scripts/media-audiobooks.py

@@ -35,7 +35,9 @@ by what the rows actually hold:
    rest. One rule that always resolves beats a shelf that is half author and half
    narrator; the author stays visible in the book folder's own name, which is the
    title Plex shows.
- * Nothing is guessed at. A chapter row with no book or no narrator parks, an audio
+ * Nothing is guessed at. A chapter row with no book or no narrator parks — and so
+   does one whose names are a tag-scan placeholder (`[Unknown Album]`), which
+   unrelated books share: filing on it would merge them onto one shelf. An audio
    file Plex never matched parks, a video container parks, and a loose file in a
    folder holding two books parks: nothing says which book owns it.
 
@@ -59,6 +61,31 @@ AUDIO_EXT = {".mp3", ".m4a", ".m4b", ".ogg", ".oga", ".opus", ".wav", ".flac",
 VIDEO_EXT = {".mkv", ".mp4", ".webm", ".avi", ".mov", ".mpg", ".mpeg", ".ts",
              ".m2ts", ".vob", ".ifo", ".wmv", ".iso", ".img", ".bdmv", ".ogm",
              ".divx"}
+
+# Tag-scan placeholders. These strings are not identities: 1,106 chapters from
+# 14 unrelated top-level folders carry the album `[Unknown Album]`, so filing on
+# them would merge books that have nothing to do with each other — the exact
+# shape this relayout exists to make impossible. Such a chapter parks with the
+# path it has today and the fix belongs in its tags. `Various Artists` is NOT a
+# placeholder: that is what a multi-cast read carries, and the one book here
+# with 1,189 chapters under it is genuinely one book.
+PLACEHOLDER_BOOK = {"[unknown album]", "unknown album", "no title", "untitled",
+                    "[untitled]", "unknown title", "n/a", "-"}
+PLACEHOLDER_NARRATOR = {"[unknown artist]", "unknown artist", "unknown author",
+                        "<unknown>", "[unknown]", "unknown"}
+
+
+def identity(value, placeholders):
+    """The tag value Plex matched, when it names something; '' when it does not.
+
+    A trailing parenthesized group is stripped for the test only, because rippers
+    glue timestamps to the placeholder (`Unknown album (03/03/2015 21:39:55)`).
+    """
+    v = (value or "").strip()
+    bare = re.sub(r"\s*\([^()]*\)\s*$", "", v).strip().casefold()
+    return "" if bare in placeholders else v
+
+
 # The characters Plex documents as breaking playback. They are dropped, not
 # substituted: a replacement character is a guess at what the title meant.
 BAD_CHARS = set('<>:"/\\|?*')
@@ -170,15 +197,17 @@ def group_books():
         d = os.path.dirname(path)
         AUDIO_BY_DIR[d].add(path)
         CHILD_OF[os.path.dirname(d)].add(d)   # so a cover above Part 1/Part 2 sees both
-        narrator = (r["narrator"] or "").strip()
+        narrator = identity(r["narrator"], PLACEHOLDER_NARRATOR)
-        book = (r["book"] or "").strip()
+        book = identity(r["book"], PLACEHOLDER_BOOK)
         if not book:
-            park(path, "a chapter row no book names — Plex has the file but no "
+            park(path, "a chapter row that names no book — Plex's album title is a "
-                       "album item to put it in")
+                       "placeholder like [Unknown Album], so filing on it would "
+                       "merge unrelated books onto one shelf")
             continue
         if not narrator:
-            park(path, "a chapter row no narrator names — the book has no artist "
+            park(path, "a chapter row that names no narrator — the album's artist "
-                       "row, so no shelf owns it")
+                       "row is a placeholder like [Unknown Artist], so no shelf "
+                       "owns it")
             continue
         key = (narrator.casefold(), book.casefold(), (r["year"] or "").strip())
         g = BOOKS.setdefault(key, {"narrators": [], "books": [], "year": key[2],
@@ -191,9 +220,15 @@ def group_books():
 
 
 def book_folder(g):
-    name = safe(dominant(g["books"])) or "Untitled"
+    """The shelf Plex's own rows name: <narrator>/<book> (<year>). None when a
-    return os.path.join(ARGS.root, safe(dominant(g["narrators"])) or "Unknown Narrator",
+    name is made of characters no path can hold — inventing a shelf is filing it
-                        f"{name} ({g['year']})" if g["year"] else name)
+    wrong, so those chapters park instead."""
+    narrator = safe(dominant(g["narrators"]))
+    book = safe(dominant(g["books"]))
+    if not narrator or not book:
+        return None
+    return os.path.join(ARGS.root, narrator,
+                        f"{book} ({g['year']})" if g["year"] else book)
 
 
 def place_books():
@@ -201,6 +236,11 @@ def place_books():
     for key in sorted(BOOKS):
         g = BOOKS[key]
         folder = book_folder(g)
+        if folder is None:
+            for path in sorted(g["members"]):
+                park(path, "a book or narrator Plex spells with characters no "
+                           "folder name can hold")
+            continue
         for path in sorted(g["members"]):
             ext = HELD[path][1]
             base = os.path.splitext(os.path.basename(path))[0]

serverAppConfigs-docs/Dankserver/Media Relayout.md

@@ -336,8 +336,7 @@ The group is the identity Plex asserts in its own database — **(narrator, book
 year)** — so one book arriving in four part folders becomes one folder, and a
 1965 and a 2020 recording that share a title stay two books.
 
-Two laws here are the opposite of the music arm's, and both are forced by what
+Two laws are forced by what the rows actually hold:
-the rows actually hold:
 
 +- **A chapter is never renumbered.** Most books contain chapters whose index Plex
   does not know, so a number written into a name would be invented — and it would
@@ -352,8 +351,10 @@ the rows actually hold:
 
 What it refuses, the music arm's list with one addition: a video container, audio
 no chapter row names, and a loose file in a folder holding two books all park under
-`_unsorted` with the path they have today — and so does a chapter whose row has
+`_unsorted` with the path they have today — and so does a chapter whose row names
-**no book or no narrator**, because inventing a shelf is filing it wrong.
+**no book or no narrator**, placeholder included (`[Unknown Album]`, `no title`,
+`[Unknown Artist]`): unrelated books share those strings, so filing on one merges
+them. `Various Artists` is not a placeholder — that is a multi-cast read.
 
 ## Laws
 

tests/media_audiobooks.bats

@@ -126,6 +126,23 @@ setup() {
     at "$G/NoExt/part01" 9000
     row "$G/NoExt/part01" "Archivist" "Tapes" 1971 1 "Tape One"
 
+    # Tag-scan placeholders. Two unrelated books whose album rows both read
+    # `[Unknown Album]`: the name is shared, so filing on it would merge books
+    # that have nothing to do with each other. A rip timestamp can be glued to
+    # the placeholder, and a multi-cast read says `Various Artists` — which IS a
+    # narrator.
+    H="$AB/Packs"
+    at "$H/Stross/Ship/c1.mp3" 9000
+    at "$H/Leckie/State/c1.mp3" 9000
+    at "$H/Rip/tape.mp3" 9000
+    at "$H/NoWho/Real Book.mp3" 9000
+    at "$H/Multicast/Genesis.mp3" 9000
+    row "$H/Stross/Ship/c1.mp3" "Various Artists" "[Unknown Album]" "" 1 "Part 1"
+    row "$H/Leckie/State/c1.mp3" "Various Artists" "[Unknown Album]" "" 1 "Part 1"
+    row "$H/Rip/tape.mp3" "Ann Reader" "Unknown album (03/03/2015 21:39:55)" "" 1 "One"
+    row "$H/NoWho/Real Book.mp3" "[Unknown Artist]" "A Named Book" 2001 1 "One"
+    row "$H/Multicast/Genesis.mp3" "Various Artists" "The Bible" "" 1 "Genesis"
+
     # The enum TSV is what scripts/media-census.py enumerate writes: bytes, ext,
     # path, no header.
     python3 - "$AB" "$ENUM" <<'PY'
@@ -319,6 +336,28 @@ PY
     [ "$(kind "$G/blank narrator.mp3")" = "park" ]
 }
 
+@test "books that share a placeholder album name never share a shelf" {
+    plan
+    [ "$(dst "$H/Stross/Ship/c1.mp3")" = "$PARK/Packs/Stross/Ship/c1.mp3" ]
+    [ "$(dst "$H/Leckie/State/c1.mp3")" = "$PARK/Packs/Leckie/State/c1.mp3" ]
+}
+
+@test "a placeholder with a rip timestamp glued to it is still a placeholder" {
+    plan
+    [ "$(kind "$H/Rip/tape.mp3")" = "park" ]
+}
+
+@test "a narrator placeholder parks even when the book is named" {
+    plan
+    [ "$(kind "$H/NoWho/Real Book.mp3")" = "park" ]
+}
+
+@test "Various Artists is a multi-cast narrator and files its book" {
+    plan
+    [ "$(dst "$H/Multicast/Genesis.mp3")" = \
+        "$AB/Various Artists/The Bible/Genesis.mp3" ]
+}
+
 @test "the row, not the extension, decides what a chapter is" {
     plan
     [ "$(kind "$G/NoExt/part01")" = "chapter" ]