weaseljson/contrib/schemagen/test_schemagen.py

#!/usr/bin/env python3
"""Tests for weaseljson_schemagen.py."""

import json
import os
import re
import shutil
import subprocess
import sys
import tempfile
import textwrap
import unittest

SCRIPT = os.path.join(os.path.dirname(__file__), "weaseljson_schemagen.py")


class SchemagenEnumTest(unittest.TestCase):
    def run_schemagen(self, schema, args=None):
        """Run schemagen on a schema dict. Returns (returncode, stdout, stderr)."""
        with tempfile.NamedTemporaryFile("w", suffix=".json", delete=False) as fp:
            json.dump(schema, fp)
            schema_path = fp.name
        try:
            cmd = [sys.executable, SCRIPT, schema_path]
            if args:
                cmd.extend(args)
            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
            return result.returncode, result.stdout, result.stderr
        finally:
            os.unlink(schema_path)

    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)
        self.assertEqual(rc, 0, msg=stderr)
        self.assertIn("enum class Role : int { foo_bar, foo_bar_1 };", stdout)
        self.assertIn(
            'static constexpr const char *Role_names[] = { "foo-bar", "foo_bar" };',
            stdout,
        )

    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)
        self.assertEqual(rc, 0, msg=stderr)
        self.assertIn("enum class Role : int { admin, user, guest };", stdout)


class SchemagenKeywordTest(unittest.TestCase):
    def run_schemagen(self, schema, args=None):
        """Run schemagen on a schema dict. Returns (returncode, stdout, stderr)."""
        with tempfile.NamedTemporaryFile("w", suffix=".json", delete=False) as fp:
            json.dump(schema, fp)
            schema_path = fp.name
        try:
            cmd = [sys.executable, SCRIPT, schema_path]
            if args:
                cmd.extend(args)
            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
            return result.returncode, result.stdout, result.stderr
        finally:
            os.unlink(schema_path)

    def test_cpp20_keywords_are_sanitized(self):
        """C++20 keywords used as JSON property names must be suffixed."""
        keywords = [
            "concept",
            "consteval",
            "constinit",
            "co_await",
            "co_return",
            "co_yield",
            "requires",
            "module",
            "import",
        ]
        schema = {"type": "object", "additionalProperties": False, "properties": {}}
        for kw in keywords:
            schema["properties"][kw] = {"type": "string"}
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertEqual(rc, 0, msg=stderr)
        for kw in keywords:
            self.assertIn(f"std::optional<std::string> {kw}_;", stdout)
            self.assertNotIn(f"std::optional<std::string> {kw};", stdout)


class SchemagenCollisionTest(unittest.TestCase):
    """Regression tests for issue #21: generated Root alias / Kind enum collisions."""

    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.compiler = shutil.which("c++")

    def generate_and_compile(self, schema):
        """Run schemagen on schema and syntax-check the resulting header."""
        with tempfile.TemporaryDirectory() as tmpdir:
            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")
            cmd = [
                sys.executable,
                SCRIPT,
                schema_path,
                "-o",
                header_path,
                "--namespace",
                "test_schema",
            ]
            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
            self.assertEqual(result.returncode, 0, msg=result.stderr)

            if self.compiler:
                cpp_path = os.path.join(tmpdir, "test.cpp")
                with open(cpp_path, "w") as fp:
                    fp.write(
                        '#include "gen.h"\n'
                        "int main() {\n"
                        "  test_schema::RootBuilder b;\n"
                        "  test_schema::Root r = b.take();\n"
                        "  (void)r;\n"
                        "}\n"
                    )
                comp = subprocess.run(
                    [
                        self.compiler,
                        "-std=c++20",
                        "-fsyntax-only",
                        "-I",
                        self.include_dir,
                        "-I",
                        tmpdir,
                        cpp_path,
                    ],
                    capture_output=True,
                    text=True,
                    check=False,
                )
                self.assertEqual(comp.returncode, 0, msg=comp.stderr)

            with open(header_path) as fp:
                return fp.read()

    def test_root_alias_does_not_collide_with_user_type(self):
        schema = {
            "type": "array",
            "items": {"$ref": "#/$defs/Root"},
            "$defs": {"Root": {"enum": ["a", "b"]}},
        }
        out = self.generate_and_compile(schema)
        self.assertIn("enum class Root1 : int { a, b };", out)
        self.assertIn("using Root = std::vector<Root1>;", out)
        self.assertNotIn("using Root = std::vector<Root>;", out)

    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",
                    "additionalProperties": False,
                    "properties": {},
                }
            },
        }
        out = self.generate_and_compile(schema)
        self.assertIn("struct Arr0", out)
        m = re.search(r"enum class Kind : uint8_t \{([^}]+)\}", out)
        self.assertIsNotNone(m)
        enumerators = [e.strip() for e in m.group(1).split(",")]
        self.assertIn("Arr0", enumerators)
        self.assertIn("Arr1", enumerators)
        self.assertEqual(len(enumerators), len(set(enumerators)))

    def test_skip_user_type_is_allowed(self):
        schema = {
            "type": "array",
            "items": {"$ref": "#/$defs/Skip"},
            "$defs": {
                "Skip": {
                    "type": "object",
                    "additionalProperties": False,
                    "properties": {},
                }
            },
        }
        out = self.generate_and_compile(schema)
        self.assertIn("struct Skip", out)
        self.assertNotIn("struct Skip1", out)
        m = re.search(r"enum class Kind : uint8_t \{([^}]+)\}", out)
        self.assertIsNotNone(m)
        enumerators = [e.strip() for e in m.group(1).split(",")]
        self.assertIn("Skip", enumerators)
        self.assertIn("Arr0", enumerators)
        self.assertEqual(len(enumerators), len(set(enumerators)))

    def test_non_object_defs_reused_across_refs(self):
        """Regression test for issue #17: enum and array $defs must be reused."""
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {
                "role1": {"$ref": "#/$defs/Role"},
                "role2": {"$ref": "#/$defs/Role"},
                "roles1": {"$ref": "#/$defs/Roles"},
                "roles2": {"$ref": "#/$defs/Roles"},
            },
            "$defs": {
                "Role": {"enum": ["admin", "user"]},
                "Roles": {"type": "array", "items": {"$ref": "#/$defs/Role"}},
            },
        }
        out = self.generate_and_compile(schema)
        # Exactly one Role enum is generated.
        self.assertIn("enum class Role : int { admin, user };", out)
        self.assertNotIn("enum class Role1 : int", out)
        self.assertNotIn("enum class Role2 : int", out)
        # The array of enum is represented by a single kind.
        m = re.search(r"enum class Kind : uint8_t \{([^}]+)\}", out)
        self.assertIsNotNone(m)
        enumerators = [e.strip() for e in m.group(1).split(",")]
        self.assertEqual(enumerators.count("Arr0"), 1)
        # All four fields use the same C++ types.
        self.assertIn("std::optional<Role> role1;", out)
        self.assertIn("std::optional<Role> role2;", out)
        self.assertIn("std::optional<std::vector<Role>> roles1;", out)
        self.assertIn("std::optional<std::vector<Role>> roles2;", out)


class SchemagenAdditionalPropertiesTest(unittest.TestCase):
    def run_schemagen(self, schema, args=None):
        """Run schemagen on a schema dict. Returns (returncode, stdout, stderr)."""
        with tempfile.NamedTemporaryFile("w", suffix=".json", delete=False) as fp:
            json.dump(schema, fp)
            schema_path = fp.name
        try:
            cmd = [sys.executable, SCRIPT, schema_path]
            if args:
                cmd.extend(args)
            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
            return result.returncode, result.stdout, result.stderr
        finally:
            os.unlink(schema_path)

    def test_additional_properties_true_rejected(self):
        schema = {
            "type": "object",
            "additionalProperties": True,
            "properties": {"name": {"type": "string"}},
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertNotEqual(rc, 0)
        self.assertIn("additionalProperties: true is not supported", stderr)

    def test_additional_properties_absent_rejected(self):
        schema = {
            "type": "object",
            "properties": {"name": {"type": "string"}},
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertNotEqual(rc, 0)
        self.assertIn("additionalProperties is required for object schemas", stderr)

    def test_additional_properties_false_accepted(self):
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {"name": {"type": "string"}},
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertEqual(rc, 0, msg=stderr)


class SchemagenCyclicArrayTest(unittest.TestCase):
    """Regression tests for issue #33: cyclic array $ref targets."""

    def run_schemagen(self, schema, args=None):
        """Run schemagen on a schema dict. Returns (returncode, stdout, stderr)."""
        with tempfile.NamedTemporaryFile("w", suffix=".json", delete=False) as fp:
            json.dump(schema, fp)
            schema_path = fp.name
        try:
            cmd = [sys.executable, SCRIPT, schema_path]
            if args:
                cmd.extend(args)
            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
            return result.returncode, result.stdout, result.stderr
        finally:
            os.unlink(schema_path)

    def test_direct_self_referential_array_rejected(self):
        schema = {
            "type": "array",
            "items": {"$ref": "#/$defs/Node"},
            "$defs": {
                "Node": {
                    "type": "array",
                    "items": {"$ref": "#/$defs/Node"},
                }
            },
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertNotEqual(rc, 0)
        self.assertIn("recursive array type is not supported", stderr)
        self.assertIn("Node", stderr)

    def test_object_field_to_self_referential_array_rejected(self):
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {"items": {"$ref": "#/$defs/Items"}},
            "$defs": {
                "Items": {
                    "type": "array",
                    "items": {"$ref": "#/$defs/Items"},
                }
            },
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertNotEqual(rc, 0)
        self.assertIn("recursive array type is not supported", stderr)
        self.assertIn("Items", stderr)

    def test_chain_of_array_refs_rejected(self):
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {"x": {"$ref": "#/$defs/A"}},
            "$defs": {
                "A": {"type": "array", "items": {"$ref": "#/$defs/B"}},
                "B": {"type": "array", "items": {"$ref": "#/$defs/A"}},
            },
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertNotEqual(rc, 0)
        self.assertIn("recursive array type is not supported", stderr)

    def test_non_recursive_array_refs_still_allowed(self):
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {"roles": {"$ref": "#/$defs/Roles"}},
            "$defs": {
                "Role": {"enum": ["admin", "user"]},
                "Roles": {
                    "type": "array",
                    "items": {"$ref": "#/$defs/Role"},
                },
            },
        }
        rc, stdout, stderr = self.run_schemagen(schema)
        self.assertEqual(rc, 0, msg=stderr)
        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 $refs."""
        if not self.compiler:
            self.skipTest("C++ compiler not available")
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {"self": {"$ref": "#/$defs/Self"}},
            "$defs": {
                "Self": {
                    "type": ["object", "null"],
                    "additionalProperties": False,
                    "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."""

    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 _build_cases_array(self, name, entries):
        lines = [
            f"  struct {name}Case {{ const char *s; WeaselJsonStatus expected; long long v; }};"
        ]
        lines.append(f"  {name}Case {name}_cases[] = {{")
        for s, exp, v in entries:
            val = f"{v}LL" if isinstance(v, int) else v
            lines.append(f'    {{ R"({s})", {exp}, {val} }},')
        lines.append("  };")
        return "\n".join(lines)

    def test_integer_boundary_root(self):
        if not self.compiler:
            self.skipTest("C++ compiler not available")
        cases = [
            ("9223372036854775807.0", "WeaselJson_OK", 9223372036854775807),
            ("9223372036854775807", "WeaselJson_OK", 9223372036854775807),
            ("9223372036854775806.0", "WeaselJson_OK", 9223372036854775806),
            ("9223372036854775808", "WeaselJson_REJECT", 0),
            ("-9223372036854775808", "WeaselJson_OK", "-9223372036854775807LL - 1"),
            ("-9223372036854775808.0", "WeaselJson_OK", "-9223372036854775807LL - 1"),
            ("-9223372036854775809", "WeaselJson_REJECT", 0),
            ("1e3", "WeaselJson_OK", 1000),
            ("2.0", "WeaselJson_OK", 2),
            ("0.001", "WeaselJson_REJECT", 0),
            ("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),
            # 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(
            f"""
            #include "gen.h"
            #include <cstdio>
            #include <cstring>
            {cases_src}
            int main() {{
              for (const auto \u0026c : root_cases) {{
                test_schema::RootBuilder b;
                char buf[512];
                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("root case %s expected %d got %d\\n", c.s, c.expected, st);
                  return 1;
                }}
                if (st == WeaselJson_OK \u0026\u0026 b.take() != c.v) {{
                  std::printf("root case %s value mismatch\\n", c.s);
                  return 2;
                }}
              }}
              return 0;
            }}
            """
        )
        with tempfile.TemporaryDirectory() as tmpdir:
            self._compile_harness(tmpdir, {"type": "integer"}, harness)

    def test_integer_boundary_object_field(self):
        if not self.compiler:
            self.skipTest("C++ compiler not available")
        cases = [
            ('{"age":9223372036854775807.0}', "WeaselJson_OK", 9223372036854775807),
            ('{"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),
            # 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",
                "-9223372036854775807LL - 1",
            ),
        ]
        cases_src = self._build_cases_array("object", cases)
        harness = textwrap.dedent(
            f"""
            #include "gen.h"
            #include <cstdio>
            #include <cstring>
            {cases_src}
            int main() {{
              for (const auto \u0026c : object_cases) {{
                test_schema::RootBuilder b;
                char buf[512];
                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("object case %s expected %d got %d\\n", c.s, c.expected, st);
                  return 3;
                }}
                if (st == WeaselJson_OK \u0026\u0026 b.take().age != c.v) {{
                  std::printf("object case %s value mismatch\\n", c.s);
                  return 4;
                }}
              }}
              return 0;
            }}
            """
        )
        schema = {
            "type": "object",
            "additionalProperties": False,
            "properties": {"age": {"type": "integer"}},
            "required": ["age"],
        }
        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)


class SchemagenStringEscapeTest(unittest.TestCase):
    """Regression tests for issue #35: control characters in string literals."""

    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.compiler = shutil.which("c++")

    def generate_and_compile(self, schema):
        """Run schemagen on schema and syntax-check the resulting header."""
        with tempfile.TemporaryDirectory() as tmpdir:
            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")
            cmd = [
                sys.executable,
                SCRIPT,
                schema_path,
                "-o",
                header_path,
                "--namespace",
                "test_schema",
            ]
            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
            self.assertEqual(result.returncode, 0, msg=result.stderr)

            if self.compiler:
                cpp_path = os.path.join(tmpdir, "test.cpp")
                with open(cpp_path, "w") as fp:
                    fp.write(
                        '#include "gen.h"\n'
                        "int main() {\n"
                        "  test_schema::RootBuilder b;\n"
                        "  test_schema::Root r = b.take();\n"
                        "  (void)r;\n"
                        "}\n"
                    )
                comp = subprocess.run(
                    [
                        self.compiler,
                        "-std=c++20",
                        "-fsyntax-only",
                        "-I",
                        self.include_dir,
                        "-I",
                        tmpdir,
                        cpp_path,
                    ],
                    capture_output=True,
                    text=True,
                    check=False,
                )
                self.assertEqual(comp.returncode, 0, msg=comp.stderr)

            with open(header_path) as fp:
                return fp.read()

    def test_newline_in_property_key(self):
        """A JSON key containing a newline must become a valid C++ literal."""
        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",
            "additionalProperties": False,
            "properties": {"x": {"enum": ["a\nb"]}},
        }
        out = self.generate_and_compile(schema)
        self.assertIn('static constexpr const char *X_names[] = { "a\\nb" };', out)

    def test_mixed_control_chars_in_enum_value(self):
        """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"]},
            },
        }
        out = self.generate_and_compile(schema)
        self.assertIn(
            'static constexpr const char *X_names[] = { "x\\ny\\rz\\tw\\vq\\u0000\\u0001" };',
            out,
        )

    def test_backslash_and_quote_still_escaped(self):
        """Existing escaping for backslash and double quote must remain correct."""
        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)


if __name__ == "__main__":
    unittest.main()