Coverage for src/wiktextract/extractor/es/tags.py: 86%

1from .models import WordEntry

3# https://es.wiktionary.org/wiki/Wikcionario:Lista_de_etiquetas

5# https://es.wiktionary.org/wiki/Plantilla:uso

6USO_TAGS = {

7 "académico": "academic",

8 "afectado": "literary",

9 # "afectuoso": "affectionate",

10 "anticuado": "outdated",

11 "antiguo": "obsolete",

12 "arcaico": "obsolete",

13 "arcaizante": "obsolete",

14 "arcaísmo": "obsolete",

15 "bajo": "colloquial",

16 "chistoso": "jocular",

17 "coloq": "colloquial",

18 "coloq.": "colloquial",

19 "coloquial": "colloquial",

20 # "culto": "worship",

21 "cómico": "jocular",

22 "despect.": "derogatory",

23 "despectivo": "derogatory",

24 "desus": "outdated",

25 "desus.": "outdated",

26 "desusada": "outdated",

27 "desusado": "outdated",

28 "elevado": "literary",

29 "epiceno": "epicene",

30 "eufemismo": "euphemism",

31 "eutca": "adjective",

32 "familiar": "colloquial",

33 "figurado": "figurative",

34 "formal": "formal",

35 "germanía": "slang",

36 "grosero": "vulgar",

37 "humorístico": "jocular",

38 "infantil": "childish",

39 "informal": "colloquial",

40 "infrecuente": "rare",

41 "irónico": "ironic",

42 "jerga": "slang",

43 # "jerga legal": "legal jargon",

44 # "jerga metalera": "metal slang",

45 # "jerga skinhead": "skinhead slang",

46 "jergal": "slang",

47 "jocoso": "jocular",

48 "literario": "literary",

49 "malsonante": "vulgar",

50 # "mayúscula": "capital letter",

51 # "mayúscula disciplinas": "usually lowercase",

52 # "mayúscula puntos cardinales":

53 # "It is lowercase except when it is part of a proper noun",

54 # "mayúscula taxones": "taxonomy rules for capitalization",

55 "medieval": "Medieval",

56 "minúscula": "lower case",

57 "neologismo": "neologism",

58 "obsoleto": "obsolete",

59 # "ordinal compuesto": "rules for compound ordinal numbers",

60 # "ordinal-compuesto": "rules for compound ordinal numbers",

61 "peyorativo": "derogatory",

62 "poco frecuente": "rare",

63 "poco usado": "rare",

64 "popular": "colloquial",

65 "poético": "literary",

66 "raro": "rare",

67 # "rur": "rural",

68 # "rural": "rural",

69 "sebtc": "noun",

70 "setc": "noun",

71 # "sin uso": "The editors have been unable to find any examples of use of

72 # this word in published texts or corpus",

73 "slang": "slang",

74 "soez": "vulgar",

75 "sutp": "plural",

76 "suts": "singular",

77 # "trans-prefijo": "",

78 "ucsp": ["plural", "noun"],

79 "umcp": "pronominal",

80 "umcs": "noun",

81 "umcv": "vocative",

82 "umep": "plural",

83 "umpl": "plural",

84 "utca": "adjective",

85 "utcadv": "adverb",

86 "utcaf": ["feminine", "adjective"],

87 "utcam": ["masculine", "adjective"],

88 "utcc": "conjunction",

89 "utcf": ["feminine", "noun"],

90 "utcg": "gerund",

91 # "utci": "It is also used as intransitive",

92 "utcm": ["masculine", "noun"],

93 "utcp": "pronominal",

94 "utcprnl": "pronominal",

95 "utcs": "noun",

96 "utcsf": ["feminine", "noun"],

97 "utcsm": ["masculine", "noun"],

98 "utcsma": ["masculine", "feminine", "noun"],

99 "utcsmf": "noun",

100 "utct": "transitive",

101 "utmp": ["pronominal", "verb"],

102 "utrep": "repeated",

103 "vulg": "vulgar",

104 "vulgar": "vulgar",

105}

106

107# https://es.wiktionary.org/wiki/Plantilla:ámbito

108AMBITO_TAGS = {

109 "Acaxochitlán": "Acaxochitlán",

110 "Alemania": "Germany",

111 "Algarve": "Algarve (Portugal)",

112 "Almería": "Almería",

113 "Am.": "America",

114 "Amecameca": "Amecameca",

115 "América": "America",

116 "América Central": "Central America",

117 "América Latina": "America",

118 "América central": "Central America",

119 "América del Sur": "South America",

120 "Andalucía": "Andalusia",

121 "Antioquia": "Antioquia",

122 "Aragón": "Aragon",

123 "Aragón Oriental": "Eastern Aragon",

124 "Arg.": "Argentina",

125 "Argentina": "Argentina",

126 "Asturias": "Asturias",

127 "Atlapexco": "Atlapexco",

128 "Australia": "Australia",

129 "Baja California": "Lower California",

130 "Baja Navarra": "Lower Navarre (France)",

131 "Bearn": "Bearn (France)",

132 "Bearne": "Bearn (France)",

133 "Belluno": "Belluno",

134 "Bolivia": "Bolivia",

135 "Bolonia": "Bologna",

136 "Brasil": "Brazil",

137 "Brasil meridional": "Southern Brazil",

138 "Burgos": "Burgos",

139 "Calpan": "Calpan",

140 "Campeche": "Campeche",

141 "Canadá": "Canada",

142 "Canarias": "Canaries",

143 "Canoa": "Canoe",

144 "Cantabria": "Cantabria",

145 "Caribe": "Caribbean",

146 "Carpi": "Carpi",

147 "Cartagena": "Cartagena",

148 "Castilla": "Castile",

149 "Cataluña": "Catalonia",

150 "Centro América": "Central America",

151 "Centro de Chile": "Center of Chile",

152 "Centro de México": "Mexico Center",

153 "Centroamérica": "Central America",

154 "Ceuta": "Ceuta",

155 "Chiapas": "Chiapas",

156 "Chicontepec": "Chicontepec",

157 "Chihuahua": "Chihuahua",

158 "Chile": "Chile",

159 "Chiloé": "Chiloé (Chile)",

160 "Chipilo": "Chipilo",

161 "Chl.": "Chile",

162 "Cholula": "Cholula",

163 "Chubut": "Chubut",

164 "Ciudad de México": "Mexico City",

165 "Colombia": "Colombia",

166 "Connacht": "Connacht (Ireland)",

167 "Connemara": "Connemara (Ireland)",

168 "Cono Sur": "South Cone",

169 "Costa Rica": "Costa Rica",

170 "Cuba": "Cuba",

171 "Cuentepec": "Cuentepec",

172 "Cuetzalan": "Cuetzalan",

173 "Cádiz": "Cádiz",

174 "Córdoba (España)": "Córdoba (Spain)",

175 "Dominicana": "Dominican Republic",

176 "EEUU": "United States",

177 "Ecuador": "Ecuador",

178 "El Salv.": "El Salvador",

179 "El Salvador": "El Salvador",

180 "Escocia": "Scotland",

181 "España": "Spain",

182 "Estados Unidos": "United States",

183 "Europa": "Europe",

184 "Euskadi": "Basque Country",

185 "Extremadura": "Extremadura",

186 "Extremadura (España)": "Extremadura",

187 "Filipinas": "Philippines",

188 "Francia": "France",

189 "Galicia": "Galicia",

190 "Gascuña": "Gascony (France)",

191 "Granada": "Grenada",

192 # "Grischun": "grisón",

193 "Guadalajara": "Guadalajara (Spain)",

194 "Guanajuato": "Guanajuato",

195 "Guatemala": "Guatemala",

196 "Guernsey": "Guernsey",

197 "Guinea Ecuatorial": "Equatorial Guinea",

198 "Hidalgo": "Hidalgo",

199 "Hond.": "Honduras",

200 "Honduras": "Honduras",

201 "Huauchinango": "Huauchinango",

202 "Huejutla": "Huejutla",

203 "Huelva": "Huelva (Spain)",

204 "Hueyapan": "Hueyapan",

205 "Inglaterra": "England",

206 "Iparralde": "Iparralde",

207 "Irlanda": "Ireland",

208 "Islas Baleares": "Balearic Islands",

209 "Italia": "Italy",

210 "Jalisco": "Jalisco",

211 "Jaltocán": "Jaltocan",

212 "Jamaica": "Jamaica",

213 "Jersey": "Jersey",

214 "La Rioja": "La Rioja (Spain)",

215 "La Rioja (Argentina)": "La Rioja (Argentina)",

216 "Labort": "Labort (France)",

217 "Languedoc": "Languedoc (France)",

218 "Lapurdi": "Labort (France)",

219 "León": "León (Spain)",

220 "Liechtenstein": "Liechtenstein",

221 "Logudoro": "Logudoro",

222 "Lunfardo": "Lunfardo",

223 "Mallorca": "Mallorca (Balearic Islands)",

224 "Marruecos": "Morocco",

225 "Matlapa": "Matlapa",

226 "Michoacán": "Michoacán (Mexico)",

227 "Milpa Alta": "Milpa Alta",

228 "Mirandola": "Mirandola",

229 "Munster": "Munster (Ireland)",

230 "Murcia": "Murcia",

231 "Méjico": "Mexico",

232 "México": "Mexico",

233 "México (México)": "Mexico DF",

234 "Módena": "Modena",

235 "Navarra": "Navarra",

236 "Nicaragua": "Nicaragua",

237 "Normandía": "Normandy",

238 "Norte de Argentina": "Northern Argentina",

239 "Norte de Chile": "Northern Chile",

240 "Nueva Zelanda": "New Zealand",

241 "Nueva Zelandia": "New Zealand",

242 "Nuevo León": "Nuevo León",

243 "Nuevo México": "New Mexico",

244 "Oaxaca": "Oaxaca",

245 "Orizatlán": "Orizatlán",

246 "Palencia": "Palencia",

247 "Panamá": "Panama",

248 "Paraguay": "Paraguay",

249 "País Vasco": "Basque Country",

250 "País Vasco francés": "French Basque Country",

251 "Perú": "Peru",

252 "Portugal": "Portugal",

253 "Provenza": "Provence (France)",

254 "Puebla": "Puebla",

255 "Puerto Rico": "Puerto Rico",

256 # "Puter": "high engadino"

257 "Quebec": "Quebec",

258 "Querétaro": "Querétaro",

259 "Reino Unido": "United Kingdom",

260 "República Dominicana": "Dominican Republic",

261 "Ribera de Navarra": "Ribera Navarra",

262 "Rioja": "Rioja (Spain)",

263 "Rioplatense": "Río de la Plata",

264 "Río de la Plata": "Río de la Plata",

265 "Salamanca": "Salamanca",

266 "Salamanca (España)": "Salamanca",

267 "San Juan Quiahije": "San Juan Quiahije",

268 "San Luis Potosí": "San Luis Potosí",

269 "Santa María Yosoyúa": "Santa María Yosoyúa",

270 "Sevilla": "Seville",

271 "Sinaloa": "Sinaloa",

272 "Sola": "Sola (France)",

273 "Sonora": "Sonora",

274 "Soria": "Soria (Spain)",

275 "Soule": "Sola (France)",

276 "Sudamérica": "South America",

277 "Suiza": "Switzerland",

278 "Sur de Chile": "Southern Chile",

279 "Suramérica": "South America",

280 "Surmiran": "Surmirano",

281 "Sursilvan": "Sursilvano",

282 "Sutsilvan": "Sutsilvano",

283 "Tamazunchale": "Tamazunchale",

284 "Tepeojuma": "Tepeojuma",

285 "Texcoco": "Texcoco",

286 "Tlaxcala": "Tlaxcala",

287 "Tlaxpanaloya": "Tlaxpanaloya",

288 "Toulouse": "Toulouse",

289 "USA": "United States",

290 "Ulster": "Ulster (Ireland, R. U.)",

291 "Uruguay": "Uruguay",

292 "Valencia": "Valencia",

293 "Vallader": "Bajo engadino",

294 "Venecia": "Venice",

295 "Venezuela": "Venezuela",

296 "Veracruz": "Veracruz",

297 "Vizcaya": "Vizcaya (Spain)",

298 "Waterford": "Waterford (Ireland)",

299 "Xayacatlán": "Xayacatlán",

300 "Xilitla": "Xilitla",

301 "Xochiatipan": "Xochiatipan",

302 "Yaganiza": "Yaganiza",

303 "Yahualica": "Yahualica",

304 "Yojovi": "Yojovi",

305 "Yucatán": "Yucatán",

306 "Zacatecas": "Zacatecas",

307 "Zamora": "Zamora (Spain)",

308 "Zuberoa": "Sola (France)",

309 "Zulia": "Zulia (Venezuela)",

310 # "alto engadino": "alto engadino",

311 "anglonormando": "Anglo-Norman",

312 # "bajo engadino": "bajo engadino",

313 # "grischun": "grisón",

314 # "grisón": "grisón",

315 # "haquetía": "haquety",

316 "logudorés": "Logudoro",

317 "lunf": "Lunfardo",

318 "lunfardismo": "Lunfardo",

319 "lunfardo": "Lunfardo",

320 "parlache": ["Colombia", "slang"],

321 # "puter": "high engadino",

322 "rioplatense": "Río de la Plata",

323 "rpl": "Río de la Plata",

324 "subsilvano": "Sursilvan",

325 "supramirano": "Surmiran",

326 "suprasilvano": "Sursilvan",

327 "sur de Chile": "Southern Chile",

328 "surmirano": "Surmiran",

329 "sursilvano": "Sursilvan",

330 "sutsilvano": "Sursilvan",

331 "vallader": "bajo engadino",

332 "Á. R. Plata": "Río de la Plata",

333 "Álava": "Álava",

334}

335

336

337# https://es.wiktionary.org/wiki/Plantilla:csem

338CSEM_TOPICS = {

339 "aeronáutica": "aeronautics",

340 "agricultura": "agriculture",

341 "ajedrez": "chess",

342 # "Algas": "algae",

343 "alimento": "food",

344 "alimentos": "food",

345 "alpinismo": "mountaineering",

346 "alquimia": "alchemy",

347 "anatomía": "anatomy",

348 # "Anfibios": "amphibians",

349 # "Angiología": "angiology",

350 # "Animales": "animals",

351 # "Animales extintos": "extinct animals",

352 "antropología": "anthropology",

353 # "Antropotomía": "anthropotomy",

354 # "Antropónimos": "anthroponyms",

355 # "Anélidos": "annelids",

356 # "Apellidos": "surnames",

357 "apicultura": "beekeeping",

358 # "Arbustos": "shrubbery",

359 "aritmética": "arithmetic",

360 "armas": "weaponry",

361 "arqueología": "archeology",

362 "arquitectura": "architecture",

363 "arte": "art",

364 "arte marciales": "martial arts",

365 "artes marciales": "martial arts",

366 # "Artrópodos": "arthropods",

367 # "Arácnidos": "arachnids",

368 "astrofísica": "astrophysics",

369 "astrología": "astrology",

370 "astronomía": "astronomy",

371 "atletismo": "athletics",

372 # "Audiología": "audiology",

373 # "Automovilismo": "motoring",

374 # "Aves": "birds",

375 # "Bacterias": "bacteria",

376 "danza": "dance",

377 "baloncesto": "basketball",

378 "balonmano": "handball",

379 # "Batería de cocina": "cookware",

380 # "Bebidas": "drinks",

381 "billar": "billiards",

382 "biología": "biology",

383 "bioquímica": "biochemistry",

384 "bolos": "bowling",

385 "botánica": "botany",

386 "béisbol": "baseball",

387 # "Caza": "hunt",

388 # "Cactus": "cactus",

389 # "Campamento": "camp",

390 "cardiología": "cardiology",

391 "carpintería": "carpentry",

392 # "Casos gramaticales": "grammatical cases",

393 # "Cereales": "cereals",

394 # "Cerrajería": "locksmith",

395 "cetrería": "falconry",

396 "ciclismo": "cycling",

397 "ciencia": "science",

398 "ciencia ficción": "science fiction",

399 # "Cine": "cinema",

400 "cinegética": "hunting",

401 "cinematografía": "cinematography",

402 # "Cinología": "cynology",

403 "cirugía": "surgery",

404 "ciudades": "cities",

405 # "Cnidarios": "cnidarians",

406 # "Colores": "colors",

407 # "Comercio": "trade",

408 "comunicación": "communication",

409 # "Condimentos": "condiments",

410 # "Constelaciones": "constellations",

411 "construcción": "construction",

412 "contabilidad": "accounting",

413 "continentes": "continents",

414 # "Cordilleras": "mountain ranges",

415 "correos": "mail",

416 # "Cosmetología": "cosmetology",

417 "cosmología": "cosmology",

418 "cosmética": "cosmetics",

419 "costura": "sewing",

420 "cristianismo": "Christianity",

421 "cronología": "chronology",

422 # "Crustáceos": "crustaceans",

423 # "Cubertería": "cutlery",

424 # "Cultura": "culture",

425 "deporte": "sports",

426 # "Derecho": "right",

427 # "Dinosaurios": "dinosaurs",

428 # "Dioses": "gods",

429 "diseño": "design",

430 "días de la semana": "weekdays",

431 "ecología": "ecology",

432 "economía": "economics",

433 # "Edafología": "edaphology",

434 "educación": "education",

435 "electricidad": "electricity",

436 "electromagnetismo": "electromagnetism",

437 "electrónica": "electronics",

438 # "Elementos químicos": "chemical elements",

439 # "Emojis": "emoji",

440 # "Emoticonos": "emoticons",

441 # "Enfermedades": "diseases",

442 "enología": "oenology",

443 # "Enseñanza": "teaching",

444 "entomología": "entomology",

445 # "Equinodermos": "echinoderms",

446 # "Equitación": "horse riding",

447 # "Eras históricas": "historical eras",

448 # "Escultura": "sculpture",

449 "esgrima": "fencing",

450 # "Especias": "spices",

451 "estaciones": "seasons",

452 "estadística": "statistics",

453 # "Estomatología": "stomatology",

454 # "Estética": "esthetic",

455 "fabril": "manufacturing",

456 # "Fantasía": "fancy",

457 # "Farmacia": "pharmacy",

458 "farmacología": "pharmacology",

459 "feminismo": "feminism",

460 # "Festividades": "festivities",

461 "ficción": "fiction",

462 # "Ficción fantástica": "fantasy fiction",

463 "ficología": "phycology",

464 "filatelia": "philately",

465 "filosofía": "philosophy",

466 "finanzas": "finance",

467 "fisiología": "physiology",

468 # "Flores": "flowers",

469 # "Fobias": "phobias",

470 "folclore": "folklore",

471 "fonética": "phonetics",

472 # "Formas": "shapes",

473 "fotografía": "photography",

474 # "Fraccionarios": "fractionals",

475 # "Frutas": "fruit",

476 # "Frutos": "fruits",

477 "fármacos": "drugs",

478 # "Física": "physical",

479 "fútbol": "soccer",

480 # "Ganadería": "cattle raising",

481 # "Gastronomía": "gastronomy",

482 # "Gentilicios": "gentilicios",

483 "genética": "genetics",

484 "geografía": "geography",

485 "geología": "geology",

486 "geometría": "geometry",

487 # "Gimnasia": "gym",

488 # "Glotónimos": "gluttonyms",

489 "gramática": "grammar",

490 # "Granjería": "farming",

491 # "Guarismos": "figures",

492 "halconería": "falconry",

493 "herramientas": "tools",

494 "heráldica": "heraldry",

495 "hidrología": "hydrology",

496 # "Hierbas": "herbs",

497 # "Higiene": "hygiene",

498 # "Hipocorísticos": "hypocoristic",

499 "historia": "history",

500 # "Historieta": "cartoon",

501 # "Hockey sobre césped": "field hockey",

502 # "Hongos": "fungus",

503 "horticultura": "horticulture",

504 # "Hostelería": "hostelry",

505 # "Huesos": "bones",

506 # "Humanidades": "humanities",

507 "ictiología": "ichthyology",

508 # "Lenguas": "languages",

509 "imprenta": "printing",

510 # "Industria": "industry",

511 "informática": "computing",

512 "ingeniería": "engineering",

513 "inmunología": "immunology",

514 "insectos": "insects",

515 # "Instrumentos": "instruments",

516 # "Instrumentos de medición": "measurement tools",

517 # "Instrumentos musicales": "musical instruments",

518 "interfaz gráfica de usuario": "graphical user interface",

519 "internet": "Internet",

520 # "Invertebrados": "invertebrates",

521 "islam": "Islam",

522 # "Islas": "islands",

523 # "Judaísmo": "judaism",

524 "juegos": "games",

525 # "Juguetes": "toys",

526 "lgbt": "LGBT",

527 # "Lagos": "lakes",

528 "lexicografía": "lexicography",

529 "lingüística": "linguistics",

530 "literatura": "literature",

531 # "Logística": "logistics",

532 # "Lucha": "struggle",

533 # "Líquidos": "liquids",

534 "lógica": "logic",

535 "malabarismo": "juggling",

536 "mamíferos": "mammals",

537 # "Mares": "seas",

538 "náutica": "nautical",

539 "matemática": "mathematics",

540 # "Materia": "subject",

541 # "Materiales": "materials",

542 "mecánica": "mechanics",

543 "medicina": "medicine",

544 # "Meses": "months",

545 # "Metales": "metals",

546 "metalurgia": "metallurgy",

547 "meteorología": "meteorology",

548 "metrología": "metrology",

549 "micología": "mycology",

550 "microbiología": "microbiology",

551 "milicia": "military",

552 # "Minerales": "minerals",

553 "mineralogía": "mineralogy",

554 "minería": "mining",

555 "mitología": "mythology",

556 "mobiliario": "furniture",

557 # "Moluscos": "mollusks",

558 # "Monedas": "coins",

559 # "Moneras": "moneras",

560 # "Montañas": "mountains",

561 "muebles": "furniture",

562 "música": "music",

563 # "Naipes": "playing cards",

564 "natación": "swimming",

565 # "Naturaleza": "nature",

566 # "Nemátodos": "nematodes",

567 "neurología": "neurology",

568 "numismática": "numismatics",

569 # "Nutrición": "nutrition",

570 # "Números": "numbers",

571 "ocultismo": "occultism",

572 # "Ocupaciones": "activities",

573 # "Océanos": "oceans",

574 "odontología": "odontology",

575 # "Oficios": "trades",

576 "oftalmología": "ophthalmology",

577 "ornitología": "ornithology",

578 "paleontología": "paleontology",

579 "parapsicología": "parapsychology",

580 # "Parentesco": "relationship",

581 # "Partes del día": "parts of the day",

582 "países": "countries",

583 "peces": "fish",

584 # "Penínsulas": "peninsulas",

585 "periodismo": "journalism",

586 "perros": "dogs",

587 # "Personajes bíblicos": "biblical characters",

588 # "Personajes ficticios": "fictional characters",

589 # "Personajes históricos": "historical figures",

590 "pesca": "fishing",

591 # "Pesos y medidas": "weights and measures",

592 # "Pintura": "paint",

593 "planetas": "planets",

594 # "Plantas": "floors",

595 # "Platelmintos": "platyhelminths",

596 # "Platos": "dishes",

597 # "Poblaciones": "populations",

598 "poesía": "poetry",

599 # "Política": "policy",

600 "pragmática": "pragmatics",

601 # "Prehistoria": "prehistory",

602 # "Vestimenta": "outfit",

603 # "Profesiones": "professions",

604 # "Protistas": "protists",

605 # "Pseudociencias": "pseudosciences",

606 "psicología": "psychology",

607 "psiquiatría": "psychiatry",

608 "química": "chemistry",

609 "química orgánica": "organic chemistry",

610 # "Radiocomunicación": "radiocomunication",

611 # "Regiones": "regions",

612 # "Reinos biológicos": "biological kingdoms",

613 "religión": "religion",

614 # "Relojería": "watchmaking",

615 # "Reptiles": "reptiles",

616 # "Restaurantes": "restaurants",

617 # "Retórica": "rhetoric",

618 "rugby": "rugby",

619 # "Ríos": "rivers",

620 # "Sabores": "flavors",

621 "salud": "health",

622 # "Saludos": "greetings",

623 # "Satélites": "satellites",

624 # "Seguridad": "security",

625 # "Semiología": "semiology",

626 "semiótica": "semiotics",

627 # "Sentidos": "senses",

628 # "Sentimientos": "feelings",

629 "serpientes": "snakes",

630 "sexualidad": "sexuality",

631 # "Signos": "signs",

632 # "Signos ortográficos": "spelling signs",

633 "silvicultura": "forestry",

634 # "Sociedad": "society",

635 "sociología": "sociology",

636 # "Símbolos": "symbols",

637 # "Símbolos alquímicos": "alchemical symbols",

638 # "Símbolos astronómicos": "astronomical symbols",

639 # "Símbolos de unidades monetarias": "symbols of monetary units",

640 "tauromaquia": "bullfighting",

641 "taxonomía": "taxonomy",

642 "teatro": "theater",

643 "tecnología": "technology",

644 "textiles": "textiles",

645 "telecomunicaciones": "telecommunications",

646 # "Telecomunicación": "telecommunication",

647 "tenis": "tennis",

648 "teología": "theology",

649 "termodinámica": "thermodynamics",

650 "tiempo": "time",

651 "tipografía": "typography",

652 "topografía": "topography",

653 # "Topónimos": "toponyms",

654 "transporte": "transport",

655 # "Tribus urbanas": "urban tribes",

656 "turismo": "tourism",

657 # "Unidades de tiempo": "time units",

658 # "Urbanismo": "town planning",

659 # "Utensilios": "utensils",

660 "vegetales": "vegetable",

661 "vehículos": "vehicles",

662 "verduras": "vegetable",

663 # "Vertebrados": "vertebrates",

664 # "Veterinaria": "vet",

665 # "Virtudes": "virtues",

666 # "Vivienda": "living place",

667 # "Waterpolo": "water polo",

668 "zoología": "zoology",

669 "zootomía": "zootomy",

670 "álgebra": "algebra",

671 # "Árboles": "trees",

672 "ética": "ethics",

673 "óptica": "optics",

674}

675

676NUMBER_TAGS = {

677 # "inflect.*" templates

678 "singular": "singular",

679 "plural": "plural",

680}

681

682GENDER_TAGS = {

683 "masculino": "masculine",

684 "femenino": "feminine",

685 "neutro": "neuter",

686}

687

688COMPARISON_TAGS = {

689 "positivo": "positive",

690 "comparativo": "comparative",

691 "superlativo": "superlative",

692}

693

694PERSON_TAGS = {

695 "primera": "first-person",

696 "segunda": "second-person",

697 "tercera": "third-person",

698}

699

700TENSE_TAGS = {

701 "presente": "present",

702 "pretérito imperfecto": ["past", "imperfect"],

703 "pretérito indefinido": ["indefinite", "preterite"],

704 "futuro": "future",

705 "condicional": "conditional",

706 "pretérito perfecto": ["present", "perfect"],

707 "pretérito pluscuamperfecto": "pluperfect",

708 "pretérito anterior": ["past", "anterior"],

709 "futuro perfecto": ["future", "perfect"],

710 "condicional perfecto": ["conditional", "perfect"],

711}

712

713VERB_FORM_TAGS = {

714 "infinitivo": "infinitive",

715 "gerundio": "gerund",

716 "participio": "participle",

717}

718

719

720ALL_TAGS = {

721 **NUMBER_TAGS,

722 **GENDER_TAGS,

723 **COMPARISON_TAGS,

724 **PERSON_TAGS,

725 **TENSE_TAGS,

726 **VERB_FORM_TAGS,

727 "afirmativo": "affirmative",

728 "negativo": "negative",

729 "simples": "simple",

730 "compuestas": "compound",

731}

732

733

734def translate_raw_tags(data: WordEntry):

735 raw_tags = []

736 for raw_tag in data.raw_tags:

737 lower_raw_tag = raw_tag.lower()

738 if lower_raw_tag in ALL_TAGS:

739 tr_tag = ALL_TAGS[lower_raw_tag]

740 if isinstance(tr_tag, str): 740 ↛ 742line 740 didn't jump to line 742 because the condition on line 740 was always true

741 data.tags.append(tr_tag)

742 elif isinstance(tr_tag, list):

743 data.tags.extend(tr_tag)

744 elif lower_raw_tag in CSEM_TOPICS and hasattr(data, "topics"):

745 data.topics.append(CSEM_TOPICS[lower_raw_tag])

746 else:

747 raw_tags.append(raw_tag)

748 data.raw_tags = raw_tags