Overview
Comment: | [core][py] code clarification: separate specific inner functions from gc engine core |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | trunk | core |
Files: | files | file ages | folders |
SHA3-256: |
0b126eb25409bfe36d6edd4543814063 |
User & Date: | olr on 2020-08-19 15:11:44 |
Other Links: | manifest | tags |
Context
2020-08-19
| ||
15:53 | [core][js] code clarification: separate specific inner functions from gc engine core check-in: 1975bd1394 user: olr tags: trunk, core | |
15:11 | [core][py] code clarification: separate specific inner functions from gc engine core check-in: 0b126eb254 user: olr tags: trunk, core | |
14:55 | [fr] ajustements check-in: 947bd905af user: olr tags: trunk, fr | |
Changes
Modified gc_core/py/lang_core/gc_engine.py from [8f5c1e4716] to [472d04d897].
︙ | ︙ | |||
9 10 11 12 13 14 15 16 17 18 19 20 21 22 | from itertools import chain from ..graphspell.spellchecker import SpellChecker from ..graphspell.echo import echo from .. import text from . import gc_options try: # LibreOffice / OpenOffice from com.sun.star.linguistic2 import SingleProofreadingError from com.sun.star.text.TextMarkupType import PROOFREADING from com.sun.star.beans import PropertyValue | > | 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | from itertools import chain from ..graphspell.spellchecker import SpellChecker from ..graphspell.echo import echo from .. import text from . import gc_functions from . import gc_options try: # LibreOffice / OpenOffice from com.sun.star.linguistic2 import SingleProofreadingError from com.sun.star.text.TextMarkupType import PROOFREADING from com.sun.star.beans import PropertyValue |
︙ | ︙ | |||
68 69 70 71 72 73 74 75 76 77 78 79 80 81 | global _dOptionsColors global _oTokenizer try: _sAppContext = sContext _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}") _oSpellChecker.activateStorage() _oTokenizer = _oSpellChecker.getTokenizer() gc_options.load(sContext) _dOptionsColors = gc_options.getOptionsColors(sContext, sColorType) except: traceback.print_exc() def getSpellChecker (): | > | 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | global _dOptionsColors global _oTokenizer try: _sAppContext = sContext _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}") _oSpellChecker.activateStorage() _oTokenizer = _oSpellChecker.getTokenizer() gc_functions.load(sContext, _oSpellChecker) gc_options.load(sContext) _dOptionsColors = gc_options.getOptionsColors(sContext, sColorType) except: traceback.print_exc() def getSpellChecker (): |
︙ | ︙ | |||
255 256 257 258 259 260 261 | # s += "{}\t{}\n".format(nPos, dToken) return s def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False): "analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors" #sText = unicodedata.normalize("NFC", sText) dOpt = dOptions or gc_options.dOptions | | | 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 | # s += "{}\t{}\n".format(nPos, dToken) return s def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False): "analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors" #sText = unicodedata.normalize("NFC", sText) 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()) |
︙ | ︙ | |||
334 335 336 337 338 339 340 | for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup: if sRuleId not in _aIgnoredRules: for m in zRegex.finditer(sText): bCondMemo = None for sFuncCond, cActionType, sWhat, *eAct in lActions: # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ] try: | | | | 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 | for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup: if sRuleId not in _aIgnoredRules: for m in zRegex.finditer(sText): bCondMemo = None for sFuncCond, cActionType, sWhat, *eAct in lActions: # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ] try: bCondMemo = not sFuncCond or getattr(gc_functions, sFuncCond)(sText, sText0, m, self.dTokenPos, sCountry, bCondMemo) if bCondMemo: if bDebug: echo("RULE: " + sLineId) if cActionType == "-": # grammar error nErrorStart = nOffset + m.start(eAct[0]) if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1): self.dError[nErrorStart] = self._createErrorFromRegex(sText, sText0, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext) self.dErrorPriority[nErrorStart] = nPriority self.dSentenceError[nErrorStart] = self.dError[nErrorStart] elif cActionType == "~": # text processor sText = self.rewriteText(sText, sWhat, eAct[0], m, bUppercase) bChange = True if bDebug: echo("~ " + sText + " -- " + m.group(eAct[0]) + " # " + sLineId) elif cActionType == "=": # disambiguation if not bParagraph: getattr(gc_functions, sWhat)(sText, m, self.dTokenPos) if bDebug: echo("= " + m.group(0) + " # " + sLineId) elif cActionType == ">": # we do nothing, this test is just a condition to apply all following actions pass else: echo("# error: unknown action at " + sLineId) |
︙ | ︙ | |||
587 588 589 590 591 592 593 | # Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL ] # TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ] # Disambiguator [ option, condition, "=", replacement/suggestion/action ] # Tag [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ] # Immunity [ option, condition, "!", "", iTokenStart, iTokenEnd ] # Test [ option, condition, ">", "" ] if not sOption or dOptions.get(sOption, False): | | | 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 | # Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL ] # TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ] # Disambiguator [ option, condition, "=", replacement/suggestion/action ] # Tag [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ] # Immunity [ option, condition, "!", "", iTokenStart, iTokenEnd ] # Test [ option, condition, ">", "" ] if not sOption or dOptions.get(sOption, False): bCondMemo = not sFuncCond or getattr(gc_functions, sFuncCond)(self.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, self.dTags, self.sSentence, self.sSentence0) if bCondMemo: if cActionType == "-": # grammar error iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, iURL = eAct nTokenErrorStart = nTokenOffset + iTokenStart if iTokenStart > 0 else nLastToken + iTokenStart if "bImmune" not in self.lToken[nTokenErrorStart]: nTokenErrorEnd = nTokenOffset + iTokenEnd if iTokenEnd > 0 else nLastToken + iTokenEnd |
︙ | ︙ | |||
614 615 616 617 618 619 620 | nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1] self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug) bChange = True if bDebug: echo(" TEXT_PROCESSOR: [{}:{}] > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat)) elif cActionType == "=": # disambiguation | | | 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 | nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1] self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug) bChange = True if bDebug: echo(" TEXT_PROCESSOR: [{}:{}] > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat)) elif cActionType == "=": # disambiguation getattr(gc_functions, sWhat)(self.lToken, nTokenOffset, nLastToken) if bDebug: echo(" DISAMBIGUATOR: ({}) [{}:{}]".format(sWhat, self.lToken[nTokenOffset+1]["sValue"], self.lToken[nLastToken]["sValue"])) elif cActionType == ">": # we do nothing, this test is just a condition to apply all following actions if bDebug: echo(" COND_OK") elif cActionType == "/": |
︙ | ︙ | |||
670 671 672 673 674 675 676 | return bChange def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext): nStart = nOffset + m.start(iGroup) nEnd = nOffset + m.end(iGroup) # suggestions if sRepl[0:1] == "=": | | | | | | 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 | return bChange def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext): nStart = nOffset + m.start(iGroup) nEnd = nOffset + m.end(iGroup) # suggestions if sRepl[0:1] == "=": sSugg = getattr(gc_functions, sRepl[1:])(sText, m) lSugg = sSugg.split("|") if sSugg else [] elif sRepl == "_": lSugg = [] else: lSugg = m.expand(sRepl).split("|") if bCaseSvty and lSugg and m.group(iGroup)[0:1].isupper(): lSugg = list(map(lambda s: s.upper(), lSugg)) if m.group(iGroup).isupper() else list(map(lambda s: s[0:1].upper()+s[1:], lSugg)) # Message sMessage = getattr(gc_functions, sMsg[1:])(sText, m) if sMsg[0:1] == "=" else m.expand(sMsg) if bShowRuleId: sMessage += " #" + sLineId + " / " + sRuleId # if _bWriterError: return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL) return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) def _createErrorFromTokens (self, sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext): # suggestions if sSugg[0:1] == "=": sSugg = getattr(gc_functions, sSugg[1:])(self.lToken, nTokenOffset, nLastToken) lSugg = sSugg.split("|") if sSugg else [] elif sSugg == "_": lSugg = [] else: lSugg = self._expand(sSugg, nTokenOffset, nLastToken).split("|") if bCaseSvty and lSugg and self.lToken[iFirstToken]["sValue"][0:1].isupper(): lSugg = list(map(lambda s: s.upper(), lSugg)) if self.sSentence[nStart:nEnd].isupper() else list(map(lambda s: s[0:1].upper()+s[1:], lSugg)) # Message sMessage = getattr(gc_functions, sMsg[1:])(self.lToken, nTokenOffset, nLastToken) if sMsg[0:1] == "=" else self._expand(sMsg, nTokenOffset, nLastToken) if bShowRuleId: sMessage += " #" + sLineId + " / " + sRuleId # if _bWriterError: return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL) return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext) |
︙ | ︙ | |||
763 764 765 766 767 768 769 | if sRepl == "*": sNew = " " * nLen elif sRepl == "_": sNew = "_" * nLen elif sRepl == "@": sNew = "@" * nLen elif sRepl[0:1] == "=": | | | 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 | if sRepl == "*": sNew = " " * nLen elif sRepl == "_": sNew = "_" * nLen elif sRepl == "@": sNew = "@" * nLen elif sRepl[0:1] == "=": sNew = getattr(gc_functions, sRepl[1:])(sText, m) sNew = sNew + " " * (nLen-len(sNew)) if bUppercase and m.group(iGroup)[0:1].isupper(): sNew = sNew.capitalize() else: sNew = m.expand(sRepl) sNew = sNew + " " * (nLen-len(sNew)) return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):] |
︙ | ︙ | |||
793 794 795 796 797 798 799 | if nTokenRewriteEnd - nTokenRewriteStart == 0: self.lToken[nTokenRewriteStart]["sNewValue"] = "_" else: for i in range(nTokenRewriteStart, nTokenRewriteEnd+1): self.lToken[i]["sNewValue"] = "_" else: if sWhat.startswith("="): | | | 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 | if nTokenRewriteEnd - nTokenRewriteStart == 0: self.lToken[nTokenRewriteStart]["sNewValue"] = "_" else: for i in range(nTokenRewriteStart, nTokenRewriteEnd+1): self.lToken[i]["sNewValue"] = "_" else: if sWhat.startswith("="): sWhat = getattr(gc_functions, sWhat[1:])(self.lToken, nTokenOffset, nLastToken) else: sWhat = self._expand(sWhat, nTokenOffset, nLastToken) bUppercase = bCaseSvty and self.lToken[nTokenRewriteStart]["sValue"][0:1].isupper() if nTokenRewriteEnd - nTokenRewriteStart == 0: # one token if bUppercase: sWhat = sWhat[0:1].upper() + sWhat[1:] |
︙ | ︙ | |||
867 868 869 870 871 872 873 | except KeyError: echo(self) echo(dToken) if bDebug: echo(" TEXT REWRITED: " + self.sSentence) self.lToken.clear() self.lToken = lNewToken | < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < < | 869 870 871 872 873 874 875 | except KeyError: echo(self) echo(dToken) if bDebug: echo(" TEXT REWRITED: " + self.sSentence) self.lToken.clear() self.lToken = lNewToken |
Added gc_core/py/lang_core/gc_functions.py version [da32688995].
> > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > | 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 51 52 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 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 | """ 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 def option (sOpt): "return True if option <sOpt> is active" return gc_options.dOptions.get(sOpt, False) #### Functions to get text outside pattern scope # warning: check compile_rules.py to understand how it works _zNextWord = re.compile(r" +(\w[\w-]*)") _zPrevWord = re.compile(r"(\w[\w-]*) +$") def nextword (s, iStart, n): "get the nth word of the input string or empty string" m = re.match("(?: +[\\w%-]+){" + str(n-1) + "} +([\\w%-]+)", s[iStart:]) if not m: return None return (iStart+m.start(1), m.group(1)) def prevword (s, iEnd, n): "get the (-)nth word of the input string or empty string" m = re.search("([\\w%-]+) +(?:[\\w%-]+ +){" + str(n-1) + "}$", s[:iEnd]) if not m: return None return (m.start(1), m.group(1)) def nextword1 (s, iStart): "get next word (optimization)" m = _zNextWord.match(s[iStart:]) if not m: return None return (iStart+m.start(1), m.group(1)) def prevword1 (s, iEnd): "get previous word (optimization)" m = _zPrevWord.search(s[:iEnd]) if not m: return None return (m.start(1), m.group(1)) def look (s, sPattern, sNegPattern=None): "seek sPattern in s (before/after/fulltext), if sNegPattern not in s" if sNegPattern and re.search(sNegPattern, s): return False if re.search(sPattern, s): return True return False def look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=""): "returns True if s has pattern sPattern and m.group(1) has pattern sPatternGroup1" m = re.search(sPattern, s) if not m: return False try: sWord = m.group(1) nPos = m.start(1) + nOffset except IndexError: return False return morph(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1) #### Analyse groups for regex rules def displayInfo (dTokenPos, tWord): "for debugging: retrieve info of word" if not tWord: echo("> nothing to find") return True lMorph = _oSpellChecker.getMorph(tWord[1]) if not lMorph: echo("> not in dictionary") return True echo("TOKENS:", dTokenPos) if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]: echo("DA: " + str(dTokenPos[tWord[0]]["lMorph"])) echo("FSA: " + str(lMorph)) return True def morph (dTokenPos, tWord, sPattern, sNegPattern="", bNoWord=False): "analyse a tuple (position, word), returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)" if not tWord: return bNoWord lMorph = dTokenPos[tWord[0]]["lMorph"] if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]] else _oSpellChecker.getMorph(tWord[1]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) def analyse (sWord, sPattern, sNegPattern=""): "analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)" lMorph = _oSpellChecker.getMorph(sWord) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) #### Analyse tokens for graph rules def g_value (dToken, sValues, nLeft=None, nRight=None): "test if <dToken['sValue']> is in sValues (each value should be separated with |)" sValue = "|"+dToken["sValue"]+"|" if nLeft is None else "|"+dToken["sValue"][slice(nLeft, nRight)]+"|" if sValue in sValues: return True if dToken["sValue"][0:2].istitle(): # we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout". if sValue.lower() in sValues: return True elif dToken["sValue"].isupper(): #if sValue.lower() in sValues: # return True sValue = "|"+sValue[1:].capitalize() if sValue in sValues: return True sValue = sValue.lower() if sValue in sValues: return True return False def g_morph (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True): "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies" if "lMorph" in dToken: lMorph = dToken["lMorph"] else: if nLeft is not None: lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)]) if bMemorizeMorph: dToken["lMorph"] = lMorph else: lMorph = _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) def g_analyse (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True): "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)" if nLeft is not None: lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)]) if bMemorizeMorph: dToken["lMorph"] = lMorph else: lMorph = _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) return all(zPattern.search(sMorph) for sMorph in lMorph) zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) return any(zPattern.search(sMorph) for sMorph in lMorph) def g_merged_analyse (dToken1, dToken2, cMerger, sPattern, sNegPattern="", bSetMorph=True): "merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)" lMorph = _oSpellChecker.getMorph(dToken1["sValue"] + cMerger + dToken2["sValue"]) if not lMorph: return False # check negative condition if sNegPattern: if sNegPattern == "*": # all morph must match sPattern zPattern = re.compile(sPattern) bResult = all(zPattern.search(sMorph) for sMorph in lMorph) if bResult and bSetMorph: dToken1["lMorph"] = lMorph return bResult zNegPattern = re.compile(sNegPattern) if any(zNegPattern.search(sMorph) for sMorph in lMorph): return False # search sPattern zPattern = re.compile(sPattern) bResult = any(zPattern.search(sMorph) for sMorph in lMorph) if bResult and bSetMorph: dToken1["lMorph"] = lMorph return bResult def g_tag_before (dToken, dTags, sTag): "returns True if <sTag> is present on tokens before <dToken>" if sTag not in dTags: return False if dToken["i"] > dTags[sTag][0]: return True return False def g_tag_after (dToken, dTags, sTag): "returns True if <sTag> is present on tokens after <dToken>" if sTag not in dTags: return False if dToken["i"] < dTags[sTag][1]: return True return False def g_tag (dToken, sTag): "returns True if <sTag> is present on token <dToken>" return "aTags" in dToken and sTag in dToken["aTags"] def g_meta (dToken, sType): "returns True if <sType> is equal to the token type" return dToken["sType"] == sType def g_space_between_tokens (dToken1, dToken2, nMin, nMax=None): "checks if spaces between tokens is >= <nMin> and <= <nMax>" nSpace = dToken2["nStart"] - dToken1["nEnd"] if nSpace < nMin: return False if nMax is not None and nSpace > nMax: return False return True def g_token (lToken, i): "return token at index <i> in lToken (or the closest one)" if i < 0: return lToken[0] if i >= len(lToken): return lToken[-1] return lToken[i] #### Disambiguator for regex rules def select (dTokenPos, nPos, sWord, sPattern, lDefault=None): "Disambiguation: select morphologies of <sWord> matching <sPattern>" if not sWord: return True if nPos not in dTokenPos: echo("Error. There should be a token at this position: ", nPos) return True lMorph = _oSpellChecker.getMorph(sWord) if not lMorph or len(lMorph) == 1: return True lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dTokenPos[nPos]["lMorph"] = lSelect elif lDefault: dTokenPos[nPos]["lMorph"] = lDefault return True def exclude (dTokenPos, nPos, sWord, sPattern, lDefault=None): "Disambiguation: exclude morphologies of <sWord> matching <sPattern>" if not sWord: return True if nPos not in dTokenPos: echo("Error. There should be a token at this position: ", nPos) return True lMorph = _oSpellChecker.getMorph(sWord) if not lMorph or len(lMorph) == 1: return True lSelect = [ sMorph for sMorph in lMorph if not re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dTokenPos[nPos]["lMorph"] = lSelect elif lDefault: dTokenPos[nPos]["lMorph"] = lDefault return True def define (dTokenPos, nPos, sMorphs): "Disambiguation: set morphologies of token at <nPos> with <sMorphs>" if nPos not in dTokenPos: echo("Error. There should be a token at this position: ", nPos) return True dTokenPos[nPos]["lMorph"] = sMorphs.split("|") return True #### Disambiguation for graph rules def g_select (dToken, sPattern, lDefault=None): "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph or len(lMorph) == 1: if lDefault: dToken["lMorph"] = lDefault #echo("DA:", dToken["sValue"], dToken["lMorph"]) return True lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dToken["lMorph"] = lSelect elif lDefault: dToken["lMorph"] = lDefault #echo("DA:", dToken["sValue"], dToken["lMorph"]) return True def g_exclude (dToken, sPattern, lDefault=None): "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) if not lMorph or len(lMorph) == 1: if lDefault: dToken["lMorph"] = lDefault #echo("DA:", dToken["sValue"], dToken["lMorph"]) return True lSelect = [ sMorph for sMorph in lMorph if not re.search(sPattern, sMorph) ] if lSelect: if len(lSelect) != len(lMorph): dToken["lMorph"] = lSelect elif lDefault: dToken["lMorph"] = lDefault #echo("DA:", dToken["sValue"], dToken["lMorph"]) return True def g_add_morph (dToken, sNewMorph): "Disambiguation: add a morphology to a token" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) lMorph.extend(sNewMorph.split("|")) dToken["lMorph"] = lMorph return True def g_rewrite (dToken, sToReplace, sReplace): "Disambiguation: rewrite morphologies" lMorph = dToken["lMorph"] if "lMorph" in dToken else _oSpellChecker.getMorph(dToken["sValue"]) dToken["lMorph"] = [ sMorph.replace(sToReplace, sReplace) for sMorph in lMorph ] return True def g_define (dToken, sMorphs): "Disambiguation: set morphologies of <dToken>, always return True" dToken["lMorph"] = sMorphs.split("|") #echo("DA:", dToken["sValue"], lMorph) return True def g_define_from (dToken, nLeft=None, nRight=None): "Disambiguation: set morphologies of <dToken> with slicing its value with <nLeft> and <nRight>" if nLeft is not None: dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)]) else: dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"]) return True def g_change_meta (dToken, sType): "Disambiguation: change type of token" dToken["sType"] = sType return True #### GRAMMAR CHECKER PLUGINS ${plugins} #### CALLABLES FOR REGEX RULES (generated code) ${callables} #### CALLABLES FOR GRAPH RULES (generated code) ${graph_callables} |