Created
March 5, 2018 23:23
-
-
Save Avlyssna/22566c2e175b3b18c41bc73fd07d3a9e to your computer and use it in GitHub Desktop.
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
# Standard library imports | |
import re | |
# Third-party imports | |
import editdistance | |
import unidecode | |
def convert_to_expression(string): | |
patterns = ['\w', '\s'] | |
expression = '' | |
previous = None | |
for letter in string: | |
for pattern in patterns: | |
if re.match(pattern, letter): | |
if not previous == pattern: | |
previous = pattern | |
expression += '{}+'.format(pattern) | |
break | |
else: | |
previous = letter | |
expression += letter | |
return expression | |
def count_fuzzy_matches(needle, haystack, maximum_distance=2, minimum_length=6): | |
# We normalize the text to prevent skewed edit distance | |
needle = unidecode.unidecode(needle).lower() | |
haystack = haystack.lower() | |
# We search without fuzz if the string is too short | |
if len(needle) < minimum_length: | |
return haystack.count(needle) | |
expression = convert_to_expression(needle) | |
matches = 0 | |
for match in re.finditer(expression, haystack): | |
if editdistance.eval(match.group(0), needle) <= maximum_distance: | |
matches += 1 | |
return matches |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment