republisher/repub/entrypoint.py

from __future__ import annotations

import argparse
import logging
import os
import sys

import repub.crawl as crawl_module
from repub.web import create_app

FeedNameFilter = crawl_module.FeedNameFilter
check_runtime = crawl_module.check_runtime

__all__ = ["FeedNameFilter", "check_runtime", "entrypoint", "parse_args"]

logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)
logger.propagate = False
if not logger.handlers:
    handler = logging.StreamHandler()
    handler.setLevel(logging.DEBUG)
    handler.setFormatter(
        logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
    )
    logger.addHandler(handler)


def parse_args(argv: list[str] | None = None) -> tuple[str, argparse.Namespace]:
    raw_args = list(argv) if argv is not None else sys.argv[1:]

    parser = argparse.ArgumentParser(description="Mirror RSS and Atom feeds")
    subparsers = parser.add_subparsers(dest="command")

    serve_parser = subparsers.add_parser("serve", help="Start the republisher web UI")
    serve_parser.add_argument(
        "--host",
        default=os.environ.get("REPUB_HOST", "127.0.0.1"),
        help="Host interface for the web UI",
    )
    serve_parser.add_argument(
        "--port",
        default=os.environ.get("REPUB_PORT", "8080"),
        help="Port for the web UI",
    )

    crawl_parser = subparsers.add_parser("crawl", help="Run the feed crawler once")
    crawl_parser.add_argument(
        "-c",
        "--config",
        default="repub.toml",
        help="Path to runtime config TOML file",
    )
    if not raw_args:
        raw_args = ["serve"]
    elif raw_args[0] in {"-c", "--config"}:
        raw_args = ["crawl", *raw_args]
    elif raw_args[0] not in {"serve", "crawl"}:
        raw_args = ["serve", *raw_args]

    args = parser.parse_args(raw_args)
    command = args.command or "serve"
    return command, args


def entrypoint(argv: list[str] | None = None) -> int:
    command, args = parse_args(argv)

    if command == "crawl":
        crawl_module.check_runtime = check_runtime
        return crawl_module.crawl_from_config(args.config)

    try:
        port = int(args.port)
    except ValueError:
        logger.error("Invalid REPUB_PORT/--port value: %s", args.port)
        return 2

    app = create_app()
    app.run(host=args.host, port=port)
    return 0


if __name__ == "__main__":
    sys.exit(entrypoint())