feat(categorizer): implement load_registry, merge_registry, categorize_all

tests/categorizer.py

@@ -1,4 +1,5 @@
 import ast
+import tomllib
 from dataclasses import dataclass, field
 from enum import Enum
 from pathlib import Path
@@ -141,3 +142,40 @@ def auto_classify(path: Path, durations: dict[str, float] | None = None) -> Cate
   batch_group=batch_group,
   source="auto",
  )
+
+def load_registry(toml_path: Path) -> dict[str, dict]:
+ if not toml_path.exists():
+  return {}
+ with toml_path.open("rb") as f:
+  data = tomllib.load(f)
+ return data.get("files", {})
+
+def merge_registry(auto: CategoryRecord, entry: dict) -> CategoryRecord:
+ warnings = list(auto.warnings)
+ if "fixture_class" in entry and entry["fixture_class"] != auto.fixture_class.value:
+  warnings.append(f"fixture_class-override: {auto.fixture_class.value} -> {entry['fixture_class']}")
+ if "subsystems" in entry and set(entry["subsystems"]) != set(auto.subsystems):
+  warnings.append(f"subsystems-override: {auto.subsystems} -> {entry['subsystems']}")
+ return CategoryRecord(
+  filename=auto.filename,
+  fixture_class=FixtureClass(entry.get("fixture_class", auto.fixture_class.value)),
+  subsystems=list(entry.get("subsystems", auto.subsystems)),
+  speed=Speed(entry.get("speed", auto.speed.value)),
+  batch_group=entry.get("batch_group", auto.batch_group),
+  notes=entry.get("notes", auto.notes),
+  test_order=dict(auto.test_order),
+  source="registry",
+  warnings=warnings,
+ )
+
+def categorize_all(tests_dir: Path, registry_path: Path) -> list[CategoryRecord]:
+ registry = load_registry(registry_path)
+ records: list[CategoryRecord] = []
+ for path in sorted(tests_dir.glob("test_*.py")):
+  auto = auto_classify(path)
+  entry = registry.get(path.name, {})
+  if entry:
+   records.append(merge_registry(auto, entry))
+  else:
+   records.append(auto)
+ return records