Coverage for src/wiktextract/extractor/nl/tags.py: 85%

1from .models import WordEntry

3# https://nl.wiktionary.org/wiki/Categorie:Lemmasjablonen

4# https://nl.wiktionary.org/wiki/Categorie:Werkwoordsjablonen

5GLOSS_TAG_TEMPLATES = frozenset(

6 [

7 "absol",

8 "accus",

9 "auxl",

10 "copl",

11 "deponens",

12 "ditr",

13 "erga",

14 "inerg",

15 "intr",

16 "modl",

17 "onpr",

18 "ov",

19 "rcpq",

20 "refl",

21 "s-verb",

22 "plurt",

23 "singt",

24 "versterkend voorvoegsel",

25 ]

26)

29# https://nl.wiktionary.org/wiki/Categorie:Werkwoordsjablonen

30# https://nl.wiktionary.org/wiki/Categorie:WikiWoordenboek:Contextlabels

31GLOSS_TAGS = {

32 "figuurlijk": "figuratively",

33 "afkorting": "abbreviation",

34 "causatief": "causative",

35 # "chattaal": "",

36 "dichterlijk": "poetic",

37 "eufemisme": "euphemistic",

38 "familienaam": "surname",

39 "formeel": "formal",

40 "gezegde": "proverb",

41 # "heteroniem": "heteronym",

42 "historisch": "historical",

43 "informeel": "informal",

44 "initiaalwoord": "acronym",

45 # "klemtoonhomogram": "",

46 "krachtterm": "vulgar",

47 # "leesteken": "punctuation",

48 "letterwoord": "acronym",

49 "middeleeuwen": "Middle-Ages",

50 "vrouwelijke naam": ["feminine", "name"],

51 "mannelijke naam": ["masculine", "name"],

52 "mannelijke en vrouwelijke naam": ["masculine", "feminine", "name"],

53 "neologisme": "neologism",

54 "oudheid": "archaic",

55 # "palindroom": "palindrome",

56 "pejoratief": "pejorative",

57 "persoon": "person",

58 # "pregnant": "extra meaning",

59 "samenkoppeling": "compound",

60 # "sanitair": "",

61 "scheldwoord": "pejorative",

62 "schertsend": "humorous",

63 "spottend": "ironic",

64 "spreektaal": "vernacular",

65 "spreekwoord": "proverb",

66 # "stopwoord": "filled pause",

67 "straattaal": "slang",

68 "streektaal": "regiolectal",

69 "taal": "linguistics",

70 "toponiem": "toponymic",

71 "verkorting": "clipping",

72 "verouderd": "obsolete",

73 "Vroegnieuwnederlands": "Early-Modern-Dutch",

74 "vulgair": "vulgar",

75 "zegswijze": "idiomatic",

76 "zeldzaam": "rare",

77 "Latijns-Amerika": "Latin-America",

78 "absoluut": "absolute", # Sjabloon:absol

79 "accusatief": "accusative", # Sjabloon:accus

80 "hulpwerkwoord": "auxiliary", # Sjabloon:auxl

81 "koppelwerkwoord": "copulative", # Sjabloon:copl

82 "deponens": "deponent",

83 "ditransitief": "ditransitive", # Sjabloon:ditr

84 "ergatief": "ergative", # Sjabloon:erga

85 "inergatief": "unergative", # Sjabloon:inerg

86 "onovergankelijk": "intransitive", # Sjabloon:intr

87 "modaal werkwoord": ["modal", "verb"], # Sjabloon:modl

88 "onpersoonlijk": "impersonal", # Sjabloon:onpr

89 "overgankelijk": "transitive", # Sjabloon:ov

90 "wederkerig": "reciprocal", # Sjabloon:rcpq

91 "wederkerend": "reflexive", # Sjabloon:refl

92 "alleen meervoud": "plural-only", # Sjabloon:plurt

93 "geen meervoud": "no-plural", # Sjabloon:singt

94 "versterkend voorvoegsel": ["intensifier", "prefix"],

95 "in een bijzin": "with-subordinate-clause", # Sjabloon:ovt-mv-bijz

96 "bij inversie": "inversion", # Sjabloon:1ps

97}

99TABLE_TAGS = {

100 # Sjabloon:-nlnoun-

101 "enkelvoud": "singular",

102 "meervoud": "plural",

103 "verkleinwoord": "diminutive",

104 "bezitsvorm": "possessive",

105 # Sjabloon:adjcomp

106 "stellend": "positive",

107 "vergrotend": "comparative",

108 "overtreffend": "superlative",

109 "onverbogen": "uninflected",

110 "verbogen": "inflected",

111 "partitief": "partitive",

112 # Sjabloon:-nlverb-

113 "onbepaalde wijs": "infinitive",

114 "kort": "short-form",

115 "onvoltooid": "imperfect",

116 "tegenwoordig": "present",

117 "toekomend": "future",

118 "voltooid": "perfect",

119 "onvoltooid deelwoord": ["imperfect", "participle"],

120 "voltooid deelwoord": ["past", "participle"],

121 "gebiedende wijs": "imperative",

122 "aanvoegende wijs": "subjunctive",

123 "aantonende wijs": "indicative",

124 "eerste": "first-person",

125 "tweede": "second-person",

126 "derde": "third-person",

127 "verleden": "past",

128 "voorwaardelijk": "conditional",

129 "hoofdzin": "main-clause",

130 "bijzin": "subordinate-clause",

131 # Sjabloon:-nlname-

132 "nominatief": "nominative",

133 "genitief": "genitive",

134 # Sjabloon:-denoun-

135 "datief": "dative",

136 "accusatief": "accusative",

137 # Sjabloon:-nlverb-reflex-

138 "tegenwoordige tijd": "present",

139 "verleden tijd": "past",

140 "toekomende tijd": "future",

141 "1": "first-person",

142 "2": "second-person",

143 "3": "third-person",

144 "voltooide tijd": "past",

145 # Sjabloon:-dumverb-

146 "onv. deelwoord": ["imperfect", "participle"],

147 "volt deelwoord": ["past", "participle"],

148 "aantonend": "indicative",

149 "aanvoegend": "subjunctive",

150}

151

152

153HEADER_LINE_TAGS = {

154 "dim. tant.": ["diminutive", "noun"], # Sjabloon:dimt

155}

156

157

158TAGS = {**GLOSS_TAGS, **TABLE_TAGS, **HEADER_LINE_TAGS}

159

160# https://nl.wiktionary.org/wiki/Categorie:WikiWoordenboek:Contextlabels

161TOPICS = {

162 "aardrijkskunde": "geography",

163 "adel": "nobility",

164 "anatomie": "anatomy",

165 "antropologie": "anthropology",

166 "archeologie": "archaeology",

167 "astrologie": "astrology",

168 "astronomie": "astronomy",

169 # "bacteriën": "bacterium",

170 # "badminton": "badminton",

171 "basketbal": "basketball",

172 "bedrijf": "business",

173 "bedrijfskunde": "business", # "business administration",

174 # "bedrijfstak": "industrial branch",

175 "beeldhouwkunst": "arts", # "sculpting"

176 # "beroep": "profession",

177 "beschrijvende plantkunde": "botany", # "descriptive botany"

178 # "bidsprinkhanen": "mantises",

179 "biochemie": "biochemistry",

180 "biologie": "biology",

181 "bloemplanten": "botany",

182 "boekbinderij": "bookbinding",

183 "boekhouding": "accounting",

184 "bosbouw": "forestry",

185 "bouwkunde": "architecture",

186 # "breukgetal": "",

187 "bridge": "bridge",

188 # "buideldieren": "marsupial",

189 # "buikpotigen": "",

190 # "buissnaveligen": "",

191 # "buistandigen": "",

192 # "cloacadieren": "monotreme",

193 "communicatie": "communications",

194 # "coniferen": "conifers",

195 "cosmetica": "cosmetics",

196 "cryptografie": "cryptography",

197 # "cultuur": "culture",

198 "dag": "weekday",

199 "dans": "dance",

200 "demografie": "demography",

201 "demoniem": "demonym",

202 "dichtkunst": "poetry",

203 # "dierengeluid": "animal sound",

204 "diergeneeskunde": ["veterinary", "medicine"],

205 "dierkunde": "zoology",

206 # "dierluizen": "",

207 "diplomatie": "diplomacy",

208 "drinken": "beverages",

209 # "duifachtigen": "",

210 # "duikers": "",

211 # "dysfemisme": "dysphemism",

212 "ecologie": "ecology",

213 "economie": "economics",

214 # "eendvogels": "anseriform",

215 "eenheid": "units-of-measure",

216 "effectenhandel": "trading",

217 "egyptologie": "Egyptology",

218 # "toponiem: eiland": "",

219 "elektronica": "electronics",

220 "elektrotechniek": "electrical-engineering",

221 # "element": "element",

222 "emotie": "emotion",

223 # "evenhoevigen": "",

224 "familie": "familiar",

225 "farmacologie": "pharmacology",

226 # "feest": "party",

227 "fietsen": "cycling",

228 "filatelie": "philately",

229 "filmkunst": "cinematography",

230 "filosofie": "philosophy",

231 "financieel": "financial",

232 # "flamingoachtigen": "",

233 "folklore": "folklore",

234 "fotografie": "photography",

235 # "fruit": "fruit",

236 # "futen": "grebe",

237 "fysiologie": "physiology",

238 "genetica": "genetics",

239 # "gentachtigen": "",

240 "geologie": "geology",

241 "geopolitiek": "geopolitics",

242 "gereedschap": "tools",

243 "geschiedenis": "history",

244 "glaciologie": "glaciology",

245 # "godheid": "deity",

246 # "graan": "grain",

247 "grammatica": "grammar",

248 "groente": "vegetable",

249 # "grondmechanica": "",

250 "haar": "hairstyle",

251 "handel": "business",

252 "heraldiek": "heraldry",

253 "hobby": "hobbies",

254 "hoofddeksel": "headgear",

255 # "horeca": "",

256 "houtbewerking": "woodworking",

257 # "huishouden": "housekeeping",

258 "imkerij": "beekeeping",

259 # "industrie": "industry",

260 "informatica": "computer sciences",

261 "internet": "Internet",

262 # "jaarwisseling": "",

263 "jachttaal": "hunting",

264 # "jongerentaal": "",

265 "juridisch": "legal",

266 "kaartspel": "card-games",

267 # "kamperen": "camping",

268 # "kerst": "Christmas",

269 # "kindertaal": "child language",

270 "kleding": "clothing",

271 "kleur": "colour",

272 # "knutselen": "",

273 "kookkunst": "culinary",

274 # "krachtsport": "",

275 "kristallografie": "crystallography",

276 # "kruid": "",

277 # "kuiperij": "",

278 "kunst": "arts",

279 "landbouw": "agriculture",

280 "landmeetkunde": "surveying",

281 "leenstelsel": "feudalism",

282 # "leerbewerking": "",

283 # "leidekkerij": "",

284 "letterkunde": "literature",

285 "lhbt": "LGBT",

286 "logica": "logic",

287 "luchtvaart": "aviation",

288 # "maatschappij": "company",

289 # "magie": "magic",

290 "makelaardij": "real-estate",

291 # "materiaalkunde": "materials science",

292 # "media": "",

293 "medisch": "medicine",

294 # "meer": "lake",

295 "meetkunde": "geometry",

296 "metaalbewerking": "metalworking",

297 "metallurgie": "metallurgy",

298 "klimatologie": "climatology",

299 "meteorologie": "meteorology",

300 # "metonymisch": "",

301 "meubel": "furniture",

302 "mijnbouw": "mining",

303 "milieukunde": "ecology",

304 "militair": "military",

305 "mineraal": "mining",

306 "mineralogie": "mineralogy",

307 # "misdaad": "crime",

308 "mode": "fashion",

309 # "molenaarsambacht": "",

310 "muziek": "music",

311 "muziekinstrument": "music",

312 "mycologie": "mycology",

313 "mythologie": "mythology",

314 "natuurkunde": "physics",

315 "neurologie": "neurology",

316 "numismatiek": "numismatics",

317 "oenologie": "oenology",

318 "onderwijs": "education",

319 "oorlog": "war",

320 "optica": "optics",

321 "ordehandhaving": "law enforcement",

322 # "paardrijden": "horseriding",

323 # "planologie": "planology",

324 "plantkunde": "botany",

325 "politiek": "politics",

326 "post": "mail",

327 "psychologie": "psychology",

328 "regering": "government",

329 "religie": "religion",

330 # "ruimtevaart": "space travel",

331 "schaak": "chess",

332 "scheepvaart": "shipping",

333 "scheikunde": "chemistry",

334 # "schilderkunst": "painting",

335 # "schoeisel": "shoewear",

336 "scouting": "scouting",

337 "seismologie": "seismology",

338 "seksualiteit": "sexuality",

339 "sieraad": "jewellery",

340 # "slapen": "sleep",

341 # "snoepgoed": "candy",

342 "sociologie": "sociology",

343 # "specerij": "spice",

344 "speelgoed": "toys",

345 "spel": "games",

346 # "spellingsalfabet": "spelling alphabet",

347 "spoorwegen": "railways",

348 "sport": "sports",

349 "statistiek": "statistics",

350 # "sterrenbeeld": "constellation",

351 "valutanaam": "money",

352 "taalkunde": "linguistics",

353 "tandheelkunde": "dentistry",

354 "techniek": "technology",

355 # "teken- en schrijfmateriaal": "",

356 "tekstkritiek": "textual criticism",

357 "telecommunicatie": "telecommunications",

358 "tennis": "tennis",

359 "textiel": "textiles",

360 "textielindustrie": "textiles",

361 "thermodynamica": "thermodynamics",

362 # "tijdrekening": "timekeeping",

363 "toerisme": "tourism",

364 "toneel": "theater",

365 "transport": "transport",

366 "tuinbouw": "horticulture",

367 # "tuinieren": "gardening",

368 "typografie": "typography",

369 "valkerij": "falconry",

370 # "veeteelt": "husbandry",

371 "verkeer": "traffic",

372 "visserij": "fishing",

373 "voeding": "food",

374 "voetbal": "football",

375 "volleybal": "volleyball",

376 # "waterbeheer": "water management",

377 "wegenbouw": ["road", "construction"],

378 "werelddeel": "continents",

379 "werktuigbouwkunde": "mechanical-engineering",

380 "wetenschap": "sciences",

381 "wielrennen": "cycling",

382 # "Wikimedia": "Wikimedia",

383 # "wikitaal": "",

384 # "windstreek": "",

385 # "wintersport": "",

386 "wiskunde": "mathematics",

387 # "wonen": "",

388 "zoötomie": "zootomy",

389 "zwemmen": "swimming",

390}

391

392

393def translate_raw_tags(data: WordEntry) -> None:

394 raw_tags = []

395 for raw_tag in data.raw_tags:

396 if raw_tag in TAGS:

397 tr_tag = TAGS[raw_tag]

398 if isinstance(tr_tag, str):

399 data.tags.append(tr_tag)

400 elif isinstance(tr_tag, list): 400 ↛ 395line 400 didn't jump to line 395 because the condition on line 400 was always true

401 data.tags.extend(tr_tag)

402 elif raw_tag in TOPICS and hasattr(data, "topics"):

403 tr_topic = TOPICS[raw_tag]

404 if isinstance(tr_topic, str): 404 ↛ 406line 404 didn't jump to line 406 because the condition on line 404 was always true

405 data.topics.append(tr_topic)

406 elif isinstance(tr_topic, list):

407 data.topics.extend(tr_topic)

408 else:

409 raw_tags.append(raw_tag)

410 data.raw_tags = raw_tags

411

412

413# used in translation, linkage and gloss lists

414LIST_ITEM_TAG_TEMPLATES = {

415 "m": "masculine",

416 "f": "feminine",

417 "n": "neuter",

418 "c": "common",

419 "s": "singular",

420 "p": "plural",

421 "a": "animate",

422 "i": "inanimate",

423 "impf": "imperfective",

424 "pf": "perfective",

425}