#!/usr/bin/env python3
"""
Fix processor_results statistics (frames_processed, output_size_bytes)
for all jobs that have missing data due to Worker crash.
"""

import os
import sys
import re
import psycopg2

def fix_processor_stats():
    conn = psycopg2.connect(os.environ.get('DATABASE_URL', 'postgres://accusys@localhost:5432/momentry'))
    cur = conn.cursor()
    
    # Find jobs with missing frames_processed
    cur.execute("""
        SELECT DISTINCT mj.uuid, mj.id
        FROM public.monitor_jobs mj
        JOIN public.processor_results pr ON pr.job_id = mj.id
        WHERE pr.frames_processed = 0
        AND pr.status = 'completed'
        ORDER BY mj.created_at DESC
    """)
    
    jobs = cur.fetchall()
    print(f"Found {len(jobs)} jobs with missing statistics")
    
    for uuid, job_id in jobs:
        print(f"\nProcessing UUID: {uuid}")
        
        # Get total_frames from YOLO output
        yolo_file = f'/Users/accusys/momentry/output/{uuid}.yolo.json'
        total_frames = 0
        
        if os.path.exists(yolo_file):
            with open(yolo_file, 'r') as f:
                content = f.read(5000)
                match = re.search(r'"total_frames": (\d+)', content)
                if match:
                    total_frames = int(match.group(1))
                    print(f"  total_frames: {total_frames}")
        
        if total_frames > 0:
            # Update frames_processed
            cur.execute("""
                UPDATE public.processor_results 
                SET frames_processed = %s
                WHERE job_id = %s
            """, (total_frames, job_id))
            
            # Update output_size_bytes for each processor
            processors = ['asr', 'yolo', 'face', 'ocr', 'pose', 'cut', 'appearance', 'asrx']
            for proc in processors:
                file_path = f'/Users/accusys/momentry/output/{uuid}.{proc}.json'
                if os.path.exists(file_path):
                    size = os.path.getsize(file_path)
                    cur.execute("""
                        UPDATE public.processor_results 
                        SET output_size_bytes = %s
                        WHERE job_id = %s AND processor_type = %s
                    """, (size, job_id, proc))
                    print(f"  {proc}: {size} bytes")
            
            conn.commit()
            print(f"  ✓ Updated")
        else:
            print(f"  ⚠ Skipped (no total_frames)")
    
    conn.close()
    print(f"\nCompleted: {len(jobs)} jobs processed")

if __name__ == '__main__':
    fix_processor_stats()