Merge pull request 'fix(media): the series is the name before the marker; a sweep carries its own empty subfolders' (#95) from fix/media-series-key into main

scripts/media-apply.py

@@ -241,6 +241,11 @@ def sweep_targets(root, journal):
     journalled destination lives under it. A symlink anywhere inside disqualifies
     the whole subtree: this tool never follows a link, and deleting the folder
     that holds one would delete someone's mount point.
+
+    Proof carries downward: once a folder qualifies, every empty directory inside
+    it qualifies too. A release's junk (``Screens/``, ``Sample/``) is never itself
+    a move source, so without that rule it holds its emptied parent on disk
+    forever — the parent can never be removed while the child stands.
     """
     moves = [r for r in journal.records if r.get("op") == "move"]
     made = {r["dst"] for r in journal.records if r.get("op") == "mkdir"}
@@ -268,8 +273,15 @@ def sweep_targets(root, journal):
                 return False
         return True
 
-    return sorted((d for d in marked if removable(d)),
-                  key=lambda q: (-q.count(os.sep), q))
+    roots = [d for d in marked if removable(d)]
+    targets = set(roots)
+    for d in roots:
+        for dirpath, dirnames, _ in os.walk(d):
+            for c in dirnames:
+                p = os.path.join(dirpath, c)
+                if removable(p):
+                    targets.add(p)
+    return sorted(targets, key=lambda q: (-q.count(os.sep), q))
 
 
 def do_sweep(args, root, journal):

scripts/media-plan.py

@@ -222,8 +222,9 @@ eps = collections.defaultdict(list)
 for r in erows:
     if r["path"] in marks | extras:
         continue
-    if eng.ep_of(r["path"]):
-        eps[eng.key_of(r["title"])].append(r)
+    ep = eng.ep_of(r["path"])
+    if ep:
+        eps[ep[0]].append(r)      # keyed by the SERIES, never the episode title
 tv_keys = {k for k, v in eps.items() if len(v) >= 5}
 tv_set = {r["path"] for k, v in eps.items() if k in tv_keys for r in v}
 # A folder INSIDE a movie's folder is bonus territory even when its own name is
@@ -776,19 +777,17 @@ readmes.append(f"README in {ROOT}: this library was relaid out into Jellyfin's "
                "one-folder-per-movie layout; `_release-group watermarks/`, "
                "`_unsorted files/` and `_unsorted bonus/` hold files no film claims.")
 for key in tv_keys:
-    nm = "_TV needs a TV library - " + collections.Counter(
-        r["title"] for r in eps[key]).most_common(1)[0][0]
-    readmes.append(f"README in {ROOT}/{sanitize(nm)}: these are TV episodes found in "
-                   "the MOVIES library; move the folder to a TV library source, else "
-                   "Jellyfin groups them wrongly as one movie.")
+    readmes.append(f"README in {ROOT}/{sanitize('_TV needs a TV library - ' + key)}: "
+                   "these are TV episodes found in the MOVIES library; move the folder "
+                   "to a TV library source, else Jellyfin groups them wrongly as one "
+                   "movie.")
 
 # --------------------------------------------------------------------- TV
 for key in tv_keys:
     items = eps[key]
-    title = collections.Counter(r["title"] for r in items).most_common(1)[0][0]
     year = collections.Counter(r["year"] for r in items if r["year"] != "?")
     yr = year.most_common(1)[0][0] if year else None
-    base = f"_TV needs a TV library - {sanitize(title)}" + (f" ({yr})" if yr else "")
+    base = f"_TV needs a TV library - {sanitize(key)}" + (f" ({yr})" if yr else "")
     tops = {parts_of(r["path"])[0] for r in items}
     members = sorted([r["path"] for r in items]
                      + [q for q in extras | marks if len(parts_of(q)) > 1

scripts/media-titles.py

@@ -322,13 +322,22 @@ def key_of(title):
 
 
 def ep_of(path):
-    """(show, episode-token) when the basename carries SxxEyy / 1x04 / Part N."""
+    """(series, episode-token) when the basename carries SxxEyy / 1x04 / Part N.
+
+    The series is the name BEFORE the marker. The box-set convention writes
+    "Monk - S05E03 - Mr. Monk and the Big Game", and the episode title that
+    follows the marker is not the show's name: keying on the whole title gave
+    every episode of one series its own group, so a 124-episode box set never
+    reached the size that calls something a series and each episode was filed
+    as its own film. A file named only by its marker has nothing before it, so
+    its whole title stands in."""
     name = os.path.splitext(os.path.basename(path))[0]
     m = EP_RE.search(name)
     if not m:
         return None
-    show, _ = title_of(path)
-    return show, norm(m.group(1)).replace(" ", "")
+    head = name[:m.start()].strip(" ._\u2013-")
+    series = title_of(head)[0] if head else None
+    return series or title_of(path)[0], norm(m.group(1)).replace(" ", "")
 
 
 def base_words(title, key):

serverAppConfigs-docs/Dankserver/Media Relayout.md

@@ -105,14 +105,10 @@ curl -s -K /tmp/jf.hdr -o /dev/null -w "jellyfin scan: %{http_code}\n" \
 
 ## Laws
 
-- **The journal lives beside the library, never in `/tmp`.** The live run's
-  `/mnt/entropy/media-relayout.jsonl` is the only rollback instrument; a journal
-  a reboot clears is not an instrument.
-- **An apply breaks [[Plex]] playback for every moved item until its section is
-  rescanned.** The database keeps the release-folder path, so streams fail
-  `Couldn't find the file to stream` while the scanner works through the section.
-  Trigger the scans in the same window as the apply, and never read a 404 in that
-  window as a lost file — the file is where the journal says it is.
+- **A moved file is a 404 in [[Plex]] until its section is rescanned.** The
+  database keeps the release-folder path, so playback fails `Couldn't find the
+  file to stream` while the scanner works through the section. Never read such a
+  404 as a lost file: the file is where the journal says it is.
 - **Plex's matched title outranks the filename**, and a Plex year of `0` means
   *indexed but never matched* — trusting it named folders `Title (0)`, which is
   a Jellyfin item with no year, no poster and no identity. A year that is not a
@@ -159,6 +155,18 @@ curl -s -K /tmp/jf.hdr -o /dev/null -w "jellyfin scan: %{http_code}\n" \
   inside disqualifies the subtree, because the thing behind a link is not this
   tool's to delete. Every removal is journalled as `rmdir` and `rollback`
   recreates the folder, so the sweep is undone by the same command as the moves.
+  Proof carries downward: inside a folder the journal proves emptied, every
+  empty directory goes with it. A release's `Screens/` or `Sample/` is never a
+  move source itself, so 146 of them held their emptied parents on disk after
+  the first sweep.
+- **An episode-shaped name marks a SERIES, not a film — and the series is the
+  name BEFORE the marker.** `Monk - S05E03 - Mr. Monk and the Big Game` is series
+  `Monk`. Keyed on the whole title instead, every episode became a group of one
+  and never reached the five-episode size that calls something a series, so a
+  box set was filed as 124 movies in 124 folders. The threshold still earns its
+  keep: a lone film named `Part 2` stays a film. Episodes of a series are parked
+  in `_TV needs a TV library - <series>` for a human to move to a TV source —
+  the movie tool never files TV.
 
 ## Rollback
 

tests/media_relayout.bats

@@ -71,6 +71,20 @@ setup() {
     at "$LIB/Alien (1979)/._Alien.1979.1080p.BluRay.x265.10bit.mkv" 220
     # A bonus file whose name is a number: never a movie folder named "1".
     at "$LIB/Bruce Lee Collection 1971-1981/.Extra 1.mkv" 2700000
+    # A TV box set sitting in the movie library. This one names each file
+    # "Show - SxxEyy - Episode Title", so the episode title comes AFTER the
+    # marker; that convention is what made 124 episodes of one series look like
+    # 124 different films, each under its own threshold.
+    for e in 01 02 03 04 05; do
+        at "$LIB/Monk 2002 Seasons 1 to 8/Season 1/Monk - S01E$e - Mr Monk and the Rival.mkv" 3000000
+    done
+    # The same trouble named the other way round, with no episode title at all.
+    for e in 01 02 03 04 05; do
+        at "$LIB/Big Little Lies Season 1/Big Little Lies S01E$e.mp4" 3000000
+    done
+    # A film whose own name carries a bare "Part 2": one episode-shaped token is
+    # not a series, and it must not be dragged into the TV pile.
+    at "$LIB/The Godfather Part 2 (1974)/The.Godfather.Part.2.1974.1080p.BluRay.mkv" 9000000
 
     probe_row "$LIB/Alien (1979)/Alien.1979.1080p.BluRay.x265.10bit.mkv" 4700
     probe_row "$LIB/Alien (1979)/Featurettes/A Bug And A Bite - Making Alien.mkv" 2700
@@ -82,11 +96,18 @@ setup() {
     probe_row "$LIB/VHS 2 (2013)/VHS.2.2013.1080p.BluRay.x265.mkv" 5700
     probe_row "$LIB/AMERICAN POP/AMERICAN.POP.2023.1080p.WEB-DL.mkv" 6300
     probe_row "$LIB/Bruce Lee Collection 1971-1981/.Extra 1.mkv" 5220
+    for e in 01 02 03 04 05; do
+        probe_row "$LIB/Monk 2002 Seasons 1 to 8/Season 1/Monk - S01E$e - Mr Monk and the Rival.mkv" 2600
+        probe_row "$LIB/Big Little Lies Season 1/Big Little Lies S01E$e.mp4" 3300
+    done
+    probe_row "$LIB/The Godfather Part 2 (1974)/The.Godfather.Part.2.1974.1080p.BluRay.mkv" 6200
     plex_row "$LIB/Alien (1979)/Alien.1979.1080p.BluRay.x265.10bit.mkv" "Alien" "1979"
     plex_row "$LIB/Marnie (1964)/Marnie.1964.1080p.BluRay.x265.mkv" "Marnie" "1964"
     plex_row "$LIB/VHS 2 (2013)/VHS.2.2013.1080p.BluRay.x265.mkv" "V/H/S/2" "2013"
     # An unmatched Plex row: the leaf title echoes the file and the year is 0.
     plex_row "$LIB/AMERICAN POP/AMERICAN.POP.2023.1080p.WEB-DL.mkv" "AMERICAN POP" "0"
+    plex_row "$LIB/The Godfather Part 2 (1974)/The.Godfather.Part.2.1974.1080p.BluRay.mkv" \
+        "The Godfather Part 2" "1974"
 
     export MEDIA_ROOT="$LIB"
     run python3 "$CENSUS" enumerate --root "$LIB" --out "$ENUM"
@@ -191,6 +212,37 @@ for line in open(sys.argv[1]):
     grep -q "UNNAMED" "$EXC"
 }
 
+@test "a box set in the movie library is quarantined, not filed as movies" {
+    plan
+    local d
+    d="$(dst_of "$LIB/Monk 2002 Seasons 1 to 8/Season 1/Monk - S01E01 - Mr Monk and the Rival.mkv")"
+    [[ "$d" == "$LIB"/_TV\ needs\ a\ TV\ library\ -\ monk* ]]
+    d="$(dst_of "$LIB/Big Little Lies Season 1/Big Little Lies S01E01.mp4")"
+    [[ "$d" == "$LIB"/_TV\ needs\ a\ TV\ library\ -\ big\ little\ lies* ]]
+    # one series is one pile, whatever its episodes are called
+    run python3 -c '
+import re, sys
+pile = {}
+for line in open(sys.argv[1]):
+    f = line.rstrip("\n").split("\t")
+    if len(f) > 2 and f[0] == "move":
+        m = re.search(r"/_TV needs a TV library - ([^/]*)/", f[2] + "/")
+        if m:
+            pile[m.group(1)] = pile.get(m.group(1), 0) + 1
+for k in sorted(pile):
+    print(f"{k}={pile[k]}")
+' "$OUT"
+    [ "${#lines[@]}" -eq 2 ]
+    [[ "${lines[0]}" == big\ little\ lies*=5 ]]
+    [[ "${lines[1]}" == monk*=5 ]]
+}
+
+@test "a film named Part 2 is not called a series" {
+    plan
+    [ "$(dst_of "$LIB/The Godfather Part 2 (1974)/The.Godfather.Part.2.1974.1080p.BluRay.mkv")" \
+        = "$LIB/The Godfather Part 2 (1974)/The Godfather Part 2 (1974).mkv" ]
+}
+
 @test "every file in the census is placed or kept — nothing is dropped" {
     plan
     python3 - "$ENUM" "$OUT" <<'PY'
@@ -356,6 +408,17 @@ PY
     [ -d "$LIB/A Empty Placeholder" ]
 }
 
+@test "a swept folder carries the empty junk folders inside it" {
+    mkdir -p "$LIB/AMERICAN POP/Screens"   # screenshots, never a move source
+    plan
+    apply_plan
+    run python3 "$APPLY" sweep --root "$LIB" --journal "$JOURNAL" --apply
+    [ "$status" -eq 0 ]
+    [[ "$output" == *"0 left in place"* ]]
+    [ ! -e "$LIB/AMERICAN POP/Screens" ]
+    [ ! -e "$LIB/AMERICAN POP" ]
+}
+
 @test "sweep without --apply reports the husks and changes nothing" {
     plan
     apply_plan