redo loop for date parsing

app.py

@@ -40,30 +40,42 @@ def extract_features(tokens, labels):
     for token, label in zip(tokens, labels):  
         print(f"Debug -- Processing token: {token}")
 
-        # Check complete date pattern 
-        if re.match(date_pattern, current_date): 
+        # If we already have some part of a date and the next token could still be part of it, continue accumulating
+        if current_date and re.match(partial_date_pattern, token): 
+            current_date += token
+            print(f"Debug -- Potential partial date: {current_date}")
+        # If the accumulated entity matches a complete date after appending this token
+        elif re.match(date_pattern, current_date + token):
+            current_date += token
             merged_entities.append((current_date, 'date'))
-            print(f"Debug -- Completed date added: {current_date}")
-            current_date = ""
-        # Check if the token matches a partial date pattern
+            print(f"Debug -- Complete date added: {current_date}")
+            current_date = ""  # Reset for next entity
+        # If the token could start a new date (e.g., '14' could be a day or hour)
         elif re.match(partial_date_pattern, token):
-            print(f"Debug -- Potentially building date: Token Start {token} After Token")
-            current_date += token
+            current_date = token
+            print(f"Debug -- Potentially starting a new date: {token}")
         else: 
+        # If no patterns are detected and there is any accumulated data
             if current_date: 
-                merged_entities.append((current_date, 'date'))
+                # Finalize accumulated partial date
                 print(f"Debug -- Date finalized: {current_date}")
-                current_date = ""
+                merged_entities.append((current_date, 'date'))
+                current_date = ""  # Reset for next entity
 
+            # Append token as non-date
             print(f"Debug -- Appending non-date Token: {token}")
-            merged_entities.append((token, 'other'))
+            merged_entities.append((token, 'non-date'))
 
-    if current_date: 
+    # If there's any leftover accumulated date data, add it to merged_entities
+    if current_date:
         print(f"Debug -- Dangling leftover date added: {current_date}")
         merged_entities.append((current_date, 'date'))
 
     return merged_entities
 
+
+
+
     # NOTE: labels aren't being applied properly ... This is the LABEL approach 
     #
     # Loop through tokens and labels