Finding identical matches in text

difflib_matches.py

import difflib

#Finding identical matches in text with number of characters >=5. Min length should be adjusted for real case.
def find_overlaps(text1, text2, min_length=5):
    matcher = difflib.SequenceMatcher(None, text1, text2)
    matches = []
    for match in matcher.get_matching_blocks():
        if match.size >= min_length:
            overlap = text1[match.a: match.a + match.size]
            matches.append(overlap)
    return matches
    
#Example usage:
text1 = "The quick brown fox jumps over the lazy dog"
text2 = "A quick brown fox leaped over the lazy hound"


print(find_overlaps(text1, text2, min_length=5))
# Result:
# [' quick brown fox ', ' over the lazy ']