fix(stats): report complete vocabulary summary totals

src/core/services/immersion-tracker/__tests__/query.test.ts

@@ -31,6 +31,7 @@ import {
   getKanjiOccurrences,
   getSessionSummaries,
   getVocabularyStats,
+  getVocabularySummary,
   getKanjiStats,
   getSessionEvents,
   getSessionTimeline,
@@ -1875,6 +1876,88 @@ test('getVocabularyStats returns rows ordered by frequency descending', () => {
   }
 });
 
+test('getVocabularySummary counts every tracked vocabulary row instead of a display page', () => {
+  const dbPath = makeDbPath();
+  const db = openTestDb(dbPath);
+
+  try {
+    ensureSchema(db);
+    const nowSec = Math.floor(Date.now() / 1000);
+    const insertWord = db.prepare(`
+      INSERT INTO imm_words (
+        headword, word, reading, part_of_speech, pos1, pos2, pos3,
+        first_seen, last_seen, frequency
+      ) VALUES (?, ?, '', 'noun', '名詞', '一般', '', ?, ?, 1)
+    `);
+    const insertKanji = db.prepare(`
+      INSERT INTO imm_kanji (kanji, first_seen, last_seen, frequency)
+      VALUES (?, ?, ?, 1)
+    `);
+
+    for (let index = 0; index < 501; index += 1) {
+      insertWord.run(`単語${index}`, `単語${index}`, nowSec - 8 * 86_400, nowSec - 8 * 86_400);
+    }
+    for (let index = 0; index < 201; index += 1) {
+      insertKanji.run(
+        String.fromCodePoint(0x4e00 + index),
+        nowSec - 8 * 86_400,
+        nowSec - 8 * 86_400,
+      );
+    }
+    insertWord.run('今週', '今週', nowSec - 86_400, nowSec - 86_400);
+
+    assert.deepEqual(getVocabularySummary(db, new Set(['単語0', '今週']), nowSec * 1000), {
+      uniqueWords: 502,
+      uniqueWordsWithoutNames: 502,
+      uniqueKanji: 201,
+      newThisWeek: 1,
+      newThisWeekWithoutNames: 1,
+      knownWordCount: 2,
+      knownWordCountWithoutNames: 2,
+    });
+  } finally {
+    db.close();
+    cleanupDbPath(dbPath);
+  }
+});
+
+test('getVocabularySummary applies vocabulary exclusions and Hide Names totals', () => {
+  const dbPath = makeDbPath();
+  const db = openTestDb(dbPath);
+
+  try {
+    ensureSchema(db);
+    const insertWord = db.prepare(`
+      INSERT INTO imm_words (
+        headword, word, reading, part_of_speech, pos1, pos2, pos3,
+        first_seen, last_seen, frequency
+      ) VALUES (?, ?, '', 'noun', '名詞', ?, '', 1, 1, 1)
+    `);
+    insertWord.run('猫', '猫', '一般');
+    insertWord.run('太郎', '太郎', '固有名詞');
+    insertWord.run('東京', '東京都', '一般');
+    db.prepare(
+      `
+      INSERT INTO imm_stats_excluded_words (headword, word, reading)
+      VALUES ('東京', '東京', '')
+    `,
+    ).run();
+
+    assert.deepEqual(getVocabularySummary(db, new Set(['猫', '太郎', '東京']), 9 * 86_400_000), {
+      uniqueWords: 2,
+      uniqueWordsWithoutNames: 1,
+      uniqueKanji: 0,
+      newThisWeek: 0,
+      newThisWeekWithoutNames: 0,
+      knownWordCount: 2,
+      knownWordCountWithoutNames: 1,
+    });
+  } finally {
+    db.close();
+    cleanupDbPath(dbPath);
+  }
+});
+
 test('getVocabularyStats filters rows that fail tokenizer vocabulary rules', () => {
   const dbPath = makeDbPath();
   const db = openTestDb(dbPath);

src/core/services/immersion-tracker/query-lexical.ts

@@ -13,6 +13,7 @@ import type {
   SimilarWordRow,
   StatsExcludedWordRow,
   VocabularyStatsRow,
+  VocabularyStatsSummary,
   WordAnimeAppearanceRow,
   WordDetailRow,
   WordOccurrenceRow,
@@ -153,6 +154,75 @@ export function getVocabularyStats(
   return visibleRows.slice(0, limit);
 }
 
+function excludedVocabularyAliases(
+  word: Pick<VocabularyStatsRow, 'headword' | 'word' | 'reading'>,
+): string[] {
+  const aliases = [word.headword.trim(), word.word.trim()].filter(Boolean);
+  if (aliases.length === 0) aliases.push(word.reading.trim());
+  return [...new Set(aliases)];
+}
+
+function timestampSeconds(timestamp: number): number {
+  return timestamp < 10_000_000_000 ? timestamp : Math.floor(timestamp / 1000);
+}
+
+export function getVocabularySummary(
+  db: DatabaseSync,
+  knownWords: ReadonlySet<string> | null,
+  nowMs: number = Date.now(),
+): VocabularyStatsSummary {
+  const words = db
+    .prepare(
+      `
+      SELECT id AS wordId, headword, word, reading,
+        part_of_speech AS partOfSpeech, pos1, pos2, pos3,
+        frequency, frequency_rank AS frequencyRank,
+        first_seen AS firstSeen, last_seen AS lastSeen,
+        0 AS animeCount
+      FROM imm_words
+    `,
+    )
+    .all() as VocabularyStatsRow[];
+  const excludedAliases = new Set(
+    getStatsExcludedWords(db).flatMap((word) => excludedVocabularyAliases(word)),
+  );
+  const weekAgoSec = nowMs / 1000 - 7 * 86_400;
+  const summary: VocabularyStatsSummary = {
+    uniqueWords: 0,
+    uniqueWordsWithoutNames: 0,
+    uniqueKanji: (db.prepare('SELECT COUNT(*) AS count FROM imm_kanji').get() as { count: number })
+      .count,
+    newThisWeek: 0,
+    newThisWeekWithoutNames: 0,
+    knownWordCount: knownWords ? 0 : null,
+    knownWordCountWithoutNames: knownWords ? 0 : null,
+  };
+
+  for (const word of words) {
+    if (
+      !isVocabularyStatsRowVisible(word) ||
+      excludedVocabularyAliases(word).some((alias) => excludedAliases.has(alias))
+    ) {
+      continue;
+    }
+    const isName = word.pos2 === '固有名詞';
+    const isNewThisWeek = timestampSeconds(fromDbTimestamp(word.firstSeen) ?? 0) >= weekAgoSec;
+    const isKnown = knownWords?.has(word.headword) ?? false;
+    summary.uniqueWords += 1;
+    if (!isName) summary.uniqueWordsWithoutNames += 1;
+    if (isNewThisWeek) {
+      summary.newThisWeek += 1;
+      if (!isName) summary.newThisWeekWithoutNames += 1;
+    }
+    if (isKnown) {
+      summary.knownWordCount! += 1;
+      if (!isName) summary.knownWordCountWithoutNames! += 1;
+    }
+  }
+
+  return summary;
+}
+
 export function getStatsExcludedWords(db: DatabaseSync): StatsExcludedWordRow[] {
   return db
     .prepare(

src/core/services/immersion-tracker/types.ts

@@ -306,6 +306,16 @@ export interface VocabularyStatsRow {
   lastSeen: number;
 }
 
+export interface VocabularyStatsSummary {
+  uniqueWords: number;
+  uniqueWordsWithoutNames: number;
+  uniqueKanji: number;
+  newThisWeek: number;
+  newThisWeekWithoutNames: number;
+  knownWordCount: number | null;
+  knownWordCountWithoutNames: number | null;
+}
+
 export interface StatsExcludedWordRow {
   headword: string;
   word: string;