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
|
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
|
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
-
+
-
+
-
-
+
+
-
-
-
-
-
-
+
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
-
+
-
-
+
+
-
+
+
+
-
-
-
+
+
+
-
+
-
+
|
author = "${author}"
_rules = None # module gc_rules
# data
_sAppContext = "" # what software is running
_dOptions = None
_oSpellChecker = None
_oTokenizer = None
_aIgnoredRules = set()
# functions
_createRegexError = None
#### Initialization
def load (sContext="Python"):
global _oSpellChecker
global _sAppContext
global _dOptions
global _oTokenizer
global _createRegexError
global _createTokenError
try:
_oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_extended_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
_sAppContext = sContext
_dOptions = dict(gc_options.getOptions(sContext)) # duplication necessary, to be able to reset to default
_oTokenizer = _oSpellChecker.getTokenizer()
_oSpellChecker = None
_dAnalyses = {} # cache for data from dictionary
_oSpellChecker.activateStorage()
_createRegexError = _createRegexWriterError if _bWriterError else _createRegexDictError
except:
traceback.print_exc()
def _getRules (bParagraph):
try:
if not bParagraph:
return _rules.lSentenceRules
return _rules.lParagraphRules
except:
_loadRules()
if not bParagraph:
return _rules.lSentenceRules
return _rules.lParagraphRules
def _loadRules ():
from . import gc_rules
global _rules
_rules = gc_rules
# compile rules regex
for sOption, lRuleGroup in chain(_rules.lParagraphRules, _rules.lSentenceRules):
if sOption != "@@@@":
for aRule in lRuleGroup:
try:
aRule[0] = re.compile(aRule[0])
except:
echo("Bad regular expression in # " + str(aRule[2]))
aRule[0] = "(?i)<Grammalecte>"
#### Parsing
_zEndOfSentence = re.compile(r'([.?!:;…][ .?!… »”")]*|.$)')
_zBeginOfParagraph = re.compile(r"^\W*")
_zEndOfParagraph = re.compile(r"\W*$")
def _getSentenceBoundaries (sText):
iStart = _zBeginOfParagraph.match(sText).end()
for m in _zEndOfSentence.finditer(sText):
yield (iStart, m.end())
iStart = m.end()
def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False):
"analyses the paragraph sText and returns list of errors"
#sText = unicodedata.normalize("NFC", sText)
aErrors = None
sAlt = sText
sRealText = sText
dDA = {} # Disambiguisator. Key = position; value = list of morphologies
sNew, aErrors = _proofread(sText, sAlt, 0, True, dDA, dPriority, sCountry, dOpt, bDebug, bContext)
sNew, aErrors = _proofread(None, sText, sRealText, 0, True, dPriority, sCountry, dOpt, bShowRuleId, bDebug, bContext)
if sNew:
sText = sNew
except:
raise
# cleanup
if " " in sText:
sText = sText.replace(" ", ' ') # nbsp
if " " in sText:
sText = sText.replace(" ", ' ') # nnbsp
if "'" in sText:
sText = sText.replace("'", "’")
if "‑" in sText:
sText = sText.replace("‑", "-") # nobreakdash
# parse sentences
for iStart, iEnd in _getSentenceBoundaries(sText):
if 4 < (iEnd - iStart) < 2000:
dDA.clear()
_, errs = _proofread(sText[iStart:iEnd], sAlt[iStart:iEnd], iStart, False, dDA, dPriority, sCountry, dOpt, bDebug, bContext)
oSentence = TokenSentence(sText[iStart:iEnd], sRealText[iStart:iEnd], iStart)
_, errs = _proofread(oSentence, sText[iStart:iEnd], sRealText[iStart:iEnd], iStart, False, dPriority, sCountry, dOpt, bShowRuleId, bDebug, bContext)
aErrors.update(errs)
except:
raise
return aErrors.values() # this is a view (iterable)
def _getSentenceBoundaries (sText):
iStart = _zBeginOfParagraph.match(sText).end()
for m in _zEndOfSentence.finditer(sText):
yield (iStart, m.end())
iStart = m.end()
def _proofread (s, sx, nOffset, bParagraph, dDA, dPriority, sCountry, dOptions, bDebug, bContext):
bChange = False
bIdRule = option('idrule')
bParagraphChange = False
bSentenceChange = False
dTokenPos = oSentence.dTokenPos if oSentence else {}
for sOption, lRuleGroup in _getRules(bParagraph):
if sOption == "@@@@":
# graph rules
if not bParagraph and bSentenceChange:
oSentence.update(s)
bSentenceChange = False
for sGraphName, sLineId in lRuleGroup:
if bDebug:
print("\n>>>> GRAPH:", sGraphName, sLineId)
bParagraphChange, errs = oSentence.parse(dAllGraph[sGraphName], dPriority, sCountry, dOptions, bShowRuleId, bDebug, bContext)
dErrs.update(errs)
if bParagraphChange:
s = oSentence.rewrite(bDebug)
if not sOption or dOptions.get(sOption, False):
elif not sOption or dOptions.get(sOption, False):
# regex rules
for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup:
if sRuleId not in _aIgnoredRules:
for m in zRegex.finditer(s):
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 globals()[sFuncCond](s, sx, m, dDA, sCountry, bCondMemo)
bCondMemo = not sFuncCond or globals()[sFuncCond](s, sx, m, dTokenPos, sCountry, bCondMemo)
if bCondMemo:
if cActionType == "-":
# grammar error
nErrorStart = nOffset + m.start(eAct[0])
if nErrorStart not in dErrs or nPriority > dPriority[nErrorStart]:
dErrs[nErrorStart] = _createError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bIdRule, sOption, bContext)
if nErrorStart not in dErrs or nPriority > dPriority.get(nErrorStart, -1):
dErrs[nErrorStart] = _createRegexError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext)
dPriority[nErrorStart] = nPriority
elif cActionType == "~":
# text processor
s = _rewrite(s, sWhat, eAct[0], m, bUppercase)
bChange = True
bParagraphChange = True
bSentenceChange = True
if bDebug:
echo("~ " + s + " -- " + m.group(eAct[0]) + " # " + sLineId)
elif cActionType == "=":
# disambiguation
if not bParagraph:
globals()[sWhat](s, m, dDA)
if bDebug:
echo("= " + m.group(0) + " # " + sLineId + "\nDA: " + str(dDA))
globals()[sWhat](s, m, 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)
elif cActionType == ">":
break
except Exception as e:
raise Exception(str(e), "# " + sLineId + " # " + sRuleId)
if bChange:
if bParagraphChange:
return (s, dErrs)
return (False, dErrs)
def _createWriterError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext):
def _createRegexWriterError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error for Writer (LO/OO)"
xErr = SingleProofreadingError()
#xErr = uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
xErr.nErrorStart = nOffset + m.start(iGroup)
xErr.nErrorLength = m.end(iGroup) - m.start(iGroup)
xErr.nErrorType = PROOFREADING
xErr.aRuleIdentifier = sRuleId
|
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
|
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
|
-
-
+
-
-
-
+
-
+
-
+
-
+
-
-
-
-
-
-
+
+
-
-
+
+
-
+
-
-
-
+
-
+
|
xErr.aSuggestions = ()
else:
if bUppercase and m.group(iGroup)[0:1].isupper():
xErr.aSuggestions = tuple(map(str.capitalize, m.expand(sRepl).split("|")))
else:
xErr.aSuggestions = tuple(m.expand(sRepl).split("|"))
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](s, m)
else:
sMessage = m.expand(sMsg)
if bIdRule:
if bShowRuleId:
xErr.aShortComment += " # " + sLineId + " # " + sRuleId
# URL
if sURL:
p = PropertyValue()
p.Name = "FullCommentURL"
p.Value = sURL
xErr.aProperties = (p,)
else:
xErr.aProperties = ()
return xErr
def _createDictError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bIdRule, sOption, bContext):
def _createRegexDictError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error as a dictionary"
dErr = {}
dErr["nStart"] = nOffset + m.start(iGroup)
dErr["nEnd"] = nOffset + m.end(iGroup)
dErr["sLineId"] = sLineId
dErr["sRuleId"] = sRuleId
dErr["sType"] = sOption if sOption else "notype"
# suggestions
if sRepl[0:1] == "=":
sugg = globals()[sRepl[1:]](s, m)
if sugg:
if bUppercase and m.group(iGroup)[0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, sugg.split("|")))
else:
dErr["aSuggestions"] = sugg.split("|")
else:
dErr["aSuggestions"] = ()
dErr["aSuggestions"] = []
elif sRepl == "_":
dErr["aSuggestions"] = ()
dErr["aSuggestions"] = []
else:
if bUppercase and m.group(iGroup)[0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, m.expand(sRepl).split("|")))
else:
dErr["aSuggestions"] = m.expand(sRepl).split("|")
# Message
if sMsg[0:1] == "=":
sMessage = globals()[sMsg[1:]](s, m)
else:
sMessage = m.expand(sMsg)
dErr["sMessage"] = sMessage
if bIdRule:
def _rewrite (s, sRepl, iGroup, m, bUppercase):
"text processor: write sRepl in s at iGroup position"
def _rewrite (sSentence, sRepl, iGroup, m, bUppercase):
"text processor: write <sRepl> in <sSentence> at <iGroup> position"
nLen = m.end(iGroup) - m.start(iGroup)
if sRepl == "*":
sNew = " " * nLen
elif sRepl == ">" or sRepl == "_" or sRepl == "~":
elif sRepl == "_":
sNew = sRepl + " " * (nLen-1)
elif sRepl == "@":
sNew = "@" * nLen
sNew = globals()[sRepl[1:]](s, m)
sNew = globals()[sRepl[1:]](sSentence, 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 s[0:m.start(iGroup)] + sNew + s[m.end(iGroup):]
return sSentence[0:m.start(iGroup)] + sNew + sSentence[m.end(iGroup):]
def ignoreRule (sRuleId):
_aIgnoredRules.add(sRuleId)
def resetIgnoreRules ():
|
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
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
|
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
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
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
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
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
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
839
840
841
842
843
844
845
846
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
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
|
-
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
+
+
-
-
+
-
-
-
+
+
-
-
+
-
-
+
+
-
-
+
-
+
-
-
+
+
+
+
+
+
+
-
-
-
-
-
-
-
+
-
-
+
+
-
-
+
-
+
-
-
+
+
+
-
+
+
+
+
+
+
+
+
+
|
if sNegPattern and re.search(sNegPattern, s):
return False
if re.search(sPattern, s):
return True
return False
def look_chk1 (dDA, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=None):
def look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=None):
"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(dDA, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)
return morph(dDA, (nPos, sWord), sPatternGroup1, False)
return morphex(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)
return morph(dTokenPos, (nPos, sWord), sPatternGroup1, False)
#### Disambiguator
def select (dTokenPos, nPos, sWord, sPattern, lDefault=None):
if not sWord:
return True
if nPos not in dTokenPos:
print("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):
if not sWord:
return True
if nPos not in dTokenPos:
print("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, lMorph):
if nPos not in dTokenPos:
print("Error. There should be a token at this position: ", nPos)
return True
dTokenPos[nPos]["lMorph"] = lMorph
return True
#### TOKEN SENTENCE CHECKER
class TokenSentence:
def __init__ (self, sSentence, sSentence0, nOffset):
self.sSentence = sSentence
self.sSentence0 = sSentence0
self.nOffsetWithinParagraph = nOffset
self.lToken = list(_oTokenizer.genTokens(sSentence, True))
self.dTokenPos = { dToken["nStart"]: dToken for dToken in self.lToken }
self.dTags = {}
self.createError = self._createWriterError if _bWriterError else self._createDictError
def update (self, sSentence):
self.sSentence = sSentence
self.lToken = list(_oTokenizer.genTokens(sSentence, True))
def _getNextMatchingNodes (self, dToken, dGraph, dNode, bDebug=False):
"generator: return nodes where <dToken> “values” match <dNode> arcs"
# token value
if dToken["sValue"] in dNode:
if bDebug:
print(" MATCH:", dToken["sValue"])
yield dGraph[dNode[dToken["sValue"]]]
if dToken["sValue"][0:2].istitle(): # we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
sValue = dToken["sValue"].lower()
if sValue in dNode:
if bDebug:
print(" MATCH:", sValue)
yield dGraph[dNode[sValue]]
elif dToken["sValue"].isupper():
sValue = dToken["sValue"].lower()
if sValue in dNode:
if bDebug:
print(" MATCH:", sValue)
yield dGraph[dNode[sValue]]
sValue = dToken["sValue"].capitalize()
if sValue in dNode:
if bDebug:
print(" MATCH:", sValue)
yield dGraph[dNode[sValue]]
# token lemmas
if "<lemmas>" in dNode:
for sLemma in _oSpellChecker.getLemma(dToken["sValue"]):
if sLemma in dNode["<lemmas>"]:
if bDebug:
print(" MATCH: >" + sLemma)
yield dGraph[dNode["<lemmas>"][sLemma]]
# universal arc
if "*" in dNode:
if dToken["sType"] != "PUNC":
if bDebug:
print(" MATCH: *")
yield dGraph[dNode["*"]]
# regex value arcs
if "<re_value>" in dNode:
for sRegex in dNode["<re_value>"]:
if "¬" not in sRegex:
# no anti-pattern
if re.search(sRegex, dToken["sValue"]):
if bDebug:
print(" MATCH: ~" + sRegex)
yield dGraph[dNode["<re_value>"][sRegex]]
else:
# there is an anti-pattern
sPattern, sNegPattern = sRegex.split("¬", 1)
if sNegPattern and re.search(sNegPattern, dToken["sValue"]):
continue
if re.search(sPattern, dToken["sValue"]):
if bDebug:
print(" MATCH: ~" + sRegex)
yield dGraph[dNode["<re_value>"][sRegex]]
# regex morph arcs
if "<re_morph>" in dNode:
for sRegex in dNode["<re_morph>"]:
if "¬" not in sRegex:
# no anti-pattern
if any(re.search(sRegex, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
if bDebug:
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
else:
# there is an anti-pattern
sPattern, sNegPattern = sRegex.split("¬", 1)
if sNegPattern == "*":
# all morphologies must match with <sPattern>
if sPattern and all(re.search(sPattern, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
if bDebug:
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
else:
if sNegPattern and any(re.search(sNegPattern, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
continue
if any(re.search(sPattern, sMorph) for sMorph in _oSpellChecker.getMorph(dToken["sValue"])):
if bDebug:
print(" MATCH: @" + sRegex)
yield dGraph[dNode["<re_morph>"][sRegex]]
def parse (self, dGraph, dPriority, sCountry="${country_default}", dOptions=None, bShowRuleId=False, bDebug=False, bContext=False):
dErr = {}
dPriority = {} # Key = position; value = priority
dOpt = _dOptions if not dOptions else dOptions
lPointer = []
bChange = False
for dToken in self.lToken:
if bDebug:
print("TOKEN:", dToken["sValue"])
# check arcs for each existing pointer
lNextPointer = []
for dPointer in lPointer:
for dNode in self._getNextMatchingNodes(dToken, dGraph, dPointer["dNode"], bDebug):
lNextPointer.append({"iToken": dPointer["iToken"], "dNode": dNode})
lPointer = lNextPointer
# check arcs of first nodes
for dNode in self._getNextMatchingNodes(dToken, dGraph, dGraph[0], bDebug):
lPointer.append({"iToken": dToken["i"], "dNode": dNode})
# check if there is rules to check for each pointer
for dPointer in lPointer:
#if bDebug:
# print("+", dPointer)
if "<rules>" in dPointer["dNode"]:
bHasChanged, errs = self._executeActions(dGraph, dPointer["dNode"]["<rules>"], dPointer["iToken"]-1, dToken["i"], dPriority, dOpt, sCountry, bShowRuleId, bDebug, bContext)
dErr.update(errs)
if bHasChanged:
bChange = True
return (bChange, dErr)
def _executeActions (self, dGraph, dNode, nTokenOffset, nLastToken, dPriority, dOptions, sCountry, bShowRuleId, bDebug, bContext):
"execute actions found in the DARG"
dErrs = {}
bChange = False
for sLineId, nextNodeKey in dNode.items():
bCondMemo = None
for sRuleId in dGraph[nextNodeKey]:
try:
if bDebug:
print("ACTION:", sRuleId)
print(dRule[sRuleId])
sOption, sFuncCond, cActionType, sWhat, *eAct = dRule[sRuleId]
# Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, nPriority, message, URL ]
# TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd ]
# Disambiguator [ option, condition, "=", replacement/suggestion/action ]
# Tag [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
# Test [ option, condition, ">", "" ]
if not sOption or dOptions.get(sOption, False):
bCondMemo = not sFuncCond or globals()[sFuncCond](self.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, self.dTags, self.sSentence, self.sSentence0)
if bCondMemo:
if cActionType == "-":
# grammar error
nTokenErrorStart = nTokenOffset + eAct[0]
nTokenErrorEnd = (nTokenOffset + eAct[1]) if eAct[1] else nLastToken
nErrorStart = self.nOffsetWithinParagraph + self.lToken[nTokenErrorStart]["nStart"]
nErrorEnd = self.nOffsetWithinParagraph + self.lToken[nTokenErrorEnd]["nEnd"]
if nErrorStart not in dErrs or eAct[2] > dPriority.get(nErrorStart, -1):
dErrs[nErrorStart] = self.createError(sWhat, nTokenOffset, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, True, eAct[3], eAct[4], bShowRuleId, "notype", bContext)
dPriority[nErrorStart] = eAct[2]
if bDebug:
print("-", sRuleId, dErrs[nErrorStart])
elif cActionType == "~":
# text processor
nEndToken = (nTokenOffset + eAct[1]) if eAct[1] else nLastToken
self._tagAndPrepareTokenForRewriting(sWhat, nTokenOffset + eAct[0], nEndToken, bDebug)
if bDebug:
print("~", sRuleId)
bChange = True
elif cActionType == "=":
# disambiguation
globals()[sWhat](self.lToken, nTokenOffset)
if bDebug:
print("=", sRuleId)
elif cActionType == ">":
# we do nothing, this test is just a condition to apply all following actions
if bDebug:
print(">", sRuleId)
pass
elif cActionType == "/":
# tags
nTokenTag = nTokenOffset + eAct[0]
if sWhat not in self.dTags:
self.dTags[sWhat] = (nTokenTag, nTokenTag)
elif nTokenTag > self.dTags[sWhat][1]:
self.dTags[sWhat] = (self.dTags[sWhat][0], nTokenTag)
if bDebug:
print("/", sRuleId)
else:
print("# error: unknown action at " + sLineId)
elif cActionType == ">":
if bDebug:
print(">!", sRuleId)
break
except Exception as e:
raise Exception(str(e), sLineId, sRuleId, self.sSentence)
return bChange, dErrs
def _createWriterError (self, sSugg, nTokenOffset, iFirstToken, nStart, nEnd, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error for Writer (LO/OO)"
xErr = SingleProofreadingError()
#xErr = uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
xErr.nErrorStart = nStart
xErr.nErrorLength = nEnd - nStart
xErr.nErrorType = PROOFREADING
xErr.aRuleIdentifier = sRuleId
# suggestions
if sSugg[0:1] == "=":
sSugg = globals()[sSugg[1:]](self.lToken, nTokenOffset)
if sSugg:
if bUppercase and self.lToken[iFirstToken]["sValue"][0:1].isupper():
xErr.aSuggestions = tuple(map(str.capitalize, sSugg.split("|")))
else:
xErr.aSuggestions = tuple(sSugg.split("|"))
else:
xErr.aSuggestions = ()
elif sSugg == "_":
xErr.aSuggestions = ()
else:
if bUppercase and self.lToken[iFirstToken]["sValue"][0:1].isupper():
xErr.aSuggestions = tuple(map(str.capitalize, self._expand(sSugg, nTokenOffset).split("|")))
else:
xErr.aSuggestions = tuple(self._expand(sSugg, nTokenOffset).split("|"))
# Message
sMessage = globals()[sMsg[1:]](self.lToken) if sMsg[0:1] == "=" else self._expand(sMsg, nTokenOffset)
xErr.aShortComment = sMessage # sMessage.split("|")[0] # in context menu
xErr.aFullComment = sMessage # sMessage.split("|")[-1] # in dialog
if bShowRuleId:
xErr.aShortComment += " " + sLineId + " # " + sRuleId
# URL
if sURL:
p = PropertyValue()
p.Name = "FullCommentURL"
p.Value = sURL
xErr.aProperties = (p,)
else:
xErr.aProperties = ()
return xErr
def _createDictError (self, sSugg, nTokenOffset, iFirstToken, nStart, nEnd, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
"error as a dictionary"
dErr = {}
dErr["nStart"] = nStart
dErr["nEnd"] = nEnd
dErr["sLineId"] = sLineId
dErr["sRuleId"] = sRuleId
dErr["sType"] = sOption if sOption else "notype"
# suggestions
if sSugg[0:1] == "=":
sSugg = globals()[sSugg[1:]](self.lToken, nTokenOffset)
if sSugg:
if bUppercase and self.lToken[iFirstToken]["sValue"][0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, sSugg.split("|")))
else:
dErr["aSuggestions"] = sSugg.split("|")
else:
dErr["aSuggestions"] = []
elif sSugg == "_":
dErr["aSuggestions"] = []
else:
if bUppercase and self.lToken[iFirstToken]["sValue"][0:1].isupper():
dErr["aSuggestions"] = list(map(str.capitalize, self._expand(sSugg, nTokenOffset).split("|")))
else:
dErr["aSuggestions"] = self._expand(sSugg, nTokenOffset).split("|")
# Message
dErr["sMessage"] = globals()[sMsg[1:]](self.lToken) if sMsg[0:1] == "=" else self._expand(sMsg, nTokenOffset)
if bShowRuleId:
dErr["sMessage"] += " " + sLineId + " # " + sRuleId
# URL
dErr["URL"] = sURL if sURL else ""
# Context
if bContext:
dErr['sUnderlined'] = self.sSentence0[dErr["nStart"]:dErr["nEnd"]]
dErr['sBefore'] = self.sSentence0[max(0,dErr["nStart"]-80):dErr["nStart"]]
dErr['sAfter'] = self.sSentence0[dErr["nEnd"]:dErr["nEnd"]+80]
return dErr
def _expand (self, sMsg, nTokenOffset):
#print("*", sMsg)
for m in re.finditer(r"\\([0-9]+)", sMsg):
sMsg = sMsg.replace(m.group(0), self.lToken[int(m.group(1))+nTokenOffset]["sValue"])
#print(">", sMsg)
return sMsg
def _tagAndPrepareTokenForRewriting (self, sWhat, nTokenRewriteStart, nTokenRewriteEnd, bUppercase=True, bDebug=False):
"text processor: rewrite tokens between <nTokenRewriteStart> and <nTokenRewriteEnd> position"
if bDebug:
print("REWRITING:", nTokenRewriteStart, nTokenRewriteEnd)
if sWhat == "*":
# purge text
if nTokenRewriteEnd - nTokenRewriteStart == 0:
self.lToken[nTokenRewriteStart]["bToRemove"] = True
else:
for i in range(nTokenRewriteStart, nTokenRewriteEnd+1):
self.lToken[i]["bToRemove"] = True
else:
if sWhat.startswith("="):
sWhat = globals()[sWhat[1:]](self.lToken)
bUppercase = bUppercase and self.lToken[nTokenRewriteStart]["sValue"][0:1].isupper()
if nTokenRewriteEnd - nTokenRewriteStart == 0:
sWhat = sWhat + " " * (len(self.lToken[nTokenRewriteStart]["sValue"])-len(sWhat))
if bUppercase:
sWhat = sWhat[0:1].upper() + sWhat[1:]
self.lToken[nTokenRewriteStart]["sNewValue"] = sWhat
else:
lTokenValue = sWhat.split("|")
if len(lTokenValue) != (nTokenRewriteEnd - nTokenRewriteStart + 1):
print("Error. Text processor: number of replacements != number of tokens.")
return
for i, sValue in zip(range(nTokenRewriteStart, nTokenRewriteEnd+1), lTokenValue):
if bUppercase:
sValue = sValue[0:1].upper() + sValue[1:]
self.lToken[i]["sNewValue"] = sValue
def rewrite (self, bDebug=False):
"rewrite the sentence, modify tokens, purge the token list"
lNewToken = []
for i, dToken in enumerate(self.lToken):
if "bToRemove" in dToken:
# remove useless token
self.sSentence = self.sSentence[:dToken["nStart"]] + " " * (dToken["nEnd"] - dToken["nStart"]) + self.sSentence[dToken["nEnd"]:]
if bDebug:
print("removed:", dToken["sValue"])
else:
lNewToken.append(dToken)
if "sNewValue" in dToken:
# rewrite token and sentence
if bDebug:
print(dToken["sValue"], "->", dToken["sNewValue"])
dToken["sRealValue"] = dToken["sValue"]
dToken["sValue"] = dToken["sNewValue"]
nDiffLen = len(dToken["sRealValue"]) - len(dToken["sNewValue"])
sNewRepl = (dToken["sNewValue"] + " " * nDiffLen) if nDiffLen >= 0 else dToken["sNewValue"][:len(dToken["sRealValue"])]
self.sSentence = self.sSentence[:dToken["nStart"]] + sNewRepl + self.sSentence[dToken["nEnd"]:]
del dToken["sNewValue"]
if bDebug:
print(self.sSentence)
self.lToken.clear()
self.lToken = lNewToken
return self.sSentence
#### Analyse tokens
def g_morph (dToken, sPattern, sNegPattern=""):
"analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies"
if "lMorph" in dToken:
lMorph = dToken["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)
else:
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=""):
"analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
lMorph = _oSpellChecker.getMorph(dToken["sValue"])
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)
else:
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_tag_before (dToken, dTags, sTag):
if sTag not in dTags:
return False
if dToken["nStart"] > dTags[sTag][0]:
return True
return False
def g_tag_after (dToken, dTags, sTag):
if sTag not in dTags:
return False
if dToken["nStart"] < dTags[sTag][1]:
return True
return False
#### Disambiguator
def select (dDA, nPos, sWord, sPattern, lDefault=None):
if not sWord:
def g_select (dToken, sPattern, lDefault=None):
"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:
return True
if nPos in dDA:
return True
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return True
if len(_dAnalyses[sWord]) == 1:
lSelect = [ sMorph for sMorph in _dAnalyses[sWord] if re.search(sPattern, sMorph) ]
lSelect = [ sMorph for sMorph in lMorph if re.search(sPattern, sMorph) ]
if lSelect:
if len(lSelect) != len(_dAnalyses[sWord]):
dDA[nPos] = lSelect
if len(lSelect) != len(lMorph):
dToken["lMorph"] = lSelect
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
dDA[nPos] = lDefault
dToken["lMorph"] = lDefault
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
def exclude (dDA, nPos, sWord, sPattern, lDefault=None):
if not sWord:
def g_exclude (dToken, sPattern, lDefault=None):
"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
#print("DA:", dToken["sValue"], dToken["lMorph"])
return True
if nPos in dDA:
return True
if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
return True
if len(_dAnalyses[sWord]) == 1:
return True
lSelect = [ sMorph for sMorph in _dAnalyses[sWord] if not re.search(sPattern, sMorph) ]
if len(lSelect) != len(_dAnalyses[sWord]):
dDA[nPos] = lSelect
if len(lSelect) != len(lMorph):
dToken["lMorph"] = lSelect
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
dDA[nPos] = lDefault
dToken["lMorph"] = lDefault
#echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
def define (dDA, nPos, lMorph):
dDA[nPos] = lMorph
def g_define (dToken, lMorph):
"set morphologies of <dToken>, always return True"
dToken["lMorph"] = lMorph
#echo("= "+str(nPos)+" "+str(dDA[nPos]))
|