feat: Introduce bot-descarga service for PDF downloads and remote bot control. Add Docker configuration, environment variables, and a GUI for agent management. Enhance README with bot details and installation instructions.
This commit is contained in:
erik
@@ -0,0 +1,20 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import Header, HTTPException
|
||||
|
||||
|
||||
def get_api_token() -> str:
|
||||
return os.getenv("BOT_API_TOKEN", "dev-token-change-me")
|
||||
|
||||
|
||||
def require_bearer(authorization: Optional[str] = Header(default=None)) -> str:
|
||||
expected = get_api_token()
|
||||
if not authorization or not authorization.lower().startswith("bearer "):
|
||||
raise HTTPException(status_code=401, detail="Authorization Bearer requerido")
|
||||
token = authorization.split(" ", 1)[1].strip()
|
||||
if token != expected:
|
||||
raise HTTPException(status_code=401, detail="Token inválido")
|
||||
return token
|
||||
@@ -0,0 +1,159 @@
|
||||
"""Persistencia Postgres del servicio bot-descarga (DB compartida IPSExtractor)."""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import uuid
|
||||
from contextlib import contextmanager
|
||||
from datetime import datetime, timezone
|
||||
from typing import Any, Iterator
|
||||
|
||||
from sqlalchemy import (
|
||||
JSON,
|
||||
Boolean,
|
||||
DateTime,
|
||||
ForeignKey,
|
||||
Integer,
|
||||
String,
|
||||
Text,
|
||||
create_engine,
|
||||
text,
|
||||
)
|
||||
from sqlalchemy.orm import DeclarativeBase, Mapped, Session, mapped_column, sessionmaker
|
||||
|
||||
DATABASE_URL = os.getenv(
|
||||
"DATABASE_URL",
|
||||
"postgresql+psycopg://ipsextractor:ipsextractor@database:5432/ipsextractor",
|
||||
)
|
||||
|
||||
engine = create_engine(DATABASE_URL, pool_pre_ping=True)
|
||||
SessionLocal = sessionmaker(bind=engine, autoflush=False, autocommit=False)
|
||||
|
||||
|
||||
class Base(DeclarativeBase):
|
||||
pass
|
||||
|
||||
|
||||
def utcnow() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
|
||||
def new_id() -> str:
|
||||
return str(uuid.uuid4())
|
||||
|
||||
|
||||
def _iso(dt: datetime | None) -> str | None:
|
||||
if dt is None:
|
||||
return None
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=timezone.utc)
|
||||
return dt.astimezone().isoformat(timespec="seconds")
|
||||
|
||||
|
||||
class Job(Base):
|
||||
"""Contenedor Desktop (lectura / FK)."""
|
||||
|
||||
__tablename__ = "jobs"
|
||||
|
||||
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_id)
|
||||
status: Mapped[str] = mapped_column(String(32), default="pending", index=True)
|
||||
title: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
job_metadata: Mapped[dict[str, Any]] = mapped_column("metadata", JSON, default=dict)
|
||||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
|
||||
|
||||
class Task(Base):
|
||||
__tablename__ = "tasks"
|
||||
|
||||
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_id)
|
||||
job_id: Mapped[str | None] = mapped_column(
|
||||
String(36), ForeignKey("jobs.id"), nullable=True, index=True
|
||||
)
|
||||
type: Mapped[str] = mapped_column(String(64), index=True)
|
||||
status: Mapped[str] = mapped_column(String(32), default="pending", index=True)
|
||||
title: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
request: Mapped[dict[str, Any]] = mapped_column(JSON, default=dict)
|
||||
result: Mapped[dict[str, Any]] = mapped_column(JSON, default=dict)
|
||||
error: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
owner_id: Mapped[str | None] = mapped_column(String(36), nullable=True, index=True)
|
||||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
|
||||
|
||||
class DownloadWorkerRow(Base):
|
||||
__tablename__ = "download_workers"
|
||||
|
||||
id: Mapped[str] = mapped_column(String(36), primary_key=True)
|
||||
hostname: Mapped[str] = mapped_column(Text, default="")
|
||||
max_concurrent: Mapped[int] = mapped_column(Integer, default=1)
|
||||
status: Mapped[str] = mapped_column(String(32), index=True)
|
||||
last_heartbeat: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
current_job_id: Mapped[str | None] = mapped_column(String(36), nullable=True)
|
||||
|
||||
|
||||
class DownloadJobRow(Base):
|
||||
__tablename__ = "download_jobs"
|
||||
|
||||
id: Mapped[str] = mapped_column(String(36), primary_key=True, default=new_id)
|
||||
job_id: Mapped[str | None] = mapped_column(
|
||||
String(36), ForeignKey("jobs.id"), nullable=True, index=True
|
||||
)
|
||||
task_id: Mapped[str | None] = mapped_column(
|
||||
String(36), ForeignKey("tasks.id"), nullable=True, index=True
|
||||
)
|
||||
worker_id: Mapped[str] = mapped_column(String(36), index=True)
|
||||
status: Mapped[str] = mapped_column(String(32), default="pending", index=True)
|
||||
title: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
excel_key: Mapped[str] = mapped_column(Text, default="")
|
||||
downloads_prefix: Mapped[str] = mapped_column(Text, default="")
|
||||
original_filename: Mapped[str] = mapped_column(Text, default="")
|
||||
cancel_requested: Mapped[bool] = mapped_column(Boolean, default=False)
|
||||
result: Mapped[dict[str, Any]] = mapped_column(JSON, default=dict)
|
||||
error: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
started_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
finished_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True)
|
||||
|
||||
|
||||
class DownloadJobEventRow(Base):
|
||||
__tablename__ = "download_job_events"
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
||||
download_job_id: Mapped[str] = mapped_column(
|
||||
String(36), ForeignKey("download_jobs.id"), index=True
|
||||
)
|
||||
event_type: Mapped[str] = mapped_column(String(64))
|
||||
message: Mapped[str] = mapped_column(Text)
|
||||
timestamp: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow)
|
||||
radicado: Mapped[str | None] = mapped_column(String(255), nullable=True)
|
||||
nit: Mapped[str | None] = mapped_column(String(64), nullable=True)
|
||||
idx: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
||||
total: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
||||
metadata_json: Mapped[dict[str, Any]] = mapped_column("metadata", JSON, default=dict)
|
||||
|
||||
|
||||
def init_db() -> None:
|
||||
if DATABASE_URL.startswith("postgresql"):
|
||||
with engine.connect().execution_options(isolation_level="AUTOCOMMIT") as connection:
|
||||
connection.execute(text("SELECT pg_advisory_lock(74512004)"))
|
||||
try:
|
||||
Base.metadata.create_all(bind=connection)
|
||||
finally:
|
||||
connection.execute(text("SELECT pg_advisory_unlock(74512004)"))
|
||||
return
|
||||
Base.metadata.create_all(bind=engine)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def session_scope() -> Iterator[Session]:
|
||||
session = SessionLocal()
|
||||
try:
|
||||
yield session
|
||||
session.commit()
|
||||
except Exception:
|
||||
session.rollback()
|
||||
raise
|
||||
finally:
|
||||
session.close()
|
||||
@@ -0,0 +1,215 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import BinaryIO, List, Optional
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class MinioSettings:
|
||||
endpoint: str = "https://s3.builker.xyz"
|
||||
bucket: str = "pys-cuentas-medicas"
|
||||
access_key: str = ""
|
||||
secret_key: str = ""
|
||||
region: str = "us-east-1"
|
||||
anonymous: bool = True
|
||||
|
||||
@classmethod
|
||||
def from_env(cls) -> "MinioSettings":
|
||||
access_key = (os.getenv("MINIO_ACCESS_KEY") or "").strip()
|
||||
secret_key = (os.getenv("MINIO_SECRET_KEY") or "").strip()
|
||||
anon_flag = (os.getenv("MINIO_ANONYMOUS") or "").strip().lower()
|
||||
if anon_flag in ("0", "false", "no"):
|
||||
anonymous = False
|
||||
elif anon_flag in ("1", "true", "yes"):
|
||||
anonymous = True
|
||||
else:
|
||||
anonymous = not (access_key and secret_key)
|
||||
return cls(
|
||||
endpoint=os.getenv("MINIO_ENDPOINT", "https://s3.builker.xyz").rstrip("/"),
|
||||
bucket=os.getenv("MINIO_BUCKET", "pys-cuentas-medicas"),
|
||||
access_key=access_key,
|
||||
secret_key=secret_key,
|
||||
region=os.getenv("MINIO_REGION", "us-east-1"),
|
||||
anonymous=anonymous,
|
||||
)
|
||||
|
||||
|
||||
def excel_key(job_id: str, filename: str = "input.xlsx") -> str:
|
||||
return f"uploads/{job_id}/{filename}"
|
||||
|
||||
|
||||
def downloads_prefix(job_id: str) -> str:
|
||||
return f"downloads/{job_id}/"
|
||||
|
||||
|
||||
def pdf_key(job_id: str, nit: str, radicado: str) -> str:
|
||||
return f"downloads/{job_id}/{nit}/{radicado}.pdf"
|
||||
|
||||
|
||||
def meta_key(job_id: str) -> str:
|
||||
return f"uploads/{job_id}/meta.json"
|
||||
|
||||
|
||||
def manifest_key(job_id: str) -> str:
|
||||
return f"downloads/{job_id}/_manifest.json"
|
||||
|
||||
|
||||
def _s3_client(settings: MinioSettings):
|
||||
import boto3
|
||||
from botocore import UNSIGNED
|
||||
from botocore.client import Config
|
||||
|
||||
s3_cfg = {
|
||||
"addressing_style": "path",
|
||||
"request_checksum_calculation": "when_required",
|
||||
"response_checksum_validation": "when_required",
|
||||
}
|
||||
if settings.anonymous:
|
||||
return boto3.client(
|
||||
"s3",
|
||||
endpoint_url=settings.endpoint,
|
||||
region_name=settings.region,
|
||||
config=Config(signature_version=UNSIGNED, s3=s3_cfg),
|
||||
)
|
||||
return boto3.client(
|
||||
"s3",
|
||||
endpoint_url=settings.endpoint,
|
||||
aws_access_key_id=settings.access_key,
|
||||
aws_secret_access_key=settings.secret_key,
|
||||
region_name=settings.region,
|
||||
config=Config(signature_version="s3v4", s3=s3_cfg),
|
||||
)
|
||||
|
||||
|
||||
class MinioStorage:
|
||||
"""Cliente S3-compatible para MinIO (uploads/downloads por job_id)."""
|
||||
|
||||
def __init__(self, settings: Optional[MinioSettings] = None):
|
||||
self.settings = settings or MinioSettings.from_env()
|
||||
self._client = None
|
||||
|
||||
@property
|
||||
def client(self):
|
||||
if self._client is None:
|
||||
self._client = _s3_client(self.settings)
|
||||
return self._client
|
||||
|
||||
@property
|
||||
def bucket(self) -> str:
|
||||
return self.settings.bucket
|
||||
|
||||
def put_bytes(self, key: str, data: bytes, content_type: str = "application/octet-stream") -> str:
|
||||
self.client.put_object(
|
||||
Bucket=self.bucket,
|
||||
Key=key,
|
||||
Body=data,
|
||||
ContentType=content_type,
|
||||
)
|
||||
return key
|
||||
|
||||
def put_file(self, key: str, path: str | Path, content_type: str = "application/octet-stream") -> str:
|
||||
path = Path(path)
|
||||
return self.put_bytes(key, path.read_bytes(), content_type=content_type)
|
||||
|
||||
def put_stream(self, key: str, stream: BinaryIO, content_type: str = "application/octet-stream") -> str:
|
||||
data = stream.read()
|
||||
return self.put_bytes(key, data, content_type=content_type)
|
||||
|
||||
def get_bytes(self, key: str) -> bytes:
|
||||
obj = self.client.get_object(Bucket=self.bucket, Key=key)
|
||||
return obj["Body"].read()
|
||||
|
||||
def download_file(self, key: str, dest: str | Path) -> Path:
|
||||
dest = Path(dest)
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
self.client.download_file(self.bucket, key, str(dest))
|
||||
return dest
|
||||
|
||||
def exists(self, key: str) -> bool:
|
||||
try:
|
||||
self.client.head_object(Bucket=self.bucket, Key=key)
|
||||
return True
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
def list_keys(self, prefix: str) -> List[str]:
|
||||
keys: List[str] = []
|
||||
token = None
|
||||
while True:
|
||||
kwargs = {"Bucket": self.bucket, "Prefix": prefix}
|
||||
if token:
|
||||
kwargs["ContinuationToken"] = token
|
||||
resp = self.client.list_objects_v2(**kwargs)
|
||||
for item in resp.get("Contents") or []:
|
||||
keys.append(item["Key"])
|
||||
if not resp.get("IsTruncated"):
|
||||
break
|
||||
token = resp.get("NextContinuationToken")
|
||||
return keys
|
||||
|
||||
def presigned_get(self, key: str, expires_in: int = 3600) -> str:
|
||||
if self.settings.anonymous:
|
||||
return f"{self.settings.endpoint}/{self.bucket}/{key}"
|
||||
return self.client.generate_presigned_url(
|
||||
"get_object",
|
||||
Params={"Bucket": self.bucket, "Key": key},
|
||||
ExpiresIn=expires_in,
|
||||
)
|
||||
|
||||
def upload_excel(
|
||||
self,
|
||||
job_id: str,
|
||||
data: bytes,
|
||||
original_filename: str,
|
||||
content_type: str = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
|
||||
) -> str:
|
||||
ext = Path(original_filename).suffix.lower() or ".xlsx"
|
||||
canonical = f"input{ext}" if ext in (".xlsx", ".xls", ".csv") else "input.xlsx"
|
||||
key = excel_key(job_id, canonical)
|
||||
self.put_bytes(key, data, content_type=content_type)
|
||||
meta = {
|
||||
"original_filename": original_filename,
|
||||
"size": len(data),
|
||||
"canonical": canonical,
|
||||
}
|
||||
self.put_bytes(meta_key(job_id), json.dumps(meta).encode("utf-8"), "application/json")
|
||||
return key
|
||||
|
||||
def upload_pdf(self, job_id: str, nit: str, radicado: str, local_path: str | Path) -> str:
|
||||
key = pdf_key(job_id, nit, radicado)
|
||||
self.put_file(key, local_path, content_type="application/pdf")
|
||||
return key
|
||||
|
||||
def write_manifest(self, job_id: str, keys: List[str]) -> str:
|
||||
key = manifest_key(job_id)
|
||||
payload = {"job_id": job_id, "files": keys, "count": len(keys)}
|
||||
self.put_bytes(key, json.dumps(payload, ensure_ascii=False).encode("utf-8"), "application/json")
|
||||
return key
|
||||
|
||||
def list_download_files(self, job_id: str, prefix: str | None = None) -> dict:
|
||||
"""Lista PDFs de una corrida (manifest o list_keys)."""
|
||||
prefix = prefix or downloads_prefix(job_id)
|
||||
files: List[dict] = []
|
||||
try:
|
||||
raw = self.get_bytes(manifest_key(job_id))
|
||||
payload = json.loads(raw.decode("utf-8"))
|
||||
for key in payload.get("files") or []:
|
||||
files.append(self._file_entry(str(key)))
|
||||
except Exception:
|
||||
for key in self.list_keys(prefix):
|
||||
if key.endswith("/_manifest.json") or key.endswith("_manifest.json"):
|
||||
continue
|
||||
files.append(self._file_entry(key))
|
||||
return {"job_id": job_id, "prefix": prefix, "files": files, "count": len(files)}
|
||||
|
||||
@staticmethod
|
||||
def _file_entry(key: str) -> dict:
|
||||
# downloads/{job_id}/{nit}/{radicado}.pdf
|
||||
parts = key.strip("/").split("/")
|
||||
nit = parts[-2] if len(parts) >= 3 else None
|
||||
name = parts[-1] if parts else key
|
||||
radicado = name[:-4] if name.lower().endswith(".pdf") else name
|
||||
return {"key": key, "nit": nit, "radicado": radicado}
|
||||
@@ -0,0 +1,466 @@
|
||||
"""Repositorio sobre PostgreSQL (tablas download_* + sync de tasks)."""
|
||||
from __future__ import annotations
|
||||
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from sqlalchemy import select
|
||||
|
||||
from domain.models import (
|
||||
Job,
|
||||
JobEventRecord,
|
||||
JobStatus,
|
||||
Worker,
|
||||
WorkerStatus,
|
||||
utc_now,
|
||||
)
|
||||
from infrastructure.database import (
|
||||
DownloadJobEventRow,
|
||||
DownloadJobRow,
|
||||
DownloadWorkerRow,
|
||||
Task,
|
||||
_iso,
|
||||
init_db,
|
||||
session_scope,
|
||||
utcnow,
|
||||
)
|
||||
from infrastructure.storage_minio import downloads_prefix
|
||||
|
||||
HEARTBEAT_OFFLINE_SECONDS = 45
|
||||
|
||||
|
||||
def _parse_iso(value: str | None) -> datetime | None:
|
||||
if not value:
|
||||
return None
|
||||
dt = datetime.fromisoformat(value)
|
||||
if dt.tzinfo is None:
|
||||
dt = dt.replace(tzinfo=timezone.utc)
|
||||
return dt
|
||||
|
||||
|
||||
class JobStore:
|
||||
"""API de persistencia compatible con el store SQLite anterior."""
|
||||
|
||||
def __init__(self, db_path: str | None = None):
|
||||
# db_path ignorado (compat); usa DATABASE_URL.
|
||||
init_db()
|
||||
|
||||
def _row_worker(self, row: DownloadWorkerRow) -> Worker:
|
||||
worker = Worker(
|
||||
id=row.id,
|
||||
hostname=row.hostname or "",
|
||||
max_concurrent=int(row.max_concurrent or 1),
|
||||
status=row.status,
|
||||
last_heartbeat=_iso(row.last_heartbeat) or utc_now(),
|
||||
current_job_id=row.current_job_id,
|
||||
)
|
||||
return self._refresh_worker_status(worker)
|
||||
|
||||
def _row_job(self, row: DownloadJobRow) -> Job:
|
||||
return Job(
|
||||
id=row.id,
|
||||
worker_id=row.worker_id,
|
||||
status=row.status,
|
||||
title=row.title or "",
|
||||
excel_key=row.excel_key or "",
|
||||
downloads_prefix=row.downloads_prefix or "",
|
||||
original_filename=row.original_filename or "",
|
||||
cancel_requested=bool(row.cancel_requested),
|
||||
result=dict(row.result or {}),
|
||||
error=row.error,
|
||||
created_at=_iso(row.created_at) or utc_now(),
|
||||
started_at=_iso(row.started_at),
|
||||
finished_at=_iso(row.finished_at),
|
||||
job_id=row.job_id,
|
||||
task_id=row.task_id,
|
||||
)
|
||||
|
||||
def _refresh_worker_status(self, worker: Worker) -> Worker:
|
||||
try:
|
||||
hb = datetime.fromisoformat(worker.last_heartbeat)
|
||||
if hb.tzinfo is None:
|
||||
hb = hb.replace(tzinfo=timezone.utc)
|
||||
age = datetime.now(timezone.utc) - hb.astimezone(timezone.utc)
|
||||
if age > timedelta(seconds=HEARTBEAT_OFFLINE_SECONDS):
|
||||
worker.status = WorkerStatus.OFFLINE.value
|
||||
elif worker.current_job_id:
|
||||
worker.status = WorkerStatus.BUSY.value
|
||||
else:
|
||||
worker.status = WorkerStatus.ONLINE.value
|
||||
except Exception:
|
||||
worker.status = WorkerStatus.OFFLINE.value
|
||||
return worker
|
||||
|
||||
def register_worker(
|
||||
self,
|
||||
worker_id: str,
|
||||
hostname: str = "",
|
||||
max_concurrent: int = 1,
|
||||
) -> Worker:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadWorkerRow, worker_id)
|
||||
now = utcnow()
|
||||
if row:
|
||||
row.hostname = hostname
|
||||
row.max_concurrent = max_concurrent
|
||||
row.status = WorkerStatus.ONLINE.value
|
||||
row.last_heartbeat = now
|
||||
row.current_job_id = None
|
||||
else:
|
||||
row = DownloadWorkerRow(
|
||||
id=worker_id,
|
||||
hostname=hostname,
|
||||
max_concurrent=max_concurrent,
|
||||
status=WorkerStatus.ONLINE.value,
|
||||
last_heartbeat=now,
|
||||
current_job_id=None,
|
||||
)
|
||||
session.add(row)
|
||||
session.flush()
|
||||
return self._row_worker(row)
|
||||
|
||||
def heartbeat(self, worker_id: str) -> Optional[Worker]:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadWorkerRow, worker_id)
|
||||
if not row:
|
||||
return None
|
||||
row.last_heartbeat = utcnow()
|
||||
row.status = (
|
||||
WorkerStatus.BUSY.value if row.current_job_id else WorkerStatus.ONLINE.value
|
||||
)
|
||||
session.flush()
|
||||
return self._row_worker(row)
|
||||
|
||||
def get_worker(self, worker_id: str) -> Optional[Worker]:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadWorkerRow, worker_id)
|
||||
if not row:
|
||||
return None
|
||||
return self._row_worker(row)
|
||||
|
||||
def list_workers(self) -> List[Worker]:
|
||||
with session_scope() as session:
|
||||
rows = session.scalars(
|
||||
select(DownloadWorkerRow).order_by(DownloadWorkerRow.id)
|
||||
).all()
|
||||
return [self._row_worker(r) for r in rows]
|
||||
|
||||
def is_worker_online(self, worker_id: str) -> bool:
|
||||
worker = self.get_worker(worker_id)
|
||||
if not worker:
|
||||
return False
|
||||
return worker.status in (WorkerStatus.ONLINE.value, WorkerStatus.BUSY.value)
|
||||
|
||||
def update_excel_key(self, job_id: str, excel_key: str) -> Optional[Job]:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadJobRow, job_id)
|
||||
if not row:
|
||||
return None
|
||||
row.excel_key = excel_key
|
||||
session.flush()
|
||||
return self._row_job(row)
|
||||
|
||||
def create_job(
|
||||
self,
|
||||
worker_id: str,
|
||||
excel_key: str,
|
||||
original_filename: str = "",
|
||||
title: str = "",
|
||||
*,
|
||||
job_id: Optional[str] = None,
|
||||
task_id: Optional[str] = None,
|
||||
) -> Job:
|
||||
import uuid as uuid_mod
|
||||
|
||||
download_id = str(uuid_mod.uuid4())
|
||||
prefix = downloads_prefix(download_id)
|
||||
with session_scope() as session:
|
||||
row = DownloadJobRow(
|
||||
id=download_id,
|
||||
job_id=job_id,
|
||||
task_id=task_id,
|
||||
worker_id=worker_id,
|
||||
status=JobStatus.PENDING.value,
|
||||
title=title or f"Descarga {original_filename}",
|
||||
excel_key=excel_key,
|
||||
downloads_prefix=prefix,
|
||||
original_filename=original_filename,
|
||||
cancel_requested=False,
|
||||
result={},
|
||||
created_at=utcnow(),
|
||||
)
|
||||
session.add(row)
|
||||
session.flush()
|
||||
return self._row_job(row)
|
||||
|
||||
def get_job(self, job_id: str) -> Optional[Job]:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadJobRow, job_id)
|
||||
if not row:
|
||||
return None
|
||||
return self._row_job(row)
|
||||
|
||||
def list_jobs(
|
||||
self,
|
||||
limit: int = 100,
|
||||
*,
|
||||
job_id: Optional[str] = None,
|
||||
) -> List[Job]:
|
||||
with session_scope() as session:
|
||||
stmt = select(DownloadJobRow).order_by(DownloadJobRow.created_at.desc()).limit(limit)
|
||||
if job_id:
|
||||
stmt = (
|
||||
select(DownloadJobRow)
|
||||
.where(DownloadJobRow.job_id == job_id)
|
||||
.order_by(DownloadJobRow.created_at.desc())
|
||||
.limit(limit)
|
||||
)
|
||||
rows = session.scalars(stmt).all()
|
||||
return [self._row_job(r) for r in rows]
|
||||
|
||||
def claim_pending(self, worker_id: str) -> Optional[Job]:
|
||||
with session_scope() as session:
|
||||
worker = session.get(DownloadWorkerRow, worker_id)
|
||||
if not worker or worker.current_job_id:
|
||||
return None
|
||||
|
||||
row = session.scalars(
|
||||
select(DownloadJobRow)
|
||||
.where(
|
||||
DownloadJobRow.worker_id == worker_id,
|
||||
DownloadJobRow.status == JobStatus.PENDING.value,
|
||||
)
|
||||
.order_by(DownloadJobRow.created_at.asc())
|
||||
.limit(1)
|
||||
).first()
|
||||
if not row:
|
||||
return None
|
||||
|
||||
now = utcnow()
|
||||
row.status = JobStatus.RUNNING.value
|
||||
row.started_at = now
|
||||
worker.current_job_id = row.id
|
||||
worker.status = WorkerStatus.BUSY.value
|
||||
worker.last_heartbeat = now
|
||||
|
||||
if row.task_id:
|
||||
task = session.get(Task, row.task_id)
|
||||
if task:
|
||||
task.status = JobStatus.RUNNING.value
|
||||
task.started_at = now
|
||||
task.updated_at = now
|
||||
|
||||
session.flush()
|
||||
return self._row_job(row)
|
||||
|
||||
def request_cancel(self, job_id: str) -> Optional[Job]:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadJobRow, job_id)
|
||||
if not row:
|
||||
return None
|
||||
if row.status in (
|
||||
JobStatus.COMPLETED.value,
|
||||
JobStatus.FAILED.value,
|
||||
JobStatus.CANCELLED.value,
|
||||
):
|
||||
return self._row_job(row)
|
||||
|
||||
now = utcnow()
|
||||
row.cancel_requested = True
|
||||
if row.status == JobStatus.PENDING.value:
|
||||
row.status = JobStatus.CANCELLED.value
|
||||
row.finished_at = now
|
||||
self._sync_task(session, row, status=JobStatus.CANCELLED.value)
|
||||
session.flush()
|
||||
return self._row_job(row)
|
||||
|
||||
def is_cancel_requested(self, job_id: str) -> bool:
|
||||
job = self.get_job(job_id)
|
||||
return bool(job and job.cancel_requested)
|
||||
|
||||
def _sync_task(
|
||||
self,
|
||||
session,
|
||||
row: DownloadJobRow,
|
||||
*,
|
||||
status: Optional[str] = None,
|
||||
result: Optional[Dict[str, Any]] = None,
|
||||
error: Optional[str] = None,
|
||||
) -> None:
|
||||
if not row.task_id:
|
||||
return
|
||||
task = session.get(Task, row.task_id)
|
||||
if not task:
|
||||
return
|
||||
now = utcnow()
|
||||
if status:
|
||||
task.status = status
|
||||
if result is not None:
|
||||
task.result = {
|
||||
**dict(task.result or {}),
|
||||
"download_job_id": row.id,
|
||||
**result,
|
||||
}
|
||||
if error is not None:
|
||||
task.error = error
|
||||
task.updated_at = now
|
||||
if status in (
|
||||
JobStatus.COMPLETED.value,
|
||||
JobStatus.FAILED.value,
|
||||
JobStatus.CANCELLED.value,
|
||||
):
|
||||
task.finished_at = now
|
||||
|
||||
def patch_job(
|
||||
self,
|
||||
job_id: str,
|
||||
*,
|
||||
status: Optional[str] = None,
|
||||
result: Optional[Dict[str, Any]] = None,
|
||||
error: Optional[str] = None,
|
||||
) -> Optional[Job]:
|
||||
with session_scope() as session:
|
||||
row = session.get(DownloadJobRow, job_id)
|
||||
if not row:
|
||||
return None
|
||||
|
||||
new_status = status or row.status
|
||||
if result is not None:
|
||||
row.result = result
|
||||
if error is not None:
|
||||
row.error = error
|
||||
row.status = new_status
|
||||
|
||||
finished = False
|
||||
if new_status in (
|
||||
JobStatus.COMPLETED.value,
|
||||
JobStatus.FAILED.value,
|
||||
JobStatus.CANCELLED.value,
|
||||
):
|
||||
row.finished_at = row.finished_at or utcnow()
|
||||
finished = True
|
||||
|
||||
self._sync_task(
|
||||
session,
|
||||
row,
|
||||
status=new_status if status else None,
|
||||
result=result,
|
||||
error=error,
|
||||
)
|
||||
|
||||
if finished:
|
||||
worker = session.get(DownloadWorkerRow, row.worker_id)
|
||||
if worker and worker.current_job_id == job_id:
|
||||
worker.current_job_id = None
|
||||
worker.status = WorkerStatus.ONLINE.value
|
||||
|
||||
session.flush()
|
||||
return self._row_job(row)
|
||||
|
||||
def add_event(
|
||||
self,
|
||||
job_id: str,
|
||||
event_type: str,
|
||||
message: str,
|
||||
*,
|
||||
radicado: Optional[str] = None,
|
||||
nit: Optional[str] = None,
|
||||
index: Optional[int] = None,
|
||||
total: Optional[int] = None,
|
||||
metadata: Optional[Dict[str, Any]] = None,
|
||||
timestamp: Optional[str] = None,
|
||||
) -> JobEventRecord:
|
||||
with session_scope() as session:
|
||||
ts = _parse_iso(timestamp) or utcnow()
|
||||
ev = DownloadJobEventRow(
|
||||
download_job_id=job_id,
|
||||
event_type=event_type,
|
||||
message=message,
|
||||
timestamp=ts,
|
||||
radicado=radicado,
|
||||
nit=nit,
|
||||
idx=index,
|
||||
total=total,
|
||||
metadata_json=metadata or {},
|
||||
)
|
||||
session.add(ev)
|
||||
session.flush()
|
||||
return JobEventRecord(
|
||||
id=int(ev.id),
|
||||
job_id=job_id,
|
||||
event_type=event_type,
|
||||
message=message,
|
||||
timestamp=_iso(ts) or utc_now(),
|
||||
radicado=radicado,
|
||||
nit=nit,
|
||||
index=index,
|
||||
total=total,
|
||||
metadata=metadata or {},
|
||||
)
|
||||
|
||||
def list_events(self, job_id: str, since_id: int = 0) -> List[JobEventRecord]:
|
||||
with session_scope() as session:
|
||||
rows = session.scalars(
|
||||
select(DownloadJobEventRow)
|
||||
.where(
|
||||
DownloadJobEventRow.download_job_id == job_id,
|
||||
DownloadJobEventRow.id > since_id,
|
||||
)
|
||||
.order_by(DownloadJobEventRow.id.asc())
|
||||
).all()
|
||||
return [
|
||||
JobEventRecord(
|
||||
id=int(r.id),
|
||||
job_id=r.download_job_id,
|
||||
event_type=r.event_type,
|
||||
message=r.message,
|
||||
timestamp=_iso(r.timestamp) or utc_now(),
|
||||
radicado=r.radicado,
|
||||
nit=r.nit,
|
||||
index=r.idx,
|
||||
total=r.total,
|
||||
metadata=dict(r.metadata_json or {}),
|
||||
)
|
||||
for r in rows
|
||||
]
|
||||
|
||||
def create_downloads_task(
|
||||
self,
|
||||
*,
|
||||
parent_job_id: str,
|
||||
download_job_id: str,
|
||||
worker_id: str,
|
||||
title: str,
|
||||
original_filename: str,
|
||||
) -> str:
|
||||
"""Crea Task(type=downloads) y la asocia al download_job. Devuelve task_id."""
|
||||
with session_scope() as session:
|
||||
now = utcnow()
|
||||
task = Task(
|
||||
job_id=parent_job_id,
|
||||
type="downloads",
|
||||
status=JobStatus.PENDING.value,
|
||||
title=title or f"Bot descarga ({original_filename})",
|
||||
request={
|
||||
"worker_id": worker_id,
|
||||
"original_filename": original_filename,
|
||||
"download_job_id": download_job_id,
|
||||
},
|
||||
result={"download_job_id": download_job_id},
|
||||
created_at=now,
|
||||
updated_at=now,
|
||||
)
|
||||
session.add(task)
|
||||
session.flush()
|
||||
row = session.get(DownloadJobRow, download_job_id)
|
||||
if row:
|
||||
row.task_id = task.id
|
||||
row.job_id = parent_job_id
|
||||
session.flush()
|
||||
return task.id
|
||||
|
||||
def parent_job_exists(self, parent_job_id: str) -> bool:
|
||||
from infrastructure.database import Job as IpsJob
|
||||
|
||||
with session_scope() as session:
|
||||
return session.get(IpsJob, parent_job_id) is not None
|
||||
Reference in New Issue
Block a user