onedeuxtriseigo.nullpo.dev
Pop-up dictionary browser extension for language learning. Successor to Yomichan. (PERSONAL FORK)
1/*
2 * Copyright (C) 2023-2025 Yomitan Authors
3 * Copyright (C) 2021-2022 Yomichan Authors
4 *
5 * This program is free software: you can redistribute it and/or modify
6 * it under the terms of the GNU General Public License as published by
7 * the Free Software Foundation, either version 3 of the License, or
8 * (at your option) any later version.
9 *
10 * This program is distributed in the hope that it will be useful,
11 * but WITHOUT ANY WARRANTY; without even the implied warranty of
12 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 * GNU General Public License for more details.
14 *
15 * You should have received a copy of the GNU General Public License
16 * along with this program. If not, see <https://www.gnu.org/licenses/>.
17 */
18
19import type * as DictionaryData from './dictionary-data';
20
21// Common
22
23/**
24 * A generic dictionary entry which is used as the base interface.
25 */
26export type DictionaryEntry = KanjiDictionaryEntry | TermDictionaryEntry;
27
28export type DictionaryEntryType = DictionaryEntry['type'];
29
30/**
31 * A tag represents some brief information about part of a dictionary entry.
32 */
33export type Tag = {
34 /**
35 * The name of the tag.
36 */
37 name: string;
38 /**
39 * The category of the tag.
40 */
41 category: string;
42 /**
43 * A number indicating the sorting order of the tag.
44 */
45 order: number;
46 /**
47 * A score value for the tag.
48 */
49 score: number;
50 /**
51 * An array of descriptions for the tag. * If there are multiple entries,
52 * the values will typically have originated from different dictionaries.
53 * However, there is no correlation between the length of this array and
54 * the length of the `dictionaries` field, as duplicates are removed.
55 */
56 content: string[];
57 /**
58 * An array of dictionary names that contained a tag with this name and category.
59 */
60 dictionaries: string[];
61 /**
62 * Whether or not this tag is redundant with previous tags.
63 */
64 redundant: boolean;
65};
66
67// Kanji
68
69/**
70 * A dictionary entry for a kanji character.
71 */
72export type KanjiDictionaryEntry = {
73 /**
74 * The type of the entry.
75 */
76 type: 'kanji';
77 /**
78 * The kanji character that was looked up.
79 */
80 character: string;
81 /**
82 * The name of the dictionary that the information originated from.
83 */
84 dictionary: string;
85 /**
86 * The index of the dictionary in the original list of dictionaries used for the lookup.
87 */
88 dictionaryIndex: number;
89 /**
90 * The alias of the dictionary
91 */
92 dictionaryAlias: string;
93 /**
94 * Onyomi readings for the kanji character.
95 */
96 onyomi: string[];
97 /**
98 * Kunyomi readings for the kanji character.
99 */
100 kunyomi: string[];
101 /**
102 * Tags for the kanji character.
103 */
104 tags: Tag[];
105 /**
106 * An object containing stats about the kanji character.
107 */
108 stats: KanjiStatGroups;
109 /**
110 * Definitions for the kanji character.
111 */
112 definitions: string[];
113 /**
114 * Frequency information for the kanji character.
115 */
116 frequencies: KanjiFrequency[];
117};
118
119/**
120 * An object with groups of stats about a kanji character.
121 */
122export type KanjiStatGroups = {
123 /**
124 * A group of stats.
125 * @param propName The name of the group.
126 */
127 [propName: string]: KanjiStat[];
128};
129
130/**
131 * A stat represents a generic piece of information about a kanji character.
132 */
133export type KanjiStat = {
134 /**
135 * The name of the stat.
136 */
137 name: string;
138 /**
139 * The category of the stat.
140 */
141 category: string;
142 /**
143 * A description of the stat.
144 */
145 content: string;
146 /**
147 * A number indicating the sorting order of the stat.
148 */
149 order: number;
150 /**
151 * A score value for the stat.
152 */
153 score: number;
154 /**
155 * The name of the dictionary that the stat originated from.
156 */
157 dictionary: string;
158 /**
159 * A value for the stat.
160 */
161 value: number | string;
162};
163
164/**
165 * Frequency information corresponds to how frequently a character appears in a corpus,
166 * which can be a number of occurrences or an overall rank.
167 */
168export type KanjiFrequency = {
169 /**
170 * The original order of the frequency, which is usually used for sorting.
171 */
172 index: number;
173 /**
174 * The name of the dictionary that the frequency information originated from.
175 */
176 dictionary: string;
177 /**
178 * The index of the dictionary in the original list of dictionaries used for the lookup.
179 */
180 dictionaryIndex: number;
181 /**
182 * The alias of the dictionary
183 */
184 dictionaryAlias: string;
185 /**
186 * The kanji character for the frequency.
187 */
188 character: string;
189 /**
190 * The frequency for the character, as a number of occurrences or an overall rank.
191 */
192 frequency: number;
193 /**
194 * A display value to show to the user.
195 */
196 displayValue: string | null;
197 /**
198 * Whether or not the displayValue string was parsed to determine the frequency value.
199 */
200 displayValueParsed: boolean;
201};
202
203// Terms
204
205/**
206 * A dictionary entry for a term or group of terms.
207 */
208export type TermDictionaryEntry = {
209 /**
210 * The type of the entry.
211 */
212 type: 'term';
213 /**
214 * Whether or not any of the sources is a primary source. Primary sources are derived from the
215 * original search text, while non-primary sources originate from related terms.
216 */
217 isPrimary: boolean;
218 /**
219 * Ways that a looked-up word might be transformed into this term.
220 */
221 textProcessorRuleChainCandidates: textProcessorRuleChainCandidate[];
222 /**
223 * Ways that a looked-up word might be an inflected form of this term.
224 */
225 inflectionRuleChainCandidates: InflectionRuleChainCandidate[];
226 /**
227 * A score for the dictionary entry.
228 */
229 score: number;
230 /**
231 * The sorting value based on the determined term frequency.
232 */
233 frequencyOrder: number;
234 /**
235 * The index of the dictionary in the original list of dictionaries used for the lookup.
236 */
237 dictionaryIndex: number;
238 /**
239 * The alias of the dictionary
240 */
241 dictionaryAlias: string;
242 /**
243 * The number of primary sources that had an exact text match for the term.
244 */
245 sourceTermExactMatchCount: number;
246 /**
247 * Whether the term reading matched the primary reading.
248 */
249 matchPrimaryReading: boolean;
250 /**
251 * The maximum length of the original text for all primary sources.
252 */
253 maxOriginalTextLength: number;
254 /**
255 * Headwords for the entry.
256 */
257 headwords: TermHeadword[];
258 /**
259 * Definitions for the entry.
260 */
261 definitions: TermDefinition[];
262 /**
263 * Pronunciations for the entry.
264 */
265 pronunciations: TermPronunciation[];
266 /**
267 * Frequencies for the entry.
268 */
269 frequencies: TermFrequency[];
270};
271
272export type InflectionRuleChainCandidate = {
273 source: InflectionSource;
274 inflectionRules: InflectionRuleChain;
275};
276
277type textProcessorRuleChainCandidate = string[];
278
279export type InflectionRuleChain = InflectionRule[];
280
281export type InflectionRule = {
282 name: string;
283 description?: string;
284};
285
286export type InflectionSource = 'algorithm' | 'dictionary' | 'both';
287
288/**
289 * A term headword is a combination of a term, reading, and auxiliary information.
290 */
291export type TermHeadword = {
292 /**
293 * The original order of the headword, which is usually used for sorting.
294 */
295 index: number;
296 /**
297 * The text for the term.
298 */
299 term: string;
300 /**
301 * The reading of the term.
302 */
303 reading: string;
304 /**
305 * The sources of the term.
306 */
307 sources: TermSource[];
308 /**
309 * Tags for the headword.
310 */
311 tags: Tag[];
312 /**
313 * List of word classes (part of speech) for the headword.
314 */
315 wordClasses: string[];
316};
317
318/**
319 * A definition contains a list of entries and information about what what terms it corresponds to.
320 */
321export type TermDefinition = {
322 /**
323 * The original order of the definition, which is usually used for sorting.
324 */
325 index: number;
326 /**
327 * A list of headwords that this definition corresponds to.
328 */
329 headwordIndices: number[];
330 /**
331 * The name of the dictionary that the definition information originated from.
332 */
333 dictionary: string;
334 /**
335 * The index of the dictionary in the original list of dictionaries used for the lookup.
336 */
337 dictionaryIndex: number;
338 /**
339 * The alias of the dictionary
340 */
341 dictionaryAlias: string;
342 /**
343 * Database ID for the definition.
344 */
345 id: number;
346 /**
347 * A score for the definition.
348 */
349 score: number;
350 /**
351 * The sorting value based on the determined term frequency.
352 */
353 frequencyOrder: number;
354 /**
355 * A list of database sequence numbers for the term. A value of `-1` corresponds to no sequence.
356 * The list can have multiple values if multiple definitions with different sequences have been merged.
357 * The list should always have at least one item.
358 */
359 sequences: number[];
360 /**
361 * Whether or not any of the sources is a primary source. Primary sources are derived from the
362 * original search text, while non-primary sources originate from related terms.
363 */
364 isPrimary: boolean;
365 /**
366 * Tags for the definition.
367 */
368 tags: Tag[];
369 /**
370 * The definition entries.
371 */
372 entries: DictionaryData.TermGlossaryContent[];
373};
374
375/**
376 * A term pronunciation represents different ways to pronounce one of the headwords.
377 */
378export type TermPronunciation = {
379 /**
380 * The original order of the pronunciation, which is usually used for sorting.
381 */
382 index: number;
383 /**
384 * Which headword this pronunciation corresponds to.
385 */
386 headwordIndex: number;
387 /**
388 * The name of the dictionary that the proununciation information originated from.
389 */
390 dictionary: string;
391 /**
392 * The index of the dictionary in the original list of dictionaries used for the lookup.
393 */
394 dictionaryIndex: number;
395 /**
396 * The alias of the dictionary
397 */
398 dictionaryAlias: string;
399 /**
400 * The pronunciations for the term.
401 */
402 pronunciations: Pronunciation[];
403};
404
405export type Pronunciation = PitchAccent | PhoneticTranscription;
406
407/**
408 * Pitch accent information for a term, represented as the position of the downstep.
409 */
410export type PitchAccent = {
411 /**
412 * Type of the pronunciation, for disambiguation between union type members.
413 */
414 type: 'pitch-accent';
415 /**
416 * Position of the downstep, as a number of mora.
417 */
418 positions: number | string;
419 /**
420 * Positions of morae with a nasal sound.
421 */
422 nasalPositions: number[];
423 /**
424 * Positions of morae with a devoiced sound.
425 */
426 devoicePositions: number[];
427 /**
428 * Tags for the pitch accent.
429 */
430 tags: Tag[];
431};
432
433export type PhoneticTranscription = {
434 /**
435 * Type of the pronunciation, for disambiguation between union type members.
436 */
437 type: 'phonetic-transcription';
438 /**
439 * An IPA transcription.
440 */
441 ipa: string;
442 /**
443 * Tags for the IPA transcription.
444 */
445 tags: Tag[];
446};
447
448export type PronunciationType = Pronunciation['type'];
449
450export type PronunciationGeneric<T extends PronunciationType> = Extract<Pronunciation, {type: T}>;
451
452/**
453 * Frequency information corresponds to how frequently a term appears in a corpus,
454 * which can be a number of occurrences or an overall rank.
455 */
456export type TermFrequency = {
457 /**
458 * The original order of the frequency, which is usually used for sorting.
459 */
460 index: number;
461 /**
462 * Which headword this frequency corresponds to.
463 */
464 headwordIndex: number;
465 /**
466 * The name of the dictionary that the frequency information originated from.
467 */
468 dictionary: string;
469 /**
470 * The index of the dictionary in the original list of dictionaries used for the lookup.
471 */
472 dictionaryIndex: number;
473 /**
474 * The alias of the dictionary
475 */
476 dictionaryAlias: string;
477 /**
478 * Whether or not the frequency had an explicit reading specified.
479 */
480 hasReading: boolean;
481 /**
482 * The frequency for the term, as a number of occurrences or an overall rank.
483 */
484 frequency: number;
485 /**
486 * A display value to show to the user.
487 */
488 displayValue: string | null;
489 /**
490 * Whether or not the displayValue string was parsed to determine the frequency value.
491 */
492 displayValueParsed: boolean;
493};
494
495/**
496 * Enum representing how the search term relates to the final term.
497 */
498export type TermSourceMatchType = 'exact' | 'prefix' | 'suffix';
499
500/**
501 * Enum representing what database field was used to match the source term.
502 */
503export type TermSourceMatchSource = 'term' | 'reading' | 'sequence';
504
505/**
506 * Source information represents how the original text was transformed to get to the final term.
507 */
508export type TermSource = {
509 /**
510 * The original text that was searched.
511 */
512 originalText: string;
513 /**
514 * The original text after being transformed, but before applying deinflections.
515 */
516 transformedText: string;
517 /**
518 * The final text after applying deinflections.
519 */
520 deinflectedText: string;
521 /**
522 * How the deinflected text matches the value from the database.
523 */
524 matchType: TermSourceMatchType;
525 /**
526 * Which field was used to match the database entry.
527 */
528 matchSource: TermSourceMatchSource;
529 /**
530 * Whether or not this source is a primary source. Primary sources are derived from the
531 * original search text, while non-primary sources originate from related terms.
532 */
533 isPrimary: boolean;
534};