From 701b05a75d0bed4406a88f1814950c5f02a3ff6f Mon Sep 17 00:00:00 2001
From: dschlueter <dschlueter@kitux.de>
Date: Wed, 29 Apr 2026 07:58:41 +0200
Subject: [PATCH] Fix Jellyfin playlist integration and tracklist matching for
 single-CD albums
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- hint_extractor: add _normalize_vertical_tracklist() to handle bare-number/
  title/duration format (Tufaranka-style tracklists)
- hint_extractor: fix level-1 tracklist match — allow disc_num=None (single-CD)
  by assuming disc=1; previously no tracklist title was ever applied to single-
  CD tracks because the guard required disc_num to be set
- music_enricher: register module in sys.modules before exec_module() so
  @dataclass definitions in jellyfin_playlist_generator work correctly

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 hint_extractor.py | 58 +++++++++++++++++++++++++++++++++++++++++++----
 music_enricher.py |  1 +
 2 files changed, 55 insertions(+), 4 deletions(-)

diff --git a/hint_extractor.py b/hint_extractor.py
index a5dcced..cfcb0ff 100755
--- a/hint_extractor.py
+++ b/hint_extractor.py
@@ -138,7 +138,56 @@ def _read_tags(path: Path) -> Tuple[Dict[str, str], Optional[float]]:
         return {}, None
 
 
+_STANDALONE_NUM_RE = re.compile(r"^\d{1,3}$")
+_DURATION_ONLY_RE  = re.compile(r"^\d{1,2}:\d{2}$")
+
+
+def _normalize_vertical_tracklist(text: str) -> Optional[str]:
+    """
+    Erkennt 'vertikales' Format:
+      1
+      Katka dovádí
+      3:22
+      2
+      Záludná
+    → konvertiert zu '1. Katka dovádí  3:22\\n2. Záludná ...'
+    """
+    non_empty = [l.strip() for l in text.splitlines() if l.strip()]
+    # Mindestens 3 Standalone-Zahlen als Heuristik
+    num_lines = sum(1 for l in non_empty if _STANDALONE_NUM_RE.match(l))
+    if num_lines < 3:
+        return None
+
+    result = []
+    i = 0
+    while i < len(non_empty):
+        line = non_empty[i]
+        if _STANDALONE_NUM_RE.match(line) and i + 1 < len(non_empty):
+            title_candidate = non_empty[i + 1]
+            # Nächste Zeile darf selbst keine Zahl und keine Dauer sein
+            if not _STANDALONE_NUM_RE.match(title_candidate) and not _DURATION_ONLY_RE.match(title_candidate):
+                duration = ""
+                skip = 2
+                if i + 2 < len(non_empty) and _DURATION_ONLY_RE.match(non_empty[i + 2]):
+                    duration = non_empty[i + 2]
+                    skip = 3
+                entry = f"{line}. {title_candidate}"
+                if duration:
+                    entry += f"  {duration}"
+                result.append(entry)
+                i += skip
+                continue
+        i += 1
+
+    return "\n".join(result) if len(result) >= 3 else None
+
+
 def _parse_tracklist(text: str) -> List[Dict[str, str]]:
+    # Vertikales Format normalisieren bevor das reguläre Parsing läuft
+    normalized = _normalize_vertical_tracklist(text)
+    if normalized:
+        text = normalized
+
     tracks: List[Dict[str, str]] = []
     current_disc = 1
 
@@ -522,13 +571,14 @@ def extract_hints(scan: AlbumScan, use_ocr: bool = True) -> AlbumHints:
         if parsed_tracklist:
             matched_tl: Optional[Dict[str, str]] = None
 
-            # 1. Exakt per Tracknummer + Disc (nur wenn beides aus Tag/Dateiname bekannt)
-            if track_num and disc_num:
+            # 1. Exakt per Tracknummer + Disc (disc_num=None → Single-CD, assume 1)
+            if track_num:
+                assumed_disc = disc_num if disc_num else 1
                 for tl_entry in parsed_tracklist:
                     tl_track = tl_entry.get("track")
-                    tl_disc = tl_entry.get("disc", "1")
+                    tl_disc = int(tl_entry.get("disc", "1"))
                     if (tl_track and int(tl_track) == track_num
-                            and int(tl_disc) == disc_num):
+                            and tl_disc == assumed_disc):
                         matched_tl = tl_entry
                         break
 
diff --git a/music_enricher.py b/music_enricher.py
index d2ac0b4..a8d6355 100755
--- a/music_enricher.py
+++ b/music_enricher.py
@@ -55,6 +55,7 @@ def _run_jellyfin_generator(album_dir: Path, generator_path: Path) -> None:
     try:
         spec = importlib.util.spec_from_file_location("jellyfin_pg", generator_path)
         mod = importlib.util.module_from_spec(spec)  # type: ignore[arg-type]
+        sys.modules["jellyfin_pg"] = mod   # muss vor exec_module stehen (für @dataclass)
         spec.loader.exec_module(mod)  # type: ignore[union-attr]
 
         media_files = mod.collect_media_recursive(album_dir)