refactor: extract audiobook parsing primitives

CHANGELOG.md

@@ -8,6 +8,8 @@ Follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) · versioned wi
 ## [Unreleased]
 
 ### Changed
+- **Audiobook parser extraction.** Dialogue detection, PDF dehyphenation, and shared speaker-heuristic constants now
+  live in `audiobook-parse.js`, loaded before the Audiobook casting workflow without changing its legacy API.
 - **Rehearser voice-picker extraction.** Voice preview state and matched voice-choice presentation now live in
   `rehearser-voice-picker.js`; matching, import, and assignment actions remain compatible with the existing cast API.
 - **Rehearser stage extraction.** Stage font scaling, cast-sidebar collapse state, cast filtering/sorting, and cast-strip

TODO.md

@@ -127,6 +127,7 @@ architecture change: the larger Audiobook/Rehearser/style split.
 - [x] Extract Rehearser voice-picker presentation and preview state into `rehearser-voice-picker.js`.
 - [x] Extract Rehearser library persistence and IndexedDB migration into `rehearser-library.js`.
 - [ ] Extract Audiobook parsing and casting.
+- [x] Extract Audiobook parsing primitives and speaker-heuristic constants into `audiobook-parse.js`.
 - [ ] Split `style.css` by feature.
 - [ ] Do not migrate to TypeScript or rewrite the frontend until behavior is covered by tests.
 

VERSION

@@ -1 +1 @@
-1.24.26
+1.24.27

docs/ARCHITECTURE.md

@@ -33,6 +33,7 @@ Done incrementally as global-scope ordered files (no ES-module change needed)
 - ⬜ `rehearser-cast.js` — `renderCastList`, sort/filter, online voice picker, character research.
 - ✅ `rehearser-stage.js` — stage font/cast sidebar controls and cast-strip rendering; playback and transport remain in `rehearser.js`.
 - ✅ `rehearser-voice-picker.js` — voice preview state and matched-choice presentation; import and assignment actions remain in `rehearser.js`.
+- ✅ `audiobook-parse.js` — dialogue detection, dehyphenation, and speaker-heuristic constants; the casting pipeline remains in `audiobook.js`.
 - ⬜ `rehearser-train.js` — mic record / STT compare.
 - ✅ `rehearser-library.js` — SQLite persistence helpers and IndexedDB migration; import/export and auto-save remain
   in `rehearser.js` until their UI/event-handler dependencies are isolated.

static/index.html

@@ -10,7 +10,7 @@
   <meta name="format-detection" content="telephone=no">
   <meta name="color-scheme" content="light dark">
   <meta name="theme-color" content="#2563EB">
-  <meta name="app-version" content="1.24.26">
+  <meta name="app-version" content="1.24.27">
   <link rel="manifest" href="/manifest.webmanifest">
   <link rel="icon" href="/static/icon.svg" type="image/svg+xml">
   <link rel="apple-touch-icon" href="/static/icon.svg">
@@ -27,7 +27,7 @@
 
   <!-- ── Core styles (local — no CDN dependency for first paint) ────────── -->
   <link rel="stylesheet" href="/static/vendor/mdi/materialdesignicons.min.css">
-  <link rel="stylesheet" href="/static/style.css?v=1.24.26">
+  <link rel="stylesheet" href="/static/style.css?v=1.24.27">
 
 
   <!-- ── Flag icons — non-blocking (loaded async, icons appear after JS) ── -->
@@ -392,7 +392,7 @@ window.toggleNavTree = function(treeId, chevronId) {
 </script>
 
 <!-- loader.js: fetches sections → loads JS modules → removes skeleton -->
-<script src="/static/loader.js?v=1.24.26"></script>
+<script src="/static/loader.js?v=1.24.27"></script>
 
 </body>
 </html>

static/js/audiobook-parse.js

@@ -0,0 +1,25 @@
+// ── Audiobook parsing primitives ────────────────────────────────────────────
+// Kept dependency-free so the Reader can load these helpers before the larger
+// audiobook casting workflow. The casting pipeline continues to use the same
+// legacy global function names during the incremental migration.
+
+const AB_DIALOGUE_RE = /[«»„“”"‟‚‘’『「<]|(?:^|\n)\s*[—–]\s/;
+function audiobookHasDialogue(t) { return AB_DIALOGUE_RE.test(t || ''); }
+
+function audiobookDehyphenate(t) {
+  return (t || '').replace(/([a-zäöüß])-\s+(?=[a-zäöüßA-ZÄÖÜ])/g, '$1');
+}
+
+const AB_SPEECH_VERBS = '(?:sagte|fragte|rief|antwortete|erwiderte|entgegnete|meinte|flüsterte|wisperte|raunte|murmelte|brummte|knurrte|brüllte|schrie|stammelte|fauchte|zischte|seufzte|lachte|kicherte|befahl|wiederholte|fuhr\\s+fort|grunzte|versetzte|unterbrach|drängte|herrschte|keuchte|hauchte|ächzte|stöhnte|jammerte|spottete|höhnte|warf\\s+ein|setzte\\s+hinzu|erklärte|verkündete|widersprach|beharrte|gestand|bestätigte|erinnerte|dachte|überlegte|sinnierte|said|asked|replied|answered|whispered|murmured|muttered|shouted|cried|called|exclaimed|added|continued)';
+const AB_NOTNAME = new Set([
+  'Der', 'Die', 'Das', 'Den', 'Dem', 'Ein', 'Eine', 'Einen', 'Er', 'Sie', 'Es', 'Ich', 'Du', 'Wir', 'Ihr', 'Man',
+  'Und', 'Aber', 'Da', 'Dann', 'Doch', 'So', 'Nun', 'Jetzt', 'The', 'He', 'She', 'It', 'They', 'A', 'An', 'And', 'But', 'Then', 'Now',
+  'Sofort', 'Plötzlich', 'Endlich', 'Schließlich', 'Stille', 'Schweigen', 'Stimme', 'Stimmen', 'Frage', 'Antwort',
+  'Gelächter', 'Wieder', 'Gleich', 'Sogleich', 'Langsam', 'Leise', 'Laut', 'Kaum', 'Vielleicht', 'Natürlich', 'Wirklich',
+  'Ja', 'Nein', 'Komm', 'Warte', 'Halt', 'Geh', 'Hier', 'Dort', 'Oben', 'Unten', 'Schon', 'Noch', 'Auch', 'Nur', 'Immer', 'Nie']);
+const _AB_NAME = "([A-ZÄÖÜ][A-Za-zäöüß'\\-]+)";
+const AB_PERSON_NOUNS = new Set(['Mann','Frau','Junge','Mädchen','Alte','Alter','Fremde','Fremder','Krieger','Kriegerin',
+  'Wächter','Wache','Soldat','Hauptmann','Ork','Ritter','Magier','Magierin','Zwerg','Elf','Elfe','Händler','Wirt','Wirtin',
+  'Bauer','Priester','Priesterin','Nachbar','Nachbarin','Sklave','Sklavin','Verweser','Inquisitor','General','König','Königin',
+  'Prinz','Prinzessin','Fürst','Fürstin','Baron','Baronin','Bote','Diener','Dienerin','Knabe','Kind','Reiter','Reiterin',
+  'Bogenschütze','Schmied','Schmiedin','Heiler','Heilerin','Gelehrte','Gelehrter','Kapitän','Anführer','Anführerin']);

static/js/audiobook.js

@@ -624,34 +624,6 @@ function _abClearDraft() {
 // dialogue delimiter; treating it as one split scare-quoted words out as
 // speakerless "dialogue" fragments (confirmed live: "Zelt", "Skipperedikt",
 // "Seulaslintan" etc.).
-const AB_DIALOGUE_RE = /[«»„“”"‟‚‘’『「<]|(?:^|\n)\s*[—–]\s/;
-function audiobookHasDialogue(t) { return AB_DIALOGUE_RE.test(t || ''); }
-
-// Join words hyphenated across a PDF line break ("Schwer- tes" → "Schwertes")
-// so the audiobook reads cleanly and speaker tags aren't split.
-function audiobookDehyphenate(t) { return (t || '').replace(/([a-zäöüß])-\s+(?=[a-zäöüßA-ZÄÖÜ])/g, '$1'); }
-
-// Speech-tag heuristic so the book still casts with REAL names when the LLM is down.
-const AB_SPEECH_VERBS = '(?:sagte|fragte|rief|antwortete|erwiderte|entgegnete|meinte|flüsterte|wisperte|raunte|murmelte|brummte|knurrte|brüllte|schrie|stammelte|fauchte|zischte|seufzte|lachte|kicherte|befahl|wiederholte|fuhr\\s+fort|grunzte|versetzte|unterbrach|drängte|herrschte|keuchte|hauchte|ächzte|stöhnte|jammerte|spottete|höhnte|warf\\s+ein|setzte\\s+hinzu|erklärte|verkündete|widersprach|beharrte|gestand|bestätigte|erinnerte|dachte|überlegte|sinnierte|said|asked|replied|answered|whispered|murmured|muttered|shouted|cried|called|exclaimed|added|continued)';
-const AB_NOTNAME = new Set([
-  'Der', 'Die', 'Das', 'Den', 'Dem', 'Ein', 'Eine', 'Einen', 'Er', 'Sie', 'Es', 'Ich', 'Du', 'Wir', 'Ihr', 'Man',
-  'Und', 'Aber', 'Da', 'Dann', 'Doch', 'So', 'Nun', 'Jetzt', 'The', 'He', 'She', 'It', 'They', 'A', 'An', 'And', 'But', 'Then', 'Now',
-  // common sentence-initial adverbs / interjections / abstractions that are NOT characters
-  'Sofort', 'Plötzlich', 'Endlich', 'Schließlich', 'Stille', 'Schweigen', 'Stimme', 'Stimmen', 'Frage', 'Antwort',
-  'Gelächter', 'Wieder', 'Gleich', 'Sogleich', 'Langsam', 'Leise', 'Laut', 'Kaum', 'Vielleicht', 'Natürlich', 'Wirklich',
-  'Ja', 'Nein', 'Komm', 'Warte', 'Halt', 'Geh', 'Hier', 'Dort', 'Oben', 'Unten', 'Schon', 'Noch', 'Auch', 'Nur', 'Immer', 'Nie']);
-const _AB_NAME = "([A-ZÄÖÜ][A-Za-zäöüß'\\-]+)";
-
-// Person/role nouns that are plausible speakers when no proper name is found.
-// A generic "der/die + any capitalized noun" fallback assigned scenery words
-// as characters (PLATZ from "auf dem Platz", GESICHTER, KLEINIGKEIT) — a
-// closed whitelist can't make that class of mistake.
-const AB_PERSON_NOUNS = new Set(['Mann','Frau','Junge','Mädchen','Alte','Alter','Fremde','Fremder','Krieger','Kriegerin',
-  'Wächter','Wache','Soldat','Hauptmann','Ork','Ritter','Magier','Magierin','Zwerg','Elf','Elfe','Händler','Wirt','Wirtin',
-  'Bauer','Priester','Priesterin','Nachbar','Nachbarin','Sklave','Sklavin','Verweser','Inquisitor','General','König','Königin',
-  'Prinz','Prinzessin','Fürst','Fürstin','Baron','Baronin','Bote','Diener','Dienerin','Knabe','Kind','Reiter','Reiterin',
-  'Bogenschütze','Schmied','Schmiedin','Heiler','Heilerin','Gelehrte','Gelehrter','Kapitän','Anführer','Anführerin']);
-
 // Deterministic Unknown-resolution — the LLM keeps missing mechanical
 // patterns no matter how explicitly the prompt spells them out (measured:
 // ~44% Unknown on a full book WITH the rules in the prompt), so apply them
@@ -7034,4 +7006,3 @@ function audiobookExportDialog() {
     modal.style.display = 'flex';
   }
 }
-

static/module-manifest.json

@@ -5,8 +5,8 @@
   ],
   "lazy": {
     "s-rehearser": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker"],
-    "s-reader": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker", "characters-library", "reader", "audiobook/network", "audiobook", "character-sheets"],
+    "s-reader": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker", "characters-library", "reader", "audiobook/network", "audiobook-parse", "audiobook", "character-sheets"],
-    "s-library": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker", "characters-library", "reader", "audiobook/network", "audiobook", "character-sheets", "library", "character-columns", "library-characters", "sillytavern"],
+    "s-library": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker", "characters-library", "reader", "audiobook/network", "audiobook-parse", "audiobook", "character-sheets", "library", "character-columns", "library-characters", "sillytavern"],
-    "s-caststudio": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker", "characters-library", "reader", "audiobook/network", "audiobook", "character-sheets", "library", "character-columns", "library-characters", "sillytavern", "studio"]
+    "s-caststudio": ["rehearser-parse", "rehearser", "rehearser-library", "rehearser-stage", "rehearser-voice-picker", "characters-library", "reader", "audiobook/network", "audiobook-parse", "audiobook", "character-sheets", "library", "character-columns", "library-characters", "sillytavern", "studio"]
   }
 }