Merge pull request 'fix(media): verify read the library the way the servers write it' (#103) from fix/media-verify-wal-read into main

scripts/media-census.py

@@ -130,6 +130,26 @@ where p.file like ? and p.deleted_at is null and mi.deleted_at is null
   and al.deleted_at is null
 """
 
+def open_plex_ro(db):
+    """Plex's library, read the way Plex writes it.
+
+    `immutable=1` tells sqlite the file never changes, so it skips the
+    write-ahead log: every row a scan has committed but not yet checkpointed
+    is invisible, and reading a live database that way can fail outright as
+    "database disk image is malformed". Plain ro reads the WAL through its
+    -shm; immutable is only the fallback for a database whose -shm cannot be
+    read. The same law scripts/media-verify.py states.
+    """
+    last = None
+    for opt in ("mode=ro", "mode=ro&immutable=1"):
+        try:
+            return sqlite3.connect(f"file:{db}?{opt}", uri=True)
+        except sqlite3.Error as e:
+            last = e
+    sys.exit(f"cannot open the Plex database read-only ({db}): {last}\n"
+             "Plex runs rootless here: run this as the container's owner, never "
+             "with sudo — rootless storage is per-user, so root sees nothing.")
+
 
 def enumerate_lib(root, out):
     """One row per real file under root: size, extension, path."""
@@ -229,13 +249,7 @@ def probe(enum, out, jobs):
 
 def plex(root, db, out):
     """Plex's matched titles for files under root, from its DB, read-only."""
-    uri = f"file:{db}?mode=ro&immutable=1"
-    try:
-        con = sqlite3.connect(uri, uri=True)
-    except sqlite3.Error as e:
-        sys.exit(f"cannot open the Plex database read-only ({db}): {e}\n"
-                 "Plex runs rootless here: run this as the container's owner, never "
-                 "with sudo — rootless storage is per-user, so root sees nothing.")
+    con = open_plex_ro(db)
     with open(out, "w", newline="") as fh:
         w = csv.writer(fh, delimiter="\t", lineterminator="\n")
         w.writerow(PLEX_COLS)
@@ -426,13 +440,7 @@ def audiobooks(root, db, out):
     at least one un-indexed chapter, so the relayout that reads this file must
     not renumber anything from it.
     """
-    uri = f"file:{db}?mode=ro&immutable=1"
-    try:
-        con = sqlite3.connect(uri, uri=True)
-    except sqlite3.Error as e:
-        sys.exit(f"cannot open the Plex database read-only ({db}): {e}\n"
-                 "Plex runs rootless here: run this as the container's owner, never "
-                 "with sudo — rootless storage is per-user, so root sees nothing.")
+    con = open_plex_ro(db)
     tables = {r[0] for r in con.execute(
         "select name from sqlite_master where type='table'")}
     missing = {"media_parts", "media_items", "metadata_items"} - tables