feat(anki): add media timing review before card creation (#203)

This commit is contained in:
2026-09-04 01:40:56 -07:00
committed by GitHub
parent 99266294b8
commit 84f718043a
78 changed files with 7022 additions and 135 deletions
@@ -46,12 +46,13 @@ test('on will quit cleanup handler runs all cleanup steps', () => {
cleanupInternalSubtitleTrackCache: () => calls.push('cleanup-internal-subtitles'),
cleanupYoutubeSubtitleTempDirs: () => calls.push('cleanup-youtube-subtitles'),
cleanupYoutubeMediaCache: () => calls.push('cleanup-youtube-media'),
cleanupRemoteMediaWindows: () => calls.push('cleanup-remote-media-windows'),
cleanupJellyfinSubtitleCache: () => calls.push('cleanup-jellyfin-subtitles'),
stopDiscordPresenceService: () => calls.push('stop-discord-presence'),
});
cleanup();
assert.equal(calls.length, 35);
assert.equal(calls.length, 36);
assert.equal(calls[0], 'destroy-tray');
assert.equal(calls[calls.length - 1], 'stop-discord-presence');
assert.ok(calls.includes('cleanup-jellyfin-subtitles'));
@@ -60,6 +61,7 @@ test('on will quit cleanup handler runs all cleanup steps', () => {
assert.ok(calls.includes('clear-linux-mpv-fullscreen-overlay-refresh-timeouts'));
assert.ok(calls.includes('cleanup-youtube-subtitles'));
assert.ok(calls.includes('cleanup-youtube-media'));
assert.ok(calls.includes('cleanup-remote-media-windows'));
assert.ok(calls.indexOf('flush-mpv-log') < calls.indexOf('destroy-socket'));
});
@@ -102,6 +104,7 @@ test('on will quit cleanup handler cleans jellyfin subtitle cache when stopping
cleanupInternalSubtitleTrackCache: () => calls.push('cleanup-internal-subtitles'),
cleanupYoutubeSubtitleTempDirs: () => calls.push('cleanup-youtube-subtitles'),
cleanupYoutubeMediaCache: () => calls.push('cleanup-youtube-media'),
cleanupRemoteMediaWindows: () => calls.push('cleanup-remote-media-windows'),
cleanupJellyfinSubtitleCache: () => calls.push('cleanup-jellyfin-subtitles'),
stopDiscordPresenceService: () => calls.push('stop-discord-presence'),
});
@@ -32,6 +32,7 @@ export function createOnWillQuitCleanupHandler(deps: {
cleanupInternalSubtitleTrackCache: () => void;
cleanupYoutubeSubtitleTempDirs: () => void;
cleanupYoutubeMediaCache: () => void;
cleanupRemoteMediaWindows: () => void;
cleanupJellyfinSubtitleCache: () => void;
stopDiscordPresenceService: () => void;
}) {
@@ -76,6 +77,7 @@ export function createOnWillQuitCleanupHandler(deps: {
}
deps.cleanupYoutubeSubtitleTempDirs();
deps.cleanupYoutubeMediaCache();
deps.cleanupRemoteMediaWindows();
deps.stopDiscordPresenceService();
return Promise.resolve(stopSyncAutoScheduler);
};
@@ -75,6 +75,7 @@ test('cleanup deps builder returns handlers that guard optional runtime objects'
cleanupInternalSubtitleTrackCache: () => calls.push('cleanup-internal-subtitles'),
cleanupYoutubeSubtitleTempDirs: () => calls.push('cleanup-youtube-subtitles'),
cleanupYoutubeMediaCache: () => calls.push('cleanup-youtube-media'),
cleanupRemoteMediaWindows: () => calls.push('cleanup-remote-media-windows'),
cleanupJellyfinSubtitleCache: () => calls.push('cleanup-jellyfin-subtitles'),
stopDiscordPresenceService: () => calls.push('stop-discord-presence'),
});
@@ -157,6 +158,7 @@ test('cleanup deps builder skips destroyed yomitan window', () => {
cleanupInternalSubtitleTrackCache: () => {},
cleanupYoutubeSubtitleTempDirs: () => {},
cleanupYoutubeMediaCache: () => {},
cleanupRemoteMediaWindows: () => {},
cleanupJellyfinSubtitleCache: () => {},
stopDiscordPresenceService: () => {},
});
@@ -210,6 +212,7 @@ test('cleanup deps builder skips global shortcut cleanup before app ready', () =
cleanupInternalSubtitleTrackCache: () => {},
cleanupYoutubeSubtitleTempDirs: () => {},
cleanupYoutubeMediaCache: () => {},
cleanupRemoteMediaWindows: () => {},
cleanupJellyfinSubtitleCache: () => {},
stopDiscordPresenceService: () => {},
});
@@ -61,6 +61,7 @@ export function createBuildOnWillQuitCleanupDepsHandler(deps: {
cleanupInternalSubtitleTrackCache: () => void;
cleanupYoutubeSubtitleTempDirs: () => void;
cleanupYoutubeMediaCache: () => void;
cleanupRemoteMediaWindows: () => void;
cleanupJellyfinSubtitleCache: () => void;
stopDiscordPresenceService: () => void;
}) {
@@ -148,6 +149,7 @@ export function createBuildOnWillQuitCleanupDepsHandler(deps: {
cleanupInternalSubtitleTrackCache: () => deps.cleanupInternalSubtitleTrackCache(),
cleanupYoutubeSubtitleTempDirs: () => deps.cleanupYoutubeSubtitleTempDirs(),
cleanupYoutubeMediaCache: () => deps.cleanupYoutubeMediaCache(),
cleanupRemoteMediaWindows: () => deps.cleanupRemoteMediaWindows(),
cleanupJellyfinSubtitleCache: () => deps.cleanupJellyfinSubtitleCache(),
stopDiscordPresenceService: () => deps.stopDiscordPresenceService(),
});
@@ -52,6 +52,7 @@ test('composeStartupLifecycleHandlers returns callable startup lifecycle handler
cleanupInternalSubtitleTrackCache: () => {},
cleanupYoutubeSubtitleTempDirs: () => {},
cleanupYoutubeMediaCache: () => {},
cleanupRemoteMediaWindows: () => {},
cleanupJellyfinSubtitleCache: () => {},
stopDiscordPresenceService: () => {},
},
@@ -156,6 +156,7 @@ test('createConfigHotReloadAppliedHandler applies only changed Anki media option
const config = deepCloneConfig(DEFAULT_CONFIG);
config.ankiConnect.media.normalizeAudio = false;
config.ankiConnect.media.mirrorMpvVolume = false;
config.ankiConnect.media.reviewTiming = true;
const ankiPatches: unknown[] = [];
const applyHotReload = createConfigHotReloadAppliedHandler({
@@ -181,10 +182,18 @@ test('createConfigHotReloadAppliedHandler applies only changed Anki media option
},
config,
);
applyHotReload(
{
hotReloadFields: ['ankiConnect.media.reviewTiming'],
restartRequiredFields: [],
},
config,
);
assert.deepEqual(ankiPatches, [
{ media: { normalizeAudio: false } },
{ media: { mirrorMpvVolume: false } },
{ media: { reviewTiming: true } },
]);
});
@@ -100,6 +100,9 @@ function buildAnkiRuntimeConfigPatch(
if (diff.hotReloadFields.includes('ankiConnect.media.mirrorMpvVolume')) {
mediaPatch.mirrorMpvVolume = config.ankiConnect.media.mirrorMpvVolume;
}
if (diff.hotReloadFields.includes('ankiConnect.media.reviewTiming')) {
mediaPatch.reviewTiming = config.ankiConnect.media.reviewTiming;
}
if (Object.keys(mediaPatch).length > 0) {
patch.media = mediaPatch;
}
@@ -0,0 +1,42 @@
import { IPC_CHANNELS, type OverlayHostedModal } from '../../shared/ipc/contracts';
import type { MediaTimingReviewOpenPayload } from '../../types/anki';
import { openOverlayHostedModal, retryOverlayModalOpen } from './overlay-hosted-modal-open';
const MODAL: OverlayHostedModal = 'media-timing-review';
export async function openMediaTimingReviewModal(
deps: {
ensureOverlayStartupPrereqs: () => void;
ensureOverlayWindowsReadyForVisibilityActions: () => void;
sendToActiveOverlayWindow: (
channel: string,
payload?: unknown,
runtimeOptions?: {
restoreOnModalClose?: OverlayHostedModal;
preferModalWindow?: boolean;
},
) => boolean;
waitForModalOpen: (modal: OverlayHostedModal, timeoutMs: number) => Promise<boolean>;
logWarn: (message: string) => void;
},
payload: MediaTimingReviewOpenPayload,
): Promise<boolean> {
return await retryOverlayModalOpen(
{ waitForModalOpen: deps.waitForModalOpen, logWarn: deps.logWarn },
{
modal: MODAL,
// The review renderer regularly needs more than the 1.5 s the other modals allow; a
// premature retry re-sends the payload and reloads the waveform for nothing.
timeoutMs: 4_000,
retryWarning:
'Media timing review did not acknowledge modal open; retrying the dedicated modal window.',
sendOpen: () =>
openOverlayHostedModal(deps, {
channel: IPC_CHANNELS.event.mediaTimingReviewOpen,
modal: MODAL,
payload,
preferModalWindow: true,
}),
},
);
}
@@ -0,0 +1,859 @@
import assert from 'node:assert/strict';
import { describe, test } from 'node:test';
import type { MediaTimingReviewOpenPayload } from '../../types/anki';
import type { SpeechWaveformOptions } from '../../core/services/media-timing-waveform';
import type {
RemoteMediaWindow,
RemoteMediaWindowRange,
RemoteMediaWindowSource,
} from '../../core/services/remote-media-window-cache';
import type { MediaTimingPreviewSession } from '../../core/services/media-timing-preview';
type MediaTimingPreviewSessionLike = Pick<MediaTimingPreviewSession, 'start'>;
import {
buildMediaTimingReviewPayload,
collectMediaTimingContextLines,
createMediaTimingReviewRuntime,
} from './media-timing-review';
describe('buildMediaTimingReviewPayload', () => {
test('starts from the padded range and leaves two seconds to drag on each side', () => {
const payload = buildMediaTimingReviewPayload(
{
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0.5,
maxMediaDuration: 30,
},
{ reviewId: 'review-1', mediaDuration: 100 },
);
assert.equal(payload.selectionStartTime, 9.5);
assert.equal(payload.selectionEndTime, 12.5);
assert.equal(payload.timelineStartTime, 7.5);
assert.equal(payload.timelineEndTime, 14.5);
});
test('clamps the padded selection and timeline to media bounds', () => {
const payload = buildMediaTimingReviewPayload(
{
kind: 'word',
text: '字幕',
startTime: 0.2,
endTime: 9.8,
audioPadding: 1,
maxMediaDuration: 30,
},
{ reviewId: 'review-2', mediaDuration: 10 },
);
assert.equal(payload.selectionStartTime, 0);
assert.equal(payload.selectionEndTime, 10);
assert.equal(payload.timelineStartTime, 0);
assert.equal(payload.timelineEndTime, 10);
});
test('keeps an uncapped selection when max media duration is disabled', () => {
const payload = buildMediaTimingReviewPayload(
{
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 55,
audioPadding: 1,
maxMediaDuration: 0,
},
{ reviewId: 'review-unlimited', mediaDuration: 100 },
);
assert.equal(payload.selectionStartTime, 9);
assert.equal(payload.selectionEndTime, 56);
assert.equal(payload.maxMediaDuration, 0);
});
});
async function startActiveMediaTimingReview(
options: {
maxMediaDuration?: number;
decisionTimeoutMs?: number;
generateWaveform?: () => Promise<number[]>;
play?: () => Promise<void>;
} = {},
) {
const previewCalls: Array<[number, number]> = [];
let publishPayload!: (payload: MediaTimingReviewOpenPayload) => void;
const openedPayload = new Promise<MediaTimingReviewOpenPayload>((resolve) => {
publishPayload = resolve;
});
const runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async (name) => (name === 'duration' ? 100 : name === 'pause' ? true : null),
send: () => undefined,
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => 'mpv',
generateWaveform: options.generateWaveform ?? (async () => []),
decisionTimeoutMs: options.decisionTimeoutMs,
createPreviewSession: () => ({
start: async () => undefined,
play: async (startTime, endTime) => {
previewCalls.push([startTime, endTime]);
await options.play?.();
},
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async (payload) => {
publishPayload(payload);
return true;
},
showStatus: () => undefined,
});
const pendingDecision = runtime.requestReview({
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0,
maxMediaDuration: options.maxMediaDuration ?? 30,
});
return { runtime, payload: await openedPayload, pendingDecision, previewCalls };
}
test('media timing review pauses playback, resolves exact timing, and restores playing state', async () => {
const commands: Array<Array<string | number>> = [];
const previewCalls: Array<[number, number]> = [];
let runtime: ReturnType<typeof createMediaTimingReviewRuntime>;
runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async (name) =>
({ pause: false, duration: 100, aid: 2, volume: 60 })[
name as 'pause' | 'duration' | 'aid' | 'volume'
],
send: ({ command }) => commands.push(command),
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => 'mpv',
generateWaveform: async () => [],
createPreviewSession: () => ({
start: async () => undefined,
play: async (startTime, endTime) => {
previewCalls.push([startTime, endTime]);
},
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async (payload) => {
queueMicrotask(() => {
void runtime
.previewRange({
reviewId: payload.reviewId,
startTime: 9.5,
endTime: 12.5,
})
.then(() => {
runtime.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'confirm', startTime: 9.5, endTime: 12.5 },
});
});
});
return true;
},
showStatus: () => undefined,
});
const decision = await runtime.requestReview({
kind: 'word',
text: '字幕',
startTime: 10,
endTime: 12,
noteId: 42,
audioPadding: 0.5,
maxMediaDuration: 30,
});
assert.deepEqual(decision, { action: 'confirm', startTime: 9.5, endTime: 12.5 });
assert.deepEqual(commands, [
['set_property', 'pause', 'yes'],
['set_property', 'pause', 'no'],
]);
assert.deepEqual(previewCalls, [[9.5, 12.5]]);
});
test('media timing review analyzes the visible range on the selected audio stream', async () => {
const waveformCalls: SpeechWaveformOptions[] = [];
let runtime: ReturnType<typeof createMediaTimingReviewRuntime>;
runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
currentAudioStreamIndex: 4,
requestProperty: async (name) => (name === 'duration' ? 100 : name === 'pause' ? true : null),
send: () => undefined,
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => 'mpv',
generateWaveform: async (options) => {
waveformCalls.push(options);
return [0.1, 0.8, 0.2];
},
createPreviewSession: () => ({
start: async () => undefined,
play: async () => undefined,
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async (payload) => {
const waveform = await runtime.getWaveform({
reviewId: payload.reviewId,
startTime: payload.timelineStartTime,
endTime: payload.timelineEndTime,
});
assert.deepEqual(waveform, { ok: true, peaks: [0.1, 0.8, 0.2] });
runtime.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'use-original' },
});
return true;
},
showStatus: () => undefined,
});
await runtime.requestReview({
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0.5,
maxMediaDuration: 30,
});
assert.deepEqual(waveformCalls, [
{
mediaPath: '/video/show.mkv',
startTime: 7.5,
endTime: 14.5,
audioStreamIndex: 4,
},
]);
});
const REMOTE_STREAM_URL = 'https://jellyfin.example/Videos/abc/stream?static=true';
function createWindowStub(options: { fail?: boolean } = {}) {
const calls: Array<{ source: RemoteMediaWindowSource; range: RemoteMediaWindowRange }> = [];
const acquireMediaWindow = async (
source: RemoteMediaWindowSource,
range: RemoteMediaWindowRange,
): Promise<RemoteMediaWindow> => {
calls.push({ source, range });
if (options.fail) throw new Error('offline');
const windowPath = `/tmp/window-${range.startTime}-${range.endTime}.mkv`;
return {
path: windowPath,
startTime: range.startTime,
endTime: range.endTime,
sourcePath: source.path,
audioStreamIndex: source.audioStreamIndex ?? null,
media: {
path: windowPath,
source: 'remote-window',
singleResolvedStream: true,
absoluteTimestamps: true,
},
};
};
return { calls, acquireMediaWindow };
}
function createRemoteReviewRuntime(options: {
windowStub: ReturnType<typeof createWindowStub>;
waveformCalls: SpeechWaveformOptions[];
previewStarts: Array<Parameters<MediaTimingPreviewSessionLike['start']>[0]>;
previewPlays: Array<[string, number, number]>;
disposed: string[];
openModal: (
runtime: ReturnType<typeof createMediaTimingReviewRuntime>,
payload: MediaTimingReviewOpenPayload,
) => Promise<void>;
}) {
let runtime!: ReturnType<typeof createMediaTimingReviewRuntime>;
runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: REMOTE_STREAM_URL,
currentAudioStreamIndex: 2,
requestProperty: async (name) =>
({ pause: true, duration: 100, aid: 3, volume: 60 })[
name as 'pause' | 'duration' | 'aid' | 'volume'
] ?? null,
send: () => undefined,
}),
getCurrentMediaPath: () => REMOTE_STREAM_URL,
getMpvExecutablePath: () => 'mpv',
resolveMediaSource: async () => ({
path: REMOTE_STREAM_URL,
inputOptions: { reconnect: true },
}),
acquireMediaWindow: options.windowStub.acquireMediaWindow,
generateWaveform: async (waveformOptions) => {
options.waveformCalls.push(waveformOptions);
return [0.1, 0.8, 0.2];
},
createPreviewSession: () => {
let mediaPath = '';
return {
start: async (startOptions) => {
mediaPath = startOptions.mediaPath;
options.previewStarts.push(startOptions);
},
play: async (startTime, endTime) => {
options.previewPlays.push([mediaPath, startTime, endTime]);
},
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => {
options.disposed.push(mediaPath);
},
};
},
openModal: async (payload) => {
await options.openModal(runtime, payload);
return true;
},
showStatus: () => undefined,
});
return runtime;
}
test('media timing review downloads one window of a remote stream for the waveform and preview', async () => {
const windowStub = createWindowStub();
const waveformCalls: SpeechWaveformOptions[] = [];
const previewStarts: Array<Parameters<MediaTimingPreviewSessionLike['start']>[0]> = [];
const previewPlays: Array<[string, number, number]> = [];
const disposed: string[] = [];
const runtime = createRemoteReviewRuntime({
windowStub,
waveformCalls,
previewStarts,
previewPlays,
disposed,
openModal: async (active, payload) => {
const waveform = await active.getWaveform({
reviewId: payload.reviewId,
startTime: payload.timelineStartTime,
endTime: payload.timelineEndTime,
});
assert.deepEqual(waveform, { ok: true, peaks: [0.1, 0.8, 0.2] });
assert.deepEqual(
await active.previewRange({ reviewId: payload.reviewId, startTime: 9.5, endTime: 12.5 }),
{ ok: true },
);
active.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'confirm', startTime: 9.5, endTime: 12.5 },
});
},
});
const decision = await runtime.requestReview({
kind: 'word',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0.5,
maxMediaDuration: 30,
});
assert.deepEqual(decision, { action: 'confirm', startTime: 9.5, endTime: 12.5 });
assert.deepEqual(windowStub.calls, [
{
source: { path: REMOTE_STREAM_URL, inputOptions: { reconnect: true }, audioStreamIndex: 2 },
range: { startTime: 7.5, endTime: 14.5 },
},
]);
assert.deepEqual(waveformCalls, [
{
mediaPath: {
path: '/tmp/window-7.5-14.5.mkv',
source: 'remote-window',
singleResolvedStream: true,
absoluteTimestamps: true,
},
startTime: 7.5,
endTime: 14.5,
},
]);
assert.deepEqual(previewStarts, [
{
mediaPath: '/tmp/window-7.5-14.5.mkv',
executablePath: 'mpv',
volume: 60,
absoluteTimestamps: true,
},
]);
assert.deepEqual(previewPlays, [['/tmp/window-7.5-14.5.mkv', 9.5, 12.5]]);
assert.deepEqual(disposed, ['/tmp/window-7.5-14.5.mkv']);
});
test('media timing review restarts the preview on a wider window when the timeline grows', async () => {
const windowStub = createWindowStub();
const waveformCalls: SpeechWaveformOptions[] = [];
const previewStarts: Array<Parameters<MediaTimingPreviewSessionLike['start']>[0]> = [];
const previewPlays: Array<[string, number, number]> = [];
const disposed: string[] = [];
const runtime = createRemoteReviewRuntime({
windowStub,
waveformCalls,
previewStarts,
previewPlays,
disposed,
openModal: async (active, payload) => {
await active.previewRange({ reviewId: payload.reviewId, startTime: 9.5, endTime: 12.5 });
// The user revealed two more seconds before the clip.
await active.getWaveform({ reviewId: payload.reviewId, startTime: 5.5, endTime: 14.5 });
await active.previewRange({ reviewId: payload.reviewId, startTime: 6, endTime: 12.5 });
active.resolveReview({ reviewId: payload.reviewId, decision: { action: 'use-original' } });
},
});
await runtime.requestReview({
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0.5,
maxMediaDuration: 30,
});
assert.deepEqual(
windowStub.calls.map((call) => call.range),
[
{ startTime: 7.5, endTime: 14.5 },
{ startTime: 5.5, endTime: 14.5 },
],
);
assert.deepEqual(
previewStarts.map((start) => start.mediaPath),
['/tmp/window-7.5-14.5.mkv', '/tmp/window-5.5-14.5.mkv'],
);
assert.deepEqual(previewPlays, [
['/tmp/window-7.5-14.5.mkv', 9.5, 12.5],
['/tmp/window-5.5-14.5.mkv', 6, 12.5],
]);
assert.deepEqual(disposed, ['/tmp/window-7.5-14.5.mkv', '/tmp/window-5.5-14.5.mkv']);
assert.equal(waveformCalls[0]?.startTime, 5.5);
});
test('media timing review falls back to the remote stream after one failed window download', async () => {
const windowStub = createWindowStub({ fail: true });
const waveformCalls: SpeechWaveformOptions[] = [];
const previewStarts: Array<Parameters<MediaTimingPreviewSessionLike['start']>[0]> = [];
const previewPlays: Array<[string, number, number]> = [];
const disposed: string[] = [];
const runtime = createRemoteReviewRuntime({
windowStub,
waveformCalls,
previewStarts,
previewPlays,
disposed,
openModal: async (active, payload) => {
await active.getWaveform({
reviewId: payload.reviewId,
startTime: payload.timelineStartTime,
endTime: payload.timelineEndTime,
});
await active.previewRange({ reviewId: payload.reviewId, startTime: 9.5, endTime: 12.5 });
active.resolveReview({ reviewId: payload.reviewId, decision: { action: 'use-original' } });
},
});
await runtime.requestReview({
kind: 'word',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0.5,
maxMediaDuration: 30,
});
assert.equal(windowStub.calls.length, 1);
assert.deepEqual(waveformCalls, [
{
mediaPath: { path: REMOTE_STREAM_URL, inputOptions: { reconnect: true } },
startTime: 7.5,
endTime: 14.5,
audioStreamIndex: 2,
},
]);
assert.deepEqual(previewStarts, [
{ mediaPath: REMOTE_STREAM_URL, executablePath: 'mpv', volume: 60, audioTrackId: 3 },
]);
assert.deepEqual(previewPlays, [[REMOTE_STREAM_URL, 9.5, 12.5]]);
});
test('media timing review never downloads windows for local media', async () => {
const windowStub = createWindowStub();
let runtime!: ReturnType<typeof createMediaTimingReviewRuntime>;
runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async (name) => (name === 'duration' ? 100 : name === 'pause' ? true : null),
send: () => undefined,
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => 'mpv',
resolveMediaSource: async () => ({ path: '/video/show.mkv' }),
acquireMediaWindow: windowStub.acquireMediaWindow,
generateWaveform: async () => [0.1, 0.8, 0.2],
createPreviewSession: () => ({
start: async () => undefined,
play: async () => undefined,
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async (payload) => {
await runtime.getWaveform({ reviewId: payload.reviewId, startTime: 7.5, endTime: 14.5 });
runtime.resolveReview({ reviewId: payload.reviewId, decision: { action: 'use-original' } });
return true;
},
showStatus: () => undefined,
});
await runtime.requestReview({
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0.5,
maxMediaDuration: 30,
});
assert.equal(windowStub.calls.length, 0);
});
test('media timing review rejects stale and out-of-range actions before allowing discard', async () => {
const { runtime, payload, pendingDecision, previewCalls } = await startActiveMediaTimingReview({
maxMediaDuration: 3,
});
assert.deepEqual(
await runtime.previewRange({ reviewId: 'stale-review', startTime: 10, endTime: 12 }),
{ ok: false, stale: true, message: 'This timing review is no longer active.' },
);
assert.deepEqual(
runtime.resolveReview({
reviewId: 'stale-review',
decision: { action: 'confirm', startTime: 10, endTime: 12 },
}),
{ ok: false, stale: true, message: 'This timing review is no longer active.' },
);
assert.deepEqual(
runtime.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'confirm', startTime: 10, endTime: 14 },
}),
{ ok: false, message: 'The selected timing range is invalid.' },
);
assert.deepEqual(
runtime.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'confirm', startTime: 99, endTime: 100.5 },
}),
{ ok: false, message: 'The selected timing range is invalid.' },
);
assert.deepEqual(
runtime.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'confirm', startTime: 10, endTime: 12, text: ' ' },
}),
{ ok: false, message: 'The combined sentence text is invalid.' },
);
assert.deepEqual(
runtime.resolveReview({ reviewId: payload.reviewId, decision: { action: 'discard' } }),
{ ok: true },
);
assert.deepEqual(await pendingDecision, { action: 'discard' });
assert.deepEqual(previewCalls, []);
});
test('collectMediaTimingContextLines splits cues around the mined range', () => {
const cues = [
{ text: '一行目', startTime: 0, endTime: 2 },
{ text: '二行目', startTime: 2.5, endTime: 4 },
{ text: '', startTime: 4.2, endTime: 4.4 },
{ text: '採掘行', startTime: 5, endTime: 7 },
{ text: '四行目', startTime: 7.5, endTime: 9 },
{ text: '五行目', startTime: 9.5, endTime: 11 },
];
const context = collectMediaTimingContextLines({ cues, startTime: 5, endTime: 7 });
assert.deepEqual(context.previous, [
{ text: '一行目', startTime: 0, endTime: 2 },
{ text: '二行目', startTime: 2.5, endTime: 4 },
]);
assert.deepEqual(context.next, [
{ text: '四行目', startTime: 7.5, endTime: 9 },
{ text: '五行目', startTime: 9.5, endTime: 11 },
]);
});
test('collectMediaTimingContextLines falls back to played history when no cues are loaded', () => {
const context = collectMediaTimingContextLines({
cues: [],
fallbackPrevious: [
{ displayText: '前の行', startTime: 1, endTime: 2 },
{ displayText: '採掘行', startTime: 5, endTime: 7 },
],
startTime: 5,
endTime: 7,
});
assert.deepEqual(context.previous, [{ text: '前の行', startTime: 1, endTime: 2 }]);
assert.deepEqual(context.next, []);
});
test('media timing review watchdog falls back when the renderer stops responding', async () => {
const { pendingDecision } = await startActiveMediaTimingReview({ decisionTimeoutMs: 0 });
assert.deepEqual(await pendingDecision, { action: 'use-original' });
});
test('media timing review does not resume playback when the prior state is unavailable', async () => {
const commands: Array<Array<string | number>> = [];
let runtime: ReturnType<typeof createMediaTimingReviewRuntime>;
runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async () => null,
send: ({ command }) => commands.push(command),
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => '',
generateWaveform: async () => [],
createPreviewSession: () => ({
start: async () => {
throw new Error('preview unavailable');
},
play: async () => undefined,
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async (payload) => {
queueMicrotask(() => {
runtime.resolveReview({
reviewId: payload.reviewId,
decision: { action: 'use-original' },
});
});
return true;
},
showStatus: () => undefined,
});
assert.deepEqual(
await runtime.requestReview({
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0,
maxMediaDuration: 30,
}),
{ action: 'use-original' },
);
assert.deepEqual(commands, [['set_property', 'pause', 'yes']]);
});
test('media timing review restores playback when setup fails after pausing', async () => {
const commands: Array<Array<string | number>> = [];
const runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async (name) => (name === 'pause' ? false : null),
send: ({ command }) => commands.push(command),
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => {
throw new Error('preview setup failed');
},
generateWaveform: async () => [],
createPreviewSession: () => ({
start: async () => undefined,
play: async () => undefined,
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async () => true,
showStatus: () => undefined,
});
assert.deepEqual(
await runtime.requestReview({
kind: 'word',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0,
maxMediaDuration: 30,
}),
{ action: 'use-original' },
);
assert.deepEqual(commands, [
['set_property', 'pause', 'yes'],
['set_property', 'pause', 'no'],
]);
});
test('disposing an open review settles it with original timing and restores playback', async () => {
const commands: Array<Array<string | number>> = [];
const runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async (name) => (name === 'pause' ? false : null),
send: ({ command }) => commands.push(command),
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => 'mpv',
generateWaveform: async () => [],
createPreviewSession: () => ({
start: async () => undefined,
play: async () => undefined,
stop: async () => undefined,
onPlaybackEnded: () => undefined,
dispose: () => undefined,
}),
openModal: async () => true,
showStatus: () => undefined,
});
const pending = runtime.requestReview({
kind: 'word',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0,
maxMediaDuration: 30,
});
await new Promise<void>((resolve) => setImmediate(resolve));
await runtime.dispose();
assert.deepEqual(await pending, { action: 'use-original' });
assert.deepEqual(commands, [
['set_property', 'pause', 'yes'],
['set_property', 'pause', 'no'],
]);
});
test('media timing review forwards the hidden player finishing a preview to the modal', async () => {
const endedReviewIds: string[] = [];
const playback: { ended?: () => void } = {};
let publishPayload!: (payload: MediaTimingReviewOpenPayload) => void;
const openedPayload = new Promise<MediaTimingReviewOpenPayload>((resolve) => {
publishPayload = resolve;
});
const runtime = createMediaTimingReviewRuntime({
getMpvClient: () => ({
connected: true,
currentVideoPath: '/video/show.mkv',
requestProperty: async (name) => (name === 'duration' ? 100 : null),
send: () => undefined,
}),
getCurrentMediaPath: () => '/video/show.mkv',
getMpvExecutablePath: () => 'mpv',
generateWaveform: async () => [],
createPreviewSession: () => ({
start: async () => undefined,
play: async () => undefined,
stop: async () => undefined,
onPlaybackEnded: (listener) => {
playback.ended = listener;
},
dispose: () => undefined,
}),
openModal: async (payload) => {
publishPayload(payload);
return true;
},
onPreviewEnded: (reviewId) => {
endedReviewIds.push(reviewId);
},
showStatus: () => undefined,
});
const pendingDecision = runtime.requestReview({
kind: 'sentence',
text: '字幕',
startTime: 10,
endTime: 12,
audioPadding: 0,
maxMediaDuration: 30,
});
const payload = await openedPayload;
assert.deepEqual(
await runtime.previewRange({ reviewId: payload.reviewId, startTime: 10, endTime: 12 }),
{
ok: true,
},
);
assert.ok(playback.ended);
playback.ended();
assert.deepEqual(endedReviewIds, [payload.reviewId]);
runtime.resolveReview({ reviewId: payload.reviewId, decision: { action: 'use-original' } });
await pendingDecision;
playback.ended();
assert.deepEqual(endedReviewIds, [payload.reviewId]);
});
test('preview reports a stale review when the review ends during playback', async () => {
let endReview: (() => Promise<void>) | null = null;
const { runtime, payload, pendingDecision } = await startActiveMediaTimingReview({
play: async () => {
await endReview?.();
},
});
endReview = () => runtime.dispose();
assert.deepEqual(
await runtime.previewRange({ reviewId: payload.reviewId, startTime: 10, endTime: 12 }),
{ ok: false, stale: true, message: 'This timing review is no longer active.' },
);
await pendingDecision;
});
test('waveform reports a stale review when the review ends during analysis', async () => {
let endReview: (() => Promise<void>) | null = null;
const { runtime, payload, pendingDecision } = await startActiveMediaTimingReview({
generateWaveform: async () => {
await endReview?.();
return [0.1, 0.9, 0.2];
},
});
endReview = () => runtime.dispose();
assert.deepEqual(
await runtime.getWaveform({ reviewId: payload.reviewId, startTime: 8, endTime: 14 }),
{ ok: false, stale: true, message: 'This timing review is no longer active.' },
);
await pendingDecision;
});
+589
View File
@@ -0,0 +1,589 @@
import { randomUUID } from 'crypto';
import type {
MediaTimingReviewActionResult,
MediaTimingReviewContextLine,
MediaTimingReviewDecision,
MediaTimingReviewOpenPayload,
MediaTimingReviewPreviewRequest,
MediaTimingReviewRequest,
MediaTimingReviewResolveRequest,
MediaTimingReviewWaveformRequest,
MediaTimingReviewWaveformResult,
} from '../../types/anki';
import type { SpeechWaveformOptions } from '../../core/services/media-timing-waveform';
import {
isRemoteMediaWindowSourcePath,
type RemoteMediaWindow,
type RemoteMediaWindowRange,
type RemoteMediaWindowSource,
} from '../../core/services/remote-media-window-cache';
import type { MediaInput, MediaInputOptions } from '../../media-input';
const INITIAL_TIMELINE_MARGIN_SECONDS = 2;
const REVIEW_DECISION_TIMEOUT_MS = 5 * 60_000;
const CONTEXT_LINE_LIMIT = 12;
const CONTEXT_LINE_EPSILON_SECONDS = 0.05;
interface ReviewMpvClient {
connected: boolean;
currentVideoPath: string;
currentAudioStreamIndex?: number | null;
requestProperty?: (name: string) => Promise<unknown>;
send: (payload: { command: Array<string | number> }) => void;
}
interface PreviewSession {
start(options: {
mediaPath: string;
executablePath?: string;
audioTrackId?: number;
volume?: number;
absoluteTimestamps?: boolean;
}): Promise<void>;
play(startTime: number, endTime: number): Promise<void>;
stop(): Promise<void>;
/** Fires when the player reaches the end of the clip started by play(). */
onPlaybackEnded(listener: () => void): void;
dispose(): void;
}
interface ReviewMediaSource {
path: string;
inputOptions?: MediaInputOptions;
singleResolvedStream?: boolean;
}
interface ActiveReview {
payload: MediaTimingReviewOpenPayload;
/** What the hidden mpv preview plays when no cached window is available. */
mediaPath: string;
/** What the waveform reads when no cached window is available. */
waveformMedia: MediaInput;
audioStreamIndex?: number;
/** Remote source to download windows of; null for local media or without a cache. */
windowSource: RemoteMediaWindowSource | null;
/** Latest window returned for this review; reused while it still covers the request. */
window: RemoteMediaWindow | null;
windowRequest: (RemoteMediaWindowRange & { promise: Promise<RemoteMediaWindow | null> }) | null;
windowFailed: boolean;
previewOptions: { executablePath?: string; audioTrackId?: number; volume?: number };
preview: { path: string; session: Promise<PreviewSession> } | null;
mpvClient: ReviewMpvClient;
restorePlayback: boolean;
resolve: (decision: MediaTimingReviewDecision) => void;
}
export interface MediaTimingReviewRuntimeDeps {
getMpvClient: () => ReviewMpvClient | null;
getCurrentMediaPath: () => string | null;
getMpvExecutablePath: () => string;
createPreviewSession: () => PreviewSession;
generateWaveform: (options: SpeechWaveformOptions) => Promise<number[]>;
/** Resolves the FFmpeg-readable stream URL and headers behind the current media path. */
resolveMediaSource?: () => Promise<ReviewMediaSource | null>;
/** Downloads (or reuses) a local window of a remote source covering the range. */
acquireMediaWindow?: (
source: RemoteMediaWindowSource,
range: RemoteMediaWindowRange,
) => Promise<RemoteMediaWindow>;
getSubtitleContextLines?: (range: { startTime: number; endTime: number }) => {
previous: MediaTimingReviewContextLine[];
next: MediaTimingReviewContextLine[];
};
decisionTimeoutMs?: number;
openModal: (payload: MediaTimingReviewOpenPayload) => Promise<boolean>;
/** Tells the modal that the hidden player finished the previewed clip. */
onPreviewEnded?: (reviewId: string) => void;
showStatus: (message: string) => void;
}
function finiteNumber(value: unknown): number | null {
return typeof value === 'number' && Number.isFinite(value) ? value : null;
}
function booleanProperty(value: unknown): boolean | null {
if (typeof value === 'boolean') return value;
if (value === 'yes' || value === 1) return true;
if (value === 'no' || value === 0) return false;
return null;
}
/**
* Picks the subtitle lines adjacent to the mined range that the review modal can pull
* onto the card. Parsed cues cover both directions; when none are loaded (e.g. the
* active track was never parsed) the timing tracker's history still provides the
* lines that already played, so only "next" is unavailable.
*/
export function collectMediaTimingContextLines(options: {
cues: readonly { text: string; startTime: number; endTime: number }[];
fallbackPrevious?: readonly { displayText: string; startTime: number; endTime: number }[];
startTime: number;
endTime: number;
}): { previous: MediaTimingReviewContextLine[]; next: MediaTimingReviewContextLine[] } {
const usable = options.cues
.filter(
(cue) =>
cue.text.trim().length > 0 &&
Number.isFinite(cue.startTime) &&
Number.isFinite(cue.endTime) &&
cue.endTime > cue.startTime,
)
.sort((a, b) => a.startTime - b.startTime || a.endTime - b.endTime);
let previous = usable
.filter((cue) => cue.endTime <= options.startTime + CONTEXT_LINE_EPSILON_SECONDS)
.slice(-CONTEXT_LINE_LIMIT)
.map(({ text, startTime, endTime }) => ({ text: text.trim(), startTime, endTime }));
const next = usable
.filter((cue) => cue.startTime >= options.endTime - CONTEXT_LINE_EPSILON_SECONDS)
.slice(0, CONTEXT_LINE_LIMIT)
.map(({ text, startTime, endTime }) => ({ text: text.trim(), startTime, endTime }));
if (previous.length === 0 && options.fallbackPrevious) {
previous = options.fallbackPrevious
.filter(
(entry) =>
entry.displayText.trim().length > 0 &&
Number.isFinite(entry.startTime) &&
Number.isFinite(entry.endTime) &&
entry.endTime > entry.startTime &&
entry.endTime <= options.startTime + CONTEXT_LINE_EPSILON_SECONDS,
)
.slice(-CONTEXT_LINE_LIMIT)
.map((entry) => ({
text: entry.displayText.trim(),
startTime: entry.startTime,
endTime: entry.endTime,
}));
}
return { previous, next };
}
/**
* Result for requests that name a review main has already resolved or disposed (decision
* watchdog, overlay teardown, duplicate modal). The renderer closes on it instead of
* leaving the user with controls that can never succeed.
*/
function staleReviewResult(): MediaTimingReviewActionResult {
return { ok: false, stale: true, message: 'This timing review is no longer active.' };
}
function isValidMediaTimingRange(
payload: MediaTimingReviewOpenPayload,
startTime: number,
endTime: number,
): boolean {
return (
Number.isFinite(startTime) &&
Number.isFinite(endTime) &&
startTime >= 0 &&
endTime > startTime &&
(payload.maxMediaDuration <= 0 || endTime - startTime <= payload.maxMediaDuration + 0.001) &&
(payload.mediaDuration === undefined || endTime <= payload.mediaDuration + 0.001)
);
}
export function buildMediaTimingReviewPayload(
request: MediaTimingReviewRequest,
options: {
reviewId: string;
mediaDuration?: number;
contextLines?: {
previous: MediaTimingReviewContextLine[];
next: MediaTimingReviewContextLine[];
};
},
): MediaTimingReviewOpenPayload {
const duration = finiteNumber(options.mediaDuration);
const maxTime = duration !== null && duration > 0 ? duration : Number.POSITIVE_INFINITY;
const paddedStart = Math.max(0, request.startTime - request.audioPadding);
let paddedEnd = Math.min(maxTime, request.endTime + request.audioPadding);
const maxMediaDuration = Math.max(0, request.maxMediaDuration);
if (maxMediaDuration > 0 && paddedEnd - paddedStart > maxMediaDuration) {
paddedEnd = paddedStart + maxMediaDuration;
}
if (paddedEnd <= paddedStart) {
paddedEnd = Math.min(maxTime, paddedStart + 0.1);
}
const timelineStartTime = Math.max(0, paddedStart - INITIAL_TIMELINE_MARGIN_SECONDS);
const timelineEndTime = Math.max(
paddedEnd,
Math.min(maxTime, paddedEnd + INITIAL_TIMELINE_MARGIN_SECONDS),
);
return {
reviewId: options.reviewId,
kind: request.kind,
text: request.text,
previousLines: options.contextLines?.previous ?? [],
nextLines: options.contextLines?.next ?? [],
...(request.noteId !== undefined ? { noteId: request.noteId } : {}),
originalStartTime: request.startTime,
originalEndTime: request.endTime,
selectionStartTime: paddedStart,
selectionEndTime: paddedEnd,
timelineStartTime,
timelineEndTime,
...(duration !== null && duration > 0 ? { mediaDuration: duration } : {}),
maxMediaDuration,
};
}
export function createMediaTimingReviewRuntime(deps: MediaTimingReviewRuntimeDeps) {
let active: ActiveReview | null = null;
let reviewInProgress = false;
let pendingPauseRestore: ReviewMpvClient | null = null;
function restorePendingPlayback(): void {
const mpvClient = pendingPauseRestore;
pendingPauseRestore = null;
if (mpvClient?.connected) {
mpvClient.send({ command: ['set_property', 'pause', 'no'] });
}
}
function ensureWindow(
review: ActiveReview,
range: RemoteMediaWindowRange,
): Promise<RemoteMediaWindow | null> {
const { windowSource } = review;
if (!windowSource || review.windowFailed || !deps.acquireMediaWindow) {
return Promise.resolve(null);
}
const coversRange = (candidate: RemoteMediaWindowRange): boolean =>
candidate.startTime <= range.startTime && candidate.endTime >= range.endTime;
if (review.window && coversRange(review.window)) return Promise.resolve(review.window);
const inFlight = review.windowRequest;
if (inFlight && coversRange(inFlight)) return inFlight.promise;
const request = {
startTime: range.startTime,
endTime: range.endTime,
promise: Promise.resolve<RemoteMediaWindow | null>(null),
};
request.promise = deps
.acquireMediaWindow(windowSource, { startTime: range.startTime, endTime: range.endTime })
.then((window) => {
review.window = window;
return window;
})
.catch(() => {
// Fall back to the remote source for the rest of this review instead of retrying.
review.windowFailed = true;
return null;
})
.finally(() => {
if (review.windowRequest === request) review.windowRequest = null;
});
review.windowRequest = request;
return request.promise;
}
/**
* Returns the preview player for the range, restarting it when the range needs a
* different file (the first cached window, or a wider one after the timeline grew).
*/
async function previewFor(
review: ActiveReview,
range: RemoteMediaWindowRange,
): Promise<PreviewSession> {
const window = await ensureWindow(review, range);
if (active !== review) {
// The review ended during the download; do not start a player nobody will dispose.
throw new Error('This timing review is no longer active.');
}
const mediaPath = window?.path ?? review.mediaPath;
if (review.preview?.path === mediaPath) return review.preview.session;
const previous = review.preview;
const session = deps.createPreviewSession();
session.onPlaybackEnded(() => {
if (active === review && review.preview?.session === started) {
deps.onPreviewEnded?.(review.payload.reviewId);
}
});
const { audioTrackId, ...previewOptions } = review.previewOptions;
const started = session
.start({
mediaPath,
...previewOptions,
// A cached window keeps one audio stream, so mpv's track id from the source no longer applies.
...(window
? { absoluteTimestamps: true }
: audioTrackId !== undefined
? { audioTrackId }
: {}),
})
.then(() => session)
.catch((error) => {
session.dispose();
throw error;
});
review.preview = { path: mediaPath, session: started };
void started.catch(() => {});
if (previous) void previous.session.then((old) => old.dispose()).catch(() => {});
return started;
}
async function runReview(request: MediaTimingReviewRequest): Promise<MediaTimingReviewDecision> {
const mpvClient = deps.getMpvClient();
const mediaPath =
deps.getCurrentMediaPath()?.trim() || mpvClient?.currentVideoPath?.trim() || '';
if (!mpvClient?.connected || !mediaPath) {
deps.showStatus('Timing review unavailable. Using the original subtitle timing.');
return { action: 'use-original' };
}
const [pauseRaw, durationRaw, audioTrackRaw, volumeRaw, resolvedSource] = await Promise.all([
mpvClient.requestProperty?.('pause').catch(() => null) ?? null,
mpvClient.requestProperty?.('duration').catch(() => null) ?? null,
mpvClient.requestProperty?.('aid').catch(() => null) ?? null,
mpvClient.requestProperty?.('volume').catch(() => null) ?? null,
deps.resolveMediaSource?.().catch(() => null) ?? null,
]);
const pauseState = booleanProperty(pauseRaw);
mpvClient.send({ command: ['set_property', 'pause', 'yes'] });
pendingPauseRestore = pauseState === false ? mpvClient : null;
let contextLines: ReturnType<NonNullable<typeof deps.getSubtitleContextLines>> | undefined;
try {
contextLines = deps.getSubtitleContextLines?.({
startTime: request.startTime,
endTime: request.endTime,
});
} catch {
contextLines = undefined;
}
const payload = buildMediaTimingReviewPayload(request, {
reviewId: randomUUID(),
mediaDuration: finiteNumber(durationRaw) ?? undefined,
...(contextLines ? { contextLines } : {}),
});
const sourcePath = resolvedSource?.path.trim() || mediaPath;
const inputOptions = resolvedSource?.inputOptions;
const audioStreamIndex =
resolvedSource?.singleResolvedStream || mpvClient.currentAudioStreamIndex == null
? undefined
: mpvClient.currentAudioStreamIndex;
const windowSource: RemoteMediaWindowSource | null =
deps.acquireMediaWindow && isRemoteMediaWindowSourcePath(sourcePath)
? {
path: sourcePath,
...(inputOptions ? { inputOptions } : {}),
audioStreamIndex: audioStreamIndex ?? null,
}
: null;
let resolveDecision!: (decision: MediaTimingReviewDecision) => void;
const decisionPromise = new Promise<MediaTimingReviewDecision>((resolve) => {
resolveDecision = resolve;
});
const review: ActiveReview = {
payload,
mediaPath,
waveformMedia: inputOptions ? { path: sourcePath, inputOptions } : sourcePath,
...(audioStreamIndex !== undefined ? { audioStreamIndex } : {}),
windowSource,
window: null,
windowRequest: null,
windowFailed: false,
previewOptions: {
executablePath: deps.getMpvExecutablePath(),
audioTrackId: finiteNumber(audioTrackRaw) ?? undefined,
volume: finiteNumber(volumeRaw) ?? undefined,
},
preview: null,
mpvClient,
restorePlayback: pendingPauseRestore === mpvClient,
resolve: resolveDecision,
};
active = review;
pendingPauseRestore = null;
// Download the visible timeline once now; the waveform and preview both wait on it.
void previewFor(review, {
startTime: payload.timelineStartTime,
endTime: payload.timelineEndTime,
}).catch(() => {});
const opened = await deps.openModal(payload).catch(() => false);
if (!opened) {
await cleanupActiveReview();
deps.showStatus('Timing review could not open. Using the original subtitle timing.');
return { action: 'use-original' };
}
const decisionWatchdog = setTimeout(
() => resolveDecision({ action: 'use-original' }),
Math.max(0, deps.decisionTimeoutMs ?? REVIEW_DECISION_TIMEOUT_MS),
);
let decision: MediaTimingReviewDecision;
try {
decision = await decisionPromise;
} finally {
clearTimeout(decisionWatchdog);
}
await cleanupActiveReview();
return decision;
}
async function requestReview(
request: MediaTimingReviewRequest,
): Promise<MediaTimingReviewDecision> {
if (active || reviewInProgress) {
deps.showStatus('Finish the current timing review before mining another card.');
return { action: 'use-original' };
}
reviewInProgress = true;
try {
return await runReview(request);
} catch {
await cleanupActiveReview();
restorePendingPlayback();
deps.showStatus('Timing review failed. Using the original subtitle timing.');
return { action: 'use-original' };
} finally {
reviewInProgress = false;
}
}
async function previewRange(
request: MediaTimingReviewPreviewRequest,
): Promise<MediaTimingReviewActionResult> {
const current = active;
if (!current || request.reviewId !== current.payload.reviewId) {
return staleReviewResult();
}
if (!isValidMediaTimingRange(current.payload, request.startTime, request.endTime)) {
return { ok: false, message: 'The selected preview range is invalid.' };
}
try {
const previewSession = await previewFor(current, request);
if (active !== current) {
return staleReviewResult();
}
await previewSession.play(request.startTime, request.endTime);
// Playback spans the whole clip, so the review can end (watchdog, teardown) while
// it runs; reporting success would leave the modal open on a dead review.
if (active !== current) {
return staleReviewResult();
}
return { ok: true };
} catch (error) {
if (active !== current) {
return staleReviewResult();
}
return {
ok: false,
message: `Audio preview unavailable: ${error instanceof Error ? error.message : String(error)}`,
};
}
}
async function getWaveform(
request: MediaTimingReviewWaveformRequest,
): Promise<MediaTimingReviewWaveformResult> {
const current = active;
if (!current || request.reviewId !== current.payload.reviewId) {
return staleReviewResult();
}
if (
!Number.isFinite(request.startTime) ||
!Number.isFinite(request.endTime) ||
request.startTime < 0 ||
request.endTime <= request.startTime ||
(current.payload.mediaDuration !== undefined &&
request.endTime > current.payload.mediaDuration + 0.001)
) {
return { ok: false, message: 'The waveform range is invalid.' };
}
try {
const window = await ensureWindow(current, request);
if (active !== current) {
return staleReviewResult();
}
const peaks = await deps.generateWaveform({
mediaPath: window?.media ?? current.waveformMedia,
startTime: request.startTime,
endTime: request.endTime,
...(!window && current.audioStreamIndex !== undefined
? { audioStreamIndex: current.audioStreamIndex }
: {}),
});
// ffmpeg decoding runs long enough for the review to end underneath it.
if (active !== current) {
return staleReviewResult();
}
if (peaks.length < 2 || peaks.some((peak) => !Number.isFinite(peak))) {
return { ok: false, message: 'Timing waveform is unavailable.' };
}
return { ok: true, peaks };
} catch {
if (active !== current) {
return staleReviewResult();
}
return { ok: false, message: 'Timing waveform is unavailable.' };
}
}
async function stopPreview(reviewId: string): Promise<MediaTimingReviewActionResult> {
const current = active;
if (!current || reviewId !== current.payload.reviewId) {
return staleReviewResult();
}
try {
const previewSession = current.preview ? await current.preview.session : null;
await previewSession?.stop();
return { ok: true };
} catch (error) {
return {
ok: false,
message: `Could not stop preview: ${error instanceof Error ? error.message : String(error)}`,
};
}
}
function resolveReview(request: MediaTimingReviewResolveRequest): MediaTimingReviewActionResult {
const current = active;
if (!current || request.reviewId !== current.payload.reviewId) {
return staleReviewResult();
}
if (request.decision.action === 'confirm') {
const { startTime, endTime, text } = request.decision;
if (!isValidMediaTimingRange(current.payload, startTime, endTime)) {
return { ok: false, message: 'The selected timing range is invalid.' };
}
if (text !== undefined && (typeof text !== 'string' || text.trim().length === 0)) {
return { ok: false, message: 'The combined sentence text is invalid.' };
}
}
current.resolve(request.decision);
return { ok: true };
}
async function cleanupActiveReview(): Promise<void> {
const current = active;
active = null;
if (!current) return;
void current.preview?.session.then((session) => session.dispose()).catch(() => {});
if (current.restorePlayback && current.mpvClient.connected) {
current.mpvClient.send({ command: ['set_property', 'pause', 'no'] });
}
}
async function dispose(): Promise<void> {
active?.resolve({ action: 'use-original' });
await cleanupActiveReview();
restorePendingPlayback();
}
return {
requestReview,
previewRange,
getWaveform,
stopPreview,
resolveReview,
dispose,
};
}
@@ -3,6 +3,7 @@ import test from 'node:test';
import { parseSubtitleCues } from '../../core/services/subtitle-cue-parser';
import {
resolveCanonicalPrimarySubtitle,
resolvePrimarySubtitle,
resolvePrimarySubtitleText,
stripCanonicalFragmentLines,
} from './primary-subtitle-text';
@@ -702,3 +703,37 @@ test('resolvePrimarySubtitleText publishes a wrapped caption sentence as one cue
'(東)≪好きだと\n自覚してしまったものの➡',
);
});
test('resolvePrimarySubtitle drops a finished caption row lingering beside a fresh line', () => {
// Broadcast captions give each row its own event, and a row of the previous line can
// outlive its siblings by a frame. mpv's sub-text still lists it, so the mined line
// must come from the parsed cue that is actually running, with that cue's timings.
const ass = [
'[Script Info]',
'PlayResY: 540',
'',
'[Events]',
'Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text',
'Dialogue: 0,0:14:30.00,0:14:33.00,Default,,0,0,0,,{\\pos(232,437)\\fscx50}{\\fscx100}東{\\fscx50}{\\fscx100}ずっと 言えなかっ',
'Dialogue: 0,0:14:30.00,0:14:33.02,Default,,0,0,0,,{\\pos(232,497)}たが',
'Dialogue: 0,0:14:33.00,0:14:36.00,Default,,0,0,0,,{\\pos(232,437)}⸨もし お互い',
'Dialogue: 0,0:14:33.00,0:14:36.00,Default,,0,0,0,,{\\pos(232,497)}本命 受かったら 大学 近いし➡',
].join('\n');
const cues = parseSubtitleCues(ass, 'polar-opposites-s02e09.ass');
const resolved = resolvePrimarySubtitle({
liveText: 'たが\n⸨もし お互い\n本命 受かったら 大学 近いし➡',
currentTimeSec: 14 * 60 + 33.05,
cues,
});
assert.deepEqual(
{ ...resolved, cues: resolved?.cues.map((cue) => cue.text) },
{
text: '⸨もし お互い\n本命 受かったら 大学 近いし➡',
startTime: 14 * 60 + 33,
endTime: 14 * 60 + 36,
cues: ['⸨もし お互い\n本命 受かったら 大学 近いし➡'],
},
);
});
+21 -9
View File
@@ -319,6 +319,26 @@ export function resolveRecordedPrimarySubtitleText(options: {
);
}
/**
* The parsed view of the live text with its cue timings: a canonical animation when one
* explains the live lines, otherwise the active parsed cues. Null when the parsed cues
* cannot account for every live line, in which case callers keep the raw mpv text.
*/
export function resolvePrimarySubtitle(options: {
liveText: string;
currentTimeSec: number;
cues: readonly SubtitleCue[] | null | undefined;
}): ResolvedPrimarySubtitle | null {
const liveText = decodedLiveText(options.liveText, options.cues);
if (!liveText.trim()) {
return null;
}
return (
resolveCanonicalPrimarySubtitle({ ...options, liveText }) ??
resolveActiveParsedPrimarySubtitle({ ...options, liveText })
);
}
export function resolvePrimarySubtitleText(options: {
liveText: string;
currentTimeSec: number;
@@ -328,13 +348,5 @@ export function resolvePrimarySubtitleText(options: {
if (!liveText.trim()) {
return liveText;
}
return (
resolveCanonicalPrimarySubtitle({
liveText,
currentTimeSec: options.currentTimeSec,
cues: options.cues,
})?.text ??
resolveActiveParsedPrimarySubtitle({ ...options, liveText })?.text ??
removeLiveGlyphFragmentLines(liveText)
);
return resolvePrimarySubtitle(options)?.text ?? removeLiveGlyphFragmentLines(liveText);
}