"""
HubSpot PLG pipeline — loads contacts, email metrics, list membership,
workflow events, form submissions, and campaign specs into DuckDB (local)
or BigQuery (production).

Usage:
    python hubspot_plg_pipeline.py                # DuckDB (default)
    python hubspot_plg_pipeline.py --destination bigquery
"""

import argparse
import logging

import dlt

from hubspot_plg import hubspot_plg

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] %(name)s - %(message)s",
)
logger = logging.getLogger("hubspot_plg_pipeline")


def run(destination: str = "duckdb") -> None:
    pipeline = dlt.pipeline(
        pipeline_name="hubspot_plg",
        dataset_name="hubspot_plg_data",
        destination=destination,
        progress="log",
    )

    source = hubspot_plg()

    logger.info("Running hubspot_plg pipeline -> %s", destination)
    load_info = pipeline.run(source)
    logger.info("Load info:\n%s", load_info)

    row_counts = pipeline.last_trace.last_normalize_info
    logger.info("Row counts:\n%s", row_counts)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="HubSpot PLG pipeline")
    parser.add_argument(
        "--destination",
        default="duckdb",
        choices=["duckdb", "bigquery"],
        help="dlt destination (default: duckdb)",
    )
    args = parser.parse_args()
    run(destination=args.destination)