Update app.py

app.py

@@ -1,8 +1,17 @@
 # libraries
 from flask import Flask, render_template, request, redirect, url_for, flash, session, send_from_directory
 import os
-from utility.utils import extract_text_from_images,Data_Extractor,json_to_llm_str,process_extracted_text,process_resume_data
+import logging
+from utility.utils import extract_text_from_images, Data_Extractor, json_to_llm_str, process_extracted_text, process_resume_data
 from backup.backup import NER_Model
+from paddleOCR import 
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s %(levelname)s: %(message)s', handlers=[
+    logging.FileHandler("app.log"),
+    logging.StreamHandler()
+])
+
 # Flask App
 app = Flask(__name__)
 app.secret_key = 'your_secret_key'
@@ -19,17 +28,20 @@ if not os.path.exists(app.config['UPLOAD_FOLDER']):
 @app.route('/')
 def index():
     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)
 
 @app.route('/upload', methods=['POST'])
 def upload_file():
     if 'files' not in request.files:
         flash('No file part')
+        logging.warning("No file part found in the request")
         return redirect(request.url)
 
     files = request.files.getlist('files')  # Get multiple 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 = []
@@ -38,9 +50,11 @@ def upload_file():
             filename = file.filename
             file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
             uploaded_files.append(filename)
+            logging.info(f"Uploaded file: {filename}")
 
     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')
@@ -48,8 +62,10 @@ def remove_file():
     uploaded_files = session.get('uploaded_files', [])
     for filename in uploaded_files:
         os.remove(os.path.join(app.config['UPLOAD_FOLDER'], filename))
+        logging.info(f"Removed file: {filename}")
     session.pop('uploaded_files', None)
     flash('Files successfully removed')
+    logging.info("All uploaded files removed")
     return redirect(url_for('index'))
 
 @app.route('/process', methods=['POST'])
@@ -57,58 +73,60 @@ def process_file():
     uploaded_files = session.get('uploaded_files', [])
     if not uploaded_files:
         flash('No files selected for processing')
+        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}")
 
-    # Extract text from all images
-    extracted_text,processed_Img = extract_text_from_images(file_paths,RESULT_FOLDER)
-    # Convert PDF to text   
-    print("extracted_text----------------------------",extracted_text)
-    print("extracted_text type----------------------------",type(extracted_text))
-
-    print("processed_Img----------------------------",processed_Img)
-    print("processed_Img type----------------------------",type(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)
-         print("llmText---------->",llmText)
-         LLMdata = Data_Extractor(llmText)
-         print("LLM data----------------------------",LLMdata)        
-              
+        llmText = json_to_llm_str(extracted_text)
+        logging.info(f"LLM text: {llmText}")
+        
+        LLMdata = Data_Extractor(llmText)
+        logging.info(f"LLM data: {LLMdata}")
+
     except Exception as e:
-         # Handling any exceptions during the process
-         print(f"An error occurred: {e}")
-         # Run the backup model in case of an exception
-         print("Running backup model...")   
-         
-         text=json_to_llm_str(extracted_text)
-         LLMdata=NER_Model(text)
-         print("NER data----------------------------",LLMdata)            
-         
-     
-    cont_data=process_extracted_text(extracted_text)
-    print("cont_data----------------------------",cont_data) 
-    #storing the paresed results
-    processed_data = process_resume_data(LLMdata,cont_data,extracted_text)    
+        logging.error(f"Error during LLM processing: {e}")
+        logging.info("Running backup model...")
+        
+        # Run the backup model in case of an exception
+        text = json_to_llm_str(extracted_text)
+        LLMdata = NER_Model(text)
+        logging.info(f"NER model data: {LLMdata}")
+
+    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}")
 
     session['processed_data'] = processed_data
     session['processed_Img'] = processed_Img
-    flash('Data processed and analyzed successfully ')
+    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', {})
     processed_Img = session.get('processed_Img', {})
-    return render_template('result.html', data=processed_data,Img=processed_Img)
+    logging.info(f"Displaying results: Data - {processed_data}, Images - {processed_Img}")
+    return render_template('result.html', data=processed_data, Img=processed_Img)
 
 @app.route('/uploads/<filename>')
 def uploaded_file(filename):
+    logging.info(f"Serving file: {filename}")
     return send_from_directory(app.config['UPLOAD_FOLDER'], filename)
 
 if __name__ == '__main__':
-    app.run(debug=True)
+    logging.info("Starting Flask app")
+    app.run(debug=True)