mirror of
https://github.com/ksyasuda/SubMiner.git
synced 2026-04-03 18:12:07 -07:00
Refactor startup, queries, and workflow into focused modules (#36)
* chore(backlog): add mining workflow milestone and tasks
* refactor: split character dictionary runtime modules
* refactor: split shared type entrypoints
* refactor: use bun serve for stats server
* feat: add repo-local subminer workflow plugin
* fix: add stats server node fallback
* refactor: split immersion tracker query modules
* chore: update backlog task records
* refactor: migrate shared type imports
* refactor: compose startup and setup window wiring
* Add backlog tasks and launcher time helper tests
- Track follow-up cleanup work in Backlog.md
- Replace Date.now usage with shared nowMs helper
- Add launcher args/parser and core regression tests
* test: increase launcher test timeout for CI stability
* fix: address CodeRabbit review feedback
* refactor(main): extract remaining inline runtime logic from main
* chore(backlog): update task notes and changelog fragment
* refactor: split main boot phases
* test: stabilize bun coverage reporting
* Switch plausible endpoint and harden coverage lane parsing
- update docs-site tracking to use the Plausible capture endpoint
- tighten coverage lane argument and LCOV parsing checks
- make script entrypoint use CommonJS main guard
* Restrict docs analytics and build coverage input
- limit Plausible init to docs.subminer.moe
- build Yomitan before src coverage lane
* fix(ci): normalize Windows shortcut paths for cross-platform tests
* Fix verification and immersion-tracker grouping
- isolate verifier artifacts and lease handling
- switch weekly/monthly tracker cutoffs to calendar boundaries
- tighten boot lifecycle and zip writer tests
* fix: resolve CI type failures in boot and immersion query tests
* fix: remove strict spread usage in Date mocks
* fix: use explicit super args for MockDate constructors
* Factor out mock date helper in tracker tests
- reuse a shared `withMockDate` helper for date-sensitive query tests
- make monthly rollup assertions key off `videoId` instead of row order
* fix: use variadic array type for MockDate constructor args
TS2367: fixed-length tuple made args.length === 0 unreachable.
* refactor: remove unused createMainBootRuntimes/Handlers aggregate functions
These functions were never called by production code — main.ts imports
the individual composeBoot* re-exports directly.
* refactor: remove boot re-export alias layer
main.ts now imports directly from the runtime/composers and runtime/domains
modules, eliminating the intermediate boot/ indirection.
* refactor: consolidate 3 near-identical setup window factories
Extract shared createSetupWindowHandler with a config parameter.
Public API unchanged.
* refactor: parameterize duplicated getAffected*Ids query helpers
Four structurally identical functions collapsed into two parameterized
helpers while preserving the existing public API.
* refactor: inline identity composers (stats-startup, overlay-window)
composeStatsStartupRuntime was a no-op that returned its input.
composeOverlayWindowHandlers was a 1-line delegation.
Both removed in favor of direct usage.
* chore: remove unused token/queue file path constants from main.ts
* fix: replace any types in boot services with proper signatures
* refactor: deduplicate ensureDir into shared/fs-utils
5 copies of mkdir-p-if-not-exists consolidated into one shared module
with ensureDir (directory path) and ensureDirForFile (file path) variants.
* fix: tighten type safety in boot services
- Add AppLifecycleShape and OverlayModalInputStateShape constraints
so TAppLifecycleApp and TOverlayModalInputState generics are bounded
- Remove unsafe `as { handleModalInputStateChange? }` cast — now
directly callable via the constraint
- Use `satisfies AppLifecycleShape` for structural validation on the
appLifecycleApp object literal
- Document Electron App.on incompatibility with simple signatures
* refactor: inline subtitle-prefetch-runtime-composer
The composer was a pure pass-through that destructured an object and
reassembled it with the same fields. Inlined at the call site.
* chore: consolidate duplicate import paths in main.ts
* test: extract mpv composer test fixture factory to reduce duplication
* test: add behavioral assertions to composer tests
Upgrade 8 composer test files from shape-only typeof checks to behavioral
assertions that invoke returned handlers and verify injected dependencies are
actually called, following the mpv-runtime-composer pattern.
* refactor: normalize import extensions in query modules
* refactor: consolidate toDbMs into query-shared.ts
* refactor: remove Node.js fallback from stats-server, use Bun only
* Fix monthly rollup test expectations
- Preserve multi-arg Date construction in mock helper
- Align rollup assertions with the correct videoId
* fix: address PR 36 CodeRabbit follow-ups
* fix: harden coverage lane cleanup
* fix(stats): fallback to node server when Bun.serve unavailable
* fix(ci): restore coverage lane compatibility
* chore(backlog): close TASK-242
* fix: address latest CodeRabbit review round
* fix: guard disabled immersion retention windows
* fix: migrate discord rpc wrapper
* fix(ci): add changelog fragment for PR 36
* fix: stabilize macOS visible overlay toggle
* fix: pin installed mpv plugin to current binary
* fix: strip inline subtitle markup from sidebar cues
* fix(renderer): restore subtitle sidebar mpv passthrough
* feat(discord): add configurable presence style presets
Replace the hardcoded "Mining and crafting (Anki cards)" meme message
with a preset system. New `discordPresence.presenceStyle` option
supports four presets: "default" (clean bilingual), "meme" (the OG
Minecraft joke), "japanese" (fully JP), and "minimal". The default
preset shows "Sentence Mining" with 日本語学習中 as the small image
tooltip. Existing users can set presenceStyle to "meme" to keep the
old behavior.
* fix: finalize v0.10.0 release prep
* docs: add subtitle sidebar guide and release note
* chore(backlog): mark docs task done
* fix: lazily resolve youtube playback socket path
* chore(release): build v0.10.0 changelog
* Revert "chore(release): build v0.10.0 changelog"
This reverts commit 9741c0f020.
This commit is contained in:
GitHub
257
src/core/services/immersion-tracker/query-lexical.ts
Normal file
257
src/core/services/immersion-tracker/query-lexical.ts
Normal file
@@ -0,0 +1,257 @@
|
||||
import type { DatabaseSync } from './sqlite';
|
||||
import type {
|
||||
KanjiAnimeAppearanceRow,
|
||||
KanjiDetailRow,
|
||||
KanjiOccurrenceRow,
|
||||
KanjiStatsRow,
|
||||
KanjiWordRow,
|
||||
SessionEventRow,
|
||||
SimilarWordRow,
|
||||
VocabularyStatsRow,
|
||||
WordAnimeAppearanceRow,
|
||||
WordDetailRow,
|
||||
WordOccurrenceRow,
|
||||
} from './types';
|
||||
|
||||
export function getVocabularyStats(
|
||||
db: DatabaseSync,
|
||||
limit = 100,
|
||||
excludePos?: string[],
|
||||
): VocabularyStatsRow[] {
|
||||
const hasExclude = excludePos && excludePos.length > 0;
|
||||
const placeholders = hasExclude ? excludePos.map(() => '?').join(', ') : '';
|
||||
const whereClause = hasExclude
|
||||
? `WHERE (part_of_speech IS NULL OR part_of_speech NOT IN (${placeholders}))`
|
||||
: '';
|
||||
const stmt = db.prepare(`
|
||||
SELECT w.id AS wordId, w.headword, w.word, w.reading,
|
||||
w.part_of_speech AS partOfSpeech, w.pos1, w.pos2, w.pos3,
|
||||
w.frequency, w.frequency_rank AS frequencyRank,
|
||||
w.first_seen AS firstSeen, w.last_seen AS lastSeen,
|
||||
COUNT(DISTINCT sl.anime_id) AS animeCount
|
||||
FROM imm_words w
|
||||
LEFT JOIN imm_word_line_occurrences o ON o.word_id = w.id
|
||||
LEFT JOIN imm_subtitle_lines sl ON sl.line_id = o.line_id AND sl.anime_id IS NOT NULL
|
||||
${whereClause ? whereClause.replace('part_of_speech', 'w.part_of_speech') : ''}
|
||||
GROUP BY w.id
|
||||
ORDER BY w.frequency DESC LIMIT ?
|
||||
`);
|
||||
const params = hasExclude ? [...excludePos, limit] : [limit];
|
||||
return stmt.all(...params) as VocabularyStatsRow[];
|
||||
}
|
||||
|
||||
export function getKanjiStats(db: DatabaseSync, limit = 100): KanjiStatsRow[] {
|
||||
const stmt = db.prepare(`
|
||||
SELECT id AS kanjiId, kanji, frequency,
|
||||
first_seen AS firstSeen, last_seen AS lastSeen
|
||||
FROM imm_kanji ORDER BY frequency DESC LIMIT ?
|
||||
`);
|
||||
return stmt.all(limit) as KanjiStatsRow[];
|
||||
}
|
||||
|
||||
export function getWordOccurrences(
|
||||
db: DatabaseSync,
|
||||
headword: string,
|
||||
word: string,
|
||||
reading: string,
|
||||
limit = 100,
|
||||
offset = 0,
|
||||
): WordOccurrenceRow[] {
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT
|
||||
l.anime_id AS animeId,
|
||||
a.canonical_title AS animeTitle,
|
||||
l.video_id AS videoId,
|
||||
v.canonical_title AS videoTitle,
|
||||
v.source_path AS sourcePath,
|
||||
l.secondary_text AS secondaryText,
|
||||
l.session_id AS sessionId,
|
||||
l.line_index AS lineIndex,
|
||||
l.segment_start_ms AS segmentStartMs,
|
||||
l.segment_end_ms AS segmentEndMs,
|
||||
l.text AS text,
|
||||
o.occurrence_count AS occurrenceCount
|
||||
FROM imm_word_line_occurrences o
|
||||
JOIN imm_words w ON w.id = o.word_id
|
||||
JOIN imm_subtitle_lines l ON l.line_id = o.line_id
|
||||
JOIN imm_videos v ON v.video_id = l.video_id
|
||||
LEFT JOIN imm_anime a ON a.anime_id = l.anime_id
|
||||
WHERE w.headword = ? AND w.word = ? AND w.reading = ?
|
||||
ORDER BY l.CREATED_DATE DESC, l.line_id DESC
|
||||
LIMIT ?
|
||||
OFFSET ?
|
||||
`,
|
||||
)
|
||||
.all(headword, word, reading, limit, offset) as unknown as WordOccurrenceRow[];
|
||||
}
|
||||
|
||||
export function getKanjiOccurrences(
|
||||
db: DatabaseSync,
|
||||
kanji: string,
|
||||
limit = 100,
|
||||
offset = 0,
|
||||
): KanjiOccurrenceRow[] {
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT
|
||||
l.anime_id AS animeId,
|
||||
a.canonical_title AS animeTitle,
|
||||
l.video_id AS videoId,
|
||||
v.canonical_title AS videoTitle,
|
||||
v.source_path AS sourcePath,
|
||||
l.secondary_text AS secondaryText,
|
||||
l.session_id AS sessionId,
|
||||
l.line_index AS lineIndex,
|
||||
l.segment_start_ms AS segmentStartMs,
|
||||
l.segment_end_ms AS segmentEndMs,
|
||||
l.text AS text,
|
||||
o.occurrence_count AS occurrenceCount
|
||||
FROM imm_kanji_line_occurrences o
|
||||
JOIN imm_kanji k ON k.id = o.kanji_id
|
||||
JOIN imm_subtitle_lines l ON l.line_id = o.line_id
|
||||
JOIN imm_videos v ON v.video_id = l.video_id
|
||||
LEFT JOIN imm_anime a ON a.anime_id = l.anime_id
|
||||
WHERE k.kanji = ?
|
||||
ORDER BY l.CREATED_DATE DESC, l.line_id DESC
|
||||
LIMIT ?
|
||||
OFFSET ?
|
||||
`,
|
||||
)
|
||||
.all(kanji, limit, offset) as unknown as KanjiOccurrenceRow[];
|
||||
}
|
||||
|
||||
export function getSessionEvents(
|
||||
db: DatabaseSync,
|
||||
sessionId: number,
|
||||
limit = 500,
|
||||
eventTypes?: number[],
|
||||
): SessionEventRow[] {
|
||||
if (!eventTypes || eventTypes.length === 0) {
|
||||
const stmt = db.prepare(`
|
||||
SELECT event_type AS eventType, ts_ms AS tsMs, payload_json AS payload
|
||||
FROM imm_session_events WHERE session_id = ? ORDER BY ts_ms ASC LIMIT ?
|
||||
`);
|
||||
return stmt.all(sessionId, limit) as SessionEventRow[];
|
||||
}
|
||||
|
||||
const placeholders = eventTypes.map(() => '?').join(', ');
|
||||
const stmt = db.prepare(`
|
||||
SELECT event_type AS eventType, ts_ms AS tsMs, payload_json AS payload
|
||||
FROM imm_session_events
|
||||
WHERE session_id = ? AND event_type IN (${placeholders})
|
||||
ORDER BY ts_ms ASC
|
||||
LIMIT ?
|
||||
`);
|
||||
return stmt.all(sessionId, ...eventTypes, limit) as SessionEventRow[];
|
||||
}
|
||||
|
||||
export function getWordDetail(db: DatabaseSync, wordId: number): WordDetailRow | null {
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT id AS wordId, headword, word, reading,
|
||||
part_of_speech AS partOfSpeech, pos1, pos2, pos3,
|
||||
frequency, first_seen AS firstSeen, last_seen AS lastSeen
|
||||
FROM imm_words WHERE id = ?
|
||||
`,
|
||||
)
|
||||
.get(wordId) as WordDetailRow | null;
|
||||
}
|
||||
|
||||
export function getWordAnimeAppearances(
|
||||
db: DatabaseSync,
|
||||
wordId: number,
|
||||
): WordAnimeAppearanceRow[] {
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT a.anime_id AS animeId, a.canonical_title AS animeTitle,
|
||||
SUM(o.occurrence_count) AS occurrenceCount
|
||||
FROM imm_word_line_occurrences o
|
||||
JOIN imm_subtitle_lines sl ON sl.line_id = o.line_id
|
||||
JOIN imm_anime a ON a.anime_id = sl.anime_id
|
||||
WHERE o.word_id = ? AND sl.anime_id IS NOT NULL
|
||||
GROUP BY a.anime_id
|
||||
ORDER BY occurrenceCount DESC
|
||||
`,
|
||||
)
|
||||
.all(wordId) as WordAnimeAppearanceRow[];
|
||||
}
|
||||
|
||||
export function getSimilarWords(db: DatabaseSync, wordId: number, limit = 10): SimilarWordRow[] {
|
||||
const word = db.prepare('SELECT headword, reading FROM imm_words WHERE id = ?').get(wordId) as {
|
||||
headword: string;
|
||||
reading: string;
|
||||
} | null;
|
||||
if (!word || word.headword.trim() === '') return [];
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT id AS wordId, headword, word, reading, frequency
|
||||
FROM imm_words
|
||||
WHERE id != ?
|
||||
AND (reading = ? OR headword LIKE ? OR headword LIKE ?)
|
||||
ORDER BY frequency DESC
|
||||
LIMIT ?
|
||||
`,
|
||||
)
|
||||
.all(
|
||||
wordId,
|
||||
word.reading,
|
||||
`%${word.headword.charAt(0)}%`,
|
||||
`%${word.headword.charAt(word.headword.length - 1)}%`,
|
||||
limit,
|
||||
) as SimilarWordRow[];
|
||||
}
|
||||
|
||||
export function getKanjiDetail(db: DatabaseSync, kanjiId: number): KanjiDetailRow | null {
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT id AS kanjiId, kanji, frequency, first_seen AS firstSeen, last_seen AS lastSeen
|
||||
FROM imm_kanji WHERE id = ?
|
||||
`,
|
||||
)
|
||||
.get(kanjiId) as KanjiDetailRow | null;
|
||||
}
|
||||
|
||||
export function getKanjiAnimeAppearances(
|
||||
db: DatabaseSync,
|
||||
kanjiId: number,
|
||||
): KanjiAnimeAppearanceRow[] {
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT a.anime_id AS animeId, a.canonical_title AS animeTitle,
|
||||
SUM(o.occurrence_count) AS occurrenceCount
|
||||
FROM imm_kanji_line_occurrences o
|
||||
JOIN imm_subtitle_lines sl ON sl.line_id = o.line_id
|
||||
JOIN imm_anime a ON a.anime_id = sl.anime_id
|
||||
WHERE o.kanji_id = ? AND sl.anime_id IS NOT NULL
|
||||
GROUP BY a.anime_id
|
||||
ORDER BY occurrenceCount DESC
|
||||
`,
|
||||
)
|
||||
.all(kanjiId) as KanjiAnimeAppearanceRow[];
|
||||
}
|
||||
|
||||
export function getKanjiWords(db: DatabaseSync, kanjiId: number, limit = 20): KanjiWordRow[] {
|
||||
const kanjiRow = db.prepare('SELECT kanji FROM imm_kanji WHERE id = ?').get(kanjiId) as {
|
||||
kanji: string;
|
||||
} | null;
|
||||
if (!kanjiRow) return [];
|
||||
return db
|
||||
.prepare(
|
||||
`
|
||||
SELECT id AS wordId, headword, word, reading, frequency
|
||||
FROM imm_words
|
||||
WHERE headword LIKE ?
|
||||
ORDER BY frequency DESC
|
||||
LIMIT ?
|
||||
`,
|
||||
)
|
||||
.all(`%${kanjiRow.kanji}%`, limit) as KanjiWordRow[];
|
||||
}
|
||||
Reference in New Issue
Block a user