Deduplicate voice actor image downloads per AniList person ID

- Avoid repeated downloads when multiple characters share the same voice actor - Add coverage for shared voice actor image download behavior
2026-03-06 19:57:26 -08:00 · 2026-03-06 17:21:19 -08:00
parent 4d60f64bea
commit 94abd0f372
2 changed files with 292 additions and 40 deletions
--- a/src/main/character-dictionary-runtime.test.ts
+++ b/src/main/character-dictionary-runtime.test.ts
@@ -160,8 +160,19 @@ test('generateForCurrentMedia emits structured-content glossary so image stays w
    });

    const result = await runtime.generateForCurrentMedia();
-    const termBank = JSON.parse(readStoredZipEntry(result.zipPath, 'term_bank_1.json').toString('utf8')) as Array<
-      [string, string, string, string, number, Array<string | Record<string, unknown>>, number, string]
+    const termBank = JSON.parse(
+      readStoredZipEntry(result.zipPath, 'term_bank_1.json').toString('utf8'),
+    ) as Array<
+      [
+        string,
+        string,
+        string,
+        string,
+        number,
+        Array<string | Record<string, unknown>>,
+        number,
+        string,
+      ]
    >;
    const alexia = termBank.find(([term]) => term === 'アレクシア');

@@ -205,8 +216,10 @@ test('generateForCurrentMedia emits structured-content glossary so image stays w
    assert.equal(badge.content, 'Side Character');

    const descSection = children.find(
-      (c) => (c as { tag?: string }).tag === 'details' && Array.isArray((c as { content?: unknown[] }).content) &&
-        ((c as { content: Array<{ content?: string }> }).content[0]?.content === 'Description'),
+      (c) =>
+        (c as { tag?: string }).tag === 'details' &&
+        Array.isArray((c as { content?: unknown[] }).content) &&
+        (c as { content: Array<{ content?: string }> }).content[0]?.content === 'Description',
    ) as { tag: string; content: Array<Record<string, unknown>> } | undefined;
    assert.ok(descSection, 'expected Description collapsible section');
    const descBody = descSection.content[1] as { content: string };
@@ -215,13 +228,20 @@ test('generateForCurrentMedia emits structured-content glossary so image stays w
    );

    const infoSection = children.find(
-      (c) => (c as { tag?: string }).tag === 'details' && Array.isArray((c as { content?: unknown[] }).content) &&
-        ((c as { content: Array<{ content?: string }> }).content[0]?.content === 'Character Information'),
+      (c) =>
+        (c as { tag?: string }).tag === 'details' &&
+        Array.isArray((c as { content?: unknown[] }).content) &&
+        (c as { content: Array<{ content?: string }> }).content[0]?.content ===
+          'Character Information',
    ) as { tag: string; content: Array<Record<string, unknown>> } | undefined;
-    assert.ok(infoSection, 'expected Character Information collapsible section with parsed __Race:__ field');
+    assert.ok(
+      infoSection,
+      'expected Character Information collapsible section with parsed __Race:__ field',
+    );

    const topLevelImageGlossaryEntry = glossary.find(
-      (item) => typeof item === 'object' && item !== null && (item as { type?: string }).type === 'image',
+      (item) =>
+        typeof item === 'object' && item !== null && (item as { type?: string }).type === 'image',
    );
    assert.equal(topLevelImageGlossaryEntry, undefined);
  } finally {
@@ -322,8 +342,19 @@ test('generateForCurrentMedia adds kana aliases for romanized names when native
    });

    const result = await runtime.generateForCurrentMedia();
-    const termBank = JSON.parse(readStoredZipEntry(result.zipPath, 'term_bank_1.json').toString('utf8')) as Array<
-      [string, string, string, string, number, Array<string | Record<string, unknown>>, number, string]
+    const termBank = JSON.parse(
+      readStoredZipEntry(result.zipPath, 'term_bank_1.json').toString('utf8'),
+    ) as Array<
+      [
+        string,
+        string,
+        string,
+        string,
+        number,
+        Array<string | Record<string, unknown>>,
+        number,
+        string,
+      ]
    >;

    const kazuma = termBank.find(([term]) => term === 'カズマ');
@@ -430,7 +461,7 @@ test('getOrCreateCurrentSnapshot persists and reuses normalized snapshot data',
    throw new Error(`Unexpected fetch URL: ${url}`);
  }) as typeof globalThis.fetch;

-    try {
+  try {
    const runtime = createCharacterDictionaryRuntimeService({
      userDataPath,
      getCurrentMediaPath: () => '/tmp/eminence-s01e05.mkv',
@@ -466,7 +497,16 @@ test('getOrCreateCurrentSnapshot persists and reuses normalized snapshot data',
      mediaId: number;
      entryCount: number;
      termEntries: Array<
-        [string, string, string, string, number, Array<string | Record<string, unknown>>, number, string]
+        [
+          string,
+          string,
+          string,
+          string,
+          number,
+          Array<string | Record<string, unknown>>,
+          number,
+          string,
+        ]
      >;
    };
    assert.equal(snapshot.mediaId, 130298);
@@ -600,12 +640,27 @@ test('getOrCreateCurrentSnapshot rebuilds snapshots written with an older format
    const snapshot = JSON.parse(fs.readFileSync(snapshotPath, 'utf8')) as {
      formatVersion: number;
      termEntries: Array<
-        [string, string, string, string, number, Array<string | Record<string, unknown>>, number, string]
+        [
+          string,
+          string,
+          string,
+          string,
+          number,
+          Array<string | Record<string, unknown>>,
+          number,
+          string,
+        ]
      >;
    };
    assert.equal(snapshot.formatVersion > 9, true);
-    assert.equal(snapshot.termEntries.some(([term]) => term === 'アルファ'), true);
-    assert.equal(snapshot.termEntries.some(([term]) => term === 'stale'), false);
+    assert.equal(
+      snapshot.termEntries.some(([term]) => term === 'アルファ'),
+      true,
+    );
+    assert.equal(
+      snapshot.termEntries.some(([term]) => term === 'stale'),
+      false,
+    );
  } finally {
    globalThis.fetch = originalFetch;
  }
@@ -737,6 +792,168 @@ test('generateForCurrentMedia logs progress while resolving and rebuilding snaps
  }
 });

+test('generateForCurrentMedia downloads shared voice actor images once per AniList person id', async () => {
+  const userDataPath = makeTempDir();
+  const originalFetch = globalThis.fetch;
+  const fetchedImageUrls: string[] = [];
+
+  globalThis.fetch = (async (input: string | URL | Request, init?: RequestInit) => {
+    const url = typeof input === 'string' ? input : input instanceof URL ? input.href : input.url;
+    if (url === GRAPHQL_URL) {
+      const body = JSON.parse(String(init?.body ?? '{}')) as {
+        query?: string;
+      };
+
+      if (body.query?.includes('Page(perPage: 10)')) {
+        return new Response(
+          JSON.stringify({
+            data: {
+              Page: {
+                media: [
+                  {
+                    id: 130298,
+                    episodes: 20,
+                    title: {
+                      romaji: 'Kage no Jitsuryokusha ni Naritakute!',
+                      english: 'The Eminence in Shadow',
+                      native: '陰の実力者になりたくて！',
+                    },
+                  },
+                ],
+              },
+            },
+          }),
+          {
+            status: 200,
+            headers: { 'content-type': 'application/json' },
+          },
+        );
+      }
+
+      if (body.query?.includes('characters(page: $page')) {
+        return new Response(
+          JSON.stringify({
+            data: {
+              Media: {
+                title: {
+                  romaji: 'Kage no Jitsuryokusha ni Naritakute!',
+                  english: 'The Eminence in Shadow',
+                  native: '陰の実力者になりたくて！',
+                },
+                characters: {
+                  pageInfo: { hasNextPage: false },
+                  edges: [
+                    {
+                      role: 'MAIN',
+                      voiceActors: [
+                        {
+                          id: 9001,
+                          name: {
+                            full: 'Kana Hanazawa',
+                            native: '花澤香菜',
+                          },
+                          image: {
+                            large: null,
+                            medium: 'https://example.com/kana.png',
+                          },
+                        },
+                      ],
+                      node: {
+                        id: 321,
+                        description: 'Alpha is the second-in-command of Shadow Garden.',
+                        image: {
+                          large: 'https://example.com/alpha.png',
+                          medium: null,
+                        },
+                        name: {
+                          full: 'Alpha',
+                          native: 'アルファ',
+                        },
+                      },
+                    },
+                    {
+                      role: 'SUPPORTING',
+                      voiceActors: [
+                        {
+                          id: 9001,
+                          name: {
+                            full: 'Kana Hanazawa',
+                            native: '花澤香菜',
+                          },
+                          image: {
+                            large: null,
+                            medium: 'https://example.com/kana.png',
+                          },
+                        },
+                      ],
+                      node: {
+                        id: 654,
+                        description: 'Beta documents Shadow Garden operations.',
+                        image: {
+                          large: 'https://example.com/beta.png',
+                          medium: null,
+                        },
+                        name: {
+                          full: 'Beta',
+                          native: 'ベータ',
+                        },
+                      },
+                    },
+                  ],
+                },
+              },
+            },
+          }),
+          {
+            status: 200,
+            headers: { 'content-type': 'application/json' },
+          },
+        );
+      }
+    }
+
+    if (
+      url === 'https://example.com/alpha.png' ||
+      url === 'https://example.com/beta.png' ||
+      url === 'https://example.com/kana.png'
+    ) {
+      fetchedImageUrls.push(url);
+      return new Response(PNG_1X1, {
+        status: 200,
+        headers: { 'content-type': 'image/png' },
+      });
+    }
+
+    throw new Error(`Unexpected fetch URL: ${url}`);
+  }) as typeof globalThis.fetch;
+
+  try {
+    const runtime = createCharacterDictionaryRuntimeService({
+      userDataPath,
+      getCurrentMediaPath: () => '/tmp/eminence-s01e05.mkv',
+      getCurrentMediaTitle: () => 'The Eminence in Shadow - S01E05',
+      resolveMediaPathForJimaku: (mediaPath) => mediaPath,
+      guessAnilistMediaInfo: async () => ({
+        title: 'The Eminence in Shadow',
+        episode: 5,
+        source: 'fallback',
+      }),
+      now: () => 1_700_000_000_100,
+      sleep: async () => undefined,
+    });
+
+    await runtime.generateForCurrentMedia();
+
+    assert.deepEqual(fetchedImageUrls, [
+      'https://example.com/alpha.png',
+      'https://example.com/kana.png',
+      'https://example.com/beta.png',
+    ]);
+  } finally {
+    globalThis.fetch = originalFetch;
+  }
+});
+
 test('buildMergedDictionary combines stored snapshots into one stable dictionary', async () => {
  const userDataPath = makeTempDir();
  const originalFetch = globalThis.fetch;
@@ -913,8 +1130,19 @@ test('buildMergedDictionary combines stored snapshots into one stable dictionary
    const index = JSON.parse(readStoredZipEntry(merged.zipPath, 'index.json').toString('utf8')) as {
      title: string;
    };
-    const termBank = JSON.parse(readStoredZipEntry(merged.zipPath, 'term_bank_1.json').toString('utf8')) as Array<
-      [string, string, string, string, number, Array<string | Record<string, unknown>>, number, string]
+    const termBank = JSON.parse(
+      readStoredZipEntry(merged.zipPath, 'term_bank_1.json').toString('utf8'),
+    ) as Array<
+      [
+        string,
+        string,
+        string,
+        string,
+        number,
+        Array<string | Record<string, unknown>>,
+        number,
+        string,
+      ]
    >;
    const frieren = termBank.find(([term]) => term === 'フリーレン');
    const alpha = termBank.find(([term]) => term === 'アルファ');
@@ -1064,7 +1292,10 @@ test('generateForCurrentMedia paces AniList requests and character image downloa
    await runtime.generateForCurrentMedia();

    assert.deepEqual(sleepCalls, [2000, 250]);
-    assert.deepEqual(imageRequests, ['https://example.com/alpha.png', 'https://example.com/beta.png']);
+    assert.deepEqual(imageRequests, [
+      'https://example.com/alpha.png',
+      'https://example.com/beta.png',
+    ]);
  } finally {
    globalThis.fetch = originalFetch;
  }
--- a/src/main/character-dictionary-runtime.ts
+++ b/src/main/character-dictionary-runtime.ts
@@ -449,20 +449,13 @@ function romanizedTokenToKatakana(token: string): string | null {
      continue;
    }

-    if (
-      current === 'n' &&
-      next.length > 0 &&
-      next !== 'y' &&
-      !'aeiou'.includes(next)
-    ) {
+    if (current === 'n' && next.length > 0 && next !== 'y' && !'aeiou'.includes(next)) {
      output += 'ン';
      i += 1;
      continue;
    }

-    const digraph = ROMANIZED_KANA_DIGRAPHS.find(([romaji]) =>
-      normalized.startsWith(romaji, i),
-    );
+    const digraph = ROMANIZED_KANA_DIGRAPHS.find(([romaji]) => normalized.startsWith(romaji, i));
    if (digraph) {
      output += digraph[1];
      i += digraph[0].length;
@@ -750,7 +743,13 @@ function writeSnapshot(snapshotPath: string, snapshot: CharacterDictionarySnapsh
 }

 function roleBadgeStyle(role: CharacterDictionaryRole): Record<string, string> {
-  const base = { borderRadius: '4px', padding: '0.15em 0.5em', fontSize: '0.8em', fontWeight: 'bold', color: '#fff' };
+  const base = {
+    borderRadius: '4px',
+    padding: '0.15em 0.5em',
+    fontSize: '0.8em',
+    fontWeight: 'bold',
+    color: '#fff',
+  };
  if (role === 'main') return { ...base, backgroundColor: '#4a8c3f' };
  if (role === 'primary') return { ...base, backgroundColor: '#5c82b0' };
  if (role === 'side') return { ...base, backgroundColor: '#7889a0' };
@@ -788,7 +787,9 @@ function buildVoicedByContent(
    const va = voiceActors[0]!;
    const vaImgPath = vaImagePaths.get(va.id);
    const vaLabel = va.nativeName
-      ? va.fullName ? `${va.nativeName} (${va.fullName})` : va.nativeName
+      ? va.fullName
+        ? `${va.nativeName} (${va.fullName})`
+        : va.nativeName
      : va.fullName;

    if (vaImgPath) {
@@ -799,7 +800,12 @@ function buildVoicedByContent(
          content: [
            {
              tag: 'td',
-              style: { verticalAlign: 'top', padding: '0', paddingRight: '0.4em', borderWidth: '0' },
+              style: {
+                verticalAlign: 'top',
+                padding: '0',
+                paddingRight: '0.4em',
+                borderWidth: '0',
+              },
              content: {
                tag: 'img',
                path: vaImgPath,
@@ -829,7 +835,9 @@ function buildVoicedByContent(
  const items: Array<Record<string, unknown>> = [];
  for (const va of voiceActors) {
    const vaLabel = va.nativeName
-      ? va.fullName ? `${va.nativeName} (${va.fullName})` : va.nativeName
+      ? va.fullName
+        ? `${va.nativeName} (${va.fullName})`
+        : va.nativeName
      : va.fullName;
    items.push({ tag: 'li', content: vaLabel });
  }
@@ -844,9 +852,7 @@ function createDefinitionGlossary(
 ): CharacterDictionaryGlossaryEntry[] {
  const displayName = character.nativeName || character.fullName || `Character ${character.id}`;
  const secondaryName =
-    character.nativeName &&
-    character.fullName &&
-    character.fullName !== character.nativeName
+    character.nativeName && character.fullName && character.fullName !== character.nativeName
      ? character.fullName
      : null;
  const { fields, text: descriptionText } = parseCharacterDescription(character.description);
@@ -1275,7 +1281,10 @@ async function fetchCharactersForMedia(
  };
 }

-async function downloadCharacterImage(imageUrl: string, charId: number): Promise<{
+async function downloadCharacterImage(
+  imageUrl: string,
+  charId: number,
+): Promise<{
  filename: string;
  ext: string;
  bytes: Buffer;
@@ -1379,7 +1388,10 @@ function buildDictionaryZip(
  const zipFiles: Array<{ name: string; data: Buffer }> = [
    {
      name: 'index.json',
-      data: Buffer.from(JSON.stringify(createIndex(dictionaryTitle, description, revision), null, 2), 'utf8'),
+      data: Buffer.from(
+        JSON.stringify(createIndex(dictionaryTitle, description, revision), null, 2),
+        'utf8',
+      ),
    },
    {
      name: 'tag_bank_1.json',
@@ -1454,7 +1466,9 @@ export function createCharacterDictionaryRuntimeService(deps: CharacterDictionar
    }
    deps.logInfo?.(
      `[dictionary] current anime guess: ${guessed.title.trim()}${
-        typeof guessed.episode === 'number' && guessed.episode > 0 ? ` (episode ${guessed.episode})` : ''
+        typeof guessed.episode === 'number' && guessed.episode > 0
+          ? ` (episode ${guessed.episode})`
+          : ''
      }`,
    );
    const resolved = await resolveAniListMediaIdFromGuess(guessed, beforeRequest);
@@ -1486,7 +1500,9 @@ export function createCharacterDictionaryRuntimeService(deps: CharacterDictionar
      mediaId,
      beforeRequest,
      (page) => {
-        deps.logInfo?.(`[dictionary] downloaded AniList character page ${page} for AniList ${mediaId}`);
+        deps.logInfo?.(
+          `[dictionary] downloaded AniList character page ${page} for AniList ${mediaId}`,
+        );
      },
    );
    if (characters.length === 0) {
@@ -1496,12 +1512,14 @@ export function createCharacterDictionaryRuntimeService(deps: CharacterDictionar
    const imagesByCharacterId = new Map<number, CharacterDictionarySnapshotImage>();
    const imagesByVaId = new Map<number, CharacterDictionarySnapshotImage>();
    const allImageUrls: Array<{ id: number; url: string; kind: 'character' | 'va' }> = [];
+    const seenVaIds = new Set<number>();
    for (const character of characters) {
      if (character.imageUrl) {
        allImageUrls.push({ id: character.id, url: character.imageUrl, kind: 'character' });
      }
      for (const va of character.voiceActors) {
-        if (va.imageUrl && !allImageUrls.some((u) => u.kind === 'va' && u.id === va.id)) {
+        if (va.imageUrl && !seenVaIds.has(va.id)) {
+          seenVaIds.add(va.id);
          allImageUrls.push({ id: va.id, url: va.imageUrl, kind: 'va' });
        }
      }
@@ -1601,7 +1619,10 @@ export function createCharacterDictionaryRuntimeService(deps: CharacterDictionar
        entryCount,
      };
    },
-    generateForCurrentMedia: async (targetPath?: string, _options?: CharacterDictionaryGenerateOptions) => {
+    generateForCurrentMedia: async (
+      targetPath?: string,
+      _options?: CharacterDictionaryGenerateOptions,
+    ) => {
      let hasAniListRequest = false;
      const waitForAniListRequestSlot = async (): Promise<void> => {
        if (!hasAniListRequest) {