Update model_utils.py

model_utils.py

@@ -23,39 +23,23 @@ def initialize_data_dict():
 def parse_products(raw_text):
     structured = []
     lines = raw_text.split('\n')
-
     for line in lines:
-        line = line.strip()
-        if not line:
-            continue
-
         match = re.match(r"(\d+)\s+(.*)\s+([\d,]+\.\d{2})\s+([\d,]+\.\d{2})", line)
         if match:
             qty, desc, unit_price, amount = match.groups()
             structured.append({
-                "qty": int(qty),
+                "qty": qty,
                 "description": desc.strip(),
-                "unit_price": float(unit_price.replace(",", "")),
-                "amount": float(amount.replace(",", ""))
-            })
-            continue
-
-        match_description_mixed = re.search(r"^(.*?)(\d+)\s+[^A-Za-z0-9\s]?([\d.,]+)\s+[^A-Za-z0-9\s]?([\d.,]+)$", line)
-        if match_description_mixed:
-            structured.append({
-                "qty": int(match_description_mixed.group(2)),
-                "description": match_description_mixed.group(1).strip(" .:-"),
-                "unit_price": float(match_description_mixed.group(3).replace(",", "")),
-                "amount": float(match_description_mixed.group(4).replace(",", ""))
+                "unit_price": unit_price,
+                "amount": amount
             })
-        else:
+        elif line.strip():
             structured.append({
                 "qty": 0,
-                "description": line,
-                "unit_price": 0.0,
-                "amount": 0.0
+                "description": line.strip(),
+                "unit_price": 0,
+                "amount": 0
             })
-
     return structured
 
 def extract_invoice_data_from_image(image_path: str):