From 38444404d135fe0eb8c3de60868eda236b72f701 Mon Sep 17 00:00:00 2001
From: Abdessamad Derraz <3028866+Abdess@users.noreply.github.com>
Date: Wed, 21 Oct 2026 05:08:00 +0200
Subject: [PATCH] fix: surface data rows that name no registry key

The buildbot system row was planned as refresh_data_dirs.py --key
'buildbot system', which always exits 1 on an unknown key. A data row now
runs only when its subject is a _data_dirs.yml entry; the rest is shown
for a human to add.
---
 scripts/refresh_stale.py    | 19 ++++++++++++++++---
 tests/test_refresh_stale.py | 10 ++++++++++
 2 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/scripts/refresh_stale.py b/scripts/refresh_stale.py
index 8712b101..d83f8828 100755
--- a/scripts/refresh_stale.py
+++ b/scripts/refresh_stale.py
@@ -25,7 +25,8 @@ Mapping (stale -> command):
     catalogs/fbneo recipes  python -m scripts.scraper.romset_dat_importer
                             --source fbneo --fetch
 
-Surfaced only (no refresh): coreinfo gaps, redump/no-intro/tosec packs,
+Surfaced only (no refresh): data rows that are not a _data_dirs.yml key
+(the registry itself, buildbot assets it does not track), coreinfo gaps, redump/no-intro/tosec packs,
 CI pins (install.py SHA-256, PyPI, pinned actions), profile_sync. Each needs
 a human read (new .info file, manual DAT download, PyPI version bump).
 
@@ -46,12 +47,14 @@ import sys
 import time
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from dataclasses import dataclass
+from functools import lru_cache
 from pathlib import Path
 
 REPO_ROOT = Path(__file__).resolve().parents[1]
 LOG_DIR = REPO_ROOT / "tmp" / "refresh_stale"
 CHECK_FRESHNESS = REPO_ROOT / "scripts" / "check_freshness.py"
 PLATFORMS_REGISTRY = REPO_ROOT / "platforms" / "_registry.yml"
+DATA_DIRS_REGISTRY = REPO_ROOT / "platforms" / "_data_dirs.yml"
 
 AUTO_AREAS = ("platforms", "native", "targets", "data", "catalogs")
 MANUAL_AREAS = ("coreinfo", "ci", "profiles")
@@ -91,6 +94,15 @@ def _load_platform_registry() -> dict[str, dict]:
         return (yaml.safe_load(fh) or {}).get("platforms") or {}
 
 
+@lru_cache(maxsize=1)
+def _data_dir_keys() -> frozenset[str]:
+    """The entries refresh_data_dirs.py --key accepts."""
+    import yaml
+
+    with DATA_DIRS_REGISTRY.open(encoding="utf-8") as fh:
+        return frozenset((yaml.safe_load(fh) or {}).get("data_directories") or {})
+
+
 def _run_check_freshness(areas: tuple[str, ...], extra: list[str]) -> list[dict]:
     """Run check_freshness.py --json and return its findings."""
     cmd = [sys.executable, str(CHECK_FRESHNESS), "--json"]
@@ -246,8 +258,9 @@ def _command_for(
         ]
 
     if area == "data":
-        if subject == "_data_dirs.yml":
-            # The registry file itself cannot be refreshed, but its entries can.
+        if subject not in _data_dir_keys():
+            # "_data_dirs.yml" and "buildbot system" name the registry and
+            # what it does not track yet: a human adds the entry.
             return None
         return [
             sys.executable,
diff --git a/tests/test_refresh_stale.py b/tests/test_refresh_stale.py
index 691f9f9a..3b7b01eb 100644
--- a/tests/test_refresh_stale.py
+++ b/tests/test_refresh_stale.py
@@ -101,6 +101,16 @@ class Planning(unittest.TestCase):
         )
         self.assertEqual([f["subject"] for f in surfaced], ["redump"])
 
+    def test_a_data_row_outside_the_registry_needs_a_human(self):
+        """refresh_data_dirs.py --key 'buildbot system' exits 1 on an unknown
+        key: the row asks for a registry entry, not a refresh."""
+        jobs, surfaced, _ = self._plan(
+            finding("data", "buildbot system"), finding("data", "_data_dirs.yml")
+        )
+        self.assertEqual(jobs, [])
+        self.assertEqual([f["subject"] for f in surfaced],
+                         ["buildbot system", "_data_dirs.yml"])
+
     def test_only_stale_rows_run_and_errors_are_shown(self):
         jobs, surfaced, ignored = self._plan(
             finding("data", "a", "OK"),