Grammalecte  Changes On Branch 2bcf7228cc69426f

Hide Diff Patch Unified Diff

Changes In Branch multid Through [2bcf7228cc] Excluding Merge-Ins

This is equivalent to a diff from 62c389aedf to 2bcf7228cc

2018-02-16
15:46
[fx][graphspell] merge multid: multi-dictionaries > editable personal dictionary check-in: 607d532bca user: olr tags: trunk, new_feature, fx, graphspell
2018-02-13
14:24
[graphspell][js] fix variables name check-in: 63ccb31875 user: olr tags: graphspell, multid
14:23
[graphspell][py] fix variables name check-in: 2bcf7228cc user: olr tags: graphspell, multid
13:39
[core][js] multi-dictionaries check-in: d8959f76a4 user: olr tags: core, multid
13:38
[graphspell][js] rename vars check-in: 62c389aedf user: olr tags: trunk, graphspell
10:47
[graphspell][js] spellchecker wrapper for ibdawg check-in: c989c20101 user: olr tags: trunk, graphspell

Modified gc_core/js/lang_core/gc_engine.js from [2f5e964b5d] to [08b8dd1900].

︙︙
35
36
37
38
39
40
41

42
43
44
45
46
47
48



// data
let _sAppContext = "";                                  // what software is running
let _dOptions = null;
let _aIgnoredRules = new Set();
let _oDict = null;

let _dAnalyses = new Map();                             // cache for data from dictionary


var gc_engine = {

    //// Informations









>








35
36
37
38
39
40
41
42
43
44
45
46
47
48
49



// data
let _sAppContext = "";                                  // what software is running
let _dOptions = null;
let _aIgnoredRules = new Set();
let _oDict = null;
let _oSpellChecker = null;
let _dAnalyses = new Map();                             // cache for data from dictionary


var gc_engine = {

    //// Informations
︙︙
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

    },

    //// Initialization

    load: function (sContext="JavaScript", sPath="") {
        try {
            if (typeof(require) !== 'undefined') {
                var ibdawg = require("resource://grammalecte/graphspell/ibdawg.js");
                _oDict = new ibdawg.IBDAWG("${dic_filename}.json");



            } else {
                _oDict = new IBDAWG("${dic_filename}.json", sPath);


            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    getDictionary: function () {
        return _oDict;
    },

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {
            _dOptions.set(sOpt, bVal);








|
|
>
>
>

|
>
>










|








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

    },

    //// Initialization

    load: function (sContext="JavaScript", sPath="") {
        try {
            if (typeof(require) !== 'undefined') {
                //var ibdawg = require("resource://grammalecte/graphspell/ibdawg.js");
                //_oDict = new ibdawg.IBDAWG("${dic_filename}.json");
                console.log("<resource:>");
                var spellchecker = require("resource://grammalecte/graphspell/spellchecker.js");
                _oSpellChecker = new spellchecker.Spellchecker("${lang}", "${dic_filename}.json");
            } else {
                //_oDict = new IBDAWG("${dic_filename}.json", sPath);
                console.log("no <resource:>");
                _oSpellChecker = new Spellchecker("${lang}", "${dic_filename}.json", sPath);
            }
            _sAppContext = sContext;
            _dOptions = gc_options.getOptions(sContext).gl_shallowCopy();     // duplication necessary, to be able to reset to default
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    getDictionary: function () {
        return _oSpellChecker;
    },

    //// Options

    setOption: function (sOpt, bVal) {
        if (_dOptions.has(sOpt)) {
            _dOptions.set(sOpt, bVal);
︙︙
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402

        helpers.echo("DA: " + dDA.get(aWord[0]));
    }
    helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
    return true;
}

function _storeMorphFromFSA (sWord) {
    // retrieves morphologies list from _oDict -> _dAnalyses
    //helpers.echo("register: "+sWord + " " + _oDict.getMorph(sWord).toString())
    _dAnalyses.set(sWord, _oDict.getMorph(sWord));
    return !!_dAnalyses.get(sWord);
}

function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
    // analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
    if (!aWord) {
        //helpers.echo("morph: noword, returns " + bNoWord);








|
|
|








392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408

        helpers.echo("DA: " + dDA.get(aWord[0]));
    }
    helpers.echo("FSA: " + _dAnalyses.get(aWord[1]));
    return true;
}

function _storeMorphFromFSA (sWord) {
    // retrieves morphologies list from _oSpellChecker -> _dAnalyses
    //helpers.echo("register: "+sWord + " " + _oSpellChecker.getMorph(sWord).toString())
    _dAnalyses.set(sWord, _oSpellChecker.getMorph(sWord));
    return !!_dAnalyses.get(sWord);
}

function morph (dDA, aWord, sPattern, bStrict=true, bNoWord=false) {
    // analyse a tuple (position, word), return true if sPattern in morphologies (disambiguation on)
    if (!aWord) {
        //helpers.echo("morph: noword, returns " + bNoWord);
︙︙

Modified gc_lang/fr/webext/gce_worker.js from [2a64cce6de] to [30916bedcd].

︙︙
32
33
34
35
36
37
38

39
40
41
42
43
44
45

//console.log("[Worker] GC Engine Worker [start]");
//console.log(self);

importScripts("grammalecte/graphspell/helpers.js");
importScripts("grammalecte/graphspell/str_transform.js");
importScripts("grammalecte/graphspell/char_player.js");
importScripts("grammalecte/graphspell/ibdawg.js");

importScripts("grammalecte/text.js");
importScripts("grammalecte/graphspell/tokenizer.js");
importScripts("grammalecte/fr/conj.js");
importScripts("grammalecte/fr/mfsp.js");
importScripts("grammalecte/fr/phonet.js");
importScripts("grammalecte/fr/cregex.js");
importScripts("grammalecte/fr/gc_options.js");








>








32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

//console.log("[Worker] GC Engine Worker [start]");
//console.log(self);

importScripts("grammalecte/graphspell/helpers.js");
importScripts("grammalecte/graphspell/str_transform.js");
importScripts("grammalecte/graphspell/char_player.js");
importScripts("grammalecte/graphspell/ibdawg.js");
importScripts("grammalecte/graphspell/spellchecker.js");
importScripts("grammalecte/text.js");
importScripts("grammalecte/graphspell/tokenizer.js");
importScripts("grammalecte/fr/conj.js");
importScripts("grammalecte/fr/mfsp.js");
importScripts("grammalecte/fr/phonet.js");
importScripts("grammalecte/fr/cregex.js");
importScripts("grammalecte/fr/gc_options.js");
︙︙

Modified graphspell/spellchecker.py from [19c7dd4df2] to [781d3c301e].

︙︙
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


dDefaultDictionaries = {
    "fr": "fr.bdic",
    "en": "en.bdic"
}


class Spellchecker ():

    def __init__ (self, sLangCode, sfMainDic="", sfExtendedDic="", sfPersonalDic=""):
        "returns True if the main dictionary is loaded"
        self.sLangCode = sLangCode
        if not sfMainDic:
            sfMainDic = dDefaultDictionaries.get(sLangCode, "")
        self.oMainDic = self._loadDictionary(sfMainDic)
        self.oExtendedDic = self._loadDictionary(sfExtendedDic)
        self.oPersonalDic = self._loadDictionary(sfPersonalDic)
        return bool(self.oMainDic)

    def _loadDictionary (self, sfDictionary):
        "returns an IBDAWG object"
        if not sfDictionary:
            return None
        try:
            return ibdawg.IBDAWG(sfDictionary)








|









<








15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

32
33
34
35
36
37
38


dDefaultDictionaries = {
    "fr": "fr.bdic",
    "en": "en.bdic"
}


class SpellChecker ():

    def __init__ (self, sLangCode, sfMainDic="", sfExtendedDic="", sfPersonalDic=""):
        "returns True if the main dictionary is loaded"
        self.sLangCode = sLangCode
        if not sfMainDic:
            sfMainDic = dDefaultDictionaries.get(sLangCode, "")
        self.oMainDic = self._loadDictionary(sfMainDic)
        self.oExtendedDic = self._loadDictionary(sfExtendedDic)
        self.oPersonalDic = self._loadDictionary(sfPersonalDic)


    def _loadDictionary (self, sfDictionary):
        "returns an IBDAWG object"
        if not sfDictionary:
            return None
        try:
            return ibdawg.IBDAWG(sfDictionary)
︙︙
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106

            return True
        if self.oPersonalDic and self.oPersonalDic.isValidToken(sToken):
            return True
        return False

    def isValid (self, sWord):
        "checks if sWord is valid (different casing tested if the first letter is a capital)"
        if self.oMainDic.isValid(sToken):
            return True
        if self.oExtendedDic and self.oExtendedDic.isValid(sToken):
            return True
        if self.oPersonalDic and self.oPersonalDic.isValid(sToken):
            return True
        return False

    def lookup (self, sWord):
        "checks if sWord is in dictionary as is (strict verification)"
        if self.oMainDic.lookup(sToken):
            return True
        if self.oExtendedDic and self.oExtendedDic.lookup(sToken):
            return True
        if self.oPersonalDic and self.oPersonalDic.lookup(sToken):
            return True
        return False

    def getMorph (self, sWord):
        "retrieves morphologies list, different casing allowed"
        lResult = self.oMainDic.getMorph(sToken)
        if self.oExtendedDic:
            lResult.extends(self.oExtendedDic.getMorph(sToken))
        if self.oPersonalDic:
            lResult.extends(self.oPersonalDic.getMorph(sToken))
        return lResult

    def suggest (self, sWord, nSuggLimit=10):
        "generator: returns 1,2 or 3 lists of suggestions"
        yield self.oMainDic.suggest(sWord, nSuggLimit)
        if self.oExtendedDic:
            yield self.oExtendedDic.suggest(sWord, nSuggLimit)








|

|

|





|

|

|





|

|

|








67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105

            return True
        if self.oPersonalDic and self.oPersonalDic.isValidToken(sToken):
            return True
        return False

    def isValid (self, sWord):
        "checks if sWord is valid (different casing tested if the first letter is a capital)"
        if self.oMainDic.isValid(sWord):
            return True
        if self.oExtendedDic and self.oExtendedDic.isValid(sWord):
            return True
        if self.oPersonalDic and self.oPersonalDic.isValid(sWord):
            return True
        return False

    def lookup (self, sWord):
        "checks if sWord is in dictionary as is (strict verification)"
        if self.oMainDic.lookup(sWord):
            return True
        if self.oExtendedDic and self.oExtendedDic.lookup(sWord):
            return True
        if self.oPersonalDic and self.oPersonalDic.lookup(sWord):
            return True
        return False

    def getMorph (self, sWord):
        "retrieves morphologies list, different casing allowed"
        lResult = self.oMainDic.getMorph(sWord)
        if self.oExtendedDic:
            lResult.extends(self.oExtendedDic.getMorph(sWord))
        if self.oPersonalDic:
            lResult.extends(self.oPersonalDic.getMorph(sWord))
        return lResult

    def suggest (self, sWord, nSuggLimit=10):
        "generator: returns 1,2 or 3 lists of suggestions"
        yield self.oMainDic.suggest(sWord, nSuggLimit)
        if self.oExtendedDic:
            yield self.oExtendedDic.suggest(sWord, nSuggLimit)
︙︙

Fossil 2.24 [8be0372c10] 2024-04-23 13:25:26
This page was generated in about 0.014s