Restore multi-copy digit capture and add AniList selection (#56)

This commit is contained in:
2026-04-25 21:44:55 -07:00
committed by GitHub
parent 7ac51cd5e9
commit d8934647a9
140 changed files with 4097 additions and 326 deletions
+219
View File
@@ -4069,6 +4069,225 @@ test('tokenizeSubtitle clears all annotations for explanatory contrast endings',
);
});
test('tokenizeSubtitle clears annotations for ことに while preserving lexical N+1 target', async () => {
const result = await tokenizeSubtitle(
'さっきの俺と違うことに気付かないのかい?',
makeDepsFromYomitanTokens(
[
{ surface: 'さっき', reading: 'さっき', headword: 'さっき' },
{ surface: 'の', reading: 'の', headword: 'の' },
{ surface: '俺', reading: 'おれ', headword: '俺' },
{ surface: 'と', reading: 'と', headword: 'と' },
{ surface: '違う', reading: 'ちがう', headword: '違う' },
{ surface: 'ことに', reading: 'ことに', headword: '事' },
{ surface: '気付かない', reading: 'きづかない', headword: '気付く' },
{ surface: 'の', reading: 'の', headword: 'の' },
{ surface: 'かい', reading: 'かい', headword: 'かい' },
{ surface: '', reading: '', headword: '' },
],
{
getFrequencyDictionaryEnabled: () => true,
getFrequencyRank: (text) =>
text === '違う' ? 900 : text === '事' ? 81 : text === '気付く' ? 1500 : null,
getJlptLevel: (text) =>
text === '違う' ? 'N4' : text === '事' ? 'N4' : text === '気付く' ? 'N3' : null,
isKnownWord: (text) => ['さっき', 'の', '俺', 'と', '気付く', 'かい', ''].includes(text),
getMinSentenceWordsForNPlusOne: () => 1,
tokenizeWithMecab: async () => [
{
headword: 'さっき',
surface: 'さっき',
reading: 'サッキ',
startPos: 0,
endPos: 3,
partOfSpeech: PartOfSpeech.noun,
pos1: '名詞',
pos2: '副詞可能',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: 'の',
surface: 'の',
reading: '',
startPos: 3,
endPos: 4,
partOfSpeech: PartOfSpeech.particle,
pos1: '助詞',
pos2: '連体化',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: '俺',
surface: '俺',
reading: 'オレ',
startPos: 4,
endPos: 5,
partOfSpeech: PartOfSpeech.noun,
pos1: '名詞',
pos2: '代名詞',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: 'と',
surface: 'と',
reading: 'ト',
startPos: 5,
endPos: 6,
partOfSpeech: PartOfSpeech.particle,
pos1: '助詞',
pos2: '格助詞',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: '違う',
surface: '違う',
reading: 'チガウ',
startPos: 6,
endPos: 8,
partOfSpeech: PartOfSpeech.verb,
pos1: '動詞',
pos2: '自立',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: '事',
surface: 'こと',
reading: 'コト',
startPos: 8,
endPos: 10,
partOfSpeech: PartOfSpeech.noun,
pos1: '名詞',
pos2: '非自立',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: 'に',
surface: 'に',
reading: 'ニ',
startPos: 10,
endPos: 11,
partOfSpeech: PartOfSpeech.particle,
pos1: '助詞',
pos2: '格助詞',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: '気付く',
surface: '気付か',
reading: 'キヅカ',
startPos: 11,
endPos: 14,
partOfSpeech: PartOfSpeech.verb,
pos1: '動詞',
pos2: '自立',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: 'ない',
surface: 'ない',
reading: 'ナイ',
startPos: 14,
endPos: 16,
partOfSpeech: PartOfSpeech.bound_auxiliary,
pos1: '助動詞',
pos2: '*',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: 'の',
surface: 'の',
reading: '',
startPos: 16,
endPos: 17,
partOfSpeech: PartOfSpeech.particle,
pos1: '助詞',
pos2: '終助詞',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: 'かい',
surface: 'かい',
reading: 'カイ',
startPos: 17,
endPos: 19,
partOfSpeech: PartOfSpeech.particle,
pos1: '助詞',
pos2: '終助詞',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
{
headword: '',
surface: '',
reading: '',
startPos: 19,
endPos: 20,
partOfSpeech: PartOfSpeech.symbol,
pos1: '記号',
pos2: '一般',
isMerged: false,
isKnown: false,
isNPlusOneTarget: false,
},
],
},
),
);
const tokenSummary = result.tokens?.map((token) => ({
surface: token.surface,
headword: token.headword,
isKnown: token.isKnown,
isNPlusOneTarget: token.isNPlusOneTarget,
frequencyRank: token.frequencyRank,
jlptLevel: token.jlptLevel,
}));
assert.deepEqual(
tokenSummary?.find((token) => token.surface === 'ことに'),
{
surface: 'ことに',
headword: '事',
isKnown: false,
isNPlusOneTarget: false,
frequencyRank: undefined,
jlptLevel: undefined,
},
);
assert.deepEqual(
tokenSummary?.find((token) => token.surface === '違う'),
{
surface: '違う',
headword: '違う',
isKnown: false,
isNPlusOneTarget: true,
frequencyRank: 900,
jlptLevel: 'N4',
},
);
});
test('tokenizeSubtitle excludes default non-independent pos2 from N+1 when JLPT/frequency are disabled', async () => {
let mecabCalls = 0;
const result = await tokenizeSubtitle(