Grammalecte  Check-in [6fe239d966]

Overview
Comment:[graphspell][build][core] add community dictionary
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | build | graphspell | multid
Files: files | file ages | folders
SHA3-256: 6fe239d96648197a4d4aa0ff002a95d79e99413dea99a27b4d522950b5e729d0
User & Date: olr on 2018-03-20 12:32:08
Other Links: branch diff | manifest | tags
Context
2018-03-20
12:43
[build][fr][bug] config.ini: fix build check-in: 5d03787a55 user: olr tags: fr, build, multid
12:32
[graphspell][build][core] add community dictionary check-in: 6fe239d966 user: olr tags: core, build, graphspell, multid
12:04
[tb] comment: spelling mistake check-in: 0726b05211 user: olr tags: tb, multid
Changes

Modified gc_core/js/lang_core/gc_engine.js from [2ba338046d] to [7ee1350cd7].

319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335

    //// Initialization

    load: function (sContext="JavaScript", sPath="") {
        try {
            if (typeof(require) !== 'undefined') {
                var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_personal_filename_js}");
            } else {
                _oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_personal_filename_js}");
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }







|

|







319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335

    //// Initialization

    load: function (sContext="JavaScript", sPath="") {
        try {
            if (typeof(require) !== 'undefined') {
                var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.SpellChecker("${lang}", "", "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            } else {
                _oSpellChecker = new SpellChecker("${lang}", sPath, "${dic_main_filename_js}", "${dic_extended_filename_js}", "${dic_community_filename_js}", "${dic_personal_filename_js}");
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }

Modified gc_core/py/lang_core/gc_engine.py from [b15edd00ca] to [72ecd7c680].

288
289
290
291
292
293
294
295
296
297
298
299
300
301
302


def load (sContext="Python"):
    global _oSpellChecker
    global _sAppContext
    global _dOptions
    try:
        _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_extended_filename_py}", "${dic_personal_filename_py}")
        _sAppContext = sContext
        _dOptions = dict(gc_options.getOptions(sContext))   # duplication necessary, to be able to reset to default
    except:
        traceback.print_exc()


def setOption (sOpt, bVal):







|







288
289
290
291
292
293
294
295
296
297
298
299
300
301
302


def load (sContext="Python"):
    global _oSpellChecker
    global _sAppContext
    global _dOptions
    try:
        _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_extended_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
        _sAppContext = sContext
        _dOptions = dict(gc_options.getOptions(sContext))   # duplication necessary, to be able to reset to default
    except:
        traceback.print_exc()


def setOption (sOpt, bVal):

Modified gc_lang/fr/config.ini from [5898e7ef09] to [25d4196521].

18
19
20
21
22
23
24




25
26
27
28
29
30
31
lexicon_src = lexicons/French.lex
dic_filename = fr
dic_name = French
# extended dictionary
lexicon_extended_src = lexicons/French.extended.lex
dic_extended_filename = fr.extended
dic_extended_name = Français - dictionnaire étendu




# personal dictionary
lexicon_personal_src = lexicons/French.personal.lex
dic_personal_filename = fr.personal
dic_personal_name = Français - dictionnaire personnel
# Finite state automaton compression: 1, 2 (experimental) or 3 (experimental)
fsa_method = 1
# stemming method: S for suffixes only, A for prefixes and suffixes







>
>
>
>







18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
lexicon_src = lexicons/French.lex
dic_filename = fr
dic_name = French
# extended dictionary
lexicon_extended_src = lexicons/French.extended.lex
dic_extended_filename = fr.extended
dic_extended_name = Français - dictionnaire étendu
# community dictionary
lexicon_extended_src = lexicons/French.community.lex
dic_extended_filename = fr.community
dic_extended_name = Français - dictionnaire communautaire
# personal dictionary
lexicon_personal_src = lexicons/French.personal.lex
dic_personal_filename = fr.personal
dic_personal_name = Français - dictionnaire personnel
# Finite state automaton compression: 1, 2 (experimental) or 3 (experimental)
fsa_method = 1
# stemming method: S for suffixes only, A for prefixes and suffixes

Modified graphspell-js/spellchecker.js from [a4e4ee731d] to [a6a425b5cc].

24
25
26
27
28
29
30
31
32
33
34
35
36
37
38

39
40
41
42
43
44
45
    ["fr", "fr.json"],
    ["en", "en.json"]
]);


class SpellChecker {

    constructor (sLangCode, sPath="", mainDic="", extentedDic="", personalDic="") {
        // returns true if the main dictionary is loaded
        this.sLangCode = sLangCode;
        if (!mainDic) {
            mainDic = dDefaultDictionaries.gl_get(sLangCode, "");
        }
        this.oMainDic = this._loadDictionary(mainDic, sPath, true);
        this.oExtendedDic = this._loadDictionary(extentedDic, sPath);

        this.oPersonalDic = this._loadDictionary(personalDic, sPath);
        this.oTokenizer = null;
    }

    _loadDictionary (dictionary, sPath, bNecessary=false) {
        // returns an IBDAWG object
        if (!dictionary) {







|







>







24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
    ["fr", "fr.json"],
    ["en", "en.json"]
]);


class SpellChecker {

    constructor (sLangCode, sPath="", mainDic="", extentedDic="", communityDic="", personalDic="") {
        // returns true if the main dictionary is loaded
        this.sLangCode = sLangCode;
        if (!mainDic) {
            mainDic = dDefaultDictionaries.gl_get(sLangCode, "");
        }
        this.oMainDic = this._loadDictionary(mainDic, sPath, true);
        this.oExtendedDic = this._loadDictionary(extentedDic, sPath);
        this.oCommunityDic = this._loadDictionary(communityDic, sPath);
        this.oPersonalDic = this._loadDictionary(personalDic, sPath);
        this.oTokenizer = null;
    }

    _loadDictionary (dictionary, sPath, bNecessary=false) {
        // returns an IBDAWG object
        if (!dictionary) {
85
86
87
88
89
90
91






92
93
94
95
96
97
98
    }

    setExtendedDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oExtendedDic = this._loadDictionary(dictionary);
        return Boolean(this.oExtendedDic);
    }







    setPersonalDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oPersonalDic = this._loadDictionary(dictionary);
        return Boolean(this.oPersonalDic);
    }








>
>
>
>
>
>







86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
    }

    setExtendedDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oExtendedDic = this._loadDictionary(dictionary);
        return Boolean(this.oExtendedDic);
    }

    setCommunityDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oCommunityDic = this._loadDictionary(dictionary);
        return Boolean(this.oCommunityDic);
    }

    setPersonalDictionary (dictionary) {
        // returns true if the dictionary is loaded
        this.oPersonalDic = this._loadDictionary(dictionary);
        return Boolean(this.oPersonalDic);
    }

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
    isValidToken (sToken) {
        // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)
        if (this.oMainDic.isValidToken(sToken)) {
            return true;
        }
        if (this.oExtendedDic && this.oExtendedDic.isValidToken(sToken)) {
            return true;



        }
        if (this.oPersonalDic && this.oPersonalDic.isValidToken(sToken)) {
            return true;
        }
        return false;
    }

    isValid (sWord) {
        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (this.oMainDic.isValid(sWord)) {
            return true;
        }
        if (this.oExtendedDic && this.oExtendedDic.isValid(sWord)) {
            return true;



        }
        if (this.oPersonalDic && this.oPersonalDic.isValid(sWord)) {
            return true;
        }
        return false;
    }

    lookup (sWord) {
        // checks if sWord is in dictionary as is (strict verification)
        if (this.oMainDic.lookup(sWord)) {
            return true;
        }
        if (this.oExtendedDic && this.oExtendedDic.lookup(sWord)) {
            return true;



        }
        if (this.oPersonalDic && this.oPersonalDic.lookup(sWord)) {
            return true;
        }
        return false;
    }

    getMorph (sWord) {
        // retrieves morphologies list, different casing allowed
        let lResult = this.oMainDic.getMorph(sWord);
        if (this.oExtendedDic) {
            lResult.push(...this.oExtendedDic.getMorph(sWord));
        }



        if (this.oPersonalDic) {
            lResult.push(...this.oPersonalDic.getMorph(sWord));
        }
        return lResult;
    }

    * suggest (sWord, nSuggLimit=10) {
        // generator: returns 1, 2 or 3 lists of suggestions
        yield this.oMainDic.suggest(sWord, nSuggLimit);
        if (this.oExtendedDic) {
            yield this.oExtendedDic.suggest(sWord, nSuggLimit);
        }



        if (this.oPersonalDic) {
            yield this.oPersonalDic.suggest(sWord, nSuggLimit);
        }
    }

    * select (sPattern="") {
        // generator: returns all entries which morphology fits <sPattern>
        yield* this.oMainDic.select(sPattern)
        if (this.oExtendedDic) {
            yield* this.oExtendedDic.select(sPattern);
        }



        if (this.oPersonalDic) {
            yield* this.oPersonalDic.select(sPattern);
        }
    }
}

if (typeof(exports) !== 'undefined') {
    exports.SpellChecker = SpellChecker;
}







>
>
>














>
>
>














>
>
>













>
>
>












>
>
>











>
>
>









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
    isValidToken (sToken) {
        // checks if sToken is valid (if there is hyphens in sToken, sToken is split, each part is checked)
        if (this.oMainDic.isValidToken(sToken)) {
            return true;
        }
        if (this.oExtendedDic && this.oExtendedDic.isValidToken(sToken)) {
            return true;
        }
        if (this.oCommunityDic && this.oCommunityDic.isValidToken(sToken)) {
            return true;
        }
        if (this.oPersonalDic && this.oPersonalDic.isValidToken(sToken)) {
            return true;
        }
        return false;
    }

    isValid (sWord) {
        // checks if sWord is valid (different casing tested if the first letter is a capital)
        if (this.oMainDic.isValid(sWord)) {
            return true;
        }
        if (this.oExtendedDic && this.oExtendedDic.isValid(sWord)) {
            return true;
        }
        if (this.oCommunityDic && this.oCommunityDic.isValid(sToken)) {
            return true;
        }
        if (this.oPersonalDic && this.oPersonalDic.isValid(sWord)) {
            return true;
        }
        return false;
    }

    lookup (sWord) {
        // checks if sWord is in dictionary as is (strict verification)
        if (this.oMainDic.lookup(sWord)) {
            return true;
        }
        if (this.oExtendedDic && this.oExtendedDic.lookup(sWord)) {
            return true;
        }
        if (this.oCommunityDic && this.oCommunityDic.lookup(sToken)) {
            return true;
        }
        if (this.oPersonalDic && this.oPersonalDic.lookup(sWord)) {
            return true;
        }
        return false;
    }

    getMorph (sWord) {
        // retrieves morphologies list, different casing allowed
        let lResult = this.oMainDic.getMorph(sWord);
        if (this.oExtendedDic) {
            lResult.push(...this.oExtendedDic.getMorph(sWord));
        }
        if (this.oCommunityDic) {
            lResult.push(...this.oCommunityDic.getMorph(sWord));
        }
        if (this.oPersonalDic) {
            lResult.push(...this.oPersonalDic.getMorph(sWord));
        }
        return lResult;
    }

    * suggest (sWord, nSuggLimit=10) {
        // generator: returns 1, 2 or 3 lists of suggestions
        yield this.oMainDic.suggest(sWord, nSuggLimit);
        if (this.oExtendedDic) {
            yield this.oExtendedDic.suggest(sWord, nSuggLimit);
        }
        if (this.oCommunityDic) {
            yield this.oCommunityDic.suggest(sWord, nSuggLimit);
        }
        if (this.oPersonalDic) {
            yield this.oPersonalDic.suggest(sWord, nSuggLimit);
        }
    }

    * select (sPattern="") {
        // generator: returns all entries which morphology fits <sPattern>
        yield* this.oMainDic.select(sPattern)
        if (this.oExtendedDic) {
            yield* this.oExtendedDic.select(sPattern);
        }
        if (this.oCommunityDic) {
            yield* this.oCommunityDic.select(sPattern);
        }
        if (this.oPersonalDic) {
            yield* this.oPersonalDic.select(sPattern);
        }
    }
}

if (typeof(exports) !== 'undefined') {
    exports.SpellChecker = SpellChecker;
}

Modified graphspell/spellchecker.py from [aaa0229431] to [4d329ce1f7].

18
19
20
21
22
23
24
25
26
27
28
29
30
31

32
33
34
35
36
37
38
    "fr": "fr.bdic",
    "en": "en.bdic"
}


class SpellChecker ():

    def __init__ (self, sLangCode, sfMainDic="", sfExtendedDic="", sfPersonalDic=""):
        "returns True if the main dictionary is loaded"
        self.sLangCode = sLangCode
        if not sfMainDic:
            sfMainDic = dDefaultDictionaries.get(sLangCode, "")
        self.oMainDic = self._loadDictionary(sfMainDic, True)
        self.oExtendedDic = self._loadDictionary(sfExtendedDic)

        self.oPersonalDic = self._loadDictionary(sfPersonalDic)
        self.oTokenizer = None

    def _loadDictionary (self, source, bNecessary=False):
        "returns an IBDAWG object"
        if not source:
            return None







|






>







18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
    "fr": "fr.bdic",
    "en": "en.bdic"
}


class SpellChecker ():

    def __init__ (self, sLangCode, sfMainDic="", sfExtendedDic="", sfCommunityDic="", sfPersonalDic=""):
        "returns True if the main dictionary is loaded"
        self.sLangCode = sLangCode
        if not sfMainDic:
            sfMainDic = dDefaultDictionaries.get(sLangCode, "")
        self.oMainDic = self._loadDictionary(sfMainDic, True)
        self.oExtendedDic = self._loadDictionary(sfExtendedDic)
        self.oCommunityDic = self._loadDictionary(sfCommunityDic)
        self.oPersonalDic = self._loadDictionary(sfPersonalDic)
        self.oTokenizer = None

    def _loadDictionary (self, source, bNecessary=False):
        "returns an IBDAWG object"
        if not source:
            return None
58
59
60
61
62
63
64





65
66
67
68
69
70
71
        self.oMainDic = self._loadDictionary(source)
        return bool(self.oMainDic)
            
    def setExtendedDictionary (self, source):
        "returns True if the dictionary is loaded"
        self.oExtendedDic = self._loadDictionary(source)
        return bool(self.oExtendedDic)






    def setPersonalDictionary (self, source):
        "returns True if the dictionary is loaded"
        self.oPersonalDic = self._loadDictionary(source)
        return bool(self.oPersonalDic)

    # parse text functions







>
>
>
>
>







59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
        self.oMainDic = self._loadDictionary(source)
        return bool(self.oMainDic)
            
    def setExtendedDictionary (self, source):
        "returns True if the dictionary is loaded"
        self.oExtendedDic = self._loadDictionary(source)
        return bool(self.oExtendedDic)

    def setCommunityDictionary (self, source):
        "returns True if the dictionary is loaded"
        self.oCommunityDic = self._loadDictionary(source)
        return bool(self.oPersonalDic)

    def setPersonalDictionary (self, source):
        "returns True if the dictionary is loaded"
        self.oPersonalDic = self._loadDictionary(source)
        return bool(self.oPersonalDic)

    # parse text functions
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

    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
        if self.oExtendedDic and self.oExtendedDic.isValidToken(sToken):
            return True


        if self.oPersonalDic and self.oPersonalDic.isValidToken(sToken):
            return True
        return False

    def isValid (self, sWord):
        "checks if sWord is valid (different casing tested if the first letter is a capital)"
        if self.oMainDic.isValid(sWord):
            return True
        if self.oExtendedDic and self.oExtendedDic.isValid(sWord):


            return True
        if self.oPersonalDic and self.oPersonalDic.isValid(sWord):
            return True
        return False

    def lookup (self, sWord):
        "checks if sWord is in dictionary as is (strict verification)"
        if self.oMainDic.lookup(sWord):
            return True
        if self.oExtendedDic and self.oExtendedDic.lookup(sWord):
            return True


        if self.oPersonalDic and self.oPersonalDic.lookup(sWord):
            return True
        return False

    def getMorph (self, sWord):
        "retrieves morphologies list, different casing allowed"
        lResult = self.oMainDic.getMorph(sWord)
        if self.oExtendedDic:
            lResult.extend(self.oExtendedDic.getMorph(sWord))


        if self.oPersonalDic:
            lResult.extend(self.oPersonalDic.getMorph(sWord))
        return lResult

    def getLemma (self, sWord):
        return set([ 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"
        yield self.oMainDic.suggest(sWord, nSuggLimit)
        if self.oExtendedDic:
            yield self.oExtendedDic.suggest(sWord, nSuggLimit)


        if self.oPersonalDic:
            yield self.oPersonalDic.suggest(sWord, nSuggLimit)

    def select (self, sPattern=""):
        "generator: returns all entries which morphology fits <sPattern>"
        yield from self.oMainDic.select(sPattern)
        if self.oExtendedDic:
            yield from self.oExtendedDic.select(sPattern)


        if self.oPersonalDic:
            yield from self.oPersonalDic.select(sPattern)

    def drawPath (self, sWord):
        self.oMainDic.drawPath(sWord)
        if self.oExtendedDic:
            print("-----")
            self.oExtendedDic.drawPath(sWord)



        if self.oPersonalDic:
            print("-----")
            self.oPersonalDic.drawPath(sWord)







>
>









>
>











>
>









>
>












>
>








>
>








>
>
>



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

    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
        if self.oExtendedDic and self.oExtendedDic.isValidToken(sToken):
            return True
        if self.oCommunityDic and self.oCommunityDic.isValidToken(sToken):
            return True
        if self.oPersonalDic and self.oPersonalDic.isValidToken(sToken):
            return True
        return False

    def isValid (self, sWord):
        "checks if sWord is valid (different casing tested if the first letter is a capital)"
        if self.oMainDic.isValid(sWord):
            return True
        if self.oExtendedDic and self.oExtendedDic.isValid(sWord):
            return True
        if self.oCommunityDic and self.oCommunityDic.isValid(sToken):
            return True
        if self.oPersonalDic and self.oPersonalDic.isValid(sWord):
            return True
        return False

    def lookup (self, sWord):
        "checks if sWord is in dictionary as is (strict verification)"
        if self.oMainDic.lookup(sWord):
            return True
        if self.oExtendedDic and self.oExtendedDic.lookup(sWord):
            return True
        if self.oCommunityDic and self.oCommunityDic.lookup(sToken):
            return True
        if self.oPersonalDic and self.oPersonalDic.lookup(sWord):
            return True
        return False

    def getMorph (self, sWord):
        "retrieves morphologies list, different casing allowed"
        lResult = self.oMainDic.getMorph(sWord)
        if self.oExtendedDic:
            lResult.extend(self.oExtendedDic.getMorph(sWord))
        if self.oCommunityDic:
            lResult.extend(self.oCommunityDic.getMorph(sWord))
        if self.oPersonalDic:
            lResult.extend(self.oPersonalDic.getMorph(sWord))
        return lResult

    def getLemma (self, sWord):
        return set([ 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"
        yield self.oMainDic.suggest(sWord, nSuggLimit)
        if self.oExtendedDic:
            yield self.oExtendedDic.suggest(sWord, nSuggLimit)
        if self.oCommunityDic:
            yield self.oCommunityDic.suggest(sWord, nSuggLimit)
        if self.oPersonalDic:
            yield self.oPersonalDic.suggest(sWord, nSuggLimit)

    def select (self, sPattern=""):
        "generator: returns all entries which morphology fits <sPattern>"
        yield from self.oMainDic.select(sPattern)
        if self.oExtendedDic:
            yield from self.oExtendedDic.select(sPattern)
        if self.oCommunityDic:
            yield from self.oCommunityDic.select(sPattern)
        if self.oPersonalDic:
            yield from self.oPersonalDic.select(sPattern)

    def drawPath (self, sWord):
        self.oMainDic.drawPath(sWord)
        if self.oExtendedDic:
            print("-----")
            self.oExtendedDic.drawPath(sWord)
        if self.oCommunityDic:
            print("-----")
            self.oCommunityDic.drawPath(sWord)
        if self.oPersonalDic:
            print("-----")
            self.oPersonalDic.drawPath(sWord)

Modified make.py from [b9941a6809] to [8e3260b6ad].

303
304
305
306
307
308
309
310
311
312
313
314


315
316
317
318
319


320
321
322
323
324
325
326
            dVars[sf[:-3]] = open("js_extension/"+sf, "r", encoding="utf-8").read()
        for sf in os.listdir("graphspell-js"):
            if not os.path.isdir("graphspell-js/"+sf):
                file_util.copy_file("graphspell-js/"+sf, "grammalecte-js/graphspell")
                helpers.copyAndFileTemplate("graphspell-js/"+sf, "grammalecte-js/graphspell/"+sf, dVars)


def copyGraphspellDictionaries (dVars, bJavaScript=False, bExtendedDict=False, bPersonalDict=False):
    dVars["dic_main_filename_py"] = ""
    dVars["dic_main_filename_js"] = ""
    dVars["dic_extended_filename_py"] = ""
    dVars["dic_extended_filename_js"] = ""


    dVars["dic_personal_filename_py"] = ""
    dVars["dic_personal_filename_js"] = ""
    lDict = [ ("main", dVars['dic_filename']) ]
    if bExtendedDict:
        lDict.append(("extended", dVars['dic_extended_filename']))


    if bPersonalDict:
        lDict.append(("personal", dVars['dic_personal_filename']))
    for sType, sFileName in lDict:
        spfPyDic = "graphspell/_dictionaries/" + sFileName + ".bdic"
        spfJSDic = "graphspell-js/_dictionaries/" + sFileName + ".json"
        if not os.path.isfile(spfPyDic) or (bJavaScript and not os.path.isfile(spfJSDic)):
            buildDictionary(dVars, sType, bJavaScript)







|




>
>





>
>







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
            dVars[sf[:-3]] = open("js_extension/"+sf, "r", encoding="utf-8").read()
        for sf in os.listdir("graphspell-js"):
            if not os.path.isdir("graphspell-js/"+sf):
                file_util.copy_file("graphspell-js/"+sf, "grammalecte-js/graphspell")
                helpers.copyAndFileTemplate("graphspell-js/"+sf, "grammalecte-js/graphspell/"+sf, dVars)


def copyGraphspellDictionaries (dVars, bJavaScript=False, bExtendedDict=False, bCommunityDict=False, bPersonalDict=False):
    dVars["dic_main_filename_py"] = ""
    dVars["dic_main_filename_js"] = ""
    dVars["dic_extended_filename_py"] = ""
    dVars["dic_extended_filename_js"] = ""
    dVars["dic_community_filename_py"] = ""
    dVars["dic_community_filename_js"] = ""
    dVars["dic_personal_filename_py"] = ""
    dVars["dic_personal_filename_js"] = ""
    lDict = [ ("main", dVars['dic_filename']) ]
    if bExtendedDict:
        lDict.append(("extended", dVars['dic_extended_filename']))
    if bCommunityDict:
        lDict.append(("community", dVars['dic_community_filename']))
    if bPersonalDict:
        lDict.append(("personal", dVars['dic_personal_filename']))
    for sType, sFileName in lDict:
        spfPyDic = "graphspell/_dictionaries/" + sFileName + ".bdic"
        spfJSDic = "graphspell-js/_dictionaries/" + sFileName + ".json"
        if not os.path.isfile(spfPyDic) or (bJavaScript and not os.path.isfile(spfJSDic)):
            buildDictionary(dVars, sType, bJavaScript)
337
338
339
340
341
342
343




344
345
346
347
348
349
350
        spfLexSrc = dVars['lexicon_src']
        sfDictDst = dVars['dic_filename']
        sDicName = dVars['dic_name']
    elif sType == "extended":
        spfLexSrc = dVars['lexicon_extended_src']
        sfDictDst = dVars['dic_extended_filename']
        sDicName = dVars['dic_extended_name']




    elif sType == "personal":
        spfLexSrc = dVars['lexicon_personal_src']
        sfDictDst = dVars['dic_personal_filename']
        sDicName = dVars['dic_personal_name']
    lex_build.build(spfLexSrc, dVars['lang'], dVars['lang_name'], sfDictDst, bJavaScript, sDicName, dVars['stemming_method'], int(dVars['fsa_method']))









>
>
>
>







341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
        spfLexSrc = dVars['lexicon_src']
        sfDictDst = dVars['dic_filename']
        sDicName = dVars['dic_name']
    elif sType == "extended":
        spfLexSrc = dVars['lexicon_extended_src']
        sfDictDst = dVars['dic_extended_filename']
        sDicName = dVars['dic_extended_name']
    elif sType == "community":
        spfLexSrc = dVars['lexicon_community_src']
        sfDictDst = dVars['dic_community_filename']
        sDicName = dVars['dic_community_name']
    elif sType == "personal":
        spfLexSrc = dVars['lexicon_personal_src']
        sfDictDst = dVars['dic_personal_filename']
        sDicName = dVars['dic_personal_name']
    lex_build.build(spfLexSrc, dVars['lang'], dVars['lang_name'], sfDictDst, bJavaScript, sDicName, dVars['stemming_method'], int(dVars['fsa_method']))


358
359
360
361
362
363
364

365
366
367
368
369
370
371
    xParser.add_argument("-ba", "--build_data_after", help="launch build_data.py (only part 2: before dictionary building)", action="store_true")
    xParser.add_argument("-d", "--dict", help="generate FSA dictionary", action="store_true")
    xParser.add_argument("-t", "--tests", help="run unit tests", action="store_true")
    xParser.add_argument("-p", "--perf", help="run performance tests", action="store_true")
    xParser.add_argument("-pm", "--perf_memo", help="run performance tests and store results in perf_memo.txt", action="store_true")
    xParser.add_argument("-js", "--javascript", help="JavaScript build for Firefox", action="store_true")
    xParser.add_argument("-aed", "--add_extended_dictionary", help="add extended dictionary to the build", action="store_true")

    xParser.add_argument("-apd", "--add_personal_dictionary", help="add personal dictionary to the build", action="store_true")
    xParser.add_argument("-fx", "--firefox", help="Launch Firefox Developper for WebExtension testing", action="store_true")
    xParser.add_argument("-we", "--web_ext", help="Launch Firefox Nightly for WebExtension testing", action="store_true")
    xParser.add_argument("-tb", "--thunderbird", help="Launch Thunderbird", action="store_true")
    xParser.add_argument("-i", "--install", help="install the extension in Writer (path of unopkg must be set in config.ini)", action="store_true")
    xArgs = xParser.parse_args()








>







366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
    xParser.add_argument("-ba", "--build_data_after", help="launch build_data.py (only part 2: before dictionary building)", action="store_true")
    xParser.add_argument("-d", "--dict", help="generate FSA dictionary", action="store_true")
    xParser.add_argument("-t", "--tests", help="run unit tests", action="store_true")
    xParser.add_argument("-p", "--perf", help="run performance tests", action="store_true")
    xParser.add_argument("-pm", "--perf_memo", help="run performance tests and store results in perf_memo.txt", action="store_true")
    xParser.add_argument("-js", "--javascript", help="JavaScript build for Firefox", action="store_true")
    xParser.add_argument("-aed", "--add_extended_dictionary", help="add extended dictionary to the build", action="store_true")
    xParser.add_argument("-acd", "--add_community_dictionary", help="add community dictionary to the build", action="store_true")
    xParser.add_argument("-apd", "--add_personal_dictionary", help="add personal dictionary to the build", action="store_true")
    xParser.add_argument("-fx", "--firefox", help="Launch Firefox Developper for WebExtension testing", action="store_true")
    xParser.add_argument("-we", "--web_ext", help="Launch Firefox Nightly for WebExtension testing", action="store_true")
    xParser.add_argument("-tb", "--thunderbird", help="Launch Thunderbird", action="store_true")
    xParser.add_argument("-i", "--install", help="install the extension in Writer (path of unopkg must be set in config.ini)", action="store_true")
    xArgs = xParser.parse_args()

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
    for sLang in xArgs.lang:
        if os.path.exists("gc_lang/"+sLang) and os.path.isdir("gc_lang/"+sLang):
            xConfig = getConfig(sLang)
            dVars = xConfig._sections['args']

            if not dVars["lexicon_extended_src"]:
                xArgs.add_extended_dictionary = False


            if not dVars["lexicon_personal_src"]:
                xArgs.add_personal_dictionary = False

            # build data
            build_data_module = None
            if xArgs.build_data_before or xArgs.build_data_after:
                # lang data
                try:
                    build_data_module = importlib.import_module("gc_lang."+sLang+".build_data")
                except ImportError:
                    print("# Error. Couldn’t import file build_data.py in folder gc_lang/"+sLang)
            if build_data_module and xArgs.build_data_before:
                build_data_module.before('gc_lang/'+sLang, dVars, xArgs.javascript)
            if xArgs.dict:
                buildDictionary(dVars, "main", xArgs.javascript)
                if xArgs.add_extended_dictionary:
                    buildDictionary(dVars, "extended", xArgs.javascript)


                if xArgs.add_personal_dictionary:
                    buildDictionary(dVars, "personal", xArgs.javascript)
            if build_data_module and xArgs.build_data_after:
                build_data_module.after('gc_lang/'+sLang, dVars, xArgs.javascript)

            # copy dictionaries from Graphspell
            copyGraphspellDictionaries(dVars, xArgs.javascript, xArgs.add_extended_dictionary, xArgs.add_personal_dictionary)

            # make
            sVersion = create(sLang, xConfig, xArgs.install, xArgs.javascript, )

            # tests
            if xArgs.tests or xArgs.perf or xArgs.perf_memo:
                print("> Running tests")







>
>

















>
>






|







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
426
427
428
429
430
431
432
433
    for sLang in xArgs.lang:
        if os.path.exists("gc_lang/"+sLang) and os.path.isdir("gc_lang/"+sLang):
            xConfig = getConfig(sLang)
            dVars = xConfig._sections['args']

            if not dVars["lexicon_extended_src"]:
                xArgs.add_extended_dictionary = False
            if not dVars["lexicon_community_src"]:
                xArgs.add_community_dictionary = False
            if not dVars["lexicon_personal_src"]:
                xArgs.add_personal_dictionary = False

            # build data
            build_data_module = None
            if xArgs.build_data_before or xArgs.build_data_after:
                # lang data
                try:
                    build_data_module = importlib.import_module("gc_lang."+sLang+".build_data")
                except ImportError:
                    print("# Error. Couldn’t import file build_data.py in folder gc_lang/"+sLang)
            if build_data_module and xArgs.build_data_before:
                build_data_module.before('gc_lang/'+sLang, dVars, xArgs.javascript)
            if xArgs.dict:
                buildDictionary(dVars, "main", xArgs.javascript)
                if xArgs.add_extended_dictionary:
                    buildDictionary(dVars, "extended", xArgs.javascript)
                if xArgs.add_community_dictionary:
                    buildDictionary(dVars, "community", xArgs.javascript)
                if xArgs.add_personal_dictionary:
                    buildDictionary(dVars, "personal", xArgs.javascript)
            if build_data_module and xArgs.build_data_after:
                build_data_module.after('gc_lang/'+sLang, dVars, xArgs.javascript)

            # copy dictionaries from Graphspell
            copyGraphspellDictionaries(dVars, xArgs.javascript, xArgs.add_extended_dictionary, xArgs.add_community_dictionary, xArgs.add_personal_dictionary)

            # make
            sVersion = create(sLang, xConfig, xArgs.install, xArgs.javascript, )

            # tests
            if xArgs.tests or xArgs.perf or xArgs.perf_memo:
                print("> Running tests")