downloads(#934): instant startup reconcile of stuck-'unverified' history from tracks truth

Complements the AcoustID-scan-time heal: re-links library_history rows still
showing 'unverified' to the verified/human_verified status their file already
carries in the tracks table — matching exact path AND basename, so a file that
moved (media-server import / reorganize) heals even though the stored history
path is frozen. Upgrade-only and non-destructive (no deletes, no bulk
migration).

Why this is needed on top of the scan-time fix:
- It clears the EXISTING backlog (e.g. 5551 rows) on the next restart with NO
  re-fingerprinting and no AcoustID API calls — the file's status is already in
  tracks from the prior scan; this just propagates it to the frozen history row.
- It covers human_verified files, which the AcoustID scan skips entirely
  (file_verif_status == 'human_verified' returns early), so their stale history
  rows would otherwise never heal.

Runs once on DB init (cheap, idempotent). 5 real-sqlite tests.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LWJk7EuM7YktQeNyqQwTZY
This commit is contained in:
dev 2026-06-27 19:22:36 +02:00
parent 3a92571c71
commit a42cf3b865
2 changed files with 197 additions and 0 deletions

View file

@ -1000,6 +1000,10 @@ class MusicDatabase:
self._init_manual_library_match_table()
self._backfill_mirrored_track_source_ids()
# Self-heal the Unverified review queue: lift history rows stuck at
# 'unverified' whose file has since been verified (issue #934). Cheap,
# idempotent (only touches rows that need it), so it's safe every boot.
self.reconcile_unverified_history_from_tracks()
def _backfill_mirrored_track_source_ids(self) -> int:
"""One-time, idempotent: assign a stable source_track_id to mirrored tracks
@ -13857,6 +13861,59 @@ class MusicDatabase:
logger.error("Error querying unverified library history: %s", e)
return []
def reconcile_unverified_history_from_tracks(self) -> int:
"""Heal library_history rows stuck at 'unverified' whose underlying file
has since been confirmed in the tracks table (AcoustID scan PASS or a
human decision). Matches by exact path AND basename the same physical
file keeps its filename across path-form differences (relative vs
absolute, library moved/reorganized, different mount), which is why an
exact-path-only heal left thousands of already-verified files showing as
Unverified (issue #934).
Upgrade-only and non-destructive: it only lifts 'unverified' rows to the
confirmed status, never downgrades and never deletes. Returns the number
of rows healed. Genuinely-unverified rows and orphans (no matching
track) are left untouched.
"""
healed = 0
try:
conn = self._get_connection()
cursor = conn.cursor()
rank = {'verified': 1, 'human_verified': 2}
by_path = {}
by_base = {}
cursor.execute(
"SELECT file_path, verification_status FROM tracks "
"WHERE verification_status IN ('verified', 'human_verified') "
"AND file_path IS NOT NULL AND file_path != ''")
for fp, st in cursor.fetchall():
if not fp:
continue
by_path[fp] = st
base = os.path.basename(fp)
if base and rank.get(st, 0) >= rank.get(by_base.get(base), 0):
by_base[base] = st
updates = []
cursor.execute(
"SELECT id, file_path FROM library_history "
"WHERE verification_status = 'unverified' "
"AND file_path IS NOT NULL AND file_path != ''")
for rid, fp in cursor.fetchall():
target = by_path.get(fp) or by_base.get(os.path.basename(fp or ''))
if target:
updates.append((target, rid))
for status, rid in updates:
cursor.execute(
"UPDATE library_history SET verification_status = ? WHERE id = ?",
(status, rid))
healed += 1
if healed:
conn.commit()
logger.info("Reconciled %d unverified history rows from tracks truth", healed)
except Exception as e:
logger.error("Error reconciling unverified history: %s", e)
return healed
def get_library_history_stats(self):
"""Return counts per event_type and per download_source."""
try:

View file

@ -0,0 +1,140 @@
"""Issue #934 — one-time reconcile that clears the existing backlog of
``library_history`` rows stuck at 'unverified' even though the file has since
been verified (by an AcoustID scan, or human-confirmed). Heals from the
``tracks`` truth, matching exact path AND basename (so a reorganized/moved file
heals too), upgrade-only. Never deletes anything."""
import sqlite3
import sys
import types
if "spotipy" not in sys.modules: # match the suite's lightweight stubs
spotipy = types.ModuleType("spotipy")
spotipy.Spotify = object
oauth2 = types.ModuleType("spotipy.oauth2")
oauth2.SpotifyOAuth = object
oauth2.SpotifyClientCredentials = object
spotipy.oauth2 = oauth2
sys.modules["spotipy"] = spotipy
sys.modules["spotipy.oauth2"] = oauth2
if "config.settings" not in sys.modules:
config_pkg = types.ModuleType("config")
settings_mod = types.ModuleType("config.settings")
class _DummyConfigManager:
def get(self, key, default=None):
return default
def get_active_media_server(self):
return "primary"
settings_mod.config_manager = _DummyConfigManager()
config_pkg.settings = settings_mod
sys.modules["config"] = config_pkg
sys.modules["config.settings"] = settings_mod
from database.music_database import MusicDatabase # noqa: E402
class _NonClosingConn:
def __init__(self, real):
self._real = real
def cursor(self):
return self._real.cursor()
def commit(self):
return self._real.commit()
def close(self):
pass
def __enter__(self):
return self
def __exit__(self, *args):
pass
class _InMemoryDB(MusicDatabase):
def __init__(self):
self._conn = sqlite3.connect(":memory:")
self._conn.row_factory = sqlite3.Row
self._conn.execute(
"CREATE TABLE tracks (id INTEGER PRIMARY KEY, file_path TEXT, "
"verification_status TEXT)"
)
self._conn.execute(
"CREATE TABLE library_history ("
"id INTEGER PRIMARY KEY AUTOINCREMENT, event_type TEXT, title TEXT, "
"artist_name TEXT, album_name TEXT, file_path TEXT, "
"download_source TEXT, verification_status TEXT, "
"created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP)"
)
def _get_connection(self):
return _NonClosingConn(self._conn)
def _add_track(self, tid, path, status):
self._conn.execute(
"INSERT INTO tracks (id, file_path, verification_status) VALUES (?,?,?)",
(tid, path, status))
self._conn.commit()
def _add_history(self, path, status, title="Song"):
self._conn.execute(
"INSERT INTO library_history (event_type, title, file_path, "
"verification_status) VALUES ('download', ?, ?, ?)",
(title, path, status))
self._conn.commit()
def _status_of(self, hid):
return self._conn.execute(
"SELECT verification_status FROM library_history WHERE id = ?", (hid,)
).fetchone()[0]
def test_reconcile_heals_exact_path_match():
db = _InMemoryDB()
db._add_track(1, "/lib/A/01 - Song.flac", "verified")
db._add_history("/lib/A/01 - Song.flac", "unverified")
healed = db.reconcile_unverified_history_from_tracks()
assert healed == 1
assert db._status_of(1) == "verified"
def test_reconcile_heals_by_basename_when_path_form_differs():
db = _InMemoryDB()
db._add_track(1, "/library/Artist/Album/01 - Song.flac", "verified")
# History stored the transfer-folder path; basename still matches.
db._add_history("/transfer/Artist - Album/01 - Song.flac", "unverified")
healed = db.reconcile_unverified_history_from_tracks()
assert healed == 1
assert db._status_of(1) == "verified"
def test_reconcile_propagates_human_verified():
db = _InMemoryDB()
db._add_track(1, "/lib/01 - Song.flac", "human_verified")
db._add_history("/lib/01 - Song.flac", "unverified")
db.reconcile_unverified_history_from_tracks()
assert db._status_of(1) == "human_verified"
def test_reconcile_leaves_genuinely_unverified_rows():
db = _InMemoryDB()
db._add_track(1, "/lib/01 - Song.flac", "unverified") # track itself unconfirmed
db._add_history("/lib/01 - Song.flac", "unverified")
healed = db.reconcile_unverified_history_from_tracks()
assert healed == 0
assert db._status_of(1) == "unverified"
def test_reconcile_leaves_orphans_untouched():
db = _InMemoryDB()
# No track references this file at all (deleted / re-downloaded elsewhere).
db._add_history("/lib/gone.flac", "unverified")
healed = db.reconcile_unverified_history_from_tracks()
assert healed == 0
assert db._status_of(1) == "unverified"