Setup HF Space: Gradio app, deps (gradio), apt packages

app.py

@@ -1,97 +1,4 @@
-import os
-import uuid
-import json
-from flask import Flask, request, render_template, jsonify, send_file
-from werkzeug.utils import secure_filename
-from pdf_comparator import PDFComparator
-import tempfile
-import shutil
+import gradio as gr
+from pdf_comparator import create_demo
 
-app = Flask(__name__)
-app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max file size
-app.config['UPLOAD_FOLDER'] = 'uploads'
-app.config['RESULTS_FOLDER'] = 'results'
-
-# Ensure directories exist
-os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
-os.makedirs(app.config['RESULTS_FOLDER'], exist_ok=True)
-
-ALLOWED_EXTENSIONS = {'pdf'}
-
-def allowed_file(filename):
-    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
-
-@app.route('/')
-def index():
-    return render_template('index.html')
-
-@app.route('/upload', methods=['POST'])
-def upload_files():
-    if 'pdf1' not in request.files or 'pdf2' not in request.files:
-        return jsonify({'error': 'Both PDF files are required'}), 400
-    
-    pdf1 = request.files['pdf1']
-    pdf2 = request.files['pdf2']
-    
-    if pdf1.filename == '' or pdf2.filename == '':
-        return jsonify({'error': 'Both PDF files are required'}), 400
-    
-    if not (allowed_file(pdf1.filename) and allowed_file(pdf2.filename)):
-        return jsonify({'error': 'Only PDF files are allowed'}), 400
-    
-    # Create unique session directory
-    session_id = str(uuid.uuid4())
-    session_dir = os.path.join(app.config['UPLOAD_FOLDER'], session_id)
-    os.makedirs(session_dir, exist_ok=True)
-    
-    # Save uploaded files
-    pdf1_path = os.path.join(session_dir, secure_filename(pdf1.filename))
-    pdf2_path = os.path.join(session_dir, secure_filename(pdf2.filename))
-    
-    pdf1.save(pdf1_path)
-    pdf2.save(pdf2_path)
-    
-    try:
-        # Initialize PDF comparator
-        comparator = PDFComparator()
-        
-        # Perform comparison
-        results = comparator.compare_pdfs(pdf1_path, pdf2_path, session_id)
-        
-        # Save results
-        results_path = os.path.join(app.config['RESULTS_FOLDER'], f'{session_id}_results.json')
-        with open(results_path, 'w') as f:
-            json.dump(results, f, indent=2)
-        
-        return jsonify({
-            'success': True,
-            'session_id': session_id,
-            'results': results
-        })
-        
-    except Exception as e:
-        return jsonify({'error': str(e)}), 500
-
-@app.route('/results/<session_id>')
-def get_results(session_id):
-    results_path = os.path.join(app.config['RESULTS_FOLDER'], f'{session_id}_results.json')
-    
-    if not os.path.exists(results_path):
-        return jsonify({'error': 'Results not found'}), 404
-    
-    with open(results_path, 'r') as f:
-        results = json.load(f)
-    
-    return jsonify(results)
-
-@app.route('/download/<session_id>/<filename>')
-def download_file(session_id, filename):
-    file_path = os.path.join(app.config['UPLOAD_FOLDER'], session_id, filename)
-    
-    if not os.path.exists(file_path):
-        return jsonify({'error': 'File not found'}), 404
-    
-    return send_file(file_path, as_attachment=True)
-
-if __name__ == '__main__':
-    app.run(debug=True, host='0.0.0.0', port=5000)
+demo = create_demo()

apt.txt

@@ -0,0 +1,3 @@
+poppler-utils
+tesseract-ocr
+libzbar0

requirements.txt

@@ -14,3 +14,4 @@ matplotlib==3.7.2
 pandas==2.0.3
 reportlab==4.0.4
 regex==2023.10.3
+gradio==4.44.0