updates to date logic

app.py

@@ -27,13 +27,18 @@ def extract_features(tokens, labels):
     current_date = ""
 
     print(f"Debug -- Starting entity extraction")
+    #date_pattern = r"\d{1,2}/\d{1,2}/\d{2,4}"  # Matches full date formats like MM/DD/YYYY or DD/MM/YYYY
+    #partial_date_pattern = r"\d{1,2}$|[/-]$"  # Matches partial date components like "12" or "/" at the end
+
     date_pattern = r"\d{1,2}/\d{1,2}/\d{2,4}"  # Matches full date formats like MM/DD/YYYY or DD/MM/YYYY
-    partial_date_pattern = r"\d{1,2}$|[/-]$"  # Matches partial date components like "12" or "/" at the end
+    partial_date_pattern = r"^\d{1,2}/?$|^[/-]$"  # Matches partial date components like "12", "/", "02/", etc.
+
 
     
     # Loop through tokens and labels 
     for token, label in zip(tokens, labels): 
         print(f"Debug -- Potentially creating date,, token: {token} label: {label}")
+        
         if label == 'LABEL_1':
             # Check for partial date fragments (like '12' or '/')
             if re.match(partial_date_pattern, token):
@@ -41,7 +46,7 @@ def extract_features(tokens, labels):
                 current_date += token # Append token to the current entity
 
             # If the accumulated entity matches a full date
-            if re.match(date_pattern, current_date):
+            elif re.match(date_pattern, current_date):
                 merged_entities.append((current_date, 'date'))
                 print(f"Debug -- Complete date added: {token}")
                 current_date = ""  # Reset for next entity
@@ -62,6 +67,7 @@ def extract_features(tokens, labels):
                     print(f"Debug -- Finalizing leftover date added: {current_date}")
                     current_date = ""  # Reset
 
+                # Append LABEL_0 token
                 merged_entities.append((token, label))
 
     if current_date: