Update app.py

app.py

@@ -32,12 +32,18 @@ if not os.path.exists(app.config['RESULT_FOLDER']):
     os.makedirs(app.config['RESULT_FOLDER'])
 
 # Set the PaddleOCR home directory to a writable location
-#os.environ['PADDLEOCR_HOME'] = os.path.join(app.config['UPLOAD_FOLDER'], '.paddleocr')  # Change made here
 os.environ['PADDLEOCR_HOME'] = '/tmp/.paddleocr' 
 
+# Check if PaddleOCR home directory is writable
+if not os.path.exists('/tmp/.paddleocr'):
+    os.makedirs('/tmp/.paddleocr', exist_ok=True)
+    logging.info("Created PaddleOCR home directory.")
+else:
+    logging.info("PaddleOCR home directory exists.")
+
 @app.route('/')
 def index():
-    uploaded_files = session.get('uploaded_files', [])  # Retrieve the session data
+    uploaded_files = session.get('uploaded_files', [])
     logging.info(f"Accessed index page, uploaded files: {uploaded_files}")
     return render_template('index.html', uploaded_files=uploaded_files)
 
@@ -48,38 +54,38 @@ def upload_file():
         logging.warning("No file part found in the request")
         return redirect(request.url)
 
-    files = request.files.getlist('files')  # Get multiple files
+    files = request.files.getlist('files')  
     if not files or all(file.filename == '' for file in files):
         flash('No selected files')
         logging.warning("No files selected for upload")
         return redirect(request.url)
 
-    uploaded_files = session.get('uploaded_files', [])  # Get the existing session data
+    uploaded_files = session.get('uploaded_files', [])
     for file in files:
         if file:
             filename = file.filename
             file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
             file.save(file_path)
-            uploaded_files.append(filename)  # Add each file to the session's list
-            logging.info(f"Uploaded file: {filename}")
+            uploaded_files.append(filename)
+            logging.info(f"Uploaded file: {filename} at {file_path}")
 
-    session['uploaded_files'] = uploaded_files  # Save uploaded files in session
+    session['uploaded_files'] = uploaded_files  
     flash('Files successfully uploaded')
     logging.info(f"Files successfully uploaded: {uploaded_files}")
     return redirect(url_for('index'))
 
 @app.route('/remove_file')
 def remove_file():
-    uploaded_files = session.get('uploaded_files', [])  # Get the uploaded files from the session
+    uploaded_files = session.get('uploaded_files', [])
     for filename in uploaded_files:
         file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
-        if os.path.exists(file_path):  # Check if the file exists before trying to remove it
+        if os.path.exists(file_path):
             os.remove(file_path)
             logging.info(f"Removed file: {filename}")
         else:
-            logging.warning(f"File not found for removal: {filename}")
+            logging.warning(f"File not found for removal: {file_path}")  # More specific log
 
-    session.pop('uploaded_files', None)  # Clear the session files
+    session.pop('uploaded_files', None)  
     flash('Files successfully removed')
     logging.info("All uploaded files removed")
     return redirect(url_for('index'))
@@ -92,20 +98,17 @@ def process_file():
         logging.warning("No files selected for processing")
         return redirect(url_for('index'))
 
-    # Create a list of file paths for the extracted text function
     file_paths = [os.path.join(app.config['UPLOAD_FOLDER'], filename) for filename in uploaded_files]
     logging.info(f"Processing files: {file_paths}")
 
-    extracted_text = {}  # Initialize extracted_text
-    processed_Img = {}  # Initialize processed_Img to avoid the UnboundLocalError
+    extracted_text = {}
+    processed_Img = {}
 
     try:
-        # Extract text from all images
         extracted_text, processed_Img = extract_text_from_images(file_paths, RESULT_FOLDER)
         logging.info(f"Extracted text: {extracted_text}")
         logging.info(f"Processed images: {processed_Img}")
 
-        # Call the Gemma model API and get the professional data
         llmText = json_to_llm_str(extracted_text)
         logging.info(f"LLM text: {llmText}")
         
@@ -116,7 +119,7 @@ def process_file():
         logging.error(f"Error during LLM processing: {e}")
         logging.info("Running backup model...")
 
-        LLMdata = {}  # Ensure LLMdata is initialized
+        LLMdata = {}
        
         if extracted_text:
             text = json_to_llm_str(extracted_text)
@@ -125,25 +128,22 @@ def process_file():
         else:
             logging.warning("No extracted text available for backup model")
 
-    # Processing results
     cont_data = process_extracted_text(extracted_text)
     logging.info(f"Contextual data: {cont_data}")
-    
-    # Storing the parsed results
+
     processed_data = process_resume_data(LLMdata, cont_data, extracted_text)
     logging.info(f"Processed data: {processed_data}")
 
-    # Store processed data and images in session
     session['processed_data'] = processed_data
-    session['processed_Img'] = processed_Img  # This will be either empty or populated from the try block
+    session['processed_Img'] = processed_Img
     flash('Data processed and analyzed successfully')
     logging.info("Data processed and analyzed successfully")
     return redirect(url_for('result'))
 
 @app.route('/result')
 def result():
-    processed_data = session.get('processed_data', {})  # Retrieve processed data from the session
-    processed_Img = session.get('processed_Img', {})  # Retrieve processed images from the session
+    processed_data = session.get('processed_data', {})
+    processed_Img = session.get('processed_Img', {})
     logging.info(f"Displaying results: Data - {processed_data}, Images - {processed_Img}")
     return render_template('result.html', data=processed_data, Img=processed_Img)