Grammalecte  Diff

Differences From Artifact [73eee3ee03]:

To Artifact [0a316c953c]:


25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
})

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 != sWord[i:i+1]:
            sNewWord += c
    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







|







25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
})

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", "e").replace("ei", "e").replace("ph", "f")


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