Grammalecte  Check-in [47ddd1a06d]

Overview
Comment:Détection des locutions dans le lexicographe
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | Lexicographe
Files: files | file ages | folders
SHA3-256: 47ddd1a06d9f24427a0c7e4a467a8055558c1ee68543bc47cdac5b848d898e26
User & Date: IllusionPerdu on 2017-10-29 11:19:23
Other Links: branch diff | manifest | tags
Context
2017-10-29
11:56
Quelques corrections dans le fichier locutions.txt check-in: a6bed5e7d3 user: IllusionPerdu tags: Lexicographe
11:19
Détection des locutions dans le lexicographe check-in: 47ddd1a06d user: IllusionPerdu tags: Lexicographe
2017-10-28
13:47
[build][fr] rename locutions files check-in: 4ffad6e596 user: olr tags: trunk, fr, build
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Modified gc_core/js/text.js from [9bf91b3594] to [abcdad5f85]. 

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

// JavaScript
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}


var text = {
    getParagraph: function* (sText) {
        // generator: returns paragraphs of text
        let iStart = 0;
        let iEnd = 0;
        sText = sText.replace("\r\n", "\n").replace("\r", "\n");
        while ((iEnd = sText.indexOf("\n", iStart)) !== -1) {
            yield sText.slice(iStart, iEnd);
            iStart = iEnd + 1;
        }
        yield sText.slice(iStart);
    },

    wrap: function* (sText, nWidth=80) {














|




|








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

// JavaScript
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}


var text = {
    getParagraph: function* (sText, sSepParagraph = "\n") {
        // generator: returns paragraphs of text
        let iStart = 0;
        let iEnd = 0;
        sText = sText.replace("\r\n", "\n").replace("\r", "\n");
        while ((iEnd = sText.indexOf(sSepParagraph, iStart)) !== -1) {
            yield sText.slice(iStart, iEnd);
            iStart = iEnd + 1;
        }
        yield sText.slice(iStart);
    },

    wrap: function* (sText, nWidth=80) {
︙︙
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

        }
        yield sText;
    },

    getReadableError: function (oErr) {
        // Returns an error oErr as a readable error
        try {
            let sResult = "\n* " + oErr['nStart'] + ":" + oErr['nEnd'] 
                        + "  # " + oErr['sLineId'] + "  # " + oErr['sRuleId'] + ":\n";
            sResult += "  " + oErr["sMessage"];
            if (oErr["aSuggestions"].length > 0) {
                sResult += "\n  > Suggestions : " + oErr["aSuggestions"].join(" | ");
            }
            if (oErr["URL"] !== "") {
                sResult += "\n  > URL: " + oErr["URL"];








|








41
42
43
44
45
46
47
48
49
50
51
52
53
54
55

        }
        yield sText;
    },

    getReadableError: function (oErr) {
        // Returns an error oErr as a readable error
        try {
            let sResult = "\n* " + oErr['nStart'] + ":" + oErr['nEnd']
                        + "  # " + oErr['sLineId'] + "  # " + oErr['sRuleId'] + ":\n";
            sResult += "  " + oErr["sMessage"];
            if (oErr["aSuggestions"].length > 0) {
                sResult += "\n  > Suggestions : " + oErr["aSuggestions"].join(" | ");
            }
            if (oErr["URL"] !== "") {
                sResult += "\n  > URL: " + oErr["URL"];
︙︙

Modified gc_lang/fr/build_data.py from [1ffed9614b] to [b7abe812ee].

︙︙
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268

                '    "dMasForm": ' +  json.dumps(dMasForm, ensure_ascii=False) + "\n}"
        open(sp+"/modules-js/mfsp_data.json", "w", encoding="utf-8", newline="\n").write(sCode)


def makePhonetTable (sp, bJS=False):
    print("> Correspondances phonétiques ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    
    try:
        oDict = ibdawg.IBDAWG("French.bdic")
    except:
        traceback.print_exc()
        return

    with open(sp+"/data/phonet_simil.txt", 'r', encoding='utf-8') as hSrc:








|








254
255
256
257
258
259
260
261
262
263
264
265
266
267
268

                '    "dMasForm": ' +  json.dumps(dMasForm, ensure_ascii=False) + "\n}"
        open(sp+"/modules-js/mfsp_data.json", "w", encoding="utf-8", newline="\n").write(sCode)


def makePhonetTable (sp, bJS=False):
    print("> Correspondances phonétiques ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")

    try:
        oDict = ibdawg.IBDAWG("French.bdic")
    except:
        traceback.print_exc()
        return

    with open(sp+"/data/phonet_simil.txt", 'r', encoding='utf-8') as hSrc:
︙︙
314
315
316
317
318
319
320
321
322


323
324
325
326
327
328
329

    with open(sp+"/data/locutions.txt", 'r', encoding='utf-8') as hSrc:
        dLocutions = {}
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():
                lElem = sLine.strip().split()
                dCur = dLocutions
                for sWord in lElem:
                    if sWord not in dCur:
                        dCur[sWord] = {}


                    dCur = dCur[sWord]

    sCode = "# generated data (do not edit)\n\n" + \
            "dLocutions = " + str(dLocutions) + "\n"
    open(sp+"/modules/locutions_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
    if bJS:
        open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocutions, ensure_ascii=False))








|

>
>








314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331

    with open(sp+"/data/locutions.txt", 'r', encoding='utf-8') as hSrc:
        dLocutions = {}
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():
                lElem = sLine.strip().split()
                dCur = dLocutions
                for sWord in lElem:
                    if sWord not in dCur and not sWord.startswith(":"):
                        dCur[sWord] = {}
                    if sWord not in dCur and sWord.startswith(":"):
                        dCur[sWord] = ''
                    dCur = dCur[sWord]

    sCode = "# generated data (do not edit)\n\n" + \
            "dLocutions = " + str(dLocutions) + "\n"
    open(sp+"/modules/locutions_data.py", "w", encoding="utf-8", newline="\n").write(sCode)
    if bJS:
        open(sp+"/modules-js/locutions_data.json", "w", encoding="utf-8", newline="\n").write(json.dumps(dLocutions, ensure_ascii=False))
︙︙

Modified gc_lang/fr/data/locutions.txt from [190d018874] to [61c34d6abd].

cannot compute difference between binary files

Modified gc_lang/fr/modules-js/lexicographe.js from [08da929c5c] to [543985fcfa]. 

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

// Grammalecte - Lexicographe
// License: MPL 2
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";

${string}
${map}


if (typeof(require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}

const _dTAGS = new Map ([
    [':G', "[mot grammatical]"],
    [':N', " nom,"],
    [':A', " adjectif,"],
    [':M1', " prénom,"],
    [':M2', " patronyme,"],
    [':MP', " nom propre,"],
    [':W', " adverbe,"],












|



|








1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

// Grammalecte - Lexicographe
// License: MPL 2
/*jslint esversion: 6*/
/*global require,exports*/

"use strict";

${string}
${map}


if (typeof (require) !== 'undefined') {
    var helpers = require("resource://grammalecte/helpers.js");
}

const _dTAGS = new Map([
    [':G', "[mot grammatical]"],
    [':N', " nom,"],
    [':A', " adjectif,"],
    [':M1', " prénom,"],
    [':M2', " patronyme,"],
    [':MP', " nom propre,"],
    [':W', " adverbe,"],
︙︙
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

    [':Oi', " pronom indéfini,"],
    [':On', " pronom indéfini négatif,"],
    [':Ot', " pronom interrogatif,"],
    [':Or', " pronom relatif,"],
    [':Ow', " pronom adverbial,"],
    [':Os', " pronom personnel sujet,"],
    [':Oo', " pronom personnel objet,"],
    [':C',  " conjonction,"],
    [':Ĉ',  " conjonction (él.),"],
    [':Cc', " conjonction de coordination,"],
    [':Cs', " conjonction de subordination,"],
    [':Ĉs', " conjonction de subordination (él.),"],
    



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

    [':Zp', " préfixe,"],
    [':Zs', " suffixe,"],

    [':V1', " verbe (1ᵉʳ gr.),"],
    [':V2', " verbe (2ᵉ gr.),"],
    [':V3', " verbe (3ᵉ gr.),"],
    [':V0e', " verbe,"],
    [':V0a', " verbe,"],

    [':O1', " 1ʳᵉ pers.,"],
    [':O2', " 2ᵉ pers.,"],
    [':O3', " 3ᵉ pers.,"],
    
    [':e', " épicène"],
    [':m', " masculin"],
    [':f', " féminin"],
    [':s', " singulier"],
    [':p', " pluriel"],
    [':i', " invariable"],









|
<


<
|
>
>
>



















|








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

    [':Oi', " pronom indéfini,"],
    [':On', " pronom indéfini négatif,"],
    [':Ot', " pronom interrogatif,"],
    [':Or', " pronom relatif,"],
    [':Ow', " pronom adverbial,"],
    [':Os', " pronom personnel sujet,"],
    [':Oo', " pronom personnel objet,"],
    [':C', " conjonction,"],

    [':Cc', " conjonction de coordination,"],
    [':Cs', " conjonction de subordination,"],


    [':Ĺ', " locution,"],
    [':Ĉ', " locution conjonctivale (él.),"],
    [':Ĉs', " locution conjonctivale de subordination (él.),"],
    [':Ŵ', " locution adverbiale (él.),"],
    [':Ñ', " locution nominale (él.),"],
    [':Â', " locution adjectivale (él.),"],
    [':Ṽ', " locution verbale (él.),"],
    [':Ŕ', " locution prépositive (él.),"],
    [':Ĵ', " locution interjective (él.),"],

    [':Zp', " préfixe,"],
    [':Zs', " suffixe,"],

    [':V1', " verbe (1ᵉʳ gr.),"],
    [':V2', " verbe (2ᵉ gr.),"],
    [':V3', " verbe (3ᵉ gr.),"],
    [':V0e', " verbe,"],
    [':V0a', " verbe,"],

    [':O1', " 1ʳᵉ pers.,"],
    [':O2', " 2ᵉ pers.,"],
    [':O3', " 3ᵉ pers.,"],

    [':e', " épicène"],
    [':m', " masculin"],
    [':f', " féminin"],
    [':s', " singulier"],
    [':p', " pluriel"],
    [':i', " invariable"],
︙︙
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

    ['/C', " {classique}"],
    ['/M', ""],
    ['/R', " {réforme}"],
    ['/A', ""],
    ['/X', ""]
]);

const _dPFX = new Map ([
    ['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"],
    ['quoiqu', "(quoique), conjonction de subordination"],
    ['jusqu', "(jusque), préposition"]
]);

const _dAD = new Map ([
    ['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"]
]);

const _dSeparator = new Map ([
    ['.', "point"],
    ['·', "point médian"],
    ['…', "points de suspension"],
    [':', "deux-points"],
    [';', "point-virgule"],
    [',', "virgule"],
    ['?', "point d’interrogation"],








|















|









|


|



|


















|








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

    ['/C', " {classique}"],
    ['/M', ""],
    ['/R', " {réforme}"],
    ['/A', ""],
    ['/X', ""]
]);

const _dPFX = new Map([
    ['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"],
    ['quoiqu', "(quoique), conjonction de subordination"],
    ['jusqu', "(jusque), préposition"]
]);

const _dAD = new Map([
    ['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"]
]);

const _dSeparator = new Map([
    ['.', "point"],
    ['·', "point médian"],
    ['…', "points de suspension"],
    [':', "deux-points"],
    [';', "point-virgule"],
    [',', "virgule"],
    ['?', "point d’interrogation"],
︙︙
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

    ['<', "inférieur à"],
    ['>', "supérieur à"],
]);


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
        // return a list [type, token_string, values]
        let m = null;
        try {
            switch (oToken.sType) {
                case 'SEPARATOR':



                    return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dSeparator.gl_get(oToken.sValue, "caractère indéterminé")] };

                    break;
                case 'NUM':


                    return { sType: oToken.sType, sValue: oToken.sValue, aLabel: ["nombre"] };


                    break;
                case 'LINK':


                    return { sType: oToken.sType, sValue: oToken.sValue.slice(0,40)+"…", aLabel: ["hyperlien"] };


                    break;
                case 'ELPFX':
                    let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase();



                    return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dPFX.gl_get(sTemp, "préfixe élidé inconnu")] };

                    break;
                case 'FOLDER':


                    return { sType: oToken.sType, sValue: oToken.sValue.slice(0,40)+"…", aLabel: ["dossier"] };


                    break;
                case 'WORD': 
                    if (oToken.sValue.gl_count("-") > 4) {



                        return { sType: "COMPLEX", sValue: oToken.sValue, aLabel: ["élément complexe indéterminé"] };
                    }
                    else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [];
                        for (let s of lMorph){
                            if (s.includes(":"))  aElem.push( this._formatTags(s) );
                        }


                        return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem};

                    }
                    else if (m = this._zCompoundWord.exec(oToken.sValue)) {
                        // mots composés
                        let lMorph = this.oDict.getMorph(m[1]);
                        let aElem = [];
                        for (let s of lMorph){
                            if (s.includes(":"))  aElem.push( this._formatTags(s) );
                        }
                        aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase()));


                        return { sType: oToken.sType, sValue: oToken.sValue, aLabel: aElem };

                    }
                    else {



                        return { sType: "UNKNOWN", sValue: oToken.sValue, aLabel: ["inconnu du dictionnaire"] };

                    }
                    break;
            }
        }
        catch (e) {
            helpers.logerror(e);
        }
        return null;
    }

    _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;
            }
        }
        if (sRes.startsWith(" verbe") && !sRes.endsWith("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatSuffix (s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));
        }
        if (!s.includes("-")) {
            return _dAD.get(s.replace("’", "'"));
        }
        if (s.endsWith("ous")) {
            s += '2';
        }
        let nPos = s.indexOf("-");
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos+1));
    }
}













































































































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








|

>
>
>
|
|
|
|
|
>
|






>
>
>
|
>


>
>
|
>
>


>
>
|
>
>



>
>
>
|
>


>
>
|
>
>

|

>
>
>
|
|
|


|
|

>
>
|
>
|
|



|
|


>
>
|
>
|
|
>
>
>
|
>



<
|





|




















|










|

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



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
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445

    ['<', "inférieur à"],
    ['>', "supérieur à"],
]);


class Lexicographe {

    constructor(oDict, oTokenizer, oLocution) {
        this.oDict = oDict;
        this.oTokenizer = oTokenizer;
        this.oLocution = JSON.parse(oLocution);

        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
        // return a list [type, token_string, values]
        let m = null;
        try {
            switch (oToken.sType) {
                case 'SEPARATOR':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabel: [_dSeparator.gl_get(oToken.sValue, "caractère indéterminé")]
                    };
                    break;
                case 'NUM':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabel: ["nombre"]
                    };
                    break;
                case 'LINK':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabel: ["hyperlien"]
                    };
                    break;
                case 'ELPFX':
                    let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase();
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue,
                        aLabel: [_dPFX.gl_get(sTemp, "préfixe élidé inconnu")]
                    };
                    break;
                case 'FOLDER':
                    return {
                        sType: oToken.sType,
                        sValue: oToken.sValue.slice(0, 40) + "…",
                        aLabel: ["dossier"]
                    };
                    break;
                case 'WORD':
                    if (oToken.sValue.gl_count("-") > 4) {
                        return {
                            sType: "COMPLEX",
                            sValue: oToken.sValue,
                            aLabel: ["élément complexe indéterminé"]
                        };
                    } else if (this.oDict.isValidToken(oToken.sValue)) {
                        let lMorph = this.oDict.getMorph(oToken.sValue);
                        let aElem = [];
                        for (let s of lMorph) {
                            if (s.includes(":")) aElem.push(this._formatTags(s));
                        }
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: aElem
                        };
                    } else if (m = this._zCompoundWord.exec(oToken.sValue)) {
                        // mots composés
                        let lMorph = this.oDict.getMorph(m[1]);
                        let aElem = [];
                        for (let s of lMorph) {
                            if (s.includes(":")) aElem.push(this._formatTags(s));
                        }
                        aElem.push("-" + m[2] + ": " + this._formatSuffix(m[2].toLowerCase()));
                        return {
                            sType: oToken.sType,
                            sValue: oToken.sValue,
                            aLabel: aElem
                        };
                    } else {
                        return {
                            sType: "UNKNOWN",
                            sValue: oToken.sValue,
                            aLabel: ["inconnu du dictionnaire"]
                        };
                    }
                    break;
            }

        } catch (e) {
            helpers.logerror(e);
        }
        return null;
    }

    _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;
            }
        }
        if (sRes.startsWith(" verbe") && !sRes.endsWith("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            helpers.echo(sRes);
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatSuffix(s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));
        }
        if (!s.includes("-")) {
            return _dAD.get(s.replace("’", "'"));
        }
        if (s.endsWith("ous")) {
            s += '2';
        }
        let nPos = s.indexOf("-");
        return _dAD.get(s.slice(0, nPos)) + " +" + _dAD.get(s.slice(nPos + 1));
    }

    getListOfTokens(sText, bInfo = true) {
        let aElem = [];
        sText = sText.replace("'", "’").trim();
        if (sText !== "") {
            let aRes = null;
            for (let oToken of this.oTokenizer.genTokens(sText)) {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else if (oToken.sType !== "SPACE") {
                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    elpfxToword(sELPFX){
        return sELPFX.replace('’', 'e');
    }

    getListOfTokensReduc(sText, bInfo = true) {
        let lstToken = this.getListOfTokens(sText, false);
        //console.log(lstToken);
        //console.log(this.oLocution);

        let id = 0;
        let aElem = [];
        let aRes = null;
        let isType = {'WORD':1,'ELPFX':1};
        do {
            let oToken = lstToken[id]
            let aLocution = this.oLocution[this.elpfxToword(oToken.sValue)];
            //console.log('Start cherche', oToken.sValue, aLocution);
            let stop = false;
            let start = id + 1;
            let lastTokenWord = '';
            let ok = false;
            let oLst = [];
            oLst.push(oToken);
            while (!stop && typeof aLocution !== "undefined") {
                if (start > lstToken.length){
                    break;
                }
                let typeToken = '';
                let nextToken = lstToken[start];
                //console.log(start, nextToken, aLocution);

                if ( typeof nextToken !== "undefined" ) {
                    aLocution = aLocution[this.elpfxToword(nextToken.sValue)];
                    typeToken = nextToken.sType;
                } else {
                    aLocution = "undefined";
                }

                if ( typeToken in isType && typeof aLocution !== "undefined") {
                    lastTokenWord = Object.keys(aLocution)[0];
                    start++;
                    oLst.push(nextToken);
                    //console.log( nextToken.sValue );
                } else if ( !(typeToken in isType) || typeof aLocution == "undefined") {
                    stop = true;
                    if ( lastTokenWord.substring(0, 1) == ':' ) {
                        ok = true;
                    }
                }
            };

            if ( ok ){
                let word = '';
                for (let oToken of oLst) {
                    word += oToken.sValue+' ';
                    //console.log('***',word);
                }
                id = id + oLst.length-1;
                let tmpToken = {
                    'nEnd':oLst[oLst.length-1].nEnd,
                    'nStart':oLst[0].nStart,
                    'sType':"WORD",
                    'sValue':word.replace('’ ','’').trim()
                };
                if (bInfo) {
                    aElem.push({
                        sType: tmpToken.sType,
                        sValue: tmpToken.sValue,
                        aLabel: [this._formatTags(lastTokenWord).replace(/(\(él.\))/g,'').trim()]
                    });
                } else {
                    aElem.push(tmpToken);
                }
            } else {
                if (bInfo) {
                    aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else {
                    aElem.push(oToken);
                }
            }
            id++;
        } while (id < lstToken.length);
        return aElem;
    }
}


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

Modified gc_lang/fr/modules-js/locutions_data.json from [12115cc355] to [dc783a64f8].

cannot compute difference between binary files

Modified gc_lang/fr/modules-js/phonet_data.json from [63815e6d96] to [45669375f1].

cannot compute difference between binary files

Modified gc_lang/fr/modules/locutions_data.py from [4e9754ba4b] to [3a4e4822b6].

cannot compute difference between binary files

Modified gc_lang/fr/modules/phonet_data.py from [be2bb20c17] to [497cbd30f5].

cannot compute difference between binary files

Modified gc_lang/fr/webext/gce_worker.js from [ad4b1695da] to [ac6f473dd4].

︙︙
136
137
138
139
140
141
142

143
144
145
146
147
148
149


let bInitDone = false;

let oDict = null;
let oTokenizer = null;
let oLxg = null;
let oTest = null;



/*
    Technical note:
    This worker don’t work as a PromiseWorker (which returns a promise),  so when we send request
    to this worker, we can’t wait the return of the answer just after the request made.
    The answer is received by the background in another function (onmessage).








>








136
137
138
139
140
141
142
143
144
145
146
147
148
149
150


let bInitDone = false;

let oDict = null;
let oTokenizer = null;
let oLxg = null;
let oTest = null;
let oLocution = null;


/*
    Technical note:
    This worker don’t work as a PromiseWorker (which returns a promise),  so when we send request
    to this worker, we can’t wait the return of the answer just after the request made.
    The answer is received by the background in another function (onmessage).
︙︙
158
159
160
161
162
163
164




165
166
167
168
169
170
171
172
173
174
175
176

            conj.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/conj_data.json"));
            phonet.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/phonet_data.json"));
            mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json"));
            //console.log("[Worker] Modules have been initialized…");
            gc_engine.load(sContext, sExtensionPath+"grammalecte/_dictionaries");
            oDict = gc_engine.getDictionary();
            oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json");




            oLxg = new Lexicographe(oDict);
            if (dOptions !== null) {
                gc_engine.setOptions(dOptions);
            }
            oTokenizer = new Tokenizer("fr");
            //tests();
            bInitDone = true;
        } else {
            console.log("[Worker] Already initialized…")
        }
        // we always retrieve options from the gc_engine, for setOptions filters obsolete options
        postMessage(createResponse("init", gc_engine.getOptions(), dInfo, true));








>
>
>
>
|



<








159
160
161
162
163
164
165
166
167
168
169
170
171
172
173

174
175
176
177
178
179
180

            conj.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/conj_data.json"));
            phonet.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/phonet_data.json"));
            mfsp.init(helpers.loadFile(sExtensionPath + "/grammalecte/fr/mfsp_data.json"));
            //console.log("[Worker] Modules have been initialized…");
            gc_engine.load(sContext, sExtensionPath+"grammalecte/_dictionaries");
            oDict = gc_engine.getDictionary();
            oTest = new TestGrammarChecking(gc_engine, sExtensionPath+"/grammalecte/fr/tests_data.json");
            oTokenizer = new Tokenizer("fr");

            oLocution =  helpers.loadFile(sExtensionPath + "/grammalecte/fr/locutions_data.json");

            oLxg = new Lexicographe(oDict, oTokenizer, oLocution);
            if (dOptions !== null) {
                gc_engine.setOptions(dOptions);
            }

            //tests();
            bInitDone = true;
        } else {
            console.log("[Worker] Already initialized…")
        }
        // we always retrieve options from the gc_engine, for setOptions filters obsolete options
        postMessage(createResponse("init", gc_engine.getOptions(), dInfo, true));
︙︙
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


// Lexicographer

function getListOfTokens (sText, dInfo={}) {
    try {
        for (let sParagraph of text.getParagraph(sText)) {
            if (sParagraph.trim() !== "") {
                let aElem = [];
                let aRes = null;
                for (let oToken of oTokenizer.genTokens(sParagraph)) {
                    aRes = oLxg.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                }
                postMessage(createResponse("getListOfTokens", aElem, dInfo, false));
            }
        }
        postMessage(createResponse("getListOfTokens", null, dInfo, true));
    }
    catch (e) {
        helpers.logerror(e);
        postMessage(createResponse("getListOfTokens", createErrorResult(e, "no tokens"), dInfo, true, true));
    }
}








<
<
<
<
<
<
<
<
|










298
299
300
301
302
303
304








305
306
307
308
309
310
311
312
313
314


// Lexicographer

function getListOfTokens (sText, dInfo={}) {
    try {
        for (let sParagraph of text.getParagraph(sText)) {
            if (sParagraph.trim() !== "") {








                postMessage(createResponse("getListOfTokens", oLxg.getListOfTokensReduc(sParagraph, true), dInfo, false));
            }
        }
        postMessage(createResponse("getListOfTokens", null, dInfo, true));
    }
    catch (e) {
        helpers.logerror(e);
        postMessage(createResponse("getListOfTokens", createErrorResult(e, "no tokens"), dInfo, true, true));
    }
}

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.023s