Merge pull request 'fix(media): a number too long to be an episode is not one' (#107) from fix/episode-marker-guard into main

scripts/media-shows.py

@@ -168,12 +168,16 @@ SEASON_META = re.compile(r"^season\.nfo$", re.I)
 FOLDER_IMAGE = re.compile(r"^folder\.(jpg|jpeg|png|webp|bmp)$", re.I)
 SEASON_DIR_RE = re.compile(r"(?i)^\s*(?:season[\s._-]*(\d{1,3})|s(\d{1,2}))\s*$")
 BAD_CHARS = re.compile(r'[<>:"/|?*]')
-# SxxEyy with an optional second episode, plus the 1x04 form. The second number
-# is guarded so a resolution never reads as an episode: "S01E01-1080p" is ONE
-# episode, and the longest-match backtracking of \d{1,3} is what the (?![\dpP])
-# after it closes off.
+# SxxEyy with an optional second episode, plus the 1x04 form. Both episode numbers
+# are guarded so a longer digit run never reads as an episode. A resolution glued
+# on stays legal — "S01E01-1080p" is ONE episode — while "S03E2019" and
+# "S04E47370355" (both real names on the array, from a box set whose provider rows
+# say the same junk) state no episode at all: the run is an airdate or a pack
+# index, and the first three digits of it would steal E201 and E473 from the
+# episodes that own them. No marker means the file is numbered by its provider
+# row, or by tvdb's title, or it parks.
 EP_RANGE = re.compile(r"(?i)(?<![a-z0-9])s(?:eason[\s._-]*)?(\d{1,2})[\s._-]*"
-                      r"e(?:p(?:isode)[\s._-]*)?(\d{1,3})"
+                      r"e(?:p(?:isode)[\s._-]*)?(\d{1,3})(?![\dpP])"
                       r"(?:[\s._-]*(?:-|to[\s._-]*|ep)[\s._-]*(?:s\d{1,2}[\s._-]*)?e?"
                       r"(\d{1,3})(?![\dpP]))?")
 NX_RE = re.compile(r"(?i)(?<![a-z0-9])(\d{1,2})x(\d{2,3})(?![a-z0-9])")
@@ -201,6 +205,11 @@ EXTRA_KIND = {"trailer": "trailers", "tmbd": "trailers", "intro": "other",
               "deleted": "deleted scenes", "other": "other", "epilogue": "other",
               "opening": "other", "featurette": "featurettes", "short": "shorts"}
 SHORT_MAX = 45 * 60        # over this, a file with no episode evidence is film-shaped
+# An episode number above this is not an episode number: the array's box sets
+# carry 2019 (an airdate fragment) and 47370355 (a pack index) in the column the
+# metadata server recorded as the match. tvdb's episode list is the only door on
+# such a row; nothing files at E1000 or beyond.
+EP_MAX = 999
 
 
 def rel(p):
@@ -748,10 +757,11 @@ for r in video:
         else:
             season = fs if fs is not None else num(t["season"])
             ep = leading_index(r["base"]) or num(t["episode"])
-            if not 0 <= season <= 200 or ep <= 0:
+            if not 0 <= season <= 200 or not 1 <= ep <= EP_MAX:
                 # Season 0 IS a season: specials live in Season 00 by Jellyfin's own
-                # contract. A season that is a YEAR is the date matcher's doing, and
-                # the only authority on it is tvdb's episode list for the series.
+                # contract. A season that is a YEAR is the date matcher's doing and an
+                # episode above EP_MAX is a box set's airdate or pack index; neither is
+                # a number, and the only authority on either is tvdb's episode list.
                 recovered = tvdb_number(t)
                 if not recovered:
                     unknown.append(
@@ -1199,7 +1209,9 @@ def write_exceptions():
                 f"{n} S{'/'.join(f'{x:02d}' for x in ss)}"
                 for n, ss in clash[:300]) + "\n")
         map_ids = {e["id"] for e in MAP.values()}
-        unseen = sorted(f for f in MAP if f not in MAP_SEEN)
+        on_array = {rel(p).split("/")[0] for p in held}
+        stalled = sorted(f for f in MAP if f not in MAP_SEEN and f in on_array)
+        unseen = sorted(f for f in MAP if f not in MAP_SEEN and f not in on_array)
         unanswered = sorted({f"{identity(s)[0]} ({s['tvdb']})"
                              for s in canon.values()
                              if s.get("tvdb") in map_ids and not s.get("canon")})
@@ -1211,9 +1223,20 @@ def write_exceptions():
                      "       and re-plan, because a rename is idempotent.\n")
             fh.write("       " + "; ".join(
                 f"{f} -> {MAP[f]['id']}" for f in sorted(MAP_SEEN)) + "\n")
+        if stalled:
+            fh.write(f"\n{len(stalled):>6} map rows name a folder on the array that\n")
+            fh.write("       never became a series: every file in it parked, so the id\n"
+                     "       had nothing to name. The map names a RECORD — it numbers\n"
+                     "       no episodes and owns no bonus material, so read the park\n"
+                     "       reasons above this line: a folder of openings, endings and\n"
+                     "       promos with no show to claim them is the usual shape.\n")
+            fh.write("       " + "; ".join(
+                f"{f} -> {MAP[f]['id']}" for f in stalled[:300]) + "\n")
         if unseen:
             fh.write(f"\n{len(unseen):>6} map rows name no folder on the array: the\n")
-            fh.write("       pack moved, or the row carries a name the array never held.\n")
+            fh.write("       pack moved (into the review pile counts: the map reads\n"
+                     "       top-level folders only), or the row carries a name the\n"
+                     "       array never held.\n")
             fh.write("       " + "; ".join(unseen[:300]) + "\n")
         if MAP_CLASH:
             fh.write(f"\n{len(MAP_CLASH):>6} folders carry a provider tvdb id the map\n")

serverAppConfigs-docs/Dankserver/Media Relayout.md

@@ -228,7 +228,10 @@ scripts/media-apply.py apply --plan /mnt/entropy/media-relayout-shows2-plan.tsv
 
 Evidence, strongest first — the order the planner believes things:
 
-- the **episode marker the file's own name states** (`S01E02-E03`, `1x04`);
+- the **episode marker the file's own name states** (`S01E02-E03`, `1x04`); a digit
+  run longer than three at that position is NOT a number — `S03E2019` and
+  `S04E47370355` are one box set's airdate fragment and pack index — so such a file
+  is renumbered by tvdb's title or parks, and is never truncated down to fit;
 - the **`Season NN` folder it sits in and the number its name leads with inside
   it**: `Season 19/01 Charles Barkley, Nirvana.avi` is S19E01;
 - the **provider row**: which episode the file IS, and the numbering of a file

tests/media_shows.bats

@@ -513,6 +513,46 @@ PY
     [[ "$output" == *"Best Of The Examples.mkv"* ]]
 }
 
+
+# A release pack can carry a number that is not an episode at all: two files of
+# the Attack on Titan box set on the array are named S03E2019 and S04E47370355,
+# and the provider rows the server recorded for them say the same junk. Reading
+# either as "the first three digits" files the box set under E201 and E473 and
+# steals those episode slots from their real owners, so a run too long to be an
+# episode is no marker and no number: the file is renumbered from tvdb's title
+# when the series' id answers it, and parks when nothing answers.
+@test "an episode number longer than three digits never files as an episode" {
+    file "$LIB/Junk Numbers/Attack Pack S03E2019.mkv" 5000
+    title_row "$LIB/Junk Numbers/Attack Pack S03E2019.mkv" "Attack Pack" 2013 3 2019
+    plan_park
+    run grep -c -- "- S03E201 -" "$OUT"
+    [ "$output" = "0" ]
+    [[ "$(dst "$LIB/Junk Numbers/Attack Pack S03E2019.mkv")" == "$OUTSIDE/"* ]]
+    grep -q "a provider row of season 3 episode 2019" "$EXC"
+}
+
+@test "a provider episode too long to be one is renumbered by the title tvdb states" {
+    printf '{"tvdb:series:4242": %s, "tvdb:episodes:4242": %s}\n' \
+        '{"name": "Attack Pack", "year": "2013"}' \
+        '{"3/7": "A Title tvdb Holds"}' > "$CACHE"
+    file "$LIB/Junk Numbers/Attack Pack S03E2019.mkv" 5000
+    title_row "$LIB/Junk Numbers/Attack Pack S03E2019.mkv" \
+        "Attack Pack" 2013 3 2019 "" "" "A Title tvdb Holds" "4242"
+    plan
+    want="$LIB/Attack Pack (2013) [tvdbid-4242]/Season 03"
+    want+="/Attack Pack (2013) - S03E07 - A Title tvdb Holds.mkv"
+    [ "$(dst "$LIB/Junk Numbers/Attack Pack S03E2019.mkv")" = "$want" ]
+}
+
+@test "a resolution glued to the marker still reads as one episode" {
+    file "$LIB/Junk Numbers/Glued Mark S01E02-1080p.mkv" 5000
+    title_row "$LIB/Junk Numbers/Glued Mark S01E02-1080p.mkv" \
+        "The Examples" 2010 1 2 "" "" "Second Look"
+    plan
+    [ "$(dst "$LIB/Junk Numbers/Glued Mark S01E02-1080p.mkv")" \
+        = "$LIB/The Examples (2010)/Season 01/The Examples (2010) - S01E02 - Second Look.mkv" ]
+}
+
 # Anime numbering is the one place a tvdb title can be confidently wrong: a pack
 # numbered by its release group still names S05E01, and tvdb answers that slot with
 # a different episode. A season the authority does not hold, or holds fewer of than
@@ -655,6 +695,20 @@ plan_map() {                          # the plan, with the operator's map in han
     [ "$status" -eq 0 ]
 }
 
+@test "a map row whose folder is on the array but never became a series says so" {
+    # The array holds three folders exactly like this one: a credits/extras pack
+    # the operator mapped to a record, whose every file is bonus material with no
+    # series to own it. The folder IS on the array, and telling the operator the
+    # pack moved sends them hunting for a folder that never left.
+    printf 'Credit Pack\t114801\tthe record tvdb names\n' > "$BATS_TEST_TMPDIR/ids.tsv"
+    file "$LIB/Credit Pack/01. Extras/NCOP 01.mkv" 1200
+    plan_map "$BATS_TEST_TMPDIR/ids.tsv"
+    grep -q "bonus material with no series to own it" "$EXC"
+    grep -q "never became a series" "$EXC"
+    run grep "no folder on the array" "$EXC"
+    [ "$status" -ne 0 ]
+}
+
 @test "a map line whose id is not a number stops the plan" {
     printf 'Black Clover 001\tnotanid\ttypo\n' > "$BATS_TEST_TMPDIR/ids.tsv"
     file "$LIB/Black Clover 001/Season 01/Black.Clover.001.mkv" 5000