Update app.py

app.py

@@ -103,13 +103,13 @@ def extract_items(text):
             # Pattern for invoice_4.pdf: "Monitor 24 inch | 7 | 150.00 | 1050.00"
             table_row_pattern = r"\|?\s*([A-Za-z\s\d-]+(?:\s[A-Za-z\s\d-]+)*?)\s*\|?\s*(\d+)\s*\|?\s*([\d.]+)\s*\|?\s*([\d.]+)\s*\|?"
         else:
-            # Pattern for Invoice_6164752968.pdf: "1 x Chicken Frankie | 60 | 6 | 54 | 2.5% | 1.35 | 2.5% | 1.35 | 56.7"
-            # Adjusted to be more flexible for potential spacing or formatting issues
-            table_row_pattern = r"\|?\s*(\d+\s*x\s*[A-Za-z\s\d-]+(?:\s[A-Za-z\s\d-]+)*?)\s*\|?\s*([\d.]+)\s*\|?\s*([\d.]+)\s*\|?\s*([\d.]+)\s*(?:\|?\s*[\d.%]+\s*\|?\s*[\d.]+){2}\s*\|?\s*([\d.]+)\s*\|?"
+            # Simplified pattern for Invoice_6164752968.pdf: "1 x Chicken Frankie | 60 | 6 | 54 | 2.5% | 1.35 | 2.5% | 1.35 | 56.7"
+            table_row_pattern = r"(\d+\s*x\s*[A-Za-z\s\d-]+(?:\s[A-Za-z\s\d-]+)*?)\s*(?:\|\s*)?([\d.]+)\s*(?:\|\s*)?([\d.]+)\s*(?:\|\s*)?([\d.]+)\s*(?:\|\s*[0-9.%]+\s*\|?\s*[\d.]+){2}\s*(?:\|\s*)?([\d.]+)"
 
         for line in table_lines:
             line = line.strip()
             if not line or "HSN Code" in line or "Total" in line:
+                print(f"Skipping irrelevant line: {line}")
                 continue
             # Skip alignment rows (e.g., "|---|---|")
             if re.match(r"\|?\s*[-:]+(\s*\|\s*[-:]+)*\s*\|?", line):
@@ -118,16 +118,10 @@ def extract_items(text):
             print(f"Processing main table row: {line}")  # Debug
             match = re.match(table_row_pattern, line)
             if match:
-                if table_format[0] == "Item Description":
-                    description = match.group(1).strip()
-                    quantity = int(match.group(2))
-                    unit_price = float(match.group(3))
-                    total_price = float(match.group(4))
-                else:
-                    description = match.group(1).strip()
-                    quantity = int(description.split(' x ')[0].strip()) if ' x ' in description else 1
-                    unit_price = float(match.group(2))  # Gross value
-                    total_price = float(match.group(5))  # Total after taxes
+                description = match.group(1).strip()
+                quantity = int(description.split(' x ')[0].strip()) if ' x ' in description else 1
+                unit_price = float(match.group(2))  # Gross value
+                total_price = float(match.group(5))  # Total after taxes
                 items.append({
                     "description": description,
                     "quantity": quantity,
@@ -136,7 +130,27 @@ def extract_items(text):
                 })
                 print(f"Extracted Item: {description}, Qty: {quantity}, Unit Price: {unit_price}, Total Price: {total_price}")  # Debug
             else:
-                print(f"Failed to match main table row: {line}")
+                # Fallback: Split by | and validate fields manually
+                fields = [f.strip() for f in line.split('|')]
+                print(f"Fallback processing: {fields}")  # Debug
+                if len(fields) >= 9:  # Expecting at least 9 fields (description, gross value, discount, net value, CGST %, CGST amount, SGST %, SGST amount, total)
+                    try:
+                        description = fields[0].strip()
+                        if not description.startswith('1 x'):
+                            continue  # Skip if not an item row
+                        quantity = int(description.split(' x ')[0].strip())
+                        unit_price = float(fields[1].strip())  # Gross value
+                        total_price = float(fields[-1].strip())  # Total after taxes
+                        items.append({
+                            "description": description,
+                            "quantity": quantity,
+                            "unit_price": unit_price,
+                            "total_price": total_price
+                        })
+                        print(f"Fallback Extracted Item: {description}, Qty: {quantity}, Unit Price: {unit_price}, Total Price: {total_price}")  # Debug
+                    except (ValueError, IndexError) as e:
+                        print(f"Failed fallback parsing for line '{line}': {str(e)}")
+                        continue
 
     # Extract platform fee table (e.g., Sr.No Particulars)
     platform_fee_start = -1