feat(youtube): add mediaCache mode and safer stream media extraction (#130)

This commit is contained in:
2026-06-27 19:20:18 -07:00
committed by GitHub
parent d199376364
commit 5326ad32f5
52 changed files with 4065 additions and 165 deletions
@@ -2,6 +2,7 @@ import assert from 'node:assert/strict';
import test from 'node:test';
import { CardCreationService } from './card-creation';
import type { MediaInput } from '../media-generator';
import type { AnkiConnectConfig } from '../types/anki';
type CardCreationDeps = ConstructorParameters<typeof CardCreationService>[0];
@@ -266,6 +267,8 @@ test('manual clipboard subtitle update skips audio when sentence audio field is
test('manual clipboard subtitle update uses resolved mpv stream URLs for remote media', async () => {
const audioPaths: string[] = [];
const imagePaths: string[] = [];
const recordMediaPath = (mediaInput: MediaInput): string =>
typeof mediaInput === 'string' ? mediaInput : mediaInput.path;
const edlSource = [
'edl://!new_stream;!no_clip;!no_chapters;%70%https://audio.example/videoplayback?mime=audio%2Fwebm',
'!new_stream;!no_clip;!no_chapters;%69%https://video.example/videoplayback?mime=video%2Fmp4',
@@ -338,11 +341,11 @@ test('manual clipboard subtitle update uses resolved mpv stream URLs for remote
},
mediaGenerator: {
generateAudio: async (path) => {
audioPaths.push(path);
audioPaths.push(recordMediaPath(path));
return Buffer.from('audio');
},
generateScreenshot: async (path) => {
imagePaths.push(path);
imagePaths.push(recordMediaPath(path));
return Buffer.from('image');
},
generateAnimatedImage: async () => null,
+258 -2
View File
@@ -2,6 +2,7 @@ import assert from 'node:assert/strict';
import test from 'node:test';
import { CardCreationService } from './card-creation';
import type { MediaInput } from '../media-generator';
import type { AnkiConnectConfig } from '../types/anki';
test('CardCreationService counts locally created sentence cards', async () => {
@@ -287,6 +288,8 @@ test('CardCreationService keeps updating after recordCardsMinedCallback throws',
test('CardCreationService uses stream-open-filename for remote media generation', async () => {
const audioPaths: string[] = [];
const imagePaths: string[] = [];
const recordMediaPath = (mediaInput: MediaInput): string =>
typeof mediaInput === 'string' ? mediaInput : mediaInput.path;
const edlSource = [
'edl://!new_stream;!no_clip;!no_chapters;%70%https://audio.example/videoplayback?mime=audio%2Fwebm',
'!new_stream;!no_clip;!no_chapters;%69%https://video.example/videoplayback?mime=video%2Fmp4',
@@ -345,11 +348,11 @@ test('CardCreationService uses stream-open-filename for remote media generation'
},
mediaGenerator: {
generateAudio: async (path) => {
audioPaths.push(path);
audioPaths.push(recordMediaPath(path));
return Buffer.from('audio');
},
generateScreenshot: async (path) => {
imagePaths.push(path);
imagePaths.push(recordMediaPath(path));
return Buffer.from('image');
},
generateAnimatedImage: async () => null,
@@ -398,6 +401,259 @@ test('CardCreationService uses stream-open-filename for remote media generation'
assert.deepEqual(imagePaths, ['https://video.example/videoplayback?mime=video%2Fmp4']);
});
test('CardCreationService does not use mpv stream indexes for ready cached YouTube media', async () => {
const audioCalls: Array<{ path: string; audioStreamIndex?: number }> = [];
const service = new CardCreationService({
getConfig: () =>
({
deck: 'Mining',
fields: {
sentence: 'Sentence',
audio: 'SentenceAudio',
image: 'Picture',
},
media: {
generateAudio: true,
generateImage: false,
imageFormat: 'jpg',
},
behavior: {},
ai: false,
}) as AnkiConnectConfig,
getAiConfig: () => ({}),
getTimingTracker: () => ({}) as never,
getMpvClient: () =>
({
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
currentSubText: '字幕',
currentSubStart: 10,
currentSubEnd: 12,
currentTimePos: 11,
currentAudioStreamIndex: 0,
}) as never,
getCachedMediaPath: async () => '/tmp/subminer-youtube-media-cache/media.mkv',
shouldRequireRemoteMediaCache: () => true,
client: {
addNote: async () => 42,
addTags: async () => undefined,
notesInfo: async () => [
{
noteId: 42,
fields: {
Sentence: { value: '' },
SentenceAudio: { value: '' },
Picture: { value: '' },
},
},
],
updateNoteFields: async () => undefined,
storeMediaFile: async () => undefined,
findNotes: async () => [],
retrieveMediaFile: async () => '',
},
mediaGenerator: {
generateAudio: async (path, _startTime, _endTime, _padding, audioStreamIndex) => {
audioCalls.push({ path: typeof path === 'string' ? path : path.path, audioStreamIndex });
return Buffer.from('audio');
},
generateScreenshot: async () => null,
generateAnimatedImage: async () => null,
},
showOsdNotification: () => undefined,
showUpdateResult: () => undefined,
showStatusNotification: () => undefined,
showNotification: async () => undefined,
beginUpdateProgress: () => undefined,
endUpdateProgress: () => undefined,
withUpdateProgress: async (_message, action) => action(),
resolveConfiguredFieldName: (noteInfo, preferredName) => {
if (!preferredName) return null;
return Object.keys(noteInfo.fields).find((field) => field === preferredName) ?? null;
},
resolveNoteFieldName: (noteInfo, preferredName) => {
if (!preferredName) return null;
return Object.keys(noteInfo.fields).find((field) => field === preferredName) ?? null;
},
getAnimatedImageLeadInSeconds: async () => 0,
extractFields: () => ({}),
processSentence: (sentence) => sentence,
setCardTypeFields: () => undefined,
mergeFieldValue: (_existing, newValue) => newValue,
formatMiscInfoPattern: () => '',
getEffectiveSentenceCardConfig: () => ({
model: 'Sentence',
sentenceField: 'Sentence',
audioField: 'SentenceAudio',
lapisEnabled: false,
kikuEnabled: false,
kikuFieldGrouping: 'disabled',
kikuDeleteDuplicateInAuto: false,
}),
getFallbackDurationSeconds: () => 10,
appendKnownWordsFromNoteInfo: () => undefined,
isUpdateInProgress: () => false,
setUpdateInProgress: () => undefined,
trackLastAddedNoteId: () => undefined,
});
const created = await service.createSentenceCard('テスト', 10, 12);
assert.equal(created, true);
assert.deepEqual(audioCalls, [
{
path: '/tmp/subminer-youtube-media-cache/media.mkv',
audioStreamIndex: undefined,
},
]);
});
test('CardCreationService queues YouTube media when required cache is not ready', async () => {
const mediaCalls: string[] = [];
const updates: Array<{ noteId: number; fields: Record<string, string> }> = [];
const queuedUpdates: Array<{
sourceUrl: string;
noteId: number;
startTime: number;
endTime: number;
label: string | number;
audioFieldName?: string;
imageFieldName?: string;
miscInfoFieldName?: string;
generateAudio: boolean;
generateImage: boolean;
}> = [];
let streamRequests = 0;
const service = new CardCreationService({
getConfig: () =>
({
deck: 'Mining',
fields: {
sentence: 'Sentence',
audio: 'SentenceAudio',
image: 'Picture',
miscInfo: 'MiscInfo',
},
media: {
generateAudio: true,
generateImage: true,
imageFormat: 'jpg',
},
behavior: {},
ai: false,
}) as AnkiConnectConfig,
getAiConfig: () => ({}),
getTimingTracker: () => ({}) as never,
getMpvClient: () =>
({
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
currentSubText: '字幕',
currentSubStart: 10,
currentSubEnd: 12,
currentTimePos: 11,
currentAudioStreamIndex: 2,
requestProperty: async () => {
streamRequests += 1;
return 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123';
},
}) as never,
getCachedMediaPath: async () => null,
shouldRequireRemoteMediaCache: () => true,
queuePendingYoutubeMediaUpdate: (job) => {
queuedUpdates.push(job);
},
client: {
addNote: async () => 42,
addTags: async () => undefined,
notesInfo: async () => [
{
noteId: 42,
fields: {
Sentence: { value: '' },
SentenceAudio: { value: '' },
Picture: { value: '' },
MiscInfo: { value: '' },
},
},
],
updateNoteFields: async (noteId, fields) => {
updates.push({ noteId, fields });
},
storeMediaFile: async () => undefined,
findNotes: async () => [],
retrieveMediaFile: async () => '',
},
mediaGenerator: {
generateAudio: async () => {
mediaCalls.push('audio');
return Buffer.from('audio');
},
generateScreenshot: async () => {
mediaCalls.push('image');
return Buffer.from('image');
},
generateAnimatedImage: async () => null,
},
showOsdNotification: () => undefined,
showUpdateResult: () => undefined,
showStatusNotification: () => undefined,
showNotification: async () => undefined,
beginUpdateProgress: () => undefined,
endUpdateProgress: () => undefined,
withUpdateProgress: async (_message, action) => action(),
resolveConfiguredFieldName: (noteInfo, preferredName) => {
if (!preferredName) return null;
return Object.keys(noteInfo.fields).find((field) => field === preferredName) ?? null;
},
resolveNoteFieldName: (noteInfo, preferredName) => {
if (!preferredName) return null;
return Object.keys(noteInfo.fields).find((field) => field === preferredName) ?? null;
},
getAnimatedImageLeadInSeconds: async () => 0,
extractFields: () => ({}),
processSentence: (sentence) => sentence,
setCardTypeFields: () => undefined,
mergeFieldValue: (_existing, newValue) => newValue,
formatMiscInfoPattern: () => '',
getEffectiveSentenceCardConfig: () => ({
model: 'Sentence',
sentenceField: 'Sentence',
audioField: 'SentenceAudio',
lapisEnabled: false,
kikuEnabled: false,
kikuFieldGrouping: 'disabled',
kikuDeleteDuplicateInAuto: false,
}),
getFallbackDurationSeconds: () => 10,
appendKnownWordsFromNoteInfo: () => undefined,
isUpdateInProgress: () => false,
setUpdateInProgress: () => undefined,
trackLastAddedNoteId: () => undefined,
});
const created = await service.createSentenceCard('テスト', 10, 12);
assert.equal(created, true);
assert.equal(streamRequests, 0);
assert.deepEqual(mediaCalls, []);
assert.deepEqual(queuedUpdates, [
{
sourceUrl: 'https://www.youtube.com/watch?v=abc123',
noteId: 42,
startTime: 10,
endTime: 12,
label: 'テスト',
audioFieldName: 'SentenceAudio',
imageFieldName: 'Picture',
miscInfoFieldName: 'MiscInfo',
generateAudio: true,
generateImage: true,
},
]);
assert.deepEqual(updates, []);
});
test('CardCreationService tracks pre-add duplicate note ids for kiku sentence cards', async () => {
const trackedDuplicates: Array<{ noteId: number; duplicateNoteIds: number[] }> = [];
const duplicateLookupExpressions: string[] = [];
+125 -49
View File
@@ -5,15 +5,29 @@ import {
} from '../anki-field-config';
import { AnkiConnectConfig } from '../types/anki';
import { createLogger } from '../logger';
import type { MediaInput } from '../media-input';
import { SubtitleTimingTracker } from '../subtitle-timing-tracker';
import { AiConfig } from '../types/integrations';
import { MpvClient } from '../types/runtime';
import { resolveSentenceBackText } from './ai';
import { resolveMediaGenerationInputPath } from './media-source';
import {
resolveMediaGenerationInput,
resolveAudioStreamIndexForMediaGeneration,
type MediaGenerationInputResolverOptions,
} from './media-source';
import { shouldMarkWordAndSentenceCard } from './note-field-utils';
import type { PendingYoutubeMediaUpdate } from './pending-youtube-media';
const log = createLogger('anki').child('integration.card-creation');
function shouldGenerateAudio(config: AnkiConnectConfig): boolean {
return config.media?.generateAudio !== false;
}
function shouldGenerateImage(config: AnkiConnectConfig): boolean {
return config.media?.generateImage !== false;
}
export interface CardCreationNoteInfo {
noteId: number;
fields: Record<string, { value: string }>;
@@ -38,14 +52,14 @@ interface CardCreationClient {
interface CardCreationMediaGenerator {
generateAudio(
path: string,
path: MediaInput,
startTime: number,
endTime: number,
audioPadding?: number,
audioStreamIndex?: number,
): Promise<Buffer | null>;
generateScreenshot(
path: string,
path: MediaInput,
timestamp: number,
options: {
format: 'jpg' | 'png' | 'webp';
@@ -55,7 +69,7 @@ interface CardCreationMediaGenerator {
},
): Promise<Buffer | null>;
generateAnimatedImage(
path: string,
path: MediaInput,
startTime: number,
endTime: number,
audioPadding?: number,
@@ -74,6 +88,9 @@ interface CardCreationDeps {
getAiConfig: () => AiConfig;
getTimingTracker: () => SubtitleTimingTracker;
getMpvClient: () => MpvClient;
getCachedMediaPath?: MediaGenerationInputResolverOptions['getCachedMediaPath'];
shouldRequireRemoteMediaCache?: () => boolean;
queuePendingYoutubeMediaUpdate?: (job: PendingYoutubeMediaUpdate) => void;
getDeck?: () => string | undefined;
client: CardCreationClient;
mediaGenerator: CardCreationMediaGenerator;
@@ -121,6 +138,19 @@ interface CardCreationDeps {
export class CardCreationService {
constructor(private readonly deps: CardCreationDeps) {}
private getMediaResolverOptions(): MediaGenerationInputResolverOptions {
const options: MediaGenerationInputResolverOptions = {
logDebug: (message) => log.debug(message),
};
if (this.deps.getCachedMediaPath) {
options.getCachedMediaPath = this.deps.getCachedMediaPath;
}
if (this.deps.shouldRequireRemoteMediaCache?.()) {
options.remoteCacheMode = 'required';
}
return options;
}
private getConfiguredAnkiTags(): string[] {
const tags = this.deps.getConfig().tags;
if (!Array.isArray(tags)) {
@@ -246,14 +276,18 @@ export class CardCreationService {
`Clipboard update: timing range ${rangeStart.toFixed(2)}s - ${rangeEnd.toFixed(2)}s`,
);
const audioSourcePath = this.deps.getConfig().media?.generateAudio
? await resolveMediaGenerationInputPath(mpvClient, 'audio')
const config = this.deps.getConfig();
const generateAudio = shouldGenerateAudio(config);
const generateImage = shouldGenerateImage(config);
const mediaResolverOptions = this.getMediaResolverOptions();
const audioSourcePath = generateAudio
? await resolveMediaGenerationInput(mpvClient, 'audio', mediaResolverOptions)
: null;
const videoPath = this.deps.getConfig().media?.generateImage
? await resolveMediaGenerationInputPath(mpvClient, 'video')
const videoPath = generateImage
? await resolveMediaGenerationInput(mpvClient, 'video', mediaResolverOptions)
: null;
if (this.deps.getConfig().media?.generateAudio) {
if (generateAudio) {
try {
const audioFilename = this.generateAudioFilename();
const audioBuffer = audioSourcePath
@@ -281,7 +315,7 @@ export class CardCreationService {
}
}
if (this.deps.getConfig().media?.generateImage) {
if (generateImage) {
try {
const animatedLeadInSeconds = await this.deps.getAnimatedImageLeadInSeconds(noteInfo);
const imageFilename = this.generateImageFilename();
@@ -441,7 +475,7 @@ export class CardCreationService {
errors.push('audio');
}
if (this.deps.getConfig().media?.generateImage) {
if (shouldGenerateImage(this.deps.getConfig())) {
try {
const animatedLeadInSeconds = await this.deps.getAnimatedImageLeadInSeconds(noteInfo);
const imageFilename = this.generateImageFilename();
@@ -522,9 +556,23 @@ export class CardCreationService {
try {
return await this.deps.withUpdateProgress('Creating sentence card', async () => {
const videoPath = await resolveMediaGenerationInputPath(mpvClient, 'video');
const audioSourcePath = await resolveMediaGenerationInputPath(mpvClient, 'audio');
if (!videoPath) {
const config = this.deps.getConfig();
const generateAudio = shouldGenerateAudio(config);
const generateImage = shouldGenerateImage(config);
const mediaResolverOptions = this.getMediaResolverOptions();
const videoPath = generateImage
? await resolveMediaGenerationInput(mpvClient, 'video', mediaResolverOptions)
: null;
const audioSourcePath = generateAudio
? await resolveMediaGenerationInput(mpvClient, 'audio', mediaResolverOptions)
: null;
const missingRequestedMediaInput =
(generateImage && !videoPath) || (generateAudio && !audioSourcePath);
const shouldQueuePendingYoutubeMedia =
missingRequestedMediaInput &&
this.deps.shouldRequireRemoteMediaCache?.() === true &&
typeof this.deps.queuePendingYoutubeMediaUpdate === 'function';
if (missingRequestedMediaInput && !shouldQueuePendingYoutubeMedia) {
this.deps.showOsdNotification('No video loaded');
return false;
}
@@ -534,13 +582,13 @@ export class CardCreationService {
const sentenceField = sentenceCardConfig.sentenceField;
const audioFieldName = sentenceCardConfig.audioField || 'SentenceAudio';
const translationField = this.deps.getConfig().fields?.translation || 'SelectionText';
const translationField = config.fields?.translation || 'SelectionText';
let resolvedMiscInfoField: string | null = null;
let resolvedSentenceAudioField: string = audioFieldName;
fields[sentenceField] = sentence;
const ankiAiConfig = this.deps.getConfig().ai;
const ankiAiConfig = config.ai;
const ankiAiEnabled =
typeof ankiAiConfig === 'object' && ankiAiConfig !== null
? ankiAiConfig.enabled === true
@@ -563,7 +611,7 @@ export class CardCreationService {
if (sentenceCardConfig.lapisEnabled || sentenceCardConfig.kikuEnabled) {
fields.IsSentenceCard = 'x';
fields[getConfiguredWordFieldName(this.deps.getConfig())] = sentence;
fields[getConfiguredWordFieldName(config)] = sentence;
}
const pendingNoteInfo = this.createPendingNoteInfo(fields);
@@ -572,7 +620,7 @@ export class CardCreationService {
);
const pendingExpressionText = getPreferredWordValueFromExtractedFields(
pendingNoteFields,
this.deps.getConfig(),
config,
).trim();
let duplicateNoteIds: number[] = [];
if (
@@ -590,7 +638,7 @@ export class CardCreationService {
}
}
const deck = this.deps.getConfig().deck || 'Default';
const deck = config.deck || 'Default';
let noteId: number;
try {
noteId = await this.deps.client.addNote(
@@ -636,7 +684,7 @@ export class CardCreationService {
this.deps.resolveNoteFieldName(createdNoteInfo, audioFieldName) || audioFieldName;
resolvedMiscInfoField = this.deps.resolveConfiguredFieldName(
createdNoteInfo,
this.deps.getConfig().fields?.miscInfo,
config.fields?.miscInfo,
);
const cardTypeFields: Record<string, string> = {};
@@ -654,41 +702,67 @@ export class CardCreationService {
errors.push('card type fields');
}
const label = sentence.length > 30 ? sentence.substring(0, 30) + '...' : sentence;
if (shouldQueuePendingYoutubeMedia) {
this.deps.queuePendingYoutubeMediaUpdate?.({
sourceUrl: mpvClient.currentVideoPath,
noteId,
startTime,
endTime,
label,
audioFieldName: resolvedSentenceAudioField,
imageFieldName: config.fields?.image,
miscInfoFieldName: resolvedMiscInfoField ?? undefined,
generateAudio,
generateImage,
});
await this.deps.showNotification(noteId, label, 'media queued');
return true;
}
if (missingRequestedMediaInput) {
return false;
}
const mediaFields: Record<string, string> = {};
try {
const audioFilename = this.generateAudioFilename();
const audioBuffer = audioSourcePath
? await this.mediaGenerateAudio(audioSourcePath, startTime, endTime)
: null;
if (generateAudio) {
try {
const audioFilename = this.generateAudioFilename();
const audioBuffer = audioSourcePath
? await this.mediaGenerateAudio(audioSourcePath, startTime, endTime)
: null;
if (audioBuffer) {
await this.deps.client.storeMediaFile(audioFilename, audioBuffer);
const audioValue = `[sound:${audioFilename}]`;
mediaFields[resolvedSentenceAudioField] = audioValue;
miscInfoFilename = audioFilename;
if (audioBuffer) {
await this.deps.client.storeMediaFile(audioFilename, audioBuffer);
const audioValue = `[sound:${audioFilename}]`;
mediaFields[resolvedSentenceAudioField] = audioValue;
miscInfoFilename = audioFilename;
}
} catch (error) {
log.error('Failed to generate sentence audio:', (error as Error).message);
errors.push('audio');
}
} catch (error) {
log.error('Failed to generate sentence audio:', (error as Error).message);
errors.push('audio');
}
try {
const imageFilename = this.generateImageFilename();
const imageBuffer = await this.generateImageBuffer(videoPath, startTime, endTime);
if (generateImage) {
try {
const imageFilename = this.generateImageFilename();
const imageBuffer = await this.generateImageBuffer(videoPath!, startTime, endTime);
const imageField = this.deps.getConfig().fields?.image;
if (imageBuffer && imageField) {
await this.deps.client.storeMediaFile(imageFilename, imageBuffer);
mediaFields[imageField] = `<img src="${imageFilename}">`;
miscInfoFilename = imageFilename;
const imageField = config.fields?.image;
if (imageBuffer && imageField) {
await this.deps.client.storeMediaFile(imageFilename, imageBuffer);
mediaFields[imageField] = `<img src="${imageFilename}">`;
miscInfoFilename = imageFilename;
}
} catch (error) {
log.error('Failed to generate sentence image:', (error as Error).message);
errors.push('image');
}
} catch (error) {
log.error('Failed to generate sentence image:', (error as Error).message);
errors.push('image');
}
if (this.deps.getConfig().fields?.miscInfo) {
if (config.fields?.miscInfo) {
const miscInfo = this.deps.formatMiscInfoPattern(miscInfoFilename || '', startTime);
if (miscInfo && resolvedMiscInfoField) {
mediaFields[resolvedMiscInfoField] = miscInfo;
@@ -704,7 +778,6 @@ export class CardCreationService {
}
}
const label = sentence.length > 30 ? sentence.substring(0, 30) + '...' : sentence;
const errorSuffix = errors.length > 0 ? `${errors.join(', ')} failed` : undefined;
await this.deps.showNotification(noteId, label, errorSuffix);
return true;
@@ -740,7 +813,7 @@ export class CardCreationService {
}
private async mediaGenerateAudio(
videoPath: string,
videoPath: MediaInput,
startTime: number,
endTime: number,
): Promise<Buffer | null> {
@@ -754,12 +827,15 @@ export class CardCreationService {
startTime,
endTime,
this.deps.getConfig().media?.audioPadding,
mpvClient.currentAudioStreamIndex ?? undefined,
resolveAudioStreamIndexForMediaGeneration(
videoPath,
mpvClient.currentAudioStreamIndex ?? undefined,
),
);
}
private async generateImageBuffer(
videoPath: string,
videoPath: MediaInput,
startTime: number,
endTime: number,
animatedLeadInSeconds = 0,
+235 -1
View File
@@ -1,7 +1,33 @@
import assert from 'node:assert/strict';
import test from 'node:test';
import { resolveMediaGenerationInputPath } from './media-source';
import * as mediaSource from './media-source';
const { resolveMediaGenerationInputPath } = mediaSource;
type StructuredMediaInput = {
path: string;
source: string;
singleResolvedStream: boolean;
inputOptions?: {
reconnect?: boolean;
userAgent?: string;
headers?: Record<string, string>;
};
};
type StructuredMediaResolver = (
mpvClient: Parameters<typeof resolveMediaGenerationInputPath>[0],
kind?: Parameters<typeof resolveMediaGenerationInputPath>[1],
options?: {
getCachedMediaPath?: (
currentVideoPath: string,
kind: Parameters<typeof resolveMediaGenerationInputPath>[1],
) => Promise<string | null>;
remoteCacheMode?: 'optional' | 'required';
logDebug?: (message: string) => void;
},
) => Promise<StructuredMediaInput | null>;
test('resolveMediaGenerationInputPath keeps local file paths', async () => {
const result = await resolveMediaGenerationInputPath({
@@ -62,3 +88,211 @@ test('resolveMediaGenerationInputPath falls back to currentVideoPath when stream
assert.equal(result, 'https://www.youtube.com/watch?v=abc123');
});
test('resolveMediaGenerationInput returns single-stream metadata for mpv EDL URLs', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const edlSource = [
'edl://!new_stream;!no_clip;!no_chapters;%70%https://audio.example/videoplayback?mime=audio%2Fwebm',
'!new_stream;!no_clip;!no_chapters;%69%https://video.example/videoplayback?mime=video%2Fmp4',
].join(';');
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
requestProperty: async (name: string) => {
if (name === 'stream-open-filename') return edlSource;
if (name === 'user-agent') return 'Mozilla/5.0';
if (name === 'http-header-fields') {
return ['Cookie: SID=secret', 'Referer: https://www.youtube.com/', 'X-Test: ok'];
}
return null;
},
},
'audio',
);
assert.equal(result?.path, 'https://audio.example/videoplayback?mime=audio%2Fwebm');
assert.equal(result?.singleResolvedStream, true);
assert.equal(result?.inputOptions?.reconnect, true);
assert.equal(result?.inputOptions?.userAgent, 'Mozilla/5.0');
assert.deepEqual(result?.inputOptions?.headers, {
Referer: 'https://www.youtube.com/',
'X-Test': 'ok',
});
});
test('resolveMediaGenerationInput reads file-local mpv request options', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
requestProperty: async (name: string) => {
if (name === 'stream-open-filename') {
return 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123';
}
if (name === 'file-local-options/user-agent') return 'SubMiner Test Agent';
if (name === 'options/http-header-fields') return ['X-Shared: ok'];
if (name === 'file-local-options/http-header-fields') {
return ['Cookie: SID=secret', 'Referer: https://m.youtube.com/', 'X-Local: yes'];
}
return null;
},
},
'video',
);
assert.equal(result?.path, 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123');
assert.equal(result?.singleResolvedStream, true);
assert.equal(result?.inputOptions?.userAgent, 'SubMiner Test Agent');
assert.deepEqual(result?.inputOptions?.headers, {
'X-Shared': 'ok',
Referer: 'https://m.youtube.com/',
'X-Local': 'yes',
Origin: 'https://www.youtube.com',
});
});
test('resolveMediaGenerationInput prefers a ready cached media file for YouTube extraction', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
requestProperty: async () => 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123',
},
'video',
{
getCachedMediaPath: async () => '/tmp/subminer-youtube-media-cache/abc123/media.mkv',
},
);
assert.equal(result?.path, '/tmp/subminer-youtube-media-cache/abc123/media.mkv');
assert.equal(result?.source, 'youtube-cache');
assert.equal(result?.singleResolvedStream, false);
assert.equal(result?.inputOptions, undefined);
});
test('resolveMediaGenerationInput debug-logs sanitized YouTube cache hits', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const logs: string[] = [];
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123&signature=secret',
requestProperty: async () => 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123',
},
'video',
{
getCachedMediaPath: async () => '/tmp/subminer-youtube-media-cache/abc123/media.mkv',
logDebug: (message) => logs.push(message),
},
);
assert.equal(result?.source, 'youtube-cache');
assert.match(logs.join('\n'), /kind=video source=youtube-cache/);
assert.match(
logs.join('\n'),
/input=local:\/tmp\/subminer-youtube-media-cache\/abc123\/media\.mkv/,
);
assert.match(logs.join('\n'), /current=remote:www\.youtube\.com/);
assert.doesNotMatch(logs.join('\n'), /signature=secret|videoplayback/);
});
test('resolveMediaGenerationInput does not fall back to direct remote streams when cache is required', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
requestProperty: async () => 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123',
},
'video',
{
getCachedMediaPath: async () => null,
remoteCacheMode: 'required',
},
);
assert.equal(result, null);
});
test('resolveMediaGenerationInput falls back when optional cache lookup fails', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123',
requestProperty: async () => 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123',
},
'video',
{
getCachedMediaPath: async () => {
throw new Error('cache unavailable');
},
},
);
assert.equal(result?.path, 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123');
assert.equal(result?.source, 'stream-open-filename');
});
test('resolveMediaGenerationInput debug-logs sanitized required-cache misses', async () => {
const resolver = (
mediaSource as typeof mediaSource & {
resolveMediaGenerationInput?: StructuredMediaResolver;
}
).resolveMediaGenerationInput;
assert.equal(typeof resolver, 'function');
const logs: string[] = [];
const result = await resolver!(
{
currentVideoPath: 'https://www.youtube.com/watch?v=abc123&signature=secret',
requestProperty: async () => 'https://rr1---sn.example.googlevideo.com/videoplayback?id=123',
},
'video',
{
getCachedMediaPath: async () => null,
remoteCacheMode: 'required',
logDebug: (message) => logs.push(message),
},
);
assert.equal(result, null);
assert.match(logs.join('\n'), /kind=video source=cache-miss/);
assert.match(logs.join('\n'), /mode=required/);
assert.match(logs.join('\n'), /current=remote:www\.youtube\.com/);
assert.doesNotMatch(logs.join('\n'), /signature=secret|videoplayback|googlevideo/);
});
+372
View File
@@ -1,7 +1,57 @@
import { isRemoteMediaPath } from '../jimaku/utils';
import type { MediaInput, MediaInputOptions } from '../media-input';
import type { MpvClient } from '../types/runtime';
export type MediaGenerationKind = 'audio' | 'video';
export type MediaGenerationInputSource =
| 'current-path'
| 'stream-open-filename'
| 'edl-stream'
| 'youtube-cache';
export interface ResolvedMediaGenerationInput {
path: string;
kind: MediaGenerationKind;
source: MediaGenerationInputSource;
singleResolvedStream: boolean;
inputOptions?: MediaInputOptions;
}
export interface MediaGenerationInputResolverOptions {
getCachedMediaPath?: (
currentVideoPath: string,
kind: MediaGenerationKind,
) => Promise<string | null>;
remoteCacheMode?: 'optional' | 'required';
logDebug?: (message: string) => void;
}
export function resolveAudioStreamIndexForMediaGeneration(
input: MediaInput,
audioStreamIndex: number | null | undefined,
): number | undefined {
if (typeof input === 'object' && 'source' in input && input.source === 'youtube-cache') {
return undefined;
}
return audioStreamIndex ?? undefined;
}
const BLOCKED_HTTP_HEADER_NAMES = new Set(['authorization', 'cookie', 'proxy-authorization']);
const HTTP_HEADER_FIELD_PROPERTY_NAMES = [
'http-header-fields',
'options/http-header-fields',
'file-local-options/http-header-fields',
] as const;
const USER_AGENT_PROPERTY_NAMES = [
'file-local-options/user-agent',
'options/user-agent',
'user-agent',
] as const;
const REFERRER_PROPERTY_NAMES = [
'file-local-options/referrer',
'options/referrer',
'referrer',
] as const;
function trimToNonEmptyString(value: unknown): string | null {
if (typeof value !== 'string') {
@@ -11,6 +61,17 @@ function trimToNonEmptyString(value: unknown): string | null {
return trimmed.length > 0 ? trimmed : null;
}
function normalizeHeaderName(value: string): string | null {
const trimmed = value.trim();
if (!/^[A-Za-z0-9!#$%&'*+.^_`|~-]+$/.test(trimmed)) {
return null;
}
if (BLOCKED_HTTP_HEADER_NAMES.has(trimmed.toLowerCase())) {
return null;
}
return trimmed;
}
function extractUrlsFromMpvEdlSource(source: string): string[] {
const matches = source.matchAll(/%\d+%(https?:\/\/.*?)(?=;!new_stream|;!global_tags|$)/gms);
return [...matches]
@@ -53,6 +114,317 @@ function resolvePreferredUrlFromMpvEdlSource(
return kind === 'audio' ? (urls[0] ?? null) : (urls[urls.length - 1] ?? null);
}
function getHostname(value: string): string | null {
try {
return new URL(value).hostname.toLowerCase();
} catch {
return null;
}
}
function matchesHost(hostname: string, expectedHost: string): boolean {
return hostname === expectedHost || hostname.endsWith(`.${expectedHost}`);
}
function isGoogleVideoMediaPath(value: string): boolean {
const host = getHostname(value);
return Boolean(host && matchesHost(host, 'googlevideo.com'));
}
function describeMediaPathForDebugLog(value: string): string {
try {
const url = new URL(value);
if (url.protocol === 'http:' || url.protocol === 'https:') {
return `remote:${url.hostname.toLowerCase() || 'unknown'}`;
}
return `${url.protocol.replace(/:$/, '')}:`;
} catch {
// Not a URL; treat as a local file path below.
}
if (value.startsWith('edl://')) {
return 'edl:';
}
return `local:${value}`;
}
function logMediaResolutionDebug(
options: MediaGenerationInputResolverOptions,
message: string,
): void {
if (!options.logDebug) {
return;
}
try {
options.logDebug(`[media-source] ${message}`);
} catch {
// Debug logging should not affect media generation.
}
}
function logResolvedMediaGenerationInput(
options: MediaGenerationInputResolverOptions,
currentVideoPath: string,
result: ResolvedMediaGenerationInput,
): void {
logMediaResolutionDebug(
options,
[
`kind=${result.kind}`,
`source=${result.source}`,
`input=${describeMediaPathForDebugLog(result.path)}`,
`current=${describeMediaPathForDebugLog(currentVideoPath)}`,
`singleResolvedStream=${result.singleResolvedStream}`,
].join(' '),
);
}
function logMediaGenerationInputMiss(
options: MediaGenerationInputResolverOptions,
kind: MediaGenerationKind,
currentVideoPath: string,
reason: string,
): void {
logMediaResolutionDebug(
options,
[
`kind=${kind}`,
'source=cache-miss',
`reason=${reason}`,
`mode=${options.remoteCacheMode ?? 'optional'}`,
`current=${describeMediaPathForDebugLog(currentVideoPath)}`,
].join(' '),
);
}
function setHeaderIfMissing(headers: Record<string, string>, name: string, value: string): void {
const lowerName = name.toLowerCase();
if (!Object.keys(headers).some((existing) => existing.toLowerCase() === lowerName)) {
headers[name] = value;
}
}
function parseMpvHeaderField(value: string): [string, string] | null {
const separatorIndex = value.indexOf(':');
if (separatorIndex <= 0) {
return null;
}
const name = normalizeHeaderName(value.slice(0, separatorIndex));
const headerValue = trimToNonEmptyString(value.slice(separatorIndex + 1));
if (!name || !headerValue) {
return null;
}
return [name, headerValue.replace(/[\r\n]+/g, ' ')];
}
function toHeaderFields(value: unknown): string[] {
if (Array.isArray(value)) {
return value.filter((entry): entry is string => typeof entry === 'string');
}
if (typeof value === 'string') {
return value
.split(/\r?\n/)
.map((entry) => entry.trim())
.filter((entry) => entry.length > 0);
}
return [];
}
async function requestOptionalMpvProperty(
mpvClient: Pick<MpvClient, 'requestProperty'>,
name: string,
): Promise<unknown> {
if (!mpvClient.requestProperty) {
return null;
}
try {
return await mpvClient.requestProperty(name);
} catch {
return null;
}
}
async function requestFirstNonEmptyStringProperty(
mpvClient: Pick<MpvClient, 'requestProperty'>,
names: readonly string[],
): Promise<string | null> {
for (const name of names) {
const value = trimToNonEmptyString(await requestOptionalMpvProperty(mpvClient, name));
if (value) {
return value;
}
}
return null;
}
async function resolveRemoteInputOptions(
mpvClient: Pick<MpvClient, 'requestProperty'>,
resolvedPath: string,
): Promise<MediaInputOptions | undefined> {
if (!isRemoteMediaPath(resolvedPath) || !mpvClient.requestProperty) {
return undefined;
}
const headers: Record<string, string> = {};
for (const propertyName of HTTP_HEADER_FIELD_PROPERTY_NAMES) {
const mpvHeaderFields = toHeaderFields(
await requestOptionalMpvProperty(mpvClient, propertyName),
);
for (const field of mpvHeaderFields) {
const parsed = parseMpvHeaderField(field);
if (parsed) {
headers[parsed[0]] = parsed[1];
}
}
}
const userAgent = await requestFirstNonEmptyStringProperty(mpvClient, USER_AGENT_PROPERTY_NAMES);
const referrer = await requestFirstNonEmptyStringProperty(mpvClient, REFERRER_PROPERTY_NAMES);
if (referrer) {
setHeaderIfMissing(headers, 'Referer', referrer);
}
if (isGoogleVideoMediaPath(resolvedPath)) {
setHeaderIfMissing(headers, 'Referer', 'https://www.youtube.com/');
setHeaderIfMissing(headers, 'Origin', 'https://www.youtube.com');
}
return {
reconnect: true,
...(userAgent ? { userAgent } : {}),
...(Object.keys(headers).length > 0 ? { headers } : {}),
};
}
async function toResolvedMediaGenerationInput(
mpvClient: Pick<MpvClient, 'requestProperty'>,
path: string,
kind: MediaGenerationKind,
source: MediaGenerationInputSource,
singleResolvedStream: boolean,
): Promise<ResolvedMediaGenerationInput> {
const inputOptions = await resolveRemoteInputOptions(mpvClient, path);
return {
path,
kind,
source,
singleResolvedStream,
...(inputOptions ? { inputOptions } : {}),
};
}
export async function resolveMediaGenerationInput(
mpvClient: Pick<MpvClient, 'currentVideoPath' | 'requestProperty'> | null | undefined,
kind: MediaGenerationKind = 'video',
options: MediaGenerationInputResolverOptions = {},
): Promise<ResolvedMediaGenerationInput | null> {
const currentVideoPath = trimToNonEmptyString(mpvClient?.currentVideoPath);
if (!currentVideoPath) {
logMediaResolutionDebug(options, `kind=${kind} source=none reason=no-current-video`);
return null;
}
if (!isRemoteMediaPath(currentVideoPath)) {
const result: ResolvedMediaGenerationInput = {
path: currentVideoPath,
kind,
source: 'current-path',
singleResolvedStream: false,
};
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
let cachedPath: string | null = null;
if (options.getCachedMediaPath) {
try {
cachedPath = trimToNonEmptyString(await options.getCachedMediaPath(currentVideoPath, kind));
} catch {
cachedPath = null;
}
}
if (cachedPath) {
const result: ResolvedMediaGenerationInput = {
path: cachedPath,
kind,
source: 'youtube-cache',
singleResolvedStream: false,
};
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
if (options.remoteCacheMode === 'required') {
logMediaGenerationInputMiss(options, kind, currentVideoPath, 'required-cache-unavailable');
return null;
}
if (!mpvClient?.requestProperty) {
const result: ResolvedMediaGenerationInput = {
path: currentVideoPath,
kind,
source: 'current-path',
singleResolvedStream: false,
};
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
try {
const streamOpenFilename = trimToNonEmptyString(
await mpvClient.requestProperty('stream-open-filename'),
);
if (streamOpenFilename?.startsWith('edl://')) {
const preferredUrl = resolvePreferredUrlFromMpvEdlSource(streamOpenFilename, kind);
if (preferredUrl) {
const result = await toResolvedMediaGenerationInput(
mpvClient,
preferredUrl,
kind,
'edl-stream',
true,
);
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
const result = await toResolvedMediaGenerationInput(
mpvClient,
streamOpenFilename,
kind,
'stream-open-filename',
false,
);
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
if (streamOpenFilename) {
const result = await toResolvedMediaGenerationInput(
mpvClient,
streamOpenFilename,
kind,
'stream-open-filename',
isRemoteMediaPath(streamOpenFilename),
);
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
} catch {
// Fall back to the current path when mpv does not expose a resolved stream URL.
}
const result = await toResolvedMediaGenerationInput(
mpvClient,
currentVideoPath,
kind,
'current-path',
false,
);
logResolvedMediaGenerationInput(options, currentVideoPath, result);
return result;
}
export async function resolveMediaGenerationInputPath(
mpvClient: Pick<MpvClient, 'currentVideoPath' | 'requestProperty'> | null | undefined,
kind: MediaGenerationKind = 'video',
@@ -409,3 +409,59 @@ test('NoteUpdateWorkflow uses subtitle sidebar context for sentence media timing
assert.deepEqual(imageContext, sidebarContext);
assert.equal(miscInfoStartTime, 10);
});
test('NoteUpdateWorkflow queues media updates when YouTube cache is pending', async () => {
const harness = createWorkflowHarness();
const queuedUpdates: Array<{
noteId: number;
noteInfo: NoteUpdateWorkflowNoteInfo;
context?: SubtitleMiningContext;
label: string | number;
}> = [];
const mediaCalls: string[] = [];
harness.deps.client.notesInfo = async () =>
[
{
noteId: 42,
fields: {
Expression: { value: 'taberu' },
Sentence: { value: '' },
SentenceAudio: { value: '' },
Picture: { value: '' },
},
},
] satisfies NoteUpdateWorkflowNoteInfo[];
harness.deps.getConfig = () => ({
fields: {
sentence: 'Sentence',
image: 'Picture',
},
media: {
generateAudio: true,
generateImage: true,
},
behavior: {},
});
harness.deps.generateAudio = async () => {
mediaCalls.push('audio');
return Buffer.from('audio');
};
harness.deps.generateImage = async () => {
mediaCalls.push('image');
return Buffer.from('image');
};
harness.deps.queuePendingYoutubeMediaUpdate = async (job) => {
queuedUpdates.push(job);
return true;
};
await harness.workflow.execute(42);
assert.deepEqual(mediaCalls, []);
assert.equal(queuedUpdates.length, 1);
assert.equal(queuedUpdates[0]?.noteId, 42);
assert.equal(queuedUpdates[0]?.label, 'taberu');
assert.equal(queuedUpdates[0]?.context, undefined);
assert.deepEqual(harness.updates, [{ noteId: 42, fields: { Sentence: 'subtitle-text' } }]);
});
+24 -5
View File
@@ -85,6 +85,12 @@ export interface NoteUpdateWorkflowDeps {
) => Promise<Buffer | null>;
formatMiscInfoPattern: (fallbackFilename: string, startTimeSeconds?: number) => string;
consumeSubtitleMiningContext?: () => SubtitleMiningContext | null;
queuePendingYoutubeMediaUpdate?: (job: {
noteId: number;
noteInfo: NoteUpdateWorkflowNoteInfo;
context?: SubtitleMiningContext;
label: string | number;
}) => Promise<boolean>;
addConfiguredTagsToNote: (noteId: number) => Promise<void>;
showNotification: (noteId: number, label: string | number) => Promise<void>;
showOsdNotification: (message: string) => void;
@@ -195,6 +201,7 @@ export class NoteUpdateWorkflow {
sentenceField,
config.fields?.sentence,
);
const noteLabel = hasExpressionText ? expressionText : noteId;
const currentSubtitleText = subtitleMiningContext?.text ?? this.deps.getCurrentSubtitleText();
if (sentenceField && currentSubtitleText) {
@@ -227,7 +234,19 @@ export class NoteUpdateWorkflow {
}
}
if (config.media?.generateAudio) {
const generateAudio = config.media?.generateAudio !== false;
const generateImage = config.media?.generateImage !== false;
const mediaCacheQueued =
(generateAudio || generateImage) && this.deps.queuePendingYoutubeMediaUpdate
? await this.deps.queuePendingYoutubeMediaUpdate({
noteId,
noteInfo,
context: subtitleMiningContext ?? undefined,
label: noteLabel,
})
: false;
if (!mediaCacheQueued && generateAudio) {
try {
const audioFilename = this.deps.generateAudioFilename();
const audioBuffer = await this.deps.generateAudio(subtitleMiningContext ?? undefined);
@@ -252,7 +271,7 @@ export class NoteUpdateWorkflow {
}
}
if (config.media?.generateImage) {
if (!mediaCacheQueued && generateImage) {
try {
const animatedLeadInSeconds = await this.deps.getAnimatedImageLeadInSeconds(noteInfo);
const imageFilename = this.deps.generateImageFilename();
@@ -287,7 +306,7 @@ export class NoteUpdateWorkflow {
}
}
if (config.fields?.miscInfo) {
if (!mediaCacheQueued && config.fields?.miscInfo) {
const miscInfo = this.deps.formatMiscInfoPattern(
miscInfoFilename || '',
subtitleMiningContext?.startTime ?? this.deps.getCurrentSubtitleStart(),
@@ -305,8 +324,8 @@ export class NoteUpdateWorkflow {
if (updatePerformed) {
await this.deps.client.updateNoteFields(noteId, updatedFields);
await this.deps.addConfiguredTagsToNote(noteId);
this.deps.logInfo('Updated card fields for:', hasExpressionText ? expressionText : noteId);
await this.deps.showNotification(noteId, hasExpressionText ? expressionText : noteId);
this.deps.logInfo('Updated card fields for:', noteLabel);
await this.deps.showNotification(noteId, noteLabel);
}
if (shouldRunFieldGrouping && hasExpressionText && duplicateNoteId !== null) {
@@ -0,0 +1,193 @@
import assert from 'node:assert/strict';
import test from 'node:test';
import type { AnkiConnectConfig } from '../types/anki';
import {
PendingYoutubeMediaQueue,
type PendingYoutubeMediaQueueDeps,
} from './pending-youtube-media-queue';
function createDeps(
overrides: Partial<PendingYoutubeMediaQueueDeps> = {},
): PendingYoutubeMediaQueueDeps {
const warnings: unknown[][] = [];
const deps: PendingYoutubeMediaQueueDeps & { warnings: unknown[][] } = {
client: {
notesInfo: async () => [],
updateNoteFields: async () => {},
storeMediaFile: async () => {},
},
mediaGenerator: {
generateAudio: async () => Buffer.from('audio'),
generateScreenshot: async () => Buffer.from('image'),
generateAnimatedImage: async () => Buffer.from('image'),
},
getConfig: () =>
({
media: { generateAudio: true, generateImage: true },
fields: {},
}) as AnkiConnectConfig,
getCurrentVideoPath: () => 'https://www.youtube.com/watch?v=abc123',
getCachedMediaPath: async () => null,
shouldRequireRemoteMediaCache: () => true,
getSubtitleMediaRange: () => ({ startTime: 1, endTime: 2 }),
getResolvedSentenceAudioFieldName: () => 'SentenceAudio',
resolveConfiguredFieldName: () => 'Picture',
mergeFieldValue: (_existing, newValue) => newValue,
getAnimatedImageLeadInSeconds: async () => 0,
generateAudioFilename: () => 'audio.mp3',
generateImageFilename: () => 'image.webp',
formatMiscInfoPatternForMediaPath: () => '',
showStatusNotification: () => {},
showNotification: async () => {},
logInfo: () => {},
logWarn: (...args) => {
warnings.push(args);
},
logError: () => {},
warnings,
...overrides,
};
return deps;
}
test('PendingYoutubeMediaQueue treats cache lookup failures as an immediate generation fallback', async () => {
const deps = createDeps({
getCachedMediaPath: async () => {
throw new Error('cache unavailable');
},
});
const queue = new PendingYoutubeMediaQueue(deps);
const queued = await queue.queueFromNote({
noteId: 42,
noteInfo: { noteId: 42, fields: {} },
label: 'demo',
});
assert.equal(queued, false);
assert.deepEqual((deps as typeof deps & { warnings: unknown[][] }).warnings, [
[
'Failed to read YouTube cache state; falling back to immediate media generation:',
'cache unavailable',
],
]);
});
test('PendingYoutubeMediaQueue drains matching queued jobs when the cache download fails', async () => {
const statusMessages: string[] = [];
const notifications: Array<{ noteId: number; label: string | number; suffix?: string }> = [];
const updatedNotes: number[] = [];
const deps = createDeps({
client: {
notesInfo: async (noteIds) =>
noteIds.map((noteId) => ({
noteId,
fields: {
SentenceAudio: { value: '' },
Picture: { value: '' },
},
})),
updateNoteFields: async (noteId) => {
updatedNotes.push(noteId);
},
storeMediaFile: async () => {},
},
showStatusNotification: (message) => {
statusMessages.push(message);
},
showNotification: async (noteId, label, suffix) => {
notifications.push({ noteId, label, suffix });
},
});
const queue = new PendingYoutubeMediaQueue(deps);
queue.enqueue({
sourceUrl: 'https://www.youtube.com/watch?v=abc123',
noteId: 42,
startTime: 1,
endTime: 2,
label: 'queued',
generateAudio: true,
generateImage: true,
});
await queue.handleFailed('https://youtu.be/abc123');
await queue.handleReady('https://youtu.be/abc123', '/tmp/media.mkv');
assert.deepEqual(updatedNotes, []);
assert.deepEqual(notifications, [{ noteId: 42, label: 'queued', suffix: 'media cache failed' }]);
assert.equal(
statusMessages.includes('YouTube media cache failed. Media was not added to 1 queued card.'),
true,
);
});
test('PendingYoutubeMediaQueue defaults missing media flags to enabled when queuing from notes', async () => {
const updatedNotes: Array<{ noteId: number; fields: Record<string, string> }> = [];
const storedMedia: string[] = [];
const deps = createDeps({
client: {
notesInfo: async (noteIds) =>
noteIds.map((noteId) => ({
noteId,
fields: {
SentenceAudio: { value: '' },
Picture: { value: '' },
},
})),
updateNoteFields: async (noteId, fields) => {
updatedNotes.push({ noteId, fields });
},
storeMediaFile: async (filename) => {
storedMedia.push(filename);
},
},
getConfig: () => ({ media: {}, fields: { image: 'Picture' } }) as AnkiConnectConfig,
});
const queue = new PendingYoutubeMediaQueue(deps);
const queued = await queue.queueFromNote({
noteId: 42,
noteInfo: { noteId: 42, fields: {} },
label: 'demo',
});
await queue.handleReady('https://youtu.be/abc123', '/tmp/media.mkv');
assert.equal(queued, true);
assert.equal(updatedNotes.length, 1);
assert.equal(storedMedia.length, 2);
assert.match(updatedNotes[0]?.fields.SentenceAudio ?? '', /^\[sound:audio\.mp3\]$/);
assert.match(updatedNotes[0]?.fields.Picture ?? '', /^<img src="image\.webp">$/);
});
test('PendingYoutubeMediaQueue only announces a download once per source while jobs collect', () => {
const statusMessages: string[] = [];
const deps = createDeps({
showStatusNotification: (message) => {
statusMessages.push(message);
},
});
const queue = new PendingYoutubeMediaQueue(deps);
queue.enqueue({
sourceUrl: 'https://youtu.be/abc123',
noteId: 1,
startTime: 1,
endTime: 2,
label: 'first',
generateAudio: true,
generateImage: false,
});
queue.enqueue({
sourceUrl: 'https://www.youtube.com/watch?v=abc123',
noteId: 2,
startTime: 3,
endTime: 4,
label: 'second',
generateAudio: false,
generateImage: true,
});
assert.equal(statusMessages.length, 1);
});
@@ -0,0 +1,391 @@
import { DEFAULT_ANKI_CONNECT_CONFIG } from '../config';
import type { MediaInput } from '../media-input';
import type { MediaGenerator } from '../media-generator';
import type { AnkiConnectConfig } from '../types/anki';
import type { SubtitleMiningContext } from '../types/subtitle';
import { youtubeMediaUrlsMatch, type PendingYoutubeMediaUpdate } from './pending-youtube-media';
import type { MediaGenerationInputResolverOptions } from './media-source';
type PendingYoutubeMediaUpdateResult = 'updated' | 'partial' | 'failed';
export interface PendingYoutubeMediaQueueReadyOptions {
notifyNoQueued?: boolean;
}
export interface PendingYoutubeMediaQueueFailedOptions {
notifyStatus?: boolean;
}
export interface PendingYoutubeMediaNoteInfo {
noteId: number;
fields: Record<string, { value: string }>;
}
export interface PendingYoutubeMediaQueueDeps {
client: {
notesInfo(noteIds: number[]): Promise<unknown>;
updateNoteFields(noteId: number, fields: Record<string, string>): Promise<void>;
storeMediaFile(filename: string, data: Buffer): Promise<void>;
};
mediaGenerator: Pick<
MediaGenerator,
'generateAudio' | 'generateScreenshot' | 'generateAnimatedImage'
>;
getConfig: () => AnkiConnectConfig;
getCurrentVideoPath: () => string | undefined;
getCachedMediaPath: MediaGenerationInputResolverOptions['getCachedMediaPath'] | null;
shouldRequireRemoteMediaCache: () => boolean;
getSubtitleMediaRange: (context?: SubtitleMiningContext) => {
startTime: number;
endTime: number;
};
getResolvedSentenceAudioFieldName: (noteInfo: PendingYoutubeMediaNoteInfo) => string | null;
resolveConfiguredFieldName: (
noteInfo: PendingYoutubeMediaNoteInfo,
...preferredNames: (string | undefined)[]
) => string | null;
mergeFieldValue: (existing: string, newValue: string, overwrite: boolean) => string;
getAnimatedImageLeadInSeconds: (noteInfo: PendingYoutubeMediaNoteInfo) => Promise<number>;
generateAudioFilename: () => string;
generateImageFilename: () => string;
formatMiscInfoPatternForMediaPath: (
fallbackFilename: string,
startTimeSeconds: number | undefined,
mediaPath: string,
mediaTitle?: string,
) => string;
showStatusNotification: (message: string) => void;
showNotification: (noteId: number, label: string | number, errorSuffix?: string) => Promise<void>;
logInfo: (message: string, ...args: unknown[]) => void;
logWarn: (message: string, ...args: unknown[]) => void;
logError: (message: string, ...args: unknown[]) => void;
}
function trimToNonEmptyString(value: unknown): string | null {
if (typeof value !== 'string') {
return null;
}
const trimmed = value.trim();
return trimmed.length > 0 ? trimmed : null;
}
function shouldGenerateAudio(config: AnkiConnectConfig): boolean {
return config.media?.generateAudio !== false;
}
function shouldGenerateImage(config: AnkiConnectConfig): boolean {
return config.media?.generateImage !== false;
}
export class PendingYoutubeMediaQueue {
private updates: PendingYoutubeMediaUpdate[] = [];
constructor(private readonly deps: PendingYoutubeMediaQueueDeps) {}
enqueue(job: PendingYoutubeMediaUpdate): void {
if (!job.generateAudio && !job.generateImage) {
return;
}
const isFirstQueuedForSource = !this.updates.some((existing) =>
youtubeMediaUrlsMatch(existing.sourceUrl, job.sourceUrl),
);
this.updates.push(job);
this.deps.logInfo('Queued YouTube media update for note:', job.noteId);
if (isFirstQueuedForSource) {
this.deps.showStatusNotification(
'YouTube media cache is still downloading. Card media will be added when the cache is ready.',
);
}
}
async queueFromNote(job: {
noteId: number;
noteInfo: PendingYoutubeMediaNoteInfo;
context?: SubtitleMiningContext;
label: string | number;
}): Promise<boolean> {
const sourceUrl = trimToNonEmptyString(this.deps.getCurrentVideoPath());
const getCachedMediaPath = this.deps.getCachedMediaPath;
if (!sourceUrl || this.deps.shouldRequireRemoteMediaCache() !== true || !getCachedMediaPath) {
return false;
}
let cachedPath: string | null = null;
try {
cachedPath = await getCachedMediaPath(sourceUrl, 'video');
} catch (error) {
this.deps.logWarn(
'Failed to read YouTube cache state; falling back to immediate media generation:',
error instanceof Error ? error.message : String(error),
);
return false;
}
if (cachedPath) {
return false;
}
const config = this.deps.getConfig();
const mediaRange = this.deps.getSubtitleMediaRange(job.context);
this.enqueue({
sourceUrl,
noteId: job.noteId,
startTime: mediaRange.startTime,
endTime: mediaRange.endTime,
label: job.label,
audioFieldName: this.deps.getResolvedSentenceAudioFieldName(job.noteInfo) ?? undefined,
imageFieldName:
this.deps.resolveConfiguredFieldName(
job.noteInfo,
config.fields?.image,
DEFAULT_ANKI_CONNECT_CONFIG.fields.image,
) ?? undefined,
miscInfoFieldName:
this.deps.resolveConfiguredFieldName(job.noteInfo, config.fields?.miscInfo) ?? undefined,
generateAudio: shouldGenerateAudio(config),
generateImage: shouldGenerateImage(config),
});
return true;
}
async handleReady(
sourceUrl: string,
cachedPath: string,
options: PendingYoutubeMediaQueueReadyOptions = {},
): Promise<void> {
const jobs = this.takeMatchingUpdates(sourceUrl);
if (jobs.length === 0) {
if (options.notifyNoQueued !== false) {
this.deps.showStatusNotification('YouTube media cache ready.');
}
return;
}
this.deps.showStatusNotification(
`YouTube media cache ready. Adding media to ${jobs.length} queued card${
jobs.length === 1 ? '' : 's'
}.`,
);
let updatedCount = 0;
let partialCount = 0;
let failedCount = 0;
for (const job of jobs) {
try {
const result = await this.applyUpdate(job, cachedPath);
if (result === 'updated') {
updatedCount += 1;
} else if (result === 'partial') {
partialCount += 1;
} else {
failedCount += 1;
}
} catch (error) {
failedCount += 1;
this.deps.logError(
'Failed to apply queued YouTube media update:',
error instanceof Error ? error.message : String(error),
);
}
}
if (partialCount > 0 || failedCount > 0) {
this.deps.showStatusNotification(
`Queued YouTube media finished with ${updatedCount} updated, ${partialCount} partial, and ${failedCount} failed.`,
);
}
}
async handleFailed(
sourceUrl: string,
options: PendingYoutubeMediaQueueFailedOptions = {},
): Promise<void> {
const jobs = this.takeMatchingUpdates(sourceUrl);
if (jobs.length === 0) {
if (options.notifyStatus !== false) {
this.deps.showStatusNotification('YouTube media cache failed.');
}
return;
}
if (options.notifyStatus !== false) {
this.deps.showStatusNotification(
`YouTube media cache failed. Media was not added to ${jobs.length} queued card${
jobs.length === 1 ? '' : 's'
}.`,
);
}
this.deps.logWarn('Discarding queued YouTube media updates after cache failure:', jobs.length);
for (const job of jobs) {
try {
await this.deps.showNotification(job.noteId, job.label, 'media cache failed');
} catch (error) {
this.deps.logWarn(
'Failed to show queued YouTube media failure notification:',
error instanceof Error ? error.message : String(error),
);
}
}
}
private takeMatchingUpdates(sourceUrl: string): PendingYoutubeMediaUpdate[] {
const matched: PendingYoutubeMediaUpdate[] = [];
const remaining: PendingYoutubeMediaUpdate[] = [];
for (const job of this.updates) {
if (youtubeMediaUrlsMatch(job.sourceUrl, sourceUrl)) {
matched.push(job);
} else {
remaining.push(job);
}
}
this.updates = remaining;
return matched;
}
private async applyUpdate(
job: PendingYoutubeMediaUpdate,
cachedPath: string,
): Promise<PendingYoutubeMediaUpdateResult> {
const notesInfoResult = await this.deps.client.notesInfo([job.noteId]);
const notesInfo = notesInfoResult as unknown as PendingYoutubeMediaNoteInfo[];
const noteInfo = notesInfo[0];
if (!noteInfo) {
this.deps.logWarn('Queued YouTube media target note not found:', job.noteId);
return 'failed';
}
const config = this.deps.getConfig();
const mediaFields: Record<string, string> = {};
const errors: string[] = [];
let miscInfoFilename: string | null = null;
const cachedMediaInput: MediaInput = {
path: cachedPath,
source: 'youtube-cache',
};
if (job.generateAudio) {
try {
const audioFilename = this.deps.generateAudioFilename();
const audioBuffer = await this.deps.mediaGenerator.generateAudio(
cachedMediaInput,
job.startTime,
job.endTime,
config.media?.audioPadding,
undefined,
);
if (audioBuffer) {
await this.deps.client.storeMediaFile(audioFilename, audioBuffer);
const audioField =
job.audioFieldName || this.deps.getResolvedSentenceAudioFieldName(noteInfo) || null;
if (audioField) {
const existingAudio = noteInfo.fields[audioField]?.value || '';
mediaFields[audioField] = this.deps.mergeFieldValue(
existingAudio,
`[sound:${audioFilename}]`,
config.behavior?.overwriteAudio !== false,
);
}
miscInfoFilename = audioFilename;
}
} catch (error) {
errors.push('audio');
this.deps.logError('Failed to generate queued YouTube audio:', (error as Error).message);
}
}
if (job.generateImage) {
try {
const imageFilename = this.deps.generateImageFilename();
const animatedLeadInSeconds = await this.deps.getAnimatedImageLeadInSeconds(noteInfo);
const imageBuffer = await this.generateImageFromInput(
cachedMediaInput,
job.startTime,
job.endTime,
animatedLeadInSeconds,
);
if (imageBuffer) {
await this.deps.client.storeMediaFile(imageFilename, imageBuffer);
const imageField =
job.imageFieldName ||
this.deps.resolveConfiguredFieldName(
noteInfo,
config.fields?.image,
DEFAULT_ANKI_CONNECT_CONFIG.fields.image,
);
if (imageField) {
const existingImage = noteInfo.fields[imageField]?.value || '';
mediaFields[imageField] = this.deps.mergeFieldValue(
existingImage,
`<img src="${imageFilename}">`,
config.behavior?.overwriteImage !== false,
);
} else {
this.deps.logWarn(
'Image field not found on queued YouTube media note, skipping image update',
);
}
miscInfoFilename = imageFilename;
}
} catch (error) {
errors.push('image');
this.deps.logError('Failed to generate queued YouTube image:', (error as Error).message);
}
}
if (config.fields?.miscInfo && miscInfoFilename) {
const miscInfoField =
job.miscInfoFieldName ||
this.deps.resolveConfiguredFieldName(noteInfo, config.fields.miscInfo);
const miscInfo = this.deps.formatMiscInfoPatternForMediaPath(
miscInfoFilename,
job.startTime,
job.sourceUrl,
);
if (miscInfoField && miscInfo) {
mediaFields[miscInfoField] = miscInfo;
}
}
if (Object.keys(mediaFields).length === 0) {
return 'failed';
}
await this.deps.client.updateNoteFields(job.noteId, mediaFields);
const errorSuffix = errors.length > 0 ? `${errors.join(', ')} failed` : undefined;
await this.deps.showNotification(job.noteId, job.label, errorSuffix);
this.deps.logInfo('Applied queued YouTube media update for note:', job.noteId);
return errors.length === 0 ? 'updated' : 'partial';
}
private async generateImageFromInput(
videoPath: MediaInput,
startTime: number,
endTime: number,
animatedLeadInSeconds = 0,
): Promise<Buffer | null> {
const config = this.deps.getConfig();
if (config.media?.imageType === 'avif') {
return this.deps.mediaGenerator.generateAnimatedImage(
videoPath,
startTime,
endTime,
config.media?.audioPadding,
{
fps: config.media?.animatedFps,
maxWidth: config.media?.animatedMaxWidth,
maxHeight: config.media?.animatedMaxHeight,
crf: config.media?.animatedCrf,
leadingStillDuration: animatedLeadInSeconds,
},
);
}
const timestamp = startTime + (endTime - startTime) / 2;
return this.deps.mediaGenerator.generateScreenshot(videoPath, timestamp, {
format: config.media?.imageFormat as 'jpg' | 'png' | 'webp',
quality: config.media?.imageQuality,
maxWidth: config.media?.imageMaxWidth,
maxHeight: config.media?.imageMaxHeight,
});
}
}
@@ -0,0 +1,53 @@
export interface PendingYoutubeMediaUpdate {
sourceUrl: string;
noteId: number;
startTime: number;
endTime: number;
label: string | number;
audioFieldName?: string;
imageFieldName?: string;
miscInfoFieldName?: string;
generateAudio: boolean;
generateImage: boolean;
}
function trimToNonEmptyString(value: unknown): string | null {
if (typeof value !== 'string') {
return null;
}
const trimmed = value.trim();
return trimmed.length > 0 ? trimmed : null;
}
function getYoutubeVideoId(rawUrl: string): string | null {
try {
const parsed = new URL(rawUrl);
const host = parsed.hostname.toLowerCase();
if (host === 'youtu.be' || host.endsWith('.youtu.be')) {
return trimToNonEmptyString(parsed.pathname.replace(/^\/+/, '').split('/')[0]);
}
if (host === 'youtube.com' || host.endsWith('.youtube.com')) {
const watchId = trimToNonEmptyString(parsed.searchParams.get('v'));
if (watchId) {
return watchId;
}
const parts = parsed.pathname.split('/').filter(Boolean);
if (parts[0] === 'shorts' || parts[0] === 'embed' || parts[0] === 'live') {
return trimToNonEmptyString(parts[1]);
}
}
} catch {
return null;
}
return null;
}
export function youtubeMediaUrlsMatch(a: string, b: string): boolean {
if (a.trim() === b.trim()) {
return true;
}
const aVideoId = getYoutubeVideoId(a);
const bVideoId = getYoutubeVideoId(b);
return Boolean(aVideoId && bVideoId && aVideoId === bVideoId);
}