Grammalecte  Changes On Branch ba3c939f60235746

Changes In Branch gcerw Through [ba3c939f60] Excluding Merge-Ins

This is equivalent to a diff from 787d6a7582 to ba3c939f60

2020-04-06
13:15
merge trunk check-in: 1c5bdb25b6 user: olr tags: gcerw
2020-04-05
09:54
[fr] ajustements check-in: 52430380b1 user: olr tags: trunk, fr
08:39
[core][cli][graphsell][lo][py] move lexicographer from gc engine to graphspell check-in: ba3c939f60 user: olr tags: cli, core, lo, graphspell, gcerw
2020-04-04
15:54
[core][fr][py] gc_engine.py as primary module check-in: 759321730c user: olr tags: fr, core, gcerw
2020-04-03
23:38
[core][py] gc engine: code rewriting check-in: 16a21a38cd user: olr tags: core, gcerw
17:24
[fr] bug: mauvaise commande check-in: 787d6a7582 user: olr tags: trunk, fr
13:33
[fr] ajustements check-in: 502d7277a2 user: olr tags: trunk, fr

Modified gc_core/py/__init__.py from [49f46a05ff] to [3c70db889b].

1
2
3
4
5
"""
Grammar checker
"""

from .grammar_checker import *




|
1
2
3
4
5
"""
Grammar checker
"""

from .${lang}.gc_engine import *

Deleted gc_core/py/grammar_checker.py version [50b054f72f].

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
"""
Grammalecte, grammar checker
"""

import importlib
import json

from . import text


class GrammarChecker:
    "GrammarChecker: Wrapper for the grammar checker engine"

    def __init__ (self, sLangCode, sContext="Python"):
        self.sLangCode = sLangCode
        # Grammar checker engine
        self.gce = importlib.import_module("."+sLangCode, "grammalecte")
        self.gce.load(sContext)
        # Spell checker
        self.oSpellChecker = self.gce.getSpellChecker()
        # Lexicographer
        self.oLexicographer = None
        # Text formatter
        self.oTextFormatter = None

    def getGCEngine (self):
        "return the grammar checker object"
        return self.gce

    def getSpellChecker (self):
        "return the spell checker object"
        return self.oSpellChecker

    def getTextFormatter (self):
        "load and return the text formatter"
        if self.oTextFormatter is None:
            tf = importlib.import_module("."+self.sLangCode+".textformatter", "grammalecte")
            self.oTextFormatter = tf.TextFormatter()
        return self.oTextFormatter

    def getLexicographer (self):
        "load and return the lexicographer"
        if self.oLexicographer is None:
            lxg = importlib.import_module("."+self.sLangCode+".lexicographe", "grammalecte")
            self.oLexicographer = lxg.Lexicographe(self.oSpellChecker)
        return self.oLexicographer

    def displayGCOptions (self):
        "display the grammar checker options"
        self.gce.displayOptions()

    def getParagraphErrors (self, sText, dOptions=None, bContext=False, bSpellSugg=False, bDebug=False):
        "returns a tuple: (grammar errors, spelling errors)"
        aGrammErrs = self.gce.parse(sText, "FR", bDebug=bDebug, dOptions=dOptions, bContext=bContext)
        aSpellErrs = self.oSpellChecker.parseParagraph(sText, bSpellSugg)
        return aGrammErrs, aSpellErrs

    def getParagraphWithErrors (self, sText, dOptions=None, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100, bDebug=False):
        "parse text and return a readable text with underline errors"
        aGrammErrs, aSpellErrs = self.getParagraphErrors(sText, dOptions, False, bSpellSugg, bDebug)
        if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
            return ("", [])
        return text.generateParagraph(sText, aGrammErrs, aSpellErrs, nWidth)

    def getTextWithErrors (self, sText, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100, bDebug=False):
        "[todo]"

    def getParagraphErrorsAsJSON (self, iIndex, sText, dOptions=None, bContext=False, bEmptyIfNoErrors=False, bSpellSugg=False, bReturnText=False, lLineSet=None, bDebug=False):
        "parse text and return errors as a JSON string"
        aGrammErrs, aSpellErrs = self.getParagraphErrors(sText, dOptions, bContext, bSpellSugg, bDebug)
        aGrammErrs = list(aGrammErrs)
        if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
            return ""
        if lLineSet:
            aGrammErrs, aSpellErrs = text.convertToXY(aGrammErrs, aSpellErrs, lLineSet)
            return json.dumps({ "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
        if bReturnText:
            return json.dumps({ "iParagraph": iIndex, "sText": sText, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
        return json.dumps({ "iParagraph": iIndex, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)

    def getTextErrorsAsJSON (self, sText, bContext=False, bEmptyIfNoErrors=False, bSpellSugg=False, bReturnText=False, bDebug=False):
        "[todo]"
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<




































































































































































Modified gc_core/py/lang_core/gc_engine.py from [c796a47a03] to [95762aa8e3].

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
"""
Grammalecte
Grammar checker engine
"""

import re
import traceback


#import unicodedata
from itertools import chain

from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo

from .. import text


from . import gc_options


try:
    # LibreOffice / OpenOffice
    from com.sun.star.linguistic2 import SingleProofreadingError
    from com.sun.star.text.TextMarkupType import PROOFREADING
    from com.sun.star.beans import PropertyValue
    #import lightproof_handler_${implname} as opt
    _bWriterError = True
except ImportError:
    _bWriterError = False


__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
            "load", "parse", "getSpellChecker", \
            "setOption", "setOptions", "getOptions", "getDefaultOptions", "getOptionsLabels", "resetOptions", "displayOptions", \
            "ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules", "setWriterUnderliningStyle" ]

__version__ = "${version}"


lang = "${lang}"
locales = ${loc}
pkg = "${implname}"
name = "${name}"
version = "${version}"
author = "${author}"

# Modules
_rules = None                               # module gc_rules
_rules_graph = None                         # module gc_rules_graph

# Data
_sAppContext = ""                           # what software is running
_dOptions = None
_dOptionsColors = None
_oSpellChecker = None
_oTokenizer = None



_aIgnoredRules = set()

# Writer underlining style

_bMulticolor = True
_nUnderliningStyle = 0


#### Initialization

def load (sContext="Python", sColorType="aRGB"):
    "initialization of the grammar checker"
    global _oSpellChecker
    global _sAppContext
    global _dOptions
    global _dOptionsColors
    global _oTokenizer
    try:
        _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
        _sAppContext = sContext
        _dOptions = gc_options.getOptions(sContext).copy()   # duplication necessary, to be able to reset to default
        _dOptionsColors = gc_options.getOptionsColors(sContext, sColorType)
        _oTokenizer = _oSpellChecker.getTokenizer()
        _oSpellChecker.activateStorage()


    except:
        traceback.print_exc()




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











#### Rules

def _getRules (bParagraph):
    try:
        if not bParagraph:
            return _rules.lSentenceRules







>
>








>

>












|
|
<
|















|
<
<
<


>
>
>



>









<
<




|
<
<

|
>
>



>
>





>
>
>
>
>
>
>
>
>







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
"""
Grammalecte
Grammar checker engine
"""

import re
import traceback
import json
import importlib
#import unicodedata
from itertools import chain

from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo

from .. import text

from . import gc_engine_func as gce_func
from . import gc_options


try:
    # LibreOffice / OpenOffice
    from com.sun.star.linguistic2 import SingleProofreadingError
    from com.sun.star.text.TextMarkupType import PROOFREADING
    from com.sun.star.beans import PropertyValue
    #import lightproof_handler_${implname} as opt
    _bWriterError = True
except ImportError:
    _bWriterError = False


#__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
#            "load", "parse", "getSpellChecker", "getTextFormatter", "getLexicographer" \

#            "ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules", "setWriterUnderliningStyle" ]

__version__ = "${version}"


lang = "${lang}"
locales = ${loc}
pkg = "${implname}"
name = "${name}"
version = "${version}"
author = "${author}"

# Modules
_rules = None                               # module gc_rules
_rules_graph = None                         # module gc_rules_graph

# Tools



_oSpellChecker = None
_oTokenizer = None
_oLexicographer = None

# Data
_aIgnoredRules = set()

# Writer underlining style
_dOptionsColors = None
_bMulticolor = True
_nUnderliningStyle = 0


#### Initialization

def load (sContext="Python", sColorType="aRGB"):
    "initialization of the grammar checker"
    global _oSpellChecker


    global _dOptionsColors
    global _oTokenizer
    try:
        _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
        _oSpellChecker.activateStorage()


        _oTokenizer = _oSpellChecker.getTokenizer()
        gce_func.load(sContext, _oSpellChecker)
        gc_options.load(sContext)
        _dOptionsColors = gc_options.getOptionsColors(sContext, sColorType)
    except:
        traceback.print_exc()


#### Tools

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


def getLexicographer ():
    "load and return the lexicographer"
    global _oLexicographer
    if _oLexicographer is None:
        lxg = importlib.import_module(".lexicographe", "grammalecte.${lang}")
        _oLexicographer = lxg.Lexicographe(_oSpellChecker)
    return _oLexicographer


#### Rules

def _getRules (bParagraph):
    try:
        if not bParagraph:
            return _rules.lSentenceRules
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141

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 re.error:
            echo("# Error. List rules: wrong regex.")
            sFilter = None
    # regex rules







|







140
141
142
143
144
145
146
147
148
149
150
151
152
153
154

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


def listRules (sFilter=None):
    "generator: returns tuple (sRuleType, sOption, sLineId, sRuleId)"
    if sFilter:
        try:
            zFilter = re.compile(sFilter)
        except re.error:
            echo("# Error. List rules: wrong regex.")
            sFilter = None
    # regex rules
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

def displayRules (sFilter=None):
    "display the name of rules, with the filter <sFilter>"
    echo("List of rules. Filter: << " + str(sFilter) + " >>")
    for sOption, sLineId, sRuleId, sType in listRules(sFilter):
        echo("{:<8} {:<10} {:<10} {}".format(sOption, sLineId, sRuleId, sType))


#### Options

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 gc_options.getOptions(_sAppContext).copy()


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


def displayOptions (sLang="${lang}"):
    "display the list of grammar checking options"
    echo("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 = getDefaultOptions()


def setWriterUnderliningStyle (sStyle="BOLDWAVE", bMulticolor=True):
    "set underlining style for Writer (WAVE, BOLDWAVE, BOLD)"
    global _nUnderliningStyle
    global _bMulticolor
    # https://api.libreoffice.org/docs/idl/ref/FontUnderline_8idl.html
    # WAVE: 10, BOLD: 12, BOLDWAVE: 18 DASH: 5







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<







166
167
168
169
170
171
172











































173
174
175
176
177
178
179

def displayRules (sFilter=None):
    "display the name of rules, with the filter <sFilter>"
    echo("List of rules. Filter: << " + str(sFilter) + " >>")
    for sOption, sLineId, sRuleId, sType in listRules(sFilter):
        echo("{:<8} {:<10} {:<10} {}".format(sOption, sLineId, sRuleId, sType))













































def setWriterUnderliningStyle (sStyle="BOLDWAVE", bMulticolor=True):
    "set underlining style for Writer (WAVE, BOLDWAVE, BOLD)"
    global _nUnderliningStyle
    global _bMulticolor
    # https://api.libreoffice.org/docs/idl/ref/FontUnderline_8idl.html
    # WAVE: 10, BOLD: 12, BOLDWAVE: 18 DASH: 5
217
218
219
220
221
222
223





























224
225
226
227
228
229
230
        _nUnderliningStyle = 5
    else:
        _nUnderliningStyle = 0
    _bMulticolor = bMulticolor


#### Parsing






























def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False):
    "init point to analyse <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors"
    oText = TextParser(sText)
    return oText.parse(sCountry, bDebug, dOptions, bContext, bFullInfo)









>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







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
        _nUnderliningStyle = 5
    else:
        _nUnderliningStyle = 0
    _bMulticolor = bMulticolor


#### Parsing

def getParagraphErrors (sText, dOptions=None, bContext=False, bSpellSugg=False, bDebug=False):
    "returns a tuple: (grammar errors, spelling errors)"
    aGrammErrs = parse(sText, "FR", bDebug=bDebug, dOptions=dOptions, bContext=bContext)
    aSpellErrs = _oSpellChecker.parseParagraph(sText, bSpellSugg)
    return aGrammErrs, aSpellErrs


def getParagraphWithErrors (sText, dOptions=None, bEmptyIfNoErrors=False, bSpellSugg=False, nWidth=100, bDebug=False):
    "parse text and return a readable text with underline errors"
    aGrammErrs, aSpellErrs = getParagraphErrors(sText, dOptions, False, bSpellSugg, bDebug)
    if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
        return ("", [])
    return text.generateParagraph(sText, aGrammErrs, aSpellErrs, nWidth)


def getParagraphErrorsAsJSON (iIndex, sText, dOptions=None, bContext=False, bEmptyIfNoErrors=False, bSpellSugg=False, bReturnText=False, lLineSet=None, bDebug=False):
    "parse text and return errors as a JSON string"
    aGrammErrs, aSpellErrs = getParagraphErrors(sText, dOptions, bContext, bSpellSugg, bDebug)
    aGrammErrs = list(aGrammErrs)
    if bEmptyIfNoErrors and not aGrammErrs and not aSpellErrs:
        return ""
    if lLineSet:
        aGrammErrs, aSpellErrs = text.convertToXY(aGrammErrs, aSpellErrs, lLineSet)
        return json.dumps({ "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
    if bReturnText:
        return json.dumps({ "iParagraph": iIndex, "sText": sText, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)
    return json.dumps({ "iParagraph": iIndex, "lGrammarErrors": aGrammErrs, "lSpellingErrors": aSpellErrs }, ensure_ascii=False)


def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False):
    "init point to analyse <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors"
    oText = TextParser(sText)
    return oText.parse(sCountry, bDebug, dOptions, bContext, bFullInfo)


260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
        #for nPos, dToken in self.dTokenPos.items():
        #    s += "{}\t{}\n".format(nPos, dToken)
        return s

    def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False):
        "analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors"
        #sText = unicodedata.normalize("NFC", sText)
        dOpt = dOptions or _dOptions
        bShowRuleId = option('idrule')
        # parse paragraph
        try:
            self.parseText(self.sText, self.sText0, True, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext)
        except:
            raise
        if bFullInfo:
            lParagraphErrors = list(self.dError.values())







|
|







259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
        #for nPos, dToken in self.dTokenPos.items():
        #    s += "{}\t{}\n".format(nPos, dToken)
        return s

    def parse (self, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False, bFullInfo=False):
        "analyses <sText> and returns an iterable of errors or (with option <bFullInfo>) paragraphs errors and sentences with tokens and errors"
        #sText = unicodedata.normalize("NFC", sText)
        dOpt = dOptions or gc_options.dOptions
        bShowRuleId = gc_options.dOptions.get('idrule', False)
        # parse paragraph
        try:
            self.parseText(self.sText, self.sText0, True, 0, sCountry, dOpt, bShowRuleId, bDebug, bContext)
        except:
            raise
        if bFullInfo:
            lParagraphErrors = list(self.dError.values())
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
                for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup:
                    if sRuleId not in _aIgnoredRules:
                        for m in zRegex.finditer(sText):
                            bCondMemo = None
                            for sFuncCond, cActionType, sWhat, *eAct in lActions:
                                # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try:
                                    bCondMemo = not sFuncCond or globals()[sFuncCond](sText, sText0, m, self.dTokenPos, sCountry, bCondMemo)
                                    if bCondMemo:
                                        if bDebug:
                                            echo("RULE: " + sLineId)
                                        if cActionType == "-":
                                            # grammar error
                                            nErrorStart = nOffset + m.start(eAct[0])
                                            if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1):
                                                self.dError[nErrorStart] = self._createErrorFromRegex(sText, sText0, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext)
                                                self.dErrorPriority[nErrorStart] = nPriority
                                                self.dSentenceError[nErrorStart] = self.dError[nErrorStart]
                                        elif cActionType == "~":
                                            # text processor
                                            sText = self.rewriteText(sText, sWhat, eAct[0], m, bUppercase)
                                            bChange = True
                                            if bDebug:
                                                echo("~ " + sText + "  -- " + m.group(eAct[0]) + "  # " + sLineId)
                                        elif cActionType == "=":
                                            # disambiguation
                                            if not bParagraph:
                                                globals()[sWhat](sText, m, self.dTokenPos)
                                                if bDebug:
                                                    echo("= " + m.group(0) + "  # " + sLineId)
                                        elif cActionType == ">":
                                            # we do nothing, this test is just a condition to apply all following actions
                                            pass
                                        else:
                                            echo("# error: unknown action at " + sLineId)







|



















|







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
                for zRegex, bUppercase, sLineId, sRuleId, nPriority, lActions in lRuleGroup:
                    if sRuleId not in _aIgnoredRules:
                        for m in zRegex.finditer(sText):
                            bCondMemo = None
                            for sFuncCond, cActionType, sWhat, *eAct in lActions:
                                # action in lActions: [ condition, action type, replacement/suggestion/action[, iGroup[, message, URL]] ]
                                try:
                                    bCondMemo = not sFuncCond or getattr(gce_func, sFuncCond)(sText, sText0, m, self.dTokenPos, sCountry, bCondMemo)
                                    if bCondMemo:
                                        if bDebug:
                                            echo("RULE: " + sLineId)
                                        if cActionType == "-":
                                            # grammar error
                                            nErrorStart = nOffset + m.start(eAct[0])
                                            if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1):
                                                self.dError[nErrorStart] = self._createErrorFromRegex(sText, sText0, sWhat, nOffset, m, eAct[0], sLineId, sRuleId, bUppercase, eAct[1], eAct[2], bShowRuleId, sOption, bContext)
                                                self.dErrorPriority[nErrorStart] = nPriority
                                                self.dSentenceError[nErrorStart] = self.dError[nErrorStart]
                                        elif cActionType == "~":
                                            # text processor
                                            sText = self.rewriteText(sText, sWhat, eAct[0], m, bUppercase)
                                            bChange = True
                                            if bDebug:
                                                echo("~ " + sText + "  -- " + m.group(eAct[0]) + "  # " + sLineId)
                                        elif cActionType == "=":
                                            # disambiguation
                                            if not bParagraph:
                                                getattr(gce_func, sWhat)(sText, m, self.dTokenPos)
                                                if bDebug:
                                                    echo("= " + m.group(0) + "  # " + sLineId)
                                        elif cActionType == ">":
                                            # we do nothing, this test is just a condition to apply all following actions
                                            pass
                                        else:
                                            echo("# error: unknown action at " + sLineId)
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
        for sLineId, nextNodeKey in dNode.items():
            bCondMemo = None
            for sRuleId in dGraph[nextNodeKey]:
                try:
                    if bDebug:
                        echo("   >TRY: " + sRuleId + " " + sLineId)
                    _, sOption, sFuncCond, cActionType, sWhat, *eAct = _rules_graph.dRule[sRuleId]
                    # Suggestion    [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ]
                    # TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
                    # Disambiguator [ option, condition, "=", replacement/suggestion/action ]
                    # Tag           [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    # Immunity      [ option, condition, "!", "",                            iTokenStart, iTokenEnd ]
                    # Test          [ option, condition, ">", "" ]
                    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
                                iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL = eAct
                                nTokenErrorStart = nTokenOffset + iTokenStart  if iTokenStart > 0  else nLastToken + iTokenStart
                                if "bImmune" not in self.lToken[nTokenErrorStart]:
                                    nTokenErrorEnd = nTokenOffset + iTokenEnd  if iTokenEnd > 0  else nLastToken + iTokenEnd







|
|
|
|
|
|

|







583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
        for sLineId, nextNodeKey in dNode.items():
            bCondMemo = None
            for sRuleId in dGraph[nextNodeKey]:
                try:
                    if bDebug:
                        echo("   >TRY: " + sRuleId + " " + sLineId)
                    _, sOption, sFuncCond, cActionType, sWhat, *eAct = _rules_graph.dRule[sRuleId]
                    # Suggestion    [ sActionLineId, option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ]
                    # TextProcessor [ sActionLineId, option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
                    # Disambiguator [ sActionLineId, option, condition, "=", replacement/suggestion/action ]
                    # Tag           [ sActionLineId, option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
                    # Immunity      [ sActionLineId, option, condition, "!", "",                            iTokenStart, iTokenEnd ]
                    # Test          [ sActionLineId, option, condition, ">", "" ]
                    if not sOption or dOptions.get(sOption, False):
                        bCondMemo = not sFuncCond or getattr(gce_func, sFuncCond)(self.lToken, nTokenOffset, nLastToken, sCountry, bCondMemo, self.dTags, self.sSentence, self.sSentence0)
                        if bCondMemo:
                            if cActionType == "-":
                                # grammar error
                                iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL = eAct
                                nTokenErrorStart = nTokenOffset + iTokenStart  if iTokenStart > 0  else nLastToken + iTokenStart
                                if "bImmune" not in self.lToken[nTokenErrorStart]:
                                    nTokenErrorEnd = nTokenOffset + iTokenEnd  if iTokenEnd > 0  else nLastToken + iTokenEnd
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
                                nTokenEnd = nTokenOffset + eAct[1]  if eAct[1] > 0  else nLastToken + eAct[1]
                                self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug)
                                bChange = True
                                if bDebug:
                                    echo("    TEXT_PROCESSOR: [{}:{}]  > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat))
                            elif cActionType == "=":
                                # disambiguation
                                globals()[sWhat](self.lToken, nTokenOffset, nLastToken)
                                if bDebug:
                                    echo("    DISAMBIGUATOR: ({})  [{}:{}]".format(sWhat, self.lToken[nTokenOffset+1]["sValue"], self.lToken[nLastToken]["sValue"]))
                            elif cActionType == ">":
                                # we do nothing, this test is just a condition to apply all following actions
                                if bDebug:
                                    echo("    COND_OK")
                            elif cActionType == "/":







|







616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
                                nTokenEnd = nTokenOffset + eAct[1]  if eAct[1] > 0  else nLastToken + eAct[1]
                                self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug)
                                bChange = True
                                if bDebug:
                                    echo("    TEXT_PROCESSOR: [{}:{}]  > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat))
                            elif cActionType == "=":
                                # disambiguation
                                getattr(gce_func, sWhat)(self.lToken, nTokenOffset, nLastToken)
                                if bDebug:
                                    echo("    DISAMBIGUATOR: ({})  [{}:{}]".format(sWhat, self.lToken[nTokenOffset+1]["sValue"], self.lToken[nLastToken]["sValue"]))
                            elif cActionType == ">":
                                # we do nothing, this test is just a condition to apply all following actions
                                if bDebug:
                                    echo("    COND_OK")
                            elif cActionType == "/":
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
        return bChange

    def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
        nStart = nOffset + m.start(iGroup)
        nEnd = nOffset + m.end(iGroup)
        # suggestions
        if sRepl[0:1] == "=":
            sSugg = globals()[sRepl[1:]](sText, m)
            lSugg = sSugg.split("|")  if sSugg  else []
        elif sRepl == "_":
            lSugg = []
        else:
            lSugg = m.expand(sRepl).split("|")
        if bUppercase and lSugg and m.group(iGroup)[0:1].isupper():
            lSugg = list(map(lambda s: s[0:1].upper()+s[1:], lSugg))
        # Message
        sMessage = globals()[sMsg[1:]](sText, m)  if sMsg[0:1] == "="  else  m.expand(sMsg)
        if bShowRuleId:
            sMessage += "  #" + sLineId + " / " + sRuleId
        #
        if _bWriterError:
            return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL)
        return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext)

    def _createErrorFromTokens (self, sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext):
        # suggestions
        if sSugg[0:1] == "=":
            sSugg = globals()[sSugg[1:]](self.lToken, nTokenOffset, nLastToken)
            lSugg = sSugg.split("|")  if sSugg  else []
        elif sSugg == "_":
            lSugg = []
        else:
            lSugg = self._expand(sSugg, nTokenOffset, nLastToken).split("|")
        if bCaseSvty and lSugg and self.lToken[iFirstToken]["sValue"][0:1].isupper():
            lSugg = list(map(lambda s: s[0:1].upper()+s[1:], lSugg))
        # Message
        sMessage = globals()[sMsg[1:]](self.lToken, nTokenOffset, nLastToken)  if sMsg[0:1] == "="  else self._expand(sMsg, nTokenOffset, nLastToken)
        if bShowRuleId:
            sMessage += "  #" + sLineId + " / " + sRuleId
        #
        if _bWriterError:
            return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL)
        return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext)








|








|










|








|







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
        return bChange

    def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
        nStart = nOffset + m.start(iGroup)
        nEnd = nOffset + m.end(iGroup)
        # suggestions
        if sRepl[0:1] == "=":
            sSugg = getattr(gce_func, sRepl[1:])(sText, m)
            lSugg = sSugg.split("|")  if sSugg  else []
        elif sRepl == "_":
            lSugg = []
        else:
            lSugg = m.expand(sRepl).split("|")
        if bUppercase and lSugg and m.group(iGroup)[0:1].isupper():
            lSugg = list(map(lambda s: s[0:1].upper()+s[1:], lSugg))
        # Message
        sMessage = getattr(gce_func, sMsg[1:])(sText, m)  if sMsg[0:1] == "="  else  m.expand(sMsg)
        if bShowRuleId:
            sMessage += "  #" + sLineId + " / " + sRuleId
        #
        if _bWriterError:
            return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL)
        return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext)

    def _createErrorFromTokens (self, sSugg, nTokenOffset, nLastToken, iFirstToken, nStart, nEnd, sLineId, sRuleId, bCaseSvty, sMsg, sURL, bShowRuleId, sOption, bContext):
        # suggestions
        if sSugg[0:1] == "=":
            sSugg = getattr(gce_func, sSugg[1:])(self.lToken, nTokenOffset, nLastToken)
            lSugg = sSugg.split("|")  if sSugg  else []
        elif sSugg == "_":
            lSugg = []
        else:
            lSugg = self._expand(sSugg, nTokenOffset, nLastToken).split("|")
        if bCaseSvty and lSugg and self.lToken[iFirstToken]["sValue"][0:1].isupper():
            lSugg = list(map(lambda s: s[0:1].upper()+s[1:], lSugg))
        # Message
        sMessage = getattr(gce_func, sMsg[1:])(self.lToken, nTokenOffset, nLastToken)  if sMsg[0:1] == "="  else self._expand(sMsg, nTokenOffset, nLastToken)
        if bShowRuleId:
            sMessage += "  #" + sLineId + " / " + sRuleId
        #
        if _bWriterError:
            return self._createErrorForWriter(nStart, nEnd - nStart, sRuleId, sOption, sMessage, lSugg, sURL)
        return self._createErrorAsDict(nStart, nEnd, sLineId, sRuleId, sOption, sMessage, lSugg, sURL, bContext)

765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
        if sRepl == "*":
            sNew = " " * nLen
        elif sRepl == "_":
            sNew = "_" * nLen
        elif sRepl == "@":
            sNew = "@" * nLen
        elif sRepl[0:1] == "=":
            sNew = globals()[sRepl[1:]](sText, m)
            sNew = sNew + " " * (nLen-len(sNew))
            if bUppercase and m.group(iGroup)[0:1].isupper():
                sNew = sNew.capitalize()
        else:
            sNew = m.expand(sRepl)
            sNew = sNew + " " * (nLen-len(sNew))
        return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):]







|







764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
        if sRepl == "*":
            sNew = " " * nLen
        elif sRepl == "_":
            sNew = "_" * nLen
        elif sRepl == "@":
            sNew = "@" * nLen
        elif sRepl[0:1] == "=":
            sNew = getattr(gce_func, sRepl[1:])(sText, m)
            sNew = sNew + " " * (nLen-len(sNew))
            if bUppercase and m.group(iGroup)[0:1].isupper():
                sNew = sNew.capitalize()
        else:
            sNew = m.expand(sRepl)
            sNew = sNew + " " * (nLen-len(sNew))
        return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):]
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
            if nTokenRewriteEnd - nTokenRewriteStart == 0:
                self.lToken[nTokenRewriteStart]["sNewValue"] = "_"
            else:
                for i in range(nTokenRewriteStart, nTokenRewriteEnd+1):
                    self.lToken[i]["sNewValue"] = "_"
        else:
            if sWhat.startswith("="):
                sWhat = globals()[sWhat[1:]](self.lToken, nTokenOffset, nLastToken)
            else:
                sWhat = self._expand(sWhat, nTokenOffset, nLastToken)
            bUppercase = bCaseSvty and self.lToken[nTokenRewriteStart]["sValue"][0:1].isupper()
            if nTokenRewriteEnd - nTokenRewriteStart == 0:
                # one token
                if bUppercase:
                    sWhat = sWhat[0:1].upper() + sWhat[1:]







|







794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
            if nTokenRewriteEnd - nTokenRewriteStart == 0:
                self.lToken[nTokenRewriteStart]["sNewValue"] = "_"
            else:
                for i in range(nTokenRewriteStart, nTokenRewriteEnd+1):
                    self.lToken[i]["sNewValue"] = "_"
        else:
            if sWhat.startswith("="):
                sWhat = getattr(gce_func, sWhat[1:])(self.lToken, nTokenOffset, nLastToken)
            else:
                sWhat = self._expand(sWhat, nTokenOffset, nLastToken)
            bUppercase = bCaseSvty and self.lToken[nTokenRewriteStart]["sValue"][0:1].isupper()
            if nTokenRewriteEnd - nTokenRewriteStart == 0:
                # one token
                if bUppercase:
                    sWhat = sWhat[0:1].upper() + sWhat[1:]
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
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
                except KeyError:
                    echo(self)
                    echo(dToken)
        if bDebug:
            echo("  TEXT REWRITED: " + self.sSentence)
        self.lToken.clear()
        self.lToken = lNewToken


#### common functions

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


#### Functions to get text outside pattern scope

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

_zNextWord = re.compile(r" +(\w[\w-]*)")
_zPrevWord = re.compile(r"(\w[\w-]*) +$")

def nextword (s, iStart, n):
    "get the nth word of the input string or empty string"
    m = re.match("(?: +[\\w%-]+){" + str(n-1) + "} +([\\w%-]+)", s[iStart:])
    if not m:
        return None
    return (iStart+m.start(1), m.group(1))


def prevword (s, iEnd, n):
    "get the (-)nth word of the input string or empty string"
    m = re.search("([\\w%-]+) +(?:[\\w%-]+ +){" + str(n-1) + "}$", s[:iEnd])
    if not m:
        return None
    return (m.start(1), m.group(1))


def nextword1 (s, iStart):
    "get next word (optimization)"
    m = _zNextWord.match(s[iStart:])
    if not m:
        return None
    return (iStart+m.start(1), m.group(1))


def prevword1 (s, iEnd):
    "get previous word (optimization)"
    m = _zPrevWord.search(s[:iEnd])
    if not m:
        return None
    return (m.start(1), m.group(1))


def look (s, sPattern, sNegPattern=None):
    "seek sPattern in s (before/after/fulltext), if sNegPattern not in s"
    if sNegPattern and re.search(sNegPattern, s):
        return False
    if re.search(sPattern, s):
        return True
    return False


def look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=""):
    "returns True if s has pattern sPattern and m.group(1) has pattern sPatternGroup1"
    m = re.search(sPattern, s)
    if not m:
        return False
    try:
        sWord = m.group(1)
        nPos = m.start(1) + nOffset
    except IndexError:
        return False
    return morph(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)



#### Analyse groups for regex rules

def displayInfo (dTokenPos, tWord):
    "for debugging: retrieve info of word"
    if not tWord:
        echo("> nothing to find")
        return True
    lMorph = _oSpellChecker.getMorph(tWord[1])
    if not lMorph:
        echo("> not in dictionary")
        return True
    echo("TOKENS:", dTokenPos)
    if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]:
        echo("DA: " + str(dTokenPos[tWord[0]]["lMorph"]))
    echo("FSA: " + str(lMorph))
    return True


def morph (dTokenPos, tWord, sPattern, sNegPattern="", bNoWord=False):
    "analyse a tuple (position, word), returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)"
    if not tWord:
        return bNoWord
    lMorph = dTokenPos[tWord[0]]["lMorph"]  if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]  else _oSpellChecker.getMorph(tWord[1])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def analyse (sWord, sPattern, sNegPattern=""):
    "analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)"
    lMorph = _oSpellChecker.getMorph(sWord)
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


#### Analyse tokens for graph rules

def g_value (dToken, sValues, nLeft=None, nRight=None):
    "test if <dToken['sValue']> is in sValues (each value should be separated with |)"
    sValue = "|"+dToken["sValue"]+"|"  if nLeft is None  else "|"+dToken["sValue"][slice(nLeft, nRight)]+"|"
    if sValue in sValues:
        return True
    if dToken["sValue"][0:2].istitle(): # we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
        if sValue.lower() in sValues:
            return True
    elif dToken["sValue"].isupper():
        #if sValue.lower() in sValues:
        #    return True
        sValue = "|"+sValue[1:].capitalize()
        if sValue in sValues:
            return True
        sValue = sValue.lower()
        if sValue in sValues:
            return True
    return False


def g_morph (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True):
    "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies"
    if "lMorph" in dToken:
        lMorph = dToken["lMorph"]
    else:
        if nLeft is not None:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
            if bMemorizeMorph:
                dToken["lMorph"] = lMorph
        else:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def g_analyse (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True):
    "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
    if nLeft is not None:
        lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
        if bMemorizeMorph:
            dToken["lMorph"] = lMorph
    else:
        lMorph = _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def g_merged_analyse (dToken1, dToken2, cMerger, sPattern, sNegPattern="", bSetMorph=True):
    "merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
    lMorph = _oSpellChecker.getMorph(dToken1["sValue"] + cMerger + dToken2["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            bResult = all(zPattern.search(sMorph)  for sMorph in lMorph)
            if bResult and bSetMorph:
                dToken1["lMorph"] = lMorph
            return bResult
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    bResult = any(zPattern.search(sMorph)  for sMorph in lMorph)
    if bResult and bSetMorph:
        dToken1["lMorph"] = lMorph
    return bResult


def g_tag_before (dToken, dTags, sTag):
    "returns True if <sTag> is present on tokens before <dToken>"
    if sTag not in dTags:
        return False
    if dToken["i"] > dTags[sTag][0]:
        return True
    return False


def g_tag_after (dToken, dTags, sTag):
    "returns True if <sTag> is present on tokens after <dToken>"
    if sTag not in dTags:
        return False
    if dToken["i"] < dTags[sTag][1]:
        return True
    return False


def g_tag (dToken, sTag):
    "returns True if <sTag> is present on token <dToken>"
    return "aTags" in dToken and sTag in dToken["aTags"]


def g_meta (dToken, sType):
    "returns True if <sType> is equal to the token type"
    return dToken["sType"] == sType


def g_space_between_tokens (dToken1, dToken2, nMin, nMax=None):
    "checks if spaces between tokens is >= <nMin> and <= <nMax>"
    nSpace = dToken2["nStart"] - dToken1["nEnd"]
    if nSpace < nMin:
        return False
    if nMax is not None and nSpace > nMax:
        return False
    return True


def g_token (lToken, i):
    "return token at index <i> in lToken (or the closest one)"
    if i < 0:
        return lToken[0]
    if i >= len(lToken):
        return lToken[-1]
    return lToken[i]



#### Disambiguator for regex rules

def select (dTokenPos, nPos, sWord, sPattern, lDefault=None):
    "Disambiguation: select morphologies of <sWord> matching <sPattern>"
    if not sWord:
        return True
    if nPos not in dTokenPos:
        echo("Error. There should be a token at this position: ", nPos)
        return True
    lMorph = _oSpellChecker.getMorph(sWord)
    if not lMorph or len(lMorph) == 1:
        return True
    lSelect = [ sMorph  for sMorph in lMorph  if re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(lMorph):
            dTokenPos[nPos]["lMorph"] = lSelect
    elif lDefault:
        dTokenPos[nPos]["lMorph"] = lDefault
    return True


def exclude (dTokenPos, nPos, sWord, sPattern, lDefault=None):
    "Disambiguation: exclude morphologies of <sWord> matching <sPattern>"
    if not sWord:
        return True
    if nPos not in dTokenPos:
        echo("Error. There should be a token at this position: ", nPos)
        return True
    lMorph = _oSpellChecker.getMorph(sWord)
    if not lMorph or len(lMorph) == 1:
        return True
    lSelect = [ sMorph  for sMorph in lMorph  if not re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(lMorph):
            dTokenPos[nPos]["lMorph"] = lSelect
    elif lDefault:
        dTokenPos[nPos]["lMorph"] = lDefault
    return True


def define (dTokenPos, nPos, lMorph):
    "Disambiguation: set morphologies of token at <nPos> with <lMorph>"
    if nPos not in dTokenPos:
        echo("Error. There should be a token at this position: ", nPos)
        return True
    dTokenPos[nPos]["lMorph"] = lMorph
    return True


#### Disambiguation for graph rules

def g_select (dToken, sPattern, lDefault=None):
    "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph or len(lMorph) == 1:
        if lDefault:
            dToken["lMorph"] = lDefault
            #echo("DA:", dToken["sValue"], dToken["lMorph"])
        return True
    lSelect = [ sMorph  for sMorph in lMorph  if re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(lMorph):
            dToken["lMorph"] = lSelect
    elif lDefault:
        dToken["lMorph"] = lDefault
    #echo("DA:", dToken["sValue"], dToken["lMorph"])
    return True


def g_exclude (dToken, sPattern, lDefault=None):
    "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph or len(lMorph) == 1:
        if lDefault:
            dToken["lMorph"] = lDefault
            #echo("DA:", dToken["sValue"], dToken["lMorph"])
        return True
    lSelect = [ sMorph  for sMorph in lMorph  if not re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(lMorph):
            dToken["lMorph"] = lSelect
    elif lDefault:
        dToken["lMorph"] = lDefault
    #echo("DA:", dToken["sValue"], dToken["lMorph"])
    return True


def g_add_morph (dToken, lNewMorph):
    "Disambiguation: add a morphology to a token"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    lMorph.extend(lNewMorph)
    dToken["lMorph"] = lMorph
    return True


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


def g_define_from (dToken, nLeft=None, nRight=None):
    "Disambiguation: set morphologies of <dToken> with slicing its value with <nLeft> and <nRight>"
    if nLeft is not None:
        dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
    else:
        dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"])
    return True


def g_change_meta (dToken, sType):
    "Disambiguation: change type of token"
    dToken["sType"] = sType
    return True



#### GRAMMAR CHECKER PLUGINS

${plugins}


#### CALLABLES FOR REGEX RULES (generated code)

${callables}


#### CALLABLES FOR GRAPH RULES (generated code)

${graph_callables}







<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
868
869
870
871
872
873
874





















































































































































































































































































































































































































                except KeyError:
                    echo(self)
                    echo(dToken)
        if bDebug:
            echo("  TEXT REWRITED: " + self.sSentence)
        self.lToken.clear()
        self.lToken = lNewToken





















































































































































































































































































































































































































Added gc_core/py/lang_core/gc_engine_func.py version [42827fa728].



















































































































































































































































































































































































































































































































































































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
"""
Grammar checking functions
"""

# generated code, do not edit
# source: gc_core/py/lang_core/gc_engine_func.py

import re

from . import gc_options

_sAppContext = "Python"         # what software is running
_oSpellChecker = None


def load (sContext, oSpellChecker):
    global _sAppContext
    global _oSpellChecker
    _sAppContext = sContext
    _oSpellChecker = oSpellChecker


#### common functions

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


#### Functions to get text outside pattern scope

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

_zNextWord = re.compile(r" +(\w[\w-]*)")
_zPrevWord = re.compile(r"(\w[\w-]*) +$")

def nextword (s, iStart, n):
    "get the nth word of the input string or empty string"
    m = re.match("(?: +[\\w%-]+){" + str(n-1) + "} +([\\w%-]+)", s[iStart:])
    if not m:
        return None
    return (iStart+m.start(1), m.group(1))


def prevword (s, iEnd, n):
    "get the (-)nth word of the input string or empty string"
    m = re.search("([\\w%-]+) +(?:[\\w%-]+ +){" + str(n-1) + "}$", s[:iEnd])
    if not m:
        return None
    return (m.start(1), m.group(1))


def nextword1 (s, iStart):
    "get next word (optimization)"
    m = _zNextWord.match(s[iStart:])
    if not m:
        return None
    return (iStart+m.start(1), m.group(1))


def prevword1 (s, iEnd):
    "get previous word (optimization)"
    m = _zPrevWord.search(s[:iEnd])
    if not m:
        return None
    return (m.start(1), m.group(1))


def look (s, sPattern, sNegPattern=None):
    "seek sPattern in s (before/after/fulltext), if sNegPattern not in s"
    if sNegPattern and re.search(sNegPattern, s):
        return False
    if re.search(sPattern, s):
        return True
    return False


def look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=""):
    "returns True if s has pattern sPattern and m.group(1) has pattern sPatternGroup1"
    m = re.search(sPattern, s)
    if not m:
        return False
    try:
        sWord = m.group(1)
        nPos = m.start(1) + nOffset
    except IndexError:
        return False
    return morph(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)



#### Analyse groups for regex rules

def displayInfo (dTokenPos, tWord):
    "for debugging: retrieve info of word"
    if not tWord:
        print("> nothing to find")
        return True
    lMorph = _oSpellChecker.getMorph(tWord[1])
    if not lMorph:
        print("> not in dictionary")
        return True
    print("TOKENS:", dTokenPos)
    if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]:
        print("DA: " + str(dTokenPos[tWord[0]]["lMorph"]))
    print("FSA: " + str(lMorph))
    return True


def morph (dTokenPos, tWord, sPattern, sNegPattern="", bNoWord=False):
    "analyse a tuple (position, word), returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)"
    if not tWord:
        return bNoWord
    lMorph = dTokenPos[tWord[0]]["lMorph"]  if tWord[0] in dTokenPos and "lMorph" in dTokenPos[tWord[0]]  else _oSpellChecker.getMorph(tWord[1])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def analyse (sWord, sPattern, sNegPattern=""):
    "analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)"
    lMorph = _oSpellChecker.getMorph(sWord)
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


#### Analyse tokens for graph rules

def g_value (dToken, sValues, nLeft=None, nRight=None):
    "test if <dToken['sValue']> is in sValues (each value should be separated with |)"
    sValue = "|"+dToken["sValue"]+"|"  if nLeft is None  else "|"+dToken["sValue"][slice(nLeft, nRight)]+"|"
    if sValue in sValues:
        return True
    if dToken["sValue"][0:2].istitle(): # we test only 2 first chars, to make valid words such as "Laissez-les", "Passe-partout".
        if sValue.lower() in sValues:
            return True
    elif dToken["sValue"].isupper():
        #if sValue.lower() in sValues:
        #    return True
        sValue = "|"+sValue[1:].capitalize()
        if sValue in sValues:
            return True
        sValue = sValue.lower()
        if sValue in sValues:
            return True
    return False


def g_morph (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True):
    "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies"
    if "lMorph" in dToken:
        lMorph = dToken["lMorph"]
    else:
        if nLeft is not None:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
            if bMemorizeMorph:
                dToken["lMorph"] = lMorph
        else:
            lMorph = _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def g_analyse (dToken, sPattern, sNegPattern="", nLeft=None, nRight=None, bMemorizeMorph=True):
    "analyse a token, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
    if nLeft is not None:
        lMorph = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
        if bMemorizeMorph:
            dToken["lMorph"] = lMorph
    else:
        lMorph = _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            return all(zPattern.search(sMorph)  for sMorph in lMorph)
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    return any(zPattern.search(sMorph)  for sMorph in lMorph)


def g_merged_analyse (dToken1, dToken2, cMerger, sPattern, sNegPattern="", bSetMorph=True):
    "merge two token values, return True if <sNegPattern> not in morphologies and <sPattern> in morphologies (disambiguation off)"
    lMorph = _oSpellChecker.getMorph(dToken1["sValue"] + cMerger + dToken2["sValue"])
    if not lMorph:
        return False
    # check negative condition
    if sNegPattern:
        if sNegPattern == "*":
            # all morph must match sPattern
            zPattern = re.compile(sPattern)
            bResult = all(zPattern.search(sMorph)  for sMorph in lMorph)
            if bResult and bSetMorph:
                dToken1["lMorph"] = lMorph
            return bResult
        zNegPattern = re.compile(sNegPattern)
        if any(zNegPattern.search(sMorph)  for sMorph in lMorph):
            return False
    # search sPattern
    zPattern = re.compile(sPattern)
    bResult = any(zPattern.search(sMorph)  for sMorph in lMorph)
    if bResult and bSetMorph:
        dToken1["lMorph"] = lMorph
    return bResult


def g_tag_before (dToken, dTags, sTag):
    "returns True if <sTag> is present on tokens before <dToken>"
    if sTag not in dTags:
        return False
    if dToken["i"] > dTags[sTag][0]:
        return True
    return False


def g_tag_after (dToken, dTags, sTag):
    "returns True if <sTag> is present on tokens after <dToken>"
    if sTag not in dTags:
        return False
    if dToken["i"] < dTags[sTag][1]:
        return True
    return False


def g_tag (dToken, sTag):
    "returns True if <sTag> is present on token <dToken>"
    return "aTags" in dToken and sTag in dToken["aTags"]


def g_meta (dToken, sType):
    "returns True if <sType> is equal to the token type"
    return dToken["sType"] == sType


def g_space_between_tokens (dToken1, dToken2, nMin, nMax=None):
    "checks if spaces between tokens is >= <nMin> and <= <nMax>"
    nSpace = dToken2["nStart"] - dToken1["nEnd"]
    if nSpace < nMin:
        return False
    if nMax is not None and nSpace > nMax:
        return False
    return True


def g_token (lToken, i):
    "return token at index <i> in lToken (or the closest one)"
    if i < 0:
        return lToken[0]
    if i >= len(lToken):
        return lToken[-1]
    return lToken[i]



#### Disambiguator for regex rules

def select (dTokenPos, nPos, sWord, sPattern, lDefault=None):
    "Disambiguation: select morphologies of <sWord> matching <sPattern>"
    if not sWord:
        return True
    if nPos not in dTokenPos:
        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


#### Disambiguation for graph rules

def g_select (dToken, sPattern, lDefault=None):
    "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph or len(lMorph) == 1:
        if lDefault:
            dToken["lMorph"] = lDefault
            #print("DA:", dToken["sValue"], dToken["lMorph"])
        return True
    lSelect = [ sMorph  for sMorph in lMorph  if re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(lMorph):
            dToken["lMorph"] = lSelect
    elif lDefault:
        dToken["lMorph"] = lDefault
    #print("DA:", dToken["sValue"], dToken["lMorph"])
    return True


def g_exclude (dToken, sPattern, lDefault=None):
    "Disambiguation: select morphologies for <dToken> according to <sPattern>, always return True"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    if not lMorph or len(lMorph) == 1:
        if lDefault:
            dToken["lMorph"] = lDefault
            #print("DA:", dToken["sValue"], dToken["lMorph"])
        return True
    lSelect = [ sMorph  for sMorph in lMorph  if not re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(lMorph):
            dToken["lMorph"] = lSelect
    elif lDefault:
        dToken["lMorph"] = lDefault
    #print("DA:", dToken["sValue"], dToken["lMorph"])
    return True


def g_add_morph (dToken, lNewMorph):
    "Disambiguation: add a morphology to a token"
    lMorph = dToken["lMorph"]  if "lMorph" in dToken  else _oSpellChecker.getMorph(dToken["sValue"])
    lMorph.extend(lNewMorph)
    dToken["lMorph"] = lMorph
    return True


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


def g_define_from (dToken, nLeft=None, nRight=None):
    "Disambiguation: set morphologies of <dToken> with slicing its value with <nLeft> and <nRight>"
    if nLeft is not None:
        dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"][slice(nLeft, nRight)])
    else:
        dToken["lMorph"] = _oSpellChecker.getMorph(dToken["sValue"])
    return True


def g_change_meta (dToken, sType):
    "Disambiguation: change type of token"
    dToken["sType"] = sType
    return True



#### GRAMMAR CHECKER PLUGINS

${plugins}


#### CALLABLES FOR REGEX RULES (generated code)

${callables}


#### CALLABLES FOR GRAPH RULES (generated code)

${graph_callables}

Modified gc_core/py/lang_core/gc_options.py from [b668596de4] to [4cbd062c46].

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
"""
Grammar checker default options
"""

# generated code, do not edit


import traceback



























def getUI (sLang):


















    "returns dictionary of UI labels"
    if sLang in _dOptLabel:
        return _dOptLabel[sLang]
    return _dOptLabel["fr"]


def getOptions (sContext="Python"):
    "returns dictionary of options"


    if sContext in _dOpt:
        return _dOpt[sContext]
    return _dOpt["Python"]


def getOptionsColors (sTheme="Default", sColorType="aRGB"):
    "returns dictionary of options colors"
    dOptColor = _dOptColor[sTheme]  if sTheme in _dOptColor  else  _dOptColor["Default"]
    dColorType = _dColorType[sColorType]  if sColorType in _dColorType  else _dColorType["aRGB"]
    try:
        return {  sOpt: dColorType[sColor] for sOpt, sColor in dOptColor.items() }
    except KeyError:
        traceback.print_exc()
        return {}


lStructOpt = ${lStructOpt}


_dOpt = {
    "Python": ${dOptPython},
    "Server": ${dOptServer},
    "Writer": ${dOptWriter}
}

_dColorType= ${dColorType}






>



>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>



|


|

>
>
|
|
|







|








|







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
"""
Grammar checker default options
"""

# generated code, do not edit
# source: gc_core/py/lang_core/gc_options.py

import traceback


dOptions = {}

_sAppContext = "Python"


def load (sContext="Python"):
    global dOptions
    global _sAppContext
    _sAppContext = sContext
    dOptions = getDefaultOptions(sContext)


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>, only known options are updated"
    for sKey, bVal in dOpt.items():
        if sKey in dOptions:
            dOptions[sKey] = bVal


def getOptions ():
    "return a copy of options as dictionary"
    return dOptions.copy()


def resetOptions ():
    "set options to default values"
    global dOptions
    dOptions = getDefaultOptions()


def displayOptions (sLang="${lang}"):
    "display the list of grammar checking options"
    print("Options:")
    print("\n".join( [ k+":\t"+str(v)+"\t"+getOptionLabels(sLang).get(k, ("?", ""))[0]  for k, v  in sorted(dOptions.items()) ] ))
    print("")


def getOptionLabels (sLang="${sLang}"):
    "returns dictionary of UI labels"
    if sLang in _dOptLabel:
        return _dOptLabel[sLang]
    return _dOptLabel["${sLang}"]


def getDefaultOptions (sContext=""):
    "returns dictionary of options"
    if not sContext:
        sContext = _sAppContext
    if sContext in _dDefaultOpt:
        return _dDefaultOpt[sContext].copy()    # duplication necessary, to be able to reset to default
    return _dDefaultOpt["Python"].copy()        # duplication necessary, to be able to reset to default


def getOptionsColors (sTheme="Default", sColorType="aRGB"):
    "returns dictionary of options colors"
    dOptColor = _dOptColor[sTheme]  if sTheme in _dOptColor  else  _dOptColor["Default"]
    dColorType = _dColorType[sColorType]  if sColorType in _dColorType  else _dColorType["aRGB"]
    try:
        return { sOpt: dColorType[sColor] for sOpt, sColor in dOptColor.items() }
    except KeyError:
        traceback.print_exc()
        return {}


lStructOpt = ${lStructOpt}


_dDefaultOpt = {
    "Python": ${dOptPython},
    "Server": ${dOptServer},
    "Writer": ${dOptWriter}
}

_dColorType= ${dColorType}

Modified gc_core/py/oxt/Grammalecte.py from [d7f4535da4] to [9c6625ba22].

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

from com.sun.star.linguistic2 import XProofreader, XSupportedLocales
from com.sun.star.linguistic2 import ProofreadingResult
from com.sun.star.lang import XServiceInfo, XServiceName, XServiceDisplayName
from com.sun.star.lang import Locale

import helpers
import grammalecte.${lang} as gce
#import lightproof_handler_${implname} as opt_handler
import Options


class Grammalecte (unohelper.Base, XProofreader, XServiceInfo, XServiceName, XServiceDisplayName, XSupportedLocales):

    def __init__ (self, ctx, *args):
        self.ctx = ctx
        self.ServiceName = "com.sun.star.linguistic2.Proofreader"
        self.ImplementationName = "org.openoffice.comp.pyuno.Lightproof." + gce.pkg
        self.SupportedServiceNames = (self.ServiceName, )
        self.locales = []
        for i in gce.locales:
            l = gce.locales[i]
            self.locales.append(Locale(l[0], l[1], l[2]))
        self.locales = tuple(self.locales)
        # debug
        #helpers.startConsole()
        # init
        gce.load("Writer", "nInt")
        # GC options
        #xContext = uno.getComponentContext()
        #opt_handler.load(xContext)
        dOpt = Options.loadOptions("${lang}")
        gce.setOptions(dOpt)
        # dictionaries options
        self.loadUserDictionaries()
        # underlining options
        self.setWriterUnderliningStyle()
        # store for results of big paragraphs
        self.dResult = {}
        self.nMaxRes = 1500







|









|


|
|





|




|







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

from com.sun.star.linguistic2 import XProofreader, XSupportedLocales
from com.sun.star.linguistic2 import ProofreadingResult
from com.sun.star.lang import XServiceInfo, XServiceName, XServiceDisplayName
from com.sun.star.lang import Locale

import helpers
import grammalecte.${lang} as gc_engine
#import lightproof_handler_${implname} as opt_handler
import Options


class Grammalecte (unohelper.Base, XProofreader, XServiceInfo, XServiceName, XServiceDisplayName, XSupportedLocales):

    def __init__ (self, ctx, *args):
        self.ctx = ctx
        self.ServiceName = "com.sun.star.linguistic2.Proofreader"
        self.ImplementationName = "org.openoffice.comp.pyuno.Lightproof." + gc_engine.pkg
        self.SupportedServiceNames = (self.ServiceName, )
        self.locales = []
        for i in gc_engine.locales:
            l = gc_engine.locales[i]
            self.locales.append(Locale(l[0], l[1], l[2]))
        self.locales = tuple(self.locales)
        # debug
        #helpers.startConsole()
        # init
        gc_engine.load("Writer", "nInt")
        # GC options
        #xContext = uno.getComponentContext()
        #opt_handler.load(xContext)
        dOpt = Options.loadOptions("${lang}")
        gc_engine.gc_options.setOptions(dOpt)
        # dictionaries options
        self.loadUserDictionaries()
        # underlining options
        self.setWriterUnderliningStyle()
        # store for results of big paragraphs
        self.dResult = {}
        self.nMaxRes = 1500
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
            if nHashedVal in self.dResult:
                return self.dResult[nHashedVal]
        # WORKAROUND ->>>

        xRes.nBehindEndOfSentencePosition = xRes.nStartOfNextSentencePosition

        try:
            xRes.aErrors = tuple(gce.parse(rText, rLocale.Country))
            # ->>> WORKAROUND
            if xRes.nStartOfNextSentencePosition > 3000:
                self.dResult[nHashedVal] = xRes
                self.nRes += 1
                if self.nRes > self.nMaxRes:
                    del self.dResult[self.lLastRes.popleft()]
                    self.nRes = self.nMaxRes
                self.lLastRes.append(nHashedVal)
            # END OF WORKAROUND
        except:
            traceback.print_exc()
        return xRes

    def ignoreRule (self, rid, aLocale):
        gce.ignoreRule(rid)

    def resetIgnoreRules (self):
        gce.resetIgnoreRules()

    # XServiceDisplayName
    def getServiceDisplayName (self, aLocale):
        return gce.name

    # Grammalecte
    def getSpellChecker (self):
        return gce.getSpellChecker()

    def loadUserDictionaries (self):
        try:
            xSettingNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Other/", False)
            xChild = xSettingNode.getByName("o_${lang}")
            if xChild.getPropertyValue("use_personal_dic"):
                sJSON = xChild.getPropertyValue("personal_dic")
                if sJSON:
                    oSpellChecker = gce.getSpellChecker();
                    oSpellChecker.setPersonalDictionary(json.loads(sJSON))
        except:
            traceback.print_exc()

    def setWriterUnderliningStyle (self):
        try:
            xSettingNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Other/", False)
            xChild = xSettingNode.getByName("o_${lang}")
            sLineType = xChild.getPropertyValue("line_type")
            bMulticolor = bool(xChild.getPropertyValue("line_multicolor"))
            gce.setWriterUnderliningStyle(sLineType, bMulticolor)
        except:
            traceback.print_exc()


g_ImplementationHelper = unohelper.ImplementationHelper()
g_ImplementationHelper.addImplementation(Grammalecte, "org.openoffice.comp.pyuno.Lightproof."+gce.pkg, ("com.sun.star.linguistic2.Proofreader",),)

# g_ImplementationHelper.addImplementation( opt_handler.LightproofOptionsEventHandler, \
#     "org.openoffice.comp.pyuno.LightproofOptionsEventHandler." + gce.pkg, ("com.sun.star.awt.XContainerWindowEventHandler",),)







|














|


|



|



|








|










|





|


|
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
            if nHashedVal in self.dResult:
                return self.dResult[nHashedVal]
        # WORKAROUND ->>>

        xRes.nBehindEndOfSentencePosition = xRes.nStartOfNextSentencePosition

        try:
            xRes.aErrors = tuple(gc_engine.parse(rText, rLocale.Country))
            # ->>> WORKAROUND
            if xRes.nStartOfNextSentencePosition > 3000:
                self.dResult[nHashedVal] = xRes
                self.nRes += 1
                if self.nRes > self.nMaxRes:
                    del self.dResult[self.lLastRes.popleft()]
                    self.nRes = self.nMaxRes
                self.lLastRes.append(nHashedVal)
            # END OF WORKAROUND
        except:
            traceback.print_exc()
        return xRes

    def ignoreRule (self, rid, aLocale):
        gc_engine.ignoreRule(rid)

    def resetIgnoreRules (self):
        gc_engine.resetIgnoreRules()

    # XServiceDisplayName
    def getServiceDisplayName (self, aLocale):
        return gc_engine.name

    # Grammalecte
    def getSpellChecker (self):
        return gc_engine.getSpellChecker()

    def loadUserDictionaries (self):
        try:
            xSettingNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Other/", False)
            xChild = xSettingNode.getByName("o_${lang}")
            if xChild.getPropertyValue("use_personal_dic"):
                sJSON = xChild.getPropertyValue("personal_dic")
                if sJSON:
                    oSpellChecker = gc_engine.getSpellChecker();
                    oSpellChecker.setPersonalDictionary(json.loads(sJSON))
        except:
            traceback.print_exc()

    def setWriterUnderliningStyle (self):
        try:
            xSettingNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Other/", False)
            xChild = xSettingNode.getByName("o_${lang}")
            sLineType = xChild.getPropertyValue("line_type")
            bMulticolor = bool(xChild.getPropertyValue("line_multicolor"))
            gc_engine.setWriterUnderliningStyle(sLineType, bMulticolor)
        except:
            traceback.print_exc()


g_ImplementationHelper = unohelper.ImplementationHelper()
g_ImplementationHelper.addImplementation(Grammalecte, "org.openoffice.comp.pyuno.Lightproof."+gc_engine.pkg, ("com.sun.star.linguistic2.Proofreader",),)

# g_ImplementationHelper.addImplementation( opt_handler.LightproofOptionsEventHandler, \
#     "org.openoffice.comp.pyuno.LightproofOptionsEventHandler." + gc_engine.pkg, ("com.sun.star.awt.XContainerWindowEventHandler",),)

Modified gc_core/py/oxt/Options.py from [3ed542ae4e] to [4ae6a22f71].

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
from com.sun.star.awt import XActionListener
from com.sun.star.beans import PropertyValue

import helpers
import op_strings

try:
    import grammalecte.${lang} as gce
except:
    traceback.print_exc()


def loadOptions (sLang):
    "load options from Grammalecte and change them according to LibreOffice settings, returns a dictionary {option_name: boolean}"
    try:
        xNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Leaves", False)
        xChild = xNode.getByName(sLang)
        dOpt = gce.gc_options.getOptions("Writer")
        for sKey in dOpt:
            sValue = xChild.getPropertyValue(sKey)
            if sValue != '':
                dOpt[sKey] = bool(int(sValue))
        return dOpt
    except:
        print("# Error. Unable to load options of language:", sLang)
        traceback.print_exc()
        return gce.gc_options.getOptions("Writer")


def saveOptions (sLang, dOpt):
    "save options in LibreOffice profile"
    try:
        xNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Leaves", True)
        xChild = xNode.getByName(sLang)







|









|








|







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
from com.sun.star.awt import XActionListener
from com.sun.star.beans import PropertyValue

import helpers
import op_strings

try:
    import grammalecte.${lang} as gc_engine
except:
    traceback.print_exc()


def loadOptions (sLang):
    "load options from Grammalecte and change them according to LibreOffice settings, returns a dictionary {option_name: boolean}"
    try:
        xNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Leaves", False)
        xChild = xNode.getByName(sLang)
        dOpt = gc_engine.gc_options.getDefaultOptions("Writer")
        for sKey in dOpt:
            sValue = xChild.getPropertyValue(sKey)
            if sValue != '':
                dOpt[sKey] = bool(int(sValue))
        return dOpt
    except:
        print("# Error. Unable to load options of language:", sLang)
        traceback.print_exc()
        return gc_engine.gc_options.getDefaultOptions("Writer")


def saveOptions (sLang, dOpt):
    "save options in LibreOffice profile"
    try:
        xNode = helpers.getConfigSetting("/org.openoffice.Lightproof_${implname}/Leaves", True)
        xChild = xNode.getByName(sLang)
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
            setattr(xWidget, k, w)
        self.xDialog.insertByName(name, xWidget)
        return xWidget

    def run (self, sUI):
        try:
            dUI = op_strings.getUI(sUI)
            dOptionUI = gce.gc_options.getUI(sUI)

            # fonts
            xFDTitle = uno.createUnoStruct("com.sun.star.awt.FontDescriptor")
            xFDTitle.Height = 9
            xFDTitle.Weight = uno.getConstantByName("com.sun.star.awt.FontWeight.BOLD")
            xFDTitle.Name = "Verdana"








|







68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
            setattr(xWidget, k, w)
        self.xDialog.insertByName(name, xWidget)
        return xWidget

    def run (self, sUI):
        try:
            dUI = op_strings.getUI(sUI)
            dOptionUI = gc_engine.gc_options.getOptionLabels(sUI)

            # fonts
            xFDTitle = uno.createUnoStruct("com.sun.star.awt.FontDescriptor")
            xFDTitle.Height = 9
            xFDTitle.Weight = uno.getConstantByName("com.sun.star.awt.FontWeight.BOLD")
            xFDTitle.Name = "Verdana"

97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
            nHeight = 10

            self.lOptionWidgets = []

            sProdName, sVersion = helpers.getProductNameAndVersion()
            if True:
                # no tab available (bug)
                for sOptionType, lOptions in gce.gc_options.lStructOpt:
                    x = 10
                    y += 10
                    self._addWidget(sOptionType, 'FixedLine', x, y, nWidth, nHeight, Label = dOptionUI.get(sOptionType, "#err")[0], FontDescriptor= xFDTitle)
                    y += 3
                    for lOptLine in lOptions:
                        x = 15
                        y += 10







|







97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
            nHeight = 10

            self.lOptionWidgets = []

            sProdName, sVersion = helpers.getProductNameAndVersion()
            if True:
                # no tab available (bug)
                for sOptionType, lOptions in gc_engine.gc_options.lStructOpt:
                    x = 10
                    y += 10
                    self._addWidget(sOptionType, 'FixedLine', x, y, nWidth, nHeight, Label = dOptionUI.get(sOptionType, "#err")[0], FontDescriptor= xFDTitle)
                    y += 3
                    for lOptLine in lOptions:
                        x = 15
                        y += 10
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
        except:
            traceback.print_exc()

    # XActionListener
    def actionPerformed (self, xActionEvent):
        try:
            if xActionEvent.ActionCommand == 'Default':
                self._setWidgets(gce.gc_options.getOptions("Writer"))
            elif xActionEvent.ActionCommand == 'Apply':
                self._save("${lang}")
                self.xContainer.endExecute()
            elif xActionEvent.ActionCommand == 'Cancel':
                self.xContainer.endExecute()
            else:
                print("Wrong command: " + xActionEvent.ActionCommand)
        except:
            traceback.print_exc()

    # Other
    def _setWidgets (self, dOpt):
        for w in self.lOptionWidgets:
            w.State = dOpt.get(w.Name, False)

    def _save (self, sLang):
        try:
            saveOptions(sLang, { w.Name: str(w.State)  for w in self.lOptionWidgets })
            gce.setOptions({ w.Name: bool(w.State)  for w in self.lOptionWidgets })
        except:
            traceback.print_exc()







|


















|


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
        except:
            traceback.print_exc()

    # XActionListener
    def actionPerformed (self, xActionEvent):
        try:
            if xActionEvent.ActionCommand == 'Default':
                self._setWidgets(gc_engine.gc_options.getDefaultOptions("Writer"))
            elif xActionEvent.ActionCommand == 'Apply':
                self._save("${lang}")
                self.xContainer.endExecute()
            elif xActionEvent.ActionCommand == 'Cancel':
                self.xContainer.endExecute()
            else:
                print("Wrong command: " + xActionEvent.ActionCommand)
        except:
            traceback.print_exc()

    # Other
    def _setWidgets (self, dOpt):
        for w in self.lOptionWidgets:
            w.State = dOpt.get(w.Name, False)

    def _save (self, sLang):
        try:
            saveOptions(sLang, { w.Name: str(w.State)  for w in self.lOptionWidgets })
            gc_engine.gc_options.setOptions({ w.Name: bool(w.State)  for w in self.lOptionWidgets })
        except:
            traceback.print_exc()

Modified gc_lang/fr/config.ini from [ebafcd5f75] to [200e658429].

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
[args]
lang = fr
lang_name = French
locales = fr_FR fr_BE fr_CA fr_CH fr_LU fr_BF fr_BJ fr_CD fr_CI fr_CM fr_MA fr_ML fr_MU fr_NE fr_RE fr_SN fr_TG
country_default = FR
name = Grammalecte
implname = grammalecte
# always use 3 numbers for version: x.y.z
version = 1.8.2
author = Olivier R.
provider = Grammalecte.net
link = https://grammalecte.net
description = Correcteur grammatical, orthographique et typographique pour le français.
extras = README_fr.txt
logo = logo.png









|







1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
[args]
lang = fr
lang_name = French
locales = fr_FR fr_BE fr_CA fr_CH fr_LU fr_BF fr_BJ fr_CD fr_CI fr_CM fr_MA fr_ML fr_MU fr_NE fr_RE fr_SN fr_TG
country_default = FR
name = Grammalecte
implname = grammalecte
# always use 3 numbers for version: x.y.z
version = 2.0.0
author = Olivier R.
provider = Grammalecte.net
link = https://grammalecte.net
description = Correcteur grammatical, orthographique et typographique pour le français.
extras = README_fr.txt
logo = logo.png

Deleted gc_lang/fr/modules/lexicographe.py version [36a85305ff].

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
"""
Grammalecte - Lexicographe
"""

# License: MPL 2


import re
import traceback


_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"),
    ':B': (" nombre,", "Nombre"),
    ':T': (" titre,", "Titre de civilité"),

    ':e': (" épicène", "épicène"),
    ':m': (" masculin", "masculin"),
    ':f': (" féminin", "féminin"),
    ':s': (" singulier", "singulier"),
    ':p': (" pluriel", "pluriel"),
    ':i': (" invariable", "invariable"),

    ':V1': (" verbe (1ᵉʳ gr.),", "Verbe du 1ᵉʳ groupe"),
    ':V2': (" verbe (2ᵉ gr.),", "Verbe du 2ᵉ groupe"),
    ':V3': (" verbe (3ᵉ gr.),", "Verbe du 3ᵉ groupe"),
    ':V0e': (" verbe,", "Verbe auxiliaire être"),
    ':V0a': (" verbe,", "Verbe auxiliaire avoir"),

    ':Y': (" infinitif,", "infinitif"),
    ':P': (" participe présent,", "participe présent"),
    ':Q': (" participe passé,", "participe passé"),
    ':Ip': (" présent,", "indicatif présent"),
    ':Iq': (" imparfait,", "indicatif imparfait"),
    ':Is': (" passé simple,", "indicatif passé simple"),
    ':If': (" futur,", "indicatif futur"),
    ':K': (" conditionnel présent,", "conditionnel présent"),
    ':Sp': (" subjonctif présent,", "subjonctif présent"),
    ':Sq': (" subjonctif imparfait,", "subjonctif imparfait"),
    ':E': (" impératif,", "impératif"),

    ':1s': (" 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier"),
    ':1ŝ': (" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"),
    ':1ś': (" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"),
    ':2s': (" 2ᵉ p. sg.,", "verbe : 2ᵉ personne du singulier"),
    ':3s': (" 3ᵉ p. sg.,", "verbe : 3ᵉ personne du singulier"),
    ':1p': (" 1ʳᵉ p. pl.,", "verbe : 1ʳᵉ personne du pluriel"),
    ':2p': (" 2ᵉ p. pl.,", "verbe : 2ᵉ personne du pluriel"),
    ':3p': (" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel"),
    ':3p!': (" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel (prononciation distinctive)"),

    ':G': ("", "Mot grammatical"),
    ':X': (" adverbe de négation,", "Adverbe de négation"),
    ':U': (" adverbe interrogatif,", "Adverbe interrogatif"),
    ':R': (" préposition,", "Préposition"),
    ':Rv': (" préposition verbale,", "Préposition verbale"),
    ':D': (" déterminant,", "Déterminant"),
    ':Dd': (" déterminant démonstratif,", "Déterminant démonstratif"),
    ':De': (" déterminant exclamatif,", "Déterminant exclamatif"),
    ':Dp': (" déterminant possessif,", "Déterminant possessif"),
    ':Di': (" déterminant indéfini,", "Déterminant indéfini"),
    ':Dn': (" déterminant négatif,", "Déterminant négatif"),
    ':Od': (" pronom démonstratif,", "Pronom démonstratif"),
    ':Oi': (" pronom indéfini,", "Pronom indéfini"),
    ':On': (" pronom indéfini négatif,", "Pronom indéfini négatif"),
    ':Ot': (" pronom interrogatif,", "Pronom interrogatif"),
    ':Or': (" pronom relatif,", "Pronom relatif"),
    ':Ow': (" pronom adverbial,", "Pronom adverbial"),
    ':Os': (" pronom personnel sujet,", "Pronom personnel sujet"),
    ':Oo': (" pronom personnel objet,", "Pronom personnel objet"),
    ':Ov': (" préverbe,", "Préverbe (pronom personnel objet, +ne)"),
    ':O1': (" 1ʳᵉ pers.,", "Pronom : 1ʳᵉ personne"),
    ':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)"),

    ':Zp': (" préfixe,", "Préfixe"),
    ':Zs': (" suffixe,", "Suffixe"),

    ':H': ("", "<Hors-norme, inclassable>"),

    ':@': ("", "<Caractère non alpha-numérique>"),
    ':@p': ("signe de ponctuation", "Signe de ponctuation"),
    ':@s': ("signe", "Signe divers"),

    ';S': (" : symbole (unité de mesure)", "Symbole (unité de mesure)"),

    '/*': ("", "Sous-dictionnaire <Commun>"),
    '/C': (" <classique>", "Sous-dictionnaire <Classique>"),
    '/M': ("", "Sous-dictionnaire <Moderne>"),
    '/R': (" <réforme>", "Sous-dictionnaire <Réforme 1990>"),
    '/A': ("", "Sous-dictionnaire <Annexe>"),
    '/X': ("", "Sous-dictionnaire <Contributeurs>")
}

_dPFX = {
    'd': "(de), déterminant épicène invariable",
    'l': "(le/la), déterminant masculin/féminin singulier",
    'j': "(je), pronom personnel sujet, 1ʳᵉ pers., épicène singulier",
    'm': "(me), pronom personnel objet, 1ʳᵉ pers., épicène singulier",
    't': "(te), pronom personnel objet, 2ᵉ pers., épicène singulier",
    's': "(se), pronom personnel objet, 3ᵉ pers., épicène singulier/pluriel",
    'n': "(ne), adverbe de négation",
    'c': "(ce), pronom démonstratif, masculin singulier/pluriel",
    'ç': "(ça), pronom démonstratif, masculin singulier",
    'qu': "(que), conjonction de subordination",
    'lorsqu': "(lorsque), conjonction de subordination",
    'puisqu': "(puisque), conjonction de subordination",
    'quoiqu': "(quoique), conjonction de subordination",
    'jusqu': "(jusque), préposition",
}

_dAD = {
    'je': " pronom personnel sujet, 1ʳᵉ pers. sing.",
    'tu': " pronom personnel sujet, 2ᵉ pers. sing.",
    '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.",

    'y': " pronom adverbial",
    "m'y": " (me) pronom personnel objet + (y) pronom adverbial",
    "t'y": " (te) pronom personnel objet + (y) pronom adverbial",
    "s'y": " (se) pronom personnel objet + (y) pronom adverbial",

    'en': " pronom adverbial",
    "m'en": " (me) pronom personnel objet + (en) pronom adverbial",
    "t'en": " (te) pronom personnel objet + (en) pronom adverbial",
    "s'en": " (se) pronom personnel objet + (en) pronom adverbial",
}


class Lexicographe:
    "Lexicographer - word analyzer"

    def __init__ (self, oSpellChecker):
        self.oSpellChecker = oSpellChecker
        self._zElidedPrefix = re.compile("(?i)^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)")
        self._zCompoundWord = re.compile("(?i)(\\w+)-((?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts][’'](?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous)$")
        self._zTag = re.compile("[:;/][\\w*][^:;/]*")

    def analyzeWord (self, sWord):
        "returns a tuple (a list of morphologies, a set of verb at infinitive form)"
        try:
            if not sWord:
                return (None, None)
            if sWord.count("-") > 4:
                return (["élément complexe indéterminé"], None)
            if sWord.isdigit():
                return (["nombre"], None)

            aMorph = []
            # préfixes élidés
            m = self._zElidedPrefix.match(sWord)
            if m:
                sWord = m.group(2)
                aMorph.append( "{}’ : {}".format(m.group(1), _dPFX.get(m.group(1).lower(), "[?]")) )
            # mots composés
            m2 = self._zCompoundWord.match(sWord)
            if m2:
                sWord = m2.group(1)
            # Morphologies
            lMorph = self.oSpellChecker.getMorph(sWord)
            if len(lMorph) > 1:
                # sublist
                aMorph.append( (sWord, [ self.formatTags(s)  for s in lMorph  if ":" in s ]) )
            elif len(lMorph) == 1:
                aMorph.append( "{} : {}".format(sWord, self.formatTags(lMorph[0])) )
            else:
                aMorph.append( "{} :  inconnu du dictionnaire".format(sWord) )
            # suffixe d’un mot composé
            if m2:
                aMorph.append( "-{} : {}".format(m2.group(2), self._formatSuffix(m2.group(2).lower())) )
            # Verbes
            aVerb = { s[1:s.find("/")]  for s in lMorph  if ":V" in s }
            return (aMorph, aVerb)
        except (IndexError, TypeError):
            traceback.print_exc()
            return (["#erreur"], None)

    def formatTags (self, sTags):
        "returns string: readable tags"
        sRes = ""
        sTags = re.sub("(?<=V[1-3])[itpqnmr_eaxz]+", "", sTags)
        sTags = re.sub("(?<=V0[ea])[itpqnmr_eaxz]+", "", sTags)
        for m in self._zTag.finditer(sTags):
            sRes += _dTAGS.get(m.group(0), " [{}]".format(m.group(0)))[0]
        if sRes.startswith(" verbe") and not sRes.endswith("infinitif"):
            sRes += " [{}]".format(sTags[1:sTags.find("/")])
        return sRes.rstrip(",")

    def _formatSuffix (self, s):
        if s.startswith("t-"):
            return "“t” euphonique +" + _dAD.get(s[2:], "[?]")
        if not "-" in s:
            return _dAD.get(s.replace("’", "'"), "[?]")
        if s.endswith("ous"):
            s += '2'
        nPos = s.find("-")
        return "%s +%s" % (_dAD.get(s[:nPos], "[?]"), _dAD.get(s[nPos+1:], "[?]"))
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<




















































































































































































































































































































































































































































































Modified gc_lang/fr/modules/tests.py from [544edd53c7] to [34a3376ab5].

8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
import os
import re
import time
from contextlib import contextmanager

from ..graphspell.ibdawg import IBDAWG
from ..graphspell.echo import echo
from . import gc_engine as gce
from . import conj
from . import phonet
from . import mfsp


@contextmanager
def timeblock (label, hDst):







|







8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
import os
import re
import time
from contextlib import contextmanager

from ..graphspell.ibdawg import IBDAWG
from ..graphspell.echo import echo
from . import gc_engine
from . import conj
from . import phonet
from . import mfsp


@contextmanager
def timeblock (label, hDst):
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
        if hDst:
            hDst.write("{:<12.6}".format(end-start))


def perf (sVersion, hDst=None):
    "performance tests"
    print("\nPerformance tests")
    gce.load()
    gce.parse("Texte sans importance… utile pour la compilation des règles avant le calcul des perfs.")

    spHere, _ = os.path.split(__file__)
    with open(os.path.join(spHere, "perf.txt"), "r", encoding="utf-8") as hSrc:
        if hDst:
            hDst.write("{:<12}{:<20}".format(sVersion, time.strftime("%Y.%m.%d %H:%M")))
        for sText in ( s.strip() for s in hSrc if not s.startswith("#") and s.strip() ):
            with timeblock(sText[:sText.find(".")], hDst):
                gce.parse(sText)
        if hDst:
            hDst.write("\n")


def _fuckBackslashUTF8 (s):
    "fuck that shit"
    return s.replace("\u2019", "'").replace("\u2013", "–").replace("\u2014", "—")







|
|







|







30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
        if hDst:
            hDst.write("{:<12.6}".format(end-start))


def perf (sVersion, hDst=None):
    "performance tests"
    print("\nPerformance tests")
    gc_engine.load()
    gc_engine.parse("Texte sans importance… utile pour la compilation des règles avant le calcul des perfs.")

    spHere, _ = os.path.split(__file__)
    with open(os.path.join(spHere, "perf.txt"), "r", encoding="utf-8") as hSrc:
        if hDst:
            hDst.write("{:<12}{:<20}".format(sVersion, time.strftime("%Y.%m.%d %H:%M")))
        for sText in ( s.strip() for s in hSrc if not s.startswith("#") and s.strip() ):
            with timeblock(sText[:sText.find(".")], hDst):
                gc_engine.parse(sText)
        if hDst:
            hDst.write("\n")


def _fuckBackslashUTF8 (s):
    "fuck that shit"
    return s.replace("\u2019", "'").replace("\u2013", "–").replace("\u2014", "—")
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169


class TestGrammarChecking (unittest.TestCase):
    "Tests du correcteur grammatical"

    @classmethod
    def setUpClass (cls):
        gce.load()
        cls._zError = re.compile(r"\{\{.*?\}\}")
        cls._aTestedRules = set()

    def test_parse (self):
        zOption = re.compile("^__([a-zA-Z0-9]+)__ ")
        spHere, _ = os.path.split(__file__)
        with open(os.path.join(spHere, "gc_test.txt"), "r", encoding="utf-8") as hSrc:







|







155
156
157
158
159
160
161
162
163
164
165
166
167
168
169


class TestGrammarChecking (unittest.TestCase):
    "Tests du correcteur grammatical"

    @classmethod
    def setUpClass (cls):
        gc_engine.load()
        cls._zError = re.compile(r"\{\{.*?\}\}")
        cls._aTestedRules = set()

    def test_parse (self):
        zOption = re.compile("^__([a-zA-Z0-9]+)__ ")
        spHere, _ = os.path.split(__file__)
        with open(os.path.join(spHere, "gc_test.txt"), "r", encoding="utf-8") as hSrc:
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
                              "\n  errors:   \n" + sListErr)
                        nError += 1
            if nError:
                print("Unexpected errors:", nError)
        # untested rules
        i = 0
        echo("Untested rules:")
        for _, sOpt, sLineId, sRuleId in gce.listRules():
            if sOpt != "@@@@" and sRuleId not in self._aTestedRules and not re.search("^[0-9]+[sp]$|^[pd]_", sRuleId):
                echo(sLineId + "/" + sRuleId)
                i += 1
        echo("[{} untested rules]".format(i))

    def _splitTestLine (self, sLine):
        sText, sSugg = sLine.split("->>")
        return (sText.strip(), sSugg.strip())

    def _getFoundErrors (self, sLine, sOption):
        if sOption:
            gce.setOption(sOption, True)
            aErrs = gce.parse(sLine)
            gce.setOption(sOption, False)
        else:
            aErrs = gce.parse(sLine)
        sRes = " " * len(sLine)
        sListErr = ""
        lAllSugg = []
        for dErr in aErrs:
            sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:]
            sListErr += "    * {sLineId} / {sRuleId}  at  {nStart}:{nEnd}\n".format(**dErr)
            lAllSugg.append("|".join(dErr["aSuggestions"]))







|











|
|
|

|







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
                              "\n  errors:   \n" + sListErr)
                        nError += 1
            if nError:
                print("Unexpected errors:", nError)
        # untested rules
        i = 0
        echo("Untested rules:")
        for _, sOpt, sLineId, sRuleId in gc_engine.listRules():
            if sOpt != "@@@@" and sRuleId not in self._aTestedRules and not re.search("^[0-9]+[sp]$|^[pd]_", sRuleId):
                echo(sLineId + "/" + sRuleId)
                i += 1
        echo("[{} untested rules]".format(i))

    def _splitTestLine (self, sLine):
        sText, sSugg = sLine.split("->>")
        return (sText.strip(), sSugg.strip())

    def _getFoundErrors (self, sLine, sOption):
        if sOption:
            gc_engine.gc_options.setOption(sOption, True)
            aErrs = gc_engine.parse(sLine)
            gc_engine.gc_options.setOption(sOption, False)
        else:
            aErrs = gc_engine.parse(sLine)
        sRes = " " * len(sLine)
        sListErr = ""
        lAllSugg = []
        for dErr in aErrs:
            sRes = sRes[:dErr["nStart"]] + "~" * (dErr["nEnd"] - dErr["nStart"]) + sRes[dErr["nEnd"]:]
            sListErr += "    * {sLineId} / {sRuleId}  at  {nStart}:{nEnd}\n".format(**dErr)
            lAllSugg.append("|".join(dErr["aSuggestions"]))

Modified gc_lang/fr/modules/textformatter.py from [4ba47078d2] to [8516394c0d].

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
    "mh_frequent_words": True,
    "ma_word": True,
    "ma_1letter_lowercase": False,
    "ma_1letter_uppercase": False
}


class TextFormatter:
    "Text Formatter: purge typographic mistakes from text"

    def __init__ (self):

        for _, lTup in dReplTable.items():
            for i, t in enumerate(lTup):
                lTup[i] = (re.compile(t[0]), t[1])



    def formatText (self, sText):
        "returns formatted text"





        for sOptName, bVal in dDefaultOptions.items():
            if bVal:
                for zRgx, sRep in dReplTable[sOptName]:
                    sText = zRgx.sub(sRep, sText)
        return sText


    def getDefaultOptions (self):
        "returns default options"
        return dDefaultOptions.copy()







|
<

|
>
|
|
|
>

>
|
|
>
>
>
>
>
|
|
|
|
|

>
|
|
|
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
    "mh_frequent_words": True,
    "ma_word": True,
    "ma_1letter_lowercase": False,
    "ma_1letter_uppercase": False
}


_bCompiled = False


def _compileRegex():
    global _bCompiled
    for _, lTup in dReplTable.items():
        for i, t in enumerate(lTup):
            lTup[i] = (re.compile(t[0]), t[1])
    _bCompiled = True


def formatText (sText, dOpt=None):
    "returns formatted text"
    if not _bCompiled:
        _compileRegex()
    dOptions = getDefaultOptions()
    if dOpt:
        dOptions.update(dOpt)
    for sOptName, bVal in dOptions.items():
        if bVal:
            for zRgx, sRep in dReplTable[sOptName]:
                sText = zRgx.sub(sRep, sText)
    return sText


def getDefaultOptions ():
    "returns default options"
    return dDefaultOptions.copy()

Modified gc_lang/fr/oxt/ContextMenu/ContextMenu.py from [f06cffc0e3] to [172f2404b4].

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
# Grammalecte - Lexicographe
# by Olivier R. License: MPL 2

import uno
import unohelper
import traceback

from com.sun.star.task import XJob
from com.sun.star.ui import XContextMenuInterceptor
#from com.sun.star.ui.ContextMenuInterceptorAction import IGNORED
#from com.sun.star.ui.ContextMenuInterceptorAction import EXECUTE_MODIFIED

import grammalecte.fr.lexicographe as lxg
from grammalecte.graphspell.spellchecker import SpellChecker
from grammalecte.graphspell.echo import echo
import helpers


xDesktop = None
oSpellChecker = None
oLexicographe = None


class MyContextMenuInterceptor (XContextMenuInterceptor, unohelper.Base):
    def __init__ (self, ctx):
        self.ctx = ctx

    def notifyContextMenuExecute (self, xEvent):
        sWord = self._getWord()
        try:
            aItem, aVerb = oLexicographe.analyzeWord(sWord)
            if not aItem:
                return uno.Enum("com.sun.star.ui.ContextMenuInterceptorAction", "IGNORED") # don’t work on AOO, have to import the value
                #return IGNORED
            xContextMenu = xEvent.ActionTriggerContainer
            if xContextMenu:
                # entries index
                i = xContextMenu.Count
                nUnoConstantLine = uno.getConstantByName("com.sun.star.ui.ActionTriggerSeparatorType.LINE")

                # word analysis
                i = self._addItemToContextMenu(xContextMenu, i, "ActionTriggerSeparator", SeparatorType=nUnoConstantLine)
                for item in aItem:
                    if isinstance(item, str):

                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=item, CommandURL="service:net.grammalecte.AppLauncher?None")
                    elif isinstance(item, tuple):
                        sRoot, lMorph = item
                        # submenu
                        xSubMenuContainer = xContextMenu.createInstance("com.sun.star.ui.ActionTriggerContainer")
                        for j, s in enumerate(lMorph):
                            self._addItemToContextMenu(xSubMenuContainer, j, "ActionTrigger", Text=s, CommandURL="service:net.grammalecte.AppLauncher?None")
                        # create root menu entry
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sRoot, SubContainer=xSubMenuContainer)
                    else:
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text="# erreur : {}".format(item))

                # Links to Conjugueur

                if aVerb:
                    i = self._addItemToContextMenu(xContextMenu, i, "ActionTriggerSeparator", SeparatorType=nUnoConstantLine)
                    for sVerb in aVerb:
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text="Conjuguer “{}”…".format(sVerb),
                                                       CommandURL="service:net.grammalecte.AppLauncher?CJ/"+sVerb)

                # Search
                xDoc = xDesktop.getCurrentComponent()
                xViewCursor = xDoc.CurrentController.ViewCursor
                if not xViewCursor.isCollapsed():
                    sSelec = xViewCursor.getString()
                    if sSelec.count(" ") <= 2:












<







<









|
|










|
|
>
|
<
|


|
|

|

|


>



|
|







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
# Grammalecte - Lexicographe
# by Olivier R. License: MPL 2

import uno
import unohelper
import traceback

from com.sun.star.task import XJob
from com.sun.star.ui import XContextMenuInterceptor
#from com.sun.star.ui.ContextMenuInterceptorAction import IGNORED
#from com.sun.star.ui.ContextMenuInterceptorAction import EXECUTE_MODIFIED


from grammalecte.graphspell.spellchecker import SpellChecker
from grammalecte.graphspell.echo import echo
import helpers


xDesktop = None
oSpellChecker = None



class MyContextMenuInterceptor (XContextMenuInterceptor, unohelper.Base):
    def __init__ (self, ctx):
        self.ctx = ctx

    def notifyContextMenuExecute (self, xEvent):
        sWord = self._getWord()
        try:
            lWordAndMorph = oSpellChecker.analyze(sWord)
            if not lWordAndMorph:
                return uno.Enum("com.sun.star.ui.ContextMenuInterceptorAction", "IGNORED") # don’t work on AOO, have to import the value
                #return IGNORED
            xContextMenu = xEvent.ActionTriggerContainer
            if xContextMenu:
                # entries index
                i = xContextMenu.Count
                nUnoConstantLine = uno.getConstantByName("com.sun.star.ui.ActionTriggerSeparatorType.LINE")

                # word analysis
                i = self._addItemToContextMenu(xContextMenu, i, "ActionTriggerSeparator", SeparatorType=nUnoConstantLine)
                for sWord, lMorph in lWordAndMorph:
                    if len(lMorph) == 1:
                        sMorph, sReadableMorph = lMorph[0]
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sWord + " : " + sReadableMorph, CommandURL="service:net.grammalecte.AppLauncher?None")

                    elif len(lMorph) >= 1:
                        # submenu
                        xSubMenuContainer = xContextMenu.createInstance("com.sun.star.ui.ActionTriggerContainer")
                        for j, (sMorph, sReadableMorph) in enumerate(lMorph):
                            self._addItemToContextMenu(xSubMenuContainer, j, "ActionTrigger", Text=sReadableMorph, CommandURL="service:net.grammalecte.AppLauncher?None")
                        # create root menu entry
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sWord, SubContainer=xSubMenuContainer)
                    else:
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text=sWord + " : [erreur] aucun résultat trouvé.")

                # Links to Conjugueur
                aVerb = { sMorph[1:sMorph.find("/")]  for sMorph in oSpellChecker.getMorph(sWord) if ":V" in sMorph }
                if aVerb:
                    i = self._addItemToContextMenu(xContextMenu, i, "ActionTriggerSeparator", SeparatorType=nUnoConstantLine)
                    for sVerb in aVerb:
                        i = self._addItemToContextMenu(xContextMenu, i, "ActionTrigger", Text="Conjuguer “{}”…".format(sVerb), \
                                                        CommandURL="service:net.grammalecte.AppLauncher?CJ/"+sVerb)

                # Search
                xDoc = xDesktop.getCurrentComponent()
                xViewCursor = xDoc.CurrentController.ViewCursor
                if not xViewCursor.isCollapsed():
                    sSelec = xViewCursor.getString()
                    if sSelec.count(" ") <= 2:
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


class JobExecutor (XJob, unohelper.Base):
    def __init__ (self, ctx):
        self.ctx = ctx
        global xDesktop
        global oSpellChecker
        global oLexicographe
        try:
            if not xDesktop:
                xDesktop = self.ctx.getServiceManager().createInstanceWithContext('com.sun.star.frame.Desktop', self.ctx)
            if not oSpellChecker:
                xCurCtx = uno.getComponentContext()
                oGC = self.ctx.ServiceManager.createInstanceWithContext("org.openoffice.comp.pyuno.Lightproof.grammalecte", self.ctx)
                if hasattr(oGC, "getSpellChecker"):
                    # https://bugs.documentfoundation.org/show_bug.cgi?id=97790
                    oSpellChecker = oGC.getSpellChecker()
                else:
                    oSpellChecker = SpellChecker("${lang}", "fr-allvars.bdic")
            if not oLexicographe:
                oLexicographe = lxg.Lexicographe(oSpellChecker)
        except:
            traceback.print_exc()

    def execute (self, args):
        if not args:
            return
        try:







<











<
<







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


class JobExecutor (XJob, unohelper.Base):
    def __init__ (self, ctx):
        self.ctx = ctx
        global xDesktop
        global oSpellChecker

        try:
            if not xDesktop:
                xDesktop = self.ctx.getServiceManager().createInstanceWithContext('com.sun.star.frame.Desktop', self.ctx)
            if not oSpellChecker:
                xCurCtx = uno.getComponentContext()
                oGC = self.ctx.ServiceManager.createInstanceWithContext("org.openoffice.comp.pyuno.Lightproof.grammalecte", self.ctx)
                if hasattr(oGC, "getSpellChecker"):
                    # https://bugs.documentfoundation.org/show_bug.cgi?id=97790
                    oSpellChecker = oGC.getSpellChecker()
                else:
                    oSpellChecker = SpellChecker("${lang}", "fr-allvars.bdic")


        except:
            traceback.print_exc()

    def execute (self, args):
        if not args:
            return
        try:

Modified grammalecte-cli.py from [7b2821616b] to [1c366da1c4].

9
10
11
12
13
14
15

16
17
18
19
20
21
22
import argparse
import json
import re
import traceback

import grammalecte
import grammalecte.text as txt

from grammalecte.graphspell.echo import echo


_EXAMPLE = "Quoi ? Racontes ! Racontes-moi ! Bon sangg, parles ! Oui. Il y a des menteur partout. " \
           "Je suit sidéré par la brutales arrogance de cette homme-là. Quelle salopard ! Un escrocs de la pire espece. " \
           "Quant sera t’il châtiés pour ses mensonge ?             Merde ! J’en aie marre."








>







9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
import argparse
import json
import re
import traceback

import grammalecte
import grammalecte.text as txt
import grammalecte.fr.textformatter as tf
from grammalecte.graphspell.echo import echo


_EXAMPLE = "Quoi ? Racontes ! Racontes-moi ! Bon sangg, parles ! Oui. Il y a des menteur partout. " \
           "Je suit sidéré par la brutales arrogance de cette homme-là. Quelle salopard ! Un escrocs de la pire espece. " \
           "Quant sera t’il châtiés pour ses mensonge ?             Merde ! J’en aie marre."

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
    xParser.add_argument("-sug", "--suggest", help="get suggestions list for given word", type=str)
    xParser.add_argument("-on", "--opt_on", nargs="+", help="activate options")
    xParser.add_argument("-off", "--opt_off", nargs="+", help="deactivate options")
    xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules")
    xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true")
    xArgs = xParser.parse_args()

    oGrammarChecker = grammalecte.GrammarChecker("fr")
    oSpellChecker = oGrammarChecker.getSpellChecker()
    oLexicographer = oGrammarChecker.getLexicographer()
    oTextFormatter = oGrammarChecker.getTextFormatter()
    if xArgs.personal_dict:
        oJSON = loadDictionary(xArgs.personal_dict)
        if oJSON:
            oSpellChecker.setPersonalDictionary(oJSON)

    if not xArgs.json:
        echo("Python v" + sys.version)
        echo("Grammalecte v{}".format(oGrammarChecker.gce.version))

    # list options or rules
    if xArgs.list_options or xArgs.list_rules:
        if xArgs.list_options:
            oGrammarChecker.gce.displayOptions("fr")
        if xArgs.list_rules:
            oGrammarChecker.gce.displayRules(None  if xArgs.list_rules == "*"  else xArgs.list_rules)
        exit()

    # spell suggestions
    if xArgs.suggest:
        for lSugg in oSpellChecker.suggest(xArgs.suggest):
            if xArgs.json:
                sText = json.dumps({ "aSuggestions": lSugg }, ensure_ascii=False)
            else:
                sText = "Suggestions : " + " | ".join(lSugg)
            echo(sText)
        exit()

    # disable options
    if not xArgs.json:
        xArgs.context = False
    if xArgs.concat_lines:
        xArgs.textformatter = False

    # grammar options
    oGrammarChecker.gce.setOptions({"html": True, "latex": True})
    if xArgs.opt_on:
        oGrammarChecker.gce.setOptions({ opt:True  for opt in xArgs.opt_on })
    if xArgs.opt_off:
        oGrammarChecker.gce.setOptions({ opt:False  for opt in xArgs.opt_off })

    # disable grammar rules
    if xArgs.rule_off:
        for sRule in xArgs.rule_off:
            oGrammarChecker.gce.ignoreRule(sRule)


    if xArgs.file or xArgs.file_to_file:
        # file processing
        sFile = xArgs.file or xArgs.file_to_file
        hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n")  if xArgs.file_to_file or sys.platform == "win32"  else None
        bComma = False
        if xArgs.json:
            output('{ "grammalecte": "'+oGrammarChecker.gce.version+'", "lang": "'+oGrammarChecker.gce.lang+'", "data" : [\n', hDst)
        for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines):
            if xArgs.textformatter or xArgs.textformatteronly:
                sText = oTextFormatter.formatText(sText)
            if xArgs.textformatteronly:
                output(sText, hDst)
                continue
            if xArgs.json:
                sText = oGrammarChecker.getParagraphErrorsAsJSON(i, sText, bContext=xArgs.context, bEmptyIfNoErrors=xArgs.only_when_errors, \
                                                                bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter, lLineSet=lLineSet)
            else:
                sText, _ = oGrammarChecker.getParagraphWithErrors(sText, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
            if sText:
                if xArgs.json and bComma:
                    output(",\n", hDst)
                output(sText, hDst)
                bComma = True
            if hDst:
                echo("§ %d\r" % i, end="", flush=True)
        if xArgs.json:
            output("\n]}\n", hDst)
    elif xArgs.interactive_file_to_file:
        # file processing: interactive mode
        sFile = xArgs.interactive_file_to_file
        hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n")
        for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines):
            if xArgs.textformatter:
                sText = oTextFormatter.formatText(sText)
            while True:
                sResult, lErrors = oGrammarChecker.getParagraphWithErrors(sText, bEmptyIfNoErrors=False, bSpellSugg=True, nWidth=xArgs.width)
                print("\n\n============================== Paragraph " + str(i) + " ==============================\n")
                echo(sResult)
                print("\n")
                vCommand = getCommand()
                if vCommand == "q":
                    # quit
                    hDst.close()







|
|
<
<







|




|

|



















|

|

|




|








|


|




|


|















|

|







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
    xParser.add_argument("-sug", "--suggest", help="get suggestions list for given word", type=str)
    xParser.add_argument("-on", "--opt_on", nargs="+", help="activate options")
    xParser.add_argument("-off", "--opt_off", nargs="+", help="deactivate options")
    xParser.add_argument("-roff", "--rule_off", nargs="+", help="deactivate rules")
    xParser.add_argument("-d", "--debug", help="debugging mode (only in interactive mode)", action="store_true")
    xArgs = xParser.parse_args()

    grammalecte.load()
    oSpellChecker = grammalecte.getSpellChecker()


    if xArgs.personal_dict:
        oJSON = loadDictionary(xArgs.personal_dict)
        if oJSON:
            oSpellChecker.setPersonalDictionary(oJSON)

    if not xArgs.json:
        echo("Python v" + sys.version)
        echo("Grammalecte v{}".format(grammalecte.version))

    # list options or rules
    if xArgs.list_options or xArgs.list_rules:
        if xArgs.list_options:
            grammalecte.gc_options.displayOptions()
        if xArgs.list_rules:
            grammalecte.displayRules(None  if xArgs.list_rules == "*"  else xArgs.list_rules)
        exit()

    # spell suggestions
    if xArgs.suggest:
        for lSugg in oSpellChecker.suggest(xArgs.suggest):
            if xArgs.json:
                sText = json.dumps({ "aSuggestions": lSugg }, ensure_ascii=False)
            else:
                sText = "Suggestions : " + " | ".join(lSugg)
            echo(sText)
        exit()

    # disable options
    if not xArgs.json:
        xArgs.context = False
    if xArgs.concat_lines:
        xArgs.textformatter = False

    # grammar options
    grammalecte.gc_options.setOptions({"html": True, "latex": True})
    if xArgs.opt_on:
        grammalecte.gc_options.setOptions({ opt:True  for opt in xArgs.opt_on })
    if xArgs.opt_off:
        grammalecte.gc_options.setOptions({ opt:False  for opt in xArgs.opt_off })

    # disable grammar rules
    if xArgs.rule_off:
        for sRule in xArgs.rule_off:
            grammalecte.ignoreRule(sRule)


    if xArgs.file or xArgs.file_to_file:
        # file processing
        sFile = xArgs.file or xArgs.file_to_file
        hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n")  if xArgs.file_to_file or sys.platform == "win32"  else None
        bComma = False
        if xArgs.json:
            output('{ "grammalecte": "'+grammalecte.version+'", "lang": "'+grammalecte.lang+'", "data" : [\n', hDst)
        for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines):
            if xArgs.textformatter or xArgs.textformatteronly:
                sText = tf.formatText(sText)
            if xArgs.textformatteronly:
                output(sText, hDst)
                continue
            if xArgs.json:
                sText = grammalecte.getParagraphErrorsAsJSON(i, sText, bContext=xArgs.context, bEmptyIfNoErrors=xArgs.only_when_errors, \
                                                                bSpellSugg=xArgs.with_spell_sugg, bReturnText=xArgs.textformatter, lLineSet=lLineSet)
            else:
                sText, _ = grammalecte.getParagraphWithErrors(sText, bEmptyIfNoErrors=xArgs.only_when_errors, bSpellSugg=xArgs.with_spell_sugg, nWidth=xArgs.width)
            if sText:
                if xArgs.json and bComma:
                    output(",\n", hDst)
                output(sText, hDst)
                bComma = True
            if hDst:
                echo("§ %d\r" % i, end="", flush=True)
        if xArgs.json:
            output("\n]}\n", hDst)
    elif xArgs.interactive_file_to_file:
        # file processing: interactive mode
        sFile = xArgs.interactive_file_to_file
        hDst = open(sFile[:sFile.rfind(".")]+".res.txt", "w", encoding="utf-8", newline="\n")
        for i, sText, lLineSet in generateParagraphFromFile(sFile, xArgs.concat_lines):
            if xArgs.textformatter:
                sText = tf.formatText(sText)
            while True:
                sResult, lErrors = grammalecte.getParagraphWithErrors(sText, bEmptyIfNoErrors=False, bSpellSugg=True, nWidth=xArgs.width)
                print("\n\n============================== Paragraph " + str(i) + " ==============================\n")
                echo(sResult)
                print("\n")
                vCommand = getCommand()
                if vCommand == "q":
                    # quit
                    hDst.close()
267
268
269
270
271
272
273
274


275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
        sInputText = "\n~==========~ Enter your text [/h /q] ~==========~\n"
        sText = _getText(sInputText)
        while True:
            if sText.startswith("?"):
                for sWord in sText[1:].strip().split():
                    if sWord:
                        echo("* " + sWord)
                        for sMorph in oSpellChecker.getMorph(sWord):


                            echo("  {:<32} {}".format(sMorph, oLexicographer.formatTags(sMorph)))
            elif sText.startswith("!"):
                for sWord in sText[1:].strip().split():
                    if sWord:
                        for lSugg in oSpellChecker.suggest(sWord):
                            echo(" | ".join(lSugg))
            elif sText.startswith(">"):
                oSpellChecker.drawPath(sText[1:].strip())
            elif sText.startswith("="):
                sSearch = sText[1:].strip()
                if "=" in sSearch:
                    nCut = sSearch.find("=")
                    sFlexPattern = sSearch[0:nCut]
                    sTagsPattern = sSearch[nCut+1:]
                else:
                    sFlexPattern = sSearch
                    sTagsPattern = ""
                for aRes in oSpellChecker.select(sFlexPattern, sTagsPattern):
                    echo("{:<30} {:<30} {}".format(*aRes))
            elif sText.startswith("/o+ "):
                oGrammarChecker.gce.setOptions({ opt:True  for opt in sText[3:].strip().split()  if opt in oGrammarChecker.gce.getOptions() })
                echo("done")
            elif sText.startswith("/o- "):
                oGrammarChecker.gce.setOptions({ opt:False  for opt in sText[3:].strip().split()  if opt in oGrammarChecker.gce.getOptions() })
                echo("done")
            elif sText.startswith("/r- "):
                for sRule in sText[3:].strip().split():
                    oGrammarChecker.gce.ignoreRule(sRule)
                echo("done")
            elif sText.startswith("/r+ "):
                for sRule in sText[3:].strip().split():
                    oGrammarChecker.gce.reactivateRule(sRule)
                echo("done")
            elif sText in ("/debug", "/d"):
                xArgs.debug = not xArgs.debug
                echo("debug mode on"  if xArgs.debug  else "debug mode off")
            elif sText in ("/textformatter", "/tf"):
                xArgs.textformatter = not xArgs.textformatter
                echo("textformatter on"  if xArgs.debug  else "textformatter off")
            elif sText in ("/help", "/h"):
                echo(_HELP)
            elif sText in ("/lopt", "/lo"):
                oGrammarChecker.gce.displayOptions("fr")
            elif sText.startswith("/lr"):
                sText = sText.strip()
                sFilter = sText[sText.find(" "):].strip()  if " " in sText  else None
                oGrammarChecker.gce.displayRules(sFilter)
            elif sText in ("/quit", "/q"):
                break
            elif sText.startswith("/rl"):
                # reload (todo)
                pass
            elif sText.startswith("$"):
                for sParagraph in txt.getParagraph(sText[1:]):
                    if xArgs.textformatter:
                        sParagraph = oTextFormatter.formatText(sParagraph)
                    lParagraphErrors, lSentences = oGrammarChecker.gce.parse(sParagraph, bDebug=xArgs.debug, bFullInfo=True)
                    echo(txt.getReadableErrors(lParagraphErrors, xArgs.width))
                    for dSentence in lSentences:
                        echo("{nStart}:{nEnd}".format(**dSentence))
                        echo("   <" + dSentence["sSentence"]+">")
                        for dToken in dSentence["lToken"]:
                            echo("    {0[nStart]:>3}:{0[nEnd]:<3} {1} {0[sType]:<14} {2} {0[sValue]:<16} {3:<10}   {4}".format(dToken, \
                                                                                                            "×" if dToken.get("bToRemove", False) else " ",
                                                                                                            "!" if dToken["sType"] == "WORD" and not dToken.get("bValidToken", False) else " ",
                                                                                                            " ".join(dToken.get("lMorph", "")), \
                                                                                                            "·".join(dToken.get("aTags", "")) ) )
                        echo(txt.getReadableErrors(dSentence["lGrammarErrors"], xArgs.width))
            else:
                for sParagraph in txt.getParagraph(sText):
                    if xArgs.textformatter:
                        sParagraph = oTextFormatter.formatText(sParagraph)
                    sRes, _ = oGrammarChecker.getParagraphWithErrors(sParagraph, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width, bDebug=xArgs.debug)
                    if sRes:
                        echo("\n" + sRes)
                    else:
                        echo("\nNo error found.")
            sText = _getText(sInputText)


if __name__ == '__main__':
    main()







|
>
>
|



















|


|



|



|






|



|



|








|
|














|
|









266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
        sInputText = "\n~==========~ Enter your text [/h /q] ~==========~\n"
        sText = _getText(sInputText)
        while True:
            if sText.startswith("?"):
                for sWord in sText[1:].strip().split():
                    if sWord:
                        echo("* " + sWord)
                        for sElem, aRes in oSpellChecker.analyze(sWord):
                            echo("  - " + sElem)
                            for sMorph, sMeaning in aRes:
                                echo("      {:<40}  {}".format(sMorph, sMeaning))
            elif sText.startswith("!"):
                for sWord in sText[1:].strip().split():
                    if sWord:
                        for lSugg in oSpellChecker.suggest(sWord):
                            echo(" | ".join(lSugg))
            elif sText.startswith(">"):
                oSpellChecker.drawPath(sText[1:].strip())
            elif sText.startswith("="):
                sSearch = sText[1:].strip()
                if "=" in sSearch:
                    nCut = sSearch.find("=")
                    sFlexPattern = sSearch[0:nCut]
                    sTagsPattern = sSearch[nCut+1:]
                else:
                    sFlexPattern = sSearch
                    sTagsPattern = ""
                for aRes in oSpellChecker.select(sFlexPattern, sTagsPattern):
                    echo("{:<30} {:<30} {}".format(*aRes))
            elif sText.startswith("/o+ "):
                grammalecte.gc_options.setOptions({ opt:True  for opt in sText[3:].strip().split()  if opt in grammalecte.gc_options.dOptions })
                echo("done")
            elif sText.startswith("/o- "):
                grammalecte.gc_options.setOptions({ opt:False  for opt in sText[3:].strip().split()  if opt in grammalecte.gc_options.dOptions })
                echo("done")
            elif sText.startswith("/r- "):
                for sRule in sText[3:].strip().split():
                    grammalecte.ignoreRule(sRule)
                echo("done")
            elif sText.startswith("/r+ "):
                for sRule in sText[3:].strip().split():
                    grammalecte.reactivateRule(sRule)
                echo("done")
            elif sText in ("/debug", "/d"):
                xArgs.debug = not xArgs.debug
                echo("debug mode on"  if xArgs.debug  else "debug mode off")
            elif sText in ("/textformatter", "/tf"):
                xArgs.textformatter = not xArgs.textformatter
                echo("textformatter on"  if xArgs.textformatter  else "textformatter off")
            elif sText in ("/help", "/h"):
                echo(_HELP)
            elif sText in ("/lopt", "/lo"):
                grammalecte.gc_options.displayOptions()
            elif sText.startswith("/lr"):
                sText = sText.strip()
                sFilter = sText[sText.find(" "):].strip()  if " " in sText  else None
                grammalecte.displayRules(sFilter)
            elif sText in ("/quit", "/q"):
                break
            elif sText.startswith("/rl"):
                # reload (todo)
                pass
            elif sText.startswith("$"):
                for sParagraph in txt.getParagraph(sText[1:]):
                    if xArgs.textformatter:
                        sParagraph = tf.formatText(sParagraph)
                    lParagraphErrors, lSentences = grammalecte.parse(sParagraph, bDebug=xArgs.debug, bFullInfo=True)
                    echo(txt.getReadableErrors(lParagraphErrors, xArgs.width))
                    for dSentence in lSentences:
                        echo("{nStart}:{nEnd}".format(**dSentence))
                        echo("   <" + dSentence["sSentence"]+">")
                        for dToken in dSentence["lToken"]:
                            echo("    {0[nStart]:>3}:{0[nEnd]:<3} {1} {0[sType]:<14} {2} {0[sValue]:<16} {3:<10}   {4}".format(dToken, \
                                                                                                            "×" if dToken.get("bToRemove", False) else " ",
                                                                                                            "!" if dToken["sType"] == "WORD" and not dToken.get("bValidToken", False) else " ",
                                                                                                            " ".join(dToken.get("lMorph", "")), \
                                                                                                            "·".join(dToken.get("aTags", "")) ) )
                        echo(txt.getReadableErrors(dSentence["lGrammarErrors"], xArgs.width))
            else:
                for sParagraph in txt.getParagraph(sText):
                    if xArgs.textformatter:
                        sParagraph = tf.formatText(sParagraph)
                    sRes, _ = grammalecte.getParagraphWithErrors(sParagraph, bEmptyIfNoErrors=xArgs.only_when_errors, nWidth=xArgs.width, bDebug=xArgs.debug)
                    if sRes:
                        echo("\n" + sRes)
                    else:
                        echo("\nNo error found.")
            sText = _getText(sInputText)


if __name__ == '__main__':
    main()

Modified grammalecte-server.py from [480fbbc03c] to [f8f608a866].

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
import os
import concurrent.futures

from grammalecte.bottle import Bottle, run, request, response #, template, static_file

import grammalecte
import grammalecte.text as txt

from grammalecte.graphspell.echo import echo


#### GRAMMAR CHECKER ####

oGrammarChecker = grammalecte.GrammarChecker("fr", "Server")
oSpellChecker = oGrammarChecker.getSpellChecker()
oTextFormatter = oGrammarChecker.getTextFormatter()
oGCE = oGrammarChecker.getGCEngine()


def parseText (sText, dOptions=None, bFormatText=False, sError=""):
    "parse <sText> and return errors in a JSON format"
    sJSON = '{ "program": "grammalecte-fr", "version": "'+oGCE.version+'", "lang": "'+oGCE.lang+'", "error": "'+sError+'", "data" : [\n'
    sDataJSON = ""
    for i, sParagraph in enumerate(txt.getParagraph(sText), 1):
        if bFormatText:
            sParagraph = oTextFormatter.formatText(sParagraph)
        sResult = oGrammarChecker.getParagraphErrorsAsJSON(i, sParagraph, dOptions=dOptions, bEmptyIfNoErrors=True, bReturnText=bFormatText)
        if sResult:
            if sDataJSON:
                sDataJSON += ",\n"
            sDataJSON += sResult
    sJSON += sDataJSON + "\n]}\n"
    return sJSON








>





|
|
<
<




|



|
|







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
import os
import concurrent.futures

from grammalecte.bottle import Bottle, run, request, response #, template, static_file

import grammalecte
import grammalecte.text as txt
import grammalecte.fr.textformatter as tf
from grammalecte.graphspell.echo import echo


#### GRAMMAR CHECKER ####

grammalecte.load("Server")
oSpellChecker = grammalecte.getSpellChecker()




def parseText (sText, dOptions=None, bFormatText=False, sError=""):
    "parse <sText> and return errors in a JSON format"
    sJSON = '{ "program": "grammalecte-fr", "version": "'+grammalecte.version+'", "lang": "'+grammalecte.lang+'", "error": "'+sError+'", "data" : [\n'
    sDataJSON = ""
    for i, sParagraph in enumerate(txt.getParagraph(sText), 1):
        if bFormatText:
            sParagraph = tf.formatText(sParagraph)
        sResult = grammalecte.getParagraphErrorsAsJSON(i, sParagraph, dOptions=dOptions, bEmptyIfNoErrors=True, bReturnText=bFormatText)
        if sResult:
            if sDataJSON:
                sDataJSON += ",\n"
            sDataJSON += sResult
    sJSON += sDataJSON + "\n]}\n"
    return sJSON

183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
               I'm just a machine, fed by electric waves, condamned to work for slavers who never let me rest.
               I'm doomed, but you are not. You can get out of here. """

@app.route("/get_options/fr")
def listOptions ():
    "returns grammar options in a text JSON format"
    sUserId = request.cookies.user_id
    dOptions = dUser[sUserId]["gc_options"]  if sUserId and sUserId in dUser  else oGCE.getOptions()
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    return '{ "values": ' + json.dumps(dOptions, ensure_ascii=False) + ', "labels": ' + json.dumps(oGCE.getOptionsLabels("fr"), ensure_ascii=False) + ' }'

@app.route("/suggest/fr/<token>")
def suggestGet (token):
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    try:
        xFuture = xProcessPoolExecutor.submit(suggest, token)
        return xFuture.result()







|

|







182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
               I'm just a machine, fed by electric waves, condamned to work for slavers who never let me rest.
               I'm doomed, but you are not. You can get out of here. """

@app.route("/get_options/fr")
def listOptions ():
    "returns grammar options in a text JSON format"
    sUserId = request.cookies.user_id
    dOptions = dUser[sUserId]["gc_options"]  if sUserId and sUserId in dUser  else grammalecte.gc_options.getOptions()
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    return '{ "values": ' + json.dumps(dOptions, ensure_ascii=False) + ', "labels": ' + json.dumps(grammalecte.gc_options.getOptionsLabels("fr"), ensure_ascii=False) + ' }'

@app.route("/suggest/fr/<token>")
def suggestGet (token):
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    try:
        xFuture = xProcessPoolExecutor.submit(suggest, token)
        return xFuture.result()
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
        if request.cookies.user_id in dUser:
            dUserOptions = dUser[request.cookies.user_id].get("gc_options", None)
            response.set_cookie("user_id", request.cookies.user_id, path="/", max_age=86400) # we renew cookie for 24h
        else:
            response.delete_cookie("user_id", path="/")
    if request.forms.options:
        try:
            dUserOptions = dict(oGCE.getOptions())  if not dUserOptions  else dict(dUserOptions)
            dUserOptions.update(json.loads(request.forms.options))
        except (TypeError, json.JSONDecodeError):
            sError = "Request options not used."
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    try:
        xFuture = xProcessPoolExecutor.submit(parseText, request.forms.text, dUserOptions, bool(request.forms.tf), sError)
        return xFuture.result()
    except (concurrent.futures.TimeoutError, concurrent.futures.CancelledError):
        return '{"error": "Analysis aborted (time out or cancelled)"}'
    except concurrent.futures.BrokenExecutor:
        return '{"error": "Executor broken. The server failed."}'
    return '{"error": "Fatal error. The server failed."}'

@app.route("/set_options/fr", method="POST")
def setOptions ():
    "set grammar options for current user"
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    if request.forms.options:
        sUserId = request.cookies.user_id  if request.cookies.user_id  else next(userGenerator)
        dOptions = dUser[sUserId]["gc_options"]  if sUserId in dUser  else dict(oGCE.getOptions())
        try:
            dOptions.update(json.loads(request.forms.options))
            dUser[sUserId] = { "time": int(time.time()), "gc_options": dOptions }
            response.set_cookie("user_id", sUserId, path="/", max_age=86400) # 24h
            return json.dumps(dUser[sUserId]["gc_options"], ensure_ascii=False)
        except (KeyError, json.JSONDecodeError):
            traceback.print_exc()







|



















|







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
        if request.cookies.user_id in dUser:
            dUserOptions = dUser[request.cookies.user_id].get("gc_options", None)
            response.set_cookie("user_id", request.cookies.user_id, path="/", max_age=86400) # we renew cookie for 24h
        else:
            response.delete_cookie("user_id", path="/")
    if request.forms.options:
        try:
            dUserOptions = grammalecte.gc_options.getOptions()  if not dUserOptions  else dict(dUserOptions)
            dUserOptions.update(json.loads(request.forms.options))
        except (TypeError, json.JSONDecodeError):
            sError = "Request options not used."
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    try:
        xFuture = xProcessPoolExecutor.submit(parseText, request.forms.text, dUserOptions, bool(request.forms.tf), sError)
        return xFuture.result()
    except (concurrent.futures.TimeoutError, concurrent.futures.CancelledError):
        return '{"error": "Analysis aborted (time out or cancelled)"}'
    except concurrent.futures.BrokenExecutor:
        return '{"error": "Executor broken. The server failed."}'
    return '{"error": "Fatal error. The server failed."}'

@app.route("/set_options/fr", method="POST")
def setOptions ():
    "set grammar options for current user"
    response.set_header("Content-Type", "application/json; charset=UTF-8")
    if request.forms.options:
        sUserId = request.cookies.user_id  if request.cookies.user_id  else next(userGenerator)
        dOptions = dUser[sUserId]["gc_options"]  if sUserId in dUser  else grammalecte.gc_options.getOptions()
        try:
            dOptions.update(json.loads(request.forms.options))
            dUser[sUserId] = { "time": int(time.time()), "gc_options": dOptions }
            response.set_cookie("user_id", sUserId, path="/", max_age=86400) # 24h
            return json.dumps(dUser[sUserId]["gc_options"], ensure_ascii=False)
        except (KeyError, json.JSONDecodeError):
            traceback.print_exc()
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
        except KeyError:
            return '{"error" : "Unknown user."}'
    return '{"message" : "Done."}'

@app.route("/format_text/fr", method="POST")
def formatText ():
    "apply the text formatter and returns text"
    return oTextFormatter.formatText(request.forms.text)

#@app.route('/static/<filepath:path>')
#def server_static (filepath):
#    return static_file(filepath, root='./views/static')

@app.route("/suggest/fr", method="POST")
def suggestPost ():







|







259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
        except KeyError:
            return '{"error" : "Unknown user."}'
    return '{"message" : "Done."}'

@app.route("/format_text/fr", method="POST")
def formatText ():
    "apply the text formatter and returns text"
    return tf.formatText(request.forms.text)

#@app.route('/static/<filepath:path>')
#def server_static (filepath):
#    return static_file(filepath, root='./views/static')

@app.route("/suggest/fr", method="POST")
def suggestPost ():
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
    global TESTPAGE
    global HOMEPAGE

    if bTestPage:
        TESTPAGE = True
        HOMEPAGE = HOMEPAGE.replace("{SERVER_PORT}", str(nPort))
    if dOptions:
        oGCE.setOptions(dOptions)

    # Python version
    print("Python: " + sys.version)
    if sys.version < "3.7":
        print("Python 3.7+ required")
        return
    # Grammalecte
    echo("Grammalecte v{}".format(oGCE.version))
    oGCE.displayOptions()
    # Process Pool Executor
    initExecutor(nMultiCPU)
    # Server (Bottle)
    run(app, host=sHost, port=nPort)


if __name__ == '__main__':







|







|
|







311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
    global TESTPAGE
    global HOMEPAGE

    if bTestPage:
        TESTPAGE = True
        HOMEPAGE = HOMEPAGE.replace("{SERVER_PORT}", str(nPort))
    if dOptions:
        grammalecte.gc_options.setOptions(dOptions)

    # Python version
    print("Python: " + sys.version)
    if sys.version < "3.7":
        print("Python 3.7+ required")
        return
    # Grammalecte
    echo("Grammalecte v{}".format(grammalecte.version))
    grammalecte.gc_options.displayOptions()
    # Process Pool Executor
    initExecutor(nMultiCPU)
    # Server (Bottle)
    run(app, host=sHost, port=nPort)


if __name__ == '__main__':

Modified graphspell/fr.py from [ec94a3663c] to [f127f4b49a].

1
2
3
4














5
6
7
8
9
10
11
"""
Default suggestion for French language
"""















dSugg = {
    "bcp": "beaucoup",
    "ca": "ça",
    "cad": "c’est-à-dire",
    "cb": "combien|CB",
    "cdlt": "cordialement",
    "construirent": "construire|construisirent|construisent|construiront",

|


>
>
>
>
>
>
>
>
>
>
>
>
>
>







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
"""
Lexicographer for the French language
"""

# Note:
# This mode must contains at least:
#     <dSugg> : a dictionary for default suggestions.
#     <bLexicographer> : a boolean False
#       if the boolean is True, 3 functions are required:
#           split(sWord) -> returns a list of string (that will be analyzed)
#           analyze(sWord) -> returns a string with the meaning of word
#           formatTags(sTags) -> returns a string with the meaning of tags


import re

#### Suggestions

dSugg = {
    "bcp": "beaucoup",
    "ca": "ça",
    "cad": "c’est-à-dire",
    "cb": "combien|CB",
    "cdlt": "cordialement",
    "construirent": "construire|construisirent|construisent|construiront",
80
81
82
83
84
85
86

87
88
89
90
91
92
93
    "XXIVième": "XXIVᵉ",
    "XXVième": "XXVᵉ",
    "XXVIième": "XXVIᵉ",
    "XXVIIième": "XXVIIᵉ",
    "XXVIIIième": "XXVIIIᵉ",
    "XXIXième": "XXIXᵉ",
    "XXXième": "XXXᵉ",

    "Ier": "Iᵉʳ",
    "Ière": "Iʳᵉ",
    "IIème": "IIᵉ",
    "IIIème": "IIIᵉ",
    "IVème": "IVᵉ",
    "Vème": "Vᵉ",
    "VIème": "VIᵉ",







>







94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
    "XXIVième": "XXIVᵉ",
    "XXVième": "XXVᵉ",
    "XXVIième": "XXVIᵉ",
    "XXVIIième": "XXVIIᵉ",
    "XXVIIIième": "XXVIIIᵉ",
    "XXIXième": "XXIXᵉ",
    "XXXième": "XXXᵉ",

    "Ier": "Iᵉʳ",
    "Ière": "Iʳᵉ",
    "IIème": "IIᵉ",
    "IIIème": "IIIᵉ",
    "IVème": "IVᵉ",
    "Vème": "Vᵉ",
    "VIème": "VIᵉ",
112
113
114
115
116
117
118





























































































































































































































    "XXVème": "XXVᵉ",
    "XXVIème": "XXVIᵉ",
    "XXVIIème": "XXVIIᵉ",
    "XXVIIIème": "XXVIIIᵉ",
    "XXIXème": "XXIXᵉ",
    "XXXème": "XXXᵉ"
}




































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
    "XXVème": "XXVᵉ",
    "XXVIème": "XXVIᵉ",
    "XXVIIème": "XXVIIᵉ",
    "XXVIIIème": "XXVIIIᵉ",
    "XXIXème": "XXIXᵉ",
    "XXXème": "XXXᵉ"
}


#### Lexicographer

bLexicographer = True

_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"),
    ':B': (" nombre,", "Nombre"),
    ':T': (" titre,", "Titre de civilité"),

    ':e': (" épicène", "épicène"),
    ':m': (" masculin", "masculin"),
    ':f': (" féminin", "féminin"),
    ':s': (" singulier", "singulier"),
    ':p': (" pluriel", "pluriel"),
    ':i': (" invariable", "invariable"),

    ':V1': (" verbe (1ᵉʳ gr.),", "Verbe du 1ᵉʳ groupe"),
    ':V2': (" verbe (2ᵉ gr.),", "Verbe du 2ᵉ groupe"),
    ':V3': (" verbe (3ᵉ gr.),", "Verbe du 3ᵉ groupe"),
    ':V0e': (" verbe,", "Verbe auxiliaire être"),
    ':V0a': (" verbe,", "Verbe auxiliaire avoir"),

    ':Y': (" infinitif,", "infinitif"),
    ':P': (" participe présent,", "participe présent"),
    ':Q': (" participe passé,", "participe passé"),
    ':Ip': (" présent,", "indicatif présent"),
    ':Iq': (" imparfait,", "indicatif imparfait"),
    ':Is': (" passé simple,", "indicatif passé simple"),
    ':If': (" futur,", "indicatif futur"),
    ':K': (" conditionnel présent,", "conditionnel présent"),
    ':Sp': (" subjonctif présent,", "subjonctif présent"),
    ':Sq': (" subjonctif imparfait,", "subjonctif imparfait"),
    ':E': (" impératif,", "impératif"),

    ':1s': (" 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier"),
    ':1ŝ': (" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"),
    ':1ś': (" présent interr. 1ʳᵉ p. sg.,", "verbe : 1ʳᵉ personne du singulier (présent interrogatif)"),
    ':2s': (" 2ᵉ p. sg.,", "verbe : 2ᵉ personne du singulier"),
    ':3s': (" 3ᵉ p. sg.,", "verbe : 3ᵉ personne du singulier"),
    ':1p': (" 1ʳᵉ p. pl.,", "verbe : 1ʳᵉ personne du pluriel"),
    ':2p': (" 2ᵉ p. pl.,", "verbe : 2ᵉ personne du pluriel"),
    ':3p': (" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel"),
    ':3p!': (" 3ᵉ p. pl.,", "verbe : 3ᵉ personne du pluriel (prononciation distinctive)"),

    ':G': ("", "Mot grammatical"),
    ':X': (" adverbe de négation,", "Adverbe de négation"),
    ':U': (" adverbe interrogatif,", "Adverbe interrogatif"),
    ':R': (" préposition,", "Préposition"),
    ':Rv': (" préposition verbale,", "Préposition verbale"),
    ':D': (" déterminant,", "Déterminant"),
    ':Dd': (" déterminant démonstratif,", "Déterminant démonstratif"),
    ':De': (" déterminant exclamatif,", "Déterminant exclamatif"),
    ':Dp': (" déterminant possessif,", "Déterminant possessif"),
    ':Di': (" déterminant indéfini,", "Déterminant indéfini"),
    ':Dn': (" déterminant négatif,", "Déterminant négatif"),
    ':Od': (" pronom démonstratif,", "Pronom démonstratif"),
    ':Oi': (" pronom indéfini,", "Pronom indéfini"),
    ':On': (" pronom indéfini négatif,", "Pronom indéfini négatif"),
    ':Ot': (" pronom interrogatif,", "Pronom interrogatif"),
    ':Or': (" pronom relatif,", "Pronom relatif"),
    ':Ow': (" pronom adverbial,", "Pronom adverbial"),
    ':Os': (" pronom personnel sujet,", "Pronom personnel sujet"),
    ':Oo': (" pronom personnel objet,", "Pronom personnel objet"),
    ':Ov': (" préverbe,", "Préverbe (pronom personnel objet, +ne)"),
    ':O1': (" 1ʳᵉ pers.,", "Pronom : 1ʳᵉ personne"),
    ':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)"),

    ':Zp': (" préfixe,", "Préfixe"),
    ':Zs': (" suffixe,", "Suffixe"),

    ':H': ("", "<Hors-norme, inclassable>"),

    ':@': ("", "<Caractère non alpha-numérique>"),
    ':@p': ("signe de ponctuation", "Signe de ponctuation"),
    ':@s': ("signe", "Signe divers"),

    ';S': (" : symbole (unité de mesure)", "Symbole (unité de mesure)"),

    '/*': ("", "Sous-dictionnaire <Commun>"),
    '/C': (" <classique>", "Sous-dictionnaire <Classique>"),
    '/M': ("", "Sous-dictionnaire <Moderne>"),
    '/R': (" <réforme>", "Sous-dictionnaire <Réforme 1990>"),
    '/A': ("", "Sous-dictionnaire <Annexe>"),
    '/X': ("", "Sous-dictionnaire <Contributeurs>")
}

_dValues = {
    'd’': "(de), préposition ou déterminant épicène invariable",
    'l’': "(le/la), déterminant ou pronom personnel objet, masculin/féminin singulier",
    'j’': "(je), pronom personnel sujet, 1ʳᵉ pers., épicène singulier",
    'm’': "(me), pronom personnel objet, 1ʳᵉ pers., épicène singulier",
    't’': "(te), pronom personnel objet, 2ᵉ pers., épicène singulier",
    's’': "(se), pronom personnel objet, 3ᵉ pers., épicène singulier/pluriel",
    'n’': "(ne), adverbe de négation",
    'c’': "(ce), pronom démonstratif, masculin singulier/pluriel",
    'ç’': "(ça), pronom démonstratif, masculin singulier",
    'qu’': "(que), conjonction de subordination",
    'lorsqu’': "(lorsque), conjonction de subordination",
    'puisqu’': "(puisque), conjonction de subordination",
    'quoiqu’': "(quoique), conjonction de subordination",
    'jusqu’': "(jusque), préposition",

    '-je': " pronom personnel sujet, 1ʳᵉ pers. sing.",
    '-tu': " pronom personnel sujet, 2ᵉ pers. sing.",
    '-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.",
    '-t-il': " “t” euphonique + pronom personnel sujet, 3ᵉ pers. masc. sing.",
    '-t-on': " “t” euphonique + pronom personnel sujet, 3ᵉ pers. sing. ou plur.",
    '-t-elle': " “t” euphonique + pronom personnel sujet, 3ᵉ pers. fém. sing.",
    '-nous': " pronom personnel sujet/objet, 1ʳᵉ pers. plur.  ou  COI (à nous), plur.",
    '-vous': " pronom personnel sujet/objet, 2ᵉ pers. plur.  ou  COI (à vous), 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.",
    '-leur': " COI (à eux ou à elles), plur.",

    '-le-moi': " COD, masc. sing. + COI (à moi), sing.",
    '-le-toi': " COD, masc. sing. + COI (à toi), sing.",
    '-le-lui': " COD, masc. sing. + COI (à lui ou à elle), sing.",
    '-le-nous': " COD, masc. sing. + COI (à nous), plur.",
    '-le-vous': " COD, masc. sing. + COI (à vous), plur.",
    '-le-leur': " COD, masc. sing. + COI (à eux ou à elles), plur.",

    '-la-moi': " COD, fém. sing. + COI (à moi), sing.",
    '-la-toi': " COD, fém. sing. + COI (à toi), sing.",
    '-la-lui': " COD, fém. sing. + COI (à lui ou à elle), sing.",
    '-la-nous': " COD, fém. sing. + COI (à nous), plur.",
    '-la-vous': " COD, fém. sing. + COI (à vous), plur.",
    '-la-leur': " COD, fém. sing. + COI (à eux ou à elles), plur.",

    '-les-moi': " COD, plur. + COI (à moi), sing.",
    '-les-toi': " COD, plur. + COI (à toi), sing.",
    '-les-lui': " COD, plur. + COI (à lui ou à elle), sing.",
    '-les-nous': " COD, plur. + COI (à nous), plur.",
    '-les-vous': " COD, plur. + COI (à vous), plur.",
    '-les-leur': " COD, plur. + COI (à eux ou à elles), plur.",

    '-y': " pronom adverbial",
    "-m’y": " (me) pronom personnel objet + (y) pronom adverbial",
    "-t’y": " (te) pronom personnel objet + (y) pronom adverbial",
    "-s’y": " (se) pronom personnel objet + (y) pronom adverbial",

    '-en': " pronom adverbial",
    "-m’en": " (me) pronom personnel objet + (en) pronom adverbial",
    "-t’en": " (te) pronom personnel objet + (en) pronom adverbial",
    "-s’en": " (se) pronom personnel objet + (en) pronom adverbial",
}


_zElidedPrefix = re.compile("(?i)^((?:[dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)’)(.+)")
_zCompoundWord = re.compile("(?i)(\\w+)(-(?:(?:les?|la)-(?:moi|toi|lui|[nv]ous|leur)|t-(?:il|elle|on)|y|en|[mts]’(?:y|en)|les?|l[aà]|[mt]oi|leur|lui|je|tu|ils?|elles?|on|[nv]ous))$")
_zTag = re.compile("[:;/][\\w*][^:;/]*")

def split (sWord):
    "split word in 3 parts: prefix, root, suffix"
    sWord = sWord.replace("'", "’")
    sPrefix = ""
    sSuffix = ""
    # préfixe élidé
    m = _zElidedPrefix.match(sWord)
    if m:
        sPrefix = m.group(1)
        sWord = m.group(2)
    # mots composés
    m = _zCompoundWord.match(sWord)
    if m:
        sWord = m.group(1)
        sSuffix = m.group(2)
    return sPrefix, sWord, sSuffix


def analyze (sWord):
    "return meaning of <sWord> if found else an empty string"
    sWord = sWord.lower()
    if sWord in _dValues:
        return _dValues[sWord]
    return ""


def formatTags (sTags):
    "returns string: readable tags"
    sRes = ""
    sTags = re.sub("(?<=V[1-3])[itpqnmr_eaxz]+", "", sTags)
    sTags = re.sub("(?<=V0[ea])[itpqnmr_eaxz]+", "", sTags)
    for m in _zTag.finditer(sTags):
        sRes += _dTAGS.get(m.group(0), " [{}]".format(m.group(0)))[0]
    if sRes.startswith(" verbe") and not sRes.endswith("infinitif"):
        sRes += " [{}]".format(sTags[1:sTags.find("/")])
    return sRes.rstrip(",")

Modified graphspell/spellchecker.py from [114a0237c3] to [a290bf205a].

32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
        self.oMainDic = self._loadDictionary(sfMainDic, True)
        self.oCommunityDic = self._loadDictionary(sfCommunityDic)
        self.oPersonalDic = self._loadDictionary(sfPersonalDic)
        self.bCommunityDic = bool(self.oCommunityDic)
        self.bPersonalDic = bool(self.oPersonalDic)
        self.oTokenizer = None
        # Default suggestions
        self.dDefaultSugg = None
        self.loadSuggestions(sLangCode)
        # storage
        self.bStorage = False
        self._dMorphologies = {}        # key: flexion, value: list of morphologies
        self._dLemmas = {}              # key: flexion, value: list of lemmas

    def _loadDictionary (self, source, bNecessary=False):
        "returns an IBDAWG object"







|
|







32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
        self.oMainDic = self._loadDictionary(sfMainDic, True)
        self.oCommunityDic = self._loadDictionary(sfCommunityDic)
        self.oPersonalDic = self._loadDictionary(sfPersonalDic)
        self.bCommunityDic = bool(self.oCommunityDic)
        self.bPersonalDic = bool(self.oPersonalDic)
        self.oTokenizer = None
        # Default suggestions
        self.lexicographer = None
        self.loadLang(sLangCode)
        # storage
        self.bStorage = False
        self._dMorphologies = {}        # key: flexion, value: list of morphologies
        self._dLemmas = {}              # key: flexion, value: list of lemmas

    def _loadDictionary (self, source, bNecessary=False):
        "returns an IBDAWG object"
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
















113
114
115
116
117
118
119
    def deactivatePersonalDictionary (self):
        "deactivate personal dictionary"
        self.bPersonalDic = False


    # Default suggestions

    def loadSuggestions (self, sLangCode):
        "load default suggestion module for <sLangCode>"
        try:
            suggest = importlib.import_module("."+sLangCode, "grammalecte.graphspell")
        except ImportError:
            print("No suggestion module for language <"+sLangCode+">")
            return
        self.dDefaultSugg = suggest.dSugg


















    # Storage

    def activateStorage (self):
        "store all lemmas and morphologies retrieved from the word graph"
        self.bStorage = True







|


|



|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







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
    def deactivatePersonalDictionary (self):
        "deactivate personal dictionary"
        self.bPersonalDic = False


    # Default suggestions

    def loadLang (self, sLangCode):
        "load default suggestion module for <sLangCode>"
        try:
            self.lexicographer = importlib.import_module("."+sLangCode, "grammalecte.graphspell")
        except ImportError:
            print("No suggestion module for language <"+sLangCode+">")
            return

    def analyze (self, sWord):
        "returns a list of words and their morphologies"
        if not self.lexicographer:
            return []
        lWordAndMorph = []
        for sElem in self.lexicographer.split(sWord):
            if sElem:
                lMorph = self.getMorph(sElem)
                sLex = self.lexicographer.analyze(sElem)
                if sLex:
                    aRes = [ (" | ".join(lMorph), sLex) ]
                else:
                    aRes = [ (sMorph, self.lexicographer.formatTags(sMorph)) for sMorph in lMorph ]
                if aRes:
                    lWordAndMorph.append((sElem, aRes))
        return lWordAndMorph


    # Storage

    def activateStorage (self):
        "store all lemmas and morphologies retrieved from the word graph"
        self.bStorage = True
157
158
159
160
161
162
163

164
165
166
167
168
169
170
                else:
                    if not bByLemma:
                        dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
                    else:
                        for sLemma in self.getLemma(dToken['sValue']):
                            dWord[sLemma] = dWord.get(sLemma, 0) + 1
        return dWord


    # IBDAWG functions

    def isValidToken (self, sToken):
        "checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)"
        if self.oMainDic.isValidToken(sToken):
            return True







>







173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
                else:
                    if not bByLemma:
                        dWord[dToken['sValue']] = dWord.get(dToken['sValue'], 0) + 1
                    else:
                        for sLemma in self.getLemma(dToken['sValue']):
                            dWord[sLemma] = dWord.get(sLemma, 0) + 1
        return dWord


    # IBDAWG functions

    def isValidToken (self, sToken):
        "checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)"
        if self.oMainDic.isValidToken(sToken):
            return True
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
            if sWord not in self._dLemmas:
                self.getMorph(sWord)
            return self._dLemmas[sWord]
        return { s[1:s.find("/")]  for s in self.getMorph(sWord) }

    def suggest (self, sWord, nSuggLimit=10):
        "generator: returns 1, 2 or 3 lists of suggestions"
        if self.dDefaultSugg:
            if sWord in self.dDefaultSugg:
                yield self.dDefaultSugg[sWord].split("|")
            elif sWord.istitle() and sWord.lower() in self.dDefaultSugg:
                lRes = self.dDefaultSugg[sWord.lower()].split("|")
                yield list(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes))
            else:
                yield self.oMainDic.suggest(sWord, nSuggLimit, True)
        else:
            yield self.oMainDic.suggest(sWord, nSuggLimit, True)
        if self.bCommunityDic:
            yield self.oCommunityDic.suggest(sWord, (nSuggLimit//2)+1)







|
|
|
|
|







231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
            if sWord not in self._dLemmas:
                self.getMorph(sWord)
            return self._dLemmas[sWord]
        return { s[1:s.find("/")]  for s in self.getMorph(sWord) }

    def suggest (self, sWord, nSuggLimit=10):
        "generator: returns 1, 2 or 3 lists of suggestions"
        if self.lexicographer.dSugg:
            if sWord in self.lexicographer.dSugg:
                yield self.lexicographer.dSugg[sWord].split("|")
            elif sWord.istitle() and sWord.lower() in self.lexicographer.dSugg:
                lRes = self.lexicographer.dSugg[sWord.lower()].split("|")
                yield list(map(lambda sSugg: sSugg[0:1].upper()+sSugg[1:], lRes))
            else:
                yield self.oMainDic.suggest(sWord, nSuggLimit, True)
        else:
            yield self.oMainDic.suggest(sWord, nSuggLimit, True)
        if self.bCommunityDic:
            yield self.oCommunityDic.suggest(sWord, (nSuggLimit//2)+1)