scripts/media-audiobooks.py

@@ -35,11 +35,11 @@ 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 — and so
+ * Nothing is guessed at. A chapter row with no book or no narrator parks — a
-   does one whose names are a tag-scan placeholder (`[Unknown Album]`), which
+   tag-scan placeholder (`[Unknown Album]`) names neither, since unrelated books
-   unrelated books share: filing on it would merge them onto one shelf. An audio
+   share it and filing on one merges them, and so does a chapter number the ripper
-   file Plex never matched parks, a video container parks, and a loose file in a
+   mistagged as the artist (`0.4`). An audio file Plex never matched parks, a
-   folder holding two books parks: nothing says which book owns it.
+   video container parks, and a loose file in a folder holding two books parks.
 
 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
@@ -75,15 +75,21 @@ PLACEHOLDER_NARRATOR = {"[unknown artist]", "unknown artist", "unknown author",
                         "<unknown>", "[unknown]", "unknown"}
 
 
-def identity(value, placeholders):
+def identity(value, placeholders, needs_letter=False):
     """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)`).
+
+    `needs_letter` is for a NARRATOR alone: a shelf is a person's name, and 272
+    chapters here carry a chapter number in the artist tag (`0.4`, `31`). The same
+    test must never judge a BOOK title, which may honestly be `1984`.
     """
     v = (value or "").strip()
     bare = re.sub(r"\s*\([^()]*\)\s*$", "", v).strip().casefold()
-    return "" if bare in placeholders else v
+    if bare in placeholders or (needs_letter and not any(c.isalpha() for c in v)):
+        return ""
+    return v
 
 
 # The characters Plex documents as breaking playback. They are dropped, not
@@ -197,7 +203,7 @@ 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 = identity(r["narrator"], PLACEHOLDER_NARRATOR)
+        narrator = identity(r["narrator"], PLACEHOLDER_NARRATOR, needs_letter=True)
         book = identity(r["book"], PLACEHOLDER_BOOK)
         if not book:
             park(path, "a chapter row that names no book — Plex's album title is a "
@@ -205,9 +211,9 @@ def group_books():
                        "merge unrelated books onto one shelf")
             continue
         if not narrator:
-            park(path, "a chapter row that names no narrator — the album's artist "
+            park(path, "a chapter row that names no narrator — the artist row is a "
-                       "row is a placeholder like [Unknown Artist], so no shelf "
+                       "placeholder like [Unknown Artist] or a chapter number a "
-                       "owns it")
+                       "ripper mistagged as the 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],

serverAppConfigs-docs/Dankserver/Media Relayout.md

@@ -352,9 +352,9 @@ Two laws are forced by what 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 names
-**no book or no narrator**, placeholder included (`[Unknown Album]`, `no title`,
+**no book or no narrator**: a placeholder (`[Unknown Album]`, `[Unknown Artist]`)
-`[Unknown Artist]`): unrelated books share those strings, so filing on one merges
+that unrelated books share, or a chapter number mistagged as the artist (`0.4`).
-them. `Various Artists` is not a placeholder — that is a multi-cast read.
+`Various Artists` is not a placeholder — that is a multi-cast read.
 
 ## Laws
 

tests/media_audiobooks.bats

@@ -142,6 +142,10 @@ setup() {
     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 "$H/Multicast/Genesis.mp3" "Various Artists" "The Bible" "" 1 "Genesis"
+    at "$H/Numbered/01 - Grimoire.mp3" 9000
+    at "$H/Digits/1984.mp3" 9000
+    row "$H/Numbered/01 - Grimoire.mp3" "0.4" "Grimoire of the Lamb" "" 1 "One"
+    row "$H/Digits/1984.mp3" "Ann Reader" "1984" 1949 1 "One"
 
     # The enum TSV is what scripts/media-census.py enumerate writes: bytes, ext,
     # path, no header.
@@ -358,6 +362,16 @@ PY
         "$AB/Various Artists/The Bible/Genesis.mp3" ]
 }
 
+@test "a chapter number mistagged as the narrator parks" {
+    plan
+    [ "$(kind "$H/Numbered/01 - Grimoire.mp3")" = "park" ]
+}
+
+@test "a book whose title is digits still files, because only a name must have a letter" {
+    plan
+    [ "$(dst "$H/Digits/1984.mp3")" = "$AB/Ann Reader/1984 (1949)/1984.mp3" ]
+}
+
 @test "the row, not the extension, decides what a chapter is" {
     plan
     [ "$(kind "$G/NoExt/part01")" = "chapter" ]