Grammalecte  Check-in [5ac4660b30]

Overview
Comment:[fx][bug] ibdawg: suggestion mechanism > fix calculation between words in JS
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk | fx
Files: files | file ages | folders
SHA3-256: 5ac4660b3050848f8fbe5cbda1d65a35bddece6e61e76f62ca04e5394962828c
User & Date: olr on 2017-10-28 11:56:22
Other Links: manifest | tags
Context
2017-10-28
12:04
[fx] Menu buttons: option true by default for editable nodes check-in: 4dd50863c2 user: olr tags: fx, trunk
11:56
[fx][bug] ibdawg: suggestion mechanism > fix calculation between words in JS check-in: 5ac4660b30 user: olr tags: fx, trunk
11:15
[fx] Menu buttons: option false by default for editable nodes check-in: 35238657b4 user: olr tags: fx, trunk
Changes

Modified gc_core/js/char_player.js from [fa4a550e43] to [f5b2267e7d].

19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
..
59
60
61
62
63
64
65






66
67
68
69
70
71
72
    cleanWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        let sRes = "";
        for (let c of sWord) {
            sRes += this._dTransChars.gl_get(c, c);
        }
        return sWord.replace("eau", "o").replace("au", "o");
    },

    distanceDamerauLevenshtein: function (s1, s2) {
        // distance of Damerau-Levenshtein between <s1> and <s2>
        // https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
        try {
            let nLen1 = s1.length;
................................................................................
            return matrix[nLen1][nLen2];
        }
        catch (e) {
            helpers.logerror(e);
        }
    },








    // Method: Remove Useless Chars

    aVovels: new Set([
        'a', 'e', 'i', 'o', 'u', 'y',
        'à', 'é', 'î', 'ô', 'û', 'ÿ',
        'â', 'è', 'ï', 'ö', 'ù', 'ŷ',







|







 







>
>
>
>
>
>







19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
..
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
    cleanWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        let sRes = "";
        for (let c of sWord) {
            sRes += this._dTransChars.gl_get(c, c);
        }
        return sRes.replace("eau", "o").replace("au", "o");
    },

    distanceDamerauLevenshtein: function (s1, s2) {
        // distance of Damerau-Levenshtein between <s1> and <s2>
        // https://fr.wikipedia.org/wiki/Distance_de_Damerau-Levenshtein
        try {
            let nLen1 = s1.length;
................................................................................
            return matrix[nLen1][nLen2];
        }
        catch (e) {
            helpers.logerror(e);
        }
    },

    showDistance (s1, s2) {
        let s1b = this.cleanWord(s1);
        let s2b = this.cleanWord(s2);
        console.log(`Distance: ${s1} / ${s2} = ${this.distanceDamerauLevenshtein(s1, s2)})`);
        console.log(`Distance: ${s1b} / ${s2b} = ${this.distanceDamerauLevenshtein(s1b, s2b)})`);
    },

    // Method: Remove Useless Chars

    aVovels: new Set([
        'a', 'e', 'i', 'o', 'u', 'y',
        'à', 'é', 'î', 'ô', 'û', 'ÿ',
        'â', 'è', 'ï', 'ö', 'ù', 'ŷ',

Modified gc_core/js/ibdawg.js from [d3a144f471] to [c87880e4ad].

200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
            aSugg.gl_update(this._suggest(sWord.toLowerCase(), nMaxDel, nMaxHardRepl));
        }
        else if (sWord.gl_isLowerCase()) {
            aSugg.gl_update(this._suggest(sWord.gl_toCapitalize(), nMaxDel, nMaxHardRepl));
        }
        // Set to Array
        aSugg = Array.from(aSugg);
        aSugg = aSugg.filter((sSugg) => { return !sSugg.endsWith("è") && !sSugg.endsWith("È"); }); // fr language 
        if (sWord.gl_isTitle()) {
            aSugg = aSugg.map((sSugg) => { return sSugg.gl_toCapitalize(); });
        }
        let dDistTemp = new Map();
        let sCleanWord = char_player.cleanWord(sWord)
        aSugg.forEach((sSugg) => { dDistTemp.set(sSugg, char_player.distanceDamerauLevenshtein(sCleanWord, char_player.cleanWord(sSugg))); });
        aSugg = aSugg.sort((sA, sB) => { return dDistTemp.get(sA) - dDistTemp.get(sB); }).slice(0, nMaxSugg);
        dDistTemp.clear();
        if (sSfx || sPfx) {
            // we add what we removed
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx } );
        }







|




|







200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
            aSugg.gl_update(this._suggest(sWord.toLowerCase(), nMaxDel, nMaxHardRepl));
        }
        else if (sWord.gl_isLowerCase()) {
            aSugg.gl_update(this._suggest(sWord.gl_toCapitalize(), nMaxDel, nMaxHardRepl));
        }
        // Set to Array
        aSugg = Array.from(aSugg);
        aSugg = char_player.filterSugg(aSugg);
        if (sWord.gl_isTitle()) {
            aSugg = aSugg.map((sSugg) => { return sSugg.gl_toCapitalize(); });
        }
        let dDistTemp = new Map();
        let sCleanWord = char_player.cleanWord(sWord);
        aSugg.forEach((sSugg) => { dDistTemp.set(sSugg, char_player.distanceDamerauLevenshtein(sCleanWord, char_player.cleanWord(sSugg))); });
        aSugg = aSugg.sort((sA, sB) => { return dDistTemp.get(sA) - dDistTemp.get(sB); }).slice(0, nMaxSugg);
        dDistTemp.clear();
        if (sSfx || sPfx) {
            // we add what we removed
            return aSugg.map( (sSugg) => { return sPfx + sSugg + sSfx } );
        }

Modified gc_core/py/char_player.py from [3de4d3c435] to [97f69bd70d].

37
38
39
40
41
42
43







44
45
46
47
48
49
50
                d[i,   j-1] + 1,        # Insertion
                d[i-1, j-1] + nCost,    # Substitution
            )
            if i and j and s1[i] == s2[j-1] and s1[i-1] == s2[j]:
                d[i, j] = min(d[i, j], d[i-2, j-2] + nCost)     # Transposition
    return d[nLen1-1, nLen2-1]









# Method: Remove Useless Chars

_dVovels = {
    'a': '',  'e': '',  'i': '',  'o': '',  'u': '',  'y': '',
    'à': '',  'é': '',  'î': '',  'ô': '',  'û': '',  'ÿ': '',
    'â': '',  'è': '',  'ï': '',  'ö': '',  'ù': '',  'ŷ': '',







>
>
>
>
>
>
>







37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
                d[i,   j-1] + 1,        # Insertion
                d[i-1, j-1] + nCost,    # Substitution
            )
            if i and j and s1[i] == s2[j-1] and s1[i-1] == s2[j]:
                d[i, j] = min(d[i, j], d[i-2, j-2] + nCost)     # Transposition
    return d[nLen1-1, nLen2-1]


def showDistance (s1, s2):
    s1b = cleanWord(s1);
    s2b = cleanWord(s2);
    print(f"Distance: {s1} / {s2} = {distanceDamerauLevenshtein(s1, s2)}")
    print(f"Distance: {s1b} / {s2b} = {distanceDamerauLevenshtein(s1b, s2b)}")


# Method: Remove Useless Chars

_dVovels = {
    'a': '',  'e': '',  'i': '',  'o': '',  'u': '',  'y': '',
    'à': '',  'é': '',  'î': '',  'ô': '',  'û': '',  'ÿ': '',
    'â': '',  'è': '',  'ï': '',  'ö': '',  'ù': '',  'ŷ': '',