21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
'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',
'ç': 'c', 'ñ': 'n', 'k': 'q', 'w': 'v',
'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"
})
def simplifyWord (sWord):
"word simplication before calculating distance between words"
sWord = sWord.lower().translate(_xTransCharsForSimplification)
sNewWord = ""
for i, c in enumerate(sWord, 1):
|
|
>
|
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
'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',
'ç': 'c', 'ñ': 'n', 'k': 'q', 'w': 'v',
'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):
|