import argparse
import logging
import requests
import pathlib
from bs4 import BeautifulSoup


def body_filter(tag):
    return (
        tag.name == "div"
        and tag.has_attr("id")
        and tag["id"].startswith("body")
    )


def compare(url_prefix, file_path, file_name):
    data = requests.get(
        f"https://docs.otc.t-systems.com/{url_prefix}/{file_name}.json")
    page_data = None
    for item in data.json():
        if item.get("url").endswith(f"{file_name}.html") and item['content']:
            page_data = item["content"]
            break
    original = BeautifulSoup(page_data, 'html.parser')
    with open(f"{file_path}/{file_name}.html", "r") as f:
        new_content = f.read()
    new = BeautifulSoup(new_content, 'html.parser')
    t1 = original.find(body_filter)
    t2 = new.find(body_filter)
    if t1 != t2:
        logging.error("content %s != %s" % (t1, t2))
        return False
    return True


def main():
    logging.basicConfig(level=logging.DEBUG)
    parser = argparse.ArgumentParser(description="Compare document data.")
    parser.add_argument(
        "path",
        type=str,
        help="Path to the document content (i.e. docs/ecs/api-ref")
    parser.add_argument(
        "url",
        type=str,
        help="url prefix in the helpcenter (i.e. api/ecs)")
    args = parser.parse_args()
    result = True

    for f in pathlib.Path(args.path).glob("*.html"):
        logging.debug(f"Comparing {f.name}")
        if not compare(args.url, args.path, f.name.replace(".html", "")):
            result = False

    if not result:
        logging.error("Comparison showed deviations")
    else:
        logging.info("No deviations found")


if __name__ == '__main__':
    main()