Grammalecte  Check-in [48056be413]

Overview
Comment:[core] code cleaning (pylint)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | rg
Files: files | file ages | folders
SHA3-256: 48056be413279a67e3aeca763b0e4a3a46e1d16b6e3261a6089f4441bbdbcf02
User & Date: olr on 2018-06-24 14:16:22
Other Links: branch diff | manifest | tags
Context
2018-06-24
14:49
[core] code cleaning (pylint) check-in: f1726135a3 user: olr tags: core, rg
14:16
[core] code cleaning (pylint) check-in: 48056be413 user: olr tags: core, rg
12:28
[build] compile rules: generated functions are now private check-in: ec15ccafa3 user: olr tags: build, rg
Changes

Modified gc_core/py/lang_core/gc_engine.py from [a4200b43e6] to [4a05ed73f6].


1
2



3
4
5
6
7
8
9
1


2
3
4
5
6
7
8
9
10
11
+
-
-
+
+
+







"""
# Grammalecte
# Grammar checker engine
Grammalecte
Grammar checker engine
"""

import re
import sys
import os
import traceback
#import unicodedata
from itertools import chain
53
54
55
56
57
58
59

60
61
62
63
64
65
66
67
68
69
70
71
72
55
56
57
58
59
60
61
62
63
64
65
66
67

68
69
70
71
72
73
74







+





-







# functions
_createRegexError = None


#### Initialization

def load (sContext="Python"):
    "initialization of the grammar checker"
    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.activateStorage()
        _createRegexError = _createRegexWriterError  if _bWriterError  else _createRegexDictError
242
243
244
245
246
247
248
249
250
251
252




253
254
255
256
257
258
259
244
245
246
247
248
249
250




251
252
253
254
255
256
257
258
259
260
261







-
-
-
-
+
+
+
+







    sMessage = globals()[sMsg[1:]](s, m)  if sMsg[0:1] == "="  else  m.expand(sMsg)
    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,)
        xProperty = PropertyValue()
        xProperty.Name = "FullCommentURL"
        xProperty.Value = sURL
        xErr.aProperties = (xProperty,)
    else:
        xErr.aProperties = ()
    return xErr


def _createRegexDictError (s, sx, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
    "error as a dictionary"
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
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







+




+




+



















+






+





+






+




+




+




+






+





+











-
+







    else:
        sNew = m.expand(sRepl)
        sNew = sNew + " " * (nLen-len(sNew))
    return sSentence[0:m.start(iGroup)] + sNew + sSentence[m.end(iGroup):]


def ignoreRule (sRuleId):
    "disable rule <sRuleId>"
    _aIgnoredRules.add(sRuleId)


def resetIgnoreRules ():
    "clear all ignored rules"
    _aIgnoredRules.clear()


def reactivateRule (sRuleId):
    "(re)activate rule <sRuleId>"
    _aIgnoredRules.discard(sRuleId)


def listRules (sFilter=None):
    "generator: returns typle (sOption, sLineId, sRuleId)"
    if sFilter:
        try:
            zFilter = re.compile(sFilter)
        except:
            echo("# Error. List rules: wrong regex.")
            sFilter = None
    for sOption, lRuleGroup in chain(_getRules(True), _getRules(False)):
        if sOption != "@@@@":
            for _, _, sLineId, sRuleId, _, _ in lRuleGroup:
                if not sFilter or zFilter.search(sRuleId):
                    yield (sOption, sLineId, sRuleId)


def displayRules (sFilter=None):
    "display the name of rules, with the filter <sFilter>"
    echo("List of rules. Filter: << " + str(sFilter) + " >>")
    for sOption, sLineId, sRuleId in listRules(sFilter):
        echo("{:<10} {:<10} {}".format(sOption, sLineId, sRuleId))


def setOption (sOpt, bVal):
    "set option <sOpt> with <bVal> if it exists"
    if sOpt in _dOptions:
        _dOptions[sOpt] = bVal


def setOptions (dOpt):
    "update the dictionary of options with <dOpt>"
    for sKey, bVal in dOpt.items():
        if sKey in _dOptions:
            _dOptions[sKey] = bVal


def getOptions ():
    "return the dictionary of current options"
    return _dOptions


def getDefaultOptions ():
    "return the dictionary of default options"
    return dict(gc_options.getOptions(_sAppContext))


def getOptionsLabels (sLang):
    "return options labels"
    return gc_options.getUI(sLang)


def displayOptions (sLang):
    "display the list of grammar checking options"
    echo("List of options")
    echo("\n".join( [ k+":\t"+str(v)+"\t"+gc_options.getUI(sLang).get(k, ("?", ""))[0]  for k, v  in sorted(_dOptions.items()) ] ))
    echo("")


def resetOptions ():
    "set options to default values"
    global _dOptions
    _dOptions = dict(gc_options.getOptions(_sAppContext))


def getSpellChecker ():
    "return the spellchecker object"
    return _oSpellChecker


def _getPath ():
    return os.path.join(os.path.dirname(sys.modules[__name__].__file__), __name__ + ".py")



#### common functions

def option (sOpt):
    "return True if option sOpt is active"
    "return True if option <sOpt> is active"
    return _dOptions.get(sOpt, False)


def displayInfo (dTokenPos, tWord):
    "for debugging: retrieve info of word"
    if not tWord:
        echo("> nothing to find")
413
414
415
416
417
418
419
420

421
422
423


424
425
426
427
428
429
430
431
432
433
434
435


436
437
438
439


440
441
442
443
444
445
446
447

448
449
450


451
452
453
454
455
456
457
458
459
460


461
462
463
464


465
466
467
468
469
470
471
427
428
429
430
431
432
433

434
435


436
437
438
439
440
441
442
443
444
445
446
447


448
449
450
451


452
453
454
455
456
457
458
459
460

461
462


463
464
465
466
467
468
469
470
471
472


473
474
475
476


477
478
479
480
481
482
483
484
485







-
+

-
-
+
+










-
-
+
+


-
-
+
+







-
+

-
-
+
+








-
-
+
+


-
-
+
+







def morph (dTokenPos, tWord, sPattern, bStrict=True, bNoWord=False):
    "analyse a tuple (position, word), return True if sPattern in 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
    p = re.compile(sPattern)
    zPattern = re.compile(sPattern)
    if bStrict:
        return all(p.search(s)  for s in lMorph)
    return any(p.search(s)  for s in lMorph)
        return all(zPattern.search(s)  for s in lMorph)
    return any(zPattern.search(s)  for s in lMorph)


def morphex (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
    np = re.compile(sNegPattern)
    if any(np.search(s)  for s in lMorph):
    zNegPattern = re.compile(sNegPattern)
    if any(zNegPattern.search(s)  for s in lMorph):
        return False
    # search sPattern
    p = re.compile(sPattern)
    return any(p.search(s)  for s in lMorph)
    zPattern = re.compile(sPattern)
    return any(zPattern.search(s)  for s in lMorph)


def analyse (sWord, sPattern, bStrict=True):
    "analyse a word, return True if sPattern in morphologies (disambiguation off)"
    lMorph = _oSpellChecker.getMorph(sWord)
    if not lMorph:
        return False
    p = re.compile(sPattern)
    zPattern = re.compile(sPattern)
    if bStrict:
        return all(p.search(s)  for s in lMorph)
    return any(p.search(s)  for s in lMorph)
        return all(zPattern.search(s)  for s in lMorph)
    return any(zPattern.search(s)  for s in lMorph)


def analysex (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
    np = re.compile(sNegPattern)
    if any(np.search(s)  for s in lMorph):
    zNegPattern = re.compile(sNegPattern)
    if any(zNegPattern.search(s)  for s in lMorph):
        return False
    # search sPattern
    p = re.compile(sPattern)
    return any(p.search(s)  for s in lMorph)
    zPattern = re.compile(sPattern)
    return any(zPattern.search(s)  for s in lMorph)



## functions to get text outside pattern scope

# warning: check compile_rules.py to understand how it works

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
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







+


















+


















+












+












+







        return morphex(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)
    return morph(dTokenPos, (nPos, sWord), sPatternGroup1, False)


#### Disambiguator

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:
        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):
    "Disambiguation: exclude morphologies of <sWord> matching <sPattern>"
    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):
    "Disambiguation: set morphologies of token at <nPos> with <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:
    "Text parser"

    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.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):
        "generator: return nodes where <dToken> “values” match <dNode> arcs"
        # token value
        if dToken["sValue"] in dNode:
684
685
686
687
688
689
690

691
692
693
694
695
696
697
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717







+







                elif dNode["sType"] in sMeta:
                    if bDebug:
                        print("  MATCH: *" + sMeta)
                    yield dGraph[dNode["<meta>"][sMeta]]


    def parse (self, dGraph, dPriority, sCountry="${country_default}", dOptions=None, bShowRuleId=False, bDebug=False, bContext=False):
        "parse tokens from the text and execute actions encountered"
        self.dError = {}
        dPriority = {}  # Key = position; value = priority
        dOpt = _dOptions  if not dOptions  else dOptions
        lPointer = []
        bTagAndRewrite = False
        for dToken in self.lToken:
            if bDebug:
815
816
817
818
819
820
821
822
823
824
825




826
827
828
829
830
831
832
835
836
837
838
839
840
841




842
843
844
845
846
847
848
849
850
851
852







-
-
-
-
+
+
+
+







        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,)
            xProperty = PropertyValue()
            xProperty.Name = "FullCommentURL"
            xProperty.Value = sURL
            xErr.aProperties = (xProperty,)
        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 = {}
931
932
933
934
935
936
937
938

939
940
941
942
943
944
945
951
952
953
954
955
956
957

958
959
960
961
962
963
964
965







-
+







                if bDebug:
                    print("Merged token:", dTokenMerger["sValue"])
                bKeepToken = False
            if "nMergeUntil" in dToken:
                if dToken["i"] > nMergeUntil: # this token is not already merged with a previous token
                    dTokenMerger = dToken
                if dToken["nMergeUntil"] > nMergeUntil:
                    nMergeUntil = dToken["nMergeUntil"]  
                    nMergeUntil = dToken["nMergeUntil"]
                del dToken["nMergeUntil"]
            elif "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"])
                bKeepToken = False

Deleted gc_core/py/lang_core/gc_sentence.py version [c68dc1622f].

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













































































































































































































































-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
# Sentence checker

from ..graphspell.tokenizer import Tokenizer
from .gc_rules_graph import dGraph


oTokenizer = Tokenizer("${lang}")


class TokenSentence:

    def __init__ (self, sSentence, sSentence0, nOffset):
        self.sSentence = sSentence
        self.sSentence0 = sSentence0
        self.nOffset = nOffset
        self.lToken = list(oTokenizer.genTokens())

    def parse (self):
        dErr = {}
        lPointer = []
        for dToken in self.lToken:
            for i, dPointer in enumerate(lPointer):
                bValid = False
                for dNode in self._getNextMatchingNodes(dToken, dPointer["dNode"]):
                    dPointer["nOffset"] = dToken["i"]
                    dPointer["dNode"] = dNode
                    bValid = True
                if not bValid:
                    del lPointer[i]
            for dNode in self._getNextMatchingNodes(dToken, dGraph):
                lPointer.append({"nOffset": 0, "dNode": dNode})
            for dPointer in lPointer:
                if "<rules>" in dPointer["dNode"]:
                    for dNode in dGraph[dPointer["dNode"]["<rules>"]]:
                        dErr = self._executeActions(dNode, nOffset)
        return dErr

    def _getNextMatchingNodes (self, dToken, dNode):
        # token value
        if dToken["sValue"] in dNode:
            yield dGraph[dNode[dToken["sValue"]]]
        # token lemmas
        for sLemma in dToken["lLemma"]:
            if sLemma in dNode:
                yield dGraph[dNode[sLemma]]
        # universal arc
        if "*" in dNode:
            yield dGraph[dNode["*"]]
        # regex arcs
        if "~" in dNode:
            for sRegex in dNode["~"]:
                for sMorph in dToken["lMorph"]:
                    if re.search(sRegex, sMorph):
                        yield dGraph[dNode["~"][sRegex]]

    def _executeActions (self, dNode, nOffset):
        for sLineId, nextNodeKey in dNode.items():
            for sArc in dGraph[nextNodeKey]:
                bCondMemo = None
                sFuncCond, cActionType, sWhat, *eAct = dRule[sArc]
                # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroupStart, iGroupEnd[, message, URL]] ]
                try:
                    bCondMemo = not sFuncCond or globals()[sFuncCond](self, sCountry, bCondMemo)
                    if bCondMemo:
                        if cActionType == "-":
                            # grammar error
                            nErrorStart = nSentenceOffset + m.start(eAct[0])
                            nErrorEnd = nSentenceOffset + m.start(eAct[1])
                            if nErrorStart not in dErrs or nPriority > dPriority[nErrorStart]:
                                dErrs[nErrorStart] = _createError(self, sWhat, nErrorStart, nErrorEnd, sLineId, bUppercase, eAct[2], eAct[3], bIdRule, sOption, bContext)
                                dPriority[nErrorStart] = nPriority
                        elif cActionType == "~":
                            # text processor
                            self._rewrite(sWhat, nErrorStart, nErrorEnd)
                        elif cActionType == "@":
                            # jump
                            self._jump(sWhat)
                        elif cActionType == "=":
                            # disambiguation
                            globals()[sWhat](self.lToken)
                        elif cActionType == ">":
                            # we do nothing, this test is just a condition to apply all following actions
                            pass
                        else:
                            print("# error: unknown action at " + sLineId)
                    elif cActionType == ">":
                        break
                except Exception as e:
                    raise Exception(str(e), "# " + sLineId + " # " + sRuleId)

    def _createWriterError (self):
        d = {}
        return d

    def _createDictError (self):
        d = {}
        return d

    def _rewrite (self, sWhat, nErrorStart, nErrorEnd):
        "text processor: rewrite tokens between <nErrorStart> and <nErrorEnd> position"
        lTokenValue = sWhat.split("|")
        if len(lTokenValue) != (nErrorEnd - nErrorStart + 1):
            print("Error. Text processor: number of replacements != number of tokens.")
            return
        for i, sValue in zip(range(nErrorStart, nErrorEnd+1), lTokenValue):
            self.lToken[i]["sValue"] = sValue

    def _jump (self, sWhat):
        try:
            nFrom, nTo = sWhat.split(">")
            self.lToken[int(nFrom)]["iJump"] = int(nTo)
        except:
            print("# Error. Jump failed: ", sWhat)
            traceback.print_exc()
            return


#### Analyse tokens

def g_morph (dToken, sPattern, bStrict=True):
    "analyse a token, return True if <sPattern> in morphologies"
    if "lMorph" in dToken:
        lMorph = dToken["lMorph"]
    else:
        if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
            return False
        if not _dAnalyses[dToken["sValue"]]:
            return False
        lMorph = _dAnalyses[dToken["sValue"]]
    zPattern = re.compile(sPattern)
    if bStrict:
        return all(zPattern.search(sMorph)  for sMorph in lMorph)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)

def g_morphex (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:
        if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
            return False
        if not _dAnalyses[dToken["sValue"]]:
            return False
        lMorph = _dAnalyses[dToken["sValue"]]
    # check negative condition
    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, bStrict=True):
    "analyse a token, return True if <sPattern> in morphologies (disambiguation off)"
    if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
        return False
    if not _dAnalyses[dToken["sValue"]]:
        return False
    zPattern = re.compile(sPattern)
    if bStrict:
        return all(zPattern.search(sMorph)  for sMorph in _dAnalyses[dToken["sValue"]])
    return any(zPattern.search(sMorph)  for sMorph in _dAnalyses[dToken["sValue"]])


def g_analysex (dToken, sPattern, sNegPattern):
    "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
    if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
        return False
    if not _dAnalyses[dToken["sValue"]]:
        return False
    # check negative condition
    zNegPattern = re.compile(sNegPattern)
    if any(zNegPattern.search(sMorph)  for sMorph in _dAnalyses[dToken["sValue"]]):
        return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in _dAnalyses[dToken["sValue"]])


#### Go outside the rule scope

def g_nextToken (i):
    pass

def g_prevToken (i):
    pass

def g_look ():
    pass

def g_lookAndCheck ():
    pass


#### Disambiguator

def g_select (dToken, sPattern, lDefault=None):
    "select morphologies for <dToken> according to <sPattern>, always return True"
    if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
        return True
    if len(_dAnalyses[dToken["sValue"]]) == 1:
        return True
    lMorph = dToken["lMorph"] or _dAnalyses[dToken["sValue"]]
    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
    return True


def g_exclude (dToken, sPattern, lDefault=None):
    "select morphologies for <dToken> according to <sPattern>, always return True"
    if dToken["sValue"] not in _dAnalyses and not _storeMorphFromFSA(dToken["sValue"]):
        return True
    if len(_dAnalyses[dToken["sValue"]]) == 1:
        return True
    lMorph = dToken["lMorph"] or _dAnalyses[dToken["sValue"]]
    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
    return True


def g_define (dToken, lMorph):
    "set morphologies of <dToken>, always return True"
    dToken["lMorph"] = lMorph
    return True


#### CALLABLES (generated code)

${graph_callables}

Modified gc_lang/fr/modules/conj.py from [96ddf4a9dc] to [2a91e3ad80].


1



2
3
4
5
6
7
8
1

2
3
4
5
6
7
8
9
10
11
+
-
+
+
+







"""
# Grammalecte - Conjugueur
Grammalecte - Conjugueur
"""

# License: GPL 3

import re
import traceback

from .conj_data import lVtyp as _lVtyp
from .conj_data import lTags as _lTags
25
26
27
28
29
30
31

32
33
34
35
36
37
38
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42







+







_dGroup = { "0": "auxiliaire", "1": "1ᵉʳ groupe", "2": "2ᵉ groupe", "3": "3ᵉ groupe" }

_dTenseIdx = { ":PQ": 0, ":Ip": 1, ":Iq": 2, ":Is": 3, ":If": 4, ":K": 5, ":Sp": 6, ":Sq": 7, ":E": 8 }



def isVerb (sVerb):
    "return True if it’s a existing verb"
    return sVerb in _dVerb


def getConj (sVerb, sTense, sWho):
    "returns conjugation (can be an empty string)"
    if sVerb not in _dVerb:
        return None
52
53
54
55
56
57
58

59
60
61
62
63
64
65
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70







+







    "returns raw informations about sVerb"
    if sVerb not in _dVerb:
        return None
    return _lVtyp[_dVerb[sVerb][0]]


def getSimil (sWord, sMorph, bSubst=False):
    "returns a set of verbal forms similar to <sWord>, according to <sMorph>"
    if ":V" not in sMorph:
        return set()
    sInfi = sMorph[1:sMorph.find("/")]
    aSugg = set()
    tTags = _getTags(sInfi)
    if tTags:
        if not bSubst:
96
97
98
99
100
101
102

103
104
105
106
107
108
109
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115







+







            # if there is only one past participle (epi inv), unreliable.
            if len(aSugg) == 1:
                aSugg.clear()
    return aSugg


def getConjSimilInfiV1 (sInfi):
    "returns verbal forms phonetically similar to infinitive form (for verb in group 1)"
    if sInfi not in _dVerb:
        return set()
    aSugg = set()
    tTags = _getTags(sInfi)
    if tTags:
        aSugg.add(_getConjWithTags(sInfi, tTags, ":Iq", ":2s"))
        aSugg.add(_getConjWithTags(sInfi, tTags, ":Iq", ":3s"))
138
139
140
141
142
143
144
145

146
147

148
149
150


151
152
153
154
155
156
157
144
145
146
147
148
149
150

151
152

153
154
155
156
157
158
159
160
161
162
163
164
165







-
+

-
+



+
+







    "returns sWord modified by sSfx"
    if not sSfx:
        return ""
    if sSfx == "0":
        return sWord
    try:
        return sWord[:-(ord(sSfx[0])-48)] + sSfx[1:]  if sSfx[0] != '0'  else  sWord + sSfx[1:]  # 48 is the ASCII code for "0"
    except:
    except (IndexError, TypeError):
        return "## erreur, code : " + str(sSfx) + " ##"
        



class Verb ():
    "Verb and its conjugation"

    def __init__ (self, sVerb, sVerbPattern=""):
        # conjugate a unknown verb with rules from sVerbPattern
        if not isinstance(sVerb, str):
            raise TypeError("sVerb should be a string")
        if not sVerb:
            raise ValueError("Empty string.")

Modified gc_lang/fr/modules/conj_generator.py from [2e696a65e3] to [ee0a228497].


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
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
+
-
-
+
+
+





+









-
+
+













+







"""
# Conjugation generator
# beta stage, unfinished, the root for a new way to generate flexions…
Conjugation generator
beta stage, unfinished, the root for a new way to generate flexions…
"""

import re


def conjugate (sVerb, sVerbTag="i_____a", bVarPpas=True):
    "conjugate <sVerb> and returns a list of tuples (conjugation form, tags)"
    lConj = []
    cGroup = getVerbGroupChar(sVerb)
    for nCut, sAdd, sFlexTags, sPattern in getConjRules(sVerb, bVarPpas):
        if not sPattern or re.search(sPattern, sVerb):
            sFlexion = sVerb[0:-nCut] + sAdd  if nCut  else sVerb + sAdd
            lConj.append((sFlexion, ":V" + cGroup + "_" + sVerbTag + sFlexTags))
    return lConj


def getVerbGroupChar (sVerb, ):
def getVerbGroupChar (sVerb):
    "returns the group number of <sVerb> guessing on its ending"
    sVerb = sVerb.lower()
    if sVerb.endswith("er"):
        return "1"
    if sVerb.endswith("ir"):
        return "2"
    if sVerb == "être" or sVerb == "avoir":
        return "0"
    if sVerb.endswith("re"):
        return "3"
    return "4"


def getConjRules (sVerb, bVarPpas=True, nGroup=2):
    "returns a list of lists to conjugate a verb, guessing on its ending"
    if sVerb.endswith("er"):
        # premier groupe, conjugaison en fonction de la terminaison du lemme
        # 5 lettres
        if sVerb[-5:] in oConj["V1"]:
            lConj = list(oConj["V1"][sVerb[-5:]])
        # 4 lettres
        elif sVerb[-4:] in oConj["V1"]:
113
114
115
116
117
118
119
120

121
122
123
124
125
126
127
118
119
120
121
122
123
124

125
126
127
128
129
130
131
132







-
+







        [2,     "isses",        ":Sp:Sq:2s/*",      False],
        [2,     "isse",         ":Sp:3s/*",         False],
        [2,     "ît",           ":Sq:3s/*",         False],
        [2,     "is",           ":E:2s/*",          False],
        [2,     "issons",       ":E:1p/*",          False],
        [2,     "issez",        ":E:2p/*",          False]
    ],
    

    # premier groupe (bien plus irrégulier que prétendu)
    "V1": {
        # a
        # verbes en -er, -ger, -yer, -cer
        "er": [
            [2,      "er",        ":Y/*",               False],
            [2,      "ant",       ":P/*",               False],

Modified gc_lang/fr/modules/cregex.py from [a0df0d1397] to [f9eb3691d3].


1


2
3
4
5
6

7
8
9
10
11
12
13
1

2
3
4
5
6
7

8
9
10
11
12
13
14
15
+
-
+
+




-
+







"""
# Grammalecte - Compiled regular expressions
Grammalecte - Compiled regular expressions
"""

import re

#### Lemme
Lemma = re.compile("^>(\w[\w-]*)")
Lemma = re.compile(r"^>(\w[\w-]*)")

#### Analyses
Gender = re.compile(":[mfe]")
Number = re.compile(":[spi]")

#### Nom et adjectif
NA = re.compile(":[NA]")
76
77
78
79
80
81
82

83
84
85

86
87
88
89
90
91
92
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96







+



+







NPf = re.compile(":(?:M[12P]|T):f")
NPe = re.compile(":(?:M[12P]|T):e")


#### FONCTIONS

def getLemmaOfMorph (s):
    "return lemma in morphology <s>"
    return Lemma.search(s).group(1)

def checkAgreement (l1, l2):
    "returns True if agreement in gender and number is possible between morphologies <l1> and <l2>"
    # check number agreement
    if not mbInv(l1) and not mbInv(l2):
        if mbSg(l1) and not mbSg(l2):
            return False
        if mbPl(l1) and not mbPl(l2):
            return False
    # check gender agreement
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
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







-
+













+



+



+



+



+



+



+



+



+



+



+






+



+



+



+



+









+



+



+



+



+



+



+



+



+



+



+



+



                return ":e"
    return sGender

def getNumber (lMorph):
    "returns number of word (':s', ':p', ':i' or empty string)."
    sNumber = ""
    for sMorph in lMorph:
        m = Number.search(sWord)
        m = Number.search(sMorph)
        if m:
            if not sNumber:
                sNumber = m.group(0)
            elif sNumber != m.group(0):
                return ":i"
    return sNumber

# NOTE :  isWhat (lMorph)    returns True   if lMorph contains nothing else than What
#         mbWhat (lMorph)    returns True   if lMorph contains What at least once

## isXXX = it’s certain

def isNom (lMorph):
    "returns True if all morphologies are “nom”"
    return all(":N" in s  for s in lMorph)

def isNomNotAdj (lMorph):
    "returns True if all morphologies are “nom”, but not “adjectif”"
    return all(NnotA.search(s)  for s in lMorph)

def isAdj (lMorph):
    "returns True if all morphologies are “adjectif”"
    return all(":A" in s  for s in lMorph)

def isNomAdj (lMorph):
    "returns True if all morphologies are “nom” or “adjectif”"
    return all(NA.search(s)  for s in lMorph)

def isNomVconj (lMorph):
    "returns True if all morphologies are “nom” or “verbe conjugué”"
    return all(NVconj.search(s)  for s in lMorph)

def isInv (lMorph):
    "returns True if all morphologies are “invariable”"
    return all(":i" in s  for s in lMorph)

def isSg (lMorph):
    "returns True if all morphologies are “singulier”"
    return all(":s" in s  for s in lMorph)

def isPl (lMorph):
    "returns True if all morphologies are “pluriel”"
    return all(":p" in s  for s in lMorph)

def isEpi (lMorph):
    "returns True if all morphologies are “épicène”"
    return all(":e" in s  for s in lMorph)

def isMas (lMorph):
    "returns True if all morphologies are “masculin”"
    return all(":m" in s  for s in lMorph)

def isFem (lMorph):
    "returns True if all morphologies are “féminin”"
    return all(":f" in s  for s in lMorph)


## mbXXX = MAYBE XXX

def mbNom (lMorph):
    "returns True if one morphology is “nom”"
    return any(":N" in s  for s in lMorph)

def mbAdj (lMorph):
    "returns True if one morphology is “adjectif”"
    return any(":A" in s  for s in lMorph)

def mbAdjNb (lMorph):
    "returns True if one morphology is “adjectif” or “nombre”"
    return any(AD.search(s)  for s in lMorph)

def mbNomAdj (lMorph):
    "returns True if one morphology is “nom” or “adjectif”"
    return any(NA.search(s)  for s in lMorph)

def mbNomNotAdj (lMorph):
    "returns True if one morphology is “nom”, but not “adjectif”"
    b = False
    for s in lMorph:
        if ":A" in s:
            return False
        if ":N" in s:
            b = True
    return b

def mbPpasNomNotAdj (lMorph):
    "returns True if one morphology is “nom” or “participe passé”, but not “adjectif”"
    return any(PNnotA.search(s)  for s in lMorph)

def mbVconj (lMorph):
    "returns True if one morphology is “nom” or “verbe conjugué”"
    return any(Vconj.search(s)  for s in lMorph)

def mbVconj123 (lMorph):
    "returns True if one morphology is “nom” or “verbe conjugué” (but not “avoir” or “être”)"
    return any(Vconj123.search(s)  for s in lMorph)

def mbMG (lMorph):
    "returns True if one morphology is “mot grammatical”"
    return any(":G" in s  for s in lMorph)

def mbInv (lMorph):
    "returns True if one morphology is “invariable”"
    return any(":i" in s  for s in lMorph)

def mbSg (lMorph):
    "returns True if one morphology is “singulier”"
    return any(":s" in s  for s in lMorph)

def mbPl (lMorph):
    "returns True if one morphology is “pluriel”"
    return any(":p" in s  for s in lMorph)

def mbEpi (lMorph):
    "returns True if one morphology is “épicène”"
    return any(":e" in s  for s in lMorph)

def mbMas (lMorph):
    "returns True if one morphology is “masculin”"
    return any(":m" in s  for s in lMorph)

def mbFem (lMorph):
    "returns True if one morphology is “féminin”"
    return any(":f" in s  for s in lMorph)

def mbNpr (lMorph):
    "returns True if one morphology is “nom propre” or “titre de civilité”"
    return any(NP.search(s)  for s in lMorph)

def mbNprMasNotFem (lMorph):
    "returns True if one morphology is “nom propre masculin” but not “féminin”"
    if any(NPf.search(s)  for s in lMorph):
        return False
    return any(NPm.search(s)  for s in lMorph)

Modified gc_lang/fr/modules/gce_analyseur.py from [50ac148025] to [57b5310cdc].

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
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 ENGINE PLUGIN: Parsing functions for French language

from . import cregex as cr


def rewriteSubject (s1, s2):
    # s1 is supposed to be prn/patr/npr (M[12P])
    "rewrite complex subject: <s1> a prn/patr/npr (M[12P]) followed by “et” and <s2>"
    if s2 == "lui":
        return "ils"
    if s2 == "moi":
        return "nous"
    if s2 == "toi":
        return "vous"
    if s2 == "nous":
        return "nous"
    if s2 == "vous":
        return "vous"
    if s2 == "eux":
        return "ils"
    if s2 == "elle" or s2 == "elles":    
    if s2 == "elle" or s2 == "elles":
        if cr.mbNprMasNotFem(_oSpellChecker.getMorph(s1)):
            return "ils"
        # si épicène, indéterminable, mais OSEF, le féminin l’emporte
        return "elles"
    return s1 + " et " + s2


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
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







-
+















-
+







        return False
    if cr.mbVconj(lMorph) and not cr.mbMG(lMorph):
        return True
    return False


def isAmbiguousAndWrong (sWord1, sWord2, sReqMorphNA, sReqMorphConj):
    "use it if sWord1 won’t be a verb; word2 is assumed to be True via isAmbiguousNAV"
    "use it if <sWord1> won’t be a verb; <sWord2> is assumed to be True via isAmbiguousNAV"
    a2 = _oSpellChecker.getMorph(sWord2)
    if not a2:
        return False
    if cr.checkConjVerb(a2, sReqMorphConj):
        # verb word2 is ok
        return False
    a1 = _oSpellChecker.getMorph(sWord1)
    if not a1:
        return False
    if cr.checkAgreement(a1, a2) and (cr.mbAdj(a2) or cr.mbAdj(a1)):
        return False
    return True


def isVeryAmbiguousAndWrong (sWord1, sWord2, sReqMorphNA, sReqMorphConj, bLastHopeCond):
    "use it if sWord1 can be also a verb; word2 is assumed to be True via isAmbiguousNAV"
    "use it if <sWord1> can be also a verb; <sWord2> is assumed to be True via isAmbiguousNAV"
    a2 = _oSpellChecker.getMorph(sWord2)
    if not a2:
        return False
    if cr.checkConjVerb(a2, sReqMorphConj):
        # verb word2 is ok
        return False
    a1 = _oSpellChecker.getMorph(sWord1)
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

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







+













+














+
















+












+













-
+
    #if cr.isNomAdjVerb(a1): # considered True
    if bLastHopeCond:
        return True
    return False


def checkAgreement (sWord1, sWord2):
    "check agreement between <sWord1> and <sWord1>"
    a2 = _oSpellChecker.getMorph(sWord2)
    if not a2:
        return True
    a1 = _oSpellChecker.getMorph(sWord1)
    if not a1:
        return True
    return cr.checkAgreement(a1, a2)


_zUnitSpecial = re.compile("[µ/⁰¹²³⁴⁵⁶⁷⁸⁹Ωℓ·]")
_zUnitNumbers = re.compile("[0-9]")

def mbUnit (s):
    "returns True it can be a measurement unit"
    if _zUnitSpecial.search(s):
        return True
    if 1 < len(s) < 16 and s[0:1].islower() and (not s[1:].islower() or _zUnitNumbers.search(s)):
        return True
    return False


#### Syntagmes

_zEndOfNG1 = re.compile(" *$| +(?:, +|)(?:n(?:’|e |o(?:u?s|tre) )|l(?:’|e(?:urs?|s|) |a )|j(?:’|e )|m(?:’|es? |a |on )|t(?:’|es? |a |u )|s(?:’|es? |a )|c(?:’|e(?:t|tte|s|) )|ç(?:a |’)|ils? |vo(?:u?s|tre) )")
_zEndOfNG2 = re.compile(r" +(\w[\w-]+)")
_zEndOfNG3 = re.compile(r" *, +(\w[\w-]+)")

def isEndOfNG (dDA, s, iOffset):
    "returns True if next word doesn’t belong to a noun group"
    if _zEndOfNG1.match(s):
        return True
    m = _zEndOfNG2.match(s)
    if m and morphex(dDA, (iOffset+m.start(1), m.group(1)), ":[VR]", ":[NAQP]"):
        return True
    m = _zEndOfNG3.match(s)
    if m and not morph(dDA, (iOffset+m.start(1), m.group(1)), ":[NA]", False):
        return True
    return False


_zNextIsNotCOD1 = re.compile(" *,")
_zNextIsNotCOD2 = re.compile(" +(?:[mtsnj](e +|’)|[nv]ous |tu |ils? |elles? )")
_zNextIsNotCOD3 = re.compile(r" +([a-zéèî][\w-]+)")

def isNextNotCOD (dDA, s, iOffset):
    "returns True if next word is not a COD"
    if _zNextIsNotCOD1.match(s) or _zNextIsNotCOD2.match(s):
        return True
    m = _zNextIsNotCOD3.match(s)
    if m and morphex(dDA, (iOffset+m.start(1), m.group(1)), ":[123][sp]", ":[DM]"):
        return True
    return False


_zNextIsVerb1 = re.compile(" +[nmts](?:e |’)")
_zNextIsVerb2 = re.compile(r" +(\w[\w-]+)")

def isNextVerb (dDA, s, iOffset):
    "returns True if next word is a verb"
    if _zNextIsVerb1.match(s):
        return True
    m = _zNextIsVerb2.match(s)
    if m and morph(dDA, (iOffset+m.start(1), m.group(1)), ":[123][sp]", False):
        return True
    return False


#### Exceptions

aREGULARPLURAL = frozenset(["abricot", "amarante", "aubergine", "acajou", "anthracite", "brique", "caca", "café", \
                            "carotte", "cerise", "chataigne", "corail", "citron", "crème", "grave", "groseille", \
                            "jonquille", "marron", "olive", "pervenche", "prune", "sable"])
aSHOULDBEVERB = frozenset(["aller", "manger"]) 
aSHOULDBEVERB = frozenset(["aller", "manger"])

Modified gc_lang/fr/modules/gce_suggestions.py from [a5e2b1d398] to [2926468975].

1
2
3
4
5
6
7
8
9
10

11
12
13
14
15
16
17
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18










+







#### GRAMMAR CHECKING ENGINE PLUGIN: Suggestion mechanisms

from . import conj
from . import mfsp
from . import phonet


## Verbs

def suggVerb (sFlex, sWho, funcSugg2=None):
    "change <sFlex> conjugation according to <sWho>"
    aSugg = set()
    for sStem in _oSpellChecker.getLemma(sFlex):
        tTags = conj._getTags(sStem)
        if tTags:
            # we get the tense
            aTense = set()
            for sMorph in _oSpellChecker.getMorph(sFlex):
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
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







-
+
+




-
+





-
+

-
+




-
+




-
+




-
+



-
+











+










+
















+









+







        if aSugg2:
            aSugg.add(aSugg2)
    if aSugg:
        return "|".join(aSugg)
    return ""


def suggVerbPpas (sFlex, sWhat=None):
def suggVerbPpas (sFlex, sPattern=None):
    "suggest past participles for <sFlex>"
    aSugg = set()
    for sStem in _oSpellChecker.getLemma(sFlex):
        tTags = conj._getTags(sStem)
        if tTags:
            if not sWhat:
            if not sPattern:
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q2"))
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q3"))
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q4"))
                aSugg.discard("")
            elif sWhat == ":m:s":
            elif sPattern == ":m:s":
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
            elif sWhat == ":m:p":
            elif sPattern == ":m:p":
                if conj._hasConjWithTags(tTags, ":PQ", ":Q2"):
                    aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q2"))
                else:
                    aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
            elif sWhat == ":f:s":
            elif sPattern == ":f:s":
                if conj._hasConjWithTags(tTags, ":PQ", ":Q3"):
                    aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q3"))
                else:
                    aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
            elif sWhat == ":f:p":
            elif sPattern == ":f:p":
                if conj._hasConjWithTags(tTags, ":PQ", ":Q4"):
                    aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q4"))
                else:
                    aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
            elif sWhat == ":s":
            elif sPattern == ":s":
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q3"))
                aSugg.discard("")
            elif sWhat == ":p":
            elif sPattern == ":p":
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q2"))
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q4"))
                aSugg.discard("")
            else:
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":PQ", ":Q1"))
    if aSugg:
        return "|".join(aSugg)
    return ""


def suggVerbTense (sFlex, sTense, sWho):
    "change <sFlex> to a verb according to <sTense> and <sWho>"
    aSugg = set()
    for sStem in _oSpellChecker.getLemma(sFlex):
        if conj.hasConj(sStem, sTense, sWho):
            aSugg.add(conj.getConj(sStem, sTense, sWho))
    if aSugg:
        return "|".join(aSugg)
    return ""


def suggVerbImpe (sFlex):
    "change <sFlex> to a verb at imperative form"
    aSugg = set()
    for sStem in _oSpellChecker.getLemma(sFlex):
        tTags = conj._getTags(sStem)
        if tTags:
            if conj._hasConjWithTags(tTags, ":E", ":2s"):
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":E", ":2s"))
            if conj._hasConjWithTags(tTags, ":E", ":1p"):
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":E", ":1p"))
            if conj._hasConjWithTags(tTags, ":E", ":2p"):
                aSugg.add(conj._getConjWithTags(sStem, tTags, ":E", ":2p"))
    if aSugg:
        return "|".join(aSugg)
    return ""


def suggVerbInfi (sFlex):
    "returns infinitive forms of <sFlex>"
    return "|".join([ sStem  for sStem in _oSpellChecker.getLemma(sFlex)  if conj.isVerb(sStem) ])


_dQuiEst = { "je": ":1s", "j’": ":1s", "j’en": ":1s", "j’y": ":1s", \
             "tu": ":2s", "il": ":3s", "on": ":3s", "elle": ":3s", "nous": ":1p", "vous": ":2p", "ils": ":3p", "elles": ":3p" }
_lIndicatif = [":Ip", ":Iq", ":Is", ":If"]
_lSubjonctif = [":Sp", ":Sq"]

def suggVerbMode (sFlex, cMode, sSuj):
    "returns other conjugations of <sFlex> acconding to <cMode> and <sSuj>"
    if cMode == ":I":
        lMode = _lIndicatif
    elif cMode == ":S":
        lMode = _lSubjonctif
    elif cMode.startswith((":I", ":S")):
        lMode = [cMode]
    else:
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
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







+









+










+







            aSugg.add(e)
    if aSugg:
        return "|".join(aSugg)
    return ""


def hasFemForm (sFlex):
    "return True if there is a feminine form of <sFlex>"
    for sStem in _oSpellChecker.getLemma(sFlex):
        if mfsp.isFemForm(sStem) or conj.hasConj(sStem, ":PQ", ":Q3"):
            return True
    if phonet.hasSimil(sFlex, ":f"):
        return True
    return False


def hasMasForm (sFlex):
    "return True if there is a masculine form of <sFlex>"
    for sStem in _oSpellChecker.getLemma(sFlex):
        if mfsp.isFemForm(sStem) or conj.hasConj(sStem, ":PQ", ":Q1"):
            # what has a feminine form also has a masculine form
            return True
    if phonet.hasSimil(sFlex, ":m"):
        return True
    return False


def switchGender (sFlex, bPlur=None):
    "return feminine or masculine form(s) of <sFlex>"
    aSugg = set()
    if bPlur == None:
        for sMorph in _oSpellChecker.getMorph(sFlex):
            if ":f" in sMorph:
                if ":s" in sMorph:
                    aSugg.add(suggMasSing(sFlex))
                elif ":p" in sMorph:
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
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







+












+















+








+








+







                aSugg.add(suggFemSing(sFlex))
    if aSugg:
        return "|".join(aSugg)
    return ""


def switchPlural (sFlex):
    "return plural or singular form(s) of <sFlex>"
    aSugg = set()
    for sMorph in _oSpellChecker.getMorph(sFlex):
        if ":s" in sMorph:
            aSugg.add(suggPlur(sFlex))
        elif ":p" in sMorph:
            aSugg.add(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)


def suggSimil (sWord, sPattern=None, bSubst=False):
    "return list of words phonetically similar to sWord and whom POS is matching sPattern"
    aSugg = phonet.selectSimil(sWord, sPattern)
    for sMorph in _oSpellChecker.getMorph(sWord):
        aSugg.update(conj.getSimil(sWord, sMorph, bSubst))
        break
    if aSugg:
        return "|".join(aSugg)
    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"
    if sWord[0:1] == "h" or sWord[0:1] == "H":
        return "ce|cet"
    return "ce"


def suggLesLa (sWord):
    "suggest “les” or “la” according to <sWord>"
    if any( ":p" in sMorph  for sMorph in _oSpellChecker.getMorph(sWord) ):
        return "les|la"
    return "la"


_zBinary = re.compile("^[01]+$")

def formatNumber (s):
    "add spaces or hyphens to big numbers"
    nLen = len(s)
    if nLen < 4:
        return s
    sRes = ""
    # nombre ordinaire
    nEnd = nLen
    while nEnd > 0:
426
427
428
429
430
431
432

433
434
435
436
437
438
439
440
441
442
443

444
445
446
447
448
449
450
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466







+











+







    elif nLen == 9 and s.startswith("0"):
        sRes += "|" + s[0:3] + " " + s[3:5] + " " + s[5:7] + " " + s[7:9]                   # fixe belge 1
        sRes += "|" + s[0:2] + " " + s[2:5] + " " + s[5:7] + " " + s[7:9]                   # fixe belge 2
    return sRes


def formatNF (s):
    "typography: format NF reference (norme française)"
    try:
        m = re.match("NF[  -]?(C|E|P|Q|S|X|Z|EN(?:[  -]ISO|))[  -]?([0-9]+(?:[/‑-][0-9]+|))", s)
        if not m:
            return ""
        return "NF " + m.group(1).upper().replace(" ", " ").replace("-", " ") + " " + m.group(2).replace("/", "‑").replace("-", "‑")
    except:
        traceback.print_exc()
        return "# erreur #"


def undoLigature (c):
    "typography: split ligature character <c> in several chars"
    if c == "fi":
        return "fi"
    elif c == "fl":
        return "fl"
    elif c == "ff":
        return "ff"
    elif c == "ffi":
461
462
463
464
465
466
467
468

469
470
471

472
477
478
479
480
481
482
483

484
485
486
487
488
489







-
+



+



_xNormalizedCharsForInclusiveWriting = str.maketrans({
    '(': '_',  ')': '_',
    '.': '_',  '·': '_',
    '–': '_',  '—': '_',
    '/': '_'
 })
})


def normalizeInclusiveWriting (sToken):
    "typography: replace word separators used in inclusive writing by underscore (_)"
    return sToken.translate(_xNormalizedCharsForInclusiveWriting)

Modified gc_lang/fr/modules/lexicographe.py from [5e53113f51] to [a9b878f391].


1



2
3
4
5
6
7
8
9

10
11
12
13
14
15
16
1

2
3
4
5
6
7
8
9
10
11

12
13
14
15
16
17
18
19
+
-
+
+
+







-
+







"""
# Grammalecte - Lexicographe
Grammalecte - Lexicographe
"""

# License: MPL 2


import re
import traceback


_dTAGS = {  
_dTAGS = {
    ':N': (" nom,", "Nom"),
    ':A': (" adjectif,", "Adjectif"),
    ':M1': (" prénom,", "Prénom"),
    ':M2': (" patronyme,", "Patronyme, matronyme, nom de famille…"),
    ':MP': (" nom propre,", "Nom propre"),
    ':W': (" adverbe,", "Adverbe"),
    ':J': (" interjection,", "Interjection"),
76
77
78
79
80
81
82
83

84
85
86
87
88
89
90
79
80
81
82
83
84
85

86
87
88
89
90
91
92
93







-
+







    ':O2': (" 2ᵉ pers.,", "Pronom : 2ᵉ personne"),
    ':O3': (" 3ᵉ pers.,", "Pronom : 3ᵉ personne"),
    ':C': (" conjonction,", "Conjonction"),
    ':Ĉ': (" conjonction (él.),", "Conjonction (élément)"),
    ':Cc': (" conjonction de coordination,", "Conjonction de coordination"),
    ':Cs': (" conjonction de subordination,", "Conjonction de subordination"),
    ':Ĉs': (" conjonction de subordination (él.),", "Conjonction de subordination (élément)"),
    

    ':Ñ': (" locution nominale (él.),", "Locution nominale (élément)"),
    ':Â': (" locution adjectivale (él.),", "Locution adjectivale (élément)"),
    ':Ṽ': (" locution verbale (él.),", "Locution verbale (élément)"),
    ':Ŵ': (" locution adverbiale (él.),", "Locution adverbiale (élément)"),
    ':Ŕ': (" locution prépositive (él.),", "Locution prépositive (élément)"),
    ':Ĵ': (" locution interjective (él.),", "Locution interjective (élément)"),

123
124
125
126
127
128
129
130

131
132
133

134
135
136
137

138
139
140
141
142
143
144
126
127
128
129
130
131
132

133
134
135

136
137
138
139

140
141
142
143
144
145
146
147







-
+


-
+



-
+







    'il': " pronom personnel sujet, 3ᵉ pers. masc. sing.",
    'on': " pronom personnel sujet, 3ᵉ pers. sing. ou plur.",
    'elle': " pronom personnel sujet, 3ᵉ pers. fém. sing.",
    'nous': " pronom personnel sujet/objet, 1ʳᵉ pers. plur.",
    'vous': " pronom personnel sujet/objet, 2ᵉ pers. plur.",
    'ils': " pronom personnel sujet, 3ᵉ pers. masc. plur.",
    'elles': " pronom personnel sujet, 3ᵉ pers. masc. plur.",
    

    "là": " particule démonstrative",
    "ci": " particule démonstrative",
    

    'le': " COD, masc. sing.",
    'la': " COD, fém. sing.",
    'les': " COD, plur.",
        

    'moi': " COI (à moi), sing.",
    'toi': " COI (à toi), sing.",
    'lui': " COI (à lui ou à elle), sing.",
    'nous2': " COI (à nous), plur.",
    'vous2': " COI (à vous), plur.",
    'leur': " COI (à eux ou à elles), plur.",

Modified gc_lang/fr/modules/mfsp.py from [3f4814b5d6] to [8b7759e076].


1


2
3
4
5
6
7
8
1

2
3
4
5
6
7
8
9
10
+
-
+
+







"""
# Masculins, féminins, singuliers et pluriels
Masculins, féminins, singuliers et pluriels
"""

from .mfsp_data import lTagMiscPlur as _lTagMiscPlur
from .mfsp_data import lTagMasForm as _lTagMasForm
from .mfsp_data import dMiscPlur as _dMiscPlur
from .mfsp_data import dMasForm as _dMasForm


Modified gc_lang/fr/modules/phonet.py from [cc107e0763] to [df9f884192].


1



2
3
4
5
6
7
8
1

2
3
4
5
6
7
8
9
10
11
+
-
+
+
+







"""
# Grammalecte - Suggestion phonétique
Grammalecte - Suggestion phonétique
"""

# License: GPL 3

import re

from .phonet_data import dWord as _dWord
from .phonet_data import lSet as _lSet
from .phonet_data import dMorph as _dMorph

Modified gc_lang/fr/modules/textformatter.py from [8fb9ec33bf] to [d3e695233d].

1




2
3
4
5
6
7
8
1
2
3
4
5
6
7
8
9
10
11
12

+
+
+
+







#!python3

"""
Text formatter
"""

import re


dReplTable = {
    # surnumerary_spaces
    "start_of_paragraph":          [("^[  ]+", "")],
63
64
65
66
67
68
69
70

71
72
73
74
75
76
77
67
68
69
70
71
72
73

74
75
76
77
78
79
80
81







-
+







    "erase_non_breaking_hyphens":  [("­", "")],
    ## typographic signs
    "ts_apostrophe":          [ ("(?i)\\b([ldnjmtscç])['´‘′`](?=\\w)", "\\1’"),
                                ("(?i)(qu|jusqu|lorsqu|puisqu|quoiqu|quelqu|presqu|entr|aujourd|prud)['´‘′`]", "\\1’") ],
    "ts_ellipsis":            [ ("\\.\\.\\.", "…"),
                                ("(?<=…)[.][.]", "…"),
                                ("…[.](?![.])", "…") ],
    "ts_n_dash_middle":       [ (" [-—] ", " – "), 
    "ts_n_dash_middle":       [ (" [-—] ", " – "),
                                (" [-—],", " –,") ],
    "ts_m_dash_middle":       [ (" [-–] ", " — "),
                                (" [-–],", " —,") ],
    "ts_n_dash_start":        [ ("^[-—][  ]", "– "),
                                ("^– ", "– "),
                                ("^[-–—](?=[\\w.…])", "– ") ],
    "ts_m_dash_start":        [ ("^[-–][  ]", "— "),