Add debugging prints and switch to sequential processing

- Add print statements to track job creation, processing start, completion, and failures
- Use absolute path for jobs.json to avoid working directory issues
- Temporarily switch to sequential PDF processing to avoid multiprocessing issues on remote server

app.py

@@ -269,7 +269,7 @@ def logout():
     return redirect(url_for('index'))
 
 # Job storage
-JOBS_FILE = 'jobs.json'
+JOBS_FILE = os.path.join(os.path.dirname(__file__), 'jobs.json')
 RESULTS_DIR = 'results'
 os.makedirs(RESULTS_DIR, exist_ok=True)
 
@@ -385,11 +385,13 @@ def index():
             'progress': 0
         }
         save_jobs(jobs)
+        print(f"Job {job_id} created and saved")
         
         # Start processing in background
         processing_complete = False
         thread = threading.Thread(target=process_pdfs_async, args=(input_dir, output_dir, job_id))
         thread.start()
+        print(f"Thread started for job {job_id}")
         
         # Redirect to job status page
         return redirect(url_for('job_status', job_id=job_id))
@@ -423,6 +425,7 @@ def results():
 @login_required
 def jobs():
     jobs = load_jobs()
+    print(f"Loaded {len(jobs)} jobs")
     # Sort jobs by timestamp, newest first
     sorted_jobs = sorted(jobs.values(), key=lambda x: x['timestamp'], reverse=True)
     return render_template('jobs.html', jobs=sorted_jobs, user_info=get_user_info())
@@ -666,9 +669,11 @@ def process_pdfs(pdfdir, outputfolder, job_id=None):
 
 def process_pdfs_async(pdfdir, outputfolder, job_id):
     global processing_complete
+    print(f"Processing started for job {job_id}")
     try:
         jobs = load_jobs()
         if job_id not in jobs:
+            print(f"Job {job_id} not found in jobs")
             return
         
         status_file = 'status.txt'
@@ -721,9 +726,11 @@ def process_pdfs_async(pdfdir, outputfolder, job_id):
         time.sleep(0.1)
         
         # Parallel processing
-        num_processes = min(cpu_count(), len(pdf_files))
-        with Pool(processes=num_processes) as pool:
-            results = pool.map(process_single_pdf, pdf_files)
+        print(f"Processing {len(pdf_files)} files sequentially")
+        results = []
+        for pdf_file in pdf_files:
+            result = process_single_pdf(pdf_file)
+            results.append(result)
         
         # Process results sequentially
         with open(os.path.join(addresses_dir, 'Addresses.csv'), 'w') as addr_csv:
@@ -876,6 +883,7 @@ def process_pdfs_async(pdfdir, outputfolder, job_id):
             jobs[job_id]['message'] = f'Processing complete! ZIP created: {zip_filename}'
             jobs[job_id]['progress'] = 100
             save_jobs(jobs)
+            print(f"Job {job_id} completed successfully")
             
             msg = f"ZIP created: {zip_filename}\n"
             with open(status_file, 'a') as status_f:
@@ -895,6 +903,7 @@ def process_pdfs_async(pdfdir, outputfolder, job_id):
             save_jobs(jobs)
     
     except Exception as e:
+        print(f"Processing failed for job {job_id}: {e}")
         msg = f"Processing error: {e}"
         with open('status.txt', 'w') as f:
             f.write(msg)