Coverage for src/wiktextract/extractor/de/tags.py: 81%

1from .models import WordEntry

3# Sense tags

4# https://de.wiktionary.org/wiki/Vorlage:K

5# https://de.wiktionary.org/wiki/Vorlage:K/Abk

6K_TEMPLATE_TAGS = {

7 "Abl.": "ablative",

8 "Ablativ": "ablative",

9 "abw.": "derogatory",

10 "abwertend": "derogatory",

11 "AE": "US",

12 "AmE": "US",

13 "adv.": "adverbial",

14 "Akkusativ": "accusative",

15 "alemann.": "Alemannic",

16 "alemannisch": "Alemannic",

17 "allg.": "general",

18 "allgemein": "general",

19 "alltagsspr.": "colloquial",

20 "amtsspr.": "officialese",

21 # "ansonsten": "otherwise", # combined with other text

22 "attr.": "attributive",

23 # "auch": "also",

24 "bair.": "Bavarian",

25 "bairisch": "Bavarian",

26 "bar.": "Bavarian",

27 "direktional": "directional",

28 "BE": "British",

29 "BrE": "British",

30 "Bedva.": "outdated",

31 "Bedvatd.": "outdated",

32 "besonders": "especially",

33 "veraltende Bedeutung": "outdated",

34 # "bei": "",

35 # "bes.": "especially",

36 # "besonders": "especially",

37 # "beziehungsweise": "",

38 # "bzw.": "",

39 # "bildungsspr.": "",

40 # "bis": "",

41 # "bisweilen": "",

42 # "das": "",

43 "Dativ": "dative",

44 # "DDR": "",

45 "Deutschland": "Germany",

46 # "der": "",

47 "dichter.": "poetic",

48 "dichterisch": "poetic",

49 # "die": "",

50 "Dim.": "diminutive",

51 "Dimin.": "diminutive",

52 "Diminutiv": "diminutive",

53 # "eher": "",

54 "erzg.": "Erzgebirgisch",

55 "erzgeb.": "Erzgebirgisch",

56 "erzgebirgisch": "Erzgebirgisch",

57 "euph.": "euphemistic",

58 "fachspr.": "jargon",

59 "fachsprachlich": "jargon",

60 "fam.": "familiär",

61 "fig": "figurative",

62 "fig.": "figurative",

63 # "früher": "",

64 # "gegenwartslateinisch": "",

65 "geh.": "gehoben",

66 "Genitiv": "genitive",

67 "gsm": "Swiss German",

68 "häufig": "often",

69 "haben": "auxiliary",

70 "hebben": "auxiliary",

71 "hauptsächlich": "primarily",

72 "hist.": "historical",

73 "ieS": "narrowly",

74 "i.e.S.": "narrowly",

75 "i. e. S.": "narrowly",

76 # "im": "",

77 # "in": "",

78 # "in Bezug auf": "relational",

79 "indekl.": "indeclinable",

80 # "insbes.": "",

81 "Instrumental": "instrumental",

82 "intrans.": "intransitive",

83 "intransitiv": "intransitive",

84 # "iPl": "in plural",

85 "iron.": "ironic",

86 # "iwS": "",

87 # "jugendspr.": "",

88 "kinderspr.": "childish",

89 "kirchenlateinisch": "Church Latin",

90 "klasslat.": "Classical Latin",

91 "klassischlateinisch": "Classical Latin",

92 "kPl.": "no-plural",

93 "kein Plural": "no-plural",

94 "kSg.": "no-singulative",

95 "kSt.": "no-comparative",

96 "kurz für": "short-form",

97 "landsch.": "regional",

98 "landschaftlich": "regional",

99 "lautm.": "onomatopoeic",

100 "lokal": "regional",

101 "Ling.": "linguistics",

102 "mA": "accusative",

103 "md.": "Central German",

104 "mdal.": "dialectal",

105 "Med.": "medicine", # topic

106 # "meist": "mostly",

107 # "meistens": "mostly",

108 "metaphor.": "metaphoric",

109 "meton.": "metonymically",

110 "mG": "genitive",

111 "mitteld.": "Central German",

112 "mit Dativ": "with-dative",

113 "mit Akkusativ": "with-accusative",

114 # "mitunter": "",

115 "mlat.": "Medieval Latin",

116 "mittellateinisch": "Medieval Latin",

117 "mundartl.": "dialectal",

118 "nDu.": "only-dual",

119 "nigr.": "Niger",

120 "nigrisch": "Niger",

121 "nkLat.": "post-Classical Latin",

122 "nachklassischlateinisch": "post-Classical Latin",

123 "nlat.": "New Latin",

124 "neulateinisch": "New Latin",

125 "nordd.": "North German",

126 "norddeutsch": "North German",

127 "nordwestd.": "Northwestern Germany",

128 "nPl.": "plural-only",

129 "Österreich": "Austrian German",

130 "örtlich": "regional",

131 "österr.": "Austrian German",

132 "österreichisch": "Austrian German",

133 "ostfränkisch": "East Franconian German",

134 "pej.": "pejorative",

135 "personifizierend": "person",

136 "poet.": "poetic",

137 "PräpmG": "genitive prepositional",

138 "PmG": "genitive prepositional",

139 "reg.": "regional",

140 "refl.": "reflexive",

141 "reflexiv": "reflexive",

142 # "respektive": "",

143 "sal.": "casual",

144 "salopp": "casual",

145 "scherzh.": "jocular",

146 "schriftspr.": "literary",

147 # "schülerspr.": "",

148 "schwäb.": "Swabian",

149 "schwäbisch": "Swabian",

150 "Schweiz": "Swiss Standard German",

151 "schweiz.": "Swiss Standard German",

152 "schweizerisch": "Swiss Standard German",

153 "Schweizerdeutsch": "Swiss German",

154 "schweizerdeutsch": "Swiss German",

155 # "seemannsspr.": "",

156 "sein": "auxiliary verb",

157 # "sehr": "", # very

158 "selten": "rare",

159 "seltener": "rare",

160 "seltener auch": "rare",

161 "soldatenspr.": ["military", "slang"],

162 # "sonderspr.": "",

163 # "sonst": "",

164 # "sowie": "",

165 "spätlat.": "Late Latin",

166 "spätlateinisch": "Late Latin",

167 # "später": "",

168 "speziell": "special",

169 "südd.": "South German",

170 "süddt.": "South German",

171 # "techn.": "",

172 # "teils": "",

173 # "teilweise": "",

174 "temporal": "temporal",

175 "tlwva.": "outdated",

176 "tlwvatd.": "outdated",

177 "trans.": "transitive",

178 "transitiv": "transitive",

179 # "über": "",

180 # "überwiegend": "mostly",

181 "übertr.": "figurative",

182 "übertragen": "figurative",

183 "ugs.": "colloquial",

184 "umgangssprachlich": "colloquial",

185 # "und": "",

186 "ungebr.": "uncommon",

187 "unpers.": "impersonal",

188 "unpersönlich": "impersonal",

189 # "ursprünglich": "",

190 "va.": "outdated",

191 "vatd.": "outdated",

192 "veraltend": "outdated",

193 # "verh.": "",

194 "volkst.": "popular",

195 # "von": "",

196 # "vor allem": "",

197 # "vor allem in": "",

198 "vul.": "vulgar",

199 "vulg.": "vulgar",

200 "vlat.": ["vulgar", "Latin"],

201 "vulgärlat": ["vulgar", "Latin"],

202 "vulgärlateinisch": ["vulgar", "Latin"],

203 "wien.": "Vienna",

204 "wienerisch": "Vienna",

205 "Wpräp": "prepositional",

206 # "z. B.": "",

207 # "z. T.": "",

208 # "zijn": "",

209 # "zum Beispiel": "",

210 # "zum Teil": "",

211 # "zumeist": "",

212 "Kardinalzahl": "cardinal",

213 "Sammelbegriff": "collective",

214 "Fachsprache": "jargon",

215 "formale Sprachen": "formal",

216 "Programmiersprachen": "programming",

217 "Rechnerarchitektur": "programming",

218 "Geografie": "geography",

219 "Geometrie": "geometry",

220 "Finanzwesen": "finance",

221 "juristisch": "law",

222 "Physik": "physics",

223 "abstrakt": "abstract",

224 "gegenständlich": "objective",

225 "personifiziert": "personal",

226 "kirchlich": "Ecclesiastical",

227}

228

229GENDER_TAGS = {

230 "n": "neuter",

231 "m": "masculine",

232 "f": "feminine",

233 # Vorlage:Deklinationsseite Adjektiv

234 "Maskulinum": "masculine",

235 "Femininum": "feminine",

236 "Neutrum": "neuter",

237}

238

239NUMBER_TAGS = {

240 # Vorlage:Deutsch Substantiv Übersicht

241 "Singular": "singular",

242 "Plural": "plural",

243 "Pl.": "plural",

244 "Dual": "dual",

245}

246

247CASE_TAGS = {

248 # Vorlage:Deutsch Substantiv Übersicht

249 "Nominativ": "nominative",

250 "Genitiv": "genitive",

251 "Dativ": "dative",

252 "Akkusativ": "accusative",

253 # Template:Polnisch Substantiv Übersicht

254 "Lokativ": "locative",

255 "Vokativ": "vocative",

256 "Dativ Singular": ["dative", "singular"],

257 "Genitiv Singular": ["genitive", "singular"],

258 # Template:Finnisch Substantiv Übersicht

259 "Inessiv": "inessive",

260 "Elativ": "elative",

261 "Illativ": "illative",

262 "Adessiv": "adessive",

263 "Allativ": "allative",

264 "Essiv": "essive",

265 "Translativ": "translative",

266 "Abessiv": "abessive",

267 "Instruktiv": "instructive",

268 "Komitativ": "comitative",

269}

270

271COMPARISON_TAGS = {

272 # Vorlage:Deutsch Adjektiv Übersicht

273 # Vorlage:Deklinationsseite Adjektiv

274 "Positiv": "positive",

275 "Komparativ": "comparative",

276 "Superlativ": "superlative",

277}

278

279DECLENSION_TAGS = {

280 # https://en.wikipedia.org/wiki/German_declension

281 # Vorlage:Deklinationsseite Adjektiv

282 "Starke Deklination": "strong",

283 "Schwache Deklination": "weak",

284 "Gemischte Deklination": "mixed",

285}

286

287OTHER_TAGS = {

288 # Vorlage:Deklinationsseite Adjektiv

289 "Prädikativ": "predicative",

290 "erweiterte": "extended",

291 "Höflichkeitsform": "honorific",

292 # Vorlage:Deutsch Verb schwach untrennbar reflexiv

293 "nichterweitert": "not-extended",

294 "erweitert": "extended",

295 "zeitlich": "temporal",

296 "indeklinabel": "indeclinable",

297 "östlich": "Eastern",

298 "westlich": "Western",

299 "britisch": "British",

300 "Substantive": "noun",

301 "Substantiv": "noun",

302 "historisch": "historical",

303 "wörtlich": "literally",

304 "Adjektiv": "adjective",

305 "gehoben": "literary",

306 "Nebenform von": "variant",

307 "Verben": "verb",

308 "regional": "regional",

309 # Vorlage:CH&LI

310 "Schweiz und Liechtenstein": ["Switzerland", "Liechtenstein"],

311 "Switzerland and Liechtenstein": ["Switzerland", "Liechtenstein"],

312 "traditionell": "traditional",

313 "vereinfachte Schreibweise": "simplified",

314}

315

316TENSE_TAGS = {

317 # Vorlage:Deutsch Verb Übersicht

318 "Präsens": "present",

319 "Präteritum": "past",

320 "Perfekt": "perfect",

321 "Futur I": "future-i",

322 "Futur II": "future-ii",

323 "Plusquamperfekt": "pluperfect",

324 # Template:Kroatisch Verb Übersicht

325 "perfektiv": "perfective",

326 "imperfektiv": "imperfective",

327 "Imperfekt": "imperfect",

328}

329

330MOOD_TAGS = {

331 # Vorlage:Deutsch Verb Übersicht

332 # Vorlage:Deutsch Verb regelmäßig

333 "Konjunktiv I": "subjunctive-i",

334 "Konjunktiv II": "subjunctive-ii",

335 "Imperativ": "imperative",

336 "Imperative": "imperative",

337 "Indikativ": "indicative",

338}

339

340VERB_FORM_TAGS = {

341 # Vorlage:Deutsch Verb Übersicht

342 "Partizip II": "participle-2",

343 "Hilfsverb": "auxiliary",

344 "Infinitive": "infinitive",

345 "Infinitiv": "infinitive",

346 "Partizipien": "participle",

347 "unregelmäßig": "irregular",

348 "Aorist": "aorist",

349 # Template:Dänisch Verb Übersicht

350 "Partizip Perfekt": ["participle", "perfect"],

351}

352

353VOICE_TAGS = {

354 # Vorlage:Deutsch Verb unregelmäßig

355 "Aktiv": "active",

356 "Vorgangspassiv": "processual-passive",

357 "Zustandspassiv": "statal-passive",

358 "Passiv": "passive",

359 "Gerundivum": "gerundive",

360 # Vorlage:Deutsch Verb schwach untrennbar reflexiv

361 "Zustandsreflexiv": "statal-reflexive",

362}

363

364PERSON_TAGS = {

365 # Vorlage:Deutsch Verb unregelmäßig

366 "1. Person Singular": ["first-person", "singular"],

367 "1. Person Plural": ["first-person", "plural"],

368 "2. Person Singular": ["second-person", "singular"],

369 "2. Person Plural": ["second-person", "plural"],

370 "3. Person Singular": ["third-person", "singular"],

371 "3. Person Plural": ["third-person", "plural"],

372 # Vorlage:Deutsch Verb schwach untrennbar reflexiv

373 "Sg. 1. Pers.": ["first-person", "singular"],

374 "Pl. 1. Pers.": ["first-person", "plural"],

375 "Sg. 2. Pers.": ["second-person", "singular"],

376 "Pl. 2. Pers.": ["second-person", "plural"],

377 "Sg. 3. Pers.": ["third-person", "singular"],

378 "Pl. 3. Pers.": ["third-person", "plural"],

379}

380

381INFLECTION_TABLE_TAGS = {

382 # Vorlage:Deutsch Verb regelmäßig

383 "ungebräuchlich": "uncommon",

384 "veraltet": "archaic",

385 # Vorlage:Deutsch Verb schwach trennbar reflexiv

386 "Nebensatzkonjugation": "subordinate-clause",

387 "Hauptsatzkonjugation": "main-clause",

388 "regelmäßig": "regular",

389 "untrennbar": "inseparable",

390 "trennbar": "separable",

391 # Vorlage:Deutsch Nachname Übersicht

392 "Singular m": ["singular", "masculine"],

393 "Singular f": ["singular", "feminine"],

394 # Vorlage:Deklinationsseite Numerale

395 "bestimmt": "definite",

396 "unbestimmt": "indefinite",

397 "mit Possessivpronomen": ["possessive", "pronoun"],

398 # Template:Kroatisch Verb Übersicht

399 "Partizip Präteritum Aktiv": ["past", "participle", "active"],

400}

401

402GRAMMATICAL_TAGS = {

403 **K_TEMPLATE_TAGS,

404 **GENDER_TAGS,

405 **NUMBER_TAGS,

406 **CASE_TAGS,

407 **COMPARISON_TAGS,

408 **DECLENSION_TAGS,

409 **OTHER_TAGS,

410 **TENSE_TAGS,

411 **MOOD_TAGS,

412 **VERB_FORM_TAGS,

413 **VOICE_TAGS,

414 **PERSON_TAGS,

415 **INFLECTION_TABLE_TAGS,

416}

417

418K_TEMPLATE_TOPICS = {

419 "Biologie": "biology",

420 "Linguistik": "linguistics",

421 "Wortbildung": "morphology",

422 "Behörde": "government",

423 "Astronomie": "astronomy",

424 "Immobilienbranche": "real-estate",

425 "Kunst": "arts",

426 "Informatik": "computing",

427 "Nautik": "nautical",

428 "Sport": "sports",

429 "Schuhwerk": "footwear",

430 "Textilien": "textiles",

431 "Zahlungsmittel": "payment-method",

432 "Ökologie": "ecology",

433 "Internet": "Internet",

434 "Religion": "religion",

435 "Militärsprache": "military",

436 "Systematik": "systematics",

437 "Zoologie": "zoology",

438 "Seefahrt": "seafaring",

439 "Soldatensprache": {"topic": "military", "tag": "slang"},

440 "Botanik": "botany",

441 "Marine": "navy",

442 "Informationstechnologie": "computing",

443 "Betriebswirtschaftslehre": "business",

444 "Recht": "law",

445 "Elektronik": "electronics",

446 "Emotion": "emotion",

447 "Mathematik": "mathematics",

448 "Bürgerliches Recht": "civil-Law",

449 "Militär": "military",

450 "Politik": "politics",

451 "Werkzeug": "tools",

452 "Medizin": "medicine",

453 "Ornithologie": "ornithology",

454 "Technik": "technology",

455 "Waffentechnik": "weaponry",

456 "Anatomie": "anatomy",

457 "Fußball": "football",

458 "Kartenspiel": "card-games",

459 "Theoretische Informatik": "computing",

460 "militärisch": "military",

461 "Taxonomie": "taxonomy",

462}

463

464

465def translate_raw_tags(data: WordEntry) -> None:

466 raw_tags = []

467 for raw_tag in data.raw_tags:

468 if raw_tag in GRAMMATICAL_TAGS:

469 tag = GRAMMATICAL_TAGS[raw_tag]

470 if isinstance(tag, str) and tag not in data.tags:

471 data.tags.append(tag)

472 elif isinstance(tag, list): 472 ↛ 467line 472 didn't jump to line 467 because the condition on line 472 was always true

473 for t in tag:

474 if t not in data.tags: 474 ↛ 473line 474 didn't jump to line 473 because the condition on line 474 was always true

475 data.tags.append(t)

476 elif raw_tag in K_TEMPLATE_TOPICS and hasattr(data, "topics"):

477 topic = K_TEMPLATE_TOPICS[raw_tag]

478 if isinstance(topic, str) and topic not in data.topics: 478 ↛ 480line 478 didn't jump to line 480 because the condition on line 478 was always true

479 data.topics.append(topic)

480 elif isinstance(topic, dict) and topic["topic"] not in data.topics:

481 data.topics.append(topic["topic"])

482 if topic["tag"] not in data.tags:

483 data.tags.append(topic["tag"])

484 else:

485 raw_tags.append(raw_tag)

486 data.raw_tags = raw_tags