Coverage for src/wiktextract/extractor/zh/tags.py: 100%

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}

71VERB_TAGS: dict[str, str] = {

72 "及物": "transitive",

73 "不及物": "intransitive",

74 "动宾结构": "verb-object",

75 "非完": "imperfective",

76 "完": "perfective",

77 "強變化": "strong",

78 "動名詞": "supine",

79 "命令式": "imperative",

80}

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

83JA_STEM_FORMS: dict[str, str] = {

84 "未然形": "imperfective",

85 "連用形": "continuative",

86 "終止形": "terminal",

87 "連體形": "attributive",

88 "連体形": "attributive",

89 "假定形": "hypothetical",

90 "仮定形": "hypothetical",

91 "命令形": "imperative",

92}

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

95VOICE_TAGS: dict[str, str | list[str]] = {

96 "被動形": "passive",

97 "使役形": "causative",

98 "可能形": "potential",

99 "意志形": "volitional",

100 "否定形": "negative",

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

102 "尊敬形": "formal",

103 "完成形": "perfective",

104 "接續形": "conjunctive",

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

106}

107

108COMPARISON_TAGS: dict[str, str] = {

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

110 "原级": "positive",

111 "比較級": "comparative",

112 "最高級": "superlative",

113}

114

115TENSE_TAGS = {

116 "過去時": "preterite",

117 "過去式": "past",

118 "過去分詞": ["past", "participle"],

119 "現在時": "present",

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

121 "助動詞": "auxiliary",

122 # Template:de-verb

123 "弱變化": "weak",

124 "弱变化": "weak",

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

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

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

128 # Template:it-verb

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

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

131 # Template:de-adj

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

133 # Template:la-verb

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

135 "完成时主动式": ["perfect", "active"],

136 "目的动名词": "supine",

137}

138

139GRAMMATICAL_TAGS: dict[str, str] = {

140 **GENDER_TAGS,

141 **NUMBER_TAGS,

142 **COUNT_TAGS,

143 **OTHER_TAGS,

144 **VERB_TAGS,

145 **JA_STEM_FORMS,

146 **VOICE_TAGS,

147 **COMPARISON_TAGS,

148 **TENSE_TAGS,

149}

150

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

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

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

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

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

156LABEL_TAGS = {

157 "棄用": "obsolete",

158 "弃用": "obsolete",

159 "比喻": "figuratively",

160 "古": "archaic",

161 "陽": "masculine",

162 "陰": "feminine",

163 "喻": "figuratively",

164 "書": "literary",

165 "口": "colloquial",

166 "俚": "slang",

167 "俗": "slang",

168 "方": "dialectal",

169 "废": "obsolete",

170 "貶": "derogatory",

171 "罕": "rare",

172 "引": "broadly",

173 "現已罕用": "archaic",

174 # Module:Labels/data

175 "back slang": "slang",

176 "synecdochically": "synecdoche",

177 "不再自由造詞": "idiomatic",

178 "不及物": "intransitive",

179 "不可數": "uncountable",

180 "不定": "indefinite",

181 "不常見": "uncommon",

182 "不推薦使用": "proscribed",

183 "中性": "neuter",

184 "中間被動語態": "mediopassive",

185 "中間語態": "middle",

186 "主動語態": "active",

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

188 "交互": "reciprocal",

189 "以單數形式": "singular",

190 "以複數形式": "in-plural",

191 "作定語": "attributive",

192 "作格": "ergative",

193 "作表語": "predicative",

194 "使役": "causative",

195 "俗語": "idiomatic",

196 "俚語": "slang",

197 "俚语": "slang",

198 "兒童用語": "childish",

199 "公文": "bureaucratese",

200 "冒犯": "offensive",

201 "分詞": "participle",

202 "前古典": "pre-Classical",

203 "助動詞": "auxiliary",

204 "助記符": "mnemonic",

205 "及物": "transitive",

206 "反問句": "rhetoric",

207 "反身": "reflexive",

208 "口語": "colloquial",

209 "古舊": "archaic",

210 "可數": "countable",

211 "同性戀俚語": ["slang", "LGBT"],

212 "名詞化": "noun-from-verb",

213 "唯單": "singular-only",

214 "唯複": "plural-only",

215 "國際音標": "IPA",

216 "基數詞": "cardinal",

217 "大寫": "capitalized",

218 "委婉": "euphemistic",

219 "字面義": "literally",

220 "完整": "perfect",

221 "完整體": "perfective",

222 "定語": "attributive",

223 "實詞": "substantive",

224 "尊敬": "honorific",

225 "常用複數": "plural-normally",

226 "幽默": "humorous",

227 "序數詞": "ordinal",

228 "廣義來說": "broadly",

229 "引申": "broadly",

230 "弱祈使式": "jussive",

231 "強調": "emphatic",

232 "後古典": "obsolete",

233 "性別中立": "gender-neutral",

234 "情態": "modal",

235 "愛稱": "endearing",

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

237 "押韻俚語": "slang",

238 "抽象名詞": "abstract-noun",

239 "擬態詞": "ideophonic",

240 "擬聲詞": "onomatopoeic",

241 "新詞": "neologism",

242 "方言": "dialectal",

243 "書面": "literary",

244 "有比較級": "comparable",

245 "有生": "animate",

246 "正式": "formal",

247 "歷史": "historical",

248 "比喻義": "figuratively",

249 "無人稱": "impersonal",

250 "無比較級": "not-comparable",

251 "無生": "inanimate",

252 "焦點": "focus",

253 "狹義": "narrowly",

254 "監獄俚語": "slang",

255 "直陳語氣": "indicative",

256 "短信": "Internet",

257 "祈使語氣": "imperative",

258 "禮貌": "polite",

259 "種族歧視語": "slur",

260 "粉絲用語": ["slang", "lifestyle"],

261 "粗俗": "vulgar",

262 "系動詞": "copulative",

263 "網路用語": "Internet",

264 "縮寫": "abbreviation",

265 "罕用": "rare",

266 "臨時語": "nonce-word",

267 "虛擬語氣": "subjunctive",

268 "表語": "predicative",

269 "被動語態": "passive",

270 "視覺方言": "pronunciation-spelling",

271 "親切": "familiar",

272 "詈語": "expletive",

273 "詩歌": "poetic",

274 "誇飾": "excessive",

275 "語中音省略": "syncope",

276 "諷刺": "sarcastic",

277 "謙遜": "humble",

278 "貶義": "derogatory",

279 "轉喻義": "metonymically",

280 "返璞詞": "retronym",

281 "過時": "dated",

282 "陰性": "feminine",

283 "陽性": "masculine",

284 "雙及物動詞": "ditransitive",

285 "靜態動詞": "stative",

286 "非完整": "imperfect",

287 "非完整體": "imperfective",

288 "非常罕用": "rare",

289 "非標準": "nonstandard",

290 "非標準形式": "nonstandard",

291 "非正式": "informal",

292 "首字母縮略詞": "initialism",

293 "駭客語": ["Leet", "Internet"],

294 "高語域": "honorific",

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

296 "修辭學": "rhetoric",

297 "印度教": "Hinduism",

298 "摩門教": "Mormonism",

299 "物理": "particle",

300 "猶太教": "Judaism",

301 "納粹主義": "Nazism",

302 "網際網路": "Internet",

303 "耆那教": "Jainism",

304 "聖經": "Biblical",

305 "解剖學": "anatomy",

306 "貴格會": "Quakerism",

307 "錫克教": "Sikhism",

308 "馬克思主義": "Marxism",

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

310 "喃字": "Chu-Nom",

311 "反身代詞": "reflexive",

312 "字面意義": "literally",

313 "成語": "Chengyu",

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

315 "集合名詞": "collective",

316 "控制動詞": "control-verb",

317 "省略": "ellipsis",

318 "分數": "fractional",

319 "以雙數形式": "dual",

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

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

322 "主要用於肯定": "positive",

323 "古典": "Classical",

324 "中國大陸": "Mainland-China",

325 "書面語": "literary",

326}

327

328# example sentence template

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

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

331ZH_X_TAGS = {

332 "繁體": "Traditional Chinese",

333 "繁體和": "Traditional Chinese",

334 "簡體": "Simplified Chinese",

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

336 "漢語拼音": "Pinyin",

337 "粵拼": "Jyutping",

338 "現代標準漢語": "Standard Chinese",

339 "文言文": "Classical Chinese",

340 "官話白話文": "Written vernacular Chinese",

341 "粵語": "Cantonese",

342 "吳語": "Wu",

343 "廣州話": "Cantonese",

344}

345

346# classifier tags

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

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

349ZH_TAGS = {

350 "官話": "Mandarin",

351 "贛語": "Gan",

352 "客家話": "Hakka",

353 "晉語": "Jin",

354 "閩北語": "Northern Min",

355 "閩東語": "Eastern Min",

356 "閩南語": "Southern Min",

357 "潮州話": "Teochew",

358 "湘語": "Xiang",

359}

360

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

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

363ZH_PRON_TAGS = {

364 "拼音": "Pinyin",

365 "注音": "Bopomofo",

366 "潮州話拼音": "Peng'im",

367 "上海": "Shanghai",

368 "吳語學堂拼音": "Wugniu",

369 "通用拼音": "Tongyong-Pinyin",

370 "威妥瑪拼音": "Wade–Giles",

371 "耶魯官話拼音": "Yale",

372 "國語羅馬字": "Gwoyeu-Romatsyh",

373 "西里爾字母轉寫": "Palladius",

374 "漢語國際音標": "Sinological-IPA",

375 "耶魯粵拼": ["Yale", "Jyutping"],

376 "廣州話拼音": ["Cantonese", "Pinyin"],

377 "廣東拼音": "Guangdong-Romanization",

378 "國際音標": "IPA",

379 "模仿白話字": "POJ",

380}

381

382

383ALL_TAGS = {

384 **GRAMMATICAL_TAGS,

385 **LABEL_TAGS,

386 **ZH_X_TAGS,

387 **ZH_TAGS,

388 **ZH_PRON_TAGS,

389}

390

391

392def translate_raw_tags(data: WordEntry) -> WordEntry:

393 raw_tags = []

394 for raw_tag in data.raw_tags:

395 if raw_tag in ALL_TAGS:

396 tr_tag = ALL_TAGS[raw_tag]

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

398 data.tags.append(tr_tag)

399 elif isinstance(tr_tag, list):

400 data.tags.extend(tr_tag)

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

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

403 else:

404 raw_tags.append(raw_tag)

405 data.raw_tags = raw_tags

406 return data

407

408

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

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

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

412TEMPLATE_TAG_ARGS = {

413 "f": "feminine",

414 "m": "masculine",

415 "n": "neuter",

416 "c": "common",

417 # Animacy

418 "an": "animate",

419 "in": "inanimate",

420 # Animal (for Ukrainian, Belarusian, Polish)

421 "anml": "animal",

422 # Personal (for Ukrainian, Belarusian, Polish)

423 "pr": "personal",

424 # Nonpersonal not currently used

425 "np": "nonpersonal",

426 # Virility (for Polish)

427 "vr": "virile",

428 "nv": "nonvirile",

429 # Numbers

430 "s": "singular number",

431 "d": "dual number",

432 "p": "plural number",

433 # Verb qualifiers

434 "impf": "imperfective",

435 "pf": "perfective",

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

437}