fix(subtitles): preserve lyric selection and deduplicate secondary text

- Seek sidebar selections past overlapping karaoke exit spans
- Collapse duplicate long ASS lines and omit reconstructed sign grids
This commit is contained in:
2026-08-21 01:28:00 -07:00
parent 9445aef004
commit 88bb3edfa4
16 changed files with 190 additions and 11 deletions
+1
View File
@@ -52,6 +52,7 @@ export { syncYomitanDefaultAnkiServer } from './tokenizer/yomitan-parser-runtime
export { createSubtitleProcessingController } from './subtitle-processing-controller';
export {
resolveSanitizedSubtitleSeekCommand,
subtitleCueListSeekTime,
subtitleCueSeekTime,
} from './subtitle-cue-navigation';
export { createFrequencyDictionaryLookup } from './frequency-dictionary';
@@ -0,0 +1,15 @@
const MIN_FLATTENED_DUPLICATE_LENGTH = 16;
const TERMINAL_SENTENCE_PUNCTUATION = /[.!?]+$/gu;
/**
* Identifies long lines that become duplicates when positioned ASS events are
* flattened into the secondary subtitle bar. Short dialogue stays distinct.
*/
export function flattenedSecondarySubtitleLineIdentity(text: string): string | null {
const identity = text
.normalize('NFKC')
.replace(/\s+/gu, '')
.replace(TERMINAL_SENTENCE_PUNCTUATION, '');
return identity.length >= MIN_FLATTENED_DUPLICATE_LENGTH ? identity : null;
}
@@ -2,6 +2,7 @@ import assert from 'node:assert/strict';
import test from 'node:test';
import {
resolveSanitizedSubtitleSeekCommand,
subtitleCueListSeekTime,
subtitleCueSeekTime,
} from './subtitle-cue-navigation';
@@ -85,3 +86,23 @@ test('sidebar cue seeks share the boundary-safe sanitized cue timestamp', () =>
assert.equal(subtitleCueSeekTime({ startTime: 1, endTime: 2, text: 'line' }), 1.08);
assert.equal(subtitleCueSeekTime({ startTime: 1, endTime: 1.04, text: 'short' }), 1.03);
});
test('sidebar cue selection clears an overlapping previous lyric', () => {
const cues = [
{ startTime: 1, endTime: 3.4, text: 'previous lyric' },
{ startTime: 3, endTime: 5, text: 'selected lyric' },
];
assert.equal(subtitleCueListSeekTime(cues, cues[1]!), 3.48);
});
test('sidebar cue selection remains inside a short cue when overlap cannot be cleared', () => {
const cues = [
{ startTime: 1, endTime: 3.4, text: 'previous lyric' },
{ startTime: 3, endTime: 3.2, text: 'selected lyric' },
];
const seekTime = subtitleCueListSeekTime(cues, cues[1]!);
assert.ok(seekTime >= 3.19);
assert.ok(seekTime < cues[1]!.endTime);
});
@@ -42,6 +42,36 @@ export function subtitleCueSeekTime(cue: SubtitleCue): number {
);
}
/**
* Choose a stable point inside a selected cue. Karaoke lines can overlap while the
* previous line animates out, so a sidebar selection should clear that overlap when
* the selected cue has enough time remaining.
*/
export function subtitleCueListSeekTime(
cues: readonly SubtitleCue[],
selectedCue: SubtitleCue,
): number {
const groups = groupCueBoundaries(cues);
const selectedGroupIndex = groups.findIndex(
(group) =>
selectedCue.startTime >= group.startTime &&
selectedCue.startTime - group.startTime <= CUE_START_GROUP_TOLERANCE_SECONDS,
);
const previousGroupEndTime =
selectedGroupIndex > 0 ? groups[selectedGroupIndex - 1]?.endTime : undefined;
if (previousGroupEndTime === undefined || previousGroupEndTime <= selectedCue.startTime) {
return subtitleCueSeekTime(selectedCue);
}
return Math.max(
selectedCue.startTime,
Math.min(
selectedCue.endTime - CUE_END_GUARD_SECONDS,
previousGroupEndTime + CUE_BOUNDARY_SEEK_OFFSET_SECONDS,
),
);
}
/**
* Translate mpv subtitle-line navigation onto parsed cues. Generated ASS karaoke can
* contain hundreds of subtitle events for one visible line, while the parsed list has
+27
View File
@@ -10,6 +10,7 @@ import { hasAssAnimationEvidence, mergeDuplicateCues } from './subtitle-cue-dedu
export type AssCueLayout =
| { kind: 'positioned'; sourceOrder: number; y: number }
| { kind: 'fragment-grid'; sourceOrder: number }
| { kind: 'source-order'; sourceOrder: number };
export interface SubtitleCue {
@@ -210,6 +211,7 @@ const MIN_FRAGMENT_LINE_EVENTS = 8;
const MIN_FRAGMENT_LINE_PARTS = 4;
const MAX_FRAGMENT_MEDIAN_LENGTH = 4;
const MAX_FRAGMENT_LINE_TIMING_VARIANCE_SECONDS = 2;
const MAX_FRAGMENT_LINE_VERTICAL_SPAN = 48;
function parseAssTimestamp(raw: string): number | null {
const match = ASS_TIMING_PATTERN.exec(raw.trim());
@@ -385,6 +387,30 @@ interface AssFragmentPart {
text: string;
}
function reconstructedAssFragmentLayout(
parts: readonly AssFragmentPart[],
owner: AnnotatedSubtitleCue,
): AssCueLayout | undefined {
let positionedPartCount = 0;
let minimumY = Infinity;
let maximumY = -Infinity;
for (const part of parts) {
const layout = part.cue.assLayout;
if (layout?.kind !== 'positioned') continue;
positionedPartCount += 1;
minimumY = Math.min(minimumY, layout.y);
maximumY = Math.max(maximumY, layout.y);
}
if (
positionedPartCount >= MIN_FRAGMENT_LINE_PARTS &&
maximumY - minimumY > MAX_FRAGMENT_LINE_VERTICAL_SPAN
) {
return { kind: 'fragment-grid', sourceOrder: owner.order };
}
return owner.assLayout;
}
interface AssFragmentTimingCluster {
events: AnnotatedSubtitleCue[];
minStartTime: number;
@@ -515,6 +541,7 @@ function reconstructAssFragmentLine(
source: 'reconstructed-ass',
animationStartTime,
animationEndTime,
assLayout: reconstructedAssFragmentLayout(parts, owner),
overrides: [],
overrideSignature: '',
};