fix(subtitles): keep overlapping lines that join an already active cue (#221)

src/renderer/subtitle-render.test.ts

@@ -11,6 +11,7 @@ import {
   getFrequencyRankLabelForToken,
   getJlptLevelLabelForToken,
   normalizeSubtitle,
+  normalizeSubtitleForDisplay,
   prepareSecondarySubtitleLines,
   sanitizeSubtitleHoverTokenColor,
   shouldRenderTokenizedSubtitle,
@@ -1004,6 +1005,34 @@ test('normalizeSubtitle collapses explicit line breaks when collapseLineBreaks i
   );
 });
 
+test('normalizeSubtitleForDisplay always breaks between simultaneous cues', () => {
+  // The blank line marks two distinct cues on screen at once. Flattening it would run a
+  // sign or a second speaker into the line beside it as one sentence.
+  const twoCues =
+    '\u6b21\u306f\u9b3c\u5b50\u6bcd\u795e\u524d\u3000\u9b3c\u5b50\u6bcd\u795e\u524d\n\n\u611b\u97f3\u3061\u3083\u3093\u3000\u3082\u3046\u5199\u771f\u4e0a\u3052\u3066\u308b';
+
+  assert.equal(
+    normalizeSubtitleForDisplay(twoCues, false),
+    '\u6b21\u306f\u9b3c\u5b50\u6bcd\u795e\u524d \u9b3c\u5b50\u6bcd\u795e\u524d\n\u611b\u97f3\u3061\u3083\u3093 \u3082\u3046\u5199\u771f\u4e0a\u3052\u3066\u308b',
+  );
+  assert.equal(normalizeSubtitleForDisplay(twoCues, true), twoCues.replace('\n\n', '\n'));
+});
+
+test('normalizeSubtitleForDisplay preserves CRLF boundaries between simultaneous cues', () => {
+  assert.equal(normalizeSubtitleForDisplay('a\r\n\r\nb', false), 'a\nb');
+});
+
+test('normalizeSubtitleForDisplay still flattens a wrap inside one cue', () => {
+  // A typesetter's \\N inside a single utterance is what preserveLineBreaks governs.
+  assert.equal(
+    normalizeSubtitleForDisplay(
+      '\u5e38\u4eba\u304c\u4f7f\u3048\u3070\\N\u305d\u306e\u5727\u5012\u7684\u306a\u529b\u306b',
+      false,
+    ),
+    '\u5e38\u4eba\u304c\u4f7f\u3048\u3070 \u305d\u306e\u5727\u5012\u7684\u306a\u529b\u306b',
+  );
+});
+
 test('normalizeSubtitle leaves already-decoded text alone', () => {
   // Primary subtitle text is decoded from ASS once, upstream: by mpv for live lines and
   // by the cue parser for prefetched ones. A brace that survives that is literal text.

src/renderer/subtitle-render.ts

@@ -50,6 +50,21 @@ export function normalizeSubtitle(text: string, trim = true, collapseLineBreaks
   return normalizePlainSubtitleText(text, { trim, collapseLineBreaks });
 }
 
+/**
+ * Display form of a resolved subtitle. `preserveLineBreaks` governs wrapping inside one
+ * utterance, which is what a typesetter's `\N` means. The blank line the resolver puts
+ * between two simultaneous cues is a different thing and always breaks, so a sign or a
+ * second speaker never runs into the line beside it.
+ */
+export function normalizeSubtitleForDisplay(text: string, preserveLineBreaks: boolean): string {
+  return text
+    .replace(/\r\n/g, '\n')
+    .split(/\n{2,}/)
+    .map((cueText) => normalizeSubtitle(cueText, true, !preserveLineBreaks))
+    .filter((cueText) => cueText.length > 0)
+    .join('\n');
+}
+
 const HEX_COLOR_PATTERN = /^#(?:[0-9a-fA-F]{3}|[0-9a-fA-F]{4}|[0-9a-fA-F]{6}|[0-9a-fA-F]{8})$/;
 const SAFE_CSS_COLOR_PATTERN =
   /^(?:#(?:[0-9a-fA-F]{3}|[0-9a-fA-F]{4}|[0-9a-fA-F]{6}|[0-9a-fA-F]{8})|(?:rgba?|hsla?)\([^)]*\)|var\([^)]*\)|[a-zA-Z]+)$/;
@@ -414,16 +429,13 @@ function renderWithTokens(
   const fragment = document.createDocumentFragment();
 
   if (sourceText) {
-    const normalizedSource = normalizeSubtitle(sourceText, true, !preserveLineBreaks);
+    const normalizedSource = normalizeSubtitleForDisplay(sourceText, preserveLineBreaks);
     const segments = alignTokensToSourceText(tokens, normalizedSource);
 
     for (const segment of segments) {
       if (segment.kind === 'text') {
-        if (preserveLineBreaks) {
-          renderPlainTextPreserveLineBreaks(fragment, segment.text);
-        } else {
-          fragment.appendChild(document.createTextNode(segment.text));
-        }
+        // Normalization already resolved which breaks survive; every one left is real.
+        renderPlainTextPreserveLineBreaks(fragment, segment.text);
         continue;
       }
 
@@ -748,7 +760,7 @@ export function createSubtitleRenderer(ctx: RendererContext) {
       return;
     }
 
-    const normalized = normalizeSubtitle(text, true, !ctx.state.preserveSubtitleLineBreaks);
+    const normalized = normalizeSubtitleForDisplay(text, ctx.state.preserveSubtitleLineBreaks);
     const hasRenderableTokens =
       shouldRenderTokenizedSubtitle(tokens?.length ?? 0) && Boolean(tokens);
     if (