29 lines
975 B
Python
29 lines
975 B
Python
|
def is_russian_wording(text):
|
|||
|
|
"""
|
|||
|
|
Check if the text contains any Russian characters by checking
|
|||
|
|
each character against the Unicode range for Cyrillic.
|
|||
|
|
"""
|
|||
|
|
# Check if any character in the text is a Cyrillic character
|
|||
|
|
for char in text:
|
|||
|
|
if '\u0400' <= char <= '\u04FF': # Unicode range for Cyrillic characters
|
|||
|
|
return True
|
|||
|
|
return False
|
|||
|
|
|
|||
|
|
def normalize(text):
|
|||
|
|
"""
|
|||
|
|
Normalize English text to resemble Russian characters.
|
|||
|
|
"""
|
|||
|
|
if is_russian_wording(text):
|
|||
|
|
# Normalize the text by replacing characters
|
|||
|
|
text = (text.lower()
|
|||
|
|
.replace('e', 'е')
|
|||
|
|
.replace('o', 'о')
|
|||
|
|
.replace('x', 'х')
|
|||
|
|
.replace('a', 'а')
|
|||
|
|
.replace('r', 'г')
|
|||
|
|
.replace('m', 'м')
|
|||
|
|
.replace('u', 'и')
|
|||
|
|
.replace('n', 'п')
|
|||
|
|
.replace('p', 'р'))
|
|||
|
|
|
|||
|
|
return text
|