Grammalecte  Check-in [074cb33c80]

Overview
Comment:[fr][js] màj: lexicographe, tokenizer
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fr | kill_innerHTML
Files: files | file ages | folders
SHA3-256: 074cb33c80a58b9d6c4e443e433869f7c5c3f2da989177d053dac9b69bb74178
User & Date: olr on 2017-07-12 11:03:48
Other Links: branch diff | manifest | tags
Context
2017-07-13
06:50
[fx][fr][js] tokeniseur --> lexicographe check-in: b4cf00a4c8 user: olr tags: fr, fx, kill_innerHTML
2017-07-12
11:03
[fr][js] màj: lexicographe, tokenizer check-in: 074cb33c80 user: olr tags: fr, kill_innerHTML
2017-07-11
13:58
[fr] pt: à chacun, à s’en +infi check-in: 52649f7a5b user: olr tags: fr, trunk
Changes

Modified gc_core/js/tokenizer.js from [d06151ccd7] to [4eb5311054].

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
..
65
66
67
68
69
70
71










72
73
74
75
// JavaScript
// Very simple tokenizer

"use strict";

const helpers = require("resource://grammalecte/helpers.js");


const aPatterns = {
    // All regexps must start with ^.
    "default":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^[,.;:!?…«»“”"()/·]+/, 'SEPARATOR'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.])[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^\d\d?h\d\d\b/, 'HOUR'],
            [/^-?\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD']
        ],
    "fr":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^[,.;:!?…«»“”"()/·]+/, 'SEPARATOR'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.])[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'ELPFX'],
            [/^\d\d?[hm]\d\d\b/, 'HOUR'],
            [/^\d+(?:er|nd|e|de|ième|ème|eme)\b/, 'ORDINAL'],
            [/^-?\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD']
        ]
}


class Tokenizer {

    constructor (sLang) {
        this.sLang = sLang;
        if (!aPatterns.hasOwnProperty(sLang)) {
            this.sLang = "default";
        }
        this.aRules = aPatterns[sLang];
    };

    * genTokens (sText) {
        let m;
        let i = 0;
        while (sText) {
            let nCut = 1;
................................................................................
                catch (e) {
                    helpers.logerror(e);
                }
            }
            i += nCut;
            sText = sText.slice(nCut);
        }










    }
}

exports.Tokenizer = Tokenizer;







<





|












|







|













|







 







>
>
>
>
>
>
>
>
>
>




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
..
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
// JavaScript
// Very simple tokenizer

"use strict";

const helpers = require("resource://grammalecte/helpers.js");


const aPatterns = {
    // All regexps must start with ^.
    "default":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.])[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^\d\d?h\d\d\b/, 'HOUR'],
            [/^-?\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD']
        ],
    "fr":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_]+[@.])[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'ELPFX'],
            [/^\d\d?[hm]\d\d\b/, 'HOUR'],
            [/^\d+(?:er|nd|e|de|ième|ème|eme)s?\b/, 'ORDINAL'],
            [/^-?\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD']
        ]
}


class Tokenizer {

    constructor (sLang) {
        this.sLang = sLang;
        if (!aPatterns.hasOwnProperty(sLang)) {
            this.sLang = "default";
        }
        this.aRules = aPatterns[this.sLang];
    };

    * genTokens (sText) {
        let m;
        let i = 0;
        while (sText) {
            let nCut = 1;
................................................................................
                catch (e) {
                    helpers.logerror(e);
                }
            }
            i += nCut;
            sText = sText.slice(nCut);
        }
    };

    getSpellingErrors (sText, oDict) {
        let aSpellErr = [];
        for (let oToken of this.genTokens(sText)) {
            if (oToken.sType === 'WORD' && !oDict.isValidToken(oToken.sValue)) {
                aSpellErr.push(oToken);
            }
        }
        return aSpellErr;
    }
}

exports.Tokenizer = Tokenizer;

Modified gc_lang/fr/config.ini from [94e5221453] to [2a6b6ad1cb].

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
[args]
lang = fr
lang_name = French
locales = fr_FR fr_BE fr_CA fr_CH fr_LU fr_MC fr_BF fr_CI fr_SN fr_ML fr_NE fr_TG fr_BJ
country_default = FR
name = Grammalecte
implname = grammalecte
version = 0.5.17.2
author = Olivier R.
provider = Dicollecte
link = http://grammalecte.net
description = Correcteur grammatical 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
[args]
lang = fr
lang_name = French
locales = fr_FR fr_BE fr_CA fr_CH fr_LU fr_MC fr_BF fr_CI fr_SN fr_ML fr_NE fr_TG fr_BJ
country_default = FR
name = Grammalecte
implname = grammalecte
version = 0.5.18
author = Olivier R.
provider = Dicollecte
link = http://grammalecte.net
description = Correcteur grammatical pour le français.
extras = README_fr.txt
logo = logo.png

Modified gc_lang/fr/modules-js/lexicographe.js from [7e54b6b49b] to [98b82a04c2].

1
2
3
4
5
6

7
8
9

10
11
12
13
14
15
16
...
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
...
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
...
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
// Grammalecte - Lexicographe
// License: MPL 2

"use strict";

${string}



const helpers = require("resource://grammalecte/helpers.js");



const _dTAGS = new Map ([
    [':G', "[mot grammatical]"],
    [':N', " nom,"],
    [':A', " adjectif,"],
    [':M1', " prénom,"],
................................................................................

    ['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 {

    constructor (oDict) {
        this.oDict = oDict;
        this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i");
        this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?: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)$", "i");
        this._zTag = new RegExp ("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*][^:;/]*", "g");
    };
















































    analyzeText (sText) {
        sText = sText.replace(/[.,.?!:;…\/()\[\]“”«»"„{}–—#+*<>%=\n]/g, " ").replace(/\s+/g, " ");
        let iStart = 0;
        let iEnd = 0;
        let sHtml = '<div class="paragraph">\n';
        while ((iEnd = sText.indexOf(" ", iStart)) !== -1) {
            sHtml += this.analyzeWord(sText.slice(iStart, iEnd));
            iStart = iEnd + 1;
        }
        sHtml += this.analyzeWord(sText.slice(iStart));
        return sHtml + '</div>\n';
    }

    analyzeWord (sWord) {
        try {
            if (!sWord) {
                return "";
            }
            if (sWord._count("-") > 4) {
                return '<p><b class="mbok">' + sWord + "</b> <s>:</s> élément complexe indéterminé</p>\n";
            }
................................................................................
            let m2 = this._zCompoundWord.exec(sWord);
            if (m2 !== null) {
                sWord = m2[1];
            }
            // Morphologies
            let lMorph = this.oDict.getMorph(sWord);
            if (lMorph.length === 1) {
                sHtml += "<p><b>" + sWord + "</b> <s>:</s> " + this.formatTags(lMorph[0]) + "</p>\n";
            } else if (lMorph.length > 1) {
                sHtml += "<p><b>" + sWord + "</b><ul><li>" + [for (s of lMorph) if (s.includes(":")) this.formatTags(s)].join(" </li><li> ") + "</li></ul></p>\n";
            } else {
                sHtml += '<p><b class="unknown">' + sWord + "</b> <s>:</s>  absent du dictionnaire<p>\n";
            }
            // suffixe d’un mot composé
            if (m2) {
                sHtml += "<p>-<b>" + m2[2] + "</b> <s>:</s> " + this._formatSuffix(m2[2].toLowerCase()) + "</p>\n";
            }
................................................................................
        }
        catch (e) {
            helpers.logerror(e);
            return "#erreur";
        }
    };

    formatTags (sTags) {
        let sRes = "";
        sTags = sTags.replace(/V([0-3][ea]?)[itpqnmr_eaxz]+/, "V$1");
        let m;
        while ((m = this._zTag.exec(sTags)) !== null) {
            sRes += _dTAGS.get(m[0]);
            if (sRes.length > 100) {
                break;






>



>







 







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










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





|


|

|

|







 







|

|







 







|







1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
...
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
...
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
...
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
// Grammalecte - Lexicographe
// License: MPL 2

"use strict";

${string}
${map}


const helpers = require("resource://grammalecte/helpers.js");
const tkz = require("resource://grammalecte/tokenizer.js");


const _dTAGS = new Map ([
    [':G', "[mot grammatical]"],
    [':N', " nom,"],
    [':A', " adjectif,"],
    [':M1', " prénom,"],
................................................................................

    ['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"]
]);

const _dSeparator = new Map ([
    ['.', "point"],
    ['·', "point médian"],
    ['…', "points de suspension"],
    [';', "point-virgule"],
    [',', "virgule"],
    ['?', "point d’interrogation"],
    ['!', "point d’exclamation"],
    ['(', "parenthèse ouvrante"],
    [')', "parenthèse fermante"],
    ['[', "crochet ouvrante"],
    [']', "crochet fermante"],
    ['{', "accolade ouvrante"],
    ['}', "accolade fermante"],
    ['—', "tiret cadratin"],
    ['–', "tiret demi-cadratin"],
    ['«', "guillemet ouvrant (chevrons)"],
    ['»', "guillemet fermant (chevrons)"],
    ['“', "guillemet ouvrant double"],
    ['”', "guillemet fermant double"],
    ['‘', "guillemet ouvrant"],
    ['’', "guillemet fermant"],
]);


class Lexicographe {

    constructor (oDict) {
        this.oDict = oDict;
        this._zElidedPrefix = new RegExp ("^([dljmtsncç]|quoiqu|lorsqu|jusqu|puisqu|qu)['’](.+)", "i");
        this._zCompoundWord = new RegExp ("([a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ]+)-((?: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)$", "i");
        this._zTag = new RegExp ("[:;/][a-zA-Zà-ö0-9À-Öø-ÿØ-ßĀ-ʯ*][^:;/]*", "g");
    };

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        let m = null;
        try {
            helpers.echo(oToken);
            switch (oToken.sType) {
                case 'SEPARATOR':
                    return [oToken.sType, oToken.sValue, _dSeparator._get(oToken.sValue, "caractère indéterminé")];
                    break;
                case 'NUM':
                    return [oToken.sType, oToken.sValue, "nombre"];
                    break;
                case 'LINK':
                    return [oToken.sType, oToken.sValue.slice(0,40)+"…", "hyperlien"];
                    break;
                case 'ELPFX':
                    sTemp = oToken.sValue.replace("’", "'").replace("`", "'").toLowerCase();
                    return [oToken.sType, oToken.sValue, _dPFX._get(sTemp, "préfixe élidé inconnu")];
                    break;
                case 'WORD': 
                    if (oToken.sValue._count("-") > 4) {
                        return ["COMPLEX", oToken.sValue, "élément complexe indéterminé"];
                    }
                    else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [ for (s of lMorph) if (s.includes(":")) this._formatTags(s) ];
                        return [ oToken.sType, oToken.sValue, [aElem] ];
                    }
                    else if (m = this._zCompoundWord.exec(oToken.sValue)) {
                        // mots composés
                        let lMorph = this.oDict.getMorph(m[1]);
                        let aElem = [ for (s of lMorph) if (s.includes(":")) this._formatTags(s) ];
                        aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase()));
                        return [ oToken.sType, oToken.sValue, [aElem] ];
                    }
                    else {
                        return ["INCONNU", oToken.sValue, "inconnu du dictionnaire"];
                    }
                    break;
            }
        }
        catch (e) {
            helpers.logerror(e);
        }
        return null
    };

    getHTMLForText (sText) {
        sText = sText.replace(/[.,.?!:;…\/()\[\]“”«»"„{}–—#+*<>%=\n]/g, " ").replace(/\s+/g, " ");
        let iStart = 0;
        let iEnd = 0;
        let sHtml = '<div class="paragraph">\n';
        while ((iEnd = sText.indexOf(" ", iStart)) !== -1) {
            sHtml += this.getHTMLForToken(sText.slice(iStart, iEnd));
            iStart = iEnd + 1;
        }
        sHtml += this.getHTMLForToken(sText.slice(iStart));
        return sHtml + '</div>\n';
    };

    getHTMLForToken (sWord) {
        try {
            if (!sWord) {
                return "";
            }
            if (sWord._count("-") > 4) {
                return '<p><b class="mbok">' + sWord + "</b> <s>:</s> élément complexe indéterminé</p>\n";
            }
................................................................................
            let m2 = this._zCompoundWord.exec(sWord);
            if (m2 !== null) {
                sWord = m2[1];
            }
            // Morphologies
            let lMorph = this.oDict.getMorph(sWord);
            if (lMorph.length === 1) {
                sHtml += "<p><b>" + sWord + "</b> <s>:</s> " + this._formatTags(lMorph[0]) + "</p>\n";
            } else if (lMorph.length > 1) {
                sHtml += "<p><b>" + sWord + "</b><ul><li>" + [for (s of lMorph) if (s.includes(":")) this._formatTags(s)].join(" </li><li> ") + "</li></ul></p>\n";
            } else {
                sHtml += '<p><b class="unknown">' + sWord + "</b> <s>:</s>  absent du dictionnaire<p>\n";
            }
            // suffixe d’un mot composé
            if (m2) {
                sHtml += "<p>-<b>" + m2[2] + "</b> <s>:</s> " + this._formatSuffix(m2[2].toLowerCase()) + "</p>\n";
            }
................................................................................
        }
        catch (e) {
            helpers.logerror(e);
            return "#erreur";
        }
    };

    _formatTags (sTags) {
        let sRes = "";
        sTags = sTags.replace(/V([0-3][ea]?)[itpqnmr_eaxz]+/, "V$1");
        let m;
        while ((m = this._zTag.exec(sTags)) !== null) {
            sRes += _dTAGS.get(m[0]);
            if (sRes.length > 100) {
                break;

Modified gc_lang/fr/xpi/gce_worker.js from [378b08526d] to [31c05a3116].

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
...
154
155
156
157
158
159
160

161
162



















function parse (sText, sLang, bDebug, bContext) {
    let aGrammErr = gce.parse(sText, sLang, bDebug, bContext);
    return JSON.stringify(aGrammErr);
}

function parseAndSpellcheck (sText, sLang, bDebug, bContext) {
    let aGrammErr = gce.parse(sText, sLang, bDebug, bContext);
    let aSpellErr = [];
    for (let oToken of oTokenizer.genTokens(sText)) {
        if (oToken.sType === 'WORD' && !oDict.isValidToken(oToken.sValue)) {
            aSpellErr.push(oToken);
        }
    }
    return JSON.stringify({ aGrammErr: aGrammErr, aSpellErr: aSpellErr });
}

function parseAndTag (sText, iParagraph, sLang, bDebug) {
    sText = text.addHtmlEntities(sText);
    let aSpellErr = [];
    for (let oToken of oTokenizer.genTokens(sText)) {
        if (oToken.sType === 'WORD' && !oDict.isValidToken(oToken.sValue)) {
            aSpellErr.push(oToken);
        }
    }
    let aGrammErr = gce.parse(sText, sLang, bDebug);

    let sHtml = text.tagParagraph(sText, iParagraph, aGrammErr, aSpellErr);
    return sHtml;
}

function parseAndGenerateParagraph (sText, iParagraph, sLang, bDebug) {
    return text.createHTMLBlock(parseAndTag(sText, iParagraph, sLang, bDebug), iParagraph);
}
................................................................................
    return sAllRes;
}


// Lexicographer

function analyzeWords (sText) {

    return oLxg.analyzeText(sText);
}


























|
<
<
<
<
<





<
<
<
<
<
<

>







 







>
|

>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
82
83
84
85
86
87
88
89





90
91
92
93
94






95
96
97
98
99
100
101
102
103
...
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
function parse (sText, sLang, bDebug, bContext) {
    let aGrammErr = gce.parse(sText, sLang, bDebug, bContext);
    return JSON.stringify(aGrammErr);
}

function parseAndSpellcheck (sText, sLang, bDebug, bContext) {
    let aGrammErr = gce.parse(sText, sLang, bDebug, bContext);
    let aSpellErr = oTokenizer.getSpellingErrors(sText, oDict);





    return JSON.stringify({ aGrammErr: aGrammErr, aSpellErr: aSpellErr });
}

function parseAndTag (sText, iParagraph, sLang, bDebug) {
    sText = text.addHtmlEntities(sText);






    let aGrammErr = gce.parse(sText, sLang, bDebug);
    let aSpellErr = oTokenizer.getSpellingErrors(sText, oDict);
    let sHtml = text.tagParagraph(sText, iParagraph, aGrammErr, aSpellErr);
    return sHtml;
}

function parseAndGenerateParagraph (sText, iParagraph, sLang, bDebug) {
    return text.createHTMLBlock(parseAndTag(sText, iParagraph, sLang, bDebug), iParagraph);
}
................................................................................
    return sAllRes;
}


// Lexicographer

function analyzeWords (sText) {
    getListOfElements(sText);
    return oLxg.getHTMLForText(sText);
}

function getListOfElements (sText) {
    try {
        helpers.echo("=================================================");
        let aElem = [];
        let aRes = null;
        for (let oToken of oTokenizer.genTokens(sText)) {
            aRes = oLxg.getInfoForToken(oToken);
            if (aRes) {
                helpers.echo(aRes);
                aElem = aElem.concat(aRes);
            }
        }
        return JSON.stringify(aElem);
    }
    catch (e) {
        helpers.logerror(e);
    }
}

Modified gc_lang/fr/xpi/package.json from [f43a7abb52] to [7e2435c537].

1
2
3
4
5
6
7
8
9
10
11
12
{
  "name": "grammalecte-fr",
  "title": "Grammalecte [fr]",
  "id": "French-GC@grammalecte.net",
  "version": "0.5.17.2",
  "description": "Correcteur grammatical pour le français",
  "homepage": "http://www.dicollecte.org/grammalecte",
  "main": "ui.js",
  "icon": "data/img/icon-48.png",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1"
  },




|







1
2
3
4
5
6
7
8
9
10
11
12
{
  "name": "grammalecte-fr",
  "title": "Grammalecte [fr]",
  "id": "French-GC@grammalecte.net",
  "version": "0.5.18",
  "description": "Correcteur grammatical pour le français",
  "homepage": "http://www.dicollecte.org/grammalecte",
  "main": "ui.js",
  "icon": "data/img/icon-48.png",
  "scripts": {
    "test": "echo \"Error: no test specified\" && exit 1"
  },