feat(media): the audiobook relayout, filed by the book Plex matched

The audiobook tree is the one library Jellyfin does not read at all and Plex
reads completely: 58,975 chapters matched into Artist/Album/Track, where the
album is the BOOK and the book's single artist row is the NARRATOR. That is the
authority the new planner files by, never the collection folder a pack made.

  Audiobooks/<Narrator>/<Book> (<year>)/<the file's own name>

Two laws are the opposite of the music tool's, both forced by the rows: files
are never renumbered (72% of the books carry chapters with no usable index, and
playback order comes from the embedded track tag either way, so an invented
number can only lie), and the shelf is the narrator, not the author (every book
has exactly one artist row; the author survives in 10% of album titles and in no
column Plex stores, so one rule beats a shelf half authors and half narrators).

media-census.py gains the audiobooks export: the chapters Plex matched under a
root, host paths straight through, nothing outside the root and nothing Plex
deleted. 22 tests in tests/media_audiobooks.bats pin the export's join and the
plan's output.

scripts/media-census.py

@@ -5,6 +5,7 @@ r"""Read-only census of a media library — the inputs a relayout plan is built
   media-census.py probe     [--enum TSV] [--out TSV] [--jobs N]
   media-census.py plex      [--root DIR] [--db PATH] [--out TSV]
   media-census.py jellyfin  [--root DIR] [--db PATH] [--container PREFIX] [--out TSV]
+  media-census.py audiobooks [--root DIR] [--db PATH] [--out TSV]
 
 Run it on the machine that mounts the library. Nothing here writes inside the
 library and nothing is deleted; the only outputs are the TSVs below, and the
@@ -34,6 +35,14 @@ scripts/media-plan.py and scripts/media-shows.py read them instead of touching m
          album item and the tags' otherwise; `mb` is the album's MusicBrainz
          release group, `performer` the track artist the tags carry
 
+  audiobooks file <TAB> narrator <TAB> book <TAB> year <TAB> track <TAB> chapter
+         (see AB_COLS)
+         one row per chapter Plex matched under the audiobook root: `book` is the
+         album row Plex built from the files' own tags, `narrator` that book's
+         artist row — Plex keeps exactly one artist per book, which is why it, and
+         not an author parsed out of a title, names the shelf. `track` is empty
+         wherever Plex has no chapter number, which is most of this library.
+
 `probe` is the slow step (every container is opened for its header, ~10 min for
 4,800 files on a spindle array at 6 workers) so it is `nice`d: a census beside a
 live service must not starve it. `enumerate` is a stat pass, so re-censusing
@@ -99,6 +108,26 @@ MUSIC_SQL = ("""select b.Path, b.AlbumArtists, b.Artists, b.Album, b.ProductionY
 # release id is one reissue of it.
 MUSIC_PROVIDERS = ("MusicBrainzReleaseGroup", "MusicBrainzAlbum")
 
+# Plex's audiobook tree is the same Artist/Album/Track shape as its music tree:
+# the leaf (10) is a CHAPTER, its parent (9) is the BOOK, and that book's artist
+# (8) is the NARRATOR. The track's own `index` is exported because the exceptions
+# report counts how many books have chapters Plex does not number — the reason the
+# relayout refuses to invent numbers into file names.
+PLEX_ARTIST, PLEX_ALBUM, PLEX_TRACK = 8, 9, 10
+AB_COLS = ["file", "narrator", "book", "year", "track", "chapter"]
+AB_SQL = f"""
+select p.file, coalesce(ar.title,''), coalesce(al.title,''), coalesce(al.year,0),
+       coalesce(mi."index",-1), coalesce(mi.title,'')
+from media_parts p
+join media_items m on m.id = p.media_item_id
+join metadata_items mi on mi.id = m.metadata_item_id
+join metadata_items al on al.id = mi.parent_id and al.metadata_type = {PLEX_ALBUM}
+left join metadata_items ar on ar.id = al.parent_id
+                          and ar.metadata_type = {PLEX_ARTIST}
+where p.file like ? and p.deleted_at is null and mi.deleted_at is null
+  and al.deleted_at is null
+"""
+
 
 def enumerate_lib(root, out):
     """One row per real file under root: size, extension, path."""
@@ -363,6 +392,49 @@ def music(root, db, container, out):
     print(f"tracks={written} outside-root-or-blank={skipped} -> {out}")
 
 
+def audiobooks(root, db, out):
+    """The chapters Plex matched inside the audiobook library, read-only.
+
+    Plex stores HOST paths here (unlike Jellyfin, which stores the container's
+    view), so no prefix mapping is needed: the part's `file` is the path the
+    operator has today. Rows for files outside `root` are skipped, because one
+    Plex library DB carries every library on the box.
+
+    The chapter's `index` is exported as an empty field when Plex has none. That
+    is not a gap to fill in here: three quarters of the books on this box contain
+    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.")
+    tables = {r[0] for r in con.execute(
+        "select name from sqlite_master where type='table'")}
+    missing = {"media_parts", "media_items", "metadata_items"} - tables
+    if missing:
+        sys.exit(f"{db} is not a Plex library database (no "
+                 f"{', '.join(sorted(missing))})")
+    written = skipped = 0
+    with open(out, "w", newline="") as fh:
+        w = csv.writer(fh, delimiter="\t", lineterminator="\n")
+        w.writerow(AB_COLS)
+        for file, narrator, book, year, track, chapter in con.execute(
+                AB_SQL, (root.rstrip("/") + "/%",)):
+            if not file or not file.startswith(root.rstrip("/") + "/"):
+                skipped += 1              # a row for a file outside this library
+                continue
+            w.writerow([file.replace("\t", " "), narrator.replace("\t", " "),
+                        book.replace("\t", " "), "" if not year else year,
+                        "" if track is None or int(track) < 0 else track,
+                        chapter.replace("\t", " ")])
+            written += 1
+    print(f"chapters={written} outside-root={skipped} -> {out}")
+
+
 def main():
     ap = argparse.ArgumentParser(description=__doc__.splitlines()[0])
     sub = ap.add_subparsers(dest="cmd", required=True)
@@ -399,6 +471,13 @@ def main():
                    help="the in-container prefix that stands for --root"
                         " (default /data/<root's folder name>)")
     m.add_argument("--out", default="/tmp/jellyfin-music.tsv")
+    b = sub.add_parser("audiobooks",
+                       help="export the chapters Plex matched for the audiobook root")
+    b.add_argument("--root", default=os.environ.get("MEDIA_AUDIOBOOKS_ROOT",
+                                                    "/mnt/entropy/Audiobooks"),
+                   help="audiobook library root on the host")
+    b.add_argument("--db", default=PLEX_DB)
+    b.add_argument("--out", default="/tmp/plex-audiobooks.tsv")
     a = ap.parse_args()
     if a.cmd == "enumerate":
         enumerate_lib(a.root, a.out)
@@ -408,6 +487,8 @@ def main():
         plex(a.root, a.db, a.out)
     elif a.cmd == "music":
         music(a.root, a.db, a.container, a.out)
+    elif a.cmd == "audiobooks":
+        audiobooks(a.root, a.db, a.out)
     else:
         jellyfin(a.root, a.db, a.container, a.out)