scripts/upload_ejes_artifacts.py

"""Sube los artefactos de EJES a Azure (report_artifacts root) para que el Space los consuma.

Recorre data/analysis/next_goal/artifacts/ejes/<slug>/<season>/* del repo Racing y sube cada
archivo a ``{azure_report_artifacts_root}/ejes/...``. Chicos (~11MB total).

Uso: python scripts/upload_ejes_artifacts.py [--source ../data/analysis/next_goal/artifacts/ejes] [--overwrite]
"""

from __future__ import annotations

import argparse
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))

from racing_reports.config import DEFAULT_SETTINGS
from racing_reports.datastore import DataStore, _azure_credential  # noqa: F401
from azure.storage.filedatalake import DataLakeServiceClient

DEFAULT_SOURCE = Path(__file__).resolve().parents[2] / "data" / "analysis" / "next_goal" / "artifacts" / "ejes"


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--source", type=Path, default=DEFAULT_SOURCE)
    ap.add_argument("--overwrite", action="store_true")
    args = ap.parse_args()

    src: Path = args.source
    if not src.is_dir():
        raise SystemExit(f"No existe {src}")
    fs = DataStore()._filesystem_client()
    root = DEFAULT_SETTINGS.azure_report_artifacts_root.strip("/")
    files = [p for p in src.rglob("*") if p.is_file() and not p.name.startswith("_")]
    print(f"{len(files)} archivos → {root}/ejes/")
    subidos = saltados = 0
    for p in files:
        rel = p.relative_to(src).as_posix()
        remote = f"{root}/ejes/{rel}"
        fc = fs.get_file_client(remote)
        if not args.overwrite:
            try:
                fc.get_file_properties()
                saltados += 1
                continue
            except Exception:
                pass
        fc.upload_data(p.read_bytes(), overwrite=True)
        subidos += 1
    print(f"subidos: {subidos} | ya estaban: {saltados}")


if __name__ == "__main__":
    main()