Grammalecte  Diff

def distanceBetweenChars (c1, c2):
    if c1 == c2:
        return 0
    if c1 not in dDistanceBetweenChars:
        return 1
    return dDistanceBetweenChars[c1].get(c2, 1)


_xTransCharsForSimplification = str.maketrans({
    '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"
})

def simplifyWord (sWord):
    "word simplication before calculating distance between words"
    sWord = sWord.lower().translate(_xTransCharsForSimplification)
    sNewWord = ""
    for i, c in enumerate(sWord, 1):
        if c == 'e' or c != sWord[i:i+1]:  # exception for <e> to avoid confusion between crée / créai
            sNewWord += c
    return sNewWord.replace("eau", "o").replace("au", "o").replace("ai", "é").replace("ei", "é").replace("ph", "f")


_xTransNumbersToExponent = str.maketrans({
    "0": "⁰", "1": "¹", "2": "²", "3": "³", "4": "⁴", "5": "⁵", "6": "⁶", "7": "⁷", "8": "⁸", "9": "⁹"
})

def numbersToExponent (sWord):
    "convert numeral chars to exponant chars"
    return sWord.translate(_xTransNumbersToExponent)


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


# Similar chars

    "ei": ("ait", "ais"),
    "EI": ("AIT", "AIS"),
    "on": ("ons", "ont"),
    "ON": ("ONS", "ONT"),
    "oi": ("ois", "oit", "oix"),
    "OI": ("OIS", "OIT", "OIX"),
}


# Préfixes et suffixes

aPfx1 = frozenset([
    "anti", "archi", "contre", "hyper", "mé", "méta", "im", "in", "ir", "par", "proto",
    "pseudo", "pré", "re", "ré", "sans", "sous", "supra", "sur", "ultra"
])
aPfx2 = frozenset([
    "belgo", "franco", "génito", "gynéco", "médico", "russo"
])


_zWordPrefixes = re.compile("(?i)^([ldmtsnjcç]|lorsqu|presqu|jusqu|puisqu|quoiqu|quelqu|qu)[’'‘`ʼ]([\\w-]+)")
_zWordSuffixes = re.compile("(?i)^(\\w+)(-(?:t-|)(?:ils?|elles?|on|je|tu|nous|vous|ce))$")

def cut (sWord):
    "returns a tuple of strings (prefix, trimed_word, suffix)"
    sPrefix = ""
    sSuffix = ""
    m = _zWordPrefixes.search(sWord)
    if m:
        sPrefix = m.group(1) + "’"
        sWord = m.group(2)
    m = _zWordSuffixes.search(sWord)
    if m:
        sWord = m.group(1)
        sSuffix = m.group(2)
    return (sPrefix, sWord, sSuffix)


# Other functions

def filterSugg (aSugg):
    "exclude suggestions"
    return filter(lambda sSugg: not sSugg.endswith(("è", "È")), aSugg)