"""S1：用 Gotenberg 把 10 份样本转成 PDF，记录页数、耗时、是否失败。
用法：python -I convert.py <配置名> <Gotenberg 地址> [预处理后的 DOCX 目录]
"""
import json, sys, time, pathlib
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parent.parent))
import httpx, pypdfium2 as pdfium
from common import IDS, sample_file, sniff

cfg, base = sys.argv[1], sys.argv[2]
src_dir = pathlib.Path(sys.argv[3]) if len(sys.argv) > 3 else None  # 预处理后的 DOCX 目录
out = pathlib.Path(__file__).parent / "out" / cfg
out.mkdir(parents=True, exist_ok=True)
rows = {}
with httpx.Client(timeout=600) as c:
    for sid in IDS:
        f = (src_dir / f"{sid}.docx") if src_dir else sample_file(sid)
        ext = sniff(f)  # 按真实格式给扩展名，LibreOffice 据此选过滤器
        t = time.monotonic()
        r = c.post(f"{base}/forms/libreoffice/convert",
                   files={"files": (f"{sid}.{ext}", f.read_bytes())})
        dt = round(time.monotonic() - t, 1)
        if r.status_code != 200:
            rows[sid] = {"ok": False, "status": r.status_code, "err": r.text[:200], "sec": dt}
        else:
            pdf = out / f"{sid}.pdf"
            pdf.write_bytes(r.content)
            n = len(pdfium.PdfDocument(str(pdf)))
            rows[sid] = {"ok": True, "pages": n, "sec": dt}
        print(cfg, sid, rows[sid], flush=True)
(out / "result.json").write_text(json.dumps(rows, ensure_ascii=False, indent=1))