Grammalecte  Check-in [6f2fcade8d]

Overview
Comment:[core] gc engine: merge error creation functions (code clarification)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | rg
Files: files | file ages | folders
SHA3-256: 6f2fcade8d9effdf81c28d8c5a9528bef82f26cc740e324c756b4e356a6fb668
User & Date: olr on 2018-06-27 20:18:09
Other Links: branch diff | manifest | tags
Context
2018-06-27
20:53
[core] gc engine: create errors, code clarification check-in: f086eb66a0 user: olr tags: core, rg
20:18
[core] gc engine: merge error creation functions (code clarification) check-in: 6f2fcade8d user: olr tags: core, rg
18:58
[core][revert] gc engine: don’t remove merged tokens check-in: 82a84a50e8 user: olr tags: core, rg
Changes

Modified gc_core/py/lang_core/gc_engine.py from [7a8dc9f99f] to [6d8fead8fe].

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
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







-
-










-






-







# data
_sAppContext = ""                           # what software is running
_dOptions = None
_oSpellChecker = None
_oTokenizer = None
_aIgnoredRules = set()

# functions
_createRegexError = None


#### Initialization

def load (sContext="Python"):
    "initialization of the grammar checker"
    global _oSpellChecker
    global _sAppContext
    global _dOptions
    global _oTokenizer
    global _createRegexError
    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.activateStorage()
        _createRegexError = _createRegexWriterError  if _bWriterError  else _createRegexDictError
    except:
        traceback.print_exc()


def _getRules (bParagraph):
    try:
        if not bParagraph:
182
183
184
185
186
187
188
189

190
191
192
193
194
195
196
178
179
180
181
182
183
184

185
186
187
188
189
190
191
192







-
+







                            try:
                                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.get(nErrorStart, -1):
                                            dErrs[nErrorStart] = _createRegexError(s, sx, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext)
                                            dErrs[nErrorStart] = _createError(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)
                                        bParagraphChange = True
                                        bSentenceChange = True
                                        if bDebug:
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
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







-
+
-
-
-
-
-
+
+
-
-





-
+

-
+

-
+

-
+


-
+

-
+


+
+
+
+
+
+
+
+
+
-
-
-
-
+
+
+
+
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
+
-
-
+
-
-
-
-
-
-
-
-
-
-
-
+
-
-
-
-
-
-
+
+
+
+
+







                            except Exception as e:
                                raise Exception(str(e), "# " + sLineId + " # " + sRuleId)
    if bParagraphChange:
        return (s, dErrs)
    return (False, dErrs)


def _createRegexWriterError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
def _createError (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)
    nStart = nOffset + m.start(iGroup)
    nEnd = nOffset + m.end(iGroup)
    xErr.nErrorType = PROOFREADING
    xErr.aRuleIdentifier = sRuleId
    # suggestions
    if sRepl[0:1] == "=":
        sugg = globals()[sRepl[1:]](s, m)
        if sugg:
            if bUppercase and m.group(iGroup)[0:1].isupper():
                xErr.aSuggestions = tuple(map(str.capitalize, sugg.split("|")))
                lSugg = list(map(str.capitalize, sugg.split("|")))
            else:
                xErr.aSuggestions = tuple(sugg.split("|"))
                lSugg = sugg.split("|")
        else:
            xErr.aSuggestions = ()
            lSugg = []
    elif sRepl == "_":
        xErr.aSuggestions = ()
        lSugg = []
    else:
        if bUppercase and m.group(iGroup)[0:1].isupper():
            xErr.aSuggestions = tuple(map(str.capitalize, m.expand(sRepl).split("|")))
            lSugg = list(map(str.capitalize, m.expand(sRepl).split("|")))
        else:
            xErr.aSuggestions = tuple(m.expand(sRepl).split("|"))
            lSugg = m.expand(sRepl).split("|")
    # Message
    sMessage = globals()[sMsg[1:]](s, m)  if sMsg[0:1] == "="  else  m.expand(sMsg)
    if bShowRuleId:
        sMessage += "  # " + sLineId + " # " + sRuleId
    #
    if _bWriterError:
        xErr = SingleProofreadingError()    # uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
        xErr.nErrorStart = nStart
        xErr.nErrorLength = nEnd - nStart
        xErr.nErrorType = PROOFREADING
        xErr.aRuleIdentifier = sRuleId
    xErr.aShortComment = sMessage   # sMessage.split("|")[0]     # in context menu
    xErr.aFullComment = sMessage   # sMessage.split("|")[-1]    # in dialog
    if bShowRuleId:
        xErr.aShortComment += "  # " + sLineId + " # " + sRuleId
        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:
        xProperty = PropertyValue()
        xProperty.Name = "FullCommentURL"
        xProperty.Value = sURL
        xErr.aProperties = (xProperty,)
    else:
        xErr.aProperties = ()
    return xErr

        xErr.aSuggestions = tuple(lSugg)
        if sURL:
            xProperty = PropertyValue()
            xProperty.Name = "FullCommentURL"
            xProperty.Value = sURL
            xErr.aProperties = (xProperty,)
        else:
            xErr.aProperties = ()
        return xErr
    else:

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"
        dErr = {}
        dErr["nStart"] = nStart
        dErr["nEnd"] = nEnd
        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["sMessage"] = sMessage
    elif sRepl == "_":
        dErr["aSuggestions"] = []
        dErr["aSuggestions"] = lSugg
    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
    dErr["sMessage"] = globals()[sMsg[1:]](s, m)  if sMsg[0:1] == "="  else  m.expand(sMsg)
    if bShowRuleId:
        dErr["sMessage"] += "  # " + sLineId + " # " + sRuleId
    # URL
    dErr["URL"] = sURL  if sURL  else ""
        dErr["URL"] = sURL  if sURL  else ""
    # Context
    if bContext:
        dErr['sUnderlined'] = sx[m.start(iGroup):m.end(iGroup)]
        dErr['sBefore'] = sx[max(0,m.start(iGroup)-80):m.start(iGroup)]
        dErr['sAfter'] = sx[m.end(iGroup):m.end(iGroup)+80]
    return dErr
        if bContext:
            dErr['sUnderlined'] = self.sSentence0[nStart:nEnd]
            dErr['sBefore'] = self.sSentence0[max(0,nStart-80):nStart]
            dErr['sAfter'] = self.sSentence0[nEnd:nEnd+80]
        return dErr


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
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
578
579
580
581
582
583
584

585
586
587
588
589
590
591







-







        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.dError = {}
        self.createError = self._createWriterError  if _bWriterError  else self._createDictError

    def update (self, sSentence):
        "update <sSentence> and retokenize"
        self.sSentence = sSentence
        self.lToken = list(_oTokenizer.genTokens(sSentence, True))

    def _getNextMatchingNodes (self, dToken, dGraph, dNode, bDebug=False):
761
762
763
764
765
766
767
768

769
770
771
772
773
774
775
736
737
738
739
740
741
742

743
744
745
746
747
748
749
750







-
+







                                # grammar error
                                nTokenErrorStart = nTokenOffset + eAct[0]
                                if "bImmune" not in self.lToken[nTokenErrorStart]:
                                    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 dError or eAct[2] > dPriority.get(nErrorStart, -1):
                                        dError[nErrorStart] = self.createError(sWhat, nTokenOffset, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, True, eAct[3], eAct[4], bShowRuleId, "notype", bContext)
                                        dError[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("  NEW_ERROR:", dError[nErrorStart], "\n  ", dRule[sRuleId])
                            elif cActionType == "~":
                                # text processor
                                if bDebug:
                                    print("  TAG_PREPARE:\n  ", dRule[sRuleId])
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
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







-
+
-
-
-
-
-
-
-





-
+

-
+

-
+

-
+


-
+

-
+


+
+
+
+
+
+
+
+
+
-
-
-
-
+
+
+
+
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
-
-
+
+
+
+
+
+
-
-
-
-
-
-
-
-
-
-
+
-
-
+
-
-
-
-
-
-
-
-
-
-
-
+
-
-
-
-
-
-
+
+
+
+
+







                            if bDebug:
                                print("  COND_BREAK")
                            break
                except Exception as e:
                    raise Exception(str(e), sLineId, sRuleId, self.sSentence)
        return bChange, dError

    def _createWriterError (self, sSugg, nTokenOffset, iFirstToken, nStart, nEnd, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
    def _createError (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("|")))
                    lSugg = list(map(str.capitalize, sSugg.split("|")))
                else:
                    xErr.aSuggestions = tuple(sSugg.split("|"))
                    lSugg = sSugg.split("|")
            else:
                xErr.aSuggestions = ()
                lSugg = []
        elif sSugg == "_":
            xErr.aSuggestions = ()
            lSugg = []
        else:
            if bUppercase and self.lToken[iFirstToken]["sValue"][0:1].isupper():
                xErr.aSuggestions = tuple(map(str.capitalize, self._expand(sSugg, nTokenOffset).split("|")))
                lSugg = list(map(str.capitalize, self._expand(sSugg, nTokenOffset).split("|")))
            else:
                xErr.aSuggestions = tuple(self._expand(sSugg, nTokenOffset).split("|"))
                lSugg = self._expand(sSugg, nTokenOffset).split("|")
        # Message
        sMessage = globals()[sMsg[1:]](self.lToken)  if sMsg[0:1] == "="  else self._expand(sMsg, nTokenOffset)
        if bShowRuleId:
            sMessage += "  " + sLineId + " # " + sRuleId
        #
        if _bWriterError:
            xErr = SingleProofreadingError()    # uno.createUnoStruct( "com.sun.star.linguistic2.SingleProofreadingError" )
            xErr.nErrorStart = nStart
            xErr.nErrorLength = nEnd - nStart
            xErr.nErrorType = PROOFREADING
            xErr.aRuleIdentifier = sRuleId
        xErr.aShortComment = sMessage   # sMessage.split("|")[0]     # in context menu
        xErr.aFullComment = sMessage   # sMessage.split("|")[-1]    # in dialog
        if bShowRuleId:
            xErr.aShortComment += "  " + sLineId + " # " + sRuleId
            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:
            xProperty = PropertyValue()
            xProperty.Name = "FullCommentURL"
            xProperty.Value = sURL
            xErr.aProperties = (xProperty,)
        else:
            xErr.aProperties = ()
        return xErr

            xErr.aSuggestions = tuple(lSugg)
            if sURL:
                xProperty = PropertyValue()
                xProperty.Name = "FullCommentURL"
                xProperty.Value = sURL
                xErr.aProperties = (xProperty,)
            else:
                xErr.aProperties = ()
            return xErr
        else:
    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"
            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"] = []
            dErr["sMessage"] = sMessage
        elif sSugg == "_":
            dErr["aSuggestions"] = []
            dErr["aSuggestions"] = lSugg
        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 ""
            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
            if bContext:
                dErr['sUnderlined'] = self.sSentence0[nStart:nEnd]
                dErr['sBefore'] = self.sSentence0[max(0,nStart-80):nStart]
                dErr['sAfter'] = self.sSentence0[nEnd:nEnd+80]
            return dErr

    def _expand (self, sText, nTokenOffset):
        #print("*", sText)
        for m in re.finditer(r"\\([0-9]+)", sText):
            sText = sText.replace(m.group(0), self.lToken[int(m.group(1))+nTokenOffset]["sValue"])
        #print(">", sText)
        return sText