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

1from .models import WordEntry

2from .topics import LABEL_TOPICS

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}

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}

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

44COUNT_TAGS: dict[str, str] = {

45 "可數": "countable",

46 "不可數": "uncountable",

47}

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}

77VERB_TAGS: dict[str, str] = {

78 "及物": "transitive",

79 "不及物": "intransitive",

80 "动宾结构": "verb-object",

81 "非完": "imperfective",

82 "完": "perfective",

83 "強變化": "strong",

84 "動名詞": "supine",

85 "命令式": "imperative",

86}

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

89JA_STEM_FORMS: dict[str, str] = {

90 "未然形": "imperfective",

91 "連用形": "continuative",

92 "終止形": "terminal",

93 "連體形": "attributive",

94 "連体形": "attributive",

95 "假定形": "hypothetical",

96 "仮定形": "hypothetical",

97 "命令形": "imperative",

98}

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

101VOICE_TAGS: dict[str, str | list[str]] = {

102 "被動形": "passive",

103 "使役形": "causative",

104 "可能形": "potential",

105 "意志形": "volitional",

106 "否定形": "negative",

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

108 "尊敬形": "formal",

109 "完成形": "perfective",

110 "接續形": "conjunctive",

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

112}

113

114COMPARISON_TAGS: dict[str, str] = {

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

116 "原级": "positive",

117 "比較級": "comparative",

118 "最高級": "superlative",

119}

120

121TENSE_TAGS = {

122 "過去時": "preterite",

123 "過去式": "past",

124 "過去分詞": ["past", "participle"],

125 "現在時": "present",

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

127 "助動詞": "auxiliary",

128 # Template:de-verb

129 "弱變化": "weak",

130 "弱变化": "weak",

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

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

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

134 # Template:it-verb

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

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

137 # Template:de-adj

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

139 # Template:la-verb

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

141 "完成时主动式": ["perfect", "active"],

142 "目的动名词": "supine",

143}

144

145GRAMMATICAL_TAGS: dict[str, str] = {

146 **GENDER_TAGS,

147 **NUMBER_TAGS,

148 **COUNT_TAGS,

149 **OTHER_TAGS,

150 **VERB_TAGS,

151 **JA_STEM_FORMS,

152 **VOICE_TAGS,

153 **COMPARISON_TAGS,

154 **TENSE_TAGS,

155}

156

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

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

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

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

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

162LABEL_TAGS = {

163 "棄用": "obsolete",

164 "弃用": "obsolete",

165 "比喻": "figuratively",

166 "古": "archaic",

167 "陽": "masculine",

168 "陰": "feminine",

169 "喻": "figuratively",

170 "書": "literary",

171 "口": "colloquial",

172 "俚": "slang",

173 "俗": "slang",

174 "方": "dialectal",

175 "废": "obsolete",

176 "貶": "derogatory",

177 "罕": "rare",

178 "引": "broadly",

179 "現已罕用": "archaic",

180 # Module:Labels/data

181 "back slang": "slang",

182 "synecdochically": "synecdoche",

183 "不再自由造詞": "idiomatic",

184 "不及物": "intransitive",

185 "不可數": "uncountable",

186 "不定": "indefinite",

187 "不常見": "uncommon",

188 "不推薦使用": "proscribed",

189 "中性": "neuter",

190 "中間被動語態": "mediopassive",

191 "中間語態": "middle",

192 "主動語態": "active",

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

194 "交互": "reciprocal",

195 "以單數形式": "singular",

196 "以複數形式": "in-plural",

197 "作定語": "attributive",

198 "作格": "ergative",

199 "作表語": "predicative",

200 "使役": "causative",

201 "俗語": "idiomatic",

202 "俚語": "slang",

203 "俚语": "slang",

204 "兒童用語": "childish",

205 "公文": "bureaucratese",

206 "冒犯": "offensive",

207 "分詞": "participle",

208 "前古典": "pre-Classical",

209 "助動詞": "auxiliary",

210 "助記符": "mnemonic",

211 "及物": "transitive",

212 "反問句": "rhetoric",

213 "反身": "reflexive",

214 "口語": "colloquial",

215 "口语": "colloquial",

216 "古舊": "archaic",

217 "可數": "countable",

218 "同性戀俚語": ["slang", "LGBT"],

219 "名詞化": "noun-from-verb",

220 "唯單": "singular-only",

221 "唯複": "plural-only",

222 "國際音標": "IPA",

223 "基數詞": "cardinal",

224 "大寫": "capitalized",

225 "委婉": "euphemistic",

226 "字面義": "literally",

227 "完整": "perfect",

228 "完整體": "perfective",

229 "定語": "attributive",

230 "實詞": "substantive",

231 "尊敬": "honorific",

232 "敬語": "honorific",

233 "敬语": "honorific",

234 "常用複數": "plural-normally",

235 "幽默": "humorous",

236 "序數詞": "ordinal",

237 "廣義來說": "broadly",

238 "引申": "broadly",

239 "弱祈使式": "jussive",

240 "強調": "emphatic",

241 "後古典": "obsolete",

242 "性別中立": "gender-neutral",

243 "情態": "modal",

244 "愛稱": "endearing",

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

246 "押韻俚語": "slang",

247 "抽象名詞": "abstract-noun",

248 "擬態詞": "ideophonic",

249 "擬聲詞": "onomatopoeic",

250 "新詞": "neologism",

251 "方言": "dialectal",

252 "書面": "literary",

253 "书面": "literary",

254 "有比較級": "comparable",

255 "有生": "animate",

256 "正式": "formal",

257 "歷史": "historical",

258 "比喻義": "figuratively",

259 "無人稱": "impersonal",

260 "無比較級": "not-comparable",

261 "無生": "inanimate",

262 "焦點": "focus",

263 "狹義": "narrowly",

264 "監獄俚語": "slang",

265 "直陳語氣": "indicative",

266 "短信": "Internet",

267 "祈使語氣": "imperative",

268 "禮貌": "polite",

269 "種族歧視語": "slur",

270 "粉絲用語": ["slang", "lifestyle"],

271 "粗俗": "vulgar",

272 "系動詞": "copulative",

273 "網路用語": "Internet",

274 "縮寫": "abbreviation",

275 "罕用": "rare",

276 "臨時語": "nonce-word",

277 "虛擬語氣": "subjunctive",

278 "表語": "predicative",

279 "被動語態": "passive",

280 "視覺方言": "pronunciation-spelling",

281 "親切": "familiar",

282 "詈語": "expletive",

283 "詩歌": "poetic",

284 "誇飾": "excessive",

285 "語中音省略": "syncope",

286 "諷刺": "sarcastic",

287 "謙遜": "humble",

288 "貶義": "derogatory",

289 "轉喻義": "metonymically",

290 "返璞詞": "retronym",

291 "過時": "dated",

292 "陰性": "feminine",

293 "陽性": "masculine",

294 "雙及物動詞": "ditransitive",

295 "靜態動詞": "stative",

296 "非完整": "imperfect",

297 "非完整體": "imperfective",

298 "非常罕用": "rare",

299 "非標準": "nonstandard",

300 "非标准": "nonstandard",

301 "非標準形式": "nonstandard",

302 "非正式": "informal",

303 "首字母縮略詞": "initialism",

304 "駭客語": ["Leet", "Internet"],

305 "高語域": "honorific",

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

307 "修辭學": "rhetoric",

308 "印度教": "Hinduism",

309 "摩門教": "Mormonism",

310 "物理": "particle",

311 "猶太教": "Judaism",

312 "納粹主義": "Nazism",

313 "網際網路": "Internet",

314 "耆那教": "Jainism",

315 "聖經": "Biblical",

316 "解剖學": "anatomy",

317 "貴格會": "Quakerism",

318 "錫克教": "Sikhism",

319 "馬克思主義": "Marxism",

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

321 "喃字": "Chu-Nom",

322 "反身代詞": "reflexive",

323 "字面意義": "literally",

324 "成語": "Chengyu",

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

326 "集合名詞": "collective",

327 "控制動詞": "control-verb",

328 "省略": "ellipsis",

329 "分數": "fractional",

330 "以雙數形式": "dual",

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

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

333 "主要用於肯定": "positive",

334 "古典": "Classical",

335 "中國大陸": "Mainland-China",

336 "書面語": "literary",

337}

338

339# example sentence template

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

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

342ZH_X_TAGS = {

343 "繁體": "Traditional-Chinese",

344 "繁體和": "Traditional-Chinese",

345 "簡體": "Simplified-Chinese",

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

347 "漢語拼音": "Pinyin",

348 "粵拼": "Jyutping",

349 "現代標準漢語": "Standard-Chinese",

350 "文言文": "Classical-Chinese",

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

352 "粵語": "Cantonese",

353 "吳語": "Wu",

354 "廣州話": "Cantonese",

355 "臺灣華語": "Taiwanese-Mandarin",

356}

357

358# classifier tags

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

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

361ZH_TAGS = {

362 "官話": "Mandarin",

363 "贛語": "Gan",

364 "客家話": "Hakka",

365 "晉語": "Jin",

366 "閩北語": "Min-Bei",

367 "閩東語": "Min-Dong",

368 "閩南語": "Min-Nan",

369 "潮州話": "Teochew",

370 "湘語": "Xiang",

371}

372

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

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

375ZH_PRON_TAGS = {

376 "拼音": "Pinyin",

377 "注音": "Bopomofo",

378 "潮州話拼音": "Peng'im",

379 "上海": "Shanghai",

380 "吳語學堂拼音": "Wugniu",

381 "通用拼音": "Tongyong-Pinyin",

382 "威妥瑪拼音": "Wade–Giles",

383 "耶魯官話拼音": "Yale",

384 "國語羅馬字": "Gwoyeu-Romatsyh",

385 "西里爾字母轉寫": "Cyrillic",

386 "西里爾字母": "Cyrillic",

387 "漢語國際音標": "Sinological-IPA",

388 "耶魯粵拼": ["Yale", "Jyutping"],

389 "廣州話拼音": ["Cantonese", "Pinyin"],

390 "廣東拼音": "Guangdong-Romanization",

391 "國際音標": "IPA",

392 "模仿白話字": "POJ",

393 "標準粵語": "Standard-Cantonese",

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

395 "福州話": "Fuzhou",

396 "平話字": "Foochow-Romanized",

397 "客家語": "Hakka",

398 "白話字": "Phak-fa-su",

399 "泉漳話": "Hokkien",

400 "泉州": "Quanzhou",

401 "廈門": "Xiamen",

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

403 "維基詞典": "Wiktionary-specific",

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

405 "維基詞典轉寫": "Wiktionary-specific",

406 "成都話": "Chengdu",

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

408 "東干語": "Dongan",

409 "台山話": "Taishanese",

410 "四縣": "Sixian",

411 "長沙話": "Changsha",

412 "四川話拉丁化新文字": "Latinxua-Sin-Wenz",

413 "台城": "Taicheng",

414 "南昌話": "Nanchang",

415 "四縣話": "Sixian",

416 "苗栗": "Miaoli",

417 "美濃": "Neipu",

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

419 "客家話拼音方案": "Hagfa-Pinyim",

420 "太原話": "Taiyuan",

421 "老派": "dated",

422 "新加坡": "Singapore",

423 "臺羅": "Tâi-lô",

424 "普實台文": "Phofsit-Daibuun",

425 "太湖片": "Northern",

426 "吳音小字典": "MiniDict",

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

428 "上海話": "Shanghai",

429 "中古漢語": "Middle-Chinese",

430 "莆仙語": "Puxian-Min",

431 "莆仙話拼音": "Pouseng-Ping'ing",

432 "莆田": "Putian",

433 "仙遊": "Xianyou",

434 "漳州": "Zhangzhou",

435 "臺北": "Taibei",

436 "高雄": "Kaohsiung",

437 "實際讀音": "phonetic",

438 "臺灣話": "Taiwanese",

439 "常用": "general",

440 "檳城": "Penang",

441 "兒化": "Erhua",

442 "文讀": "literary",

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

444 "臺灣異讀法": ["Taiwan", "variant"],

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

446}

447

448ZH_DIAL_TAGS = {

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

450 "北京": "Beijing",

451 "燕京官話": "Northeastern-Mandarin",

452 "冀魯官話": "Jilu-Mandarin",

453 "膠遼官話": "Jiaoliao-Mandarin",

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

455 "蘭銀官話": "Lanyin-Mandarin",

456 "西南官話": "Southwestern-Mandarin",

457 "江淮官話": "Jianghuai-Mandarin",

458 "徽語": "Huizhou",

459 "南部平話": "Southern-Pinghua",

460 "濟南": "Jinan",

461 "臺灣": "Taiwan",

462}

463

464

465ALL_TAGS = {

466 **GRAMMATICAL_TAGS,

467 **LABEL_TAGS,

468 **ZH_X_TAGS,

469 **ZH_TAGS,

470 **ZH_PRON_TAGS,

471 **ZH_DIAL_TAGS,

472}

473

474

475def translate_raw_tags(data: WordEntry) -> WordEntry:

476 raw_tags = []

477 for raw_tag in data.raw_tags:

478 if raw_tag in ALL_TAGS:

479 tr_tag = ALL_TAGS[raw_tag]

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

481 data.tags.append(tr_tag)

482 elif isinstance(tr_tag, list):

483 data.tags.extend(tr_tag)

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

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

486 elif raw_tag not in raw_tags: 486 ↛ 477line 486 didn't jump to line 477 because the condition on line 486 was always true

487 raw_tags.append(raw_tag)

488 data.raw_tags = raw_tags

489 return data

490

491

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

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

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

495TEMPLATE_TAG_ARGS = {

496 "f": "feminine",

497 "m": "masculine",

498 "n": "neuter",

499 "c": "common",

500 # Animacy

501 "an": "animate",

502 "in": "inanimate",

503 # Animal (for Ukrainian, Belarusian, Polish)

504 "anml": "animal",

505 # Personal (for Ukrainian, Belarusian, Polish)

506 "pr": "personal",

507 # Nonpersonal not currently used

508 "np": "nonpersonal",

509 # Virility (for Polish)

510 "vr": "virile",

511 "nv": "nonvirile",

512 # Numbers

513 "s": "singular number",

514 "d": "dual number",

515 "p": "plural number",

516 # Verb qualifiers

517 "impf": "imperfective",

518 "pf": "perfective",

519 "mf": ["masculine", "feminine"],

520}