Update utils.py

utils.py

@@ -1,6 +1,24 @@
+import re
 from thefuzz import fuzz
 from thefuzz import process
 
+def find_query_despite_whitespace(document, query):
+
+    # Normalize spaces and newlines in the query
+    normalized_query = re.sub(r'\s+', ' ', query).strip()
+    
+    # Create a regex pattern from the normalized query to match any whitespace characters between words
+    pattern = r'\s*'.join(re.escape(word) for word in normalized_query.split())
+    
+    # Compile the regex to ignore case and search for it in the document
+    regex = re.compile(pattern, re.IGNORECASE)
+    match = regex.search(document)
+    
+    if match:
+        return document[match.start(): match.end()], match.start(), match.end()
+    else:
+        return None
+
 def rigorous_document_search(document: str, target: str):
     """
     This function performs a rigorous search of a target string within a document.