Last active
October 18, 2020 12:03
-
-
Save sharkdeng/5f77486b00311c1c8ad655942d3d9310 to your computer and use it in GitHub Desktop.
Soundex algorithm
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def soundex(string): | |
# keep first letter of a string | |
string = string.lower() | |
result = string[0] | |
string = string[1:] | |
# remove [a, e, i, o, u, y, h, w] | |
tmp = ['a', 'e', 'i', 'o', 'u', 'y', 'h', 'w'] | |
for t in tmp: | |
if t in string: | |
string.replace(t, '') | |
# Replace all consonants from position 2 onwards with digits using these rules: | |
dicts = {'bfpv': 1, | |
'cgjkqsxz': 2, | |
'dt': 3, | |
'l':4, | |
'mn':5, | |
'r':6} | |
for c in string: | |
for k in dicts: | |
if c in k: | |
result += str(dicts[k]) | |
# only keep unique adjacent digits | |
# return 4 | |
return result[:4].ljust(4, '0') | |
def test(): | |
assert soundex('gail') == 'g400' | |
assert soundex('christine') == 'c623' | |
assert soundex('kristina') == 'k623' | |
assert soundex('peter') == 'p360' | |
assert soundex('gayle') == 'g400' | |
assert soundex('christina') == 'c623' | |
assert soundex('kirstin') == 'k623' | |
assert soundex('christen') == 'c623' | |
print(soundex('Brian')) | |
print(soundex('Elizabeth')) | |
test() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment