys.executable,
+                SCRIPT,
+                schema_path,
+                "-o",
+                header_path,
+                "--namespace",
+                "test_schema",
+            ],
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        self.assertEqual(result.returncode, 0, msg=result.stderr)
+
+        lib_obj = os.path.join(tmpdir, "lib.o")
+        comp_lib = subprocess.run(
+            [
+                self.compiler,
+                "-std=c++20",
+                "-I",
+                self.include_dir,
+                "-I",
+                os.path.join(self.repo_root, "third_party", "include"),
+                "-I",
+                os.path.join(self.repo_root, "third_party", "valgrind"),
+                "-c",
+                self.lib_src,
+                "-o",
+                lib_obj,
+            ],
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        self.assertEqual(comp_lib.returncode, 0, msg=comp_lib.stderr)
+
+        cpp_path = os.path.join(tmpdir, "test.cpp")
+        with open(cpp_path, "w") as fp:
+            fp.write(harness)
+
+        exe_path = os.path.join(tmpdir, "test")
+        comp = subprocess.run(
+            [
+                self.compiler,
+                "-std=c++20",
+                "-I",
+                self.include_dir,
+                "-I",
+                tmpdir,
+                lib_obj,
+                cpp_path,
+                "-o",
+                exe_path,
+            ],
+            capture_output=True,
+            text=True,
+            check=False,
+        )
+        self.assertEqual(comp.returncode, 0, msg=comp.stderr)
+        run = subprocess.run([exe_path], capture_output=True, text=True, check=False)
+        self.assertEqual(run.returncode, 0, msg=run.stdout + run.stderr)
+
+    def test_self_referential_nullable_object_accepts_nested_null(self):
+        """A nullable object $def must stay nullable on recursive $refs."""
+        if not self.compiler:
+            self.skipTest("C++ compiler not available")
+        schema = {
+            "type": "object",
+            "properties": {"self": {"$ref": "#/$defs/Self"}},
+            "$defs": {
+                "Self": {
+                    "type": ["object", "null"],
+                    "properties": {"self": {"$ref": "#/$defs/Self"}},
+                }
+            },
+        }
+        harness = textwrap.dedent(
+            """
+            #include "gen.h"
+            #include <cstdio>
+            #include <cstring>
+            struct Case { const char *s; WeaselJsonStatus expected; };
+            int main() {
+              Case cases[] = {
+                { R"({"self": null})", WeaselJson_OK },
+                { R"({"self": {"self": null}})", WeaselJson_OK },
+                { R"({"self": {"self": {}}})", WeaselJson_OK },
+              };
+              for (const auto &c : cases) {
+                test_schema::RootBuilder b;
+                char buf[256];
+                std::strncpy(buf, c.s, sizeof(buf) - 1);
+                buf[sizeof(buf) - 1] = '\\0';
+                WeaselJsonStatus st = b.feed(buf, std::strlen(buf));
+                st = b.finish();
+                if (st != c.expected) {
+                  std::printf("case %s expected %d got %d\\n", c.s, c.expected, st);
+                  return 1;
+                }
+              }
+              return 0;
+            }
+            """
+        )
+        with tempfile.TemporaryDirectory() as tmpdir:
+            self._compile_harness(tmpdir, schema, harness)
+
+
 class SchemagenIntegerBoundaryTest(unittest.TestCase):
     """Regression tests for issue #19: integer slot parsing near int64 boundaries."""
 
@@ -466,6 +592,13 @@ 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(
@@ -508,6 +641,9 @@ 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",

contrib/schemagen/weaseljson_schemagen.py

@@ -1058,10 +1058,10 @@ 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

@@ -139,7 +139,7 @@ struct Parser3 {
     stackPtr = stack();
     std::ignore = push({N_VALUE, N_WHITESPACE, T_EOF});
     inKey = false;
-    rejected = false;
+    terminalStatus = WeaselJson_OK;
     utf8Codepoint = 0;
     utf16Surrogate = 0;
     minCodepoint = 0;
@@ -162,7 +162,7 @@ struct Parser3 {
   NumDfa numDfa;
   Utf8Dfa strDfa;
   bool inKey = false;
-  bool rejected = false;
+  WeaselJsonStatus terminalStatus = WeaselJson_OK;
 
 #ifndef HAS_MUSTTAIL
   char *stashBufForTrampoline;
@@ -650,7 +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)) {
@@ -1070,12 +1070,12 @@ constexpr inline struct ContinuationTable {
 inline WeaselJsonStatus Parser3::parse(char *buf, int len) {
   this->dataBegin = this->writeBuf = buf;
 
-  if (this->rejected) [[unlikely]] {
-    return WeaselJson_REJECT;
+  if (this->terminalStatus != WeaselJson_OK) [[unlikely]] {
+    return this->terminalStatus;
   }
 
   if (len < 0) [[unlikely]] {
-    this->rejected = true;
+    this->terminalStatus = WeaselJson_REJECT;
     return WeaselJson_REJECT;
   }
 
@@ -1085,8 +1085,8 @@ inline WeaselJsonStatus Parser3::parse(char *buf, int len) {
   // range.
   ContinuationStatus status =
       symbolTables.continuations[top()](this, buf, buf + len);
-  if (status == WeaselJson_REJECT) {
-    this->rejected = true;
+  if (status > WeaselJson_AGAIN) {
+    this->terminalStatus = WeaselJsonStatus(status);
   }
   return WeaselJsonStatus(status);
 #else
@@ -1095,8 +1095,8 @@ inline WeaselJsonStatus Parser3::parse(char *buf, int len) {
   while ((result = symbolTables.continuations[top()](
               this, stashBufForTrampoline, buf + len)) == kBounce)
     ;
-  if (result == WeaselJson_REJECT) {
-    this->rejected = true;
+  if (result > WeaselJson_AGAIN) {
+    this->terminalStatus = WeaselJsonStatus(result);
   }
   return WeaselJsonStatus(result);
 #endif

src/test.cpp

@@ -202,6 +202,62 @@ TEST_CASE("parser3") {
   }
 }
 
+TEST_CASE("overflow state is sticky") {
+  auto c = noopCallbacks();
+  // stackSize 3 is exactly big enough to hold reset()'s bootstrap, but too
+  // small for nested arrays. Overflows must be terminal like rejects: a later
+  // end-of-data call must never report OK for an incomplete document.
+  auto *parser = WeaselJsonParser_create(3, &c, nullptr, 0);
+  REQUIRE(parser != nullptr);
+
+  std::string doc = "[[";
+  REQUIRE(WeaselJsonParser_parse(parser, doc.data(), doc.size()) ==
+          WeaselJson_OVERFLOW);
+
+  // After overflow, the end-of-data call must not return OK.
+  REQUIRE(WeaselJsonParser_parse(parser, nullptr, 0) != WeaselJson_OK);
+  // It should keep reporting a terminal failure.
+  REQUIRE(WeaselJsonParser_parse(parser, nullptr, 0) != WeaselJson_OK);
+
+  // Further data chunks must also stay terminal.
+  std::string more = "]]";
+  REQUIRE(WeaselJsonParser_parse(parser, more.data(), more.size()) !=
+          WeaselJson_OK);
+
+  WeaselJsonParser_destroy(parser);
+}
+
+TEST_CASE("overflow is sticky for nested objects") {
+  auto c = noopCallbacks();
+  auto *parser = WeaselJsonParser_create(4, &c, nullptr, 0);
+  REQUIRE(parser != nullptr);
+
+  std::string doc = "{\"a\":{ \"a\":";
+  REQUIRE(WeaselJsonParser_parse(parser, doc.data(), doc.size()) ==
+          WeaselJson_OVERFLOW);
+  REQUIRE(WeaselJsonParser_parse(parser, nullptr, 0) != WeaselJson_OK);
+
+  WeaselJsonParser_destroy(parser);
+}
+
+TEST_CASE("reset clears overflow state") {
+  auto c = noopCallbacks();
+  auto *parser = WeaselJsonParser_create(3, &c, nullptr, 0);
+  REQUIRE(parser != nullptr);
+
+  std::string doc = "[[";
+  REQUIRE(WeaselJsonParser_parse(parser, doc.data(), doc.size()) ==
+          WeaselJson_OVERFLOW);
+  // After reset the parser should accept a minimal document again.
+  WeaselJsonParser_reset(parser);
+  std::string copy = "1";
+  REQUIRE(WeaselJsonParser_parse(parser, copy.data(), copy.size()) ==
+          WeaselJson_AGAIN);
+  REQUIRE(WeaselJsonParser_parse(parser, nullptr, 0) == WeaselJson_OK);
+
+  WeaselJsonParser_destroy(parser);
+}
+
 TEST_CASE("rejected state is sticky") {
   auto c = noopCallbacks();
   auto *parser = WeaselJsonParser_create(1024, &c, nullptr, 0);
@@ -274,6 +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: