diff --git a/README.md b/README.md index c9d88c4..83377a5 100644 --- a/README.md +++ b/README.md @@ -10,6 +10,8 @@ A Python web application built with Flask that automatically renames PDF files b - **Intelligent Renaming**: Renames files to "LastName_FirstName.pdf" format - **Duplicate Handling**: Automatically appends counters for duplicate names - **ZIP Support**: Upload ZIP files and download processed results as ZIP +- **Job Management**: Background processing with job status tracking and history +- **Authentication**: Microsoft Entra ID and local admin login support - **Error Handling**: Gracefully skips files that can't be processed ## Prerequisites @@ -82,16 +84,19 @@ Users can choose their preferred login method on the login page. 3. **Access the web interface**: - Open `http://127.0.0.1:3000/` - - You'll be redirected to Microsoft login - - After authentication, you'll access the app + - Authenticate using Microsoft Entra ID or admin login 4. **Upload files**: - Select individual PDF files or ZIP archives containing PDFs - - Click "Process PDFs" + - Click "Process PDFs" - this creates a background job -5. **Download results**: - - Download the `renamed_files.zip` containing all processed PDFs - - Review any skipped files listed on the results page +5. **Monitor jobs**: + - Click "View Jobs" to see processing status and history + - Jobs show as "Queued", "Processing", or "Completed" + +6. **Download results**: + - When complete, download the ZIP file from the jobs page + - Review any skipped files listed for each job ## How It Works diff --git a/pdf_renamer.py b/pdf_renamer.py index b83b565..4afa0a9 100644 --- a/pdf_renamer.py +++ b/pdf_renamer.py @@ -1,8 +1,10 @@ import os import tempfile import zipfile +import threading +import uuid from functools import wraps -from flask import Flask, request, render_template_string, send_from_directory, redirect, url_for, session +from flask import Flask, request, render_template_string, redirect, url_for, session, send_from_directory from werkzeug.utils import secure_filename from PyPDF2 import PdfReader from authlib.integrations.flask_client import OAuth @@ -32,6 +34,11 @@ microsoft = oauth.register( ALLOWED_EXTENSIONS = {'pdf', 'zip'} +# Global jobs storage (in production, use database) +jobs = {} + +def login_required(f): + def login_required(f): @wraps(f) def decorated_function(*args, **kwargs): @@ -56,6 +63,68 @@ def extract_names_from_pdf(pdf_path): except Exception as e: return None +def process_job(job_id, files): + jobs[job_id]['status'] = 'processing' + processed_files = [] + temp_extract_dirs = [] + + for file_info in files: + filepath = file_info['path'] + filename = file_info['name'] + + if filename.lower().endswith('.zip'): + # Extract ZIP + extract_dir = os.path.join(app.config['UPLOAD_FOLDER'], f'extract_{job_id}_{os.path.splitext(filename)[0]}') + os.makedirs(extract_dir, exist_ok=True) + temp_extract_dirs.append(extract_dir) + with zipfile.ZipFile(filepath, 'r') as zip_ref: + zip_ref.extractall(extract_dir) + # Process PDFs in extract_dir + for root, dirs, files_in_zip in os.walk(extract_dir): + for f in files_in_zip: + if f.lower().endswith('.pdf'): + pdf_path = os.path.join(root, f) + new_name = extract_names_from_pdf(pdf_path) + if new_name: + new_path = os.path.join(root, new_name) + counter = 1 + while os.path.exists(new_path): + base, ext = os.path.splitext(new_name) + new_path = os.path.join(root, f"{base}_{counter}{ext}") + counter += 1 + os.rename(pdf_path, new_path) + processed_files.append(('success', os.path.relpath(new_path, extract_dir), new_path)) + else: + processed_files.append(('skipped', f, None)) + else: + # Single PDF + new_name = extract_names_from_pdf(filepath) + if new_name: + new_filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{job_id}_{new_name}") + counter = 1 + while os.path.exists(new_filepath): + base, ext = os.path.splitext(new_name) + new_filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{job_id}_{base}_{counter}{ext}") + counter += 1 + os.rename(filepath, new_filepath) + processed_files.append(('success', os.path.basename(new_filepath), new_filepath)) + else: + processed_files.append(('skipped', filename, None)) + + # Create ZIP of all successful renames + successful_files = [p for p in processed_files if p[0] == 'success'] + if successful_files: + zip_output = os.path.join(app.config['UPLOAD_FOLDER'], f'renamed_{job_id}.zip') + with zipfile.ZipFile(zip_output, 'w') as zip_out: + for _, rel_name, full_path in successful_files: + zip_out.write(full_path, rel_name) + jobs[job_id]['zip_path'] = zip_output + jobs[job_id]['zip_name'] = f'renamed_{job_id}.zip' + + jobs[job_id]['status'] = 'completed' + jobs[job_id]['processed_files'] = processed_files + jobs[job_id]['skipped'] = [p[1] for p in processed_files if p[0] == 'skipped'] + @app.route('/login') def login(): return render_template_string(''' @@ -151,100 +220,36 @@ def logout(): def upload_files(): if request.method == 'POST': files = request.files.getlist('files') - processed_files = [] - temp_extract_dirs = [] + if not files or all(not f.filename for f in files): + return redirect(url_for('upload_files')) + + job_id = str(uuid.uuid4()) + jobs[job_id] = { + 'status': 'queued', + 'files': [], + 'zip_path': None, + 'zip_name': None, + 'processed_files': [], + 'skipped': [] + } + + file_list = [] for file in files: if file and allowed_file(file.filename): filename = secure_filename(file.filename) - filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename) + filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{job_id}_{filename}") file.save(filepath) - if filename.lower().endswith('.zip'): - # Extract ZIP - extract_dir = os.path.join(app.config['UPLOAD_FOLDER'], 'extract_' + os.path.splitext(filename)[0]) - os.makedirs(extract_dir, exist_ok=True) - temp_extract_dirs.append(extract_dir) - with zipfile.ZipFile(filepath, 'r') as zip_ref: - zip_ref.extractall(extract_dir) - # Process PDFs in extract_dir - for root, dirs, files_in_zip in os.walk(extract_dir): - for f in files_in_zip: - if f.lower().endswith('.pdf'): - pdf_path = os.path.join(root, f) - new_name = extract_names_from_pdf(pdf_path) - if new_name: - new_path = os.path.join(root, new_name) - counter = 1 - while os.path.exists(new_path): - base, ext = os.path.splitext(new_name) - new_path = os.path.join(root, f"{base}_{counter}{ext}") - counter += 1 - os.rename(pdf_path, new_path) - processed_files.append(('success', os.path.relpath(new_path, extract_dir), new_path)) - else: - processed_files.append(('skipped', f, None)) - else: - # Single PDF - new_name = extract_names_from_pdf(filepath) - if new_name: - new_filepath = os.path.join(app.config['UPLOAD_FOLDER'], new_name) - counter = 1 - while os.path.exists(new_filepath): - base, ext = os.path.splitext(new_name) - new_filepath = os.path.join(app.config['UPLOAD_FOLDER'], f"{base}_{counter}{ext}") - counter += 1 - os.rename(filepath, new_filepath) - processed_files.append(('success', os.path.basename(new_filepath), new_filepath)) - else: - processed_files.append(('skipped', filename, None)) + file_list.append({'name': filename, 'path': filepath}) - # Create ZIP of all successful renames - successful_files = [p for p in processed_files if p[0] == 'success'] - if successful_files: - zip_output = os.path.join(app.config['UPLOAD_FOLDER'], 'renamed_files.zip') - with zipfile.ZipFile(zip_output, 'w') as zip_out: - for _, rel_name, full_path in successful_files: - zip_out.write(full_path, rel_name) - zip_name = 'renamed_files.zip' - else: - zip_name = None + jobs[job_id]['files'] = file_list - skipped = [p[1] for p in processed_files if p[0] == 'skipped'] + # Start processing in background + thread = threading.Thread(target=process_job, args=(job_id, file_list)) + thread.daemon = True + thread.start() - return render_template_string(''' - - - - Results - - - - Logout - Logo -

Processing Results

- {% if zip_name %} -

Download Renamed PDFs (ZIP)

- {% endif %} -

Skipped Files:

- - Upload more files - - - ''', zip_name=zip_name, skipped=skipped) + return redirect(url_for('jobs')) + return render_template_string(''' @@ -260,10 +265,15 @@ def upload_files(): input[type="submit"]:hover { background-color: #218838; } .logout { position: absolute; top: 20px; right: 20px; background-color: #dc3545; color: white; text-decoration: none; padding: 10px 20px; border-radius: 5px; } .logout:hover { background-color: #c82333; } + .nav { margin-bottom: 20px; } + .nav a { margin: 0 10px; color: #007bff; text-decoration: none; } Logout +
+ View Jobs +
Logo

Upload PDF Files or ZIP to Rename

@@ -275,10 +285,66 @@ def upload_files(): ''') -@app.route('/download/') +@app.route('/jobs') @login_required -def download_file(filename): - return send_from_directory(app.config['UPLOAD_FOLDER'], filename, as_attachment=True) +def jobs(): + return render_template_string(''' + + + + Jobs + + + + Logout +
+ Upload Files +
+ Logo +

Processing Jobs

+ {% for job_id, job in jobs.items() %} +
+

Job {{ job_id[:8] }}

+

Status: {{ job.status.title() }}

+

Files: {{ job.files|length }}

+ {% if job.status == 'completed' %} + {% if job.zip_name %} +

Download ZIP

+ {% endif %} + {% if job.skipped %} +

Skipped Files:

+
    + {% for file in job.skipped %} +
  • {{ file }}
    • + {% endfor %} +
+ {% endif %} + {% endif %} +
+ {% endfor %} + {% if not jobs %} +

No jobs yet. Upload some files to get started.

+ {% endif %} + + + ''', jobs=jobs) if __name__ == '__main__': app.run(debug=True, port=3000) \ No newline at end of file