Update text_similarity.py

text_similarity.py

@@ -1,7 +1,10 @@
 import re
+import logging
 from difflib import SequenceMatcher
 from collections import defaultdict
 
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
 def extract_special_characters(text):
     """Extracts all unique special characters from a list of texts."""
     characters = re.findall(r'[^\w\s]', text)  # Finds non-alphanumeric and non-space characters
@@ -22,6 +25,8 @@ def detect_fragments(text, key_texts, threshold=0.7):
         characters_to_not_clean = extract_special_characters(key_text)
         words = clean_text(text, characters_to_not_clean).split()
 
+        logging.info(f"Words detected: {words}")
+
         key_words = key_text.split()
         
         # If the text is too short, we can't make an effective sliding window