Update app.py

app.py

@@ -75,29 +75,7 @@ ATTRIBUTE_MAPPING = {
 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", "CG COMMERCIAL MOTORS", "Fusion",
-    "control panel for single phase submerisible pumps",
-    "single phase digital starter dry run and timer panel", "5HP AV1 XL Kirloskar Pump",
-    "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", "Kirloskar Water Pump",
-    "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"
+    # Add more products here
 ]
 
 # Salesforce credentials
@@ -114,176 +92,82 @@ EXCEL_FILE_PATH = os.getenv("EXCEL_FILE_PATH", "DataStorage.xlsx")
 # Function to extract text using PaddleOCR
 def extract_text(image):
     result = ocr.ocr(image)
-    extracted_text = []
-    for line in result[0]:
-        extracted_text.append(line[1][0])
-    extracted_text_str = "\n".join(extracted_text)
-    print("Extracted Text:", extracted_text_str)  # Debug: Log extracted text
-    return extracted_text_str
+    extracted_text = "\n".join([line[1][0] for line in result[0]])
+    return extracted_text
 
 # Function to find product name from the predefined list using fuzzy matching
 def match_product_name(text):
-    best_match = None
-    best_score = 0
-
+    best_match, best_score = None, 0
     for line in text.split("\n"):
         match, score = process.extractOne(line, PRODUCT_NAMES)
         if score > best_score:
-            best_match = match
-            best_score = score
-
-    print(f"Best Match: {best_match}, Score: {best_score}")
+            best_match, best_score = match, score
     return best_match if best_score >= 70 else None
 
 # Function to find attributes and their values
 def find_attributes(text):
     structured_data = {}
-
-    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 = re.search(pattern, text, re.IGNORECASE)
         if match:
             structured_data[sf_attr] = match.group(1).strip()
-
     return structured_data
 
-# Function to sanitize numeric values
-def sanitize_numeric(value):
-    try:
-        if isinstance(value, (int, float)):
-            return value
-        if '/' in value:
-            numerator, denominator = value.split('/')
-            return float(numerator) / float(denominator)
-        sanitized = re.sub(r'[^\d\.\-]', '', value)
-        return float(sanitized) if sanitized else None
-    except (ValueError, ZeroDivisionError):
-        return None
-
-# Function to save structured data to the Excel file
-def save_to_excel(data):
-    if not data:
-        return "No data to save."
-
-    if not os.path.exists(EXCEL_FILE_PATH):
-        df = pd.DataFrame([data])
-        df.to_excel(EXCEL_FILE_PATH, index=False, engine="openpyxl")
-    else:
-        existing_df = pd.read_excel(EXCEL_FILE_PATH, engine="openpyxl")
-        new_data_df = pd.DataFrame([data])
-        updated_df = pd.concat([existing_df, new_data_df], ignore_index=True)
-        updated_df.to_excel(EXCEL_FILE_PATH, index=False, engine="openpyxl")
-
-    return EXCEL_FILE_PATH
-
 # Unified function for processing images
 def process_image(image, quantity, mode, entry_type):
     try:
-        extracted_text = extract_text(image)  # Extract text from image
-        attributes = find_attributes(extracted_text)  # Extract attributes from text
-
-        if "Productname__c" not in attributes or not attributes["Productname__c"]:
-            attributes["Productname__c"] = match_product_name(extracted_text)
-
-        attributes["Quantity__c"] = sanitize_numeric(quantity)
-
-        if not attributes:
-            return f"Extracted Text:\n{extracted_text}\n\nNo attributes found in the image.", None
-
-        numbered_output = "\n".join(
-            [f"{key.replace('__c', '').replace('_', ' ').title()}: {value}" for key, value in attributes.items()]
-        )
-
-        file_path = save_to_excel(attributes)
-
-        if mode == "Entry":
-            if entry_type == "Sales":
-                message = "Sales entry added."
-            elif entry_type == "Non-Sales":
-                message = "Non-Sales entry added."
-            else:
-                message = "Invalid entry type. Please select Sales or Non-Sales."
-        elif mode == "Exit":
-            message = "Exit mode is currently unavailable."
-        else:
-            message = "Invalid mode. Please select Entry or Exit."
-
-        return f"Extracted Text:\n{extracted_text}\n\n{numbered_output}\n\n{message}", file_path
-
+        extracted_text = extract_text(image)
+        attributes = find_attributes(extracted_text)
+        attributes["Quantity__c"] = quantity
+        numbered_output = "\n".join([f"{k}: {v}" for k, v in attributes.items()])
+        return f"Extracted Text:\n{extracted_text}\n\nAttributes:\n{numbered_output}", None
     except Exception as e:
-        return f"Error during processing: {str(e)}", None
+        return f"Error: {str(e)}", None
 
-# Function to pull data from Salesforce MotorDataAPI
-def pull_data_from_motor_api():
+# Function to pull stock data from Salesforce
+def pull_stock_data():
     try:
         sf = Salesforce(
             username=SALESFORCE_USERNAME,
             password=SALESFORCE_PASSWORD,
             security_token=SALESFORCE_SECURITY_TOKEN,
         )
-        motor_data = sf.apexecute("MotorDataAPI/", method="GET")
-        return motor_data
+        stock_data = sf.apexecute("MotorDataAPI", method="GET")
+        return stock_data
     except Exception as e:
-        print("Error pulling data from MotorDataAPI:", e)
         return f"Error: {str(e)}"
 
 # Function to format Salesforce data for display
 def format_salesforce_data():
-    try:
-        data = pull_data_from_motor_api()
-        if isinstance(data, list):
-            return "\n".join(
-                [
-                    f"{i + 1}. Product Name: {item.get('Product_Name__c', 'N/A')}, "
-                    f"Model: {item.get('Model_Name__c', 'N/A')}, "
-                    f"Current Stocks: {item.get('Current_Stocks__c', 'N/A')}"
-                    for i, item in enumerate(data)
-                ]
-            )
-        else:
-            return data
-    except Exception as e:
-        print("Error in format_salesforce_data:", e)
-        return f"Error retrieving data: {str(e)}"
-
-interface = gr.Interface(
-    tabs=[
+    data = pull_stock_data()
+    if isinstance(data, list):
+        return "\n".join([f"{item.get('Product_Name__c', 'N/A')} - {item.get('Stock', 'N/A')}" for item in data])
+    return data
+
+# Gradio interfaces
+interface = gr.TabbedInterface(
+    [
         gr.Interface(
             fn=process_image,
             inputs=[
                 gr.Image(type="numpy"),
-                gr.Number(label="Quantity", value=1, interactive=True),
-                gr.Dropdown(label="Mode", choices=["Entry", "Exit"], value="Entry"),
-                gr.Radio(label="Entry Type", choices=["Sales", "Non-Sales"], value="Sales", interactive=True)
-            ],
-            outputs=[
-                gr.Text(label="Image Data Viewer"),
-                gr.File(label="Data Storage Manager")
+                gr.Number(label="Quantity"),
+                gr.Dropdown(label="Mode", choices=["Entry", "Exit"]),
+                gr.Radio(label="Entry Type", choices=["Sales", "Non-Sales"]),
             ],
-            title="Processing - VENKATA RAMANA MOTORS",
-            description="Process images for Entry (Sales/Non-Sales) or Exit (Sales/Non-Sales) mode to update stock."
-        ),
-        gr.Interface(
-            fn=lambda: pd.read_excel(EXCEL_FILE_PATH) if os.path.exists(EXCEL_FILE_PATH) else pd.DataFrame(),
-            inputs=[],
-            outputs=gr.DataFrame(label="Sales Data"),
-            title="View Saved Data",
-            description="Review previously saved entries in tabular format."
+            outputs="text",
+            title="Process Image"
         ),
         gr.Interface(
             fn=format_salesforce_data,
             inputs=[],
-            outputs=gr.Text(label="Stock Updates"),
-            title="STOCK UPDATES",
-            description="View current stock details from Salesforce."
-        )
+            outputs="text",
+            title="Stock Updates"
+        ),
     ],
     title="VENKATA RAMANA MOTORS Dashboard",
-    description="A comprehensive tool for processing motor data, updating stocks, and viewing Salesforce records."
+    description="OCR and Salesforce integration for motor inventory."
 )
 
 if __name__ == "__main__":