descarga_factura_transporte/consulta_rapida.py

"""
Script para procesar correos específicos por ID desde un archivo JSON.
No modifica el código existente del pipeline.
"""
import sys
import os
import json
import argparse
import requests
from datetime import datetime, timedelta
from dotenv import load_dotenv

import database_utilities
import logger_manager
from pipeline import _procesar_un_correo, step_authenticate


# ============================================================================
# OBTENER CORREO POR ID
# ============================================================================
def get_email_by_id(user_email: str, token: str, message_id: str) -> dict | None:
    """Obtiene un correo desde Microsoft Graph por su ID de mensaje."""
    url = f"https://graph.microsoft.com/v1.0/users/{user_email}/messages/{message_id}"
    headers = {"Authorization": f"Bearer {token}"}
    resp = requests.get(url, headers=headers, verify=False)
    if resp.status_code != 200:
        print(f"   ❌ Error al obtener mensaje {message_id}: HTTP {resp.status_code}")
        return None
    msg = resp.json()
    utc_str = msg.get("receivedDateTime", "")
    dt_utc = datetime.fromisoformat(utc_str.replace("Z", "+00:00"))
    dt_local = dt_utc - timedelta(hours=5)
    from_obj = msg.get("from", {})
    sender = from_obj.get("emailAddress", {}).get("address", "Desconocido")
    return {
        "id": msg.get("id"),
        "fecha": dt_local.strftime("%Y-%m-%d %H:%M:%S"),
        "sender": sender,
        "subject": msg.get("subject", ""),
        "has_attach": msg.get("hasAttachments"),
    }


# ============================================================================
# PIPELINE PARA IDS
# ============================================================================
def run_pipeline_for_ids(ids: list[str]) -> None:
    # Ruta absoluta: no depende del directorio de trabajo desde el que se lance el proceso
    load_dotenv(dotenv_path=os.path.join(os.path.dirname(__file__), ".env"))
    email_addr = os.getenv("EMAIL", "")
    download_folder = os.getenv("DOWNLOAD_FOLDER", "adjuntos")
    output_folder = os.getenv("OUTPUT_FOLDER", "resultado")

    if not email_addr:
        print("❌ EMAIL no configurado en .env")
        return

    database_utilities.init_db()
    token = step_authenticate()
    if not token:
        return

    for msg_id in ids:
        email = get_email_by_id(email_addr, token, msg_id.strip())
        if not email:
            continue
        _procesar_un_correo(email, token, email_addr, download_folder, output_folder)


# ============================================================================
# MAIN
# ============================================================================
if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Procesar correos específicos por set de IDs desde tests/ids_prueba.json"
    )
    parser.add_argument(
        "--set", "-s", required=True,
        help="Nombre del set en tests/ids_prueba.json"
    )
    args = parser.parse_args()

    json_path = os.path.join(os.path.dirname(__file__), "test", "ids_prueba.json")
    if not os.path.exists(json_path):
        print(f"❌ No se encuentra {json_path}")
        sys.exit(1)

    with open(json_path) as f:
        sets = json.load(f)

    if args.set not in sets:
        print(f"❌ Set '{args.set}' no encontrado. Disponibles: {', '.join(sets.keys())}")
        sys.exit(1)

    ids = sets[args.set]["ids"]
    descripcion = sets[args.set].get("descripcion", "")
    print(f"\n📋 Set: {args.set} — {descripcion}")
    print(f"   IDs a procesar: {len(ids)}")

    logger_manager.setup_logging()

    inicio = datetime.now()
    print("\n" + "=" * 60)
    print(f"🚀 INICIO DE EJECUCIÓN: {inicio.strftime('%Y-%m-%d %H:%M:%S')}")
    print(f"📄 Log guardado en: {logger_manager.LOG_FILE}")
    print("=" * 60)

    run_pipeline_for_ids(ids)

    fin = datetime.now()
    duracion = fin - inicio
    print("\n" + "=" * 60)
    print(f"🏁 FIN DE EJECUCIÓN: {fin.strftime('%Y-%m-%d %H:%M:%S')}")
    print(f"⏱️ Duración total: {str(duracion).split('.')[0]}")
    print("=" * 60)