Grammalecte  Check-in [afcd96f2ab]

Overview
Comment:[fr] lexicographe: code cleaning
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | fr | Lexicographe
Files: files | file ages | folders
SHA3-256: afcd96f2ab0f393f78d9f2c93c8f48d0af80b4a71f7b8b88a9e14ec51fc00bf9
User & Date: olr on 2017-11-01 11:38:31
Other Links: branch diff | manifest | tags
Context
2017-11-01
13:17
[fr] lexicographe: nouveaux labels pour locutions verbales check-in: 8db44cfb54 user: olr tags: Lexicographe, fr
12:01
Ajout script de génération de locutions.txt Closed-Leaf check-in: e6c5e7908d user: IllusionPerdu tags: Lexicographe_dead
11:38
[fr] lexicographe: code cleaning check-in: afcd96f2ab user: olr tags: Lexicographe, fr
10:35
[fr] lexicographe: useless code (WTF?) check-in: 4cfb006e3a user: olr tags: Lexicographe, fr
Changes

Modified gc_lang/fr/modules-js/lexicographe.js from [5be8f7e98e] to [254ccfd456].

127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
...
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
...
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
    [':s', " singulière"],
    [':p', " plurielle"],
    [':i', " invariable"],
    ['/L', " {latin}"]
]);

const _dLocVERB = new Map([
    ['i', " intransitif"],
    ['n', " transitif indirect"],
    ['t', " transitif direct"],
    ['p', " pronominal"],
    ['m', " impersonnel"],
]);

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"],
................................................................................
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*Ṽ][^:;/]*", "g");
        this._zLocTag = new RegExp("((:L)([A-Z])?)([a-z].?)?(:.*)?");
    }

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a object {sType, sValue, aLabel}
        let m = null;
        try {
................................................................................
        while ((m = this._zTag.exec(sTags)) !== null) {
            sRes += _dTAGS.get(m[0]);
        }
        if (sRes.startsWith(" verbe") && !sRes.includes("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatTagsLoc (sTags) {
        let sRes = "";
        let oTagsVerb = this._zLocTag.exec(sTags);
        sRes += _dLocTAGS.get(oTagsVerb[1]);
        if (oTagsVerb[4] && oTagsVerb[1] === ':LV'){
            oTagsVerb[4].split(/(?!$)/u).forEach(function(sKey) {
                sRes += _dLocVERB.get(sKey);
            });
        }
        if (oTagsVerb[5]){
            let m;
            while ((m = this._zTag.exec(oTagsVerb[5])) !== null) {
                sRes += _dLocTAGS.get(m[0]);
            }
        }
        if (!sRes) {
            sRes = "#Erreur. Étiquette inconnue : [" + sTags + "]";
            return sRes;
        }
        return sRes.gl_trimRight(",");
    }

    _formatSuffix (s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));







|
|
|
|
|







 







<

|
<







 







|
<






|
|
|
|
|
|
|
|
<
<




|
<







127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
...
226
227
228
229
230
231
232

233
234

235
236
237
238
239
240
241
...
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
    [':s', " singulière"],
    [':p', " plurielle"],
    [':i', " invariable"],
    ['/L', " {latin}"]
]);

const _dLocVERB = new Map([
    ['i', ", intransitif"],
    ['n', ", transitif indirect"],
    ['t', ", transitif direct"],
    ['p', ", pronominal"],
    ['m', ", impersonnel"],
]);

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"],
................................................................................
class Lexicographe {

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


        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-Z0-9ÑÂĴĈŔÔṼŴ!][^:;/]*", "g");

    }

    getInfoForToken (oToken) {
        // Token: .sType, .sValue, .nStart, .nEnd
        // return a object {sType, sValue, aLabel}
        let m = null;
        try {
................................................................................
        while ((m = this._zTag.exec(sTags)) !== null) {
            sRes += _dTAGS.get(m[0]);
        }
        if (sRes.startsWith(" verbe") && !sRes.includes("infinitif")) {
            sRes += " [" + sTags.slice(1, sTags.indexOf(" ")) + "]";
        }
        if (!sRes) {
            return "#Erreur. Étiquette inconnue : [" + sTags + "]";

        }
        return sRes.gl_trimRight(",");
    }

    _formatTagsLoc (sTags) {
        let sRes = "";
        let m;
        while ((m = this._zTag.exec(sTags)) !== null) {
            if (m[0].startsWith(":LV")) {
                sRes += _dLocTAGS.get(":LV");
                for (let c of m[0].slice(3)) {
                    sRes += _dLocVERB.get(c);
                }
            } else {


                sRes += _dLocTAGS.get(m[0]);
            }
        }
        if (!sRes) {
            return "#Erreur. Étiquette inconnue : [" + sTags + "]";

        }
        return sRes.gl_trimRight(",");
    }

    _formatSuffix (s) {
        if (s.startsWith("t-")) {
            return "“t” euphonique +" + _dAD.get(s.slice(2));