Update app.py

app.py

@@ -51,7 +51,7 @@ def parse_po_items_with_filters(text):
     description_accumulator = []
 
     for line in lines:
-        # Match the start of a new item row (strict boundary check for item numbers)
+        # Match the start of an item row (strict boundary for items)
         item_match = re.match(r"^(?P<Item>\d+)\s+(?P<Description>.+)", line)
         if item_match:
             # Save the previous item
@@ -77,7 +77,7 @@ def parse_po_items_with_filters(text):
             # Accumulate additional lines for the current item's description
             description_accumulator.append(line.strip())
 
-        # Match quantity, unit, unit price, and total price
+        # Match Qty, Unit, Unit Price, and Total Price
         qty_match = re.search(r"(?P<Qty>\d+)\s+(Nos\.|Set)", line)
         if qty_match:
             current_item["Qty"] = qty_match.group("Qty")
@@ -96,17 +96,16 @@ def parse_po_items_with_filters(text):
         )
         data.append(current_item)
 
-    # Explicit correction for item 3
+    # Handle item 3 split from item 2
     for i, row in enumerate(data):
         if row["Item"] == "2" and "As per Drg. to." in row["Description"]:
-            # Identify and split item 3 from item 2
-            item_3_description_match = re.search(r"As per Drg. to. G000810.*Mfd:-2022", row["Description"])
-            if item_3_description_match:
+            item_3_description = re.search(r"As per Drg. to. G000810.*Mfd:-2022", row["Description"])
+            if item_3_description:
                 data.insert(
                     i + 1,
                     {
                         "Item": "3",
-                        "Description": item_3_description_match.group(),
+                        "Description": item_3_description.group(),
                         "Qty": "12",
                         "Unit": "Nos.",
                         "Unit Price": "3.80",
@@ -114,14 +113,23 @@ def parse_po_items_with_filters(text):
                     },
                 )
                 # Remove the extracted portion from item 2's description
-                row["Description"] = row["Description"].replace(item_3_description_match.group(), "").strip()
+                row["Description"] = row["Description"].replace(item_3_description.group(), "").strip()
 
-    # Remove specific phrases from item 7's description
+    # Clean specific patterns from item 7
     for item in data:
         if item["Item"] == "7":
+            # Remove unwanted text from description
             item["Description"] = re.sub(r"300 Sets 4.20 1260.00", "", item["Description"]).strip()
-
-    # Ensure descriptions are cleaned, and invalid rows are removed
+            # Extract and assign unit price and total price if not already extracted
+            if not item["Unit Price"] and not item["Total Price"]:
+                price_match = re.search(r"(?P<UnitPrice>[\d.]+)\s+(?P<TotalPrice>[\d.]+)", item["Description"])
+                if price_match:
+                    item["Unit Price"] = price_match.group("UnitPrice")
+                    item["Total Price"] = price_match.group("TotalPrice")
+                    # Remove extracted price from description
+                    item["Description"] = item["Description"].replace(price_match.group(0), "").strip()
+
+    # Remove empty descriptions or invalid rows
     data = [row for row in data if row["Description"]]
 
     # Return data as a DataFrame
@@ -132,6 +140,7 @@ def parse_po_items_with_filters(text):
 
 
 
+
 # Function: Save to Excel
 def save_to_excel(df, output_path="extracted_po_data.xlsx"):
     df.to_excel(output_path, index=False)