"""读取校招鸭公告 URL 文件并批量处理（一次性执行）。

运行（项目根目录下）：
    python init_xiaozhaoya.py
"""

from __future__ import annotations

import json
from pathlib import Path

from app.core.database import close_db, init_db
from app.core.logger import log
from app.service.announcement_batch_service import save_announcements


URLS_PATH = Path(__file__).resolve().parent / "doc" / "xiaozhaoya_announcement_links.json"


def load_urls() -> list[str]:
    """从本地 JSON 读取公告地址，过滤无效值并保持原始顺序去重。"""
    with URLS_PATH.open("r", encoding="utf-8") as json_file:
        payload = json.load(json_file)

    if not isinstance(payload, list):
        raise ValueError(f"公告地址 JSON 必须是数组：{URLS_PATH}")

    urls: list[str] = []
    seen: set[str] = set()
    for value in payload:
        if not isinstance(value, str):
            continue
        url = value.strip()
        if not url.startswith(("http://", "https://")) or url in seen:
            continue
        seen.add(url)
        urls.append(url)

    log.info("从文件读取到 {} 条公告地址（原始 {} 条）", len(urls), len(payload))
    return urls


def main() -> None:
    """读取 URL，初始化数据库并直接调用批量处理服务。"""
    urls = load_urls()
    init_db()
    try:
        save_announcements(urls)
    finally:
        close_db()


if __name__ == "__main__":
    main()