mirror of
https://github.com/ksyasuda/SubMiner.git
synced 2026-08-12 01:55:55 -07:00
feat(tokenizer): use Yomitan word classes for subtitle POS filtering (#57)
* feat(tokenizer): use Yomitan word classes for subtitle POS filtering - Carry matched headword wordClasses from termsFind into YomitanScanToken - Map recognized Yomitan wordClasses to SubMiner coarse POS before annotation - MeCab enrichment now fills only missing POS fields, preserving existing coarse pos1 - Exclude standalone grammar particles, して helper fragments, and single-kana surfaces from annotations - Respect source-text punctuation gaps when counting N+1 sentence words - Preserve known-word highlight on excluded kanji-containing tokens - Add backlog tasks 304 (N+1 boundary bug) and 305 (wordClasses POS, done) * fix(tokenizer): preserve annotation and enrichment behavior * fix: restore jlpt subtitle underlines * fix: exclude kana-only n+1 targets * fix: refresh overlay on Hyprland fullscreen * fix: address fullscreen and n-plus-one review notes * fix: address CodeRabbit review comments * fix: accept modified digits for multi-line sentence mining * Cancel pending Linux MPV fullscreen overlay refresh bursts - return a cancel handle from the Linux refresh burst scheduler - clear pending refresh bursts when overlays hide or windows close - tighten the burst test polling to wait for the async refresh * fix: suppress N+1 for kana-only candidates and fix minSentenceWords coun - Treat kana-only tokens with surrounding subtitle punctuation (…, ―, etc.) as kana-only so they are not promoted to N+1 targets - Exclude unknown tokens filtered from N+1 targeting from the minSentenceWords count so filtered kana-only unknowns cannot satisfy sentence length threshold - Add regression tests for kana-only candidate suppression and filtered-unknown padding cases * Suppress subtitle annotations for grammar fragments - Hide annotation metadata for auxiliary inflection and ja-nai endings - Preserve lexical `くれる` forms and add regression coverage * Fix kana-only N+1 tokenizer regression test - Use a pure-kana fixture for the subtitle token N+1 case - Update task notes for the latest CodeRabbit follow-up * Fix managed playback exit and tokenizer grammar splits - Ignore background stats daemons during regular app startup - Split standalone grammar endings before applying annotations - Clear helper-span annotations for auxiliary-only tokens * fix: refresh current subtitle after known-word mining * fix: suppress sigh interjection annotations * fix: preserve jlpt underline color after lookup * Replace grammar-ending permutations with shared matcher; preserve word a - Extract `grammar-ending.ts` with `isStandaloneGrammarEndingText` / `isSubtitleGrammarEndingText` pattern matchers - Replace `STANDALONE_GRAMMAR_ENDINGS` set in parser-selection-stage with shared matcher - Replace generated phrase sets in subtitle-annotation-filter with shared matcher - Remove stale duplicate subtitle-exclusion constants and helpers from annotation-stage - Manual clipboard card updates now write only to the sentence audio field, leaving word/expression audio untouched * fix: CI changelog, annotation options threading, and Jellyfin quit - Add `type: fixed` / `area:` frontmatter to `changes/319` to pass `changelog:lint` - Thread `TokenizerAnnotationOptions` through `stripSubtitleAnnotationMetadata` so `sourceText` is honored - Include `jellyfinPlay` in `shouldQuitOnDisconnectWhenOverlayRuntimeInitialized` predicate - Make mouse test `elementFromPoint` stubs coordinate-sensitive - Make Lua test `.tmp` mkdir portable on Windows * Preserve overlay across macOS flaps and mpv playlist changes - keep visible overlays alive during transient macOS tracker loss - reuse the running mpv overlay path on playlist navigation - update regression coverage and changelog fragments * fix: restore stats daemon deferral * fix: keep subtitle prefetch alive after cache hits * Fix JLPT underline color drift and AniList skipped-threshold sync - Replace JLPT `text-decoration` underlines with `border-bottom` so Chromium selection/hover cannot repaint them to another annotation's color - Lock JLPT underline color for combined annotation selectors (known, n+1, frequency) and character hover/selection states - Trigger AniList post-watch check on every mpv time-position update to catch skipped completion thresholds - Fall back to filename-parser season/episode when guessit omits them * fix: address coderabbit feedback * fix: sync AniList after seeked completion * fix: preserve ordinal frequency annotations * fix: preserve known highlighting for filtered tokens * fix: address PR #57 CodeRabbit feedback - Acquire AniList post-watch in-flight lock before async gating to prevent duplicate writes - Isolate manual watched mark result from AniList post-watch callback failures - Report known-word cache clears as mutations during immediate append when state existed - Add regression tests for each fix * fix: stop AniList setup reopening on Linux when keyring token exists - Gate setup success on token persistence: `saveToken` now returns `boolean`; on failure, keeps the setup window open instead of reporting success - Config reload passes `allowSetupPrompt: false` so playback reloads don't re-open the setup window - Add regression test for persistence-failure path * fix: suppress known highlights for subtitle particles * fix: retry transient AniList safeStorage failures * fix: hide overlay focus ring * fix: align Hyprland fullscreen overlays * fix: restore subtitle playback keybindings * fix: align Hyprland overlay windows to mpv and stop pinning them - Force-apply exact Hyprland move/resize/setprop dispatches when bounds are provided - Stop pinning overlay windows; toggle pin off when Hyprland reports pinned=true - Compensate stats overlay outer placement for Electron/Wayland content insets - Make stats overlay window and page opaque so mpv cannot show through transparent insets - Constrain stats app to h-screen with internal scroll so content covers mpv from y=0 - Lock overlay/stats window titles against page-title-updated events - Add regression coverage for placement dispatches, inset compensation, and CSS overlay mode * fix: retain frequency rank for honorific prefix-noun tokens - Add `shouldAllowHonorificPrefixNounFrequency` to exempt お/ご/御 + noun merged tokens from frequency exclusion - Add regression test for `ご機嫌` asserting rank 5484 is preserved after MeCab enrichment and annotation - Close TASK-341 * fix: map openCharacterDictionary session action to --open-character-dict - Add missing Lua CLI dispatch entry for openCharacterDictionary - Add regression test for Alt+Meta+A binding and CLI flag forwarding * fix: keep macOS overlay interactive while mpv remains active - Overlay no longer hides or becomes click-through during tracker refreshes when mpv is the focused window - Preserve already-visible overlay when tracker is temporarily not ready but mpv target signal is active - Add regression tests for active-mpv tracker refresh and transient tracker-not-ready paths * fix: address coderabbit subtitle follow-ups * fix: resolve media detail from sessions when lifetime summary is absent - Change `getMediaDetail` JOIN to LEFT JOIN on `imm_lifetime_media` and fall back to aggregated session metrics when no lifetime row exists - Add filter `AND (lm.video_id IS NOT NULL OR s.session_id IS NOT NULL)` to keep results valid - Add regression test covering the session-visible / media-detail-missing mismatch * fix: address PR-57 CodeRabbit findings and CI failures - use filtered word counts in media detail session token aggregation - cancel fullscreen refresh burst on exit via updateLinuxMpvFullscreenOverlayRefreshBurst - guard Hyprland JSON.parse in try/catch; exclude windowtitle from geometry events - narrow focus suppression from :focus to :focus-visible - apply JLPT lock selectors to word-name-match tokens (N1–N5) * fix: macOS overlay z-order and Yomitan compound token known highlighting - Release always-on-top when tracked mpv loses foreground on macOS - Skip visible overlay blur restacking on macOS to avoid covering unrelated windows - Prefer Yomitan internal parse tokens over fragmented scanner output for known-word decisions - Add regression tests for both behaviors * fix: macOS visible-overlay blur no longer invokes Windows-only blur call - Split win32/darwin branches in handleOverlayWindowBlurred so darwin visible blur returns early without calling onWindowsVisibleOverlayBlur - Add regression test asserting Windows callback stays inactive on macOS visible overlay blur - Close TASK-347
This commit is contained in:
GitHub
File diff suppressed because it is too large
Load Diff
@@ -18,57 +18,6 @@ const KATAKANA_TO_HIRAGANA_OFFSET = 0x60;
|
||||
const KATAKANA_CODEPOINT_START = 0x30a1;
|
||||
const KATAKANA_CODEPOINT_END = 0x30f6;
|
||||
const JLPT_LEVEL_LOOKUP_CACHE_LIMIT = 2048;
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_TERMS = new Set([
|
||||
'ああ',
|
||||
'ええ',
|
||||
'うう',
|
||||
'おお',
|
||||
'はあ',
|
||||
'はは',
|
||||
'へえ',
|
||||
'ふう',
|
||||
'ほう',
|
||||
]);
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_PREFIXES = ['ん', 'の', 'なん', 'なの'];
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_CORES = [
|
||||
'だ',
|
||||
'です',
|
||||
'でした',
|
||||
'だった',
|
||||
'では',
|
||||
'じゃ',
|
||||
'でしょう',
|
||||
'だろう',
|
||||
] as const;
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_TRAILING_PARTICLES = [
|
||||
'',
|
||||
'か',
|
||||
'ね',
|
||||
'よ',
|
||||
'な',
|
||||
'けど',
|
||||
'よね',
|
||||
'かな',
|
||||
'かね',
|
||||
] as const;
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDINGS = new Set(
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_PREFIXES.flatMap((prefix) =>
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_CORES.flatMap((core) =>
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_TRAILING_PARTICLES.map(
|
||||
(particle) => `${prefix}${core}${particle}`,
|
||||
),
|
||||
),
|
||||
),
|
||||
);
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_TRAILING_PARTICLE_SUFFIXES = new Set([
|
||||
'って',
|
||||
'ってよ',
|
||||
'ってね',
|
||||
'ってな',
|
||||
'ってさ',
|
||||
'ってか',
|
||||
'ってば',
|
||||
]);
|
||||
|
||||
const jlptLevelLookupCaches = new WeakMap<
|
||||
(text: string) => JlptLevel | null,
|
||||
@@ -89,6 +38,7 @@ export interface AnnotationStageOptions {
|
||||
minSentenceWordsForNPlusOne?: number;
|
||||
pos1Exclusions?: ReadonlySet<string>;
|
||||
pos2Exclusions?: ReadonlySet<string>;
|
||||
sourceText?: string;
|
||||
}
|
||||
|
||||
function resolveKnownWordText(
|
||||
@@ -103,10 +53,6 @@ function normalizePos1Tag(pos1: string | undefined): string {
|
||||
return typeof pos1 === 'string' ? pos1.trim() : '';
|
||||
}
|
||||
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_POS1 = new Set(['感動詞']);
|
||||
const SUBTITLE_ANNOTATION_GRAMMAR_ONLY_POS1 = new Set(['助詞', '助動詞', '連体詞']);
|
||||
const AUXILIARY_STEM_GRAMMAR_TAIL_POS1 = new Set(['名詞', '助動詞', '助詞']);
|
||||
|
||||
function splitNormalizedTagParts(normalizedTag: string): string[] {
|
||||
if (!normalizedTag) {
|
||||
return [];
|
||||
@@ -128,57 +74,6 @@ function isExcludedByTagSet(normalizedTag: string, exclusions: ReadonlySet<strin
|
||||
return parts.some((part) => exclusions.has(part));
|
||||
}
|
||||
|
||||
function isExcludedFromSubtitleAnnotationsByPos1(normalizedPos1: string): boolean {
|
||||
const parts = splitNormalizedTagParts(normalizedPos1);
|
||||
if (parts.some((part) => SUBTITLE_ANNOTATION_EXCLUDED_POS1.has(part))) {
|
||||
return true;
|
||||
}
|
||||
|
||||
return parts.length > 0 && parts.every((part) => SUBTITLE_ANNOTATION_GRAMMAR_ONLY_POS1.has(part));
|
||||
}
|
||||
|
||||
function isExcludedTrailingParticleMergedToken(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeJlptTextForExclusion(token.surface);
|
||||
const normalizedHeadword = normalizeJlptTextForExclusion(token.headword);
|
||||
if (
|
||||
!normalizedSurface ||
|
||||
!normalizedHeadword ||
|
||||
!normalizedSurface.startsWith(normalizedHeadword)
|
||||
) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const suffix = normalizedSurface.slice(normalizedHeadword.length);
|
||||
if (!SUBTITLE_ANNOTATION_EXCLUDED_TRAILING_PARTICLE_SUFFIXES.has(suffix)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePos1Tag(token.pos1));
|
||||
if (pos1Parts.length < 2) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const [leadingPos1, ...trailingPos1] = pos1Parts;
|
||||
if (!leadingPos1 || SUBTITLE_ANNOTATION_GRAMMAR_ONLY_POS1.has(leadingPos1)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return trailingPos1.length > 0 && trailingPos1.every((part) => part === '助詞');
|
||||
}
|
||||
|
||||
function isAuxiliaryStemGrammarTailToken(token: MergedToken): boolean {
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePos1Tag(token.pos1));
|
||||
if (
|
||||
pos1Parts.length === 0 ||
|
||||
!pos1Parts.every((part) => AUXILIARY_STEM_GRAMMAR_TAIL_POS1.has(part))
|
||||
) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos3Parts = splitNormalizedTagParts(normalizePos2Tag(token.pos3));
|
||||
return pos3Parts.includes('助動詞語幹');
|
||||
}
|
||||
|
||||
function resolvePos1Exclusions(options: AnnotationStageOptions): ReadonlySet<string> {
|
||||
if (options.pos1Exclusions) {
|
||||
return options.pos1Exclusions;
|
||||
@@ -254,6 +149,45 @@ function shouldAllowContentLedMergedTokenFrequency(
|
||||
return true;
|
||||
}
|
||||
|
||||
function shouldAllowOrdinalPrefixNounFrequency(token: MergedToken): boolean {
|
||||
const normalizedSurface = token.surface.trim();
|
||||
const normalizedHeadword = token.headword.trim();
|
||||
if (!normalizedSurface.startsWith('第') && !normalizedHeadword.startsWith('第')) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePos1Tag(token.pos1));
|
||||
const pos2Parts = splitNormalizedTagParts(normalizePos2Tag(token.pos2));
|
||||
return (
|
||||
pos1Parts.length >= 2 &&
|
||||
pos1Parts[0] === '接頭詞' &&
|
||||
pos1Parts.slice(1).some((part) => part === '名詞') &&
|
||||
pos2Parts[0] === '数接続' &&
|
||||
pos2Parts.slice(1).some((part) => part === '数')
|
||||
);
|
||||
}
|
||||
|
||||
function shouldAllowHonorificPrefixNounFrequency(token: MergedToken): boolean {
|
||||
const normalizedSurface = token.surface.trim();
|
||||
const normalizedHeadword = token.headword.trim();
|
||||
if (
|
||||
!['お', 'ご', '御'].some(
|
||||
(prefix) => normalizedSurface.startsWith(prefix) || normalizedHeadword.startsWith(prefix),
|
||||
)
|
||||
) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePos1Tag(token.pos1));
|
||||
const pos2Parts = splitNormalizedTagParts(normalizePos2Tag(token.pos2));
|
||||
return (
|
||||
pos1Parts.length >= 2 &&
|
||||
pos1Parts[0] === '接頭詞' &&
|
||||
pos1Parts.slice(1).some((part) => part === '名詞') &&
|
||||
pos2Parts[0] === '名詞接続'
|
||||
);
|
||||
}
|
||||
|
||||
function isFrequencyExcludedByPos(
|
||||
token: MergedToken,
|
||||
pos1Exclusions: ReadonlySet<string>,
|
||||
@@ -273,12 +207,24 @@ function isFrequencyExcludedByPos(
|
||||
pos1Exclusions,
|
||||
pos2Exclusions,
|
||||
);
|
||||
const allowOrdinalPrefixNounToken = shouldAllowOrdinalPrefixNounFrequency(token);
|
||||
const allowHonorificPrefixNounToken = shouldAllowHonorificPrefixNounFrequency(token);
|
||||
|
||||
if (isExcludedByTagSet(normalizedPos1, pos1Exclusions) && !allowContentLedMergedToken) {
|
||||
if (
|
||||
isExcludedByTagSet(normalizedPos1, pos1Exclusions) &&
|
||||
!allowContentLedMergedToken &&
|
||||
!allowOrdinalPrefixNounToken &&
|
||||
!allowHonorificPrefixNounToken
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isExcludedByTagSet(normalizedPos2, pos2Exclusions) && !allowContentLedMergedToken) {
|
||||
if (
|
||||
isExcludedByTagSet(normalizedPos2, pos2Exclusions) &&
|
||||
!allowContentLedMergedToken &&
|
||||
!allowOrdinalPrefixNounToken &&
|
||||
!allowHonorificPrefixNounToken
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -608,50 +554,15 @@ function isJlptEligibleToken(token: MergedToken): boolean {
|
||||
return true;
|
||||
}
|
||||
|
||||
function isExcludedFromSubtitleAnnotationsByTerm(token: MergedToken): boolean {
|
||||
const candidates = [token.surface, token.reading, resolveJlptLookupText(token)].filter(
|
||||
(candidate): candidate is string => typeof candidate === 'string' && candidate.length > 0,
|
||||
);
|
||||
|
||||
for (const candidate of candidates) {
|
||||
const trimmedCandidate = candidate.trim();
|
||||
if (!trimmedCandidate) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const normalizedCandidate = normalizeJlptTextForExclusion(trimmedCandidate);
|
||||
if (!normalizedCandidate) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_TERMS.has(trimmedCandidate) ||
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_TERMS.has(normalizedCandidate) ||
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDINGS.has(trimmedCandidate) ||
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDINGS.has(normalizedCandidate)
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (
|
||||
isTrailingSmallTsuKanaSfx(trimmedCandidate) ||
|
||||
isTrailingSmallTsuKanaSfx(normalizedCandidate) ||
|
||||
isReduplicatedKanaSfxWithOptionalTrailingTo(trimmedCandidate) ||
|
||||
isReduplicatedKanaSfxWithOptionalTrailingTo(normalizedCandidate)
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
export function shouldExcludeTokenFromSubtitleAnnotations(token: MergedToken): boolean {
|
||||
return sharedShouldExcludeTokenFromSubtitleAnnotations(token);
|
||||
}
|
||||
|
||||
export function stripSubtitleAnnotationMetadata(token: MergedToken): MergedToken {
|
||||
return sharedStripSubtitleAnnotationMetadata(token);
|
||||
export function stripSubtitleAnnotationMetadata(
|
||||
token: MergedToken,
|
||||
options: AnnotationStageOptions = {},
|
||||
): MergedToken {
|
||||
return sharedStripSubtitleAnnotationMetadata(token, options);
|
||||
}
|
||||
|
||||
function computeTokenKnownStatus(
|
||||
@@ -734,10 +645,14 @@ export function annotateTokens(
|
||||
pos2Exclusions,
|
||||
})
|
||||
) {
|
||||
return sharedStripSubtitleAnnotationMetadata(token, {
|
||||
const strippedToken = sharedStripSubtitleAnnotationMetadata(token, {
|
||||
pos1Exclusions,
|
||||
pos2Exclusions,
|
||||
});
|
||||
return {
|
||||
...strippedToken,
|
||||
isKnown: false,
|
||||
};
|
||||
}
|
||||
|
||||
const prioritizedNameMatch = nameMatchEnabled && token.isNameMatch === true;
|
||||
@@ -781,6 +696,7 @@ export function annotateTokens(
|
||||
sanitizedMinSentenceWordsForNPlusOne,
|
||||
pos1Exclusions,
|
||||
pos2Exclusions,
|
||||
options.sourceText,
|
||||
);
|
||||
|
||||
if (!nameMatchEnabled) {
|
||||
|
||||
@@ -0,0 +1,124 @@
|
||||
const KATAKANA_TO_HIRAGANA_OFFSET = 0x60;
|
||||
const KATAKANA_CODEPOINT_START = 0x30a1;
|
||||
const KATAKANA_CODEPOINT_END = 0x30f6;
|
||||
|
||||
const SENTENCE_FINAL_PARTICLE_SUFFIXES = ['', 'か', 'ね', 'よ', 'な', 'わ'] as const;
|
||||
const EXPLANATORY_ENDING_PREFIXES = ['ん', 'の', 'なん', 'なの'] as const;
|
||||
const EXPLANATORY_ENDING_CORES = [
|
||||
'だ',
|
||||
'です',
|
||||
'でした',
|
||||
'だった',
|
||||
'では',
|
||||
'じゃ',
|
||||
'でしょう',
|
||||
'だろう',
|
||||
] as const;
|
||||
const EXPLANATORY_ENDING_TRAILING_PARTICLES = [
|
||||
'',
|
||||
'か',
|
||||
'ね',
|
||||
'よ',
|
||||
'な',
|
||||
'けど',
|
||||
'よね',
|
||||
'かな',
|
||||
'かね',
|
||||
] as const;
|
||||
const EXPLANATORY_ENDING_THOUGHT_SUFFIXES = ['か', 'かな', 'かね'] as const;
|
||||
const NEGATIVE_COPULA_PREFIXES = ['じゃ', 'では'] as const;
|
||||
|
||||
export function normalizeGrammarEndingText(text: string): string {
|
||||
const raw = text.trim();
|
||||
if (!raw) {
|
||||
return '';
|
||||
}
|
||||
|
||||
let normalized = '';
|
||||
for (const char of raw) {
|
||||
const code = char.codePointAt(0);
|
||||
if (code === undefined) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (code >= KATAKANA_CODEPOINT_START && code <= KATAKANA_CODEPOINT_END) {
|
||||
normalized += String.fromCodePoint(code - KATAKANA_TO_HIRAGANA_OFFSET);
|
||||
continue;
|
||||
}
|
||||
|
||||
normalized += char;
|
||||
}
|
||||
|
||||
return normalized;
|
||||
}
|
||||
|
||||
function matchesSuffix(text: string, suffixes: readonly string[]): boolean {
|
||||
return suffixes.some((suffix) => text === suffix);
|
||||
}
|
||||
|
||||
function matchesPoliteCopulaEnding(text: string): boolean {
|
||||
if (!text.startsWith('です')) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return matchesSuffix(text.slice('です'.length), SENTENCE_FINAL_PARTICLE_SUFFIXES);
|
||||
}
|
||||
|
||||
function matchesNegativeCopulaEnding(text: string): boolean {
|
||||
for (const prefix of NEGATIVE_COPULA_PREFIXES) {
|
||||
const negativeStem = `${prefix}ない`;
|
||||
if (!text.startsWith(negativeStem)) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const suffix = text.slice(negativeStem.length);
|
||||
return (
|
||||
matchesSuffix(suffix, SENTENCE_FINAL_PARTICLE_SUFFIXES) || matchesPoliteCopulaEnding(suffix)
|
||||
);
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
function matchesExplanatoryEnding(text: string): boolean {
|
||||
for (const prefix of EXPLANATORY_ENDING_PREFIXES) {
|
||||
if (EXPLANATORY_ENDING_THOUGHT_SUFFIXES.some((suffix) => text === `${prefix}${suffix}`)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (!text.startsWith(prefix)) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const suffix = text.slice(prefix.length);
|
||||
for (const core of EXPLANATORY_ENDING_CORES) {
|
||||
if (!suffix.startsWith(core)) {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (matchesSuffix(suffix.slice(core.length), EXPLANATORY_ENDING_TRAILING_PARTICLES)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
export function isStandaloneGrammarEndingText(text: string): boolean {
|
||||
const normalized = normalizeGrammarEndingText(text);
|
||||
if (!normalized) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return matchesPoliteCopulaEnding(normalized) || matchesNegativeCopulaEnding(normalized);
|
||||
}
|
||||
|
||||
export function isSubtitleGrammarEndingText(text: string): boolean {
|
||||
const normalized = normalizeGrammarEndingText(text);
|
||||
if (!normalized) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return isStandaloneGrammarEndingText(normalized) || matchesExplanatoryEnding(normalized);
|
||||
}
|
||||
@@ -39,6 +39,33 @@ test('enrichTokensWithMecabPos1 fills missing pos1 using surface-sequence fallba
|
||||
assert.equal(enriched[0]?.pos1, '助詞');
|
||||
});
|
||||
|
||||
test('enrichTokensWithMecabPos1 backfills blank pos2 and pos3 fields', () => {
|
||||
const tokens = [
|
||||
makeToken({
|
||||
surface: 'は',
|
||||
startPos: 0,
|
||||
endPos: 1,
|
||||
pos1: '助詞',
|
||||
pos2: '',
|
||||
pos3: ' ',
|
||||
}),
|
||||
];
|
||||
const mecabTokens = [
|
||||
makeToken({
|
||||
surface: 'は',
|
||||
startPos: 0,
|
||||
endPos: 1,
|
||||
pos1: '助詞',
|
||||
pos2: '係助詞',
|
||||
pos3: '一般',
|
||||
}),
|
||||
];
|
||||
|
||||
const enriched = enrichTokensWithMecabPos1(tokens, mecabTokens);
|
||||
assert.equal(enriched[0]?.pos2, '係助詞');
|
||||
assert.equal(enriched[0]?.pos3, '一般');
|
||||
});
|
||||
|
||||
test('enrichTokensWithMecabPos1 keeps partOfSpeech unchanged and only enriches POS tags', () => {
|
||||
const tokens = [makeToken({ surface: 'これは', startPos: 0, endPos: 3 })];
|
||||
const mecabTokens = [
|
||||
|
||||
@@ -120,6 +120,13 @@ function lowerBoundByIndex(candidates: IndexedMecabToken[], targetIndex: number)
|
||||
return low;
|
||||
}
|
||||
|
||||
function coalesceMissingPosField(
|
||||
current: string | undefined,
|
||||
fallback: string | undefined,
|
||||
): string | undefined {
|
||||
return typeof current === 'string' && current.trim().length > 0 ? current : fallback;
|
||||
}
|
||||
|
||||
function joinUniqueTags(values: Array<string | undefined>): string | undefined {
|
||||
const unique: string[] = [];
|
||||
for (const value of values) {
|
||||
@@ -303,7 +310,8 @@ function fillMissingPos1BySurfaceSequence(
|
||||
|
||||
let cursor = 0;
|
||||
return tokens.map((token) => {
|
||||
if (token.pos1 && token.pos1.trim().length > 0) {
|
||||
const hasCompletePosMetadata = token.pos1?.trim() && token.pos2?.trim() && token.pos3?.trim();
|
||||
if (hasCompletePosMetadata) {
|
||||
return token;
|
||||
}
|
||||
|
||||
@@ -327,9 +335,9 @@ function fillMissingPos1BySurfaceSequence(
|
||||
cursor = best.index + 1;
|
||||
return {
|
||||
...token,
|
||||
pos1: best.pos1,
|
||||
pos2: best.pos2,
|
||||
pos3: best.pos3,
|
||||
pos1: coalesceMissingPosField(token.pos1, best.pos1),
|
||||
pos2: coalesceMissingPosField(token.pos2, best.pos2),
|
||||
pos3: coalesceMissingPosField(token.pos3, best.pos3),
|
||||
};
|
||||
});
|
||||
}
|
||||
@@ -382,7 +390,7 @@ export function enrichTokensWithMecabPos1(
|
||||
const metadataByTokenIndex = new Map<number, MecabPosMetadata>();
|
||||
|
||||
for (const [index, token] of tokens.entries()) {
|
||||
if (token.pos1) {
|
||||
if (token.pos1?.trim() && token.pos2?.trim() && token.pos3?.trim()) {
|
||||
continue;
|
||||
}
|
||||
|
||||
@@ -410,9 +418,9 @@ export function enrichTokensWithMecabPos1(
|
||||
|
||||
return {
|
||||
...token,
|
||||
pos1: metadata.pos1,
|
||||
pos2: metadata.pos2,
|
||||
pos3: metadata.pos3,
|
||||
pos1: coalesceMissingPosField(token.pos1, metadata.pos1),
|
||||
pos2: coalesceMissingPosField(token.pos2, metadata.pos2),
|
||||
pos3: coalesceMissingPosField(token.pos3, metadata.pos3),
|
||||
};
|
||||
});
|
||||
|
||||
|
||||
@@ -155,7 +155,7 @@ test('prefers the longest dictionary headword across merged segments', () => {
|
||||
);
|
||||
});
|
||||
|
||||
test('keeps the first headword when later segments are standalone words', () => {
|
||||
test('splits trailing grammar endings when later segments are standalone words', () => {
|
||||
const parseResults = [
|
||||
makeParseItem('scanning-parser', [
|
||||
[
|
||||
@@ -174,10 +174,111 @@ test('keeps the first headword when later segments are standalone words', () =>
|
||||
})),
|
||||
[
|
||||
{
|
||||
surface: '猫です',
|
||||
reading: 'ねこです',
|
||||
surface: '猫',
|
||||
reading: 'ねこ',
|
||||
headword: '猫',
|
||||
},
|
||||
{
|
||||
surface: 'です',
|
||||
reading: 'です',
|
||||
headword: 'です',
|
||||
},
|
||||
],
|
||||
);
|
||||
});
|
||||
|
||||
test('keeps preceding reading when standalone grammar ending has empty reading', () => {
|
||||
const parseResults = [
|
||||
makeParseItem('scanning-parser', [
|
||||
[
|
||||
{ text: '猫', reading: 'ねこ', headword: '猫' },
|
||||
{ text: 'です', reading: '', headword: 'です' },
|
||||
],
|
||||
]),
|
||||
];
|
||||
|
||||
const tokens = selectYomitanParseTokens(parseResults, () => false, 'headword');
|
||||
assert.deepEqual(
|
||||
tokens?.map((token) => ({
|
||||
surface: token.surface,
|
||||
reading: token.reading,
|
||||
headword: token.headword,
|
||||
})),
|
||||
[
|
||||
{
|
||||
surface: '猫',
|
||||
reading: 'ねこ',
|
||||
headword: '猫',
|
||||
},
|
||||
{
|
||||
surface: 'です',
|
||||
reading: '',
|
||||
headword: 'です',
|
||||
},
|
||||
],
|
||||
);
|
||||
});
|
||||
|
||||
test('splits trailing ja-nai grammar endings from preceding content', () => {
|
||||
const parseResults = [
|
||||
makeParseItem('scanning-parser', [
|
||||
[
|
||||
{ text: 'いる', reading: 'いる', headword: 'いる' },
|
||||
{ text: 'じゃない', reading: 'じゃない', headword: 'じゃない' },
|
||||
],
|
||||
]),
|
||||
];
|
||||
|
||||
const tokens = selectYomitanParseTokens(parseResults, () => false, 'headword');
|
||||
assert.deepEqual(
|
||||
tokens?.map((token) => ({
|
||||
surface: token.surface,
|
||||
reading: token.reading,
|
||||
headword: token.headword,
|
||||
})),
|
||||
[
|
||||
{
|
||||
surface: 'いる',
|
||||
reading: 'いる',
|
||||
headword: 'いる',
|
||||
},
|
||||
{
|
||||
surface: 'じゃない',
|
||||
reading: 'じゃない',
|
||||
headword: 'じゃない',
|
||||
},
|
||||
],
|
||||
);
|
||||
});
|
||||
|
||||
test('splits trailing negative-copula grammar endings by pattern', () => {
|
||||
const parseResults = [
|
||||
makeParseItem('scanning-parser', [
|
||||
[
|
||||
{ text: '問題', reading: 'もんだい', headword: '問題' },
|
||||
{ text: 'ではないですか', reading: 'ではないですか', headword: 'ない' },
|
||||
],
|
||||
]),
|
||||
];
|
||||
|
||||
const tokens = selectYomitanParseTokens(parseResults, () => false, 'headword');
|
||||
assert.deepEqual(
|
||||
tokens?.map((token) => ({
|
||||
surface: token.surface,
|
||||
reading: token.reading,
|
||||
headword: token.headword,
|
||||
})),
|
||||
[
|
||||
{
|
||||
surface: '問題',
|
||||
reading: 'もんだい',
|
||||
headword: '問題',
|
||||
},
|
||||
{
|
||||
surface: 'ではないですか',
|
||||
reading: 'ではないですか',
|
||||
headword: 'ない',
|
||||
},
|
||||
],
|
||||
);
|
||||
});
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { MergedToken, NPlusOneMatchMode, PartOfSpeech } from '../../../types';
|
||||
import { isStandaloneGrammarEndingText } from './grammar-ending';
|
||||
|
||||
interface YomitanParseHeadword {
|
||||
term?: unknown;
|
||||
@@ -141,6 +142,15 @@ function isKanaOnlyText(text: string): boolean {
|
||||
return text.length > 0 && Array.from(text).every((char) => isKanaChar(char));
|
||||
}
|
||||
|
||||
function isStandaloneGrammarEndingSegment(segment: YomitanParseSegment): boolean {
|
||||
const surface = segment.text?.trim() ?? '';
|
||||
const headword = extractYomitanHeadword(segment).trim();
|
||||
return (
|
||||
headword.length > 0 &&
|
||||
(isStandaloneGrammarEndingText(surface) || isStandaloneGrammarEndingText(headword))
|
||||
);
|
||||
}
|
||||
|
||||
function shouldMergeKanaContinuation(
|
||||
previousToken: MergedToken | undefined,
|
||||
continuationSurface: string,
|
||||
@@ -186,20 +196,97 @@ export function mapYomitanParseResultItemToMergedTokens(
|
||||
|
||||
let combinedSurface = '';
|
||||
let combinedReading = '';
|
||||
let combinedStart = charOffset;
|
||||
let firstHeadword = '';
|
||||
const expandedHeadwords: string[] = [];
|
||||
|
||||
const pushToken = (
|
||||
surface: string,
|
||||
reading: string,
|
||||
headword: string,
|
||||
start: number,
|
||||
end: number,
|
||||
): void => {
|
||||
tokens.push({
|
||||
surface,
|
||||
reading,
|
||||
headword,
|
||||
startPos: start,
|
||||
endPos: end,
|
||||
partOfSpeech: PartOfSpeech.other,
|
||||
pos1: '',
|
||||
isMerged: true,
|
||||
isNPlusOneTarget: false,
|
||||
isKnown: (() => {
|
||||
const matchText = resolveKnownWordText(surface, headword, knownWordMatchMode);
|
||||
return matchText ? isKnownWord(matchText) : false;
|
||||
})(),
|
||||
});
|
||||
};
|
||||
|
||||
const flushCombinedToken = (end: number): void => {
|
||||
if (!combinedSurface) {
|
||||
combinedStart = end;
|
||||
return;
|
||||
}
|
||||
|
||||
const combinedHeadword = selectMergedHeadword(
|
||||
firstHeadword,
|
||||
expandedHeadwords,
|
||||
combinedSurface,
|
||||
);
|
||||
if (!combinedHeadword) {
|
||||
const previousToken = tokens[tokens.length - 1];
|
||||
if (shouldMergeKanaContinuation(previousToken, combinedSurface)) {
|
||||
previousToken.surface += combinedSurface;
|
||||
previousToken.reading += combinedReading;
|
||||
previousToken.endPos = end;
|
||||
}
|
||||
} else {
|
||||
hasDictionaryMatch = true;
|
||||
pushToken(combinedSurface, combinedReading, combinedHeadword, combinedStart, end);
|
||||
}
|
||||
|
||||
combinedSurface = '';
|
||||
combinedReading = '';
|
||||
firstHeadword = '';
|
||||
expandedHeadwords.length = 0;
|
||||
combinedStart = end;
|
||||
};
|
||||
|
||||
for (const segment of line) {
|
||||
const segmentText = segment.text;
|
||||
if (!segmentText || segmentText.length === 0) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const segmentStart = charOffset;
|
||||
const segmentEnd = segmentStart + segmentText.length;
|
||||
charOffset = segmentEnd;
|
||||
combinedSurface += segmentText;
|
||||
if (typeof segment.reading === 'string') {
|
||||
combinedReading += segment.reading;
|
||||
}
|
||||
const segmentHeadword = extractYomitanHeadword(segment);
|
||||
if (isStandaloneGrammarEndingSegment(segment)) {
|
||||
combinedSurface = combinedSurface.slice(0, -segmentText.length);
|
||||
if (typeof segment.reading === 'string' && segment.reading.length > 0) {
|
||||
combinedReading = combinedReading.slice(0, -segment.reading.length);
|
||||
}
|
||||
flushCombinedToken(segmentStart);
|
||||
const grammarHeadword = segmentHeadword || segmentText;
|
||||
hasDictionaryMatch = true;
|
||||
pushToken(
|
||||
segmentText,
|
||||
typeof segment.reading === 'string' ? segment.reading : '',
|
||||
grammarHeadword,
|
||||
segmentStart,
|
||||
segmentEnd,
|
||||
);
|
||||
combinedStart = segmentEnd;
|
||||
continue;
|
||||
}
|
||||
|
||||
if (segmentHeadword) {
|
||||
if (!firstHeadword) {
|
||||
firstHeadword = segmentHeadword;
|
||||
@@ -210,49 +297,7 @@ export function mapYomitanParseResultItemToMergedTokens(
|
||||
}
|
||||
}
|
||||
|
||||
if (!combinedSurface) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const start = charOffset;
|
||||
const end = start + combinedSurface.length;
|
||||
charOffset = end;
|
||||
const combinedHeadword = selectMergedHeadword(
|
||||
firstHeadword,
|
||||
expandedHeadwords,
|
||||
combinedSurface,
|
||||
);
|
||||
if (!combinedHeadword) {
|
||||
const previousToken = tokens[tokens.length - 1];
|
||||
if (shouldMergeKanaContinuation(previousToken, combinedSurface)) {
|
||||
previousToken.surface += combinedSurface;
|
||||
previousToken.reading += combinedReading;
|
||||
previousToken.endPos = end;
|
||||
continue;
|
||||
}
|
||||
|
||||
// No dictionary-backed headword for this merged unit; skip it entirely so
|
||||
// downstream keyboard/frequency/JLPT flows only operate on lookup-backed tokens.
|
||||
continue;
|
||||
}
|
||||
hasDictionaryMatch = true;
|
||||
const headword = combinedHeadword;
|
||||
|
||||
tokens.push({
|
||||
surface: combinedSurface,
|
||||
reading: combinedReading,
|
||||
headword,
|
||||
startPos: start,
|
||||
endPos: end,
|
||||
partOfSpeech: PartOfSpeech.other,
|
||||
pos1: '',
|
||||
isMerged: true,
|
||||
isNPlusOneTarget: false,
|
||||
isKnown: (() => {
|
||||
const matchText = resolveKnownWordText(combinedSurface, headword, knownWordMatchMode);
|
||||
return matchText ? isKnownWord(matchText) : false;
|
||||
})(),
|
||||
});
|
||||
flushCombinedToken(charOffset);
|
||||
}
|
||||
|
||||
if (validLineCount === 0 || tokens.length === 0 || !hasDictionaryMatch) {
|
||||
|
||||
@@ -8,14 +8,21 @@ import {
|
||||
} from '../../../token-pos2-exclusions';
|
||||
import { MergedToken, PartOfSpeech } from '../../../types';
|
||||
import { shouldIgnoreJlptByTerm } from '../jlpt-token-filter';
|
||||
import { isSubtitleGrammarEndingText } from './grammar-ending';
|
||||
|
||||
const KATAKANA_TO_HIRAGANA_OFFSET = 0x60;
|
||||
const KATAKANA_CODEPOINT_START = 0x30a1;
|
||||
const KATAKANA_CODEPOINT_END = 0x30f6;
|
||||
|
||||
const STANDALONE_GRAMMAR_PARTICLE_PHRASES = ['たって', 'だって'] as const;
|
||||
const STANDALONE_GRAMMAR_PARTICLE_PHRASES_SET: ReadonlySet<string> = new Set(
|
||||
STANDALONE_GRAMMAR_PARTICLE_PHRASES,
|
||||
);
|
||||
|
||||
export const SUBTITLE_ANNOTATION_EXCLUDED_TERMS = new Set([
|
||||
'あ',
|
||||
'ああ',
|
||||
'ある',
|
||||
'あなた',
|
||||
'あんた',
|
||||
'ええ',
|
||||
@@ -25,6 +32,7 @@ export const SUBTITLE_ANNOTATION_EXCLUDED_TERMS = new Set([
|
||||
'お前',
|
||||
'こいつ',
|
||||
'こっち',
|
||||
'くれ',
|
||||
'じゃない',
|
||||
'そうだ',
|
||||
'たち',
|
||||
@@ -32,58 +40,27 @@ export const SUBTITLE_ANNOTATION_EXCLUDED_TERMS = new Set([
|
||||
'どこか',
|
||||
'なんか',
|
||||
'べき',
|
||||
'って',
|
||||
'はあ',
|
||||
'はぁ',
|
||||
'はは',
|
||||
'へえ',
|
||||
'ふう',
|
||||
'ほう',
|
||||
'やはり',
|
||||
'って',
|
||||
'何か',
|
||||
'何だ',
|
||||
'何も',
|
||||
'如何した',
|
||||
'有る',
|
||||
'在る',
|
||||
'様',
|
||||
'確かに',
|
||||
'誰も',
|
||||
'貴方',
|
||||
'もんか',
|
||||
'ものか',
|
||||
]);
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_PREFIXES = ['ん', 'の', 'なん', 'なの'];
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_CORES = [
|
||||
'だ',
|
||||
'です',
|
||||
'でした',
|
||||
'だった',
|
||||
'では',
|
||||
'じゃ',
|
||||
'でしょう',
|
||||
'だろう',
|
||||
] as const;
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_TRAILING_PARTICLES = [
|
||||
'',
|
||||
'か',
|
||||
'ね',
|
||||
'よ',
|
||||
'な',
|
||||
'けど',
|
||||
'よね',
|
||||
'かな',
|
||||
'かね',
|
||||
] as const;
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_THOUGHT_SUFFIXES = [
|
||||
'か',
|
||||
'かな',
|
||||
'かね',
|
||||
] as const;
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDINGS = new Set(
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_PREFIXES.flatMap((prefix) =>
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_CORES.flatMap((core) =>
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_TRAILING_PARTICLES.map(
|
||||
(particle) => `${prefix}${core}${particle}`,
|
||||
),
|
||||
),
|
||||
),
|
||||
);
|
||||
const SUBTITLE_ANNOTATION_EXCLUDED_TRAILING_PARTICLE_SUFFIXES = new Set([
|
||||
'って',
|
||||
'ってよ',
|
||||
@@ -95,7 +72,28 @@ const SUBTITLE_ANNOTATION_EXCLUDED_TRAILING_PARTICLE_SUFFIXES = new Set([
|
||||
]);
|
||||
const AUXILIARY_STEM_GRAMMAR_TAIL_POS1 = new Set(['名詞', '助動詞', '助詞']);
|
||||
const NON_INDEPENDENT_NOUN_HELPER_TAIL_POS1 = new Set(['助詞', '助動詞']);
|
||||
|
||||
const AUXILIARY_INFLECTION_TRAILING_POS1 = new Set(['助動詞']);
|
||||
const AUXILIARY_HELPER_SPAN_POS1 = new Set(['助詞', '助動詞', '動詞']);
|
||||
const LEXICAL_VERB_POS2 = new Set(['自立']);
|
||||
const STANDALONE_GRAMMAR_PARTICLE_SURFACES = new Set([
|
||||
'か',
|
||||
'が',
|
||||
'さ',
|
||||
'し',
|
||||
'ぞ',
|
||||
'ぜ',
|
||||
'と',
|
||||
'な',
|
||||
'に',
|
||||
'ね',
|
||||
'の',
|
||||
'は',
|
||||
'へ',
|
||||
'も',
|
||||
'や',
|
||||
'よ',
|
||||
'を',
|
||||
]);
|
||||
export interface SubtitleAnnotationFilterOptions {
|
||||
pos1Exclusions?: ReadonlySet<string>;
|
||||
pos2Exclusions?: ReadonlySet<string>;
|
||||
@@ -301,6 +299,99 @@ function isKanaOnlyNonIndependentNounHelperMerge(token: MergedToken): boolean {
|
||||
return pos1Parts.slice(1).every((part) => NON_INDEPENDENT_NOUN_HELPER_TAIL_POS1.has(part));
|
||||
}
|
||||
|
||||
function isKanaOnlyText(text: string): boolean {
|
||||
const normalized = normalizeKana(text);
|
||||
return normalized.length > 0 && [...normalized].every(isKanaChar);
|
||||
}
|
||||
|
||||
function isLexicalKureruVerb(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeKana(token.surface);
|
||||
const normalizedHeadword = normalizeKana(token.headword);
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePosTag(token.pos1));
|
||||
const pos2Parts = splitNormalizedTagParts(normalizePosTag(token.pos2));
|
||||
return (
|
||||
normalizedSurface === 'くれ' &&
|
||||
normalizedHeadword === 'くれる' &&
|
||||
pos1Parts.length === 1 &&
|
||||
pos1Parts[0] === '動詞' &&
|
||||
pos2Parts.length === 1 &&
|
||||
pos2Parts[0] === '自立'
|
||||
);
|
||||
}
|
||||
|
||||
function isStandaloneAuxiliaryInflectionFragment(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeKana(token.surface);
|
||||
if (!isKanaOnlyText(normalizedSurface)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePosTag(token.pos1));
|
||||
if (pos1Parts.length === 0) {
|
||||
return false;
|
||||
}
|
||||
|
||||
if (pos1Parts.every((part) => part === '助動詞')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
const pos2Parts = splitNormalizedTagParts(normalizePosTag(token.pos2));
|
||||
return (
|
||||
pos1Parts[0] === '動詞' &&
|
||||
pos2Parts[0] === '接尾' &&
|
||||
pos1Parts.slice(1).every((part) => AUXILIARY_INFLECTION_TRAILING_POS1.has(part))
|
||||
);
|
||||
}
|
||||
|
||||
function isAuxiliaryOnlyHelperSpan(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeKana(token.surface);
|
||||
const normalizedHeadword = normalizeKana(token.headword);
|
||||
if (!isKanaOnlyText(normalizedSurface) || !isKanaOnlyText(normalizedHeadword)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePosTag(token.pos1));
|
||||
if (
|
||||
pos1Parts.length === 0 ||
|
||||
!pos1Parts.every((part) => AUXILIARY_HELPER_SPAN_POS1.has(part)) ||
|
||||
!pos1Parts.includes('助詞') ||
|
||||
!pos1Parts.includes('動詞')
|
||||
) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos2Parts = splitNormalizedTagParts(normalizePosTag(token.pos2));
|
||||
return !pos2Parts.some((part) => LEXICAL_VERB_POS2.has(part));
|
||||
}
|
||||
|
||||
function isStandaloneSuruTeGrammarHelper(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeKana(token.surface);
|
||||
const normalizedHeadword = normalizeKana(token.headword);
|
||||
if (!normalizedSurface.startsWith('して') || normalizedHeadword !== 'する') {
|
||||
return false;
|
||||
}
|
||||
|
||||
const pos1Parts = splitNormalizedTagParts(normalizePosTag(token.pos1));
|
||||
return (
|
||||
isKanaOnlyText(normalizedSurface) && (pos1Parts.length === 0 || pos1Parts.includes('動詞'))
|
||||
);
|
||||
}
|
||||
|
||||
function isStandaloneGrammarParticle(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeKana(token.surface);
|
||||
const normalizedHeadword = normalizeKana(token.headword);
|
||||
return (
|
||||
normalizedSurface === normalizedHeadword &&
|
||||
(STANDALONE_GRAMMAR_PARTICLE_SURFACES.has(normalizedSurface) ||
|
||||
STANDALONE_GRAMMAR_PARTICLE_PHRASES_SET.has(normalizedSurface))
|
||||
);
|
||||
}
|
||||
|
||||
function isSingleKanaSurfaceFragment(token: MergedToken): boolean {
|
||||
const normalizedSurface = normalizeKana(token.surface);
|
||||
const chars = [...normalizedSurface];
|
||||
return chars.length === 1 && chars.every(isKanaChar);
|
||||
}
|
||||
|
||||
function isExcludedByTerm(token: MergedToken): boolean {
|
||||
const candidates = [token.surface, token.reading, token.headword].filter(
|
||||
(candidate): candidate is string => typeof candidate === 'string' && candidate.length > 0,
|
||||
@@ -317,21 +408,11 @@ function isExcludedByTerm(token: MergedToken): boolean {
|
||||
continue;
|
||||
}
|
||||
|
||||
if (
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_PREFIXES.some((prefix) =>
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDING_THOUGHT_SUFFIXES.some(
|
||||
(suffix) => normalized === `${prefix}${suffix}`,
|
||||
),
|
||||
)
|
||||
) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_TERMS.has(trimmed) ||
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_TERMS.has(normalized) ||
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDINGS.has(trimmed) ||
|
||||
SUBTITLE_ANNOTATION_EXCLUDED_EXPLANATORY_ENDINGS.has(normalized) ||
|
||||
isSubtitleGrammarEndingText(trimmed) ||
|
||||
isSubtitleGrammarEndingText(normalized) ||
|
||||
shouldIgnoreJlptByTerm(trimmed) ||
|
||||
shouldIgnoreJlptByTerm(normalized)
|
||||
) {
|
||||
@@ -388,10 +469,34 @@ export function shouldExcludeTokenFromSubtitleAnnotations(
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isStandaloneAuxiliaryInflectionFragment(token)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isAuxiliaryOnlyHelperSpan(token)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isStandaloneSuruTeGrammarHelper(token)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isStandaloneGrammarParticle(token)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isSingleKanaSurfaceFragment(token)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isExcludedTrailingParticleMergedToken(token)) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (isLexicalKureruVerb(token)) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return isExcludedByTerm(token);
|
||||
}
|
||||
|
||||
@@ -405,7 +510,6 @@ export function stripSubtitleAnnotationMetadata(
|
||||
|
||||
return {
|
||||
...token,
|
||||
isKnown: false,
|
||||
isNPlusOneTarget: false,
|
||||
isNameMatch: false,
|
||||
jlptLevel: undefined,
|
||||
|
||||
@@ -533,7 +533,7 @@ test('requestYomitanTermFrequencies caches repeated term+reading lookups', async
|
||||
assert.equal(frequencyCalls, 1);
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens uses left-to-right termsFind scanning instead of parseText', async () => {
|
||||
test('requestYomitanScanTokens prefers parseText tokenization over termsFind fragments', async () => {
|
||||
const scripts: string[] = [];
|
||||
const deps = createDeps(async (script) => {
|
||||
scripts.push(script);
|
||||
@@ -549,6 +549,138 @@ test('requestYomitanScanTokens uses left-to-right termsFind scanning instead of
|
||||
],
|
||||
};
|
||||
}
|
||||
if (script.includes('parseText')) {
|
||||
return [
|
||||
{
|
||||
source: 'scanning-parser',
|
||||
index: 0,
|
||||
content: [
|
||||
[
|
||||
{
|
||||
text: '取り組んで',
|
||||
reading: 'とりくんで',
|
||||
headwords: [[{ term: '取り組む' }]],
|
||||
},
|
||||
],
|
||||
],
|
||||
},
|
||||
];
|
||||
}
|
||||
return [
|
||||
{
|
||||
surface: '取り',
|
||||
reading: 'とり',
|
||||
headword: '取る',
|
||||
startPos: 0,
|
||||
endPos: 2,
|
||||
},
|
||||
{
|
||||
surface: '組んで',
|
||||
reading: 'くんで',
|
||||
headword: '組む',
|
||||
startPos: 2,
|
||||
endPos: 5,
|
||||
},
|
||||
];
|
||||
});
|
||||
|
||||
const result = await requestYomitanScanTokens('取り組んで', deps, {
|
||||
error: () => undefined,
|
||||
});
|
||||
|
||||
assert.deepEqual(result, [
|
||||
{
|
||||
surface: '取り組んで',
|
||||
reading: 'とりくんで',
|
||||
headword: '取り組む',
|
||||
startPos: 0,
|
||||
endPos: 5,
|
||||
},
|
||||
]);
|
||||
assert.ok(scripts.some((script) => script.includes('parseText')));
|
||||
assert.ok(scripts.some((script) => script.includes('termsFind')));
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens keeps scanner metadata when parse spans agree', async () => {
|
||||
const deps = createDeps(async (script) => {
|
||||
if (script.includes('optionsGetFull')) {
|
||||
return {
|
||||
profileCurrent: 0,
|
||||
profiles: [
|
||||
{
|
||||
options: {
|
||||
scanning: { length: 40 },
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
if (script.includes('parseText')) {
|
||||
return [
|
||||
{
|
||||
source: 'scanning-parser',
|
||||
index: 0,
|
||||
content: [
|
||||
[
|
||||
{
|
||||
text: 'アクア',
|
||||
reading: 'あくあ',
|
||||
headwords: [[{ term: 'アクア' }]],
|
||||
},
|
||||
],
|
||||
],
|
||||
},
|
||||
];
|
||||
}
|
||||
return [
|
||||
{
|
||||
surface: 'アクア',
|
||||
reading: 'あくあ',
|
||||
headword: 'アクア',
|
||||
startPos: 0,
|
||||
endPos: 3,
|
||||
isNameMatch: true,
|
||||
wordClasses: ['n'],
|
||||
},
|
||||
];
|
||||
});
|
||||
|
||||
const result = await requestYomitanScanTokens('アクア', deps, {
|
||||
error: () => undefined,
|
||||
});
|
||||
|
||||
assert.deepEqual(result, [
|
||||
{
|
||||
surface: 'アクア',
|
||||
reading: 'あくあ',
|
||||
headword: 'アクア',
|
||||
startPos: 0,
|
||||
endPos: 3,
|
||||
isNameMatch: true,
|
||||
wordClasses: ['n'],
|
||||
},
|
||||
]);
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens falls back to left-to-right termsFind scanning', async () => {
|
||||
const scripts: string[] = [];
|
||||
const deps = createDeps(async (script) => {
|
||||
scripts.push(script);
|
||||
if (script.includes('optionsGetFull')) {
|
||||
return {
|
||||
profileCurrent: 0,
|
||||
profiles: [
|
||||
{
|
||||
options: {
|
||||
scanning: { length: 40 },
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
if (script.includes('parseText')) {
|
||||
return [];
|
||||
}
|
||||
return [
|
||||
{
|
||||
surface: 'カズマ',
|
||||
@@ -573,6 +705,7 @@ test('requestYomitanScanTokens uses left-to-right termsFind scanning instead of
|
||||
endPos: 3,
|
||||
},
|
||||
]);
|
||||
assert.ok(scripts.some((script) => script.includes('parseText')));
|
||||
const scannerScript = scripts.find((script) => script.includes('termsFind'));
|
||||
assert.ok(scannerScript, 'expected termsFind scanning request script');
|
||||
assert.doesNotMatch(scannerScript ?? '', /parseText/);
|
||||
@@ -891,6 +1024,105 @@ test('requestYomitanScanTokens can use frequency from later exact secondary-matc
|
||||
]);
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens uses exact frequency entry when selected reading differs', async () => {
|
||||
let scannerScript = '';
|
||||
const deps = createDeps(async (script) => {
|
||||
if (script.includes('termsFind')) {
|
||||
scannerScript = script;
|
||||
return [];
|
||||
}
|
||||
if (script.includes('optionsGetFull')) {
|
||||
return {
|
||||
profileCurrent: 0,
|
||||
profileIndex: 0,
|
||||
scanLength: 40,
|
||||
dictionaries: ['JPDBv2㋕', 'Jiten', 'CC100'],
|
||||
dictionaryPriorityByName: {
|
||||
'JPDBv2㋕': 0,
|
||||
Jiten: 1,
|
||||
CC100: 2,
|
||||
},
|
||||
dictionaryFrequencyModeByName: {
|
||||
'JPDBv2㋕': 'rank-based',
|
||||
Jiten: 'rank-based',
|
||||
CC100: 'rank-based',
|
||||
},
|
||||
profiles: [
|
||||
{
|
||||
options: {
|
||||
scanning: { length: 40 },
|
||||
dictionaries: [
|
||||
{ name: 'JPDBv2㋕', enabled: true, id: 0 },
|
||||
{ name: 'Jiten', enabled: true, id: 1 },
|
||||
{ name: 'CC100', enabled: true, id: 2 },
|
||||
],
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
return null;
|
||||
});
|
||||
|
||||
await requestYomitanScanTokens('第二走者', deps, {
|
||||
error: () => undefined,
|
||||
});
|
||||
|
||||
const result = (await runInjectedYomitanScript(scannerScript, (action, params) => {
|
||||
if (action !== 'termsFind') {
|
||||
throw new Error(`unexpected action: ${action}`);
|
||||
}
|
||||
|
||||
const text = (params as { text?: string } | undefined)?.text ?? '';
|
||||
if (!text.startsWith('第二')) {
|
||||
return { originalTextLength: 0, dictionaryEntries: [] };
|
||||
}
|
||||
|
||||
return {
|
||||
originalTextLength: 2,
|
||||
dictionaryEntries: [
|
||||
{
|
||||
headwords: [
|
||||
{
|
||||
term: '第二',
|
||||
reading: 'だいに',
|
||||
sources: [{ originalText: '第二', isPrimary: true, matchType: 'exact' }],
|
||||
},
|
||||
],
|
||||
frequencies: [],
|
||||
},
|
||||
{
|
||||
headwords: [
|
||||
{
|
||||
term: '第二',
|
||||
reading: '',
|
||||
sources: [{ originalText: '第二', isPrimary: false, matchType: 'exact' }],
|
||||
},
|
||||
],
|
||||
frequencies: [
|
||||
{
|
||||
headwordIndex: 0,
|
||||
dictionary: 'JPDBv2㋕',
|
||||
frequency: 189513,
|
||||
displayValue: '1820,189513句',
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
})) as Array<Record<string, unknown>>;
|
||||
|
||||
assert.deepEqual(result?.[0], {
|
||||
surface: '第二',
|
||||
reading: 'だいに',
|
||||
headword: '第二',
|
||||
startPos: 0,
|
||||
endPos: 2,
|
||||
isNameMatch: false,
|
||||
frequencyRank: 1820,
|
||||
});
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens marks tokens backed by SubMiner character dictionary entries', async () => {
|
||||
const deps = createDeps(async (script) => {
|
||||
if (script.includes('optionsGetFull')) {
|
||||
@@ -1049,6 +1281,60 @@ test('requestYomitanScanTokens marks grouped entries when SubMiner dictionary al
|
||||
assert.equal((result as Array<{ isNameMatch?: boolean }>)[0]?.isNameMatch, true);
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens preserves matched headword word classes', async () => {
|
||||
let scannerScript = '';
|
||||
const deps = createDeps(async (script) => {
|
||||
if (script.includes('termsFind')) {
|
||||
scannerScript = script;
|
||||
return [];
|
||||
}
|
||||
if (script.includes('optionsGetFull')) {
|
||||
return {
|
||||
profileCurrent: 0,
|
||||
profiles: [
|
||||
{
|
||||
options: {
|
||||
scanning: { length: 40 },
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
return null;
|
||||
});
|
||||
|
||||
await requestYomitanScanTokens('は', deps, { error: () => undefined });
|
||||
|
||||
const result = await runInjectedYomitanScript(scannerScript, (action, params) => {
|
||||
if (action !== 'termsFind') {
|
||||
throw new Error(`unexpected action: ${action}`);
|
||||
}
|
||||
|
||||
const text = (params as { text?: string } | undefined)?.text;
|
||||
if (text !== 'は') {
|
||||
return { originalTextLength: 0, dictionaryEntries: [] };
|
||||
}
|
||||
|
||||
return {
|
||||
originalTextLength: 1,
|
||||
dictionaryEntries: [
|
||||
{
|
||||
headwords: [
|
||||
{
|
||||
term: 'は',
|
||||
reading: 'は',
|
||||
wordClasses: ['prt'],
|
||||
sources: [{ originalText: 'は', isPrimary: true, matchType: 'exact' }],
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
});
|
||||
|
||||
assert.deepEqual((result as Array<{ wordClasses?: string[] }>)[0]?.wordClasses, ['prt']);
|
||||
});
|
||||
|
||||
test('requestYomitanScanTokens skips fallback fragments without exact primary source matches', async () => {
|
||||
const deps = createDeps(async (script) => {
|
||||
if (script.includes('optionsGetFull')) {
|
||||
|
||||
@@ -53,6 +53,7 @@ export interface YomitanScanToken {
|
||||
endPos: number;
|
||||
isNameMatch?: boolean;
|
||||
frequencyRank?: number;
|
||||
wordClasses?: string[];
|
||||
}
|
||||
|
||||
interface YomitanProfileMetadata {
|
||||
@@ -91,11 +92,30 @@ function isScanTokenArray(value: unknown): value is YomitanScanToken[] {
|
||||
typeof entry.startPos === 'number' &&
|
||||
typeof entry.endPos === 'number' &&
|
||||
(entry.isNameMatch === undefined || typeof entry.isNameMatch === 'boolean') &&
|
||||
(entry.frequencyRank === undefined || typeof entry.frequencyRank === 'number'),
|
||||
(entry.frequencyRank === undefined || typeof entry.frequencyRank === 'number') &&
|
||||
(entry.wordClasses === undefined ||
|
||||
(Array.isArray(entry.wordClasses) &&
|
||||
entry.wordClasses.every((wordClass) => typeof wordClass === 'string'))),
|
||||
)
|
||||
);
|
||||
}
|
||||
|
||||
function hasSameTokenSpans(left: YomitanScanToken[], right: YomitanScanToken[]): boolean {
|
||||
if (left.length !== right.length) {
|
||||
return false;
|
||||
}
|
||||
|
||||
return left.every((token, index) => {
|
||||
const other = right[index];
|
||||
return (
|
||||
other !== undefined &&
|
||||
token.surface === other.surface &&
|
||||
token.startPos === other.startPos &&
|
||||
token.endPos === other.endPos
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
function makeTermReadingCacheKey(term: string, reading: string | null): string {
|
||||
return `${term}\u0000${reading ?? ''}`;
|
||||
}
|
||||
@@ -956,6 +976,9 @@ const YOMITAN_SCANNING_HELPERS = String.raw`
|
||||
const matchReading = typeof match.headword?.reading === 'string' ? match.headword.reading : '';
|
||||
const preferredReading =
|
||||
typeof preferredMatch.headword?.reading === 'string' ? preferredMatch.headword.reading : '';
|
||||
if (!matchReading || !preferredReading) {
|
||||
return true;
|
||||
}
|
||||
return matchReading === preferredReading;
|
||||
}
|
||||
function getBestFrequencyRankForMatches(matches, dictionaryPriorityByName, dictionaryFrequencyModeByName) {
|
||||
@@ -975,6 +998,11 @@ const YOMITAN_SCANNING_HELPERS = String.raw`
|
||||
return best;
|
||||
}
|
||||
function getPreferredHeadword(dictionaryEntries, token, dictionaryPriorityByName, dictionaryFrequencyModeByName) {
|
||||
function normalizeWordClasses(headword) {
|
||||
if (!Array.isArray(headword?.wordClasses)) { return undefined; }
|
||||
const classes = headword.wordClasses.filter((wordClass) => typeof wordClass === "string" && wordClass.trim().length > 0);
|
||||
return classes.length > 0 ? classes : undefined;
|
||||
}
|
||||
function appendDictionaryNames(target, value) {
|
||||
if (!value || typeof value !== 'object') {
|
||||
return;
|
||||
@@ -1033,6 +1061,7 @@ const YOMITAN_SCANNING_HELPERS = String.raw`
|
||||
return {
|
||||
term: preferredMatch.headword.term,
|
||||
reading: preferredMatch.headword.reading,
|
||||
wordClasses: normalizeWordClasses(preferredMatch.headword),
|
||||
isNameMatch: matchedNameDictionary || isNameDictionaryEntry(preferredMatch.dictionaryEntry),
|
||||
frequencyRank: getBestFrequencyRankForMatches(
|
||||
exactFrequencyMatches.length > 0 ? exactFrequencyMatches : exactPrimaryMatches,
|
||||
@@ -1099,7 +1128,7 @@ ${YOMITAN_SCANNING_HELPERS}
|
||||
if (preferredHeadword && typeof preferredHeadword.term === "string") {
|
||||
const reading = typeof preferredHeadword.reading === "string" ? preferredHeadword.reading : "";
|
||||
const segments = distributeFuriganaInflected(preferredHeadword.term, reading, source);
|
||||
tokens.push({
|
||||
const tokenPayload = {
|
||||
surface: segments.map((segment) => segment.text).join("") || source,
|
||||
reading: segments.map((segment) => typeof segment.reading === "string" ? segment.reading : "").join(""),
|
||||
headword: preferredHeadword.term,
|
||||
@@ -1110,7 +1139,11 @@ ${YOMITAN_SCANNING_HELPERS}
|
||||
typeof preferredHeadword.frequencyRank === "number" && Number.isFinite(preferredHeadword.frequencyRank)
|
||||
? Math.max(1, Math.floor(preferredHeadword.frequencyRank))
|
||||
: undefined,
|
||||
});
|
||||
};
|
||||
if (Array.isArray(preferredHeadword.wordClasses) && preferredHeadword.wordClasses.length > 0) {
|
||||
tokenPayload.wordClasses = preferredHeadword.wordClasses;
|
||||
}
|
||||
tokens.push(tokenPayload);
|
||||
i += originalTextLength;
|
||||
continue;
|
||||
}
|
||||
@@ -1235,6 +1268,17 @@ export async function requestYomitanScanTokens(
|
||||
return null;
|
||||
}
|
||||
|
||||
const parseResults = await requestYomitanParseResults(text, deps, logger);
|
||||
const selectedParseTokens = selectYomitanParseTokens(parseResults, () => false, 'headword');
|
||||
const parseScanTokens =
|
||||
selectedParseTokens?.map((token) => ({
|
||||
surface: token.surface,
|
||||
reading: token.reading,
|
||||
headword: token.headword,
|
||||
startPos: token.startPos,
|
||||
endPos: token.endPos,
|
||||
})) ?? null;
|
||||
|
||||
const metadata = await requestYomitanProfileMetadata(parserWindow, logger);
|
||||
const profileIndex = metadata?.profileIndex ?? 0;
|
||||
const scanLength = metadata?.scanLength ?? DEFAULT_YOMITAN_SCAN_LENGTH;
|
||||
@@ -1252,6 +1296,9 @@ export async function requestYomitanScanTokens(
|
||||
true,
|
||||
);
|
||||
if (isScanTokenArray(rawResult)) {
|
||||
if (parseScanTokens && parseScanTokens.length > 0) {
|
||||
return hasSameTokenSpans(parseScanTokens, rawResult) ? rawResult : parseScanTokens;
|
||||
}
|
||||
return rawResult;
|
||||
}
|
||||
if (Array.isArray(rawResult)) {
|
||||
@@ -1266,8 +1313,14 @@ export async function requestYomitanScanTokens(
|
||||
})) ?? null
|
||||
);
|
||||
}
|
||||
if (parseScanTokens && parseScanTokens.length > 0) {
|
||||
return parseScanTokens;
|
||||
}
|
||||
return null;
|
||||
} catch (err) {
|
||||
if (parseScanTokens && parseScanTokens.length > 0) {
|
||||
return parseScanTokens;
|
||||
}
|
||||
logger.error('Yomitan scanner request failed:', (err as Error).message);
|
||||
return null;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user