Overview
Comment: | Ajout dans le tokenizer du ~ dans la detection des dossier linux, et distintion entre les deux types de dossier windows/linux avec le changement dans le lexicographe |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | Lexicographe |
Files: | files | file ages | folders |
SHA3-256: |
11f1414b5b27a55edc22150c5948efe9 |
User & Date: | IllusionPerdu on 2017-11-02 10:58:57 |
Other Links: | branch diff | manifest | tags |
Context
2017-11-02
| ||
11:01 | [fr] restructuration des données pour éviter la confusion avec le token <:> check-in: 685f9128f0 user: olr tags: fr, Lexicographe | |
10:58 | Ajout dans le tokenizer du ~ dans la detection des dossier linux, et distintion entre les deux types de dossier windows/linux avec le changement dans le lexicographe check-in: 11f1414b5b user: IllusionPerdu tags: Lexicographe | |
10:47 | [fr] lexicographe: gestion des locutions occasionnelles check-in: 34d80cabfa user: olr tags: fr, Lexicographe | |
Changes
Modified gc_core/js/tokenizer.js from [9bb6ea03fb] to [9d996e312d].
︙ | ︙ | |||
12 13 14 15 16 17 18 | const aTkzPatterns = { // All regexps must start with ^. "default": [ [/^[ \t]+/, 'SPACE'], | | | | | | 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 | const aTkzPatterns = { // All regexps must start with ^. "default": [ [/^[ \t]+/, 'SPACE'], [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERLINUX'], [/^[a-zA-Z]:\\(?:Program Files(?: \(x86\)|)|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st.()]+)(?:\\[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERWIN'], [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'], [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]{2,}[@.])[a-zA-Z0-9][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'], [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERLINUX'], [/^[a-zA-Z]:\\(?:Program Files(?: \(x86\)|)|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st.()]+)(?:\\[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERWIN'], [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'], [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]{2,}[@.])[a-zA-Z0-9][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'], |
︙ | ︙ | |||
64 65 66 67 68 69 70 | while (sText) { let nCut = 1; for (let [zRegex, sType] of this.aRules) { try { if ((m = zRegex.exec(sText)) !== null) { if (sType == 'SEPARATOR') { for (let c of m[0]) { | | | | 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | while (sText) { let nCut = 1; for (let [zRegex, sType] of this.aRules) { try { if ((m = zRegex.exec(sText)) !== null) { if (sType == 'SEPARATOR') { for (let c of m[0]) { yield { "sType": sType, "sValue": c, "nStart": i, "nEnd": i + m[0].length } } } else { yield { "sType": sType, "sValue": m[0], "nStart": i, "nEnd": i + m[0].length } } nCut = m[0].length; break; } } catch (e) { helpers.logerror(e); |
︙ | ︙ |
Modified gc_lang/fr/modules-js/lexicographe.js from [fc0a175535] to [df1f15e3d4].
︙ | ︙ | |||
265 266 267 268 269 270 271 | let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase(); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dElidedPrefix.gl_get(sTemp, "préfixe élidé inconnu")] }; break; | | > > > > > > > | | 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 | let sTemp = oToken.sValue.replace("’", "").replace("'", "").replace("`", "").toLowerCase(); return { sType: oToken.sType, sValue: oToken.sValue, aLabel: [_dElidedPrefix.gl_get(sTemp, "préfixe élidé inconnu")] }; break; case 'FOLDERLINUX': return { sType: oToken.sType, sValue: oToken.sValue.slice(0, 40) + "…", aLabel: ["dossier Linux/Unix"] }; break; case 'FOLDERWIN': return { sType: oToken.sType, sValue: oToken.sValue.slice(0, 40) + "…", aLabel: ["dossier Windows"] }; break; case 'WORD': if (oToken.sValue.gl_count("-") > 4) { return { sType: "COMPLEX", sValue: oToken.sValue, |
︙ | ︙ |