Coverage for src/wiktextract/extractor/es/tags.py: 88%

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10 "anticuado": "outdated",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 "clásico": "Classical",

18 "coloq": "colloquial",

19 "coloq.": "colloquial",

20 "coloquial": "colloquial",

21 # "culto": "worship",

22 "cómico": "jocular",

23 "despect.": "derogatory",

24 "despectivo": "derogatory",

25 "desus": "outdated",

26 "desus.": "outdated",

27 "desusada": "outdated",

28 "desusado": "outdated",

29 "elevado": "literary",

30 "epiceno": "epicene",

31 "eufemismo": "euphemism",

32 "eutca": "adjective",

33 "familiar": "colloquial",

34 "figurado": "figurative",

35 "formal": "formal",

36 "germanía": "slang",

37 "grosero": "vulgar",

38 "humorístico": "jocular",

39 "infantil": "childish",

40 "informal": "colloquial",

41 "infrecuente": "rare",

42 "irónico": "ironic",

43 "jerga": "slang",

44 # "jerga legal": "legal jargon",

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

46 # "jerga skinhead": "skinhead slang",

47 "jergal": "slang",

48 "jocoso": "jocular",

49 "literario": "literary",

50 "malsonante": "vulgar",

51 # "mayúscula": "capital letter",

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

53 # "mayúscula puntos cardinales":

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

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

56 "medieval": "Medieval",

57 "minúscula": "lower case",

58 "moderno": "modern",

59 "neologismo": "neologism",

60 "obsoleto": "obsolete",

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

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

63 "peyorativo": "derogatory",

64 "poco frecuente": "rare",

65 "poco usado": "rare",

66 "popular": "colloquial",

67 "poético": "literary",

68 "raro": "rare",

69 # "rur": "rural",

70 # "rural": "rural",

71 "sebtc": "noun",

72 "setc": "noun",

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

74 # this word in published texts or corpus",

75 "slang": "slang",

76 "soez": "vulgar",

77 "sutp": "plural",

78 "suts": "singular",

79 # "trans-prefijo": "",

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

81 "umcp": "pronominal",

82 "umcs": "noun",

83 "umcv": "vocative",

84 "umep": "plural",

85 "umpl": "plural",

86 "utca": "adjective",

87 "utcadv": "adverb",

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

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

90 "utcc": "conjunction",

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

92 "utcg": "gerund",

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

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

95 "utcp": "pronominal",

96 "utcprnl": "pronominal",

97 "utcs": "noun",

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

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

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

101 "utcsmf": "noun",

102 "utct": "transitive",

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

104 "utrep": "repeated",

105 "vulg": "vulgar",

106 "vulgar": "vulgar",

107}

108

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

110AMBITO_TAGS = {

111 "Acaxochitlán": "Acaxochitlán",

112 "Alemania": "Germany",

113 "Algarve": "Algarve",

114 "Almería": "Almería",

115 "Am.": "America",

116 "Amecameca": "Amecameca",

117 "América": "America",

118 "América Central": "Central-America",

119 "América Latina": "America",

120 "América central": "Central-America",

121 "América del Sur": "South-America",

122 "Andalucía": "Andalusia",

123 "Antioquia": "Antioquia",

124 "Aragón": "Aragon",

125 "Aragón Oriental": "Eastern-Aragon",

126 "Arg.": "Argentina",

127 "Argentina": "Argentina",

128 "Asturias": "Asturias",

129 "Atlapexco": "Atlapexco",

130 "Australia": "Australia",

131 "Baja California": "Lower-California",

132 "Baja Navarra": "Lower-Navarre",

133 "Bearn": "Bearn",

134 "Bearne": "Bearn",

135 "Belluno": "Belluno",

136 "Bolivia": "Bolivia",

137 "Bolonia": "Bologna",

138 "Brasil": "Brazil",

139 "Brasil meridional": "Southern-Brazil",

140 "Burgos": "Burgos",

141 "Calpan": "Calpan",

142 "Campeche": "Campeche",

143 "Canadá": "Canada",

144 "Canarias": "Canaries",

145 "Canoa": "Canoe",

146 "Cantabria": "Cantabria",

147 "Caribe": "Caribbean",

148 "Carpi": "Carpi",

149 "Cartagena": "Cartagena",

150 "Castilla": "Castile",

151 "Cataluña": "Catalonia",

152 "Centro América": "Central-America",

153 "Centro de Chile": "Central-Chile",

154 "Centro de México": "Central-Mexico",

155 "Centroamérica": "Central-America",

156 "Ceuta": "Ceuta",

157 "Chiapas": "Chiapas",

158 "Chicontepec": "Chicontepec",

159 "Chihuahua": "Chihuahua",

160 "Chile": "Chile",

161 "Chiloé": "Chiloé",

162 "Chipilo": "Chipilo",

163 "Chl.": "Chile",

164 "Cholula": "Cholula",

165 "Chubut": "Chubut",

166 "Ciudad de México": "Mexico-City",

167 "Colombia": "Colombia",

168 "Connacht": "Connacht",

169 "Connemara": "Connemara",

170 "Cono Sur": "South-Cone",

171 "Costa Rica": "Costa-Rica",

172 "Cuba": "Cuba",

173 "Cuentepec": "Cuentepec",

174 "Cuetzalan": "Cuetzalan",

175 "Cádiz": "Cádiz",

176 "Córdoba (España)": "Córdoba",

177 "Dominicana": "Dominican-Republic",

178 "EEUU": "US",

179 "Ecuador": "Ecuador",

180 "El Salv.": "El-Salvador",

181 "El Salvador": "El-Salvador",

182 "Escocia": "Scotland",

183 "España": "Spain",

184 "Estados Unidos": "US",

185 "Europa": "Europe",

186 "Euskadi": "Basque Country",

187 "Extremadura": "Extremadura",

188 "Extremadura (España)": "Extremadura",

189 "Filipinas": "Philippines",

190 "Francia": "France",

191 "Galicia": "Galicia",

192 "Gascuña": "Gascony",

193 "Granada": "Grenada",

194 # "Grischun": "grisón",

195 "Guadalajara": "Guadalajara",

196 "Guanajuato": "Guanajuato",

197 "Guatemala": "Guatemala",

198 "Guernsey": "Guernsey",

199 "Guinea Ecuatorial": "Equatorial-Guinea",

200 "Hidalgo": "Hidalgo",

201 "Hond.": "Honduras",

202 "Honduras": "Honduras",

203 "Huauchinango": "Huauchinango",

204 "Huejutla": "Huejutla",

205 "Huelva": "Huelva",

206 "Hueyapan": "Hueyapan",

207 "Inglaterra": "England",

208 "Iparralde": "Iparralde",

209 "Irlanda": "Ireland",

210 "Islas Baleares": "Balearic-Islands",

211 "Italia": "Italy",

212 "Jalisco": "Jalisco",

213 "Jaltocán": "Jaltocan",

214 "Jamaica": "Jamaica",

215 "Jersey": "Jersey",

216 "La Rioja": "La Rioja",

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

218 "Labort": "Labort",

219 "Languedoc": "Languedoc",

220 "Lapurdi": "Labort",

221 "León": "León",

222 "Liechtenstein": "Liechtenstein",

223 "Logudoro": "Logudoro",

224 "Lunfardo": "Lunfardo",

225 "Mallorca": "Mallorca",

226 "Marruecos": "Morocco",

227 "Matlapa": "Matlapa",

228 "Michoacán": "Michoacán",

229 "Milpa Alta": "Milpa Alta",

230 "Mirandola": "Mirandola",

231 "Munster": "Munster",

232 "Murcia": "Murcia",

233 "Méjico": "Mexico",

234 "México": "Mexico",

235 "México (México)": "Mexico",

236 "Módena": "Modena",

237 "Navarra": "Navarra",

238 "Nicaragua": "Nicaragua",

239 "Normandía": "Normandy",

240 "Norte de Argentina": "Northern-Argentina",

241 "Norte de Chile": "Northern-Chile",

242 "Nueva Zelanda": "New-Zealand",

243 "Nueva Zelandia": "New-Zealand",

244 "Nuevo León": "Nuevo-León",

245 "Nuevo México": "New-Mexico",

246 "Oaxaca": "Oaxaca",

247 "Orizatlán": "Orizatlán",

248 "Palencia": "Palencia",

249 "Panamá": "Panama",

250 "Paraguay": "Paraguay",

251 "País Vasco": "Basque Country",

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

253 "Perú": "Peru",

254 "Portugal": "Portugal",

255 "Provenza": "Provence",

256 "Puebla": "Puebla",

257 "Puerto Rico": "Puerto-Rico",

258 # "Puter": "high engadino"

259 "Quebec": "Quebec",

260 "Querétaro": "Querétaro",

261 "Reino Unido": "UK",

262 "República Dominicana": "Dominican-Republic",

263 "Ribera de Navarra": "Ribera-Navarra",

264 "Rioja": "Rioja",

265 "Rioplatense": "Río-de-la-Plata",

266 "Río de la Plata": "Río-de-la-Plata",

267 "Salamanca": "Salamanca",

268 "Salamanca (España)": "Salamanca",

269 "San Juan Quiahije": "San-Juan-Quiahije",

270 "San Luis Potosí": "San-Luis-Potosí",

271 "Santa María Yosoyúa": "Santa-María-Yosoyúa",

272 "Sevilla": "Seville",

273 "Sinaloa": "Sinaloa",

274 "Sola": "Sola",

275 "Sonora": "Sonora",

276 "Soria": "Soria",

277 "Soule": "Sola",

278 "Sudamérica": "South-America",

279 "Suiza": "Switzerland",

280 "Sur de Chile": "Southern-Chile",

281 "Suramérica": "South-America",

282 "Surmiran": "Surmirano",

283 "Sursilvan": "Sursilvano",

284 "Sutsilvan": "Sutsilvano",

285 "Tamazunchale": "Tamazunchale",

286 "Tepeojuma": "Tepeojuma",

287 "Texcoco": "Texcoco",

288 "Tlaxcala": "Tlaxcala",

289 "Tlaxpanaloya": "Tlaxpanaloya",

290 "Toulouse": "Toulouse",

291 "USA": "United States",

292 "Ulster": "Ulster",

293 "Uruguay": "Uruguay",

294 "Valencia": "Valencia",

295 "Vallader": "Bajo-engadino",

296 "Venecia": "Venice",

297 "Venezuela": "Venezuela",

298 "Veracruz": "Veracruz",

299 "Vizcaya": "Vizcaya",

300 "Waterford": "Waterford",

301 "Xayacatlán": "Xayacatlán",

302 "Xilitla": "Xilitla",

303 "Xochiatipan": "Xochiatipan",

304 "Yaganiza": "Yaganiza",

305 "Yahualica": "Yahualica",

306 "Yojovi": "Yojovi",

307 "Yucatán": "Yucatán",

308 "Zacatecas": "Zacatecas",

309 "Zamora": "Zamora",

310 "Zuberoa": "Sola",

311 "Zulia": "Zulia",

312 # "alto engadino": "alto engadino",

313 "anglonormando": "Anglo-Norman",

314 # "bajo engadino": "bajo engadino",

315 # "grischun": "grisón",

316 # "grisón": "grisón",

317 # "haquetía": "haquety",

318 "logudorés": "Logudoro",

319 "lunf": "Lunfardo",

320 "lunfardismo": "Lunfardo",

321 "lunfardo": "Lunfardo",

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

323 # "puter": "high engadino",

324 "rioplatense": "Río-de-la-Plata",

325 "rpl": "Río-de-la-Plata",

326 "subsilvano": "Sursilvan",

327 "supramirano": "Surmiran",

328 "suprasilvano": "Sursilvan",

329 "sur de Chile": "Southern-Chile",

330 "surmirano": "Surmiran",

331 "sursilvano": "Sursilvan",

332 "sutsilvano": "Sursilvan",

333 "vallader": "Lower-Engadine",

334 "Á. R. Plata": "Río-de-la-Plata",

335 "Álava": "Álava",

336}

337

338

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

340CSEM_TOPICS = {

341 "aeronáutica": "aeronautics",

342 "agricultura": "agriculture",

343 "ajedrez": "chess",

344 # "Algas": "algae",

345 "alimento": "food",

346 "alimentos": "food",

347 "alpinismo": "mountaineering",

348 "alquimia": "alchemy",

349 "anatomía": "anatomy",

350 # "Anfibios": "amphibians",

351 # "Angiología": "angiology",

352 # "Animales": "animals",

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

354 "antropología": "anthropology",

355 # "Antropotomía": "anthropotomy",

356 # "Antropónimos": "anthroponyms",

357 # "Anélidos": "annelids",

358 # "Apellidos": "surnames",

359 "apicultura": "beekeeping",

360 # "Arbustos": "shrubbery",

361 "aritmética": "arithmetic",

362 "armas": "weaponry",

363 "arqueología": "archeology",

364 "arquitectura": "architecture",

365 "arte": "art",

366 "arte marciales": "martial arts",

367 "artes marciales": "martial arts",

368 # "Artrópodos": "arthropods",

369 # "Arácnidos": "arachnids",

370 "astrofísica": "astrophysics",

371 "astrología": "astrology",

372 "astronomía": "astronomy",

373 "atletismo": "athletics",

374 # "Audiología": "audiology",

375 # "Automovilismo": "motoring",

376 # "Aves": "birds",

377 # "Bacterias": "bacteria",

378 "danza": "dance",

379 "baloncesto": "basketball",

380 "balonmano": "handball",

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

382 # "Bebidas": "drinks",

383 "billar": "billiards",

384 "biología": "biology",

385 "bioquímica": "biochemistry",

386 "bolos": "bowling",

387 "botánica": "botany",

388 "béisbol": "baseball",

389 # "Caza": "hunt",

390 # "Cactus": "cactus",

391 # "Campamento": "camp",

392 "cardiología": "cardiology",

393 "carpintería": "carpentry",

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

395 # "Cereales": "cereals",

396 # "Cerrajería": "locksmith",

397 "cetrería": "falconry",

398 "ciclismo": "cycling",

399 "ciencia": "science",

400 "ciencia ficción": "science fiction",

401 # "Cine": "cinema",

402 "cinegética": "hunting",

403 "cinematografía": "cinematography",

404 # "Cinología": "cynology",

405 "cirugía": "surgery",

406 "ciudades": "cities",

407 # "Cnidarios": "cnidarians",

408 # "Colores": "colors",

409 # "Comercio": "trade",

410 "comunicación": "communication",

411 # "Condimentos": "condiments",

412 # "Constelaciones": "constellations",

413 "construcción": "construction",

414 "contabilidad": "accounting",

415 "continentes": "continents",

416 # "Cordilleras": "mountain ranges",

417 "correos": "mail",

418 # "Cosmetología": "cosmetology",

419 "cosmología": "cosmology",

420 "cosmética": "cosmetics",

421 "costura": "sewing",

422 "cristianismo": "Christianity",

423 "cronología": "chronology",

424 # "Crustáceos": "crustaceans",

425 # "Cubertería": "cutlery",

426 # "Cultura": "culture",

427 "deporte": "sports",

428 # "Derecho": "right",

429 # "Dinosaurios": "dinosaurs",

430 # "Dioses": "gods",

431 "diseño": "design",

432 "días de la semana": "weekdays",

433 "ecología": "ecology",

434 "economía": "economics",

435 # "Edafología": "edaphology",

436 "educación": "education",

437 "electricidad": "electricity",

438 "electromagnetismo": "electromagnetism",

439 "electrónica": "electronics",

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

441 # "Emojis": "emoji",

442 # "Emoticonos": "emoticons",

443 # "Enfermedades": "diseases",

444 "enología": "oenology",

445 # "Enseñanza": "teaching",

446 "entomología": "entomology",

447 # "Equinodermos": "echinoderms",

448 # "Equitación": "horse riding",

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

450 # "Escultura": "sculpture",

451 "esgrima": "fencing",

452 # "Especias": "spices",

453 "estaciones": "seasons",

454 "estadística": "statistics",

455 # "Estomatología": "stomatology",

456 # "Estética": "esthetic",

457 "fabril": "manufacturing",

458 # "Fantasía": "fancy",

459 # "Farmacia": "pharmacy",

460 "farmacología": "pharmacology",

461 "feminismo": "feminism",

462 # "Festividades": "festivities",

463 "ficción": "fiction",

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

465 "ficología": "phycology",

466 "filatelia": "philately",

467 "filosofía": "philosophy",

468 "finanzas": "finance",

469 "fisiología": "physiology",

470 # "Flores": "flowers",

471 # "Fobias": "phobias",

472 "folclore": "folklore",

473 "fonética": "phonetics",

474 # "Formas": "shapes",

475 "fotografía": "photography",

476 # "Fraccionarios": "fractionals",

477 # "Frutas": "fruit",

478 # "Frutos": "fruits",

479 "fármacos": "drugs",

480 # "Física": "physical",

481 "fútbol": "soccer",

482 # "Ganadería": "cattle raising",

483 # "Gastronomía": "gastronomy",

484 # "Gentilicios": "gentilicios",

485 "genética": "genetics",

486 "geografía": "geography",

487 "geología": "geology",

488 "geometría": "geometry",

489 # "Gimnasia": "gym",

490 # "Glotónimos": "gluttonyms",

491 "gramática": "grammar",

492 # "Granjería": "farming",

493 # "Guarismos": "figures",

494 "halconería": "falconry",

495 "herramientas": "tools",

496 "heráldica": "heraldry",

497 "hidrología": "hydrology",

498 # "Hierbas": "herbs",

499 # "Higiene": "hygiene",

500 # "Hipocorísticos": "hypocoristic",

501 "historia": "history",

502 # "Historieta": "cartoon",

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

504 # "Hongos": "fungus",

505 "horticultura": "horticulture",

506 # "Hostelería": "hostelry",

507 # "Huesos": "bones",

508 # "Humanidades": "humanities",

509 "ictiología": "ichthyology",

510 # "Lenguas": "languages",

511 "imprenta": "printing",

512 # "Industria": "industry",

513 "informática": "computing",

514 "ingeniería": "engineering",

515 "inmunología": "immunology",

516 "insectos": "insects",

517 # "Instrumentos": "instruments",

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

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

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

521 "internet": "Internet",

522 # "Invertebrados": "invertebrates",

523 "islam": "Islam",

524 # "Islas": "islands",

525 # "Judaísmo": "judaism",

526 "juegos": "games",

527 # "Juguetes": "toys",

528 "lgbt": "LGBT",

529 # "Lagos": "lakes",

530 "lexicografía": "lexicography",

531 "lingüística": "linguistics",

532 "literatura": "literature",

533 # "Logística": "logistics",

534 # "Lucha": "struggle",

535 # "Líquidos": "liquids",

536 "lógica": "logic",

537 "malabarismo": "juggling",

538 "mamíferos": "mammals",

539 # "Mares": "seas",

540 "náutica": "nautical",

541 "matemática": "mathematics",

542 # "Materia": "subject",

543 # "Materiales": "materials",

544 "mecánica": "mechanics",

545 "medicina": "medicine",

546 # "Meses": "months",

547 # "Metales": "metals",

548 "metalurgia": "metallurgy",

549 "meteorología": "meteorology",

550 "metrología": "metrology",

551 "micología": "mycology",

552 "microbiología": "microbiology",

553 "milicia": "military",

554 # "Minerales": "minerals",

555 "mineralogía": "mineralogy",

556 "minería": "mining",

557 "mitología": "mythology",

558 "mobiliario": "furniture",

559 # "Moluscos": "mollusks",

560 # "Monedas": "coins",

561 # "Moneras": "moneras",

562 # "Montañas": "mountains",

563 "muebles": "furniture",

564 "música": "music",

565 # "Naipes": "playing cards",

566 "natación": "swimming",

567 # "Naturaleza": "nature",

568 # "Nemátodos": "nematodes",

569 "neurología": "neurology",

570 "numismática": "numismatics",

571 # "Nutrición": "nutrition",

572 # "Números": "numbers",

573 "ocultismo": "occultism",

574 # "Ocupaciones": "activities",

575 # "Océanos": "oceans",

576 "odontología": "odontology",

577 # "Oficios": "trades",

578 "oftalmología": "ophthalmology",

579 "ornitología": "ornithology",

580 "paleontología": "paleontology",

581 "parapsicología": "parapsychology",

582 # "Parentesco": "relationship",

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

584 "países": "countries",

585 "peces": "fish",

586 # "Penínsulas": "peninsulas",

587 "periodismo": "journalism",

588 "perros": "dogs",

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

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

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

592 "pesca": "fishing",

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

594 # "Pintura": "paint",

595 "planetas": "planets",

596 # "Plantas": "floors",

597 # "Platelmintos": "platyhelminths",

598 # "Platos": "dishes",

599 # "Poblaciones": "populations",

600 "poesía": "poetry",

601 # "Política": "policy",

602 "pragmática": "pragmatics",

603 # "Prehistoria": "prehistory",

604 # "Vestimenta": "outfit",

605 # "Profesiones": "professions",

606 # "Protistas": "protists",

607 # "Pseudociencias": "pseudosciences",

608 "psicología": "psychology",

609 "psiquiatría": "psychiatry",

610 "química": "chemistry",

611 "química orgánica": "organic chemistry",

612 # "Radiocomunicación": "radiocomunication",

613 # "Regiones": "regions",

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

615 "religión": "religion",

616 # "Relojería": "watchmaking",

617 # "Reptiles": "reptiles",

618 # "Restaurantes": "restaurants",

619 # "Retórica": "rhetoric",

620 "rugby": "rugby",

621 # "Ríos": "rivers",

622 # "Sabores": "flavors",

623 "salud": "health",

624 # "Saludos": "greetings",

625 # "Satélites": "satellites",

626 # "Seguridad": "security",

627 # "Semiología": "semiology",

628 "semiótica": "semiotics",

629 # "Sentidos": "senses",

630 # "Sentimientos": "feelings",

631 "serpientes": "snakes",

632 "sexualidad": "sexuality",

633 # "Signos": "signs",

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

635 "silvicultura": "forestry",

636 # "Sociedad": "society",

637 "sociología": "sociology",

638 # "Símbolos": "symbols",

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

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

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

642 "tauromaquia": "bullfighting",

643 "taxonomía": "taxonomy",

644 "teatro": "theater",

645 "tecnología": "technology",

646 "textiles": "textiles",

647 "telecomunicaciones": "telecommunications",

648 # "Telecomunicación": "telecommunication",

649 "tenis": "tennis",

650 "teología": "theology",

651 "termodinámica": "thermodynamics",

652 "tiempo": "time",

653 "tipografía": "typography",

654 "topografía": "topography",

655 # "Topónimos": "toponyms",

656 "transporte": "transport",

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

658 "turismo": "tourism",

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

660 # "Urbanismo": "town planning",

661 # "Utensilios": "utensils",

662 "vegetales": "vegetable",

663 "vehículos": "vehicles",

664 "verduras": "vegetable",

665 # "Vertebrados": "vertebrates",

666 # "Veterinaria": "vet",

667 # "Virtudes": "virtues",

668 # "Vivienda": "living place",

669 # "Waterpolo": "water polo",

670 "zoología": "zoology",

671 "zootomía": "zootomy",

672 "álgebra": "algebra",

673 # "Árboles": "trees",

674 "ética": "ethics",

675 "óptica": "optics",

676}

677

678NUMBER_TAGS = {

679 # "inflect.*" templates

680 "singular": "singular",

681 "plural": "plural",

682 "dual": "dual",

683}

684

685GENDER_TAGS = {

686 "masculino": "masculine",

687 "femenino": "feminine",

688 "neutro": "neuter",

689}

690

691COMPARISON_TAGS = {

692 "positivo": "positive",

693 "comparativo": "comparative",

694 "superlativo": "superlative",

695}

696

697PERSON_TAGS = {

698 "primera": "first-person",

699 "segunda": "second-person",

700 "tercera": "third-person",

701}

702

703TENSE_TAGS = {

704 "presente": "present",

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

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

707 "futuro": "future",

708 "condicional": "conditional",

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

710 "pretérito pluscuamperfecto": "pluperfect",

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

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

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

714}

715

716VERB_FORM_TAGS = {

717 "infinitivo": "infinitive",

718 "gerundio": "gerund",

719 "participio": "participle",

720}

721

722TABLE_TAGS = {

723 # Plantilla:es.v

724 "formas no personales (verboides)": "impersonal",

725 "futuro compuesto": ["future", "compound"],

726 "pretérito perfecto compuesto": ["present", "perfect", "compound"],

727 "condicional simple": "conditional",

728 "condicional compuesto": ["conditional", "compound"],

729 "indicativo": "indicative",

730 "subjuntivo": "subjunctive",

731 "imperativo": "imperative",

732 # Plantilla:es.v.conj.ar

733 "formas no personales": "impersonal",

734 "formas personales": "personal",

735 "modo indicativo": "indicative",

736 "modo subjuntivo": "subjunctive",

737 "modo imperativo": "imperative",

738 "pretérito": "preterite",

739 # Template:inflect.ine.sust.atem.his.mf-C

740 "nominativo": "nominative",

741 "vocativo": "vocative",

742 "acusativo": "accusative",

743 "genitivo": "genitive",

744 "ablativo": "ablative",

745 "dativo": "dative",

746 "locativo": "locative",

747 "instrumental": "instrumental",

748 # Template:inflect.eu.sust.inanim.prop

749 "indefinido": "indefinite",

750 "definido": "definite",

751 "ergativo": "ergative",

752 "comitativo": "comitative",

753 "benefactivo": "benefactive",

754 "causativo": "causative",

755 "inesivo": "inessive",

756 "separativo": "separative",

757 "adlativo": "allative",

758 # "adl. extremo": ["allative"],

759 "adverbial": "adverbial",

760 "partitivo": "partitive",

761 "prolativo": "prolative",

762}

763

764SOUND_TAGS = {

765 # Template:pron-graf

766 "brasilero": "Brazilian",

767 "carioca": "Rio-de-Janeiro",

768 "gaúcho": "Rio-Grande-De-Sul",

769 "europeo": "European",

770 "central": "Central",

771 "valenciano": "Valencian",

772 "baleárico": "Balearic",

773 "eclesiástico": "Ecclesiastical",

774 "received pronunciation": "Received-Pronunciation",

775 "received pronunciation anticuado": ["Received-Pronunciation", "obsolete"],

776 "reino unido, obsoleto o dialectal": ["UK", "obsolete", "dialectal"],

777 "ee. uu.": "US",

778 "australia": "Australia",

779 "nueva zelanda": "New-Zealand",

780 "california": "California",

781 "received pronunciation, general american, canadá": [

782 "Received-Pronunciation",

783 "General-American",

784 "Canada",

785 ],

786 "australia, nueva zelanda": ["Australia", "New-Zealand"],

787 "india": "India",

788 "general american": "General-American",

789 "general american, canadá": ["General-American", "Canada"],

790 "general american, standard canadian": [

791 "General-American",

792 "Standard-Canadian",

793 ],

794 "londres": "London",

795}

796

797# Template:es.v

798ES_V_SUP_TAGS = {

799 "adj/adv": ["adjective", "adverb"],

800 "part": "participle",

801 "part/adj": ["participle", "adjective"],

802 "arg/uru": ["Argentina", "Uruguay"],

803}

804

805

806POS_TITLE_TAGS = {

807 "sustantiva": "substantive",

808 "femenina": "feminine",

809 "masculina": "masculine",

810 "ordinal": "ordinal",

811 "partitiva": "partitive",

812 "adjetiva": "adjectival",

813}

814

815

816ALL_TAGS = {

817 **NUMBER_TAGS,

818 **GENDER_TAGS,

819 **COMPARISON_TAGS,

820 **PERSON_TAGS,

821 **TENSE_TAGS,

822 **VERB_FORM_TAGS,

823 **TABLE_TAGS,

824 **SOUND_TAGS,

825 **ES_V_SUP_TAGS,

826 **POS_TITLE_TAGS,

827 "afirmativo": "affirmative",

828 "negativo": "negative",

829 "simples": "simple",

830 "compuestas": "compound",

831 "invariante": "invariable",

832}

833

834

835def translate_raw_tags(data: WordEntry):

836 raw_tags = []

837 for raw_tag in data.raw_tags:

838 lower_raw_tag = raw_tag.lower()

839 if lower_raw_tag in ALL_TAGS:

840 tr_tag = ALL_TAGS[lower_raw_tag]

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

842 data.tags.append(tr_tag)

843 elif isinstance(tr_tag, list): 843 ↛ 837line 843 didn't jump to line 837 because the condition on line 843 was always true

844 for tag in tr_tag:

845 if tag not in data.tags: 845 ↛ 844line 845 didn't jump to line 844 because the condition on line 845 was always true

846 data.tags.append(tag)

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

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

849 elif raw_tag in AMBITO_TAGS:

850 tr_tag = AMBITO_TAGS[raw_tag]

851 if isinstance(tr_tag, str) and tr_tag not in data.tags: 851 ↛ 853line 851 didn't jump to line 853 because the condition on line 851 was always true

852 data.tags.append(tr_tag)

853 elif isinstance(tr_tag, list):

854 data.tags.extend(tr_tag)

855 else:

856 raw_tags.append(raw_tag)

857 data.raw_tags = raw_tags