Coverage for src/wiktextract/extractor/zh/tags.py: 98%

35 statements  

« prev     ^ index     » next       coverage.py v7.11.0, created at 2025-10-30 10:31 +0000

1from .models import WordEntry 

2from .topics import LABEL_TOPICS 

3 

4GENDER_TAGS: dict[str, str] = { 

5 "陰性": "feminine", 

6 "阴性": "feminine", 

7 "陰性形式": "feminine", 

8 "陰性等價詞": "feminine", 

9 "陽性": "masculine", 

10 "陽性形式": "masculine", 

11 "中性": "neuter", 

12 "中性形式": "neuter", 

13} 

14 

15NUMBER_TAGS: dict[str, str | list[str]] = { 

16 "單數": "singular", 

17 "单数": "singular", 

18 "複數": "plural", 

19 "复数": "plural", 

20 "定單數": ["definite", "singular"], 

21 "定单数": ["definite", "singular"], 

22 "不定單數": ["indefinite", "singular"], 

23 "不定单数": ["indefinite", "singular"], 

24 "不定複數": ["indefinite", "plural"], 

25 "不定复数": ["indefinite", "plural"], 

26 "定複數": ["definite", "plural"], 

27 "斜格複數": ["oblique", "plural"], 

28 "主格單數": ["nominative", "singular"], 

29 "主格複數": ["nominative", "plural"], 

30 "屬格單數": ["genitive", "singular"], 

31 "屬格複數": ["genitive", "plural"], 

32 "陰性單數": ["feminine", "singular"], 

33 "陽性單數": ["masculine", "singular"], 

34 "陰性複數": ["feminine", "plural"], 

35 "陽性複數": ["masculine", "plural"], 

36 "中性複數": ["neuter", "plural"], 

37 "中性單數": ["neuter", "singular"], 

38 "賓格單數": ["accusative", "singular"], 

39 "賓格複數": ["accusative", "plural"], 

40 "無複數": "no-plural", 

41} 

42 

43# https://en.wikipedia.org/wiki/Count_noun 

44COUNT_TAGS: dict[str, str] = { 

45 "可數": "countable", 

46 "不可數": "uncountable", 

47} 

48 

49OTHER_TAGS: dict[str, str] = { 

50 "指小詞": "diminutive", 

51 "指小": "diminutive", 

52 "變格類型": "declension-pattern-of", 

53 "屬格": "genitive", 

54 "部分格": "partitive", 

55 "個人": "person", 

56 "無屈折": "indeclinable", 

57 "諺文": "hangeul", 

58 "漢字": "hanja", 

59 # Template:cs-proper noun 

60 "相關形容詞": ["relational", "adjective"], 

61 "關係形容詞": ["relational", "adjective"], 

62 "居民稱謂詞": "demonym", 

63 "女性居民稱謂詞": ["feminine", "demonym"], 

64 "定賓格": ["definite", "accusative"], 

65 "定宾格": ["definite", "accusative"], 

66 "拉丁字母拼寫": "romanization", 

67 "定指賓格": ["definite", "accusative"], 

68 "前元音和諧變體": "front-vowel-harmony", 

69 # Template:zh-forms 

70 "正體": "Standard-Chinese", 

71 "繁體": "Traditional-Chinese", 

72 "簡體": "Simplified-Chinese", 

73 "異體": "alternative", 

74 "仿譯詞": "calque", 

75 "貶稱詞": "pejorative", 

76} 

77 

78VERB_TAGS: dict[str, str] = { 

79 "及物": "transitive", 

80 "不及物": "intransitive", 

81 "动宾结构": "verb-object", 

82 "非完": "imperfective", 

83 "完": "perfective", 

84 "強變化": "strong", 

85 "動名詞": "supine", 

86 "命令式": "imperative", 

87} 

88 

89# https://en.wikipedia.org/wiki/Japanese_grammar#Stem_forms 

90JA_STEM_FORMS: dict[str, str] = { 

91 "未然形": "imperfective", 

92 "連用形": "continuative", 

93 "終止形": "terminal", 

94 "連體形": "attributive", 

95 "連体形": "attributive", 

96 "假定形": "hypothetical", 

97 "仮定形": "hypothetical", 

98 "命令形": "imperative", 

99} 

100 

101# https://en.wikipedia.org/wiki/Voice_(grammar) 

102VOICE_TAGS: dict[str, str | list[str]] = { 

103 "被動形": "passive", 

104 "使役形": "causative", 

105 "可能形": "potential", 

106 "意志形": "volitional", 

107 "否定形": "negative", 

108 "否定連用形": ["negative", "continuative"], 

109 "尊敬形": "formal", 

110 "完成形": "perfective", 

111 "接續形": "conjunctive", 

112 "條件形": ["hypothetical", "conditional"], 

113} 

114 

115COMPARISON_TAGS: dict[str, str] = { 

116 # https://en.wikipedia.org/wiki/Comparison_(grammar) 

117 "原级": "positive", 

118 "比較級": "comparative", 

119 "最高級": "superlative", 

120} 

121 

122TENSE_TAGS = { 

123 "過去時": "preterite", 

124 "過去式": "past", 

125 "過去分詞": ["past", "participle"], 

126 "現在時": "present", 

127 "第三人稱單數現在時": ["third-person", "singular", "present"], 

128 "助動詞": "auxiliary", 

129 # Template:de-verb 

130 "弱變化": "weak", 

131 "弱变化": "weak", 

132 "第三人稱單數簡單現在時": ["third-person", "singular", "present"], 

133 "現在分詞": ["present", "participle"], 

134 "一般過去時及過去分詞": ["past", "participle"], 

135 # Template:it-verb 

136 "第一人稱單數 現在時": ["first-person", "singular", "present"], 

137 "第一人稱單數 先過去時": ["first-person", "singular", "past", "historic"], 

138 # Template:de-adj 

139 "強變化主格陽性單數": ["strong", "nominative", "masculine", "singular"], 

140 # Template:la-verb 

141 "现在时不定式": ["present", "infinitive"], 

142 "完成时主动式": ["perfect", "active"], 

143 "目的动名词": "supine", 

144} 

145 

146GRAMMATICAL_TAGS: dict[str, str] = { 

147 **GENDER_TAGS, 

148 **NUMBER_TAGS, 

149 **COUNT_TAGS, 

150 **OTHER_TAGS, 

151 **VERB_TAGS, 

152 **JA_STEM_FORMS, 

153 **VOICE_TAGS, 

154 **COMPARISON_TAGS, 

155 **TENSE_TAGS, 

156} 

157 

158# https://zh.wiktionary.org/wiki/Template:Label 

159# https://zh.wiktionary.org/wiki/Module:Labels/data 

160# https://zh.wiktionary.org/wiki/Template:Qualifier 

161# https://zh.wiktionary.org/wiki/Template:古 

162# https://zh.wiktionary.org/wiki/Template:注释 

163LABEL_TAGS = { 

164 "棄用": "obsolete", 

165 "弃用": "obsolete", 

166 "比喻": "figuratively", 

167 "古": "archaic", 

168 "陽": "masculine", 

169 "陰": "feminine", 

170 "喻": "figuratively", 

171 "書": "literary", 

172 "口": "colloquial", 

173 "俚": "slang", 

174 "俗": "slang", 

175 "方": "dialectal", 

176 "废": "obsolete", 

177 "貶": "derogatory", 

178 "罕": "rare", 

179 "引": "broadly", 

180 "現已罕用": "archaic", 

181 # Module:Labels/data 

182 "back slang": "slang", 

183 "synecdochically": "synecdoche", 

184 "不再自由造詞": "idiomatic", 

185 "不及物": "intransitive", 

186 "不可數": "uncountable", 

187 "不定": "indefinite", 

188 "不常見": "uncommon", 

189 "不推薦使用": "proscribed", 

190 "中性": "neuter", 

191 "中間被動語態": "mediopassive", 

192 "中間語態": "middle", 

193 "主動語態": "active", 

194 "主要用於否定": ["usually", "with-negation"], 

195 "交互": "reciprocal", 

196 "以單數形式": "singular", 

197 "以複數形式": "in-plural", 

198 "作定語": "attributive", 

199 "作格": "ergative", 

200 "作表語": "predicative", 

201 "使役": "causative", 

202 "俗語": "idiomatic", 

203 "俚語": "slang", 

204 "俚语": "slang", 

205 "兒童用語": "childish", 

206 "公文": "bureaucratese", 

207 "冒犯": "offensive", 

208 "分詞": "participle", 

209 "前古典": "pre-Classical", 

210 "助動詞": "auxiliary", 

211 "助記符": "mnemonic", 

212 "及物": "transitive", 

213 "反問句": "rhetoric", 

214 "反身": "reflexive", 

215 "口語": "colloquial", 

216 "口语": "colloquial", 

217 "古舊": "archaic", 

218 "可數": "countable", 

219 "同性戀俚語": ["slang", "LGBT"], 

220 "名詞化": "noun-from-verb", 

221 "唯單": "singular-only", 

222 "唯複": "plural-only", 

223 "國際音標": "IPA", 

224 "基數詞": "cardinal", 

225 "大寫": "capitalized", 

226 "委婉": "euphemistic", 

227 "字面義": "literally", 

228 "完整": "perfect", 

229 "完整體": "perfective", 

230 "定語": "attributive", 

231 "實詞": "substantive", 

232 "尊敬": "honorific", 

233 "敬語": "honorific", 

234 "敬语": "honorific", 

235 "常用複數": "plural-normally", 

236 "幽默": "humorous", 

237 "序數詞": "ordinal", 

238 "廣義來說": "broadly", 

239 "引申": "broadly", 

240 "弱祈使式": "jussive", 

241 "強調": "emphatic", 

242 "後古典": "obsolete", 

243 "性別中立": "gender-neutral", 

244 "情態": "modal", 

245 "愛稱": "endearing", 

246 "所有格代詞": ["possessive", "pronoun", "without-noun"], 

247 "押韻俚語": "slang", 

248 "抽象名詞": "abstract-noun", 

249 "擬態詞": "ideophonic", 

250 "擬聲詞": "onomatopoeic", 

251 "新詞": "neologism", 

252 "方言": "dialectal", 

253 "書面": "literary", 

254 "书面": "literary", 

255 "有比較級": "comparable", 

256 "有生": "animate", 

257 "正式": "formal", 

258 "歷史": "historical", 

259 "比喻義": "figuratively", 

260 "無人稱": "impersonal", 

261 "無比較級": "not-comparable", 

262 "無生": "inanimate", 

263 "焦點": "focus", 

264 "狹義": "narrowly", 

265 "監獄俚語": "slang", 

266 "直陳語氣": "indicative", 

267 "短信": "Internet", 

268 "祈使語氣": "imperative", 

269 "禮貌": "polite", 

270 "種族歧視語": "slur", 

271 "粉絲用語": ["slang", "lifestyle"], 

272 "粗俗": "vulgar", 

273 "系動詞": "copulative", 

274 "網路用語": "Internet", 

275 "縮寫": "abbreviation", 

276 "罕用": "rare", 

277 "臨時語": "nonce-word", 

278 "虛擬語氣": "subjunctive", 

279 "表語": "predicative", 

280 "被動語態": "passive", 

281 "視覺方言": "pronunciation-spelling", 

282 "親切": "familiar", 

283 "詈語": "expletive", 

284 "詩歌": "poetic", 

285 "誇飾": "excessive", 

286 "語中音省略": "syncope", 

287 "諷刺": "sarcastic", 

288 "謙遜": "humble", 

289 "貶義": "derogatory", 

290 "轉喻義": "metonymically", 

291 "返璞詞": "retronym", 

292 "過時": "dated", 

293 "陰性": "feminine", 

294 "陽性": "masculine", 

295 "雙及物動詞": "ditransitive", 

296 "靜態動詞": "stative", 

297 "非完整": "imperfect", 

298 "非完整體": "imperfective", 

299 "非常罕用": "rare", 

300 "非標準": "nonstandard", 

301 "非标准": "nonstandard", 

302 "非標準形式": "nonstandard", 

303 "非正式": "informal", 

304 "首字母縮略詞": "initialism", 

305 "駭客語": ["Leet", "Internet"], 

306 "高語域": "honorific", 

307 "中醫": "Traditional-Chinese-Medicine", 

308 "修辭學": "rhetoric", 

309 "印度教": "Hinduism", 

310 "摩門教": "Mormonism", 

311 "物理": "particle", 

312 "猶太教": "Judaism", 

313 "納粹主義": "Nazism", 

314 "網際網路": "Internet", 

315 "耆那教": "Jainism", 

316 "聖經": "Biblical", 

317 "解剖學": "anatomy", 

318 "貴格會": "Quakerism", 

319 "錫克教": "Sikhism", 

320 "馬克思主義": "Marxism", 

321 # also from Module:Labels/data, but translated manually 

322 "喃字": "Chu-Nom", 

323 "反身代詞": "reflexive", 

324 "字面意義": "literally", 

325 "成語": "Chengyu", 

326 "及物、不及物": ["transitive", "intransitive"], 

327 "集合名詞": "collective", 

328 "控制動詞": "control-verb", 

329 "省略": "ellipsis", 

330 "分數": "fractional", 

331 "以雙數形式": "dual", 

332 "主要用於否定複數": ["negative", "plural"], 

333 "數詞縮寫": ["numeral", "abbreviation"], 

334 "主要用於肯定": "positive", 

335 "古典": "Classical", 

336 "中國大陸": "Mainland-China", 

337 "書面語": "literary", 

338} 

339 

340# example sentence template 

341# https://zh.wiktionary.org/wiki/Template:Zh-x 

342# https://zh.wiktionary.org/wiki/Module:Zh-usex/data 

343ZH_X_TAGS = { 

344 "繁體": "Traditional-Chinese", 

345 "繁體和": "Traditional-Chinese", 

346 "簡體": "Simplified-Chinese", 

347 "繁體和簡體": ["Traditional-Chinese", "Simplified-Chinese"], 

348 "漢語拼音": "Pinyin", 

349 "粵拼": "Jyutping", 

350 "現代標準漢語": "Standard-Chinese", 

351 "文言文": "Classical-Chinese", 

352 "官話白話文": "Written-vernacular-Chinese", 

353 "粵語": "Cantonese", 

354 "吳語": "Wu", 

355 "廣州話": "Cantonese", 

356 "臺灣華語": "Taiwanese-Mandarin", 

357} 

358 

359# classifier tags 

360# https://zh.wiktionary.org/wiki/Template:zh-mw 

361# https://zh.wiktionary.org/wiki/Module:Zh/templates 

362ZH_TAGS = { 

363 "官話": "Mandarin", 

364 "贛語": "Gan", 

365 "客家話": "Hakka", 

366 "晉語": "Jin", 

367 "閩北語": "Min-Bei", 

368 "閩東語": "Min-Dong", 

369 "閩南語": "Min-Nan", 

370 "潮州話": "Teochew", 

371 "湘語": "Xiang", 

372} 

373 

374# https://zh.wiktionary.org/wiki/Template:Zh-pron 

375# https://zh.wiktionary.org/wiki/Module:Zh-pron 

376ZH_PRON_TAGS = { 

377 "拼音": "Pinyin", 

378 "注音": "Bopomofo", 

379 "潮州話拼音": "Peng'im", 

380 "上海": "Shanghai", 

381 "吳語學堂拼音": "Wugniu", 

382 "通用拼音": "Tongyong-Pinyin", 

383 "威妥瑪拼音": "Wade–Giles", 

384 "耶魯官話拼音": "Yale", 

385 "國語羅馬字": "Gwoyeu-Romatsyh", 

386 "西里爾字母轉寫": "Cyrillic", 

387 "西里爾字母": "Cyrillic", 

388 "漢語國際音標": "Sinological-IPA", 

389 "耶魯粵拼": ["Yale", "Jyutping"], 

390 "廣州話拼音": ["Cantonese", "Pinyin"], 

391 "廣東拼音": "Guangdong-Romanization", 

392 "國際音標": "IPA", 

393 "模仿白話字": "POJ", 

394 "標準粵語": "Standard-Cantonese", 

395 "廣州–香港話": ["Guangzhou", "Hong Kong"], 

396 "福州話": "Fuzhou", 

397 "平話字": "Foochow-Romanized", 

398 "客家語": "Hakka", 

399 "白話字": "Phak-fa-su", 

400 "泉漳話": "Hokkien", 

401 "泉州": "Quanzhou", 

402 "廈門": "Xiamen", 

403 "輕尾聲異讀": "toneless-final-syllable-variant", 

404 "維基詞典": "Wiktionary-specific", 

405 "維基詞典拼音": ["Wiktionary-specific", "Pinyin"], 

406 "維基詞典轉寫": "Wiktionary-specific", 

407 "成都話": "Chengdu", 

408 "四川話拼音": ["Sichuanese", "Pinyin"], 

409 "東干語": "Dongan", 

410 "台山話": "Taishanese", 

411 "四縣": "Sixian", 

412 "長沙話": "Changsha", 

413 "四川話拉丁化新文字": "Latinxua-Sin-Wenz", 

414 "台城": "Taicheng", 

415 "南昌話": "Nanchang", 

416 "四縣話": "Sixian", 

417 "苗栗": "Miaoli", 

418 "美濃": "Neipu", 

419 "客家語拼音": "Hakka-Romanization-System", 

420 "客家話拼音方案": "Hagfa-Pinyim", 

421 "太原話": "Taiyuan", 

422 "老派": "dated", 

423 "新加坡": "Singapore", 

424 "臺羅": "Tâi-lô", 

425 "普實台文": "Phofsit-Daibuun", 

426 "太湖片": "Northern", 

427 "吳音小字典": "MiniDict", 

428 "維基詞典羅馬化": ["Wiktionary-specific", "romanization"], 

429 "上海話": "Shanghai", 

430 "中古漢語": "Middle-Chinese", 

431 "莆仙語": "Puxian-Min", 

432 "莆仙話拼音": "Pouseng-Ping'ing", 

433 "莆田": "Putian", 

434 "仙遊": "Xianyou", 

435 "漳州": "Zhangzhou", 

436 "臺北": "Taibei", 

437 "高雄": "Kaohsiung", 

438 "實際讀音": "phonetic", 

439 "臺灣話": "Taiwanese", 

440 "常用": "general", 

441 "檳城": "Penang", 

442 "兒化": "Erhua", 

443 "文讀": "literary", 

444 "中國大陸標準讀法": ["Mainland-China", "standard"], 

445 "臺灣異讀法": ["Taiwan", "variant"], 

446 "中國大陸與臺灣標準讀法": ["Mainland-China", "Taiwan", "standard"], 

447} 

448 

449ZH_DIAL_TAGS = { 

450 "白話文": "Written-vernacular-Chinese", 

451 "北京": "Beijing", 

452 "燕京官話": "Northeastern-Mandarin", 

453 "冀魯官話": "Jilu-Mandarin", 

454 "膠遼官話": "Jiaoliao-Mandarin", 

455 "中原官話": "Central-Plains-Mandarin", 

456 "蘭銀官話": "Lanyin-Mandarin", 

457 "西南官話": "Southwestern-Mandarin", 

458 "江淮官話": "Jianghuai-Mandarin", 

459 "徽語": "Huizhou", 

460 "南部平話": "Southern-Pinghua", 

461 "濟南": "Jinan", 

462 "臺灣": "Taiwan", 

463} 

464 

465TH_PRON_TAGS = { 

466 "寫法": "orthographic", 

467 "音素": "phoneme", 

468 "泰語羅馬化": "romanization", 

469 "派汶拼音": "Paiboon", 

470 "皇家轉寫": "Royal-Institute", 

471 "非正字法": "unorthographical", 

472 "短音": "short", 

473} 

474 

475 

476ALL_TAGS = { 

477 **GRAMMATICAL_TAGS, 

478 **LABEL_TAGS, 

479 **ZH_X_TAGS, 

480 **ZH_TAGS, 

481 **ZH_PRON_TAGS, 

482 **ZH_DIAL_TAGS, 

483 **TH_PRON_TAGS, 

484} 

485 

486 

487def translate_raw_tags(data: WordEntry) -> WordEntry: 

488 raw_tags = [] 

489 for raw_tag in data.raw_tags: 

490 if raw_tag in ALL_TAGS: 

491 tr_tag = ALL_TAGS[raw_tag] 

492 if isinstance(tr_tag, str) and tr_tag not in data.tags: 

493 data.tags.append(tr_tag) 

494 elif isinstance(tr_tag, list): 

495 data.tags.extend(tr_tag) 

496 elif raw_tag in LABEL_TOPICS and hasattr(data, "topics"): 

497 data.topics.append(LABEL_TOPICS[raw_tag]) 

498 elif raw_tag not in raw_tags: 498 ↛ 489line 498 didn't jump to line 489 because the condition on line 498 was always true

499 raw_tags.append(raw_tag) 

500 data.raw_tags = raw_tags 

501 return data 

502 

503 

504# https://zh.wiktionary.org/wiki/Template:T 

505# https://zh.wiktionary.org/wiki/Template:Head 

506# https://zh.wiktionary.org/wiki/Module:Gender_and_number 

507TEMPLATE_TAG_ARGS = { 

508 "f": "feminine", 

509 "m": "masculine", 

510 "n": "neuter", 

511 "c": "common", 

512 # Animacy 

513 "an": "animate", 

514 "in": "inanimate", 

515 # Animal (for Ukrainian, Belarusian, Polish) 

516 "anml": "animal", 

517 # Personal (for Ukrainian, Belarusian, Polish) 

518 "pr": "personal", 

519 # Nonpersonal not currently used 

520 "np": "nonpersonal", 

521 # Virility (for Polish) 

522 "vr": "virile", 

523 "nv": "nonvirile", 

524 # Numbers 

525 "s": "singular number", 

526 "d": "dual number", 

527 "p": "plural number", 

528 # Verb qualifiers 

529 "impf": "imperfective", 

530 "pf": "perfective", 

531 "mf": ["masculine", "feminine"], 

532}