# Phase 7 Task 7.8 - Regression-guard tests for audit heuristic.
# Per Phase 7 spec 22.5.5 (FR5):
# - BOUNDARY_FASTAPI classification requires ast.Raise(exc=HTTPException)
#   OR a return of Result(...) in the except body.
# - Otherwise re-classify as INTERNAL_SILENT_SWALLOW (logging body) or
#   INTERNAL_COMPLIANT (try/finally cleanup).
import ast
import sys
from pathlib import Path

import pytest

ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(ROOT / "scripts"))

from audit_exception_handling import (  # noqa: E402
    ExceptionVisitor,
    audit_file,
)


def _make_visitor(source: str, func_name: str):
    """Create an ExceptionVisitor positioned inside the named function."""
    tree = ast.parse(source)
    visitor = ExceptionVisitor(str(ROOT / "src" / "_test_dummy.py"))
    for node in ast.walk(tree):
        if isinstance(node, ast.FunctionDef) and node.name == func_name:
            visitor._func_stack = [node]
            return visitor
    raise ValueError(f"Function {func_name} not found in source")


def _find_handler(visitor):
    """Find the first Try node in the function body."""
    for node in visitor._func_stack[0].body:
        if isinstance(node, ast.Try):
            return node
    raise AssertionError("expected a try/except in function")


def test_is_api_handler_requires_http_exception_in_body():
    # OLD STYLE: only stderr.write (should NOT be BOUNDARY_FASTAPI after Phase 7)
    src = (
        "def _api_generate(controller):\n"
        " HTTPException = None\n"
        " try:\n"
        "  do_something()\n"
        " except Exception as e:\n"
        "  sys.stderr.write('err: ' + str(e))\n"
        "  sys.stderr.flush()\n"
    )
    visitor = _make_visitor(src, "_api_generate")
    handler = _find_handler(visitor).handlers[0]
    category, _ = visitor._classify_except(handler, _find_handler(visitor))
    assert category != "BOUNDARY_FASTAPI", (
        f"Phase 7 FR5 tightening failed: stale body (only stderr.write) "
        f"should NOT be BOUNDARY_FASTAPI; got {category}."
    )


def test_api_handler_with_http_exception_raise_is_boundary_fastapi():
    # NEW STYLE: raises HTTPException (the canonical FastAPI pattern)
    src = (
        "def _api_generate(controller):\n"
        " HTTPException = None\n"
        " try:\n"
        "  do_something()\n"
        " except Exception as e:\n"
        "  raise HTTPException(status_code=500, detail=str(e))\n"
    )
    visitor = _make_visitor(src, "_api_generate")
    try_node = _find_handler(visitor)
    handler = try_node.handlers[0]
    category, _ = visitor._classify_except(handler, try_node)
    assert category == "BOUNDARY_FASTAPI", (
        f"Phase 7 FR5 regression: handler with HTTPException raise should be "
        f"BOUNDARY_FASTAPI; got {category}."
    )


def test_non_api_handler_with_logging_is_still_internal_compliant():
    # Non-_api_* function with logging-only except body
    src = (
        "def regular_handler():\n"
        " try:\n"
        "  do_something()\n"
        " except Exception as e:\n"
        "  logging.getLogger('x').debug('err: %s', e)\n"
        "  print('err: ' + str(e))\n"
    )
    visitor = _make_visitor(src, "regular_handler")
    try_node = _find_handler(visitor)
    handler = try_node.handlers[0]
    category, _ = visitor._classify_except(handler, try_node)
    assert category in ("INTERNAL_COMPLIANT", "INTERNAL_SILENT_SWALLOW", "INTERNAL_BROAD_CATCH"), (
        f"Non-api handler should NOT be BOUNDARY_FASTAPI; got {category}."
    )


def test_15_existing_fastapi_sites_remain_classified():
    # The 13 BOUNDARY_FASTAPI sites in src/app_controller.py must remain
    # classified after the heuristic tightening (Phase 7 FR5).
    # Note: src/api_hooks.py functions do NOT have _api_ prefix, so they
    # were never classified BOUNDARY_FASTAPI; the 13 sites are all in
    # _api_* handlers in app_controller.py.
    app_controller_path = ROOT / "src" / "app_controller.py"
    if not app_controller_path.exists():
        pytest.skip(f"{app_controller_path} not found")
    report = audit_file(app_controller_path)
    fastapi_sites = [f for f in report.findings if f.category == "BOUNDARY_FASTAPI"]
    assert len(fastapi_sites) >= 10, (
        f"Phase 7 regression: expected at least 10 BOUNDARY_FASTAPI sites in "
        f"src/app_controller.py, got {len(fastapi_sites)}. The known sites "
        f"must remain classified after heuristic tightening."
    )
    src = app_controller_path.read_text(encoding="utf-8")
    for site in fastapi_sites[:3]:
        lines = src.split("\n")
        line_num = site.line
        window = "\n".join(lines[max(0, line_num - 5):line_num + 5])
        assert "HTTPException" in window or "Result[" in window, (
            f"Phase 7 regression: site at app_controller.py:{line_num} "
            f"classified BOUNDARY_FASTAPI but window doesn't contain "
            f"HTTPException or Result["
        )


def test_phase7_migrated_sites_no_longer_silent_swallow():
    # L242/L256/L5064/L5093 must not be INTERNAL_SILENT_SWALLOW after Phase 7.
    app_controller_path = ROOT / "src" / "app_controller.py"
    if not app_controller_path.exists():
        pytest.skip(f"{app_controller_path} not found")
    report = audit_file(app_controller_path)
    for f in report.findings:
        if f.line in (242, 256, 5064, 5093):
            assert f.category != "INTERNAL_SILENT_SWALLOW", (
                f"Phase 7 regression: L{f.line} should not be "
                f"INTERNAL_SILENT_SWALLOW after migration; got {f.category}"
            )


# Phase 11 Task 11.4 - Regression-guard tests for dunder-method bare-raise heuristic.
# Per Phase 11 spec (INTERNAL_RETHROW classification for dunder methods):
# - Bare `raise AttributeError(name)` / `raise NameError(name)` in
#   `__getattr__`, `__getattribute__`, `__setattr__`, `__delattr__` is the
#   canonical dunder-method programmer-error pattern (per styleguide
#   "Re-Raise Patterns": bare raises are reserved for programmer errors).
# - The audit previously classified these as INTERNAL_RETHROW (suspicious);
#   the heuristic must reclassify them as INTERNAL_PROGRAMMER_RAISE.

DUNDER_RAISE_TESTS = {
 "__getattr__": "def __getattr__(self, name):\n if name == 'controller':\n  raise AttributeError(name)\n raise AttributeError(name)",
 "__getattribute__": "def __getattribute__(self, name):\n if name == 'controller':\n  raise AttributeError(name)\n raise AttributeError(name)",
 "__setattr__": "def __setattr__(self, name, value):\n raise AttributeError(name)",
 "__delattr__": "def __delattr__(self, name):\n raise AttributeError(name)",
}


def _classify_first_raise(source, func_name):
 tree = ast.parse(source)
 for node in ast.walk(tree):
  if isinstance(node, ast.FunctionDef) and node.name == func_name:
   visitor = ExceptionVisitor(str(ROOT / "src" / "_test_dummy.py"))
   visitor._func_stack = [node]
   for sub in ast.walk(node):
    if isinstance(sub, ast.Raise) and sub.exc is not None:
     return visitor._classify_raise(sub)
 raise AssertionError(f"No raise found in {func_name}")


def test_bare_raise_attribute_error_in_getattr_is_programmer_raise():
 src = DUNDER_RAISE_TESTS["__getattr__"]
 category, hint = _classify_first_raise(src, "__getattr__")
 assert category == "INTERNAL_PROGRAMMER_RAISE", (
  f"Phase 11 regression: bare `raise AttributeError(name)` in __getattr__ "
  f"should be INTERNAL_PROGRAMMER_RAISE (canonical dunder-method pattern); "
  f"got {category}. Hint: {hint}"
 )


def test_bare_raise_name_error_in_getattr_is_programmer_raise():
 src = (
  "def __getattr__(self, name):\n"
  " if not hasattr(self, 'x'):\n"
  "  raise NameError(name)\n"
  " return self.x"
 )
 category, hint = _classify_first_raise(src, "__getattr__")
 assert category == "INTERNAL_PROGRAMMER_RAISE", (
  f"Phase 11 regression: bare `raise NameError(name)` in __getattr__ "
  f"should be INTERNAL_PROGRAMMER_RAISE (canonical dunder-method pattern); "
  f"got {category}. Hint: {hint}"
 )


def test_bare_raise_in_setattr_is_programmer_raise():
 src = DUNDER_RAISE_TESTS["__setattr__"]
 category, hint = _classify_first_raise(src, "__setattr__")
 assert category == "INTERNAL_PROGRAMMER_RAISE", (
  f"Phase 11 regression: bare `raise AttributeError` in __setattr__ "
  f"should be INTERNAL_PROGRAMMER_RAISE (canonical dunder-method pattern); "
  f"got {category}. Hint: {hint}"
 )


def test_bare_raise_in_delattr_is_programmer_raise():
 src = DUNDER_RAISE_TESTS["__delattr__"]
 category, hint = _classify_first_raise(src, "__delattr__")
 assert category == "INTERNAL_PROGRAMMER_RAISE", (
  f"Phase 11 regression: bare `raise AttributeError` in __delattr__ "
  f"should be INTERNAL_PROGRAMMER_RAISE (canonical dunder-method pattern); "
  f"got {category}. Hint: {hint}"
 )


def test_bare_raise_in_getattribute_is_programmer_raise():
 src = DUNDER_RAISE_TESTS["__getattribute__"]
 category, hint = _classify_first_raise(src, "__getattribute__")
 assert category == "INTERNAL_PROGRAMMER_RAISE", (
  f"Phase 11 regression: bare `raise AttributeError(name)` in __getattribute__ "
  f"should be INTERNAL_PROGRAMMER_RAISE (canonical dunder-method pattern); "
  f"got {category}. Hint: {hint}"
 )


# Phase 12 Task 12.1 - Regression-guard tests for the lazy-loading sentinel
# fallback heuristic.
# Per Phase 12 spec (INTERNAL_COMPLIANT classification for lazy-loading
# sentinel fallbacks in methods named _resolve/_load/_get/_try_load):
# - The except body must NOT re-raise
# - The except body must assign to a self.<attr> (directly or via nested try)
# - The except set must be in {AttributeError, ImportError, ModuleNotFoundError}
# - The enclosing function name must be in the lazy-loader set
# Pre-Phase 12 baseline: 2 UNCLEAR sites in src/gui_2.py at L65, L69
# (both in _LazyModule._resolve). Post-Phase 12: 0 UNCLEAR.

def test_lazy_loading_sentinel_fallback_in_resolve_is_compliant():
 src = (
  "def _resolve(self):\n"
  " try:\n"
  "  self._cached = getattr(self._mod, self._attr_name)\n"
  " except AttributeError:\n"
  "  try:\n"
  "   self._cached = _importlib.import_module(self._sub_name)\n"
  "  except (ImportError, ModuleNotFoundError):\n"
  "   self._cached = _FiledialogStub()\n"
  " return self._cached\n"
 )
 visitor = _make_visitor(src, "_resolve")
 try_node = _find_handler(visitor)
 handler = try_node.handlers[0]
 category, hint = visitor._classify_except(handler, try_node)
 assert category == "INTERNAL_COMPLIANT", (
  f"Phase 12 regression: lazy-loading sentinel fallback in `_resolve` "
  f"(L65-style nested try with `self._cached = _FiledialogStub()`) "
  f"should be INTERNAL_COMPLIANT (canonical graceful-degradation pattern); "
  f"got {category}. Hint: {hint}"
 )


def test_lazy_loading_sentinel_fallback_in_load_is_compliant():
 src = (
  "def _load(self, name):\n"
  " try:\n"
  "  self._cached = _importlib.import_module(name)\n"
  " except (ImportError, ModuleNotFoundError):\n"
  "  self._cached = _FooStub()\n"
  " return self._cached\n"
 )
 visitor = _make_visitor(src, "_load")
 try_node = _find_handler(visitor)
 handler = try_node.handlers[0]
 category, hint = visitor._classify_except(handler, try_node)
 assert category == "INTERNAL_COMPLIANT", (
  f"Phase 12 regression: lazy-loading sentinel fallback in `_load` "
  f"(direct `self._cached = _FooStub()`) should be INTERNAL_COMPLIANT "
  f"(canonical graceful-degradation pattern); got {category}. Hint: {hint}"
 )


def test_lazy_loading_sentinel_fallback_in_get_is_compliant():
 src = (
  "def _get(self, attr_name):\n"
  " try:\n"
  "  return getattr(self._module, attr_name)\n"
  " except AttributeError:\n"
  "  self._cached = _BarStub()\n"
  "  return self._cached\n"
 )
 visitor = _make_visitor(src, "_get")
 try_node = _find_handler(visitor)
 handler = try_node.handlers[0]
 category, hint = visitor._classify_except(handler, try_node)
 assert category == "INTERNAL_COMPLIANT", (
  f"Phase 12 regression: lazy-loading sentinel fallback in `_get` "
  f"(direct `self._cached = _BarStub()`) should be INTERNAL_COMPLIANT "
  f"(canonical graceful-degradation pattern); got {category}. Hint: {hint}"
 )


# ============ Phase 9 redo: Heuristic E regression tests (TIER1_REVIEW) ============

def test_heuristic_e_narrow_return_errorinfo_is_compliant():
 """Phase 9 redo: narrow except + return ErrorInfo(...) is a true drain.

 Per TIER1_REVIEW_phase9_dilemma_20260620: a narrow except body that
 returns a structured ErrorInfo carries the original exception and is
 the function's contract. This is NOT sliming (the error context is
 preserved in `original=e`).
 """
 src = (
  "def _classify_anthropic_error(exc, source):\n"
  " try:\n"
  "  err_data = exc.response.json()\n"
  " except (ValueError, AttributeError) as e:\n"
  "  return ErrorInfo(kind=ErrorKind.UNKNOWN, message=str(e), source=source, original=e)\n"
 )
 visitor = _make_visitor(src, "_classify_anthropic_error")
 try_node = _find_handler(visitor)
 handler = try_node.handlers[0]
 category, hint = visitor._classify_except(handler, try_node)
 assert category in ("INTERNAL_COMPLIANT", "BOUNDARY_CONVERSION"), (
  f"Heuristic E regression: narrow except + return ErrorInfo(...) "
  f"should be a compliant classification (INTERNAL_COMPLIANT via Heuristic E "
  f"or BOUNDARY_CONVERSION via existing creates_errorinfo check); got {category}. Hint: {hint}"
 )


def test_heuristic_e_narrow_dict_error_true_assign_is_compliant():
 """Phase 9 redo: narrow except + dict[error] = True is a true drain (in-band flag).

 Per TIER1_REVIEW: `except (NarrowType) as e: item["error"] = True`
 is a structured error carrier. The caller is expected to inspect the
 `error` flag (per-site decision documented in track notes; the audit
 does NOT verify caller reads the flag).
 """
 src = (
  "def _reread_file_items(file_items):\n"
  " try:\n"
  "  content = p.read_text()\n"
  "  new_item = {**item, 'content': content}\n"
  " except (OSError, UnicodeDecodeError) as e:\n"
  "  err_item = {**item, 'content': f'ERROR: {e}'}\n"
  "  err_item['error'] = True\n"
  "  refreshed.append(err_item)\n"
 )
 visitor = _make_visitor(src, "_reread_file_items")
 try_node = _find_handler(visitor)
 handler = try_node.handlers[0]
 category, hint = visitor._classify_except(handler, try_node)
 assert category == "INTERNAL_COMPLIANT", (
  f"Heuristic E regression: narrow except + dict['error'] = True "
  f"should be INTERNAL_COMPLIANT (in-band error flag carrier); got {category}. Hint: {hint}"
 )


def test_heuristic_e_empty_default_args_is_NOT_compliant():
 """Phase 9 redo: narrow except + args = {} is NOT a drain (sliming).

 Per TIER1_REVIEW: the empty-default pattern loses error context. The
 caller cannot distinguish success from failure. Heuristic E
 explicitly does NOT match this pattern (this test is a regression
 guard against future "helpful" heuristic additions that would
 laundering this sliming pattern).

 Structure: extract into a helper function so the try is at the top
 level of the function body (required by _find_handler test helper).
 """
 src = (
  "def _parse_tool_args(tool_args_str):\n"
  " try:\n"
  "  args = json.loads(tool_args_str)\n"
  " except (ValueError, TypeError):\n"
  "  args = {}\n"
  " return args\n"
 )
 visitor = _make_visitor(src, "_parse_tool_args")
 try_node = _find_handler(visitor)
 handler = try_node.handlers[0]
 category, hint = visitor._classify_except(handler, try_node)
 # The site is narrow + non-broad but the body is empty-default.
 # Heuristic E should NOT classify as COMPLIANT. May be INTERNAL_BROAD_CATCH
 # (no drain) or UNCLEAR. NOT INTERNAL_COMPLIANT or BOUNDARY_CONVERSION.
 assert category not in ("INTERNAL_COMPLIANT", "BOUNDARY_CONVERSION"), (
  f"Heuristic E regression: narrow except + args = {{}} (empty default) "
  f"must NOT be classified as compliant (INTERNAL_COMPLIANT or BOUNDARY_CONVERSION "
  f"would be sliming per TIER1_REVIEW). Got {category} which would laundering the pattern. Hint: {hint}"
 )