Grammalecte  Check-in [fa01465ba8]

    _dTransChars: new Map([
        ['à', 'a'],  ['é', 'e'],  ['î', 'i'],  ['ô', 'o'],  ['û', 'u'],  ['ÿ', 'i'],  ['y', 'i'],
        ['â', 'a'],  ['è', 'e'],  ['ï', 'i'],  ['ö', 'o'],  ['ù', 'u'],  ['ŷ', 'i'],
        ['ä', 'a'],  ['ê', 'e'],  ['í', 'i'],  ['ó', 'o'],  ['ü', 'u'],  ['ý', 'i'],
        ['á', 'a'],  ['ë', 'e'],  ['ì', 'i'],  ['ò', 'o'],  ['ú', 'u'],  ['ỳ', 'i'],
        ['ā', 'a'],  ['ē', 'e'],  ['ī', 'i'],  ['ō', 'o'],  ['ū', 'u'],  ['ȳ', 'i'],
        ['ñ', 'n'],
        ['ñ', 'n'],  ['k', 'q'],  ['w', 'v'],
        ['œ', 'oe'], ['æ', 'ae'], 
    ]),

    cleanWord: function (sWord) {
        // word simplication before calculating distance between words
        sWord = sWord.toLowerCase();
        let sNewWord = "";
        let i = 1;
        for (let c of sWord) {
            let cNew = this._dTransChars.gl_get(c, c);
            let cNext = sWord.slice(i, i+1)
            if (cNew != this._dTransChars.gl_get(cNext, cNext)) {
                sNewWord += cNew;
            }
            i++;
        }
        return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "e").replace("ei", "e");
        return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "e").replace("ei", "e").replace("ph", "f");
    },

    aVowel: new Set("aáàâäāeéèêëēiíìîïīoóòôöōuúùûüūyýỳŷÿȳœæAÁÀÂÄĀEÉÈÊËĒIÍÌÎÏĪOÓÒÔÖŌUÚÙÛÜŪYÝỲŶŸȲŒÆ"),
    aConsonant: new Set("bcçdfghjklmnñpqrstvwxzBCÇDFGHJKLMNÑPQRSTVWXZ"),
    aDouble: new Set("bcdfjklmnprstzBCDFJKLMNPRSTZ"),  // letters that may be used twice successively

# list of similar chars
# useful for suggestion mechanism

import re


_xTransChars = str.maketrans({
    'à': 'a',  'é': 'e',  'î': 'i',  'ô': 'o',  'û': 'u',  'ÿ': 'i',  "y": "i",
    'â': 'a',  'è': 'e',  'ï': 'i',  'ö': 'o',  'ù': 'u',  'ŷ': 'i',
    'ä': 'a',  'ê': 'e',  'í': 'i',  'ó': 'o',  'ü': 'u',  'ý': 'i',
    'á': 'a',  'ë': 'e',  'ì': 'i',  'ò': 'o',  'ú': 'u',  'ỳ': 'i',
    'ā': 'a',  'ē': 'e',  'ī': 'i',  'ō': 'o',  'ū': 'u',  'ȳ': 'i',
    'ñ': 'n',
    'ñ': 'n',  'k': 'q',  'w': 'v',
    'œ': 'oe',  'æ': 'ae', 
})

def cleanWord (sWord):
    "word simplication before calculating distance between words"
    sWord = sWord.lower().translate(_xTransChars)
    sNewWord = ""
    for i, c in enumerate(sWord, 1):
        if c != sWord[i:i+1]:
            sNewWord += c
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "e").replace("ei", "e")
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "e").replace("ei", "e").replace("ph", "f")


aVowel = set("aáàâäāeéèêëēiíìîïīoóòôöōuúùûüūyýỳŷÿȳœæAÁÀÂÄĀEÉÈÊËĒIÍÌÎÏĪOÓÒÔÖŌUÚÙÛÜŪYÝỲŶŸȲŒÆ")
aConsonant = set("bcçdfghjklmnñpqrstvwxzBCÇDFGHJKLMNÑPQRSTVWXZ")
aDouble = set("bcdfjklmnprstzBCDFJKLMNPRSTZ")  # letters that may be used twice successively