models.py

import datetime
from sqlalchemy import Column, Integer, String, Float, DateTime, Text, JSON, Enum as SAEnum
from database import Base
import enum


class JobStatus(str, enum.Enum):
    PENDING = "pending"
    PROCESSING = "processing"
    COMPLETED = "completed"
    FAILED = "failed"


class Job(Base):
    """Tracks every file processing request for health monitoring."""
    __tablename__ = "jobs"

    id = Column(Integer, primary_key=True, index=True)
    job_id = Column(String(64), unique=True, index=True, nullable=False)
    original_filename = Column(String(512), nullable=False)
    file_type = Column(String(10))  # "pdf" or "image"
    total_pages = Column(Integer, default=1)
    current_page = Column(Integer, default=0)
    status = Column(String(20), default=JobStatus.PENDING.value)

    # --- Results ---
    tables_found = Column(Integer, default=0)
    cells_extracted = Column(Integer, default=0)
    result_payload = Column(JSON, nullable=True)  # full extraction data

    # --- Health metrics ---
    latency_seconds = Column(Float, nullable=True)
    error_message = Column(Text, nullable=True)

    # --- Timestamps ---
    created_at = Column(DateTime, default=datetime.datetime.utcnow)
    started_at = Column(DateTime, nullable=True)
    completed_at = Column(DateTime, nullable=True)

    def to_dict(self):
        return {
            "id": self.id,
            "job_id": self.job_id,
            "original_filename": self.original_filename,
            "file_type": self.file_type,
            "total_pages": self.total_pages,
            "current_page": self.current_page,
            "status": self.status,
            "tables_found": self.tables_found,
            "cells_extracted": self.cells_extracted,
            "latency_seconds": self.latency_seconds,
            "error_message": self.error_message,
            "created_at": self.created_at.isoformat() if self.created_at else None,
            "started_at": self.started_at.isoformat() if self.started_at else None,
            "completed_at": self.completed_at.isoformat() if self.completed_at else None,
        }


class HealthLog(Base):
    """Aggregated health snapshots for the monitoring dashboard."""
    __tablename__ = "health_logs"

    id = Column(Integer, primary_key=True, index=True)
    timestamp = Column(DateTime, default=datetime.datetime.utcnow, index=True)
    total_jobs = Column(Integer, default=0)
    successful_jobs = Column(Integer, default=0)
    failed_jobs = Column(Integer, default=0)
    avg_latency = Column(Float, default=0.0)
    p95_latency = Column(Float, default=0.0)