506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
|
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
|
-
+
|
"execute actions found in the DARG"
bChange = False
for sLineId, nextNodeKey in dNode.items():
bCondMemo = None
for sRuleId in dGraph[nextNodeKey]:
try:
if bDebug:
echo(" >TRY: " + sRuleId)
echo(" >TRY: " + sRuleId + " " + sLineId)
sOption, sFuncCond, cActionType, sWhat, *eAct = _rules_graph.dRule[sRuleId]
# Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ]
# 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, ">", "" ]
|
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
|
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
|
-
+
-
+
-
-
+
-
+
-
-
+
-
+
-
+
|
nTokenErrorEnd = nTokenOffset + iTokenEnd if iTokenEnd > 0 else nLastToken + iTokenEnd
nErrorStart = self.nOffsetWithinParagraph + (self.lToken[nTokenErrorStart]["nStart"] if cStartLimit == "<" else self.lToken[nTokenErrorStart]["nEnd"])
nErrorEnd = self.nOffsetWithinParagraph + (self.lToken[nTokenErrorEnd]["nEnd"] if cEndLimit == ">" else self.lToken[nTokenErrorEnd]["nStart"])
if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1):
self.dError[nErrorStart] = self._createErrorFromTokens(sWhat, nTokenOffset, nLastToken, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, bCaseSvty, sMessage, sURL, bShowRuleId, sOption, bContext)
self.dErrorPriority[nErrorStart] = nPriority
if bDebug:
echo(" NEW_ERROR: {} {}: {}".format(sRuleId, sLineId, self.dError[nErrorStart]))
echo(" NEW_ERROR: {}".format(self.dError[nErrorStart]))
elif cActionType == "~":
# text processor
nTokenStart = nTokenOffset + eAct[0] if eAct[0] > 0 else nLastToken + eAct[0]
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: " + sRuleId + " " + sLineId)
echo(" TEXT_PROCESSOR: [{}:{}] > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat))
echo(" " + self.lToken[nTokenStart]["sValue"] + " : " + self.lToken[nTokenEnd]["sValue"] + " > ", sWhat)
echo(" DISAMBIGUATOR: {} {} ({}) {}:{}".format(sRuleId, sLineId, sWhat, self.lToken[nTokenOffset+1]["sValue"], self.lToken[nLastToken]["sValue"]))
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: " + sRuleId + " " + sLineId)
echo(" COND_OK")
pass
elif cActionType == "/":
# Tag
nTokenStart = nTokenOffset + eAct[0] if eAct[0] > 0 else nLastToken + eAct[0]
nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1]
for i in range(nTokenStart, nTokenEnd+1):
if "tags" in self.lToken[i]:
self.lToken[i]["tags"].update(sWhat.split("|"))
else:
self.lToken[i]["tags"] = set(sWhat.split("|"))
if bDebug:
echo(" TAG: " + sRuleId + " " + sLineId)
echo(" " + sWhat + " > " + self.lToken[nTokenStart]["sValue"] + " : " + self.lToken[nTokenEnd]["sValue"])
echo(" IMMUNITY:\n " + _rules_graph.dRule[sRuleId])
echo(" IMMUNITY: " + _rules_graph.dRule[sRuleId])
nTokenStart = nTokenOffset + eAct[0] if eAct[0] > 0 else nLastToken + eAct[0]
nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1]
if nTokenEnd - nTokenStart == 0:
self.lToken[nTokenStart]["bImmune"] = True
nErrorStart = self.nOffsetWithinParagraph + self.lToken[nTokenStart]["nStart"]
if nErrorStart in self.dError:
del self.dError[nErrorStart]
else:
for i in range(nTokenStart, nTokenEnd+1):
self.lToken[i]["bImmune"] = True
nErrorStart = self.nOffsetWithinParagraph + self.lToken[i]["nStart"]
if nErrorStart in self.dError:
del self.dError[nErrorStart]
else:
echo("# error: unknown action at " + sLineId)
elif cActionType == ">":
if bDebug:
echo(" COND_BREAK: " + sRuleId + " " + sLineId)
echo(" COND_BREAK")
break
except Exception as e:
raise Exception(str(e), sLineId, sRuleId, self.sSentence)
return bChange
def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
nStart = nOffset + m.start(iGroup)
|
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
|
697
698
699
700
701
702
703
704
705
706
707
708
709
710
|
-
-
|
else:
sNew = m.expand(sRepl)
sNew = sNew + " " * (nLen-len(sNew))
return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):]
def _tagAndPrepareTokenForRewriting (self, sWhat, nTokenRewriteStart, nTokenRewriteEnd, nTokenOffset, nLastToken, bCaseSvty, bDebug):
"text processor: rewrite tokens between <nTokenRewriteStart> and <nTokenRewriteEnd> position"
if bDebug:
echo(" START: {} - END: {} ".format(nTokenRewriteStart, nTokenRewriteEnd))
|
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
|
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
|
-
+
-
-
-
+
+
|
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=None):
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:
return False
if sNegPatternGroup1:
return morphex(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)
return morph(dTokenPos, (nPos, sWord), sPatternGroup1, False)
|