Update app.py

app.py

@@ -1,4 +1,3 @@
-
 import os
 from paddleocr import PaddleOCR
 from PIL import Image, ImageEnhance
@@ -71,6 +70,35 @@ ATTRIBUTE_MAPPING = {
     "coolingmethod": "coolingmethod__c"
 }
 
+# List of product names to match
+PRODUCT_NAMES = [
+    "Centrifugal mono block pump", "SINGLE PHASE MOTOR STARTER", "EasyPact EZC 100",
+    "Openwell Submersible Pumpset", "Electric Motor", "Self Priming Pump",
+    "Control panel for single phase submersible pumps", "MOTOR", "Submersible pump set",
+    "Fusion submersible pump set", "DCT", "Shock proof water proof",
+    "control panel for single phase submerisible pumps",
+    "single phase digital starter dry run and timer panel",
+    "Phase stainless steel submersible pump", "Submersible pump", "WB15X",
+    "Vtype self priming pump", "SP SHINE DISC", "havells submersible pump",
+    "Havells open well Submersible pump", "Bertolini pump CK3 90pp",
+    "WPA 772 Water Pump Assy", "bertolini TTL triplex high pressure plunger pumps",
+    "Generic plunger high pressure pump", "Apple Normal, Banana",
+    "Cast Iron KSb centrifugal pump", "5.5kw Water Pump",
+    "KSB reliable i line centrifuged pumps", "Apple Normal, Orange, Banana",
+    "Positive API 6745 hydraulic diaphragm pump", "1/2 inch Fuel Hose Pipe",
+    "Rotodel motor pump", "PVC Electrical Insulation Materials",
+    "Electric kirloskar domestic water pump", "Electrical Insulation Materials",
+    "sellowell motor pump", "bhupathi submersible pump set",
+    "Flowshine Submersible pump set", "Index submersible pump",
+    "Wintoss Plastic Electric Switch Board", "Electric 18 watt ujagar cooler pump",
+    "Generator Service", "LG WM FHT1207ZWL, LG REF GL-S292RSCY",
+    "Water tank, Filters, Water Pump", "MS Control Submersible Panel",
+    "Centrifugal Monoblock Pumps", "Electric Motor with Pump BodyBlue and White",
+    "Various Repair and Maintenance Parts", "Earthmax Pump",
+    "Water Tank, Filters, Water Pump", "Centrifugal Water Pump for Agriculture",
+    "mono block pumps"
+]
+
 # Salesforce credentials
 SALESFORCE_USERNAME = "venkatramana@sandbox.com"
 SALESFORCE_PASSWORD = "Venkat12345@"
@@ -90,14 +118,28 @@ def extract_text(image):
         extracted_text.append(line[1][0])
     return "\n".join(extracted_text)
 
+# Function to find product name from the predefined list
+def match_product_name(text):
+    for product_name in PRODUCT_NAMES:
+        if re.search(rf"\b{re.escape(product_name)}\b", text, re.IGNORECASE):
+            return product_name
+    return None
+
 # Function to find attributes and their values
 def find_attributes(text):
     structured_data = {}
+
+    # Match and add product name
+    matched_product = match_product_name(text)
+    if matched_product:
+        structured_data["Productname__c"] = matched_product
+
     for readable_attr, sf_attr in ATTRIBUTE_MAPPING.items():
         pattern = rf"{re.escape(readable_attr)}[:\-]?\s*(.+)"  # Match the attribute and capture its value
         match = re.search(pattern, text, re.IGNORECASE)
         if match:
             structured_data[sf_attr] = match.group(1).strip()
+
     return structured_data
 
 # Function to sanitize numeric values