Grammalecte  Changes On Branch 4e84b8a6cffd2022

Changes In Branch Lexicographe Through [4e84b8a6cf] Excluding Merge-Ins

This is equivalent to a diff from 4ffad6e596 to 4e84b8a6cf

2017-10-30
20:50
[fr] lexicographe: analyse des sous-parties des locutions check-in: 2ef57e5809 user: olr tags: fr, Lexicographe
16:44
[fr] lexicographe: minor changes check-in: 4e84b8a6cf user: olr tags: fr, Lexicographe
13:48
[fr] lexicographe: restructuration des données, réduction de l’échantillon de test, élisons dorénavant acceptées check-in: f8019de85c user: olr tags: fr, Lexicographe
2017-10-29
11:19
Détection des locutions dans le lexicographe check-in: 47ddd1a06d user: IllusionPerdu tags: Lexicographe
2017-10-28
19:58
[build][fr] build_data: code cleaning check-in: ba1b8fe0e2 user: olr tags: trunk, fr, build
13:47
[build][fr] rename locutions files check-in: 4ffad6e596 user: olr tags: trunk, fr, build
13:17
[build][fr] data: locutions check-in: e356116b6e user: olr tags: trunk, fr, build

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 [f2198525f4].

8
9
10
11
12
13
14

15
16
17
18
19
20
21
import json
import os

import grammalecte.ibdawg as ibdawg
from grammalecte.echo import echo
from grammalecte.str_transform import defineSuffixCode
import grammalecte.fr.conj as conj



class cd:
    """Context manager for changing the current working directory"""
    def __init__ (self, newPath):
        self.newPath = os.path.expanduser(newPath)








>







8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
import json
import os

import grammalecte.ibdawg as ibdawg
from grammalecte.echo import echo
from grammalecte.str_transform import defineSuffixCode
import grammalecte.fr.conj as conj
import grammalecte.tokenizer as tkz


class cd:
    """Context manager for changing the current working directory"""
    def __init__ (self, newPath):
        self.newPath = os.path.expanduser(newPath)

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:







|







255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
                '    "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:
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


def makeLocutions (sp, bJS=False):
    "compile list of locutions in JSON"
    print("> Locutions ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    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))


def before (spLaunch, dVars, bJS=False):
    print("========== Build Hunspell dictionaries ==========")
    makeDictionaries(spLaunch, dVars['oxt_version'])


def after (spLaunch, dVars, bJS=False):
    print("========== Build French data ==========")
    makeMfsp(spLaunch, bJS)
    makeConj(spLaunch, bJS)
    makePhonetTable(spLaunch, bJS)
    makeLocutions(spLaunch, bJS)







|
>


<
|
>
>
|



>


|


|













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


def makeLocutions (sp, bJS=False):
    "compile list of locutions in JSON"
    print("> Locutions ", end="")
    print("(Python et JavaScript)"  if bJS  else "(Python seulement)")
    with open(sp+"/data/locutions.txt", 'r', encoding='utf-8') as hSrc:
        dLocGraph = {}
        oTokenizer = tkz.Tokenizer("fr")
        for sLine in hSrc.readlines():
            if not sLine.startswith("#") and sLine.strip():

                dCur = dLocGraph
                sLoc, sTag = sLine.strip().split("\t")
                for oToken in oTokenizer.genTokens(sLoc.strip()):
                    sWord = oToken["sValue"]
                    if sWord not in dCur:
                        dCur[sWord] = {}
                    dCur = dCur[sWord]
                dCur[":"] = sTag

    sCode = "# generated data (do not edit)\n\n" + \
            "dLocutions = " + str(dLocGraph) + "\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(dLocGraph, ensure_ascii=False))


def before (spLaunch, dVars, bJS=False):
    print("========== Build Hunspell dictionaries ==========")
    makeDictionaries(spLaunch, dVars['oxt_version'])


def after (spLaunch, dVars, bJS=False):
    print("========== Build French data ==========")
    makeMfsp(spLaunch, bJS)
    makeConj(spLaunch, bJS)
    makePhonetTable(spLaunch, bJS)
    makeLocutions(spLaunch, bJS)

Modified gc_lang/fr/data/locutions.txt from [190d018874] to [e32c77973b].

1

2
3
4

5
6




7
8
à califourchon

à cœur joie
à cœur ouvert
à corps perdu

à perte de vue
à visage découvert




par ailleurs
par acquit de conscience
|
>
|
|
|
>
|
|
>
>
>
>
|
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
à califourchon
à contrecœur	:Ŵ
à cœur joie
à cœur ouvert
à corps perdu
à bâtons rompus	:Ŵ
à perte de vue
à visage découvert
à vue d’œil	:Ŵ
à l’aveuglette	:Ŵ
ad hominem	:Ŵ
en tout et pour tout	:Ŵ
par ailleurs
par acquit de conscience

Modified gc_lang/fr/modules-js/lexicographe.js from [08da929c5c] to [f3882fd6a0].

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
80
    [':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.),"],
    [':Ô', " locution pronominales (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"],

102
103
104
105
106
107
108
109

110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
    [';S', " : symbole (unité de mesure)"],

    ['/*', ""],
    ['/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"],







|
>


|















|









|


|



|


















|







104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
    [';S', " : symbole (unité de mesure)"],

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

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
    ['<', "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 = "";







|

>
>
>
|
|
|
>




|




>
>
>
|
>


>
>
|
>
>


>
>
|
>
>



>
>
>
|
>


>
>
|
>
>

|

>
>
>
|
|
|


|
|

>
>
|
>
|
|



|
|


>
>
|
>
|
|
>
>
>
|
>



<
|







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


class Lexicographe {

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

        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 object {sType, sValue, aLabel}
        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 = "";
287
288
289
290
291
292
293
294
295
296








297


298









































































299
300
301
        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;
}







|

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



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
        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 = [];
        if (sText !== "") {
            for (let oToken of this.oTokenizer.genTokens(sText)) {
                if (bInfo) {
                    let aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else if (oToken.sType !== "SPACE") {
                    aElem.push(oToken);
                }
            }
        }
        return aElem;
    }

    getListOfTokensReduc (sText, bInfo=true) {
        let aTokenList = this.getListOfTokens(sText.replace("'", "’").trim(), false);
        let iKey = 0;
        let aElem = [];
        do {
            let oToken = aTokenList[iKey];
            let sMorphLoc = '';
            let aTokenTempList = [oToken];
            if (oToken.sType == "WORD" || oToken.sType == "ELPFX"){
                let iKeyTree = iKey + 1;
                let oLocNode = this.oLocGraph[oToken.sValue.toLowerCase()];
                while (oLocNode) {
                    let oTokenNext = aTokenList[iKeyTree];
                    iKeyTree++;
                    if (oTokenNext) {
                        oLocNode = oLocNode[oTokenNext.sValue.toLowerCase()];
                    }
                    if (oLocNode && iKeyTree <= aTokenList.length) {
                        sMorphLoc = oLocNode[":"];
                        aTokenTempList.push(oTokenNext);
                    } else {
                        break;
                    }
                }
            }

            if (sMorphLoc) {
                let sWord = '';
                for (let oTokenWord of aTokenTempList) {
                    sWord += oTokenWord.sValue+' ';
                }
                let oTokenLocution = {
                    'nStart': aTokenTempList[0].nStart,
                    'nEnd': aTokenTempList[aTokenTempList.length-1].nEnd,
                    'sType': "LOC",
                    'sValue': sWord.replace('’ ','’').trim()
                };
                if (bInfo) {
                    let aFormatedTag = [];
                    for (let sTagMulti of sMorphLoc.split('|') ){
                        aFormatedTag.push( this._formatTags(sTagMulti).replace(/( \(él.\))/g,'') );
                    }
                    aElem.push({
                        sType: oTokenLocution.sType,
                        sValue: oTokenLocution.sValue,
                        aLabel: aFormatedTag
                    });
                } else {
                    aElem.push(oTokenLocution);
                }
                iKey = iKey + aTokenTempList.length;
            } else {
                if (bInfo) {
                    let aRes = this.getInfoForToken(oToken);
                    if (aRes) {
                        aElem.push(aRes);
                    }
                } else {
                    aElem.push(oToken);
                }
                iKey++;
            }
        } while (iKey < aTokenList.length);
        return aElem;
    }
}


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

Modified gc_lang/fr/modules-js/locutions_data.json from [12115cc355] to [18410d013e].

1
{"à": {"califourchon": {}, "cœur": {"joie": {}, "ouvert": {}}, "corps": {"perdu": {}}, "perte": {"de": {"vue": {}}}, "visage": {"découvert": {}}}, "par": {"ailleurs": {}, "acquit": {"de": {"conscience": {}}}}}
|
1
{"à": {"califourchon": {":": ":Ŵ"}, "contrecœur": {":": ":Ŵ"}, "cœur": {"joie": {":": ":Ŵ"}, "ouvert": {":": ":Ŵ"}}, "corps": {"perdu": {":": ":Ŵ"}}, "bâtons": {"rompus": {":": ":Ŵ"}}, "perte": {"de": {"vue": {":": ":Ŵ"}}}, "visage": {"découvert": {":": ":Ŵ"}}, "vue": {"d’": {"œil": {":": ":Ŵ"}}}, "l’": {"aveuglette": {":": ":Ŵ"}}}, "ad": {"hominem": {":": ":Ŵ"}}, "en": {"tout": {"et": {"pour": {"tout": {":": ":Ŵ"}}}}}, "par": {"ailleurs": {":": ":Ŵ"}, "acquit": {"de": {"conscience": {":": ":Ŵ"}}}}}

Modified gc_lang/fr/modules/locutions_data.py from [4e9754ba4b] to [02f99ec70a].

1
2
3
# generated data (do not edit)

dLocutions = {'à': {'califourchon': {}, 'cœur': {'joie': {}, 'ouvert': {}}, 'corps': {'perdu': {}}, 'perte': {'de': {'vue': {}}}, 'visage': {'découvert': {}}}, 'par': {'ailleurs': {}, 'acquit': {'de': {'conscience': {}}}}}


|
1
2
3
# generated data (do not edit)

dLocutions = {'à': {'califourchon': {':': ':Ŵ'}, 'contrecœur': {':': ':Ŵ'}, 'cœur': {'joie': {':': ':Ŵ'}, 'ouvert': {':': ':Ŵ'}}, 'corps': {'perdu': {':': ':Ŵ'}}, 'bâtons': {'rompus': {':': ':Ŵ'}}, 'perte': {'de': {'vue': {':': ':Ŵ'}}}, 'visage': {'découvert': {':': ':Ŵ'}}, 'vue': {'d’': {'œil': {':': ':Ŵ'}}}, 'l’': {'aveuglette': {':': ':Ŵ'}}}, 'ad': {'hominem': {':': ':Ŵ'}}, 'en': {'tout': {'et': {'pour': {'tout': {':': ':Ŵ'}}}}}, 'par': {'ailleurs': {':': ':Ŵ'}, 'acquit': {'de': {'conscience': {':': ':Ŵ'}}}}}

Modified gc_lang/fr/webext/content_scripts/panel_lxg.css from [58f7a11f55] to [ccbb028287].

52
53
54
55
56
57
58



59
60
61
62
63
64
65
}
.grammalecte_lxg_morph_list {
    padding: 2px 0 10px 20px;
}
.grammalecte_lxg_morph_elem {
    color: hsl(0, 0%, 0%);
}



.grammalecte_lxg_token_WORD {
    background-color: hsla(150, 50%, 50%, 1);
}
.grammalecte_lxg_token_ELPFX {
    background-color: hsla(150, 30%, 50%, 1);
}
.grammalecte_lxg_token_UNKNOWN {







>
>
>







52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
}
.grammalecte_lxg_morph_list {
    padding: 2px 0 10px 20px;
}
.grammalecte_lxg_morph_elem {
    color: hsl(0, 0%, 0%);
}
.grammalecte_lxg_token_LOC {
    background-color: hsla(150, 50%, 30%, 1);
}
.grammalecte_lxg_token_WORD {
    background-color: hsla(150, 50%, 50%, 1);
}
.grammalecte_lxg_token_ELPFX {
    background-color: hsla(150, 30%, 50%, 1);
}
.grammalecte_lxg_token_UNKNOWN {

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));
    }
}