Comment: | [core][fr][graphspell] code cleaning: pylint |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk | fr | core | graphspell |
Files: | files | file ages | folders |
SHA3-256: |
78b5950c87d2dfdbdce793c7f94a63fe |
User & Date: | olr on 2021-02-10 11:39:52 |
Other Links: | manifest | tags |
2021-02-10
| ||
12:11 | [fr] mise à jour du dictionnaire check-in: 53cc1dda5b user: olr tags: fr, trunk, v2.1.0 | |
11:39 | [core][fr][graphspell] code cleaning: pylint check-in: 78b5950c87 user: olr tags: core, fr, graphspell, trunk | |
10:14 | [fr] faux positifs et ajustements check-in: 4698a4f99c user: olr tags: fr, trunk | |
Modified gc_core/py/grammar_checker.py from [50b054f72f] to [73cbb643ff].
︙ | ︙ |
Modified gc_core/py/lang_core/gc_engine.py from [ce7092fc44] to [2b36e73536].
︙ | ︙ | |||
233 234 235 236 237 238 239 240 241 242 243 244 245 246 | def __init__ (self, sText): self.sText = sText self.sText0 = sText self.sSentence = "" self.sSentence0 = "" self.nOffsetWithinParagraph = 0 self.lTokens = [] self.dTokenPos = {} # {position: token} self.dTags = {} # {position: tags} self.dError = {} # {position: error} self.dSentenceError = {} # {position: error} (for the current sentence only) self.dErrorPriority = {} # {position: priority of the current error} def __str__ (self): | > | 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 | def __init__ (self, sText): self.sText = sText self.sText0 = sText self.sSentence = "" self.sSentence0 = "" self.nOffsetWithinParagraph = 0 self.lTokens = [] self.lTokens0 = [] self.dTokenPos = {} # {position: token} self.dTags = {} # {position: tags} self.dError = {} # {position: error} self.dSentenceError = {} # {position: error} (for the current sentence only) self.dErrorPriority = {} # {position: priority of the current error} def __str__ (self): |
︙ | ︙ | |||
264 265 266 267 268 269 270 | dOpt = dOptions or gc_options.dOptions bShowRuleId = gc_options.dOptions.get('idrule', False) # parse paragraph try: self.parseText(self.sText, self.sText0, True, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext) except: raise | < < | 265 266 267 268 269 270 271 272 273 274 275 276 277 278 | dOpt = dOptions or gc_options.dOptions bShowRuleId = gc_options.dOptions.get('idrule', False) # parse paragraph try: self.parseText(self.sText, self.sText0, True, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext) except: raise if bFullInfo: lParagraphErrors = list(self.dError.values()) lSentences = [] self.dSentenceError.clear() # parse sentences sText = self._getCleanText() for iStart, iEnd in text.getSentenceBoundaries(sText): |
︙ | ︙ | |||
299 300 301 302 303 304 305 | }) self.dSentenceError.clear() except: raise if bFullInfo: # Grammar checking and sentence analysis return lParagraphErrors, lSentences | < | | | 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | }) self.dSentenceError.clear() except: raise if bFullInfo: # Grammar checking and sentence analysis return lParagraphErrors, lSentences # Grammar checking only return self.dError.values() # this is a view (iterable) def _getCleanText (self): sText = self.sText if " " in sText: sText = sText.replace(" ", ' ') # nbsp if " " in sText: sText = sText.replace(" ", ' ') # nnbsp |
︙ | ︙ | |||
811 812 813 814 815 816 817 | if bUppercase: sWhat = sWhat[0:1].upper() + sWhat[1:] self.lTokens[nTokenRewriteStart]["sNewValue"] = sWhat else: # several tokens lTokenValue = sWhat.split("|") if len(lTokenValue) != (nTokenRewriteEnd - nTokenRewriteStart + 1): | | < | 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 | if bUppercase: sWhat = sWhat[0:1].upper() + sWhat[1:] self.lTokens[nTokenRewriteStart]["sNewValue"] = sWhat else: # several tokens lTokenValue = sWhat.split("|") if len(lTokenValue) != (nTokenRewriteEnd - nTokenRewriteStart + 1): if bDebug: echo("Error. Text processor: number of replacements != number of tokens.") return for i, sValue in zip(range(nTokenRewriteStart, nTokenRewriteEnd+1), lTokenValue): if not sValue or sValue == "*": self.lTokens[i]["bToRemove"] = True else: if bUppercase: sValue = sValue[0:1].upper() + sValue[1:] self.lTokens[i]["sNewValue"] = sValue def rewriteFromTags (self, bDebug=False): "rewrite the sentence, modify tokens, purge the token list" if bDebug: echo("REWRITE") lNewTokens = [] nMergeUntil = 0 dTokenMerger = {} for iToken, dToken in enumerate(self.lTokens): bKeepToken = True if dToken["sType"] != "INFO": if nMergeUntil and iToken <= nMergeUntil: # token to merge |
︙ | ︙ |
Modified gc_core/py/lang_core/gc_functions.py from [66b95f87c6] to [069bca6c44].
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 | """ Grammar checking functions """ # generated code, do not edit # template: <gc_core/py/lang_core/gc_functions.py> # variables generated in <compile_rules.py> import re from . import gc_options from ..graphspell.echo import echo _sAppContext = "Python" # what software is running _oSpellChecker = None def load (sContext, oSpellChecker): global _sAppContext global _oSpellChecker _sAppContext = sContext _oSpellChecker = oSpellChecker #### common functions | > > | 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 | """ Grammar checking functions """ # generated code, do not edit # template: <gc_core/py/lang_core/gc_functions.py> # variables generated in <compile_rules.py> import re import traceback from . import gc_options from ..graphspell.echo import echo _sAppContext = "Python" # what software is running _oSpellChecker = None def load (sContext, oSpellChecker): "mandatory first function to call: variables initialization" global _sAppContext global _oSpellChecker _sAppContext = sContext _oSpellChecker = oSpellChecker #### common functions |
︙ | ︙ |
Modified gc_core/py/lang_core/gc_options.py from [cafc10d4fb] to [dd3e857111].
︙ | ︙ | |||
12 13 14 15 16 17 18 19 20 21 22 23 24 25 | dOptions = {} _sAppContext = "Python" def load (sContext="Python"): global dOptions global _sAppContext _sAppContext = sContext dOptions = getDefaultOptions(sContext) def setOption (sOpt, bVal): | > | 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | dOptions = {} _sAppContext = "Python" def load (sContext="Python"): "mandatory first function to call: variables initialization" global dOptions global _sAppContext _sAppContext = sContext dOptions = getDefaultOptions(sContext) def setOption (sOpt, bVal): |
︙ | ︙ |
Modified gc_core/py/lang_core/tests_core.py from [be13fd30fe] to [b93cf9942d].
︙ | ︙ | |||
73 74 75 76 77 78 79 | if not os.path.exists(spfParsingTest): print(f"No file <gc_test.txt> in <{spHere}>") return with open(spfParsingTest, "r", encoding="utf-8") as hSrc: nUnexpectedErrors = 0 nTestWithExpectedError = 0 nTestWithExpectedErrorAndSugg = 0 | | | 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 | if not os.path.exists(spfParsingTest): print(f"No file <gc_test.txt> in <{spHere}>") return with open(spfParsingTest, "r", encoding="utf-8") as hSrc: nUnexpectedErrors = 0 nTestWithExpectedError = 0 nTestWithExpectedErrorAndSugg = 0 for sLine in ( s for s in hSrc if not s.startswith("#") and s.strip() ): sLineNum = sLine[:10].strip() sLine = sLine[10:].strip() sOption = None m = zOption.search(sLine) if m: sLine = sLine[m.end():] sOption = m.group(1) |
︙ | ︙ | |||
181 182 183 184 185 186 187 188 189 190 191 192 193 194 | lFoundSuggs = sFoundSuggs.split("|") if len(lExpectedSuggs) != len(lFoundSuggs) or set(lExpectedSuggs) != set(lFoundSuggs): return False return True def purgeMessage (sMessage): for sToReplace, sReplacement in [ ("l’ ", "l’"), ("d’ ", "d’"), ("n’ ", "n’"), ("j’ ", "j’"), ("m’ ", "m’"), ("t’ ", "t’"), ("s’ ", "s’"), ("qu’ ", "qu’"), ("L’ ", "L’"), ("D’ ", "D’"), ("N’ ", "N’"), ("J’ ", "J’"), ("M’ ", "M’"), ("T’ ", "T’"), ("S’ ", "S’"), ("QU’ ", "QU’") ]: sMessage = sMessage.replace(sToReplace, sReplacement) return sMessage | > | 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 | lFoundSuggs = sFoundSuggs.split("|") if len(lExpectedSuggs) != len(lFoundSuggs) or set(lExpectedSuggs) != set(lFoundSuggs): return False return True def purgeMessage (sMessage): "remove space after elided French words" for sToReplace, sReplacement in [ ("l’ ", "l’"), ("d’ ", "d’"), ("n’ ", "n’"), ("j’ ", "j’"), ("m’ ", "m’"), ("t’ ", "t’"), ("s’ ", "s’"), ("qu’ ", "qu’"), ("L’ ", "L’"), ("D’ ", "D’"), ("N’ ", "N’"), ("J’ ", "J’"), ("M’ ", "M’"), ("T’ ", "T’"), ("S’ ", "S’"), ("QU’ ", "QU’") ]: sMessage = sMessage.replace(sToReplace, sReplacement) return sMessage |
︙ | ︙ |
Modified gc_lang/fr/modules-js/gce_suggestions.js from [dddc903a64] to [fd0125da80].
︙ | ︙ | |||
168 169 170 171 172 173 174 | if (conj.hasConj(sStem, sTense, sWho)) { aSugg.add(conj.getConj(sStem, sTense, sWho)); } } } else { for (let [sTense, ] of lTenses) { | | | | | 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 | if (conj.hasConj(sStem, sTense, sWho)) { aSugg.add(conj.getConj(sStem, sTense, sWho)); } } } else { for (let [sTense, ] of lTenses) { for (let [sWho2, ] of [ ...sMorph.matchAll(/:(?:[123][sp]|P|Y)/g) ]) { if (conj.hasConj(sStem, sTense, sWho2)) { aSugg.add(conj.getConj(sStem, sTense, sWho2)); } } } } } if (aSugg.size > 0) { return Array.from(aSugg).join("|"); |
︙ | ︙ |
Modified gc_lang/fr/modules/conj.py from [bb0326be30] to [c6776ced05].
︙ | ︙ | |||
63 64 65 66 67 68 69 | def getNamesFrom (sVerb): "returns a list of names derivating from <sVerb>" if sVerb in _dVerbNames: # there are names derivated from the verb return list(_dVerbNames[sVerb]) | < | | | | | | | | | | | | | | 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 | def getNamesFrom (sVerb): "returns a list of names derivating from <sVerb>" if sVerb in _dVerbNames: # there are names derivated from the verb return list(_dVerbNames[sVerb]) # nothing found: we suggest past participles tTags = _getTags(sVerb) if tTags: aSugg = [ _getConjWithTags(sVerb, tTags, ":Q", ":m:s") ] if _hasConjWithTags(tTags, ":Q", ":f:s"): aSugg.append(_getConjWithTags(sVerb, tTags, ":Q", ":f:s")) if _hasConjWithTags(tTags, ":Q", ":m:p"): aSugg.append(_getConjWithTags(sVerb, tTags, ":Q", ":m:p")) if _hasConjWithTags(tTags, ":Q", ":f:p"): aSugg.append(_getConjWithTags(sVerb, tTags, ":Q", ":f:p")) # if there is only one past participle (epi inv), unreliable. return aSugg if len(aSugg) > 1 else [] return [] def getConjSimilInfiV1 (sInfi): "returns verbal forms phonetically similar to infinitive form (for verb in group 1)" if sInfi not in _dVerb: return [] aSugg = [] |
︙ | ︙ |
Modified gc_lang/fr/modules/gce_suggestions.py from [fdf32f5da9] to [c065ff780e].
︙ | ︙ | |||
37 38 39 40 41 42 43 | aTense[":Ip"] = "" aTense[":Iq"] = "" aTense[":Is"] = "" elif m.group(1) == ":P": aTense[":Ip"] = "" else: aTense[m.group(1)] = "" | | | | > | 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | aTense[":Ip"] = "" aTense[":Iq"] = "" aTense[":Is"] = "" elif m.group(1) == ":P": aTense[":Ip"] = "" else: aTense[m.group(1)] = "" for sTense in aTense: if sWho == ":1ś" and not conj._hasConjWithTags(tTags, sTense, ":1ś"): sWho = ":1s" if conj._hasConjWithTags(tTags, sTense, sWho): dSugg[conj._getConjWithTags(sStem, tTags, sTense, sWho)] = "" if funcSugg2: sSugg2 = funcSugg2(*args) if args else funcSugg2(sFlex) if sSugg2: dSugg[sSugg2] = "" if dSugg: if bVC: return "|".join([ joinVerbAndSuffix(sSugg, sSfx) for sSugg in dSugg ]) return "|".join(dSugg) return "" def joinVerbAndSuffix (sFlex, sSfx): "join <sFlex> verb with <sSfx> suffix, modifying <sFlex> to prevent irregular forms" if sSfx.startswith(("-t-", "-T-")) and sFlex.endswith(("t", "d", "T", "D")): return sFlex + sSfx[2:] if sFlex.endswith(("e", "a", "c", "E", "A", "C")): if re.match("(?i)-(?:en|y)$", sSfx): return sFlex + "s" + sSfx if re.match("(?i)-(?:ie?l|elle|on)$", sSfx): return sFlex + "-t" + sSfx |
︙ | ︙ | |||
106 107 108 109 110 111 112 | dSugg[conj._getConjWithTags(sStem, tTags, ":Q", ":m:s")] = "" dSugg[conj._getConjWithTags(sStem, tTags, ":Q", ":f:p")] = "" else: dSugg[conj._getConjWithTags(sStem, tTags, ":Q", ":m:s")] = "" if "" in dSugg: del dSugg[""] if dSugg: | | | | | | | | 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | dSugg[conj._getConjWithTags(sStem, tTags, ":Q", ":m:s")] = "" dSugg[conj._getConjWithTags(sStem, tTags, ":Q", ":f:p")] = "" else: dSugg[conj._getConjWithTags(sStem, tTags, ":Q", ":m:s")] = "" if "" in dSugg: del dSugg[""] if dSugg: return "|".join(dSugg) return "" def suggVerbTense (sFlex, sTense, sWho): "change <sFlex> to a verb according to <sTense> and <sWho>" dSugg = {} for sStem in _oSpellChecker.getLemma(sFlex): if conj.hasConj(sStem, sTense, sWho): dSugg[conj.getConj(sStem, sTense, sWho)] = "" if dSugg: return "|".join(dSugg) return "" def suggVerbFrom (sStem, sFlex, sWho=""): "conjugate <sStem> according to <sFlex> (and eventually <sWho>)" dSugg = {} for sMorph in _oSpellChecker.getMorph(sFlex): lTenses = [ m.group(0) for m in re.finditer(":(?:Y|I[pqsf]|S[pq]|K|P)", sMorph) ] if sWho: for sTense in lTenses: if conj.hasConj(sStem, sTense, sWho): dSugg[conj.getConj(sStem, sTense, sWho)] = "" else: for sTense in lTenses: for sWho2 in [ m.group(0) for m in re.finditer(":(?:[123][sp]|P|Y)", sMorph) ]: if conj.hasConj(sStem, sTense, sWho2): dSugg[conj.getConj(sStem, sTense, sWho2)] = "" if dSugg: return "|".join(dSugg) return "" def suggVerbImpe (sFlex, bVC=False): "change <sFlex> to a verb at imperative form" if bVC: sFlex, sSfx = splitVerb(sFlex) |
︙ | ︙ | |||
192 193 194 195 196 197 198 | if tTags: for sTense in lMode: if conj._hasConjWithTags(tTags, sTense, sWho): dSugg[conj._getConjWithTags(sStem, tTags, sTense, sWho)] = "" if sFlex in _dModeSugg: dSugg[_dModeSugg[sFlex]] = "" if dSugg: | | | 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | if tTags: for sTense in lMode: if conj._hasConjWithTags(tTags, sTense, sWho): dSugg[conj._getConjWithTags(sStem, tTags, sTense, sWho)] = "" if sFlex in _dModeSugg: dSugg[_dModeSugg[sFlex]] = "" if dSugg: return "|".join(dSugg) return "" ## Nouns and adjectives def suggPlur (sFlex, bSelfSugg=False): "returns plural forms assuming sFlex is singular" |
︙ | ︙ | |||
275 276 277 278 279 280 281 | # We also check if the verb has a feminine form. # If not, we consider it’s better to not suggest the masculine one, as it can be considered invariable. dSugg[conj.getConj(sVerb, ":Q", ":m:s")] = "" if bSuggSimil: for e in phonet.selectSimil(sFlex, ":m:[si]"): dSugg[e] = "" if dSugg: | | | 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 | # We also check if the verb has a feminine form. # If not, we consider it’s better to not suggest the masculine one, as it can be considered invariable. dSugg[conj.getConj(sVerb, ":Q", ":m:s")] = "" if bSuggSimil: for e in phonet.selectSimil(sFlex, ":m:[si]"): dSugg[e] = "" if dSugg: return "|".join(dSugg) return "" def suggMasPlur (sFlex, bSuggSimil=False): "returns masculine plural forms" dSugg = {} for sMorph in _oSpellChecker.getMorph(sFlex): |
︙ | ︙ | |||
305 306 307 308 309 310 311 | # it is necessary to filter these flexions, like “succédé” or “agi” that are not masculine plural. if sSugg.endswith("s"): dSugg[sSugg] = "" if bSuggSimil: for e in phonet.selectSimil(sFlex, ":m:[pi]"): dSugg[e] = "" if dSugg: | | | 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 | # it is necessary to filter these flexions, like “succédé” or “agi” that are not masculine plural. if sSugg.endswith("s"): dSugg[sSugg] = "" if bSuggSimil: for e in phonet.selectSimil(sFlex, ":m:[pi]"): dSugg[e] = "" if dSugg: return "|".join(dSugg) return "" def suggFemSing (sFlex, bSuggSimil=False): "returns feminine singular forms" dSugg = {} for sMorph in _oSpellChecker.getMorph(sFlex): |
︙ | ︙ | |||
330 331 332 333 334 335 336 | sVerb = cr.getLemmaOfMorph(sMorph) if conj.hasConj(sVerb, ":Q", ":f:s"): dSugg[conj.getConj(sVerb, ":Q", ":f:s")] = "" if bSuggSimil: for e in phonet.selectSimil(sFlex, ":f:[si]"): dSugg[e] = "" if dSugg: | | | 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 | sVerb = cr.getLemmaOfMorph(sMorph) if conj.hasConj(sVerb, ":Q", ":f:s"): dSugg[conj.getConj(sVerb, ":Q", ":f:s")] = "" if bSuggSimil: for e in phonet.selectSimil(sFlex, ":f:[si]"): dSugg[e] = "" if dSugg: return "|".join(dSugg) return "" def suggFemPlur (sFlex, bSuggSimil=False): "returns feminine plural forms" dSugg = {} for sMorph in _oSpellChecker.getMorph(sFlex): |
︙ | ︙ | |||
368 369 370 371 372 373 374 | lMorphSrc = _oSpellChecker.getMorph(sFlexSrc) if not lMorphSrc: return "" sGender, sNumber = cr.getGenderNumber(lMorphSrc) if sGender == ":m": if sNumber == ":s": return suggMasSing(sFlexDest) | | | | | | | | | | | | 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 | lMorphSrc = _oSpellChecker.getMorph(sFlexSrc) if not lMorphSrc: return "" sGender, sNumber = cr.getGenderNumber(lMorphSrc) if sGender == ":m": if sNumber == ":s": return suggMasSing(sFlexDest) if sNumber == ":p": return suggMasPlur(sFlexDest) return suggMasSing(sFlexDest) if sGender == ":f": if sNumber == ":s": return suggFemSing(sFlexDest) if sNumber == ":p": return suggFemPlur(sFlexDest) return suggFemSing(sFlexDest) if sGender == ":e": if sNumber == ":s": return suggSing(sFlexDest) if sNumber == ":p": return suggPlur(sFlexDest) return sFlexDest return "" def g_suggAgree (dTokenDst, dTokenSrc): "returns suggestions for <dTokenDst> that matches agreement with <dTokenSrc>" lMorphSrc = dTokenSrc["lMorph"] if "lMorph" in dTokenSrc else _oSpellChecker.getMorph(dTokenSrc["sValue"]) if not lMorphSrc: return "" sGender, sNumber = cr.getGenderNumber(lMorphSrc) if sGender == ":m": if sNumber == ":s": return suggMasSing(dTokenDst["sValue"]) if sNumber == ":p": return suggMasPlur(dTokenDst["sValue"]) return suggMasSing(dTokenDst["sValue"]) if sGender == ":f": if sNumber == ":s": return suggFemSing(dTokenDst["sValue"]) if sNumber == ":p": return suggFemPlur(dTokenDst["sValue"]) return suggFemSing(dTokenDst["sValue"]) if sGender == ":e": if sNumber == ":s": return suggSing(dTokenDst["sValue"]) if sNumber == ":p": return suggPlur(dTokenDst["sValue"]) return dTokenDst["sValue"] return "" def hasFemForm (sFlex): "return True if there is a feminine form of <sFlex>" |
︙ | ︙ | |||
468 469 470 471 472 473 474 | else: for sMorph in _oSpellChecker.getMorph(sFlex): if ":f" in sMorph: dSugg[suggMasSing(sFlex)] = "" elif ":m" in sMorph: dSugg[suggFemSing(sFlex)] = "" if dSugg: | | | | 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 | else: for sMorph in _oSpellChecker.getMorph(sFlex): if ":f" in sMorph: dSugg[suggMasSing(sFlex)] = "" elif ":m" in sMorph: dSugg[suggFemSing(sFlex)] = "" if dSugg: return "|".join(dSugg) return "" def switchPlural (sFlex): "return plural or singular form(s) of <sFlex>" aSugg = {} for sMorph in _oSpellChecker.getMorph(sFlex): if ":s" in sMorph: aSugg[suggPlur(sFlex)] = "" elif ":p" in sMorph: aSugg[suggSing(sFlex)] = "" if aSugg: return "|".join(aSugg) return "" def hasSimil (sWord, sPattern=None): "return True if there is words phonetically similar to <sWord> (according to <sPattern> if required)" return phonet.hasSimil(sWord, sPattern) |
︙ | ︙ | |||
508 509 510 511 512 513 514 | if any(re.search(sPattern, sMorph2) for sMorph2 in _oSpellChecker.getMorph(sName)): dSugg[sName] = "" else: dSugg.update(dict.fromkeys(conj.getNamesFrom(sInfi), "")) break if dSugg: if bVC: | | | | 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 | if any(re.search(sPattern, sMorph2) for sMorph2 in _oSpellChecker.getMorph(sName)): dSugg[sName] = "" else: dSugg.update(dict.fromkeys(conj.getNamesFrom(sInfi), "")) break if dSugg: if bVC: return "|".join([ joinVerbAndSuffix(sSugg, sSfx) for sSugg in dSugg ]) return "|".join(dSugg) return "" def suggCeOrCet (sWord): "suggest “ce” or “cet” or both according to the first letter of <sWord>" if re.match("(?i)[aeéèêiouyâîï]", sWord): return "cet" |
︙ | ︙ |
Modified gc_lang/fr/modules/tests_modules.py from [f7e92c1ab0] to [5c8bb6ae99].
︙ | ︙ | |||
53 54 55 56 57 58 59 | def test_isvalid_failed (self): for sWord in ["BranchE", "BRanche", "BRAnCHE", "émilie", "éMILIE", "émiLie", "aujourd'hui", "Aujourd'hui", ]: self.assertFalse(self.oSpellChecker.isValid(sWord), sWord) def test_suggest (self): for sWord in [ "déelirranttesss", "vallidasion", "Emilie", "exibission", "ditirembique", "jai", "email", | | | > > > > > > | 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | def test_isvalid_failed (self): for sWord in ["BranchE", "BRanche", "BRAnCHE", "émilie", "éMILIE", "émiLie", "aujourd'hui", "Aujourd'hui", ]: self.assertFalse(self.oSpellChecker.isValid(sWord), sWord) def test_suggest (self): for sWord in [ "déelirranttesss", "vallidasion", "Emilie", "exibission", "ditirembique", "jai", "email", "fatiqué", "coeur", "trèèèèèèèèès", "vraaaaiiiimeeeeennnt", "apele", "Co2", "emmppâiiiller", "testt", "apelaion", "exsepttion", "sintaxik", "ebriete", "ennormmement" ]: for lSugg in self.oSpellChecker.suggest(sWord): self.assertTrue(len(lSugg) > 0) #with timeblock(sWord): # aSugg = self.oSpellChecker.suggest(sWord) # print(sWord, "->", " ".join(aSugg)) def test_lemmas (self): for sWord, sInfi in [ ("suis", "suivre"), ("suis", "être"), ("a", "avoir"), ("a", "a"), ("irai", "aller"), ("jetez", "jeter"), ("finit", "finir"), ("mangé", "manger"), ("oubliait", "oublier"), ("arrivais", "arriver"), ("venait", "venir"), ("prendre", "prendre") |
︙ | ︙ |
Modified graphspell-js/dawg.js from [1c01c104ea] to [743b532572].
︙ | ︙ | |||
138 139 140 141 142 143 144 145 146 147 148 149 150 151 | if (cStemming == "A") { this.funcStemming = str_transform.changeWordWithAffixCode; } else if (cStemming == "S") { this.funcStemming = str_transform.changeWordWithSuffixCode; } else { this.funcStemming = str_transform.noStemming; } // build lWord.sort(); if (xProgressBarNode) { xProgressBarNode.value = 0; xProgressBarNode.max = lWord.length; } | > > > > | 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 | if (cStemming == "A") { this.funcStemming = str_transform.changeWordWithAffixCode; } else if (cStemming == "S") { this.funcStemming = str_transform.changeWordWithSuffixCode; } else { this.funcStemming = str_transform.noStemming; } // binary dictionary this.sByDic = ""; this.lByDic = []; // build lWord.sort(); if (xProgressBarNode) { xProgressBarNode.value = 0; xProgressBarNode.max = lWord.length; } |
︙ | ︙ |
Modified graphspell-js/ibdawg.js from [34ce7a8182] to [44a920520f].
︙ | ︙ | |||
106 107 108 109 110 111 112 | } else if (this.sWord.slice(0,1).gl_isUpperCase()) { lRes = lRes.map((sSugg) => { return sSugg.slice(0,1).toUpperCase() + sSugg.slice(1); }); lRes = [...new Set(lRes)]; } return lRes.slice(0, this.nSuggLimit); } | < < < < < < | 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | } else if (this.sWord.slice(0,1).gl_isUpperCase()) { lRes = lRes.map((sSugg) => { return sSugg.slice(0,1).toUpperCase() + sSugg.slice(1); }); lRes = [...new Set(lRes)]; } return lRes.slice(0, this.nSuggLimit); } } class IBDAWG { // INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH constructor (source, sPath="") { |
︙ | ︙ |
Modified graphspell/dawg.py from [729715ac89] to [e9390e8710].
︙ | ︙ | |||
161 162 163 164 165 166 167 168 169 170 171 172 173 174 | # calculated later self.nBytesNodeAddress = 1 self.nBytesArc = 0 self.nBytesOffset = 0 self.nMaxOffset = 0 # build lWord.sort() oProgBar = ProgressBar(0, len(lWord)) for aEntry in lWord: self.insert(aEntry) oProgBar.increment(1) oProgBar.done() | > > > > | 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | # calculated later self.nBytesNodeAddress = 1 self.nBytesArc = 0 self.nBytesOffset = 0 self.nMaxOffset = 0 # binary dictionary self.byDic = b"" self.lByDic = [] # build lWord.sort() oProgBar = ProgressBar(0, len(lWord)) for aEntry in lWord: self.insert(aEntry) oProgBar.increment(1) oProgBar.done() |
︙ | ︙ | |||
360 361 362 363 364 365 366 | # BINARY CONVERSION def _calculateBinary (self): print(" > Write DAWG as an indexable binary dictionary") self.nBytesArc = ( (self.nArcVal.bit_length() + 2) // 8 ) + 1 # We add 2 bits. See DawgNode.convToBytes() self.nBytesOffset = 0 self._calcNumBytesNodeAddress() self._calcNodesAddress() | < | 364 365 366 367 368 369 370 371 372 373 374 375 376 377 | # BINARY CONVERSION def _calculateBinary (self): print(" > Write DAWG as an indexable binary dictionary") self.nBytesArc = ( (self.nArcVal.bit_length() + 2) // 8 ) + 1 # We add 2 bits. See DawgNode.convToBytes() self.nBytesOffset = 0 self._calcNumBytesNodeAddress() self._calcNodesAddress() self.byDic = self.oRoot.convToBytes(self.nBytesArc, self.nBytesNodeAddress) for oNode in self.lMinimizedNodes: self.byDic += oNode.convToBytes(self.nBytesArc, self.nBytesNodeAddress) print(" Arc values (chars, affixes and tags): {} -> {} bytes".format( self.nArcVal, len("\t".join(self.lArcVal).encode("utf-8")) )) print(" Arc size: {} bytes, Address size: {} bytes -> {} * {} = {} bytes".format( self.nBytesArc, self.nBytesNodeAddress, \ self.nBytesArc+self.nBytesNodeAddress, self.nArc, \ (self.nBytesArc+self.nBytesNodeAddress)*self.nArc )) |
︙ | ︙ |
Modified graphspell/ibdawg.py from [bd93f6353b] to [13d2327263].
︙ | ︙ | |||
99 100 101 102 103 104 105 | if self.sWord.isupper(): lRes = list(OrderedDict.fromkeys(map(lambda sSugg: sSugg.upper(), lRes))) # use dict, when Python 3.6+ elif self.sWord[0:1].isupper(): # dont’ use <.istitle> lRes = list(OrderedDict.fromkeys(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes))) # use dict, when Python 3.6+ return lRes[:self.nSuggLimit] | < < < < < | 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | if self.sWord.isupper(): lRes = list(OrderedDict.fromkeys(map(lambda sSugg: sSugg.upper(), lRes))) # use dict, when Python 3.6+ elif self.sWord[0:1].isupper(): # dont’ use <.istitle> lRes = list(OrderedDict.fromkeys(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes))) # use dict, when Python 3.6+ return lRes[:self.nSuggLimit] class IBDAWG: """INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH""" def __init__ (self, source): if isinstance(source, str): by = pkgutil.get_data(__package__, "_dictionaries/" + source) |
︙ | ︙ |
Modified graphspell/lexgraph_fr.py from [bcc7c5a33b] to [fab156e863].
︙ | ︙ | |||
438 439 440 441 442 443 444 445 446 447 | _zPartDemForm = re.compile("([\\w]+)-(là|ci)$") _zInterroVerb = re.compile("([\\w]+)(-(?:t-(?:ie?l|elle|on)|je|tu|ie?ls?|elles?|on|[nv]ous))$") _zImperatifVerb = re.compile("([\\w]+)(-(?:l(?:es?|a)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts]['’ʼ‘‛´`′‵՚ꞌꞋ](?:y|en)|les?|la|[mt]oi|leur|lui))$") def setLabelsOnToken (dToken): # Token: .sType, .sValue, .nStart, .nEnd, .lMorph try: if dToken["sType"] == "PUNC" or dToken["sType"] == "SIGN": | > | | 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 | _zPartDemForm = re.compile("([\\w]+)-(là|ci)$") _zInterroVerb = re.compile("([\\w]+)(-(?:t-(?:ie?l|elle|on)|je|tu|ie?ls?|elles?|on|[nv]ous))$") _zImperatifVerb = re.compile("([\\w]+)(-(?:l(?:es?|a)-(?:moi|toi|lui|[nv]ous|leur)|y|en|[mts]['’ʼ‘‛´`′‵՚ꞌꞋ](?:y|en)|les?|la|[mt]oi|leur|lui))$") def setLabelsOnToken (dToken): "create an attribute “alabels” on <dToken> as a list of readable meanings" # Token: .sType, .sValue, .nStart, .nEnd, .lMorph try: if dToken["sType"] == "PUNC" or dToken["sType"] == "SIGN": dToken["aLabels"] = [ _dValues.get(dToken["sValue"], "signe de ponctuation divers") ] elif dToken["sType"] == 'SYMBOL': dToken["aLabels"] = ["symbole"] elif dToken["sType"] == 'EMOJI': dToken["aLabels"] = ["émoji"] elif dToken["sType"] == 'NUM': dToken["aLabels"] = ["nombre"] elif dToken["sType"] == 'LINK': |
︙ | ︙ | |||
505 506 507 508 509 510 511 | dToken["aLabels"] = ["token de nature inconnue"] except: return # Other functions | | > | | 506 507 508 509 510 511 512 513 514 515 516 | dToken["aLabels"] = ["token de nature inconnue"] except: return # Other functions def filterSugg (aSuggs): "exclude suggestions" return [ sSugg for sSugg in aSuggs if not sSugg.endswith(("è", "È")) ] #return filter(lambda sSugg: not sSugg.endswith(("è", "È")), aSuggs) # return an object filter |
Modified graphspell/str_transform.py from [d580e06cf9] to [4b10b3e705].
︙ | ︙ | |||
111 112 113 114 115 116 117 118 119 120 121 122 123 124 | ) if i and j and s1[i] == s2[j-1] and s1[i-1] == s2[j]: d[i, j] = min(d[i, j], d[i-2, j-2] + nCost) # Transposition return d[nLen1-1, nLen2-1] def distanceJaroWinkler (sWord1, sWord2, fBoost = .666): # https://github.com/thsig/jaro-winkler-JS #if (sWord1 == sWord2): return 1.0 nLen1 = len(sWord1) nLen2 = len(sWord2) nMax = max(nLen1, nLen2) aFlags1 = [ None for _ in range(nMax) ] aFlags2 = [ None for _ in range(nMax) ] | > | 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 | ) if i and j and s1[i] == s2[j-1] and s1[i-1] == s2[j]: d[i, j] = min(d[i, j], d[i-2, j-2] + nCost) # Transposition return d[nLen1-1, nLen2-1] def distanceJaroWinkler (sWord1, sWord2, fBoost = .666): "distance of Jaro-Winkler between <sWord1> and <sWord2>, returns a float" # https://github.com/thsig/jaro-winkler-JS #if (sWord1 == sWord2): return 1.0 nLen1 = len(sWord1) nLen2 = len(sWord2) nMax = max(nLen1, nLen2) aFlags1 = [ None for _ in range(nMax) ] aFlags2 = [ None for _ in range(nMax) ] |
︙ | ︙ | |||
217 218 219 220 221 222 223 | bTrans = abs(i2-i1) >= abs(t[1] - t[0]) if bTrans: nTrans += 1 elif not t[2]: t[2] = True nTrans += 1 break | | | | | 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 | bTrans = abs(i2-i1) >= abs(t[1] - t[0]) if bTrans: nTrans += 1 elif not t[2]: t[2] = True nTrans += 1 break if i1 > t[1] and i2 > t[0]: del lOffset[i] else: i += 1 lOffset.append([i1, i2, bTrans]) else: nLargestCS += nLocalCS nLocalCS = 0 if i1 != i2: i1 = i2 = min(i1, i2) for i in range(nMaxOffset): if i1 + i >= nLen1 and i2 + i >= nLen2: break if i1 + i < nLen1 and s1[i1+i] == s2[i2]: i1 += i - 1 i2 -= 1 break if i2 + i < nLen2 and s1[i1] == s2[i2+i]: i2 += i - 1 i1 -= 1 break i1 += 1 i2 += 1 if i1 >= nLen1 or i2 >= nLen2: nLargestCS += nLocalCS |
︙ | ︙ |
Modified pylintrc from [032bb6abd3] to [237077429f].
︙ | ︙ | |||
14 15 16 17 18 19 20 | ignore-patterns=bottle.py,gc_rules,.*_data.py # Python code to execute, usually for sys.path manipulation such as # pygtk.require(). #init-hook= # Use multiple processes to speed up Pylint. | | | 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 | ignore-patterns=bottle.py,gc_rules,.*_data.py # Python code to execute, usually for sys.path manipulation such as # pygtk.require(). #init-hook= # Use multiple processes to speed up Pylint. jobs=1 # List of plugins (as comma separated values of python modules names) to load, # usually to register additional checkers. load-plugins= # Pickle collected data for later comparisons. persistent=yes |
︙ | ︙ | |||
116 117 118 119 120 121 122 | div-method, idiv-method, rdiv-method, exception-message-attribute, invalid-str-codec, sys-max-int, bad-python3-import, | < < < > < > | 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 | div-method, idiv-method, rdiv-method, exception-message-attribute, invalid-str-codec, sys-max-int, bad-python3-import, deprecated-types-field, missing-format-attribute, next-method-defined, dict-items-not-iterating, dict-keys-not-iterating, dict-values-not-iterating, deprecated-operator-function, deprecated-urllib-function, xreadlines-attribute, exception-escape, comprehension-escape, bad-whitespace, consider-using-ternary, line-too-long # Enable the message, report, category or checker with the given id(s). You can # either give multiple identifier separated by comma (,) or put this option # multiple time (only on the command line, not in the configuration file where # it should appear only once). See also the "--disable" option for examples. enable=c-extension-no-member |
︙ | ︙ |