feat(media): a music relayout that files by the tag row Jellyfin matched

The music library is rips and discography packs whose filenames say nothing the
matcher needs. The authority is Jellyfin's own audio rows: one per track, with
the album and album-artist ids it carries in BaseItemProviders (the item JSON
holds an empty ProviderIds for albums in this build).

Grouping is what the tags assert, not where files sit: (album-artist tag, album,
year), case-folded. A compilation is one album whose tracks name many performers,
so it files once under Various Artists; two album-artist tags on one album name
are two albums. The folder spelling is the dominant one, because a name taken
from whichever row sorted first depends on row order and re-names albums that are
already filed.

An occupied path is never a destination: the executor refuses occupied targets,
so a plan that aims at one fails after the renames meant to clear it. A file
standing on its own target, or already carrying a collision suffix, is a keep -
otherwise the plan shuffles instead of being a fixed point.

scripts/media-census.py

@@ -26,6 +26,14 @@ scripts/media-plan.py and scripts/media-shows.py read them instead of touching m
           SERIES' values, `extra` is Jellyfin's own extra type when the row is
           bonus material rather than an episode
 
+  music file <TAB> artist <TAB> album <TAB> year <TAB> disc <TAB> track <TAB> title
+         <TAB> mb <TAB> performer   (see MUSIC_COLS)
+         one row per track Jellyfin has tagged: the tag read is what the row IS,
+         so `artist` is the album artist (the track artist when that is empty) and
+         `album`/`year` are the album item's provider values when the folder is an
+         album item and the tags' otherwise; `mb` is the album's MusicBrainz
+         release group, `performer` the track artist the tags carry
+
 `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
@@ -74,6 +82,23 @@ JF_TV = ("MediaBrowser.Controller.Entities.TV.Episode",
 JF_SQL = ("""select Id, Path, IndexNumber, ParentIndexNumber, ExtraType, IsVirtualItem
               from BaseItems where Type = ? and Path like ?""")
 
+# The music tree is these two entity classes. The track row carries the tags
+# Jellyfin read out of the file; the album row carries what the provider matched,
+# which is the better folder name of the two.
+JF_AUDIO = "MediaBrowser.Controller.Entities.Audio.Audio"
+JF_ALBUM = "MediaBrowser.Controller.Entities.Audio.MusicAlbum"
+MUSIC_COLS = ["file", "artist", "album", "year", "disc", "track", "title", "mb",
+              "performer"]
+MUSIC_SQL = ("""select b.Path, b.AlbumArtists, b.Artists, b.Album, b.ProductionYear,
+                       b.ParentIndexNumber, b.IndexNumber, b.Name, b.Id,
+                       a.Name, a.ProductionYear, a.Id
+                  from BaseItems b
+                  left join BaseItems a on a.Id = b.ParentId and a.Type = ?
+                 where b.Type = ? and b.Path like ?""")
+# The album's identity, in preference order. A release group is the album; a bare
+# release id is one reissue of it.
+MUSIC_PROVIDERS = ("MusicBrainzReleaseGroup", "MusicBrainzAlbum")
+
 
 def enumerate_lib(root, out):
     """One row per real file under root: size, extension, path."""
@@ -263,6 +288,81 @@ def jellyfin(root, db, container, out):
     print(f"episodes={written} virtual-or-blank={skipped} -> {out}")
 
 
+def music(root, db, container, out):
+    """The tracks Jellyfin has already tagged, for the library at root.
+
+    Jellyfin reads music metadata out of the file itself, so an Audio row IS the
+    tag read, done once, by the vendor's own parser: its album-artist, album,
+    year, disc and track columns are what the embedded tags say and its Name is
+    the track title. That makes this export the whole authority for a music
+    relayout — the path a ripper chose is not evidence of anything, and the
+    folder Jellyfin put a track under is often a release pack, not an album.
+
+    Two gaps this export answers from the row rather than the tree. Many tracks
+    sit under a folder that is not an album item at all (a disc folder, or a
+    mixed one), so the album name and year fall back to the tags when the album
+    row is absent. And an album's MusicBrainz ids are not in the row's own Data
+    — the current schema leaves that empty for music — they are rows of
+    BaseItemProviders keyed by the item's Id.
+    """
+    try:
+        con = sqlite3.connect(f"file:{db}?mode=ro", uri=True)
+    except sqlite3.Error as e:
+        sys.exit(f"cannot open the Jellyfin database read-only ({db}): {e}\n"
+                 "It is a WAL database: copy it with its -wal and -shm beside it and"
+                 " point --db at the copy. Never sudo it — the data dir belongs to"
+                 " the container's owner, and rootless storage is per-user.")
+    have = {r[1] for r in con.execute("pragma table_info(BaseItems)")}
+    need = {"Id", "ParentId", "Type", "Path", "Name", "IndexNumber",
+            "ParentIndexNumber", "ProductionYear", "Album", "AlbumArtists",
+            "Artists"}
+    if not need <= have:
+        sys.exit(f"{db} is not a Jellyfin library database with music columns"
+                 f" (BaseItems has no {','.join(sorted(need - have))})")
+    # Provider ids, best identity first: the release group is the album, a bare
+    # release id is one reissue of it and never overrides a group.
+    mb = {}
+    if "BaseItemProviders" in {r[0] for r in con.execute(
+            "select name from sqlite_master where type='table'")}:
+        rank = {p: i for i, p in enumerate(MUSIC_PROVIDERS)}
+        best = {}
+        for iid, pid, val in con.execute(
+                "select ItemId, ProviderId, ProviderValue from BaseItemProviders"
+                " where ProviderId in (?, ?)", MUSIC_PROVIDERS):
+            if iid not in best or rank[pid] < best[iid][0]:
+                best[iid] = (rank[pid], val)
+        mb = {k: v[1] for k, v in best.items()}
+
+    # The fleet's quadlets bind the share at /data, so the container's view of
+    # this library is /data/<the library's own folder name> unless told otherwise.
+    if not container:
+        container = "/data/" + os.path.basename(os.path.normpath(root))
+    prefix = container.rstrip("/") + "/"
+    written = skipped = 0
+    with open(out, "w", newline="") as fh:
+        w = csv.writer(fh, delimiter="\t", lineterminator="\n")
+        w.writerow(MUSIC_COLS)
+        for (path, aal, arts, tag_album, tag_year, disc, track, name, iid,
+             alb_name, alb_year, alb_id) in con.execute(
+                MUSIC_SQL, (JF_ALBUM, JF_AUDIO, prefix + "%")):
+            if not path or not path.startswith(prefix):
+                skipped += 1          # a row for a file outside this library
+                continue
+            # The album artist owns the folder; the track artist is the fallback
+            # for the compilations whose album-artist tag was left empty.
+            w.writerow([root + "/" + path[len(prefix):],
+                        ((aal or "").strip() or (arts or "").strip()),
+                        (alb_name or tag_album or "").replace("\t", " "),
+                        alb_year or tag_year or "",
+                        "" if disc is None else disc,
+                        "" if track is None else track,
+                        (name or "").replace("\t", " "),
+                        mb.get(alb_id or "") or mb.get(iid or "") or "",
+                        (arts or "").replace("\t", " ")])
+            written += 1
+    print(f"tracks={written} outside-root-or-blank={skipped} -> {out}")
+
+
 def main():
     ap = argparse.ArgumentParser(description=__doc__.splitlines()[0])
     sub = ap.add_subparsers(dest="cmd", required=True)
@@ -289,6 +389,16 @@ def main():
                    help="the in-container prefix that stands for --root"
                         " (default /data/<root's folder name>)")
     j.add_argument("--out", default="/tmp/jellyfin-tv.tsv")
+    m = sub.add_parser("music",
+                       help="export the tracks Jellyfin has tagged for the root")
+    m.add_argument("--root", default=os.environ.get("MEDIA_MUSIC_ROOT",
+                                                    "/mnt/entropy/Music"),
+                   help="music library root on the host")
+    m.add_argument("--db", default=JF_DB)
+    m.add_argument("--container", default=None,
+                   help="the in-container prefix that stands for --root"
+                        " (default /data/<root's folder name>)")
+    m.add_argument("--out", default="/tmp/jellyfin-music.tsv")
     a = ap.parse_args()
     if a.cmd == "enumerate":
         enumerate_lib(a.root, a.out)
@@ -296,6 +406,8 @@ def main():
         probe(a.enum, a.out, a.jobs)
     elif a.cmd == "plex":
         plex(a.root, a.db, a.out)
+    elif a.cmd == "music":
+        music(a.root, a.db, a.container, a.out)
     else:
         jellyfin(a.root, a.db, a.container, a.out)