Grammalecte  Diff

Differences From Artifact [1ca4ee03ac]:

To Artifact [b78c1f2098]:


32
33
34
35
36
37
38








































39
40
41
42
43
44
45
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85







+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+







    spellingNormalization: function (sWord) {
        let sNewWord = "";
        for (let c of sWord) {
            sNewWord += this._xTransCharsForSpelling.gl_get(c, c);
        }
        return sNewWord.normalize("NFC");
    },

    _xTransCharsForSimplification: new Map([
        ['à', 'a'],  ['é', 'é'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'y'],
        ['â', 'a'],  ['è', 'é'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'y'],
        ['ä', 'a'],  ['ê', 'é'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'y'],
        ['á', 'a'],  ['ë', 'é'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'y'],
        ['ā', 'a'],  ['ē', 'é'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'y'],
        ['ç', 'c'],  ['ñ', 'n'],
        ['œ', 'oe'], ['æ', 'ae'],
        ['ſ', 's'],  ['ffi', 'ffi'],  ['ffl', 'ffl'],  ['ff', 'ff'],  ['ſt', 'ft'],  ['fi', 'fi'],  ['fl', 'fl'],  ['st', 'st'],
        ["⁰", "0"], ["¹", "1"], ["²", "2"], ["³", "3"], ["⁴", "4"], ["⁵", "5"], ["⁶", "6"], ["⁷", "7"], ["⁸", "8"], ["⁹", "9"],
        ["₀", "0"], ["₁", "1"], ["₂", "2"], ["₃", "3"], ["₄", "4"], ["₅", "5"], ["₆", "6"], ["₇", "7"], ["₈", "8"], ["₉", "9"]
    ]),

    simplifyWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        sWord = [...sWord].map(c => this._xTransCharsForSimplification.gl_get(c, c)).join('');
        let sNewWord = "";
        let i = 1;
        for (let c of sWord) {
            if (c == 'e' || c != sWord.slice(i, i+1)) {  // exception for <e> to avoid confusion between crée / créai
                sNewWord += c;
            }
            i++;
        }
        return sNewWord.replace(/eau/g, "o").replace(/au/g, "o").replace(/ai/g, "é").replace(/ei/g, "é").replace(/ph/g, "f");
    },

    _xTransNumbersToExponent: new Map([
        ["0", "⁰"], ["1", "¹"], ["2", "²"], ["3", "³"], ["4", "⁴"], ["5", "⁵"], ["6", "⁶"], ["7", "⁷"], ["8", "⁸"], ["9", "⁹"]
    ]),

    numbersToExponent: function (sWord) {
        let sNewWord = "";
        for (let c of sWord) {
            sNewWord += this._xTransNumbersToExponent.gl_get(c, c);
        }
        return sNewWord;
    },

    longestCommonSubstring: function (string1, string2) {
        // https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Longest_common_substring
        // untested

        // init max value
        let longestCommonSubstring = 0;
192
193
194
195
196
197
198



199
200
201
202
203
204
205
206
207
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250







+
+
+









        sWord = sPfxCode.slice(1) + sWord.slice(sPfxCode.charCodeAt(0)-48);
        return sSfxCode[0] == '0' ? sWord + sSfxCode.slice(1) : sWord.slice(0, -(sSfxCode.charCodeAt(0)-48)) + sSfxCode.slice(1);
    }
};


if (typeof(exports) !== 'undefined') {
    exports.simplifyWord = str_transform.simplifyWord;
    exports.numbersToExponent = str_transform.numbersToExponent;
    exports.spellingNormalization = str_transform.spellingNormalization;
    exports.longestCommonSubstring = str_transform.longestCommonSubstring;
    exports.distanceDamerauLevenshtein = str_transform.distanceDamerauLevenshtein;
    exports.distanceDamerauLevenshtein2 = str_transform.distanceDamerauLevenshtein2;
    exports.showDistance = str_transform.showDistance;
    exports.changeWordWithSuffixCode = str_transform.changeWordWithSuffixCode;
    exports.changeWordWithAffixCode = str_transform.changeWordWithAffixCode;
    exports.defineAffixCode = str_transform.defineAffixCode;
    exports.defineSuffixCode = str_transform.defineSuffixCode;
}