Update app.py

app.py

@@ -286,6 +286,7 @@ def extract_entities(pdf_file, text):
     primary_invoice_number = "Unknown"
     vendor_name = "Unknown"
     invoice_date = datetime.now().date()
+    due_date = None  # Due Date will be None unless explicitly found in the invoice
     total_amount = 0.0
 
     # Extract items first to use as a filter for NER
@@ -296,6 +297,7 @@ def extract_entities(pdf_file, text):
     invoice_num_pattern = r"(?:Invoice\s*(?:Number|No\.?|#)|Advice\s*(?:No\.?)|Order\s*(?:Number|No\.?))\s*[:\-\s#]*([\w-]+)|(?:INV-|ORD-|Z\d{2}APOT\d{9})([\w-]+)"
     vendor_pattern = r"(?:Vendor\s*(?:Name|Company)?|Supplier|Company\s*Name|From|Sold\s*By|Restaurant\s*Name|Vendor)\s*[:\-\s]*([A-Za-z\s&\.\-]+)(?=\s*(?:Address|Invoice\s*(?:No|Number)|Date|Phone|Email|\n|$))"
     invoice_date_pattern = r"(?:Invoice\s*Date|Date|Issue\s*Date)\s*[:\-\s]*(\d{4}-\d{2}-\d{2}|\d{2}/\d{2}/\d{4}|\d{2}-\d{2}-\d{4}|[A-Za-z]+\s*\d{1,2},\s*\d{4})"
+    due_date_pattern = r"(?:Due\s*Date|Payment\s*Due\s*(?:Date)?)\s*[:\-\s]*(\d{4}-\d{2}-\d{2}|\d{2}/\d{2}/\d{4}|\d{2}-\d{2}-\d{4}|[A-Za-z]+\s*\d{1,2},\s*\d{4})"
     total_amount_pattern = r"(?:Total\s*(?:Amount|Due|Value))\s*[:\-\s]*[₹$£€]?\s*([\d,]+\.?\d*)\s*(?:USD|GBP|EUR|INR)?"
 
     # Invoice Numbers (capture all, then prioritize)
@@ -362,6 +364,24 @@ def extract_entities(pdf_file, text):
         except ValueError as e:
             print(f"Failed to parse Invoice Date '{date_str}': {str(e)}")  # Debug
 
+    # Due Date (only extract if explicitly present in the invoice)
+    due_date_match = re.search(due_date_pattern, text, re.IGNORECASE)
+    if due_date_match:
+        date_str = due_date_match.group(1)
+        try:
+            if "/" in date_str:
+                due_date = datetime.strptime(date_str, "%m/%d/%Y").date()
+            elif "," in date_str:
+                due_date = datetime.strptime(date_str, "%B %d, %Y").date()
+            elif "-" in date_str:
+                try:
+                    due_date = datetime.strptime(date_str, "%Y-%m-%d").date()
+                except ValueError:
+                    due_date = datetime.strptime(date_str, "%d-%m-%Y").date()
+            print(f"Matched Due Date: {due_date}")  # Debug
+        except ValueError as e:
+            print(f"Failed to parse Due Date '{date_str}': {str(e)}")  # Debug
+
     # Total Amount (prioritize the final total after taxes and fees)
     total_amount_matches = re.finditer(total_amount_pattern, text, re.IGNORECASE)
     total_amounts = []
@@ -394,7 +414,7 @@ def extract_entities(pdf_file, text):
                         break
     print(f"Calculated Total Amount: {total_amount}")  # Debug
 
-    return primary_invoice_number, vendor_name, invoice_date, total_amount
+    return primary_invoice_number, vendor_name, invoice_date, due_date, total_amount
 
 def fetch_vendor_history(vendor_name, invoice_number, time_window_days=30):
     """Fetch historical invoices for the vendor from Salesforce."""
@@ -506,7 +526,7 @@ def calculate_fraud_score(amount, is_amount_anomaly, is_frequency_anomaly, is_ve
         score += 10
         reasoning.append("Invoice date is in the future.")
 
-    if due_date < today and invoice_date < today:
+    if due_date and due_date < today and invoice_date < today:
         score += 15
         reasoning.append("Due date has passed, indicating potential payment delay.")
 
@@ -536,13 +556,10 @@ def process_invoice(pdf_file):
     if "Error" in text:
         return f"**Error**: {text}"
 
-    invoice_number, vendor_name, invoice_date, total_amount = extract_entities(pdf_file, text)
+    invoice_number, vendor_name, invoice_date, due_date, total_amount = extract_entities(pdf_file, text)
     items = extract_items(pdf_file, text)
     text_length = len(text)
 
-    # Calculate Due Date (Invoice Date + 30 days)
-    due_date = invoice_date + timedelta(days=30)
-
     history_df = fetch_vendor_history(vendor_name, invoice_number)
     consistency_issues = check_data_consistency(invoice_number, vendor_name, invoice_date, history_df)
 
@@ -586,19 +603,26 @@ def process_invoice(pdf_file):
         items_str = "; ".join(item['description'] for item in items)  # Fallback to raw descriptions
         print(f"Fallback items_str: {items_str}")
 
-    # Format the invoice date and due date as DD-MM-YYYY
+    # Format the invoice date as DD-MM-YYYY
     formatted_invoice_date = invoice_date.strftime("%d-%m-%Y")
-    formatted_due_date = due_date.strftime("%d-%m-%Y")
+    # Format the due date as DD-MM-YYYY only if it exists
+    formatted_due_date = due_date.strftime("%d-%m-%Y") if due_date else None
 
     output = [
         "## Fraud Detection Summary",
         f"- **Invoice Number**: {invoice_number}",
         f"- **Vendor Name**: {vendor_name}",
         f"- **Invoice Date**: {formatted_invoice_date}",
-        f"- **Due Date**: {formatted_due_date}",
-        f"- **Invoice Amount**: ${total_amount:,.2f}" if '$' in text else f"- **Invoice Amount**: ₹{total_amount:,.2f}",
     ]
 
+    # Only include Due Date in the output if it was extracted from the invoice
+    if formatted_due_date:
+        output.append(f"- **Due Date**: {formatted_due_date}")
+
+    output.append(
+        f"- **Invoice Amount**: ${total_amount:,.2f}" if '$' in text else f"- **Invoice Amount**: ₹{total_amount:,.2f}"
+    )
+
     # Add items section
     output.append("- **Items Selected**:")
     if items:
@@ -629,13 +653,15 @@ def process_invoice(pdf_file):
                 "Vendor_Name__c": vendor_name,
                 "Invoice_Amount__c": total_amount,
                 "Invoice_Date__c": str(invoice_date),
-                "Due_Date__c": str(due_date),
                 "Fraud_Score__c": fraud_score,
                 "Fraud_Reason__c": "; ".join(fraud_reasoning),
                 "Flagged__c": fraud_score > 50,
                 "Status__c": "Flagged" if fraud_score > 50 else "Cleared",
                 "Items_Selected__c": items_str
             }
+            # Only include Due_Date__c if a due date was extracted
+            if due_date:
+                record_data["Due_Date__c"] = str(due_date)
             print(f"Record data being sent to Salesforce: {record_data}")  # Debug
             sf.Invoice_Record__c.create(record_data)
             print(f"Successfully created Salesforce record with Items_Selected__c: {items_str}")  # Debug