US01-01 follow-up: replace donor characterization iteration with YAML ledger + full suite (#46)

tests/characterization/test_donor_ledger.py

@@ -0,0 +1,88 @@
+"""Ledger lint (US01-01): every donor-ledger row must carry a real source
+reference, a target location, and either existing characterization test IDs or
+a real pending backlog story."""
+import re
+from pathlib import Path
+
+import yaml
+
+REPO = Path(__file__).resolve().parents[2]
+LEDGER = REPO / "donor_ledger.yaml"
+STORIES = REPO / "delivery_backlog" / "stories"
+TESTS_DIR = Path(__file__).resolve().parent
+
+CLASSIFICATIONS = {"reuse", "extract", "refactor", "replace"}
+REQUIRED_AREAS = {"discovery", "hashing", "imaging", "nsfw", "vision", "exif",
+                  "database", "ui", "configuration", "logging", "cancellation",
+                  "error"}
+STATUSES = {"characterized", "pending"}
+
+
+def load_rows():
+    rows = yaml.safe_load(LEDGER.read_text(encoding="utf-8"))["rows"]
+    assert rows, "empty ledger"
+    return rows
+
+
+def collect_test_ids() -> set:
+    """module::function for every test in this suite."""
+    ids = set()
+    for f in TESTS_DIR.glob("test_*.py"):
+        for m in re.finditer(r"^def (test_\w+)", f.read_text(encoding="utf-8"),
+                             re.MULTILINE):
+            ids.add(f"{f.stem}::{m.group(1)}")
+    return ids
+
+
+def test_rows_have_required_fields_and_unique_ids():
+    rows = load_rows()
+    ids = [r["id"] for r in rows]
+    assert len(ids) == len(set(ids)), "duplicate row ids"
+    for r in rows:
+        for field in ("id", "area", "source", "classification", "rationale",
+                      "target", "status"):
+            assert r.get(field), f"{r.get('id', '?')}: missing {field}"
+        assert r["classification"] in CLASSIFICATIONS, r["id"]
+        assert r["status"] in STATUSES, r["id"]
+        assert len(str(r["rationale"]).strip()) >= 20, \
+            f"{r['id']}: rationale too thin to count as a documented reason"
+
+
+def test_source_references_resolve():
+    for r in load_rows():
+        src = r["source"]
+        f = REPO / src["file"]
+        assert f.is_file(), f"{r['id']}: source file {src['file']} missing"
+        text = f.read_text(encoding="utf-8")
+        for sym in src["symbols"]:
+            assert sym in text, f"{r['id']}: symbol {sym!r} not found in {src['file']}"
+
+
+def test_rows_have_tests_or_pending_story():
+    known_tests = collect_test_ids()
+    for r in load_rows():
+        tests = r.get("tests", [])
+        pending = r.get("pending_story")
+        assert tests or pending, f"{r['id']}: neither tests nor pending_story"
+        for t in tests:
+            assert t in known_tests, f"{r['id']}: unknown test id {t}"
+        if pending:
+            matches = list(STORIES.glob(f"{pending}-*.md"))
+            assert matches, f"{r['id']}: pending_story {pending} has no story file"
+        if r["status"] == "characterized":
+            assert tests, f"{r['id']}: characterized rows need test ids"
+
+
+def test_all_required_areas_covered():
+    covered = {r["area"] for r in load_rows()}
+    assert REQUIRED_AREAS <= covered, f"uncovered areas: {REQUIRED_AREAS - covered}"
+    assert covered <= REQUIRED_AREAS, f"unknown areas: {covered - REQUIRED_AREAS}"
+
+
+def test_no_legacy_file_moved():
+    # US01-01 explicitly forbids moving/archiving donors; the ledger's source
+    # files must all still exist at their original locations.
+    for donor in ("photo_analyzer.py", "nsfwtag/scoring.py", "nsfwtag/exif.py",
+                  "nsfwtag/server.py", "webapp/query.py", "webapp/runner.py",
+                  "webapp/server.py"):
+        assert (REPO / donor).is_file(), f"donor moved: {donor}"