Catalogue: classify collection into system/faction/force-org class

- dlphelper/warhammer_data.py: keyword taxonomy (40k factions incl. Chaos and
  Xenos super-faction units, plus AoS/Heresy/Kill Team/Necromunda/Epic/OW)
- dlphelper/catalogue.py: manifest+directory scanner, conservative keyword
  classifier (plural-tolerant word boundaries, longest match wins), markdown
  and jsonl reports, overrides support, audited --apply moves
- catalogue.py CLI; tests/test_catalogue.py offline classifier test
- real-data check on the user's dirs: 1624/3333 files classified so far

tests/test_catalogue.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+"""Offline classifier test for the catalogue (no network, no deps).
+
+Run with: python3 tests/test_catalogue.py
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from dlphelper.catalogue import classify  # noqa: E402
+
+CASES = [
+    # (filename, expected system, expected faction, expected class or None-any)
+    ("Thunderwolf Cavalry.7z", "Warhammer 40,000", "Adeptus Astartes", "Fast Attack"),
+    ("Wulfen.zip", "Warhammer 40,000", "Adeptus Astartes", "Elites"),
+    ("Keeper of Secrets & Shalaxi Helbane.7z", "Warhammer 40,000", "Chaos Daemons", "HQ"),
+    ("Assorted Drones.zip", "Warhammer 40,000", "T'au Empire", None),
+    ("Commander Shadowsun.zip", "Warhammer 40,000", "T'au Empire", "HQ"),
+    ("Devilfish.zip", "Warhammer 40,000", "T'au Empire", "Dedicated Transport"),
+    ("Battle Sister Scanz.zip", "Warhammer 40,000", "Adepta Sororitas", None),
+    ("Knights.zip", None, None, None),  # ambiguous keyword alone: unclassified
+    ("Khorne Demon Enginez and skull lordz.zip", "Warhammer 40,000", "Chaos Daemons", None),
+    ("Cultists.zip", "Warhammer 40,000", "Chaos Space Marines", "Elites"),
+    ("Da Troopz.zip", "Warhammer 40,000", "Orks", None),
+    ("Seraphon.zip", "Other Systems", "Age of Sigmar", None),
+    ("Leviathan Dreadnought.zip", "Warhammer 40,000", "Adeptus Astartes", "Elites"),
+    ("Poxwalkers.zip", "Warhammer 40,000", "Death Guard", "Elites"),
+    ("Kabalite Warriors.zip", "Warhammer 40,000", "Drukhari", "Troops"),
+    ("Canoptek Wraiths.zip", "Warhammer 40,000", "Necrons", "Fast Attack"),
+    ("random thing with no keywords.zip", None, None, None),
+]
+
+
+def main() -> None:
+    failures = 0
+    for name, exp_system, exp_faction, exp_class in CASES:
+        system, faction, klass = classify(name)
+        problems = []
+        if exp_system and system != exp_system:
+            problems.append(f"system={system!r} != {exp_system!r}")
+        if exp_faction and faction != exp_faction:
+            problems.append(f"faction={faction!r} != {exp_faction!r}")
+        if exp_class and klass != exp_class:
+            problems.append(f"class={klass!r} != {exp_class!r}")
+        if problems:
+            failures += 1
+            print(f"FAIL {name!r}: {', '.join(problems)}")
+        else:
+            print(f"ok   {name!r} -> {system} / {faction} / {klass}")
+    if failures:
+        print(f"\n{failures} failures")
+        sys.exit(1)
+    print("\ntest_catalogue: OK")
+
+
+if __name__ == "__main__":
+    main()