rapidfuzz usage example

rapidfuzz_matches.py

pip install rapidfuzz

from rapidfuzz import process
import re

def suggest_names_fuzzy(text, name_database, score_cutoff=80):
    suggestions = []
    # Here re.finditer(r'\b\w+\b', text) change to the list of tokens found with spacy.
    # Example how to create a list of tokens from text with spacy: https://habr.com/ru/articles/531940/
    for match in re.finditer(r'\b\w+\b', text):
        word = match.group()
        index = match.start()

        match_result = process.extractOne(word, name_database, score_cutoff=score_cutoff)
        if match_result:
            name, score, _ = match_result
            if word != name:
                suggestions.append(f"Maybe you mean '{name}' at index {index}")
    
    return suggestions
  
# Example usage:
text = "Alic went to the market. Then she met Chralie and Bobb."
name_database = ["Alice", "Charlie", "Bob", "Diana"]

result = suggest_names_fuzzy(text, name_database)
for r in result:
    print(r)