233 lines
6.9 KiB
Python
233 lines
6.9 KiB
Python
"""Repositorio para gestionar jobs."""
|
|
|
|
from typing import Optional, List
|
|
from datetime import datetime
|
|
from dataclasses import dataclass
|
|
import uuid
|
|
from .database import db
|
|
from ..constants import JobStatus
|
|
|
|
|
|
@dataclass
|
|
class Job:
|
|
"""Modelo de Job."""
|
|
job_id: str
|
|
created_at: str
|
|
updated_at: str
|
|
source_path: str
|
|
source_name: str
|
|
source_hash: Optional[str]
|
|
node_name: Optional[str]
|
|
db_name: Optional[str]
|
|
status: str
|
|
attempts: int
|
|
last_error: Optional[str]
|
|
started_at: Optional[str]
|
|
finished_at: Optional[str]
|
|
total_ms: Optional[int]
|
|
extract_ms: Optional[int]
|
|
restore_ms: Optional[int]
|
|
filelist_ms: Optional[int]
|
|
|
|
|
|
class JobRepository:
|
|
"""Repositorio para operaciones con jobs."""
|
|
|
|
@staticmethod
|
|
def create(source_path: str, source_name: str, source_hash: str) -> str:
|
|
"""
|
|
Crea un nuevo job.
|
|
|
|
Args:
|
|
source_path: Ruta completa del archivo fuente
|
|
source_name: Nombre del archivo
|
|
source_hash: Hash del archivo
|
|
|
|
Returns:
|
|
job_id del job creado
|
|
"""
|
|
job_id = str(uuid.uuid4())
|
|
now = datetime.utcnow().isoformat()
|
|
|
|
db.execute("""
|
|
INSERT INTO jobs (
|
|
job_id, created_at, updated_at, source_path, source_name,
|
|
source_hash, status, attempts
|
|
) VALUES (?, ?, ?, ?, ?, ?, ?, ?)
|
|
""", (job_id, now, now, source_path, source_name, source_hash, JobStatus.QUEUED, 0))
|
|
|
|
return job_id
|
|
|
|
@staticmethod
|
|
def get(job_id: str) -> Optional[Job]:
|
|
"""Obtiene un job por ID."""
|
|
row = db.fetchone("SELECT * FROM jobs WHERE job_id = ?", (job_id,))
|
|
if not row:
|
|
return None
|
|
return Job(**dict(row))
|
|
|
|
@staticmethod
|
|
def get_all(
|
|
status: Optional[str] = None,
|
|
limit: Optional[int] = None,
|
|
offset: int = 0
|
|
) -> List[Job]:
|
|
"""
|
|
Obtiene todos los jobs con filtros opcionales.
|
|
|
|
Args:
|
|
status: Filtrar por estado
|
|
limit: Límite de resultados
|
|
offset: Desplazamiento
|
|
|
|
Returns:
|
|
Lista de jobs
|
|
"""
|
|
query = "SELECT * FROM jobs"
|
|
params = []
|
|
|
|
if status:
|
|
query += " WHERE status = ?"
|
|
params.append(status)
|
|
|
|
query += " ORDER BY created_at DESC"
|
|
|
|
if limit:
|
|
query += f" LIMIT {limit} OFFSET {offset}"
|
|
|
|
rows = db.fetchall(query, tuple(params))
|
|
return [Job(**dict(row)) for row in rows]
|
|
|
|
@staticmethod
|
|
def update_status(
|
|
job_id: str,
|
|
status: str,
|
|
error: Optional[str] = None,
|
|
increment_attempts: bool = False
|
|
):
|
|
"""Actualiza el estado de un job."""
|
|
now = datetime.utcnow().isoformat()
|
|
|
|
updates = ["status = ?", "updated_at = ?"]
|
|
params = [status, now]
|
|
|
|
if error is not None:
|
|
updates.append("last_error = ?")
|
|
params.append(error)
|
|
|
|
if increment_attempts:
|
|
updates.append("attempts = attempts + 1")
|
|
|
|
if status == JobStatus.EXTRACTING and not db.fetchone(
|
|
"SELECT started_at FROM jobs WHERE job_id = ?", (job_id,)
|
|
)["started_at"]:
|
|
updates.append("started_at = ?")
|
|
params.append(now)
|
|
|
|
if status in [JobStatus.COMPLETED, JobStatus.FAILED, JobStatus.CANCELLED]:
|
|
updates.append("finished_at = ?")
|
|
params.append(now)
|
|
|
|
params.append(job_id)
|
|
|
|
db.execute(
|
|
f"UPDATE jobs SET {', '.join(updates)} WHERE job_id = ?",
|
|
tuple(params)
|
|
)
|
|
|
|
@staticmethod
|
|
def update_node_and_db(job_id: str, node_name: str, db_name: str):
|
|
"""Actualiza el nodo y base de datos de un job."""
|
|
now = datetime.utcnow().isoformat()
|
|
db.execute(
|
|
"UPDATE jobs SET node_name = ?, db_name = ?, updated_at = ? WHERE job_id = ?",
|
|
(node_name, db_name, now, job_id)
|
|
)
|
|
|
|
@staticmethod
|
|
def update_timing(
|
|
job_id: str,
|
|
total_ms: Optional[int] = None,
|
|
extract_ms: Optional[int] = None,
|
|
restore_ms: Optional[int] = None,
|
|
filelist_ms: Optional[int] = None
|
|
):
|
|
"""Actualiza los tiempos de ejecución."""
|
|
updates = []
|
|
params = []
|
|
|
|
if total_ms is not None:
|
|
updates.append("total_ms = ?")
|
|
params.append(total_ms)
|
|
if extract_ms is not None:
|
|
updates.append("extract_ms = ?")
|
|
params.append(extract_ms)
|
|
if restore_ms is not None:
|
|
updates.append("restore_ms = ?")
|
|
params.append(restore_ms)
|
|
if filelist_ms is not None:
|
|
updates.append("filelist_ms = ?")
|
|
params.append(filelist_ms)
|
|
|
|
if updates:
|
|
params.append(job_id)
|
|
db.execute(
|
|
f"UPDATE jobs SET {', '.join(updates)} WHERE job_id = ?",
|
|
tuple(params)
|
|
)
|
|
|
|
@staticmethod
|
|
def exists_by_hash(source_hash: str) -> bool:
|
|
"""Verifica si existe un job con el hash dado."""
|
|
row = db.fetchone(
|
|
"SELECT COUNT(*) as count FROM jobs WHERE source_hash = ?",
|
|
(source_hash,)
|
|
)
|
|
return row["count"] > 0
|
|
|
|
@staticmethod
|
|
def get_stats() -> dict:
|
|
"""Obtiene estadísticas de jobs."""
|
|
stats = {
|
|
"total": 0,
|
|
"queued": 0,
|
|
"running": 0,
|
|
"completed": 0,
|
|
"failed": 0
|
|
}
|
|
|
|
rows = db.fetchall("SELECT status, COUNT(*) as count FROM jobs GROUP BY status")
|
|
for row in rows:
|
|
status = row["status"]
|
|
count = row["count"]
|
|
stats["total"] += count
|
|
|
|
if status == JobStatus.QUEUED:
|
|
stats["queued"] = count
|
|
elif status in [JobStatus.EXTRACTING, JobStatus.RESTORING, JobStatus.CLEANING]:
|
|
stats["running"] += count
|
|
elif status == JobStatus.COMPLETED:
|
|
stats["completed"] = count
|
|
elif status in [JobStatus.FAILED, JobStatus.FAILED_RESTART, JobStatus.CANCELLED]:
|
|
stats["failed"] += count
|
|
|
|
return stats
|
|
|
|
@staticmethod
|
|
def get_average_times() -> dict:
|
|
"""Obtiene tiempos promedio de ejecución."""
|
|
row = db.fetchone("""
|
|
SELECT
|
|
AVG(total_ms) as avg_total,
|
|
AVG(extract_ms) as avg_extract,
|
|
AVG(restore_ms) as avg_restore
|
|
FROM jobs
|
|
WHERE status = ? AND total_ms IS NOT NULL
|
|
""", (JobStatus.COMPLETED,))
|
|
|
|
return {
|
|
"total_ms": int(row["avg_total"] or 0),
|
|
"extract_ms": int(row["avg_extract"] or 0),
|
|
"restore_ms": int(row["avg_restore"] or 0)
|
|
}
|