perf(tokenizer): single-pass Yomitan scan with cross-line caching and prefetch fixes (#185)

This commit is contained in:
2026-08-06 21:44:09 -07:00
committed by GitHub
parent 441ecf3c04
commit dbdf578c68
38 changed files with 4073 additions and 1720 deletions
@@ -1,5 +1,7 @@
import assert from 'node:assert/strict';
import test from 'node:test';
import { createSubtitleProcessingController } from '../../core/services/subtitle-processing-controller';
import type { SubtitleData } from '../../types';
import {
createAutoplaySubtitlePrimingRuntime,
setMpvCurrentSecondarySubText,
@@ -42,8 +44,9 @@ test('scheduleSubtitlePrefetchRefresh logs refresh failures from timer callback'
setActiveParsedSubtitleMediaPath: () => {},
subtitleProcessingController: {
consumeCachedSubtitle: () => null,
onSubtitleChange: () => {},
refreshCurrentSubtitle: () => {},
onSubtitleChange: () => true,
refreshCurrentSubtitle: () => true,
notePlainSubtitleEmitted: () => {},
},
emitSubtitlePayload: () => {},
getSubtitlePrefetchService: () => null,
@@ -93,13 +96,25 @@ test('primeCurrentSubtitleForAutoplay refreshes active subtitle cues when mpv su
setActiveParsedSubtitleMediaPath: () => {},
subtitleProcessingController: {
consumeCachedSubtitle: () => null,
onSubtitleChange: (text) => calls.push(`change:${text}`),
refreshCurrentSubtitle: (text) => calls.push(`refresh:${text ?? ''}`),
onSubtitleChange: (text) => {
calls.push(`change:${text}`);
return true;
},
refreshCurrentSubtitle: (text) => {
calls.push(`refresh:${text ?? ''}`);
return true;
},
notePlainSubtitleEmitted: () => {},
},
emitSubtitlePayload: (payload) => calls.push(`emit:${payload.text}`),
emitSubtitlePayload: (payload, options) =>
calls.push(`emit:${payload.text}:resume=${options?.resumePrefetch !== false}`),
getSubtitlePrefetchService: () => ({
pause: () => calls.push('prefetch:pause'),
onSeek: (timePos) => calls.push(`prefetch:seek:${timePos}`),
pause: () => {
calls.push('prefetch:pause');
},
resume: () => {
calls.push('prefetch:resume');
},
}),
getLastObservedTimePos: () => 12,
getVisibleOverlayVisible: () => true,
@@ -120,8 +135,10 @@ test('primeCurrentSubtitleForAutoplay refreshes active subtitle cues when mpv su
'request:time-pos',
'set:起動字幕',
'prefetch:pause',
'emit:起動字幕',
'change:起動字幕',
'emit:起動字幕:resume=false',
// Uncached priming refreshes rather than announcing a change, so an
// invalidated-but-unchanged line is still re-tokenized.
'refresh:起動字幕',
]);
});
@@ -151,13 +168,25 @@ test('primeCurrentSubtitleForAutoplay emits raw first paint on cache miss before
setActiveParsedSubtitleMediaPath: () => {},
subtitleProcessingController: {
consumeCachedSubtitle: () => null,
onSubtitleChange: (text) => calls.push(`change:${text}`),
refreshCurrentSubtitle: (text) => calls.push(`refresh:${text ?? ''}`),
onSubtitleChange: (text) => {
calls.push(`change:${text}`);
return true;
},
refreshCurrentSubtitle: (text) => {
calls.push(`refresh:${text ?? ''}`);
return true;
},
notePlainSubtitleEmitted: () => {},
},
emitSubtitlePayload: (payload) => calls.push(`emit:${payload.text}`),
emitSubtitlePayload: (payload, options) =>
calls.push(`emit:${payload.text}:resume=${options?.resumePrefetch !== false}`),
getSubtitlePrefetchService: () => ({
pause: () => calls.push('prefetch:pause'),
onSeek: (timePos) => calls.push(`prefetch:seek:${timePos}`),
pause: () => {
calls.push('prefetch:pause');
},
resume: () => {
calls.push('prefetch:resume');
},
}),
getLastObservedTimePos: () => 12,
getVisibleOverlayVisible: () => true,
@@ -175,7 +204,228 @@ test('primeCurrentSubtitleForAutoplay emits raw first paint on cache miss before
'request:sub-text',
'set:起動字幕',
'prefetch:pause',
'emit:起動字幕',
'change:起動字幕',
'emit:起動字幕:resume=false',
// Uncached priming refreshes rather than announcing a change, so an
// invalidated-but-unchanged line is still re-tokenized.
'refresh:起動字幕',
]);
});
// Driven by the real processing controller rather than a stub: the failure this
// covers is a disagreement between the priming path and the controller's own
// staleness rules, which a hand-written stub cannot reproduce.
function createPrimingRuntimeWithRealController(options: {
text: string;
calls: string[];
onTokenize: () => void;
tokenize?: (text: string) => SubtitleData | null | Promise<SubtitleData | null>;
cacheLimit?: number;
}) {
const { text, calls } = options;
let currentSubText = '';
let currentSubtitleData: SubtitleData | null = null;
const mediaPath = '/media/video.mkv';
const prefetchService = {
pause: () => calls.push('prefetch:pause'),
resume: () => calls.push('prefetch:resume'),
};
// Mirrors main.ts emitSubtitlePayload: an emit resumes prefetching unless it
// is explicitly marked as not the end of the work for the line, and every
// controller emit is so marked.
const emitSubtitlePayload = (
payload: SubtitleData,
emitOptions?: { resumePrefetch?: boolean },
): void => {
currentSubtitleData = payload;
calls.push(
emitOptions?.resumePrefetch === false
? `emit-raw:${payload.text}`
: `emit-direct:${payload.text}`,
);
if (emitOptions?.resumePrefetch !== false) {
prefetchService.resume();
}
};
const subtitleProcessingController = createSubtitleProcessingController({
tokenizeSubtitle: async (subtitleText) => {
options.onTokenize();
return options.tokenize ? options.tokenize(subtitleText) : { text: subtitleText, tokens: [] };
},
// main.ts routes controller emits through emitSubtitlePayload with
// resumePrefetch: false, so they never release the pause on their own.
emitSubtitle: (payload) => {
currentSubtitleData = payload;
calls.push(`emit:${payload.text}:tokens=${payload.tokens === null ? 'none' : 'yes'}`);
},
onProcessingSettled: () => {
prefetchService.resume();
},
...(options.cacheLimit === undefined ? {} : { cacheLimit: options.cacheLimit }),
});
const runtime = createAutoplaySubtitlePrimingRuntime({
getCurrentMediaPath: () => mediaPath,
getMpvClient: () => ({
connected: true,
currentVideoPath: mediaPath,
requestProperty: async (name) => (name === 'sub-text' ? text : null),
}),
setCurrentSubText: (value) => {
currentSubText = value;
},
getCurrentSubText: () => currentSubText,
getCurrentSubtitleData: () => currentSubtitleData,
getActiveParsedSubtitleCues: () => [],
setActiveParsedSubtitleMediaPath: () => {},
subtitleProcessingController,
emitSubtitlePayload,
getSubtitlePrefetchService: () => prefetchService,
getLastObservedTimePos: () => 12,
getVisibleOverlayVisible: () => true,
emitSecondarySubtitle: () => {},
initSubtitlePrefetch: async () => {},
refreshSubtitlePrefetchFromActiveTrack: async () => {},
logDebug: () => {},
});
return { runtime, subtitleProcessingController, mediaPath };
}
test('primeCurrentSubtitleForAutoplay re-tokenizes text whose cached annotation was invalidated', async () => {
const calls: string[] = [];
let tokenizations = 0;
const text = '起動字幕';
const { runtime, subtitleProcessingController, mediaPath } =
createPrimingRuntimeWithRealController({
text,
calls,
onTokenize: () => {
tokenizations += 1;
},
});
// The line was already tokenized and cached during normal playback.
subtitleProcessingController.onSubtitleChange(text);
await new Promise((resolve) => setTimeout(resolve, 0));
const tokenizationsBeforeInvalidation = tokenizations;
// Mining a card drops every cached tokenization.
subtitleProcessingController.invalidateTokenizationCache();
calls.length = 0;
await runtime.primeCurrentSubtitleForAutoplay(mediaPath);
await new Promise((resolve) => setTimeout(resolve, 0));
// The cache miss must schedule fresh work, or the line stays unannotated for
// as long as it is on screen.
assert.equal(
tokenizations,
tokenizationsBeforeInvalidation + 1,
'expected the invalidated subtitle to be tokenized again',
);
assert.ok(
calls.includes(`emit:${text}:tokens=yes`),
`expected an annotated emit, saw ${JSON.stringify(calls)}`,
);
});
test('primeCurrentSubtitleForAutoplay releases the prefetch pause when nothing is scheduled', async () => {
const calls: string[] = [];
const text = '起動字幕';
const { runtime, subtitleProcessingController, mediaPath } =
createPrimingRuntimeWithRealController({
text,
calls,
onTokenize: () => {},
cacheLimit: 1,
});
// Emitted at the current cache generation, then evicted from the one-entry
// cache: priming misses the cache but the controller has nothing to redo, so
// no emit is coming and the pause must be released here.
subtitleProcessingController.onSubtitleChange(text);
await new Promise((resolve) => setTimeout(resolve, 0));
subtitleProcessingController.preCacheTokenization('別の字幕', {
text: '別の字幕',
tokens: [],
});
calls.length = 0;
await runtime.primeCurrentSubtitleForAutoplay(mediaPath);
await new Promise((resolve) => setTimeout(resolve, 0));
assert.deepEqual(calls, ['prefetch:pause', `emit-raw:${text}`, 'prefetch:resume']);
});
test('primeCurrentSubtitleForAutoplay releases the prefetch pause when tokenization emits nothing', async () => {
const calls: string[] = [];
const text = '起動字幕';
const { runtime, subtitleProcessingController, mediaPath } =
createPrimingRuntimeWithRealController({
text,
calls,
onTokenize: () => {},
// Transient tokenizer failure: the controller falls back to plain text it
// has already shown, so it suppresses the emit entirely.
tokenize: () => null,
});
subtitleProcessingController.onSubtitleChange(text);
await new Promise((resolve) => setTimeout(resolve, 0));
subtitleProcessingController.invalidateTokenizationCache();
calls.length = 0;
await runtime.primeCurrentSubtitleForAutoplay(mediaPath);
await new Promise((resolve) => setTimeout(resolve, 0));
assert.ok(
!calls.some((call) => call.startsWith('emit:')),
`expected no controller emit, saw ${JSON.stringify(calls)}`,
);
assert.equal(
calls.filter((call) => call === 'prefetch:resume').length,
1,
`expected the prefetch pause to be released, saw ${JSON.stringify(calls)}`,
);
});
test('prefetch stays paused until tokenization of an uncached line completes', async () => {
const calls: string[] = [];
const text = '起動字幕';
let finishTokenization = (): void => {};
const tokenizationGate = new Promise<void>((resolve) => {
finishTokenization = resolve;
});
const { runtime, mediaPath } = createPrimingRuntimeWithRealController({
text,
calls,
onTokenize: () => {},
tokenize: async (subtitleText) => {
await tokenizationGate;
return { text: subtitleText, tokens: [] };
},
});
// Driven through the priming path, which is what takes the pause out.
await runtime.primeCurrentSubtitleForAutoplay(mediaPath);
await new Promise((resolve) => setTimeout(resolve, 0));
// Neither the priming emit nor the controller's provisional plain emit may
// release the pause: the expensive scan is still ahead of them and would
// compete with prefetching for the parser.
// One plain payload, not two: priming paints it and tells the controller, so
// the controller goes straight for the tokenized one. And it does not resume
// prefetch, because the expensive scan is still ahead of it.
assert.deepEqual(calls, ['prefetch:pause', `emit-raw:${text}`]);
finishTokenization();
await new Promise((resolve) => setTimeout(resolve, 0));
assert.deepEqual(calls, [
'prefetch:pause',
`emit-raw:${text}`,
`emit:${text}:tokens=yes`,
'prefetch:resume',
]);
});
@@ -17,7 +17,7 @@ type AutoplaySubtitlePrimingMpvClient = {
type AutoplaySubtitlePrimingPrefetchService = {
pause: () => void;
onSeek: (timePos: number) => void;
resume: () => void;
};
export interface AutoplaySubtitlePrimingRuntimeDeps {
@@ -30,10 +30,12 @@ export interface AutoplaySubtitlePrimingRuntimeDeps {
setActiveParsedSubtitleMediaPath: (mediaPath: string | null) => void;
subtitleProcessingController: {
consumeCachedSubtitle: (text: string) => SubtitleData | null;
onSubtitleChange: (text: string) => void;
refreshCurrentSubtitle: (text: string) => void;
// Both report whether processing is pending; see pausePrefetchUntilProcessed.
onSubtitleChange: (text: string) => boolean;
refreshCurrentSubtitle: (text: string) => boolean;
notePlainSubtitleEmitted: (text: string) => void;
};
emitSubtitlePayload: (payload: SubtitleData) => void;
emitSubtitlePayload: (payload: SubtitleData, options?: { resumePrefetch?: boolean }) => void;
getSubtitlePrefetchService: () => AutoplaySubtitlePrimingPrefetchService | null;
getLastObservedTimePos: () => number;
getVisibleOverlayVisible: () => boolean;
@@ -64,6 +66,19 @@ export function setMpvCurrentSecondarySubText(
export function createAutoplaySubtitlePrimingRuntime(deps: AutoplaySubtitlePrimingRuntimeDeps) {
const { subtitleProcessingController, emitSubtitlePayload } = deps;
// Prefetching is paused so the on-screen line gets the parser to itself; the
// resume rides on the controller settling (see onProcessingSettled), not on
// an emit, which a suppressed duplicate or a failed tokenization never sends.
// When the controller reports it has nothing scheduled, no settle is coming
// either, so release the pause here or prefetching idles indefinitely.
function pausePrefetchUntilProcessed(scheduleTokenization: () => boolean): void {
const prefetch = deps.getSubtitlePrefetchService();
prefetch?.pause();
if (!scheduleTokenization()) {
prefetch?.resume();
}
}
let subtitlePrefetchRefreshTimer: ReturnType<typeof setTimeout> | null = null;
let autoplaySubtitlePrimedMediaPath: string | null = null;
let visibleOverlaySubtitleRefreshAfterFirstPaintTimer: ReturnType<typeof setTimeout> | null =
@@ -104,12 +119,25 @@ export function createAutoplaySubtitlePrimingRuntime(deps: AutoplaySubtitlePrimi
const cachedPayload = subtitleProcessingController.consumeCachedSubtitle(text);
if (cachedPayload) {
subtitleProcessingController.onSubtitleChange(text);
// This emit resumes prefetching, so no pause is left outstanding.
emitSubtitlePayload(cachedPayload);
return true;
}
emitSubtitlePayload({ text, tokens: null });
subtitleProcessingController.onSubtitleChange(text);
// Provisional raw emit: keep prefetch paused until the processing
// controller is done with this line, and tell it this line has already been
// painted plain so it does not broadcast the same payload again.
emitSubtitlePayload({ text, tokens: null }, { resumePrefetch: false });
subtitleProcessingController.notePlainSubtitleEmitted(text);
// refreshCurrentSubtitle, not onSubtitleChange: the cache miss above can be
// an invalidation (mining a card) on text the controller still holds, and
// onSubtitleChange treats unchanged text as nothing to do, which would
// leave this line permanently unannotated. refreshCurrentSubtitle also
// re-tokenizes for a new cache generation.
if (!subtitleProcessingController.refreshCurrentSubtitle(text)) {
// Nothing scheduled, so no settle is coming to release the pause.
deps.getSubtitlePrefetchService()?.resume();
}
return true;
}
@@ -153,14 +181,12 @@ export function createAutoplaySubtitlePrimingRuntime(deps: AutoplaySubtitlePrimi
getCurrentSubtitleData: () => deps.getCurrentSubtitleData(),
consumeCachedSubtitle: (text) => subtitleProcessingController.consumeCachedSubtitle(text),
onSubtitleChange: (text) => {
deps.getSubtitlePrefetchService()?.pause();
deps.getSubtitlePrefetchService()?.onSeek(deps.getLastObservedTimePos());
subtitleProcessingController.onSubtitleChange(text);
pausePrefetchUntilProcessed(() => subtitleProcessingController.onSubtitleChange(text));
},
refreshCurrentSubtitle: (text) => {
deps.getSubtitlePrefetchService()?.pause();
deps.getSubtitlePrefetchService()?.onSeek(deps.getLastObservedTimePos());
subtitleProcessingController.refreshCurrentSubtitle(text);
pausePrefetchUntilProcessed(() =>
subtitleProcessingController.refreshCurrentSubtitle(text),
);
},
deferUncachedRefresh: true,
emitSubtitle: (payload) => emitSubtitlePayload(payload),
@@ -204,9 +230,7 @@ export function createAutoplaySubtitlePrimingRuntime(deps: AutoplaySubtitlePrimi
if (!text.trim()) {
return;
}
deps.getSubtitlePrefetchService()?.pause();
deps.getSubtitlePrefetchService()?.onSeek(deps.getLastObservedTimePos());
subtitleProcessingController.refreshCurrentSubtitle(text);
pausePrefetchUntilProcessed(() => subtitleProcessingController.refreshCurrentSubtitle(text));
}, VISIBLE_OVERLAY_SUBTITLE_REFRESH_AFTER_FIRST_PAINT_DELAY_MS);
visibleOverlaySubtitleRefreshAfterFirstPaintTimer.unref?.();
}
@@ -53,3 +53,52 @@ test('character dictionary sync completion refreshes subtitle state when diction
'log:[dictionary:auto-sync] refreshed current subtitle after sync (AniList 1, changed=yes, title=Frieren)',
]);
});
test('character dictionary sync completion drops cached dictionary reads before refreshing', () => {
const calls: string[] = [];
handleCharacterDictionaryAutoSyncComplete(
{
mediaId: 1,
mediaTitle: 'Frieren',
changed: true,
},
{
hasParserWindow: () => true,
invalidateCharacterDictionaryLookups: () => calls.push('invalidate-dictionary-lookups'),
clearParserCaches: () => calls.push('clear-parser'),
invalidateTokenizationCache: () => calls.push('invalidate'),
refreshSubtitlePrefetch: () => calls.push('prefetch'),
refreshCurrentSubtitle: () => calls.push('refresh-subtitle'),
logInfo: () => {},
},
);
// Must run before the refreshes, or they re-tokenize against the character
// names and images from the previous dictionary build.
assert.equal(calls[0], 'invalidate-dictionary-lookups');
assert.ok(calls.indexOf('invalidate-dictionary-lookups') < calls.indexOf('refresh-subtitle'));
});
test('character dictionary sync completion leaves cached dictionary reads alone when unchanged', () => {
const calls: string[] = [];
handleCharacterDictionaryAutoSyncComplete(
{
mediaId: 1,
mediaTitle: 'Frieren',
changed: false,
},
{
hasParserWindow: () => true,
invalidateCharacterDictionaryLookups: () => calls.push('invalidate-dictionary-lookups'),
clearParserCaches: () => calls.push('clear-parser'),
invalidateTokenizationCache: () => calls.push('invalidate'),
refreshSubtitlePrefetch: () => calls.push('prefetch'),
refreshCurrentSubtitle: () => calls.push('refresh-subtitle'),
logInfo: () => {},
},
);
assert.deepEqual(calls, []);
});
@@ -7,6 +7,12 @@ export function handleCharacterDictionaryAutoSyncComplete(
deps: {
hasParserWindow: () => boolean;
clearParserCaches: () => void;
/**
* Drops cached reads of the generated dictionary (character images, and the
* name candidates the scanner uses to skip lookups). Runs before the
* refreshes below so they re-tokenize against the new dictionary content.
*/
invalidateCharacterDictionaryLookups?: () => void;
invalidateTokenizationCache: () => void;
refreshSubtitlePrefetch: () => void;
refreshCurrentSubtitle: () => void;
@@ -14,6 +20,7 @@ export function handleCharacterDictionaryAutoSyncComplete(
},
): void {
if (completion.changed) {
deps.invalidateCharacterDictionaryLookups?.();
if (deps.hasParserWindow()) {
deps.clearParserCaches();
}
@@ -225,24 +225,35 @@ export function composeMpvRuntimeHandlers<
}
return tokenizationWarmupInFlight;
};
// Built once and reused for every tokenization: per-call rebuilds create
// fresh closures, which defeats identity-keyed caches downstream (the JLPT
// lookup cache keys on the getJlptLevel function, and the mecab availability
// WeakSet keys on the runtime deps instance).
let cachedTokenizerRuntimeDeps: TTokenizerRuntimeDeps | null = null;
const getTokenizerRuntimeDeps = (): TTokenizerRuntimeDeps => {
if (cachedTokenizerRuntimeDeps) {
return cachedTokenizerRuntimeDeps;
}
const tokenizerMainDeps = buildTokenizerDepsHandler();
const baseOnTokenizationReady = tokenizerMainDeps.onTokenizationReady;
tokenizerMainDeps.onTokenizationReady = (tokenizedText: string): void => {
if (!shouldWarmupAnnotationDictionaries()) {
baseOnTokenizationReady?.(tokenizedText);
return;
}
markTokenizationPlaybackReady();
baseOnTokenizationReady?.(tokenizedText);
if (!tokenizationWarmupCompleted) {
void prewarmSubtitleDictionaries({ showLoadingOsd: true }).catch(() => {});
}
};
cachedTokenizerRuntimeDeps = options.tokenizer.createTokenizerRuntimeDeps(tokenizerMainDeps);
return cachedTokenizerRuntimeDeps;
};
const tokenizeSubtitle = async (text: string): Promise<TTokenizedSubtitle> => {
if (!tokenizationWarmupCompleted) void startTokenizationWarmups();
await ensureTokenizationPrerequisites();
const tokenizerMainDeps = buildTokenizerDepsHandler();
if (shouldWarmupAnnotationDictionaries()) {
const onTokenizationReady = tokenizerMainDeps.onTokenizationReady;
tokenizerMainDeps.onTokenizationReady = (tokenizedText: string): void => {
markTokenizationPlaybackReady();
onTokenizationReady?.(tokenizedText);
if (!tokenizationWarmupCompleted) {
void prewarmSubtitleDictionaries({ showLoadingOsd: true }).catch(() => {});
}
};
}
return options.tokenizer.tokenizeSubtitle(
text,
options.tokenizer.createTokenizerRuntimeDeps(tokenizerMainDeps),
);
return options.tokenizer.tokenizeSubtitle(text, getTokenizerRuntimeDeps());
};
const launchBackgroundWarmupTask = createLaunchBackgroundWarmupTaskFromStartup(
@@ -6,6 +6,7 @@ export function createBuildSubtitleProcessingControllerMainDepsHandler(
return (): SubtitleProcessingControllerDeps => ({
tokenizeSubtitle: (text: string) => deps.tokenizeSubtitle(text),
emitSubtitle: (payload) => deps.emitSubtitle(payload),
onProcessingSettled: () => deps.onProcessingSettled?.(),
logDebug: deps.logDebug,
now: deps.now,
});
@@ -9,6 +9,9 @@ type TokenizerMainDeps = TokenizerDepsRuntimeOptions & {
getCurrentCharacterDictionaryMediaId?: NonNullable<
TokenizerDepsRuntimeOptions['getCurrentCharacterDictionaryMediaId']
>;
getCharacterNameCandidates?: NonNullable<
TokenizerDepsRuntimeOptions['getCharacterNameCandidates']
>;
getFrequencyDictionaryEnabled: NonNullable<
TokenizerDepsRuntimeOptions['getFrequencyDictionaryEnabled']
>;
@@ -84,6 +87,11 @@ export function createBuildTokenizerDepsMainHandler(deps: TokenizerMainDeps) {
getCurrentCharacterDictionaryMediaId: () => deps.getCurrentCharacterDictionaryMediaId!(),
}
: {}),
...(deps.getCharacterNameCandidates
? {
getCharacterNameCandidates: () => deps.getCharacterNameCandidates!(),
}
: {}),
getFrequencyDictionaryEnabled: () => deps.getFrequencyDictionaryEnabled(),
getFrequencyDictionaryMatchMode: () => deps.getFrequencyDictionaryMatchMode(),
getFrequencyRank: (text: string) => deps.getFrequencyRank(text),