refactor: extract audiobook cast cleanup

CHANGELOG.md

@@ -9,7 +9,8 @@ Follows [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) · versioned wi
 
 ### Changed
 - **Audiobook cast normalization extraction.** Same-speaker post-cast merging now lives in
-  `audiobook-cast.js`, including dialogue-only merging, keeping deterministic segment cleanup separate from live casting orchestration.
+  `audiobook-cast.js`, including dialogue-only merging, split-sentence repair, and nearby-duplicate removal,
+  keeping deterministic segment cleanup separate from live casting orchestration.
 - **Audiobook segmentation extraction.** Quote segmentation, conservative turn-taking, and dialogue-piece validation
   now live in `audiobook-segmentation.js`; the live casting pipeline remains compatible with the same global helpers.
 - **Rehearser voice-design extraction.** Character development, backend selection, and backend-refresh synchronization

VERSION

@@ -1 +1 @@
-1.24.40
+1.24.41

docs/ARCHITECTURE.md

@@ -37,7 +37,7 @@ Done incrementally as global-scope ordered files (no ES-module change needed)
 - ✅ `rehearser-voice-design.js` — character development, backend selection, and backend-refresh synchronization.
 - ✅ `audiobook-segmentation.js` — quote segmentation, conservative turn-taking, and dialogue-piece validation.
 - ✅ `audiobook-parse.js` — dialogue detection, dehyphenation, and speaker-heuristic constants; the casting pipeline remains in `audiobook.js`.
-- ✅ `audiobook-cast.js` — cast Markdown export, legacy page-stamping migration, and deterministic same-speaker/dialogue post-cast normalization helpers; live casting remains in `audiobook.js`.
+- ✅ `audiobook-cast.js` — cast Markdown export, legacy page-stamping migration, and deterministic speaker/sentence/duplicate normalization helpers; live casting remains in `audiobook.js`.
 - ✅ `static/css/resource-diagnostics.css` — isolated Performance/resource diagnostic panel styles.
 - ✅ `static/css/background-jobs.css` — isolated background-job history and retry-panel styles.
 - ✅ `static/css/voice-design.css` — isolated Voice Design form, samples, and preview-match styles.

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="1.24.40">
+  <meta name="app-version" content="1.24.41">
   <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">
@@ -27,10 +27,10 @@
 
   <!-- ── 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=1.24.40">
-  <link rel="stylesheet" href="/static/css/resource-diagnostics.css?v=1.24.40">
-  <link rel="stylesheet" href="/static/css/background-jobs.css?v=1.24.40">
-  <link rel="stylesheet" href="/static/css/voice-design.css?v=1.24.40">
+  <link rel="stylesheet" href="/static/style.css?v=1.24.41">
+  <link rel="stylesheet" href="/static/css/resource-diagnostics.css?v=1.24.41">
+  <link rel="stylesheet" href="/static/css/background-jobs.css?v=1.24.41">
+  <link rel="stylesheet" href="/static/css/voice-design.css?v=1.24.41">
 
 
   <!-- ── Flag icons — non-blocking (loaded async, icons appear after JS) ── -->
@@ -395,7 +395,7 @@ window.toggleNavTree = function(treeId, chevronId) {
 </script>
 
 <!-- loader.js: fetches sections → loads JS modules → removes skeleton -->
-<script src="/static/loader.js?v=1.24.40"></script>
+<script src="/static/loader.js?v=1.24.41"></script>
 
 </body>
 </html>

static/js/audiobook-cast.js

@@ -100,6 +100,50 @@ function _audiobookMergeAdjacentDialogue(segments) {
   return { segments: out, merged };
 }
 
+function _audiobookMergeSplitSentences(segments) {
+  const out = [];
+  let merged = 0;
+  for (const s of segments) {
+    const prev = out[out.length - 1];
+    const cur = String(s?.text || '').trim();
+    if (prev && prev.type === 'narration' && s?.type === 'narration' && cur) {
+      const prevText = String(prev.text || '').trimEnd();
+      const endsOpen = prevText && !/[.!?:;…»"'\)\]]$/.test(prevText);
+      const startsLower = /^[a-zäöüß]/.test(cur);
+      const prevIsInquit = new RegExp(_AB_INQUIT_VERBS + "[^.!?]{0,40},\\s*$", 'i').test(prevText);
+      if (endsOpen && startsLower && !prevIsInquit) {
+        prev.text = prevText + ' ' + cur;
+        merged++;
+        continue;
+      }
+    }
+    out.push(s);
+  }
+  return { segments: out, merged };
+}
+
+function _audiobookDedupNearbyDuplicates(segments) {
+  const QUOTE_CHARS = '»«„"‘’›‹';
+  const stripRe = new RegExp(`(^[${QUOTE_CHARS}\\s]+)|([${QUOTE_CHARS}\\s]+$)`, 'g');
+  const norm = (t) => String(t || '').replace(stripRe, '').toLowerCase().replace(/\s+/g, ' ').trim();
+  const WINDOW = 30;
+  const MIN_LEN = 20;
+  const out = [];
+  let removed = 0;
+  for (const s of segments) {
+    const nt = norm(s?.text);
+    if (nt.length >= MIN_LEN) {
+      let isDup = false;
+      for (let k = out.length - 1; k >= 0 && out.length - k <= WINDOW; k--) {
+        if (out[k].type === s.type && norm(out[k].text) === nt) { isDup = true; break; }
+      }
+      if (isDup) { removed++; continue; }
+    }
+    out.push(s);
+  }
+  return { segments: out, removed };
+}
+
 window.TTVC = window.TTVC || {};
 window.TTVC.audiobook = window.TTVC.audiobook || {};
 window.TTVC.audiobook.cast = {
@@ -107,4 +151,6 @@ window.TTVC.audiobook.cast = {
   stampPages: _abStampSegmentPages,
   mergeAdjacentSameSpeaker: _audiobookMergeAdjacentSameSpeaker,
   mergeAdjacentDialogue: _audiobookMergeAdjacentDialogue,
+  mergeSplitSentences: _audiobookMergeSplitSentences,
+  dedupNearbyDuplicates: _audiobookDedupNearbyDuplicates,
 };

static/js/audiobook.js

@@ -979,53 +979,6 @@ function _audiobookConsolidateSpeakerAliases(segments) {
 }
 window._audiobookConsolidateSpeakerAliases = _audiobookConsolidateSpeakerAliases;
 
-function _audiobookMergeSplitSentences(segments) {
-  const out = [];
-  let merged = 0;
-  for (const s of segments) {
-    const prev = out[out.length - 1];
-    const cur = String(s?.text || '').trim();
-    if (prev && prev.type === 'narration' && s?.type === 'narration' && cur) {
-      const prevText = String(prev.text || '').trimEnd();
-      const endsOpen = prevText && !/[.!?:;…»"'\)\]]$/.test(prevText);
-      const startsLower = /^[a-zäöüß]/.test(cur);
-      // Never merge across an inquit (", flüsterte der Geist,") — that is a
-      // SPLIT QUOTE whose second half is really dialogue; fusing it into
-      // narration would bury a line the attribution passes could still fix.
-      const prevIsInquit = new RegExp(_AB_INQUIT_VERBS + "[^.!?]{0,40},\\s*$", 'i').test(prevText);
-      if (endsOpen && startsLower && !prevIsInquit) {
-        prev.text = prevText + ' ' + cur;
-        merged++;
-        continue;
-      }
-    }
-    out.push(s);
-  }
-  return { segments: out, merged };
-}
-
-function _audiobookDedupNearbyDuplicates(segments) {
-  const QUOTE_CHARS = '»«„"‘’›‹';
-  const stripRe = new RegExp(`(^[${QUOTE_CHARS}\\s]+)|([${QUOTE_CHARS}\\s]+$)`, 'g');
-  const norm = (t) => String(t || '').replace(stripRe, '').toLowerCase().replace(/\s+/g, ' ').trim();
-  const WINDOW = 30;      // generous vs. the ~9-segment max context overlap between adjacent recast groups
-  const MIN_LEN = 20;     // skip short common lines ("Ja." "Nein.") that can legitimately repeat
-  const out = [];
-  let removed = 0;
-  for (const s of segments) {
-    const nt = norm(s?.text);
-    if (nt.length >= MIN_LEN) {
-      let isDup = false;
-      for (let k = out.length - 1; k >= 0 && out.length - k <= WINDOW; k--) {
-        if (out[k].type === s.type && norm(out[k].text) === nt) { isDup = true; break; }
-      }
-      if (isDup) { removed++; continue; }
-    }
-    out.push(s);
-  }
-  return { segments: out, removed };
-}
-
 // A bare one-word "dialogue" piece with no sentence-ending punctuation is
 // essentially never a real spoken turn ("Nein!", "Halt." always carry
 // punctuation) — it's the signature of »quoted title/name« text (German