feat: source frequency ranks from installed Yomitan dictionaries

README.md

@@ -27,7 +27,7 @@ SubMiner is an Electron overlay that sits on top of mpv. It turns your video pla
 - **Hover to look up** — Yomitan dictionary popups directly on subtitles
 - **One-key mining** — Creates Anki cards with sentence, audio, screenshot, and translation
 - **Instant auto-enrichment** — Optional local AnkiConnect proxy enriches new Yomitan cards immediately
-- **N+1 highlighting** — Marks known words from your Anki deck so unknown ones jump out
+- **Reading annotations** — Combines N+1 targeting, frequency-dictionary highlighting, and JLPT underlining while you read
 - **Subtitle tools** — Download from Jimaku, sync with alass/ffsubsync
 - **Immersion tracking** — SQLite-powered stats on your watch time and mining activity
 - **Custom texthooker page** — Built-in custom texthooker page and websocket, no extra setup

config.example.jsonc

@@ -133,7 +133,7 @@
     }, // Jlpt colors setting.
     "frequencyDictionary": {
       "enabled": false, // Enable frequency-dictionary-based highlighting based on token rank. Values: true | false
-      "sourcePath": "", // Optional absolute path to a frequency dictionary directory. If empty, built-in discovery search paths are used.
+      "sourcePath": "", // Optional absolute path to a frequency dictionary directory. If empty, SubMiner searches installed/default frequency-dictionary locations.
       "topX": 1000, // Only color tokens with frequency rank <= topX (default: 1000).
       "mode": "single", // single: use one color for all matching tokens. banded: use color ramp by frequency band. Values: single | banded
       "singleColor": "#f5a97f", // Color used when frequencyDictionary.mode is `single`.

docs/configuration.md

@@ -757,7 +757,7 @@ See `config.example.jsonc` for detailed configuration options.
 | `enableJlpt`                       | boolean     | Enable JLPT level underline styling (`false` by default)                                                            |
 | `preserveLineBreaks`               | boolean     | Preserve line breaks in visible overlay subtitle rendering (`false` by default). Enable to mirror mpv line layout.  |
 | `frequencyDictionary.enabled`      | boolean     | Enable frequency highlighting from dictionary lookups (`false` by default)                                          |
-| `frequencyDictionary.sourcePath`   | string      | Path to a local frequency dictionary root. Leave empty or omit to use the built-in bundled dictionary search paths. |
+| `frequencyDictionary.sourcePath`   | string      | Path to a local frequency dictionary root. Leave empty or omit to use installed/default frequency-dictionary search paths. |
 | `frequencyDictionary.topX`         | number      | Only color tokens whose frequency rank is `<= topX` (`1000` by default)                                             |
 | `frequencyDictionary.mode`         | string      | `"single"` or `"banded"` (`"single"` by default)                                                                    |
 | `frequencyDictionary.singleColor`  | string      | Color used for all highlighted tokens in single mode                                                                |
@@ -774,7 +774,7 @@ Frequency dictionary highlighting uses the same dictionary file format as JLPT b
 Lookup behavior:
 
 - Set `frequencyDictionary.sourcePath` to a directory containing `term_meta_bank_*.json` for a fully custom source.
-- If `sourcePath` is missing or empty, SubMiner uses bundled defaults from `vendor/jiten_freq_global` (packaged under `<resources>/jiten_freq_global` in distribution builds).
+- If `sourcePath` is missing or empty, SubMiner searches default install/runtime locations for `frequency-dictionary` directories (for example app resources, user data paths, and current working directory).
 - In both cases, only terms with a valid `frequencyRank` are used; everything else falls back to no highlighting.
 
 In `single` mode all highlights use `singleColor`; in `banded` mode tokens map to five ascending color bands from most common to least common inside the topX window.

docs/index.md

@@ -7,7 +7,7 @@ titleTemplate: Immersion Mining Workflow for MPV
 hero:
   name: SubMiner
   text: Immersion Mining for MPV
-  tagline: Watch media, mine vocabulary, and build cards without leaving the scene.
+  tagline: Watch media, mine vocabulary, and craft anki cards without leaving the scene.
   image:
     src: /assets/SubMiner.png
     alt: SubMiner logo
@@ -35,16 +35,11 @@ features:
       alt: Anki card icon
     title: Anki Card Enrichment
     details: Auto-fills card fields with subtitle sentence, clipping, image, and translation so you can focus on learning.
-  - icon:
-      src: /assets/dual-layer.svg
-      alt: Dual layer icon
-    title: Unified Overlay Stack
-    details: Primary interactive subtitle layer with a built-in secondary context bar, all in one overlay window.
   - icon:
       src: /assets/highlight.svg
       alt: Highlight icon
-    title: N+1 Highlighting
-    details: Surfaces known words from your deck so unknown targets stand out during immersion sessions.
+    title: Reading Annotations
+    details: Combines N+1 targeting, Jiten frequency highlighting, and JLPT tagging so useful cues stay visible while you read.
   - icon:
       src: /assets/tokenization.svg
       alt: Tokenization icon
@@ -55,16 +50,6 @@ features:
       alt: Subtitle download icon
     title: Subtitle Download & Sync
     details: Pull and synchronize subtitles with Jimaku plus alass/ffsubsync in one cohesive workflow.
-  - icon:
-      src: /assets/keyboard.svg
-      alt: Keyboard icon
-    title: Keyboard-Driven
-    details: Run lookups, mining actions, clipping, and workflow toggles with one configurable shortcut surface.
-  - icon:
-      src: /assets/texthooker.svg
-      alt: Texthooker icon
-    title: Texthooker & WebSocket
-    details: Stream subtitles in real time to browser tools via local WebSocket and keep your stack integrated.
 ---
 
 <script setup>

docs/jlpt-vocab-bundle.md

@@ -26,7 +26,7 @@ The expected files are:
 
 Each bank maps terms to frequency metadata; only entries with a `frequency.displayValue` are considered for JLPT tagging.
 
-SubMiner also reuses the same `term_meta_bank_*.json` format for frequency-based subtitle highlighting. The default frequency source is now bundled as `vendor/jiten_freq_global`, so users can enable `subtitleStyle.frequencyDictionary` without extra setup.
+SubMiner also reuses the same `term_meta_bank_*.json` format for frequency-based subtitle highlighting, using installed/default `frequency-dictionary` locations or an explicit `subtitleStyle.frequencyDictionary.sourcePath`.
 
 ## Source and update process
 

docs/public/config.example.jsonc

@@ -133,7 +133,7 @@
     }, // Jlpt colors setting.
     "frequencyDictionary": {
       "enabled": false, // Enable frequency-dictionary-based highlighting based on token rank. Values: true | false
-      "sourcePath": "", // Optional absolute path to a frequency dictionary directory. If empty, built-in discovery search paths are used.
+      "sourcePath": "", // Optional absolute path to a frequency dictionary directory. If empty, SubMiner searches installed/default frequency-dictionary locations.
       "topX": 1000, // Only color tokens with frequency rank <= topX (default: 1000).
       "mode": "single", // single: use one color for all matching tokens. banded: use color ramp by frequency band. Values: single | banded
       "singleColor": "#f5a97f", // Color used when frequencyDictionary.mode is `single`.

package.json

@@ -119,10 +119,6 @@
         "from": "vendor/yomitan-jlpt-vocab",
         "to": "yomitan-jlpt-vocab"
       },
-      {
-        "from": "vendor/jiten_freq_global",
-        "to": "jiten_freq_global"
-      },
       {
         "from": "assets",
         "to": "assets"

scripts/get_frequency.ts

@@ -33,7 +33,7 @@ interface CliOptions {
 function parseCliArgs(argv: string[]): CliOptions {
   const args = [...argv];
   let inputParts: string[] = [];
-  let dictionaryPath = path.join(process.cwd(), 'vendor', 'jiten_freq_global');
+  let dictionaryPath = path.join(process.cwd(), 'vendor', 'frequency-dictionary');
   let emitPretty = false;
   let emitDiagnostics = false;
   let mecabCommand: string | undefined;
@@ -394,7 +394,7 @@ function printUsage(): void {
   --color-band-5 <#hex>  Frequency band-5 color.
   --color-known <#hex>    Known-word color (default: #a6da95).
   --color-n-plus-one <#hex> N+1 target color (default: #c6a0f6).
-  --dictionary <path>    Frequency dictionary root path (default: ./vendor/jiten_freq_global)
+  --dictionary <path>    Frequency dictionary root path (default: ./vendor/frequency-dictionary)
   --mecab-command <path>  Optional MeCab binary path (default: mecab)
   --mecab-dictionary <path> Optional MeCab dictionary directory (default: system default)
   -h, --help            Show usage.

src/core/services/frequency-dictionary.test.ts

@@ -79,3 +79,30 @@ test('createFrequencyDictionaryLookup aggregates duplicate-term logs into a sing
     false,
   );
 });
+
+test('createFrequencyDictionaryLookup prefers frequency.value over displayValue', async () => {
+  const logs: string[] = [];
+  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'subminer-frequency-dict-'));
+  const bankPath = path.join(tempDir, 'term_meta_bank_1.json');
+  fs.writeFileSync(
+    bankPath,
+    JSON.stringify([
+      ['猫', 1, { frequency: { value: 1234, displayValue: 1200 } }],
+      ['犬', 2, { frequency: { displayValue: 88 } }],
+    ]),
+  );
+
+  const lookup = await createFrequencyDictionaryLookup({
+    searchPaths: [tempDir],
+    log: (message) => {
+      logs.push(message);
+    },
+  });
+
+  assert.equal(lookup('猫'), 1234);
+  assert.equal(lookup('犬'), 88);
+  assert.equal(
+    logs.some((entry) => entry.includes('Frequency dictionary loaded from')),
+    true,
+  );
+});

src/core/services/frequency-dictionary.ts

@@ -18,17 +18,14 @@ function normalizeFrequencyTerm(value: string): string {
   return value.trim().toLowerCase();
 }
 
-function extractFrequencyDisplayValue(meta: unknown): number | null {
-  if (!meta || typeof meta !== 'object') return null;
-  const frequency = (meta as { frequency?: unknown }).frequency;
-  if (!frequency || typeof frequency !== 'object') return null;
-  const displayValue = (frequency as { displayValue?: unknown }).displayValue;
-  if (typeof displayValue === 'number') {
-    if (!Number.isFinite(displayValue) || displayValue <= 0) return null;
-    return Math.floor(displayValue);
+function parsePositiveFrequencyNumber(value: unknown): number | null {
+  if (typeof value === 'number') {
+    if (!Number.isFinite(value) || value <= 0) return null;
+    return Math.floor(value);
   }
-  if (typeof displayValue === 'string') {
-    const normalized = displayValue.trim().replace(/,/g, '');
+
+  if (typeof value === 'string') {
+    const normalized = value.trim().replace(/,/g, '');
     const parsed = Number.parseInt(normalized, 10);
     if (!Number.isFinite(parsed) || parsed <= 0) return null;
     return parsed;
@@ -37,6 +34,20 @@ function extractFrequencyDisplayValue(meta: unknown): number | null {
   return null;
 }
 
+function extractFrequencyDisplayValue(meta: unknown): number | null {
+  if (!meta || typeof meta !== 'object') return null;
+  const frequency = (meta as { frequency?: unknown }).frequency;
+  if (!frequency || typeof frequency !== 'object') return null;
+  const rawValue = (frequency as { value?: unknown }).value;
+  const parsedValue = parsePositiveFrequencyNumber(rawValue);
+  if (parsedValue !== null) {
+    return parsedValue;
+  }
+
+  const displayValue = (frequency as { displayValue?: unknown }).displayValue;
+  return parsePositiveFrequencyNumber(displayValue);
+}
+
 function asFrequencyDictionaryEntry(entry: unknown): FrequencyDictionaryEntry | null {
   if (!Array.isArray(entry) || entry.length < 3) {
     return null;

src/core/services/tokenizer.test.ts

@@ -169,6 +169,55 @@ test('tokenizeSubtitle applies frequency dictionary ranks', async () => {
   assert.equal(result.tokens?.[1]?.frequencyRank, 1200);
 });
 
+test('tokenizeSubtitle loads frequency ranks from Yomitan installed dictionaries', async () => {
+  const result = await tokenizeSubtitle(
+    '猫',
+    makeDeps({
+      getFrequencyDictionaryEnabled: () => true,
+      getYomitanExt: () => ({ id: 'dummy-ext' }) as any,
+      getYomitanParserWindow: () =>
+        ({
+          isDestroyed: () => false,
+          webContents: {
+            executeJavaScript: async (script: string) => {
+              if (script.includes('getTermFrequencies')) {
+                return [
+                  {
+                    term: '猫',
+                    reading: 'ねこ',
+                    dictionary: 'freq-dict',
+                    frequency: 77,
+                    displayValue: '77',
+                    displayValueParsed: true,
+                  },
+                ];
+              }
+
+              return [
+                {
+                  source: 'scanning-parser',
+                  index: 0,
+                  content: [
+                    [
+                      {
+                        text: '猫',
+                        reading: 'ねこ',
+                        headwords: [[{ term: '猫' }]],
+                      },
+                    ],
+                  ],
+                },
+              ];
+            },
+          },
+        }) as unknown as Electron.BrowserWindow,
+    }),
+  );
+
+  assert.equal(result.tokens?.length, 1);
+  assert.equal(result.tokens?.[0]?.frequencyRank, 77);
+});
+
 test('tokenizeSubtitle uses only selected Yomitan headword for frequency lookup', async () => {
   const result = await tokenizeSubtitle(
     '猫です',

src/core/services/tokenizer.ts

@@ -10,7 +10,10 @@ import {
   JlptLevel,
 } from '../../types';
 import { selectYomitanParseTokens } from './tokenizer/parser-selection-stage';
-import { requestYomitanParseResults } from './tokenizer/yomitan-parser-runtime';
+import {
+  requestYomitanParseResults,
+  requestYomitanTermFrequencies,
+} from './tokenizer/yomitan-parser-runtime';
 
 const logger = createLogger('main:tokenizer');
 
@@ -214,6 +217,64 @@ function logSelectedYomitanGroups(text: string, tokens: MergedToken[]): void {
   });
 }
 
+function normalizePositiveFrequencyRank(value: unknown): number | null {
+  if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0) {
+    return null;
+  }
+  return Math.max(1, Math.floor(value));
+}
+
+function resolveFrequencyLookupText(token: MergedToken): string {
+  if (token.headword && token.headword.length > 0) {
+    return token.headword;
+  }
+  if (token.reading && token.reading.length > 0) {
+    return token.reading;
+  }
+  return token.surface;
+}
+
+function applyYomitanFrequencyRanks(
+  tokens: MergedToken[],
+  frequencies: ReadonlyArray<{ term: string; frequency: number }>,
+): MergedToken[] {
+  if (tokens.length === 0 || frequencies.length === 0) {
+    return tokens;
+  }
+
+  const rankByTerm = new Map<string, number>();
+  for (const frequency of frequencies) {
+    const normalizedTerm = frequency.term.trim();
+    const rank = normalizePositiveFrequencyRank(frequency.frequency);
+    if (!normalizedTerm || rank === null) {
+      continue;
+    }
+    const current = rankByTerm.get(normalizedTerm);
+    if (current === undefined || rank < current) {
+      rankByTerm.set(normalizedTerm, rank);
+    }
+  }
+
+  if (rankByTerm.size === 0) {
+    return tokens;
+  }
+
+  return tokens.map((token) => {
+    const lookupText = resolveFrequencyLookupText(token).trim();
+    if (!lookupText) {
+      return token;
+    }
+    const rank = rankByTerm.get(lookupText);
+    if (rank === undefined) {
+      return token;
+    }
+    return {
+      ...token,
+      frequencyRank: rank,
+    };
+  });
+}
+
 function getAnnotationOptions(deps: TokenizerServiceDeps): TokenizerAnnotationOptions {
   return {
     nPlusOneEnabled: deps.getNPlusOneEnabled?.() !== false,
@@ -246,14 +307,24 @@ async function parseWithYomitanInternalParser(
     logSelectedYomitanGroups(text, selectedTokens);
   }
 
+  let tokensWithFrequency = selectedTokens;
+  if (options.frequencyEnabled) {
+    const termReadingList = selectedTokens.map((token) => ({
+      term: resolveFrequencyLookupText(token),
+      reading: token.reading && token.reading.trim().length > 0 ? token.reading.trim() : null,
+    }));
+    const yomitanFrequencies = await requestYomitanTermFrequencies(termReadingList, deps, logger);
+    tokensWithFrequency = applyYomitanFrequencyRanks(selectedTokens, yomitanFrequencies);
+  }
+
   if (!needsMecabPosEnrichment(options)) {
-    return selectedTokens;
+    return tokensWithFrequency;
   }
 
   try {
     const mecabTokens = await deps.tokenizeWithMecab(text);
     const enrichTokensWithMecab = deps.enrichTokensWithMecab ?? enrichTokensWithMecabAsync;
-    return await enrichTokensWithMecab(selectedTokens, mecabTokens);
+    return await enrichTokensWithMecab(tokensWithFrequency, mecabTokens);
   } catch (err) {
     const error = err as Error;
     logger.warn(
@@ -262,7 +333,7 @@ async function parseWithYomitanInternalParser(
       `tokenCount=${selectedTokens.length}`,
       `textLength=${text.length}`,
     );
-    return selectedTokens;
+    return tokensWithFrequency;
   }
 }
 

src/core/services/tokenizer/annotation-stage.test.ts

@@ -95,6 +95,27 @@ test('annotateTokens excludes frequency for particle/bound_auxiliary and pos1 ex
   assert.deepEqual(lookupCalls, ['猫']);
 });
 
+test('annotateTokens preserves existing frequency rank when lookup is unavailable', () => {
+  const tokens = [makeToken({ surface: '猫', headword: '猫', frequencyRank: 42 })];
+
+  const result = annotateTokens(tokens, makeDeps({ getFrequencyRank: undefined }));
+
+  assert.equal(result[0]?.frequencyRank, 42);
+});
+
+test('annotateTokens prefers existing frequency rank over fallback lookup', () => {
+  const tokens = [makeToken({ surface: '猫', headword: '猫', frequencyRank: 42 })];
+
+  const result = annotateTokens(
+    tokens,
+    makeDeps({
+      getFrequencyRank: () => 9,
+    }),
+  );
+
+  assert.equal(result[0]?.frequencyRank, 42);
+});
+
 test('annotateTokens handles JLPT disabled and eligibility exclusion paths', () => {
   let disabledLookupCalls = 0;
   const disabledResult = annotateTokens(
@@ -157,3 +178,38 @@ test('annotateTokens N+1 handoff marks expected target when threshold is satisfi
   assert.equal(result[1]?.isNPlusOneTarget, true);
   assert.equal(result[2]?.isNPlusOneTarget, false);
 });
+
+test('annotateTokens N+1 minimum sentence words counts only eligible word tokens', () => {
+  const tokens = [
+    makeToken({ surface: '猫', headword: '猫', startPos: 0, endPos: 1 }),
+    makeToken({
+      surface: 'が',
+      headword: 'が',
+      partOfSpeech: PartOfSpeech.particle,
+      pos1: '助詞',
+      startPos: 1,
+      endPos: 2,
+    }),
+    makeToken({
+      surface: 'です',
+      headword: 'です',
+      partOfSpeech: PartOfSpeech.bound_auxiliary,
+      pos1: '助動詞',
+      startPos: 2,
+      endPos: 4,
+    }),
+  ];
+
+  const result = annotateTokens(
+    tokens,
+    makeDeps({
+      isKnownWord: (text) => text === 'が' || text === 'です',
+    }),
+    { minSentenceWordsForNPlusOne: 3 },
+  );
+
+  assert.equal(result[0]?.isKnown, false);
+  assert.equal(result[1]?.isKnown, true);
+  assert.equal(result[2]?.isKnown, true);
+  assert.equal(result[0]?.isNPlusOneTarget, false);
+});

src/core/services/tokenizer/annotation-stage.ts

@@ -141,6 +141,11 @@ function applyFrequencyMarking(
       return { ...token, frequencyRank: undefined };
     }
 
+    if (typeof token.frequencyRank === 'number' && Number.isFinite(token.frequencyRank)) {
+      const rank = Math.max(1, Math.floor(token.frequencyRank));
+      return { ...token, frequencyRank: rank };
+    }
+
     const lookupTexts = getFrequencyLookupTextCandidates(token);
     if (lookupTexts.length === 0) {
       return { ...token, frequencyRank: undefined };
@@ -354,6 +359,14 @@ export function annotateTokens(
   const frequencyMarkedTokens =
     frequencyEnabled && deps.getFrequencyRank
       ? applyFrequencyMarking(knownMarkedTokens, deps.getFrequencyRank)
+      : frequencyEnabled
+        ? knownMarkedTokens.map((token) => ({
+            ...token,
+            frequencyRank:
+              typeof token.frequencyRank === 'number' && Number.isFinite(token.frequencyRank)
+                ? Math.max(1, Math.floor(token.frequencyRank))
+                : undefined,
+          }))
       : knownMarkedTokens.map((token) => ({
           ...token,
           frequencyRank: undefined,

src/core/services/tokenizer/yomitan-parser-runtime.test.ts

@@ -1,6 +1,9 @@
 import assert from 'node:assert/strict';
 import test from 'node:test';
-import { syncYomitanDefaultAnkiServer } from './yomitan-parser-runtime';
+import {
+  requestYomitanTermFrequencies,
+  syncYomitanDefaultAnkiServer,
+} from './yomitan-parser-runtime';
 
 function createDeps(executeJavaScript: (script: string) => Promise<unknown>) {
   const parserWindow = {
@@ -81,3 +84,35 @@ test('syncYomitanDefaultAnkiServer no-ops for empty target url', async () => {
   assert.equal(updated, false);
   assert.equal(executeCount, 0);
 });
+
+test('requestYomitanTermFrequencies returns normalized frequency entries', async () => {
+  let scriptValue = '';
+  const deps = createDeps(async (script) => {
+    scriptValue = script;
+    return [
+      {
+        term: '猫',
+        reading: 'ねこ',
+        dictionary: 'freq-dict',
+        frequency: 77,
+        displayValue: '77',
+        displayValueParsed: true,
+      },
+      {
+        term: 'invalid',
+        dictionary: 'freq-dict',
+        frequency: 0,
+      },
+    ];
+  });
+
+  const result = await requestYomitanTermFrequencies([{ term: '猫', reading: 'ねこ' }], deps, {
+    error: () => undefined,
+  });
+
+  assert.equal(result.length, 1);
+  assert.equal(result[0]?.term, '猫');
+  assert.equal(result[0]?.frequency, 77);
+  assert.match(scriptValue, /getTermFrequencies/);
+  assert.match(scriptValue, /optionsGetFull/);
+});

src/core/services/tokenizer/yomitan-parser-runtime.ts

@@ -15,6 +15,89 @@ interface YomitanParserRuntimeDeps {
   setYomitanParserInitPromise: (promise: Promise<boolean> | null) => void;
 }
 
+export interface YomitanTermFrequency {
+  term: string;
+  reading: string | null;
+  dictionary: string;
+  frequency: number;
+  displayValue: string | null;
+  displayValueParsed: boolean;
+}
+
+export interface YomitanTermReadingPair {
+  term: string;
+  reading: string | null;
+}
+
+function isObject(value: unknown): value is Record<string, unknown> {
+  return Boolean(value && typeof value === 'object');
+}
+
+function asPositiveInteger(value: unknown): number | null {
+  if (typeof value !== 'number' || !Number.isFinite(value) || value <= 0) {
+    return null;
+  }
+  return Math.max(1, Math.floor(value));
+}
+
+function toYomitanTermFrequency(value: unknown): YomitanTermFrequency | null {
+  if (!isObject(value)) {
+    return null;
+  }
+
+  const term = typeof value.term === 'string' ? value.term.trim() : '';
+  const dictionary = typeof value.dictionary === 'string' ? value.dictionary.trim() : '';
+  const frequency = asPositiveInteger(value.frequency);
+  if (!term || !dictionary || frequency === null) {
+    return null;
+  }
+
+  const reading =
+    value.reading === null
+      ? null
+      : typeof value.reading === 'string'
+        ? value.reading
+        : null;
+  const displayValue =
+    value.displayValue === null
+      ? null
+      : typeof value.displayValue === 'string'
+        ? value.displayValue
+        : null;
+  const displayValueParsed = value.displayValueParsed === true;
+
+  return {
+    term,
+    reading,
+    dictionary,
+    frequency,
+    displayValue,
+    displayValueParsed,
+  };
+}
+
+function normalizeTermReadingList(termReadingList: YomitanTermReadingPair[]): YomitanTermReadingPair[] {
+  const normalized: YomitanTermReadingPair[] = [];
+  const seen = new Set<string>();
+
+  for (const pair of termReadingList) {
+    const term = typeof pair.term === 'string' ? pair.term.trim() : '';
+    if (!term) {
+      continue;
+    }
+    const reading =
+      typeof pair.reading === 'string' && pair.reading.trim().length > 0 ? pair.reading.trim() : null;
+    const key = `${term}\u0000${reading ?? ''}`;
+    if (seen.has(key)) {
+      continue;
+    }
+    seen.add(key);
+    normalized.push({ term, reading });
+  }
+
+  return normalized;
+}
+
 async function ensureYomitanParserWindow(
   deps: YomitanParserRuntimeDeps,
   logger: LoggerLike,
@@ -154,6 +237,79 @@ export async function requestYomitanParseResults(
   }
 }
 
+export async function requestYomitanTermFrequencies(
+  termReadingList: YomitanTermReadingPair[],
+  deps: YomitanParserRuntimeDeps,
+  logger: LoggerLike,
+): Promise<YomitanTermFrequency[]> {
+  const normalizedTermReadingList = normalizeTermReadingList(termReadingList);
+  const yomitanExt = deps.getYomitanExt();
+  if (normalizedTermReadingList.length === 0 || !yomitanExt) {
+    return [];
+  }
+
+  const isReady = await ensureYomitanParserWindow(deps, logger);
+  const parserWindow = deps.getYomitanParserWindow();
+  if (!isReady || !parserWindow || parserWindow.isDestroyed()) {
+    return [];
+  }
+
+  const script = `
+    (async () => {
+      const invoke = (action, params) =>
+        new Promise((resolve, reject) => {
+          chrome.runtime.sendMessage({ action, params }, (response) => {
+            if (chrome.runtime.lastError) {
+              reject(new Error(chrome.runtime.lastError.message));
+              return;
+            }
+            if (!response || typeof response !== "object") {
+              reject(new Error("Invalid response from Yomitan backend"));
+              return;
+            }
+            if (response.error) {
+              reject(new Error(response.error.message || "Yomitan backend error"));
+              return;
+            }
+            resolve(response.result);
+          });
+        });
+
+      const optionsFull = await invoke("optionsGetFull", undefined);
+      const profileIndex = optionsFull.profileCurrent;
+      const dictionariesRaw = optionsFull.profiles?.[profileIndex]?.options?.dictionaries ?? [];
+      const dictionaries = Array.isArray(dictionariesRaw)
+        ? dictionariesRaw
+            .filter((entry) => entry && typeof entry === "object" && entry.enabled === true && typeof entry.name === "string")
+            .map((entry) => entry.name)
+        : [];
+
+      if (dictionaries.length === 0) {
+        return [];
+      }
+
+      return await invoke("getTermFrequencies", {
+        termReadingList: ${JSON.stringify(normalizedTermReadingList)},
+        dictionaries
+      });
+    })();
+  `;
+
+  try {
+    const rawResult = await parserWindow.webContents.executeJavaScript(script, true);
+    if (!Array.isArray(rawResult)) {
+      return [];
+    }
+
+    return rawResult
+      .map((entry) => toYomitanTermFrequency(entry))
+      .filter((entry): entry is YomitanTermFrequency => entry !== null);
+  } catch (err) {
+    logger.error('Yomitan term frequency request failed:', (err as Error).message);
+    return [];
+  }
+}
+
 export async function syncYomitanDefaultAnkiServer(
   serverUrl: string,
   deps: YomitanParserRuntimeDeps,

src/main/frequency-dictionary-runtime.ts

@@ -28,7 +28,7 @@ export function getFrequencyDictionarySearchPaths(
 
   const rawSearchPaths: string[] = [];
   // User-provided path takes precedence over bundled/default roots.
-  // Root list should include `vendor/jiten_freq_global` in callers.
+  // Root list should include default installed frequency-dictionary locations in callers.
   if (sourcePath && sourcePath.trim()) {
     rawSearchPaths.push(sourcePath.trim());
     rawSearchPaths.push(path.join(sourcePath.trim(), 'frequency-dictionary'));

src/main/runtime/dictionary-runtime-main-deps.test.ts

@@ -53,9 +53,9 @@ test('frequency dictionary roots main handler returns expected root list', () =>
     joinPath: (...parts) => parts.join('/'),
   })();
 
-  assert.equal(roots.length, 15);
-  assert.equal(roots[0], '/repo/dist/main/../../vendor/jiten_freq_global');
-  assert.equal(roots[14], '/repo');
+  assert.equal(roots.length, 11);
+  assert.equal(roots[0], '/repo/dist/main/../../vendor/frequency-dictionary');
+  assert.equal(roots[10], '/repo');
 });
 
 test('frequency dictionary runtime main deps builder maps search paths/source and log prefix', () => {

src/main/runtime/dictionary-runtime-main-deps.ts

@@ -38,13 +38,9 @@ export function createBuildFrequencyDictionaryRootsMainHandler(deps: {
   joinPath: (...parts: string[]) => string;
 }) {
   return () => [
-    deps.joinPath(deps.dirname, '..', '..', 'vendor', 'jiten_freq_global'),
     deps.joinPath(deps.dirname, '..', '..', 'vendor', 'frequency-dictionary'),
-    deps.joinPath(deps.appPath, 'vendor', 'jiten_freq_global'),
     deps.joinPath(deps.appPath, 'vendor', 'frequency-dictionary'),
-    deps.joinPath(deps.resourcesPath, 'jiten_freq_global'),
     deps.joinPath(deps.resourcesPath, 'frequency-dictionary'),
-    deps.joinPath(deps.resourcesPath, 'app.asar', 'vendor', 'jiten_freq_global'),
     deps.joinPath(deps.resourcesPath, 'app.asar', 'vendor', 'frequency-dictionary'),
     deps.userDataPath,
     deps.appUserDataPath,

vendor/jiten_freq_global/index.json

@@ -1 +0,0 @@
-{"title":"Jiten","format":3,"revision":"Jiten 26-02-16","isUpdatable":true,"indexUrl":"https://api.jiten.moe/api/frequency-list/index","downloadUrl":"https://api.jiten.moe/api/frequency-list/download","sequenced":false,"frequencyMode":"rank-based","author":"Jiten","url":"https://jiten.moe","description":"Dictionary based on frequency data of all media from jiten.moe"}