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

1# Grammatical glossary appendix:

2# https://fr.wiktionary.org/wiki/Annexe:Glossaire_grammatical

3# List of templates:

4# https://fr.wiktionary.org/wiki/Wiktionnaire:Liste_de_tous_les_modèles

5from .models import WordEntry

7# https://en.wikipedia.org/wiki/Grammatical_gender

8GENDER_TAGS: dict[str, str | list[str]] = {

9 "commun": "common",

10 "féminin": "feminine",

11 "masculin": "masculine",

12 "neutre": "neuter",

13 # https://fr.wiktionary.org/wiki/Modèle:mf

14 "masculin et féminin identiques": ["masculine", "feminine"],

15 # table header: https://fr.wiktionary.org/wiki/Modèle:fr-rég

16 "masculin et féminin": ["masculine", "feminine"],

17 # "Modèle:mf ?", "Modèle:fm ?"

18 "masculin ou féminin (l’usage hésite)": ["masculine", "feminine"],

19 "féminin ou masculin (l’usage hésite)": ["feminine", "masculine"],

20 "invariable": "invariable", # Modèle:invar

21}

23# https://en.wikipedia.org/wiki/Grammatical_number

24NUMBER_TAGS: dict[str, str | list[str]] = {

25 "singulier": "singular",

26 "pluriel": "plural",

27 "duel": "dual",

28 "collectif": "collective",

29 "singulatif": "singulative",

30 "indénombrable": "uncountable", # sv-nom-c-ind

31 "au singulier": "singular",

32 "au singulier uniquement": "singular-only",

33 "au pluriel": "plural",

34 "au pluriel uniquement": "plural-only",

35 "singulier et pluriel identiques": ["singular", "plural"],

36 "nom collectif": "collective",

37 # "générique": "", # Modèle:g

38 # "nom d'unité": "", # Modèle:nu

39 "généralement indénombrable": "uncountable",

40 "dénombrable": "countable",

41}

43# https://en.wikipedia.org/wiki/Grammatical_mood

44MOOD_TAGS: dict[str, str] = {

45 "indicatif": "indicative",

46 "subjonctif": "subjunctive",

47 "conditionnel": "conditional",

48 "impératif": "imperative",

49 "volitif": "volitive",

50}

52VERB_FORM_TAGS: dict[str, str | list[str]] = {

53 "participe": "participle",

54 "imparfait": "imperfect",

55 "infinitif": "infinitive",

56 "gérondif": "gerund",

57 # template "pt-verbe-flexion"

58 "infinitif personnel": ["infinitive", "personal"],

59 "supin": "supine",

60}

62# https://en.wikipedia.org/wiki/Grammatical_case

63CASE_TAGS: dict[str, str | list[str]] = {

64 "ablatif": "ablative",

65 "accusatif": "accusative",

66 "accusatif génitif": ["accusative", "genitive"],

67 "nominatif": "nominative",

68 "datif": "dative",

69 "génitif": "genitive",

70 "vocatif": "vocative",

71 "instrumental": "instrumental",

72 "locatif": "locative",

73 "comitatif": "comitative",

74 "essif": "essive",

75 "illatif": "illative",

76}

78# https://en.wikipedia.org/wiki/Grammatical_tense

79TENSE_TAGS: dict[str, str | list[str]] = {

80 "présent": "present",

81 "passé": "past",

82 "passé simple": "past",

83 "futur": "future",

84 "futur simple": "future",

85 # https://en.wikipedia.org/wiki/Passé_composé

86 "passé composé": "past multiword-construction",

87 "plus-que-parfait": "pluperfect",

88 "passé antérieur": "past anterior",

89 "futur antérieur": "future perfect",

90 "prétérit": "preterite",

91 "présent simple, 3ᵉ pers. sing.": ["present", "third-person", "singular"],

92 "participe passé": ["participle", "past"],

93 "participe présent": ["participle", "present"],

94}

96# https://en.wikipedia.org/wiki/Grammatical_person

97PERSON_TAGS: dict[str, str | list[str]] = {

98 "1ᵉ personne": "first-person",

99 "1ʳᵉ personne": "first-person",

100 "2ᵉ personne": "second-person",

101 "3ᵉ personne": "third-person",

102 # Modèle:avk-conj

103 "1ʳᵉ du sing.": ["first-person", "singular"],

104 "2ᵉ du sing.": ["second-person", "singular"],

105 "3ᵉ du sing.": ["third-person", "singular"],

106 "1ʳᵉ du plur.": ["first-person", "plural"],

107 "2ᵉ du plur.": ["second-person", "plural"],

108 "3ᵉ du plur.": ["third-person", "plural"],

109 "4ᵉ du plur.": ["fourth-person", "plural"],

110}

111

112SEMANTICS_TAGS: dict[str, str] = {

113 # https://en.wikipedia.org/wiki/Definiteness

114 "défini": "definite",

115 "indéfini": "indefinite",

116}

117

118COMPARISON_TAGS: dict[str, str] = {

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

120 "positif": "positive",

121 "comparatif": "comparative",

122 "superlatif": "superlative",

123}

124

125# https://en.wikipedia.org/wiki/Occitan_language#Writing_system

126OCCITAN_NORM_TAGS: dict[str, str] = {

127 # https://fr.wiktionary.org/wiki/Modèle:oc-norme_mistralienne

128 "graphie mistralienne": "Mistralian",

129 # https://fr.wiktionary.org/wiki/Modèle:oc-norme_classique

130 # "graphie normalisée": "",

131 # Modèle:oc-norme bonnaudienne

132 # "graphie bonnaudienne": "",

133}

134

135# https://en.wikipedia.org/wiki/Breton_mutations

136# https://fr.wiktionary.org/wiki/Modèle:br-nom

137BRETON_MUTATION_TAGS: dict[str, str] = {

138 "non muté": "unmutated",

139 "adoucissante": "mutation-soft",

140 "durcissante": "mutation-hard",

141 "spirante": "mutation-spirant",

142 "nasale": "mutation-nasal",

143}

144

145JA_TAGS: dict[str, str] = {

146 # https://fr.wiktionary.org/wiki/Modèle:ja-trans

147 "kanji": "kanji",

148 "hiragana": "hiragana",

149 "katakana": "katakana",

150 "transcription": "transcription",

151}

152

153OTHER_GRAMMATICAL_TAGS: dict[str, str] = {

154 # https://fr.wiktionary.org/wiki/Modèle:be-tab-cas

155 "prépositionnel": "prepositional",

156 "anglicisme": "Anglicism",

157 "pronominal": "pronominal",

158 "diminutif": "diminutive",

159 "réfléchi": "reflexive", # Modèle:réfl

160 "réciproque": "reciprocal", # Modèle:réciproque

161 "impersonnel": "impersonal", # Modèle:impers

162 "transitif": "transitive", # Modèle:t

163 "intransitif": "intransitive", # Modèle:i

164 "injurieux": "offensive", # Modèle:injurieux

165 # Modèle:zh-formes

166 "simplifié": "Simplified Chinese",

167 "traditionnel": "Traditional Chinese",

168}

169

170# template text before gloss

171SENSE_TAGS: dict[str, str] = {

172 # https://fr.wiktionary.org/wiki/Modèle:figuré

173 # https://fr.wiktionary.org/wiki/Catégorie:Modèles_de_relation_entre_les_définitions

174 # Catégorie:Modèles de genre textuel

175 # Catégorie:Modèles de registre

176 "sens figuré": "figuratively",

177 "sens propre": "literally",

178 "par métonymie": "metonymically", # Modèle:par métonymie

179 "par hyperbole": "hyperbole",

180 "par extension": "broadly",

181 "par analogie": "analogy",

182 "en particulier": "especially",

183 "par litote": "litotes",

184 "par euphémisme": "euphemism",

185 "spécifiquement": "specifically",

186 "génériquement": "generically",

187 "spécialement": "especially",

188 "généralement": "generally",

189 "enclise": "enclitic",

190 "idiotisme": "idiomatic",

191 "péjoratif": "pejorative",

192 "désuet": "obsolete",

193 "archaïsme": "archaic",

194 "vieilli": "dated",

195 "néologisme": "neologism",

196 "argot": "slang",

197 "rare": "rare",

198 # "plus rare": "rare",

199 "littéraire": "literary", # Modèle:littéraire

200 "poétique": "poetic", # Modèle:poétique

201 # "didactique": "", # Modèle:didactique

202 "soutenu": "formal", # Modèle:soutenu

203 "informel": "informal", # Modèle:informel

204 "familier": "familiar", # Modèle:familier

205 "très familier": "very-familiar", # Modèle:très familier

206 "populaire": "colloquial", # Modèle:populaire

207 "vulgaire": "vulgar", # Modèle:vulgaire

208 "langage enfantin": "childish", # Modèle:enfantin

209 # Catégorie:Modèles de thématique

210 "anglicisme informatique": "Anglicism",

211 "proverbe": "proverb",

212 "collectivement": "collectively",

213 "courant": "common", # Modèle:courant

214}

215

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

217VOICE_TAGS: dict[str, str | list[str]] = {

218 # https://fr.wiktionary.org/wiki/Modèle:eo-conj

219 "participe actif": ["participle", "active"],

220 "participe passif": ["participle", "passive"],

221 "adverbe actif": ["adverb", "active"],

222 "adverbe passif": ["adverb", "passive"],

223 "substantif actif": ["subsuntive", "active"],

224 "substantif passif": ["subsuntive", "passive"],

225 "actif": "active",

226 "passif": "passive",

227}

228

229# Module:lexique/data

230LEXIQUE_TAGS = {

231 "hindouisme": "Hinduism",

232 "judaïsme": "Judaism",

233 "marxisme": "Marxism",

234 "nazisme": "Nazism",

235 "physique": "physical",

236 "rhétorique": "rhetoric",

237 "antiquité": "Ancient",

238 "antiquité grecque": "Ancient-Greek",

239 "antiquité romaine": "Ancient-Roman",

240 "bible": "Biblical",

241 "moyen âge": "Middle-Ages",

242 "union européenne": "European-Union",

243 "analyse": "analytic",

244}

245

246# Template:cmn-pron

247# https://fr.wiktionary.org/wiki/自由

248ZH_PRON_TAGS = {

249 "pinyin": "Pinyin",

250 "efeo": "EFEO", # https://en.wikipedia.org/wiki/EFEO_Chinese_transcription

251 "wade-giles": "Wade-Giles",

252 "yale": "Yale",

253 "zhuyin": "Bopomofo",

254 "mandarin": "Mandarin",

255 "cantonais": "Cantonese",

256 "cantonais (yue)": "Cantonese",

257 "jyutping": "Jyutping",

258 "hakka": "Hakka",

259 "pha̍k-fa-sṳ": "Phak-fa-su",

260 "meixian, guangdong": ["Meixian", "Guangdong"],

261 "jin": "Jin",

262 "mindong": "Eastern-Min",

263 # https://en.wikipedia.org/wiki/Bàng-uâ-cê

264 "bàng-uâ-cê (fuzhou)": ["Bang-ua-ce", "Fuzhou"],

265 "minnan": "Min",

266 "pe̍h-ōe-jī (hokkien : fujian, taïwan)": [

267 "Peh-oe-ji",

268 "Hokkien",

269 "Fujian",

270 "Taiwan",

271 ],

272 "chaozhou, peng'im": ["Chaozhou", "Peng'im"],

273 "wu": "Wu",

274 "shanghai": "Shanghai",

275 "chinois médiéval": "Medieval-Chinese",

276 "chinois archaïque": "Old-Chinese",

277 "baxter-sagart": "Baxter-Sagart",

278 "zhengzhang": "Zhengzhang",

279}

280

281ASPECT_TAGS = {

282 "perfectif": "perfective", # Modèle:perfectif

283 "imperfectif": "imperfective", # Modèle:imperfectif

284}

285

286GRAMMATICAL_TAGS: dict[str, str | list[str]] = {

287 **GENDER_TAGS,

288 **NUMBER_TAGS,

289 **MOOD_TAGS,

290 **VERB_FORM_TAGS,

291 **CASE_TAGS,

292 **TENSE_TAGS,

293 **PERSON_TAGS,

294 **SEMANTICS_TAGS,

295 **COMPARISON_TAGS,

296 **OCCITAN_NORM_TAGS,

297 **BRETON_MUTATION_TAGS,

298 **JA_TAGS,

299 **OTHER_GRAMMATICAL_TAGS,

300 **SENSE_TAGS,

301 **VOICE_TAGS,

302 **LEXIQUE_TAGS,

303 **ZH_PRON_TAGS,

304 **ASPECT_TAGS,

305}

306

307

308def translate_raw_tags(

309 data: WordEntry,

310 table_template_name: str = "",

311 tag_dict: dict[str, str] = GRAMMATICAL_TAGS,

312) -> WordEntry:

313 from .topics import SLANG_TOPICS, TOPIC_TAGS

314

315 raw_tags = []

316 for raw_tag in data.raw_tags:

317 raw_tag_lower = raw_tag.lower()

318 if raw_tag_lower in tag_dict:

319 tr_tag = tag_dict[raw_tag_lower]

320 if isinstance(tr_tag, str):

321 data.tags.append(tr_tag)

322 elif isinstance(tr_tag, list): 322 ↛ 316line 322 didn't jump to line 316 because the condition on line 322 was always true

323 data.tags.extend(tr_tag)

324 elif hasattr(data, "topics") and raw_tag_lower in TOPIC_TAGS:

325 data.topics.append(TOPIC_TAGS[raw_tag_lower])

326 elif hasattr(data, "topics") and raw_tag_lower in SLANG_TOPICS: 326 ↛ 327line 326 didn't jump to line 327 because the condition on line 326 was never true

327 data.topics.append(SLANG_TOPICS[raw_tag_lower])

328 if "slang" not in data.tags:

329 data.tags.append("slang")

330 else:

331 raw_tags.append(raw_tag)

332 data.raw_tags = raw_tags

333 if table_template_name != "":

334 return convert_table_headers(data, table_template_name)

335 return data

336

337

338def convert_table_headers(data: WordEntry, template_name: str) -> WordEntry:

339 if template_name == "avk-tab-conjug": 339 ↛ 341line 339 didn't jump to line 341 because the condition on line 339 was never true

340 # https://fr.wiktionary.org/wiki/Modèle:avk-tab-conjug

341 tags = {

342 "1": "first-person",

343 "2": "second-person",

344 "3": "third-person",

345 "4": "fourth-person",

346 }

347 return translate_raw_tags(data, tag_dict=tags)

348 return data