Grammalecte  Check-in [72f63bddd2]

Overview
Comment:[graphspell][js] tokenizer: update \w replacement again
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | graphspell | rg
Files: files | file ages | folders
SHA3-256: 72f63bddd22d08a214557d990966fd943703d9fd09e4cd9aa2035b219b715633
User & Date: olr on 2018-09-17 12:06:16
Other Links: branch diff | manifest | tags
Context
2018-09-17
12:07
[fr][bug] mauvais token sélectionné check-in: d877acf9d9 user: olr tags: fr, rg
12:06
[graphspell][js] tokenizer: update \w replacement again check-in: 72f63bddd2 user: olr tags: graphspell, rg
11:32
[fr][bugs] remove useless parameters check-in: 8b769e5c52 user: olr tags: fr, rg
Changes

Modified graphspell-js/tokenizer.js from [d579c92281] to [88bacac87d].

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
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







-
+


















-
+







            [/^[#@][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'],
            [/^[%‰+=*/<>⩾⩽-]/, 'SIGN'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ]+)*/, 'WORD']
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ_]+)*/, '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_.()-]+)*/, 'FOLDERUNIX'],
            [/^[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'],
            [/^[A-Z][.][A-Z][.](?:[A-Z][.])*/, 'WORD_ACRONYM'],
            [/^(?: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, 'WORD_ELIDED'],
            [/^\d\d?[hm]\d\d\b/, 'HOUR'],
            [/^\d+(?:ers?\b|nds?\b|es?\b|des?\b|ièmes?\b|èmes?\b|emes?\b|ᵉʳˢ?|ⁿᵈˢ?|ᵉˢ?|ᵈᵉˢ?)/, 'WORD_ORDINAL'],
            [/^\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[%‰+=*/<>⩾⩽-]/, 'SIGN'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ]+)*/, 'WORD']
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ_]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-stᴀ-ᶿ_]+)*/, 'WORD']
        ]
};


class Tokenizer {

    constructor (sLang) {