Spaces:
Sleeping
Sleeping
# libraries | |
from flask import Flask, render_template, request, redirect, url_for, flash, session, send_from_directory | |
import os | |
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 PaddleOCR | |
# Configure logging | |
logging.basicConfig( | |
level=logging.INFO, | |
handlers=[ | |
logging.StreamHandler() # Remove FileHandler and log only to the console | |
] | |
) | |
# Flask App | |
app = Flask(__name__) | |
app.secret_key = 'your_secret_key' | |
app.config['UPLOAD_FOLDER'] = 'uploads/' | |
app.config['RESULT_FOLDER'] = 'results/' | |
UPLOAD_FOLDER = 'static/uploads/' | |
RESULT_FOLDER = 'static/results/' | |
os.makedirs(UPLOAD_FOLDER, exist_ok=True) | |
os.makedirs(RESULT_FOLDER, exist_ok=True) | |
if not os.path.exists(app.config['UPLOAD_FOLDER']): | |
os.makedirs(app.config['UPLOAD_FOLDER']) | |
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'] = '/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.") | |
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) | |
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') | |
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', []) | |
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) | |
logging.info(f"Uploaded file: {filename} at {file_path}") | |
session['uploaded_files'] = uploaded_files | |
flash('Files successfully uploaded') | |
logging.info(f"Files successfully uploaded: {uploaded_files}") | |
return redirect(url_for('index')) | |
def remove_file(): | |
uploaded_files = session.get('uploaded_files', []) | |
if uploaded_file: | |
for filename in uploaded_files: | |
file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename) | |
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: {file_path}") # More specific log | |
session.pop('uploaded_files', None) | |
flash('Files successfully removed') | |
logging.info("All uploaded files removed") | |
else: | |
flash('No file to remove.') | |
logging.warning("File not found for removal") | |
return redirect(url_for('index')) | |
def reset_upload(): | |
"""Reset the uploaded file and the processed data.""" | |
uploaded_file = session.get('uploaded_file', []) | |
if uploaded_file: | |
for filename in uploaded_file: | |
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') | |
else: | |
flash('No file to remove.') | |
return redirect(url_for('index')) | |
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')) | |
file_paths = [os.path.join(app.config['UPLOAD_FOLDER'], filename) for filename in uploaded_files] | |
logging.info(f"Processing files: {file_paths}") | |
extracted_text = {} | |
processed_Img = {} | |
try: | |
extracted_text, processed_Img = extract_text_from_images(file_paths) | |
logging.info(f"Extracted text: {extracted_text}") | |
logging.info(f"Processed images: {processed_Img}") | |
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: | |
logging.error(f"Error during LLM processing: {e}") | |
logging.info("Running backup model...") | |
LLMdata = {} | |
extracted_text, processed_Img = extract_text_from_images(file_paths) | |
logging.info(f"Extracted text(Backup): {extracted_text}") | |
logging.info(f"Processed images(Backup): {processed_Img}") | |
if extracted_text: | |
text = json_to_llm_str(extracted_text) | |
LLMdata = NER_Model(text) | |
logging.info(f"NER model data: {LLMdata}") | |
else: | |
logging.warning("No extracted text available for backup model") | |
cont_data = process_extracted_text(extracted_text) | |
logging.info(f"Contextual data: {cont_data}") | |
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') | |
logging.info("Data processed and analyzed successfully") | |
return redirect(url_for('result')) | |
def result(): | |
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) | |
def uploaded_file(filename): | |
logging.info(f"Serving file: {filename}") | |
return send_from_directory(app.config['UPLOAD_FOLDER'], filename) | |
if __name__ == '__main__': | |
logging.info("Starting Flask app") | |
app.run(debug=True) | |