23
24
25
26
27
28
29
30
31
32
33
34
35
36
|
'ſ': 's', 'ffi': 'ffi', 'ffl': 'ffl', 'ff': 'ff', 'ſt': 'ft', 'fi': 'fi', 'fl': 'fl', 'st': 'st'
})
def spellingNormalization (sWord):
"nomalization NFC and removing ligatures"
return unicodedata.normalize("NFC", sWord.translate(_xTransCharsForSpelling))
#### DISTANCE CALCULATIONS
def longestCommonSubstring (s1, s2):
"longest common substring"
# http://en.wikipedia.org/wiki/Longest_common_substring_problem
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
23
24
25
26
27
28
29
30
31
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
|
'ſ': 's', 'ffi': 'ffi', 'ffl': 'ffl', 'ff': 'ff', 'ſt': 'ft', 'fi': 'fi', 'fl': 'fl', 'st': 'st'
})
def spellingNormalization (sWord):
"nomalization NFC and removing ligatures"
return unicodedata.normalize("NFC", sWord.translate(_xTransCharsForSpelling))
_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)
#### DISTANCE CALCULATIONS
def longestCommonSubstring (s1, s2):
"longest common substring"
# http://en.wikipedia.org/wiki/Longest_common_substring_problem
|