linker.py

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "requests>=2.31.0",
# ]
# ///

import argparse
import logging
import sys
from pathlib import Path

import requests

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s - %(levelname)s - %(message)s",
    handlers=[logging.StreamHandler(sys.stdout)],
)

logger = logging.getLogger(__name__)


def process_file(source_file: Path, target_file: Path, backend_url: str):
    logger.info(f"Reading {source_file}")

    with open(source_file, "r", encoding="utf-8") as f:
        file_contents = f.read()
    payload = {"format": "conllu", "source": file_contents}

    logger.info(f"Calling {backend_url}")
    response = requests.post(backend_url, json=payload)
    response.raise_for_status()

    logger.info(f"Writing {target_file}")
    target_file.parent.mkdir(parents=True, exist_ok=True)
    with open(target_file, "w", encoding="utf-8") as f:
        f.write(response.json()["target"])


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--source", type=Path, required=True)
    parser.add_argument("--target", type=Path, required=True)
    parser.add_argument(
        "--backend-url",
        type=str,
        required=True,
        help="URL of the prelinker backend endpoint from an instance of https://github.com/LiITA-LOD/text-linker",
    )
    args = parser.parse_args()

    try:
        process_file(args.source, args.target, args.backend_url)
    except KeyboardInterrupt:
        logger.info("Processing interrupted by user")
        sys.exit(1)
    except Exception as e:
        logger.error(f"Unexpected error: {e}")
        sys.exit(1)


if __name__ == "__main__":
    main()