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)
 

scripts/media-music.py

@@ -0,0 +1,445 @@
+#!/usr/bin/env python3
+r"""media-music.py — a plan that re-files the music library into Jellyfin's own shape.
+
+    media-music.py --root DIR --enum TSV --rows TSV [--out TSV] [--exceptions FILE]
+
+Jellyfin's music contract (https://jellyfin.org/docs/general/server/media/music/)
+is not the movie one. Jellyfin reads the metadata out of the file, so a folder is
+an ALBUM and nothing else, every disc of an album belongs in that one folder, the
+tags decide the track order, and a file name only matters when it carries a
+character known to break playback (`< > : " / \ | ? *`) or when a lyric file has
+to match the basename of the track it belongs to. The plan is therefore:
+
+    Music/<album artist>/<Album> (<year>)/NN - <Title>.<ext>
+                       ... the same folder, D.NN - <Title>  when the album has discs
+                       Music/Various Artists/...            when its tracks name
+                                                            more than one artist
+
+The authority is the tag row Jellyfin already read — `scripts/media-census.py
+music` — never the release-pack folder a ripper made. A file with no row is not
+guessed at: it parks under `<root>/_unsorted` with the relative path it has today.
+
+The rules below exist because of what a downloaded discography pack actually
+contains:
+
+ * A cuesheet beside exactly one audio file means the album is one image with a
+   track list inside it. That file keeps its own name: numbering it `01` would
+   claim it is one track, and Jellyfin shows one track either way.
+ * Sidecars — images, cuesheets, EAC logs, checksums, booklets, playlists —
+   follow the album the audio in their own folder belongs to. A folder holding
+   two albums gives a sidecar no single owner, so it parks instead of being
+   guessed into one.
+ * A video container (.mkv, .vob, .ifo, …) inside a music library is not music.
+   Renaming it to .mka/.m4a would tell Jellyfin to index video as audio, so it
+   parks for a human decision.
+ * Playlists move with their album and their CONTENTS are never rewritten: the
+   paths inside an .m3u go stale. Editing a file the operator owns to keep a
+   convenience file tidy is not this tool's job.
+
+Nothing is deleted and nothing is overwritten. The output is a list of rename(2)
+intents for `scripts/media-apply.py`, whose preflight refuses any target that is
+already claimed and whose journal is the rollback.
+"""
+import argparse
+import csv
+import os
+import re
+import sys
+from collections import Counter, defaultdict
+
+# What Jellyfin will index as music. .mp4/.mkv/.webm are deliberately NOT here:
+# the vendor doc says an audio-only stream in those containers is never read as
+# music, and this tool renames for a reason it can prove, not to guess at one.
+AUDIO_EXT = {".flac", ".mp3", ".m4a", ".m4b", ".ogg", ".oga", ".opus", ".wav",
+             ".wma", ".aiff", ".aif", ".ape", ".dsf", ".dff", ".wv", ".mka",
+             ".mpc", ".aac"}
+VIDEO_EXT = {".mkv", ".vob", ".ifo", ".bup", ".mpg", ".mpeg", ".avi", ".mov",
+             ".ts", ".m2ts", ".wmv", ".webm", ".mp4", ".m4v", ".iso", ".img",
+             ".bdmv", ".divx", ".ogm"}
+# A lyric has to carry the basename of its track, so it is named after the audio
+# file and not after itself. .txt counts only when its stem matches an audio stem:
+# a loose .txt in an album folder is a note.
+LYRIC_EXT = {".lrc", ".elrc", ".txt"}
+IMAGE_EXT = {".jpg", ".jpeg", ".png", ".webp", ".gif", ".bmp", ".tiff"}
+# The album-artist strings that mean "compilation", so such an album is not filed
+# under one artist who does not own it.
+VARIOUS = {"various", "various artists", "unknown", "unknown artist", "unknow"}
+# The characters Jellyfin documents as breaking playback. They are dropped, not
+# substituted: a replacement character is a guess at what the title meant.
+BAD_CHARS = set('<>:"/\\|?*')
+TRASH_DIR = re.compile(r"(^|/)(\.AGENTTRASH|\.thumbnails|\.Trash-\d+|@eaDir"
+                       r"|lost\+found)(/|$)")
+
+ARGS = None
+HELD = {}                            # path -> (bytes, ext)
+ROWS = {}                            # path -> the tag row
+PLACED = {}                          # audio path -> the destination the plan gave it
+CLAIMED = set()                      # every destination path the plan has handed out
+MOVES, KEEPS = [], []
+PARKED = defaultdict(list)           # reason -> [path]
+NOTES = defaultdict(list)            # section -> [line]
+CUE_DIRS = set()                     # source dirs holding a .cue
+AUDIO_BY_DIR = defaultdict(set)      # source dir -> audio files a row names
+CHILD_OF = defaultdict(set)          # dir -> the dirs directly below it holding audio
+FOLDERS_SEEN = {}                    # (dir, depth) -> album folders placed below it
+SUBTREE_DEPTH = 2                    # how far below a folder its audio may sit
+ALBUMS = {}                          # (artist, album, year) -> the album group
+
+AMBIGUOUS = object()
+
+
+def dominant(values):
+    """The spelling the tags mostly agree on: the most frequent value, ties broken
+    by sort so the answer never depends on the order rows arrived in."""
+    counts = Counter(values)
+    return min(counts.items(), key=lambda kv: (-kv[1], kv[0]))[0]
+
+
+def rel(path):
+    """The path as seen from the library root."""
+    return os.path.relpath(path, ARGS.root)
+
+
+def safe(name):
+    """A name every client can carry: no reserved character, nothing
+    unprintable, no trailing dot or space, and short enough to rename."""
+    out = "".join(c for c in (name or "")
+                  if c not in BAD_CHARS and (c.isprintable() or c == " "))
+    out = re.sub(r"\s+", " ", out).strip().rstrip(". ")
+    while out and len(out.encode("utf-8", "ignore")) > 200:
+        out = out[:-4].rstrip()
+    return out
+
+
+def assign(src, folder, name, ext, kind, note):
+    """Book one file into `folder` under `name`, renamed if that exact destination
+    is already taken — by another file in the plan, or by a file standing there
+    today. Two files claiming one path is the fault that costs a re-run of a 90k
+    plan, and so is a plan that only works if the renames happen in the right
+    order: the executor refuses any target that is occupied, so an occupied path
+    is never a destination, even when its occupant is scheduled to leave.
+    A file already standing where the contract puts it is a keep, not a move."""
+    stem = safe(name) or "file"
+    dst = os.path.join(folder, stem + ext)
+    if dst == src:
+        CLAIMED.add(dst.lower())          # it is standing on its own target
+        KEEPS.append((src, dst, kind))
+        return dst
+    # A file already in this folder under this name — or under the numbered
+    # variant the collision rule gives it — keeps the name it has. Renumbering it
+    # every run would turn the plan into a shuffle instead of a fixed point.
+    base = os.path.splitext(os.path.basename(src))[0]
+    if os.path.dirname(src) == folder and (base == stem
+                                           or base.startswith(stem + " (")):
+        CLAIMED.add(src.lower())
+        KEEPS.append((src, src, kind))
+        return src
+    n = 1
+    while dst.lower() in CLAIMED:
+        n += 1
+        dst = os.path.join(folder, f"{stem} ({n}){ext}")
+    if n > 1:
+        NOTES[note].append(rel(dst))
+    CLAIMED.add(dst.lower())
+    MOVES.append((src, dst, kind))
+    return dst
+
+
+def park(path, reason):
+    """Hold a file where it is, under the park folder, keeping its relative path."""
+    PARKED[reason].append(path)
+    dst = os.path.join(ARGS.park_dir, rel(path))
+    if dst != path:
+        CLAIMED.add(dst.lower())
+        MOVES.append((path, dst, "park"))
+
+
+def under_park(path):
+    """True for a file already parked: that pile is for a human to review, and
+    re-parking it every run would only push it deeper."""
+    return path.startswith(ARGS.park_dir + os.sep)
+
+
+# ---------------------------------------------------------------------- albums
+def group_albums():
+    """Every tagged track into one group per (album-artist tag, album, year).
+
+    The key is the identity the tags assert, not the folder the file sits in: one
+    album arrives as three discs in three folders, and two copies of an album in
+    one pack are one album to Jellyfin, whose album item is that name, artist and
+    year. The artist in the key is the ALBUM-artist tag and never the performer,
+    because a compilation is one album whose tracks name many performers — keying
+    on the performer would file one album once per artist.
+    """
+    for path, r in sorted(ROWS.items()):
+        if path not in HELD or under_park(path):
+            continue
+        d = os.path.dirname(path)
+        AUDIO_BY_DIR[d].add(path)
+        CHILD_OF[os.path.dirname(d)].add(d)   # so a cover above CD1/CD2 sees both
+        tag = (r["artist"] or "").strip()
+        album = (r["album"] or "").strip()
+        performer = (r["performer"] or "").strip()
+        if not album:
+            park(path, "a track no album names")
+            continue
+        if not tag and not performer:
+            park(path, "a track no artist names")
+            continue
+        key = (tag.casefold(), album.casefold(), (r["year"] or "").strip())
+        g = ALBUMS.setdefault(key, {"tags": [], "albums": [], "year": key[2],
+                                    "members": [], "performers": set(),
+                                    "mb": set()})
+        g["members"].append(path)
+        g["tags"].append(tag)
+        g["albums"].append(album)
+        g["performers"].add(performer or tag)
+        if r.get("mb"):
+            g["mb"].add(r["mb"])
+
+
+def folder_artist(g):
+    """Whose shelf the album sits on. The album-artist tag owns it when it names
+    one; when the tags name only performers, a single performer names the album
+    and several make it a compilation, which belongs to no one of them. The key is
+    case-folded, so the spelling that reaches the folder is the one the tracks
+    mostly carry — see dominant()."""
+    tags = [t for t in g["tags"] if t]
+    if tags:
+        name = dominant(tags)
+        return "Various Artists" if name.casefold() in VARIOUS else name
+    if len({p.casefold() for p in g["performers"]}) == 1:
+        return dominant(g["performers"])
+    return "Various Artists"
+
+
+def album_folder(g):
+    name = safe(dominant(g["albums"])) or "Untitled"
+    return os.path.join(ARGS.root, safe(folder_artist(g)) or "Unknown Artist",
+                        f"{name} ({g['year']})" if g["year"] else name)
+
+
+def is_cue_image(path):
+    """A folder holding this one audio file and a cuesheet is an album image."""
+    d = os.path.dirname(path)
+    return len(AUDIO_BY_DIR.get(d, ())) == 1 and d in CUE_DIRS
+
+
+def number_of(value, width):
+    return f"{int(value):0{width}d}" if str(value or "").isdigit() else ""
+
+
+def place_albums():
+    for key in sorted(ALBUMS):
+        g = ALBUMS[key]
+        folder = album_folder(g)
+        discs = {g0["disc"] for g0 in (ROWS[p] for p in g["members"]) if g0["disc"]}
+        tracks = [int(ROWS[p]["track"]) for p in g["members"]
+                  if str(ROWS[p]["track"] or "").isdigit()]
+        # More than one disc, or a disc numbered past the first: the track number
+        # alone cannot name a file uniquely, so the disc goes in front of it.
+        multi = len(discs) > 1 or any(str(d).isdigit() and int(d) > 1 for d in discs)
+        width = 3 if multi or (max(tracks, default=0) > 99) else 2
+        for path in sorted(g["members"]):
+            r = ROWS[path]
+            ext = HELD[path][1]
+            base = os.path.splitext(os.path.basename(path))[0]
+            if is_cue_image(path):
+                name = safe(base) or "image"
+            else:
+                title = safe(r["title"] or base) or "untitled"
+                num = number_of(r["track"], 2 if multi else width)
+                if multi and num:
+                    num = f"{r['disc'] or '1'}.{num}"
+                name = f"{num} - {title}" if num else title
+            PLACED[path] = assign(path, folder, name, ext, "track",
+                                  "two tracks claimed one name inside one album")
+
+
+# --------------------------------------------------------------------- sidecars
+def folders_below(d, depth):
+    """The album folders the audio in `d`, or within `depth` directories below it,
+    was placed in. Memoised, because every loose file in a big discography folder
+    asks the same question about it."""
+    if (d, depth) not in FOLDERS_SEEN:
+        seen = {os.path.dirname(PLACED[a]) for a in AUDIO_BY_DIR.get(d, ())
+                if a in PLACED}
+        if depth:
+            for child in CHILD_OF.get(d, ()):
+                seen |= folders_below(child, depth - 1)
+        FOLDERS_SEEN[(d, depth)] = seen
+    return FOLDERS_SEEN[(d, depth)]
+
+
+def owner_folder(d):
+    """The album folder that owns this directory — the first place up the tree
+    where audio sits, in the directory itself or within SUBTREE_DEPTH levels below
+    it, which is how a box with its discs in CD1/CD2 owns the cover lying above
+    them. None when no audio is near enough to say, AMBIGUOUS when the audio there
+    belongs to more than one album."""
+    while d.startswith(ARGS.root + os.sep) and d != ARGS.root:
+        folders = folders_below(d, SUBTREE_DEPTH)
+        if folders:
+            return next(iter(folders)) if len(folders) == 1 else AMBIGUOUS
+        d = os.path.dirname(d)
+    return None
+
+
+def place_sidecars():
+    """Everything that is not a tagged track: lyrics, images, cuesheets, logs,
+    booklets, playlists — and the clutter that is none of those."""
+    # The lyric rule needs the audio's stem as it is named TODAY, before the plan
+    # renames it, because that is what the sidecar's own name was copied from.
+    stem = {(d, os.path.splitext(os.path.basename(a))[0]): a
+            for d, audios in AUDIO_BY_DIR.items() for a in audios}
+    for path, (_size, ext) in sorted(HELD.items()):
+        if path in ROWS or under_park(path) or TRASH_DIR.search(path):
+            continue
+        d, base = os.path.dirname(path), os.path.splitext(os.path.basename(path))[0]
+        if ext in VIDEO_EXT:
+            park(path, "a video container inside the music library: Jellyfin will "
+                       "not read it as music, and renaming it would claim it is")
+        elif ext in AUDIO_EXT:
+            park(path, "an audio file no provider row names — its tags are not in "
+                       "the library Jellyfin has matched")
+        elif ext in (LYRIC_EXT | IMAGE_EXT) and (d, base) in stem:
+            # A lyric, or a picture named after its track: it follows that track
+            # and takes the name the track now has, or Jellyfin cannot find it.
+            audio = stem[(d, base)]
+            dst = PLACED.get(audio)
+            if dst:
+                folder, name = os.path.dirname(dst), os.path.splitext(
+                    os.path.basename(dst))[0]
+                assign(path, folder, name, ext, "lyric",
+                       "a sidecar whose name collided with another in its album")
+            else:
+                park(path, "a sidecar of a track the plan could not place")
+        else:
+            owner = owner_folder(d)
+            if owner is AMBIGUOUS:
+                park(path, "a sidecar whose folder holds more than one album, so "
+                           "nothing says which one it belongs to")
+            elif owner:
+                assign(path, owner, base, ext,
+                       "playlist" if ext in (".m3u", ".m3u8") else "sidecar",
+                       "one album folder would have carried two files of the same "
+                       "sidecar name")
+            else:
+                park(path, "not music, or music with nothing beside it to belong to")
+
+
+# ---------------------------------------------------------------------- outputs
+def write_plan():
+    """mkdir rows for every destination folder and its whole chain, then the moves.
+    Parents first: the executor creates directories in the order they are listed."""
+    chain = set()
+    for _s, dst, _k in MOVES:
+        d = os.path.dirname(dst)
+        while d and d != ARGS.root and d != os.path.dirname(d):
+            chain.add(d)
+            d = os.path.dirname(d)
+    dirs = sorted(chain, key=lambda p: (p.count("/"), p))
+    with open(ARGS.out, "w") as fh:
+        fh.write("action\tsrc\tdst\tkind\n")
+        for d in dirs:
+            fh.write(f"mkdir\t\t{d}\tdir\n")
+        for src, dst, kind in sorted(MOVES, key=lambda m: (m[1], m[0])):
+            fh.write(f"move\t{src}\t{dst}\t{kind}\n")
+        for src, dst, kind in sorted(KEEPS, key=lambda m: (m[1], m[0])):
+            fh.write(f"keep\t{src}\t{dst}\t{kind}\n")
+    parked = [m for m in MOVES if m[2] == "park"]
+    sized = sum(HELD[s][0] for s, _d, _k in MOVES if s in HELD)
+    print(f"plan: {len(MOVES) - len(parked)} moves, {len(parked)} parked"
+          f" ({sized / 2**40:.2f} TiB touched), {len(KEEPS)} already placed,"
+          f" {len(dirs)} folders -> {ARGS.out}")
+
+
+def write_exceptions():
+    with open(ARGS.exceptions, "w") as fh:
+        fh.write(f"Music relayout exceptions for {ARGS.root}\n\n")
+        fh.write(f"Everything below is parked under {ARGS.park_dir}, keeping the\n"
+                 "relative path it has today. Nothing is deleted and nothing is\n"
+                 "overwritten: a parked file is one rename from wherever the plan is\n"
+                 "pointed next.\n\n")
+        for reason in sorted(PARKED, key=lambda r: -len(PARKED[r])):
+            rs = PARKED[reason]
+            fh.write(f"{len(rs):>6} files  {reason}\n")
+            for p in sorted(rs, key=rel)[:400]:
+                fh.write(f"          {rel(p)}\n")
+            if len(rs) > 400:
+                fh.write(f"          … and {len(rs) - 400} more\n")
+            fh.write("\n")
+        for section in sorted(NOTES, key=lambda s: -len(NOTES[s])):
+            lines = sorted(set(NOTES[section]))
+            fh.write(f"{len(lines):>6}  {section}\n")
+            for line in lines[:200]:
+                fh.write(f"          {line}\n")
+            if len(lines) > 200:
+                fh.write(f"          … and {len(lines) - 200} more\n")
+            fh.write("\n")
+        no_year = sorted(f"{folder_artist(g)}/{dominant(g['albums'])}"
+                         for g in ALBUMS.values() if not g["year"])
+        if no_year:
+            fh.write(f"{len(no_year):>6} albums carry no year in any tag, so their folders\n"
+                     "       are named without one; Jellyfin still matches them.\n")
+            fh.write("       " + ", ".join(no_year[:300]) + "\n\n")
+        clash = sorted(f"{folder_artist(g)}/{dominant(g['albums'])}"
+                       for g in ALBUMS.values() if len(g["mb"]) > 1)
+        if clash:
+            fh.write(f"{len(clash):>6} albums put one folder name on more than one\n"
+                     "       MusicBrainz release group — different releases, one name.\n"
+                     "       They share the folder Jellyfin's own album item names.\n")
+            fh.write("       " + ", ".join(clash[:200]) + "\n\n")
+        fh.write("       Playlists move with their album and their contents are never\n"
+                 "       rewritten: the paths inside an .m3u go stale.\n")
+    print(f"exceptions -> {ARGS.exceptions}")
+
+
+def main():
+    global ARGS
+    ap = argparse.ArgumentParser(description=__doc__.splitlines()[0])
+    ap.add_argument("--root", default=os.environ.get("MEDIA_MUSIC_ROOT",
+                                                     "/mnt/entropy/Music"))
+    ap.add_argument("--enum", default="/tmp/music-enum.tsv",
+                    help="the enumerate TSV (bytes, ext, path)")
+    ap.add_argument("--rows", default="/tmp/jellyfin-music.tsv",
+                    help="the tag rows scripts/media-census.py music wrote")
+    ap.add_argument("--out", default="/tmp/music-plan.tsv")
+    ap.add_argument("--exceptions", default="/tmp/music-exceptions.txt")
+    ap.add_argument("--park", default="_unsorted",
+                    help="the folder inside the root that holds what cannot be filed")
+    ARGS = ap.parse_args()
+    ARGS.root = os.path.normpath(ARGS.root)
+    ARGS.park_dir = os.path.join(ARGS.root, ARGS.park)
+    read_inputs()
+    # Every path a file occupies today is claimed before a single destination is
+    # handed out: the executor refuses an occupied target, so a plan that aimed at
+    # one would only fail after the renames that were supposed to clear it.
+    CLAIMED.update(p.lower() for p in HELD)
+    for path, (_size, ext) in HELD.items():
+        if ext == ".cue":
+            CUE_DIRS.add(os.path.dirname(path))
+    group_albums()
+    place_albums()
+    place_sidecars()
+    write_plan()
+    write_exceptions()
+
+
+def read_inputs():
+    with open(ARGS.enum) as fh:
+        for line in fh:
+            parts = line.rstrip("\n").split("\t")
+            if len(parts) >= 3:
+                HELD[parts[2]] = (int(parts[0]), parts[1].lower())
+    with open(ARGS.rows, newline="") as fh:
+        for row in csv.DictReader(fh, delimiter="\t"):
+            if row.get("file"):
+                ROWS[row["file"]] = row
+    gone = [p for p in ROWS if p not in HELD]
+    if gone:
+        NOTES["a tag row whose file the census no longer sees"].extend(gone)
+
+
+if __name__ == "__main__":
+    main()

tests/media_music.bats

@@ -0,0 +1,373 @@
+#!/usr/bin/env bats
+# Seam: the music-library relayout — scripts/media-census.py music (the tag and
+# provider authority export) and scripts/media-music.py (the plan).
+#
+# Jellyfin's music rule is the opposite of the movie and TV ones: the embedded
+# tags are the metadata and the file name is only a fallback title, so the
+# authority here is the Audio row Jellyfin already matched (its album-artist,
+# album, year, disc and track columns) and NOT the path a ripper chose. Every
+# test states which authority a file has — row only, row with no album item,
+# sidecar of a file that has a row, nothing at all — and asserts where the PLAN
+# files it, never how the planner decided.
+#
+# The three outcomes that cost a re-run of a 90k-file plan: a track filed under
+# the wrong artist (it splits one album across two artists), a destination that
+# two tracks claim (the executor refuses, and the operator loses the run), and a
+# lyric file that stops matching the basename of the track it belongs to, which
+# silently loses the lyrics. Everything below is written to catch those, plus the
+# gate that matters most: the plan must replay through scripts/media-apply.py,
+# whose preflight is the fleet's only overwrite guard.
+
+load helpers
+
+PLAN="$REPO_ROOT/scripts/media-music.py"
+CENSUS="$REPO_ROOT/scripts/media-census.py"
+APPLY="$REPO_ROOT/scripts/media-apply.py"
+
+# at PATH SIZE — a file with deterministic content.
+at() { mkdir -p "$(dirname "$1")"; head -c "$2" /dev/zero > "$1"; }
+
+# row FILE ARTIST ALBUM YEAR DISC TRACK TITLE [MB] [PERFORMER]
+# One row of the authority export scripts/media-census.py music writes.
+row() {
+    printf '%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\t%s\n' \
+        "$1" "$2" "$3" "${4:-}" "${5:-}" "${6:-}" "$7" "${8:-}" "${9:-}" >> "$ROWS"
+}
+
+# dst SRC — the destination the plan gives SRC, or nothing when it does not move.
+dst() {
+    awk -F '\t' -v s="$1" '$1 == "move" && $2 == s {print $3}' "$OUT"
+}
+
+setup() {
+    MUSIC="$BATS_TEST_TMPDIR/Music"
+    PARK="$MUSIC/_unsorted"
+    ENUM="$BATS_TEST_TMPDIR/enum.tsv"
+    ROWS="$BATS_TEST_TMPDIR/rows.tsv"
+    OUT="$BATS_TEST_TMPDIR/plan.tsv"
+    EXC="$BATS_TEST_TMPDIR/exceptions.txt"
+
+    # A discography pack: the artist's own albums buried under "01. Albums",
+    # with a lyric, a cover, an EAC log and a playlist beside the tracks.
+    A="$MUSIC/Artist One - Discography [FLAC]/01. Albums/Album X"
+    at "$A/01. First.flac" 9000
+    at "$A/02. Second.flac" 9000
+    at "$A/01. First.lrc" 10
+    at "$A/cover.jpg" 20
+    at "$A/rip.log" 10
+    at "$A/Album X.m3u" 10
+
+    # A multi-disc compilation: one album (the album artist is the compilation
+    # tag), two discs, and a different performer on each track.
+    B="$MUSIC/Box (2019)"
+    at "$B/Disc 1/01 Track A.flac" 9000
+    at "$B/Disc 2/01 Track B.flac" 9000
+
+# The box cover lies above the two disc folders: the discs below it own it.
+at "$B/box.jpg" 10
+
+    # One image plus its cuesheet: a whole album in one file.
+    C="$MUSIC/Image Cue"
+    at "$C/Image.flac" 9000
+    at "$C/Image.cue" 10
+
+    # The hard cases: no row at all, a video container, two tracks claiming one
+    # number and one title, a track with no number, and a track whose album
+    # artist tag is empty so only the performer names it.
+    D="$MUSIC/Odd"
+    at "$D/loose.flac" 9000
+    at "$D/concert.mkv" 9000
+    at "$D/dup1.flac" 9000
+    at "$D/dup2.flac" 9000
+    at "$D/unnumbered.flac" 9000
+    at "$D/lone.flac" 9000
+
+    # A sidecar in a folder that holds two different albums.
+    E="$MUSIC/Mixed"
+    at "$E/one.flac" 9000
+    at "$E/two.flac" 9000
+    at "$E/notes.pdf" 10
+
+    # An album title carrying a character Jellyfin says breaks playback.
+    F="$MUSIC/Question Mark"
+    at "$F/01. Bang.flac" 9000
+
+    # An album whose tags name no album artist at all, and two different
+    # performers; and one album title carried by two different album artists.
+    G="$MUSIC/Tagless"
+    at "$G/one.flac" 9000
+    at "$G/two.flac" 9000
+    H="$MUSIC/Same Title"
+    at "$H/a.flac" 9000
+    at "$H/b.flac" 9000
+
+    # One album whose tracks disagree on the spelling of its name; the minority
+    # spelling sorts first, so it must not win the folder.
+    I="$MUSIC/Puppets"
+    at "$I/one.flac" 9000
+    at "$I/two.flac" 9000
+    at "$I/three.flac" 9000
+
+    # The authority export carries a header; the planner reads it by column name.
+    printf 'file\tartist\talbum\tyear\tdisc\ttrack\ttitle\tmb\tperformer\n' > "$ROWS"
+    row "$A/01. First.flac" "Artist One" "Album X" 2015 1 1 "First Song"
+    row "$A/02. Second.flac" "Artist One" "Album X" 2015 1 2 "Second Song: Reprise"
+    row "$B/Disc 1/01 Track A.flac" "Various Artists" "Best Of" 2019 1 1 "Track A" \
+        "" "Aaa Singer"
+    row "$B/Disc 2/01 Track B.flac" "Various Artists" "Best Of" 2019 2 1 "Track B" \
+        "" "Bbb Singer"
+    row "$C/Image.flac" "Solo" "Single Album" 2001 1 1 "Single Album"
+    row "$D/dup1.flac" "Dup Artist" "Dupes" "" "" 1 "Same"
+    row "$D/dup2.flac" "Dup Artist" "Dupes" "" "" 1 "Same"
+    row "$D/unnumbered.flac" "No Number" "No Number Album" "" "" "" "Untitled"
+    row "$D/lone.flac" "" "Session Works" "" "" 1 "Lone" "" "Session Singer"
+    row "$E/one.flac" "Mix Artist" "First Set" 2000 "" 1 "One"
+    row "$E/two.flac" "Mix Artist" "Second Set" 2001 "" 1 "Two"
+    row "$F/01. Bang.flac" "Billie" "WHEN WE ALL FALL ASLEEP, WHERE DO WE GO?" \
+        2019 "" 1 "!!!!!!"
+    row "$G/one.flac" "" "Two Seasons" 2005 "" 1 "One" "" "Alpha Band"
+    row "$G/two.flac" "" "Two Seasons" 2005 "" 2 "Two" "" "Beta Band"
+    row "$H/a.flac" "Aaa Singer" "Same Title" 2011 "" 1 "A Song"
+    row "$H/b.flac" "Bbb Singer" "Same Title" 2011 "" 1 "B Song"
+    row "$I/one.flac" "Metallica" "Master Of Puppets" 2015 "" 1 "One"
+    row "$I/two.flac" "Metallica" "Master of Puppets" 2015 "" 2 "Two"
+    row "$I/three.flac" "Metallica" "Master of Puppets" 2015 "" 3 "Three"
+
+    # The enum TSV is what scripts/media-census.py enumerate writes: bytes, ext,
+    # path, no header.
+    python3 - "$MUSIC" "$ENUM" <<'PY'
+import os, sys
+root, out = sys.argv[1], sys.argv[2]
+with open(out, "w") as fh:
+    for dirpath, _dirs, files in os.walk(root):
+        for fn in files:
+            p = os.path.join(dirpath, fn)
+            fh.write(f"{os.path.getsize(p)}\t{os.path.splitext(fn)[1].lower()}\t{p}\n")
+PY
+}
+
+plan() {
+    run python3 "$PLAN" --root "$MUSIC" --enum "$ENUM" --rows "$ROWS" \
+        --out "$OUT" --exceptions "$EXC"
+    [ "$status" -eq 0 ] || echo "planner said: $output"
+}
+
+@test "the census exports the tag and provider row Jellyfin matched for a track" {
+    DB="$BATS_TEST_TMPDIR/jellyfin.db"
+    python3 - "$DB" <<'PY'
+import sqlite3, sys, uuid
+c = sqlite3.connect(sys.argv[1])
+c.execute("""create table BaseItems (Id, ParentId, Type, Name, Path, IndexNumber,
+                                      ParentIndexNumber, ProductionYear, Album,
+                                      AlbumArtists, Artists, Data)""")
+c.execute("""create table BaseItemProviders (ItemId, ProviderId, ProviderValue)""")
+AU = "MediaBrowser.Controller.Entities.Audio.Audio"
+AL = "MediaBrowser.Controller.Entities.Audio.MusicAlbum"
+aid, trk = str(uuid.uuid4()), "/data/Music/Pack/Album X/01. First.flac"
+c.execute("insert into BaseItems values (?,?,?,?,?,?,?,?,?,?,?,?)",
+          (aid, None, AL, "Album X", "/data/Music/Pack/Album X", None, None, 2015,
+           None, "Artist One", None, '{}'))
+c.execute("insert into BaseItemProviders values (?,?,?)",
+          (aid, "MusicBrainzReleaseGroup", "rg-1234"))
+c.execute("insert into BaseItems values (?,?,?,?,?,?,?,?,?,?,?,?)",
+          (str(uuid.uuid4()), aid, AU, "First Song", trk, 1, 1, 2015,
+           "album x (the tag)", "Artist One", "Artist One", '{}'))
+c.commit()
+PY
+    run python3 "$CENSUS" music --root "$BATS_TEST_TMPDIR/Music" --db "$DB" \
+        --out "$BATS_TEST_TMPDIR/exp.tsv"
+    [ "$status" -eq 0 ]
+    run head -1 "$BATS_TEST_TMPDIR/exp.tsv"
+    [ "${lines[0]}" = "file	artist	album	year	disc	track	title	mb	performer" ]
+    tail -1 "$BATS_TEST_TMPDIR/exp.tsv" \
+        | grep -q "^$BATS_TEST_TMPDIR/Music/Pack/Album X/01\. First\.flac	Artist One	Album X	2015	1	1	First Song	rg-1234	Artist One$"
+}
+
+@test "a track whose folder is no album item still exports from its own tags" {
+    DB="$BATS_TEST_TMPDIR/jellyfin.db"
+    python3 - "$DB" <<'PY'
+import sqlite3, sys, uuid
+c = sqlite3.connect(sys.argv[1])
+c.execute("""create table BaseItems (Id, ParentId, Type, Name, Path, IndexNumber,
+                                      ParentIndexNumber, ProductionYear, Album,
+                                      AlbumArtists, Artists, Data)""")
+c.execute("""create table BaseItemProviders (ItemId, ProviderId, ProviderValue)""")
+c.execute("insert into BaseItems values (?,?,?,?,?,?,?,?,?,?,?,?)",
+          (str(uuid.uuid4()), None, "MediaBrowser.Controller.Entities.Audio.Audio",
+           "Lone", "/data/Music/Pack/lone.flac", 1, None, None,
+           "Session Works", None, "Session Singer", '{}'))
+c.commit()
+PY
+    run python3 "$CENSUS" music --root "$BATS_TEST_TMPDIR/Music" --db "$DB" \
+        --out "$BATS_TEST_TMPDIR/exp.tsv"
+    [ "$status" -eq 0 ]
+    tail -1 "$BATS_TEST_TMPDIR/exp.tsv" \
+        | grep -q "^$BATS_TEST_TMPDIR/Music/Pack/lone\.flac	Session Singer	Session Works			1	Lone		Session Singer$"
+}
+
+@test "a tagged track files under artist, album and year with a numbered title" {
+    plan
+    [ "$status" -eq 0 ]
+    [ "$(dst "$A/01. First.flac")" = "$MUSIC/Artist One/Album X (2015)/01 - First Song.flac" ]
+}
+
+@test "the tag title wins over the name the ripper gave the file" {
+    plan
+    [ "$(dst "$A/02. Second.flac")" = "$MUSIC/Artist One/Album X (2015)/02 - Second Song Reprise.flac" ]
+}
+
+@test "a character Jellyfin says breaks playback never reaches a destination" {
+    plan
+    [ "$(dst "$F/01. Bang.flac")" = "$MUSIC/Billie/WHEN WE ALL FALL ASLEEP, WHERE DO WE GO (2019)/01 - !!!!!!.flac" ]
+    run awk -F '\t' '$1 == "move" && $3 ~ /[<>:"|?*]/ {print $3}' "$OUT"
+    [ -z "$output" ]
+}
+
+@test "every disc of a multi-disc album lands in one folder, numbered apart" {
+    plan
+    [ "$(dst "$B/Disc 1/01 Track A.flac")" = "$MUSIC/Various Artists/Best Of (2019)/1.01 - Track A.flac" ]
+    [ "$(dst "$B/Disc 2/01 Track B.flac")" = "$MUSIC/Various Artists/Best Of (2019)/2.01 - Track B.flac" ]
+}
+
+@test "an album whose tracks name several artists files under Various Artists" {
+    plan
+    run awk -F '\t' '$1 == "move" && $3 ~ /\/Best Of \(2019\)\/.*\.flac$/ {print $3}' "$OUT"
+    [ "${#lines[@]}" -eq 2 ]
+    [[ "${lines[0]}" == "$MUSIC/Various Artists/"* ]]
+}
+
+@test "an album with no album artist and two performers is a compilation" {
+    plan
+    [ "$(dst "$G/one.flac")" = "$MUSIC/Various Artists/Two Seasons (2005)/01 - One.flac" ]
+    [ "$(dst "$G/two.flac")" = "$MUSIC/Various Artists/Two Seasons (2005)/02 - Two.flac" ]
+}
+
+@test "the same album title under two album artists is two albums" {
+    plan
+    [ "$(dst "$H/a.flac")" = "$MUSIC/Aaa Singer/Same Title (2011)/01 - A Song.flac" ]
+    [ "$(dst "$H/b.flac")" = "$MUSIC/Bbb Singer/Same Title (2011)/01 - B Song.flac" ]
+}
+
+@test "the folder carries the album spelling most tracks carry" {
+    plan
+    [ "$(dst "$I/one.flac")" = "$MUSIC/Metallica/Master of Puppets (2015)/01 - One.flac" ]
+    [ "$(dst "$I/two.flac")" = "$MUSIC/Metallica/Master of Puppets (2015)/02 - Two.flac" ]
+    [ "$(dst "$I/three.flac")" = "$MUSIC/Metallica/Master of Puppets (2015)/03 - Three.flac" ]
+}
+
+@test "a lyric file is renamed to match the track it belongs to" {
+    plan
+    [ "$(dst "$A/01. First.lrc")" = "$MUSIC/Artist One/Album X (2015)/01 - First Song.lrc" ]
+}
+
+@test "the album image, the rip log and the playlist follow the album folder" {
+    plan
+    [ "$(dst "$A/cover.jpg")" = "$MUSIC/Artist One/Album X (2015)/cover.jpg" ]
+    [ "$(dst "$A/rip.log")" = "$MUSIC/Artist One/Album X (2015)/rip.log" ]
+    [ "$(dst "$A/Album X.m3u")" = "$MUSIC/Artist One/Album X (2015)/Album X.m3u" ]
+}
+
+@test "a cover above the disc folders of one album follows that album" {
+    plan
+    [ "$(dst "$B/box.jpg")" = "$MUSIC/Various Artists/Best Of (2019)/box.jpg" ]
+}
+
+@test "an image carrying a whole album keeps its own name beside its cuesheet" {
+    plan
+    [ "$(dst "$C/Image.flac")" = "$MUSIC/Solo/Single Album (2001)/Image.flac" ]
+    [ "$(dst "$C/Image.cue")" = "$MUSIC/Solo/Single Album (2001)/Image.cue" ]
+}
+
+@test "an audio file no provider row names is parked, not filed under an artist" {
+    plan
+    [[ "$(dst "$D/loose.flac")" == "$PARK/Odd/loose.flac" ]]
+}
+
+@test "a video container in the music library is parked, never renamed to an audio one" {
+    plan
+    [[ "$(dst "$D/concert.mkv")" == "$PARK/Odd/concert.mkv" ]]
+    run awk -F '\t' '$1 == "move" && $3 ~ /\.mka$|\.m4a$/ {print $3}' "$OUT"
+    [ -z "$output" ]
+}
+
+@test "two tracks claiming one number and one title get two destinations" {
+    plan
+    [ "$(dst "$D/dup1.flac")" = "$MUSIC/Dup Artist/Dupes/01 - Same.flac" ]
+    [ "$(dst "$D/dup2.flac")" = "$MUSIC/Dup Artist/Dupes/01 - Same (2).flac" ]
+}
+
+@test "an album with no year is named without one, a track with no number likewise" {
+    plan
+    [ "$(dst "$D/unnumbered.flac")" = "$MUSIC/No Number/No Number Album/Untitled.flac" ]
+}
+
+@test "a track naming only a performer files under that performer" {
+    plan
+    [ "$(dst "$D/lone.flac")" = "$MUSIC/Session Singer/Session Works/01 - Lone.flac" ]
+}
+
+@test "a sidecar in a folder holding two albums parks instead of guessing" {
+    plan
+    [[ "$(dst "$E/notes.pdf")" == "$PARK/Mixed/notes.pdf" ]]
+}
+
+@test "the plan creates every folder before the move that needs it" {
+    plan
+    python3 - "$OUT" "$MUSIC" <<'PY'
+import os, sys
+made = set()
+for line in open(sys.argv[1]).read().splitlines()[1:]:
+    action, _src, dest, _kind = line.split("\t")
+    if action == "mkdir":
+        made.add(dest)
+    elif action == "move":
+        parent = os.path.dirname(dest)
+        while parent and parent != sys.argv[2]:
+            assert parent in made, f"{dest} needs {parent}, which is never made"
+            parent = os.path.dirname(parent)
+PY
+}
+
+@test "no move lands outside the music library" {
+    plan
+    run awk -F '\t' -v l="$MUSIC" \
+        '$1 == "move" && $3 !~ "^" l "/" {print $3}' "$OUT"
+    [ -z "$output" ]
+}
+
+@test "the executor preflights the plan and no target is claimed twice" {
+    plan
+    run python3 "$APPLY" apply --plan "$OUT" --root "$BATS_TEST_TMPDIR" \
+        --journal "$BATS_TEST_TMPDIR/journal.jsonl"
+    [ "$status" -eq 0 ]
+    dup=$(awk -F '\t' '$1 == "move" {print $3}' "$OUT" | sort | uniq -d)
+    [ -z "$dup" ]
+}
+
+@test "re-planning a library the plan already satisfies moves nothing" {
+    plan
+    # Applying the plan and re-censusing is what the operator does next: both
+    # authority files are keyed by path, so both are replayed through the plan
+    # the way a fresh census of the moved tree would see them. (The enum has no
+    # header; the rows export does, and its header row is not a path.)
+    python3 - "$OUT" "$ENUM" "$ROWS" <<'PY'
+import os, sys
+plan = sys.argv[1]
+moves = {}
+for line in open(plan).read().splitlines()[1:]:
+    action, src, dest, _kind = line.split("\t")
+    if action == "move":
+        moves[src] = dest
+        os.makedirs(os.path.dirname(dest), exist_ok=True)
+        os.rename(src, dest)
+for path, col in ((sys.argv[2], 2), (sys.argv[3], 0)):
+    rows = [line.rstrip("\n").split("\t") for line in open(path)]
+    with open(path, "w") as fh:
+        for f in rows:
+            f[col] = moves.get(f[col], f[col])
+            fh.write("\t".join(f) + "\n")
+PY
+    plan
+    run awk -F '\t' '$1 == "move" {print $2 " -> " $3}' "$OUT"
+    [ -z "$output" ] || { echo "moved again: $output"; false; }
+}