Changes In Branch Lexicographe Excluding Merge-Ins
This is equivalent to a diff from 4ffad6e596 to d9c2fd3783
2017-11-25
| ||
16:17 | [core][fx][fr] merge Lexicographe: detection of most common locutions check-in: c60b538430 user: olr tags: trunk, fr, core, new_feature, fx | |
2017-11-22
| ||
23:50 | [fr] màj: locutions adverbiales Closed-Leaf check-in: d9c2fd3783 user: olr tags: fr, Lexicographe | |
16:42 | [fr] màj: locutions prépositives + divers check-in: 048bf69ad3 user: olr tags: fr, Lexicographe | |
2017-10-29
| ||
11:19 | Détection des locutions dans le lexicographe check-in: 47ddd1a06d user: IllusionPerdu tags: Lexicographe | |
2017-10-28
| ||
19:58 | [build][fr] build_data: code cleaning check-in: ba1b8fe0e2 user: olr tags: trunk, fr, build | |
13:47 | [build][fr] rename locutions files check-in: 4ffad6e596 user: olr tags: trunk, fr, build | |
13:17 | [build][fr] data: locutions check-in: e356116b6e user: olr tags: trunk, fr, build | |
Modified gc_core/js/text.js from [9bf91b3594] to [abcdad5f85].
1 2 3 4 5 6 7 8 9 10 11 12 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | - + - + | // JavaScript /*jslint esversion: 6*/ /*global require,exports*/ "use strict"; if (typeof(require) !== 'undefined') { var helpers = require("resource://grammalecte/helpers.js"); } var text = { |
︙ | |||
41 42 43 44 45 46 47 | 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 | - + | } yield sText; }, getReadableError: function (oErr) { // Returns an error oErr as a readable error try { |
︙ |
Modified gc_core/js/tokenizer.js from [9bb6ea03fb] to [a34a81c6e5].
︙ | |||
12 13 14 15 16 17 18 | 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | - - + + + - - + + + | const aTkzPatterns = { // All regexps must start with ^. "default": [ [/^[ \t]+/, 'SPACE'], |
︙ | |||
64 65 66 67 68 69 70 | 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | - + - + | while (sText) { let nCut = 1; for (let [zRegex, sType] of this.aRules) { try { if ((m = zRegex.exec(sText)) !== null) { if (sType == 'SEPARATOR') { for (let c of m[0]) { |
︙ |
Modified gc_core/py/tokenizer.py from [5a9c0c9105] to [17f452887e].
1 2 3 4 5 6 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | - - + + + - - + + + | # Very simple tokenizer import re _PATTERNS = { "default": ( |
︙ |
Modified gc_lang/fr/build_data.py from [1ffed9614b] to [1c5ad0c32d].
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 | + + + + + + + + + + + + + + + | #!python3 # FRENCH DATA BUILDER # # by Olivier R. # License: MPL 2 import json import os import itertools import grammalecte.ibdawg as ibdawg from grammalecte.echo import echo from grammalecte.str_transform import defineSuffixCode import grammalecte.fr.conj as conj import grammalecte.tokenizer as tkz class cd: """Context manager for changing the current working directory""" def __init__ (self, newPath): self.newPath = os.path.expanduser(newPath) def __enter__ (self): self.savedPath = os.getcwd() os.chdir(self.newPath) def __exit__ (self, etype, value, traceback): os.chdir(self.savedPath) def readFile (spf): if os.path.isfile(spf): with open(spf, "r", encoding="utf-8") as hSrc: for sLine in hSrc: sLine = sLine.strip() if sLine == "__END__": break if sLine and not sLine.startswith("#"): yield sLine else: raise OSError("# Error. File not found or not loadable: " + spf) def makeDictionaries (sp, sVersion): with cd(sp+"/dictionnaire"): os.system("genfrdic.py -s -gl -v "+sVersion) def makeConj (sp, bJS=False): |
︙ | |||
45 46 47 48 49 50 51 | 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | - - - + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + | "spre": ":Sp", "simp": ":Sq", "cond": ":K", "impe": ":E", "1sg": ":1s", "2sg": ":2s", "3sg": ":3s", "1pl": ":1p", "2pl": ":2p", "3pl": ":3p", "1isg": ":1ś", "mas sg": ":Q1", "mas pl": ":Q2", "mas inv": ":Q1", "fem sg": ":Q3", "fem pl": ":Q4", "epi inv": ":Q1" } # read lexicon |
︙ | |||
167 168 169 170 171 172 173 | 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 | - - - - - + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + | print("(Python et JavaScript)" if bJS else "(Python seulement)") aPlurS = set() dTag = {} lTagMasForm = [] lTagMiscPlur = [] dMiscPlur = {} dMasForm = {} |
︙ | |||
254 255 256 257 258 259 260 | 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 | - + - - - - + + + - - - - - - - - + + + + + + + - - - - - - - - - - - - - + + + + + + + + + + + + | ' "dMasForm": ' + json.dumps(dMasForm, ensure_ascii=False) + "\n}" open(sp+"/modules-js/mfsp_data.json", "w", encoding="utf-8", newline="\n").write(sCode) def makePhonetTable (sp, bJS=False): print("> Correspondances phonétiques ", end="") print("(Python et JavaScript)" if bJS else "(Python seulement)") |
︙ | |||
307 308 309 310 311 312 313 | 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 | + + + - - - + + + + + + + - - - - - - - + + + + + + + + - + - + | open(sp+"/modules-js/phonet_data.json", "w", encoding="utf-8", newline="\n").write(sCode) def makeLocutions (sp, bJS=False): "compile list of locutions in JSON" print("> Locutions ", end="") print("(Python et JavaScript)" if bJS else "(Python seulement)") dLocGraph = {} oTokenizer = tkz.Tokenizer("fr") for sLine in itertools.chain(readFile(sp+"/data/locutions_adverbiales.txt"), \ |
Modified gc_lang/fr/config.ini from [c76d410d86] to [bd9c32e343].
︙ | |||
29 30 31 32 33 34 35 | 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | - + | oxt_identifier = French.linguistic.resources.from.Dicollecte.by.OlivierR # Firefox fx_identifier = French-GC@grammalecte.net fx_name = Grammalecte [fr] win_fx_dev_path = C:\Program Files\Firefox Developer Edition\firefox.exe |
︙ |
Deleted gc_lang/fr/data/locutions.txt version [190d018874].
| - - - - - - - - |
|
Added gc_lang/fr/data/locutions_adjectivales.txt version [93e8503ac2].