Spaces:
Runtime error
Runtime error
| def normalize(s): | |
| """Lowercase and strip the string to normalize it.""" | |
| return s.lower().strip() | |
| def levenshtein_distance(s1, s2): | |
| """Calculate the Levenshtein distance between two strings.""" | |
| if len(s1) < len(s2): | |
| return levenshtein_distance(s2, s1) | |
| if len(s2) == 0: | |
| return len(s1) | |
| previous_row = range(len(s2) + 1) | |
| for i, c1 in enumerate(s1): | |
| current_row = [i + 1] | |
| for j, c2 in enumerate(s2): | |
| insertions = previous_row[j + 1] + 1 | |
| deletions = current_row[j] + 1 | |
| substitutions = previous_row[j] + (c1 != c2) | |
| current_row.append(min(insertions, deletions, substitutions)) | |
| previous_row = current_row | |
| return previous_row[-1] | |
| def find_best_keyword_match(keywords, text, max_distance=3): | |
| """Find the best keyword match in the text, allowing for some misspelling.""" | |
| text_normalized = normalize(text) | |
| best_match = None | |
| lowest_distance = float('inf') | |
| for keyword in keywords: | |
| keyword_normalized = normalize(keyword) | |
| # Calculate the Levenshtein distance for composite keywords by comparing against slices of the text | |
| if ' ' in keyword_normalized: | |
| slice_length = len(keyword_normalized) | |
| for i in range(len(text_normalized) - slice_length + 1): | |
| text_slice = text_normalized[i:i+slice_length] | |
| distance = levenshtein_distance(text_slice, keyword_normalized) | |
| if distance < lowest_distance: | |
| best_match = keyword | |
| lowest_distance = distance | |
| else: | |
| # For single words, compare against each word in the text | |
| for word in text_normalized.split(): | |
| distance = levenshtein_distance(word, keyword_normalized) | |
| if distance < lowest_distance: | |
| best_match = keyword | |
| lowest_distance = distance | |
| if lowest_distance <= max_distance: | |
| return best_match | |
| return None | |
| # Example usage | |
| keywords = ["NewYork", "misplaced", "LosAngeles", "Tucson"] | |
| text = "This is an example text with a reference to Tsucon." | |
| identified_keyword = find_best_keyword_match(keywords, text) | |
| print("Identified keyword:", identified_keyword) | |