feat(categorizer): implement auto_classify using AST scan (no regex)

tests/categorizer.py

@@ -1,5 +1,7 @@
+import ast
 from dataclasses import dataclass, field
 from enum import Enum
+from pathlib import Path
 
 class FixtureClass(str, Enum):
  UNIT = "unit"
@@ -26,3 +28,50 @@ class CategoryRecord:
  test_order: dict[str, int] = field(default_factory=dict)
  source: str = "auto"
  warnings: list[str] = field(default_factory=list)
+
+_OPT_IN_PREFIXES: tuple[str, ...] = ("test_clean_install", "test_docker_build")
+_PERF_KEYWORDS: tuple[str, ...] = ("perf", "stress", "phase_3_final", "phase_4_stress")
+_FIXTURE_ARGS: dict[FixtureClass, frozenset[str]] = {
+ FixtureClass.LIVE_GUI: frozenset({"live_gui"}),
+ FixtureClass.MOCK_APP: frozenset({"mock_app", "app_instance"}),
+}
+
+def _fixture_args_used(source: str) -> set[str]:
+ try:
+  tree = ast.parse(source)
+ except SyntaxError:
+  return set()
+ found: set[str] = set()
+ for node in ast.walk(tree):
+  if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
+   found.update(a.arg for a in node.args.args)
+   found.update(a.arg for a in node.args.kwonlyargs)
+   found.update(a.arg for a in node.args.posonlyargs)
+ return found
+
+def _classify_fixture_class(path: Path, source: str) -> FixtureClass:
+ name = path.name
+ for prefix in _OPT_IN_PREFIXES:
+  if name.startswith(prefix):
+   return FixtureClass.OPT_IN
+ args = _fixture_args_used(source)
+ for fc, fixture_names in _FIXTURE_ARGS.items():
+  if args & fixture_names:
+   return fc
+ lowered = name.lower()
+ for kw in _PERF_KEYWORDS:
+  if kw in lowered:
+   return FixtureClass.PERFORMANCE
+ return FixtureClass.UNIT
+
+def auto_classify(path: Path, durations: dict[str, float] | None = None) -> CategoryRecord:
+ source = path.read_text(encoding="utf-8", errors="replace")
+ fixture_class = _classify_fixture_class(path, source)
+ return CategoryRecord(
+  filename=path.name,
+  fixture_class=fixture_class,
+  subsystems=[],
+  speed=Speed.MEDIUM,
+  batch_group="",
+  source="auto",
+ )