job persitance andupdates

pdf_renamer.py

@@ -3,6 +3,7 @@ import tempfile
 import zipfile
 import threading
 import uuid
+import json
 from datetime import datetime
 from functools import wraps
 from flask import Flask, request, render_template_string, redirect, url_for, session, send_from_directory, flash, get_flashed_messages, jsonify
@@ -54,6 +55,56 @@ except Exception as e:
     print(f"ERROR: Failed to register Microsoft OAuth provider: {e}")
     microsoft = None
 
+# Job persistence
+JOBS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'jobs.json')
+job_queue = {}
+job_lock = threading.Lock()
+
+def save_jobs():
+    """Save jobs to persistent storage"""
+    try:
+        with job_lock:
+            # Convert datetime objects to strings for JSON serialization
+            jobs_to_save = {}
+            for job_id, job in job_queue.items():
+                jobs_to_save[job_id] = job.copy()
+                # Convert any datetime objects if needed
+                if 'created_at' in jobs_to_save[job_id]:
+                    jobs_to_save[job_id]['created_at'] = str(jobs_to_save[job_id]['created_at'])
+            
+            with open(JOBS_FILE, 'w') as f:
+                json.dump(jobs_to_save, f, indent=2)
+    except Exception as e:
+        print(f"ERROR: Failed to save jobs: {e}")
+
+def load_jobs():
+    """Load jobs from persistent storage"""
+    global job_queue
+    try:
+        if os.path.exists(JOBS_FILE):
+            with open(JOBS_FILE, 'r') as f:
+                loaded_jobs = json.load(f)
+                job_queue = loaded_jobs
+                print(f"DEBUG: Loaded {len(job_queue)} jobs from persistent storage")
+        else:
+            print("DEBUG: No existing jobs file found, starting fresh")
+    except Exception as e:
+        print(f"ERROR: Failed to load jobs: {e}")
+        job_queue = {}
+
+# Load jobs on startup
+load_jobs()
+
+def update_job_status(job_id, status, **kwargs):
+    """Update job status and persist changes"""
+    with job_lock:
+        if job_id in job_queue:
+            job_queue[job_id]['status'] = status
+            job_queue[job_id].update(kwargs)
+            job_queue[job_id]['updated_at'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+            save_jobs()
+            print(f"DEBUG: Job {job_id} status updated to {status}")
+
 def analyze_failed_extractions(log_path):
     """
     Analyze failed extraction log to identify new patterns.
@@ -459,6 +510,7 @@ def process_job(job_id, files):
         print("=== DEBUG: process_job STARTED ===")
         job_queue[job_id]['status'] = 'processing'
         job_queue[job_id]['progress'] = 'Starting job processing...'
+        save_jobs()  # Persist status change
         processed_files = []
         temp_extract_dirs = []
         
@@ -614,6 +666,7 @@ def process_job(job_id, files):
             except Exception as e:
                 job_queue[job_id]['progress'] = f'Error creating ZIP: {str(e)}'
                 job_queue[job_id]['status'] = 'error'
+                save_jobs()  # Persist error status
                 print(f"DEBUG: ZIP creation failed: {str(e)}")
         else:
             job_queue[job_id]['progress'] = 'No files to archive - all files were skipped'
@@ -622,11 +675,13 @@ def process_job(job_id, files):
         job_queue[job_id]['status'] = 'completed'
         job_queue[job_id]['processed_files'] = processed_files
         job_queue[job_id]['skipped'] = [(p[1], p[2]) for p in processed_files if p[0] == 'skipped']
+        save_jobs()  # Persist completed job
         print(f"DEBUG: Job {job_id} completed successfully. Processed: {len(processed_files)}, Skipped: {len(job_queue[job_id]['skipped'])}")
 
     except Exception as e:
         job_queue[job_id]['status'] = 'error'
         job_queue[job_id]['progress'] = f'Job failed with error: {str(e)}'
+        save_jobs()  # Persist error status
         print(f"Job {job_id} failed: {str(e)}")  # Debug logging
 
 @app.route('/login')
@@ -776,7 +831,8 @@ def upload_files():
             flash('No files selected.', 'error')
             return redirect(url_for('upload_files'))
         
-        job_id = str(uuid.uuid4())
+        # Create job ID using timestamp format: YYYY-MM-DD_HH-MM-SS
+        job_id = datetime.now().strftime('%Y-%m-%d_%H-%M-%S')
         job_queue[job_id] = {
             'status': 'queued',
             'files': [],
@@ -784,7 +840,8 @@ def upload_files():
             'zip_name': None,
             'processed_files': [],
             'skipped': [],
-            'created_at': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+            'created_at': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
+            'job_id': job_id  # Store the job ID for reference
         }
         
         file_list = []
@@ -804,6 +861,9 @@ def upload_files():
         job_queue[job_id]['files'] = file_list
         print(f"Created job {job_id} with {len(file_list)} files")  # Debug logging
         
+        # Save job to persistent storage
+        save_jobs()
+        
         # Start processing in background
         def process_with_context():
             with app.app_context():
@@ -1109,6 +1169,7 @@ def delete_job(job_id):
                     os.remove(zip_path)
             # Remove the job from the queue
             del job_queue[job_id]
+            save_jobs()  # Persist job deletion
             flash('Job deleted successfully.', 'success')
         else:
             flash('Only completed jobs can be deleted.', 'error')