syncing scripts

video_transcription/ai_transcriber_v2/tracker.py

@@ -0,0 +1,84 @@
+import logging
+import os
+from datetime import datetime
+from sqlalchemy import create_engine, Column, Integer, String, DateTime, Enum, Text
+from sqlalchemy.orm import declarative_base, sessionmaker
+import enum
+
+# Setup Logging
+log_dir = "logs"
+os.makedirs(log_dir, exist_ok=True)
+log_file = os.path.join(log_dir, f"transcriber_{datetime.now().strftime('%Y%m%d')}.log")
+
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler(log_file),
+        logging.StreamHandler()
+    ]
+)
+logger = logging.getLogger(__name__)
+
+# Database Setup
+Base = declarative_base()
+DB_FILE = "job_history.db"
+
+class JobStatus(enum.Enum):
+    PENDING = "pending"
+    PROCESSING = "processing"
+    COMPLETED = "completed"
+    FAILED = "failed"
+
+class Job(Base):
+    __tablename__ = 'jobs'
+
+    id = Column(Integer, primary_key=True)
+    file_path = Column(String, unique=True, nullable=False)
+    status = Column(Enum(JobStatus), default=JobStatus.PENDING)
+    error_message = Column(Text, nullable=True)
+    last_updated = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+    
+    # Track progress of individual steps
+    step_extract = Column(String, default="pending") # pending, done, failed
+    step_transcribe = Column(String, default="pending")
+    step_translate = Column(String, default="pending")
+    step_embed = Column(String, default="pending")
+
+engine = create_engine(f'sqlite:///{DB_FILE}')
+Base.metadata.create_all(engine)
+Session = sessionmaker(bind=engine)
+
+def get_job(file_path):
+    session = Session()
+    job = session.query(Job).filter_by(file_path=file_path).first()
+    if not job:
+        job = Job(file_path=file_path)
+        session.add(job)
+        session.commit()
+    session.close()
+    return job
+
+def update_job_status(file_path, status, error=None):
+    session = Session()
+    job = session.query(Job).filter_by(file_path=file_path).first()
+    if job:
+        job.status = status
+        if error:
+            job.error_message = str(error)
+        session.commit()
+    session.close()
+
+def update_step(file_path, step_name, status):
+    session = Session()
+    job = session.query(Job).filter_by(file_path=file_path).first()
+    if job:
+        setattr(job, step_name, status)
+        session.commit()
+    session.close()
+
+def get_failed_jobs():
+    session = Session()
+    jobs = session.query(Job).filter_by(status=JobStatus.FAILED).all()
+    session.close()
+    return [j.file_path for j in jobs]