From ceb16e540530d78f3bb60e31577cb85c6bde21aa Mon Sep 17 00:00:00 2001
From: Weaselbot <weaselbot@weaselab.dev>
Date: Tue, 30 Jun 2026 12:09:26 -0400
Subject: [PATCH] schemagen: fix quadratic leading-zero strip in integer
 fallback

Replace the O(k^2) loop that erased leading zeros one byte at a time
from the front of a std::string with a single linear scan and one
erase(0, n) call.

Also adds regression tests for issue #34:
- correctness cases for numbers with leading fractional zeros
- a static check that the generated code no longer contains the
  quadratic pattern
- a large-input case (100k leading zeros) that reproduces the
  vulnerable shape

Closes #34
---
 contrib/schemagen/test_schemagen.py       | 49 +++++++++++++++++++++++
 contrib/schemagen/weaseljson_schemagen.py |  6 ++-
 2 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/contrib/schemagen/test_schemagen.py b/contrib/schemagen/test_schemagen.py
index fdf195b..4fdd0ae 100644
--- a/contrib/schemagen/test_schemagen.py
+++ b/contrib/schemagen/test_schemagen.py
@@ -382,6 +382,8 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
             ("1e-3", "WeaselJson_REJECT", 0),
             ("1000e-3", "WeaselJson_OK", 1),
             ("100.0e-2", "WeaselJson_OK", 1),
+            ("0.0001e4", "WeaselJson_OK", 1),
+            ("0.001e3", "WeaselJson_OK", 1),
             ("123.0", "WeaselJson_OK", 123),
             ("9e18", "WeaselJson_OK", 9000000000000000000),
             ("10e18", "WeaselJson_REJECT", 0),
@@ -425,6 +427,7 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
             ('{"age":-9223372036854775809}', "WeaselJson_REJECT", 0),
             ('{"age":1e3}', "WeaselJson_OK", 1000),
             ('{"age":2.0}', "WeaselJson_OK", 2),
+            ('{"age":0.0001e4}', "WeaselJson_OK", 1),
             ('{"age":0.001}', "WeaselJson_REJECT", 0),
             (
                 '{"age":-9223372036854775808.0}',
@@ -468,6 +471,52 @@ class SchemagenIntegerBoundaryTest(unittest.TestCase):
         with tempfile.TemporaryDirectory() as tmpdir:
             self._compile_harness(tmpdir, schema, harness)
 
+    def test_integer_no_quadratic_leading_zero_loop(self):
+        """Regression test for issue #34: leading-zero stripping must not be quadratic."""
+        with tempfile.TemporaryDirectory() as tmpdir:
+            schema_path = os.path.join(tmpdir, "schema.json")
+            with open(schema_path, "w") as fp:
+                json.dump({"type": "integer"}, fp)
+            result = subprocess.run(
+                [sys.executable, SCRIPT, schema_path],
+                capture_output=True,
+                text=True,
+                check=False,
+            )
+            self.assertEqual(result.returncode, 0, msg=result.stderr)
+            self.assertIn("parseJsonInt64", result.stdout)
+            self.assertNotIn("digits.erase(digits.begin())", result.stdout)
+
+    def test_integer_large_fractional_leading_zeros(self):
+        """Numbers with many leading fractional zeros must parse correctly."""
+        if not self.compiler:
+            self.skipTest("C++ compiler not available")
+        harness = textwrap.dedent(
+            """
+            #include "gen.h"
+            #include <cstdio>
+            #include <string>
+            int main() {
+              const int n = 100000;
+              std::string s = std::string("0.") + std::string(n - 1, '0') + "1e" + std::to_string(n);
+              test_schema::RootBuilder b;
+              WeaselJsonStatus st = b.feed(s.data(), static_cast<int>(s.size()));
+              st = b.finish();
+              if (st != WeaselJson_OK) {
+                std::printf("expected OK, got %d\\n", st);
+                return 1;
+              }
+              if (b.take() != 1) {
+                std::printf("expected value 1\\n");
+                return 2;
+              }
+              return 0;
+            }
+            """
+        )
+        with tempfile.TemporaryDirectory() as tmpdir:
+            self._compile_harness(tmpdir, {"type": "integer"}, harness)
+
 
 if __name__ == "__main__":
     unittest.main()
diff --git a/contrib/schemagen/weaseljson_schemagen.py b/contrib/schemagen/weaseljson_schemagen.py
index b70a51c..c64e514 100644
--- a/contrib/schemagen/weaseljson_schemagen.py
+++ b/contrib/schemagen/weaseljson_schemagen.py
@@ -1000,8 +1000,10 @@ private:
     }}
     int64_t finalExp = exp - fracDigits + trim;
     if (finalExp < 0) return false;
-    while (!digits.empty() && digits.front() == '0') digits.erase(digits.begin());
-    if (digits.empty()) {{ out = 0; return true; }}
+    size_t leadingZeros = 0;
+    while (leadingZeros < digits.size() && digits[leadingZeros] == '0') ++leadingZeros;
+    if (leadingZeros == digits.size()) {{ out = 0; return true; }}
+    if (leadingZeros > 0) digits.erase(0, leadingZeros);
 
     constexpr uint64_t kMaxNeg = 9223372036854775808ULL;
     constexpr uint64_t kMaxPos = 9223372036854775807ULL;