"""把 S3 抽样结果按位置分类：表格内 / 页眉页脚带 / 正文，分别算文本保真率。"""
import json, sys, pathlib, collections
import pdfplumber

OUT = pathlib.Path(__file__).parent / "out"
pdf_dir = pathlib.Path(sys.argv[1]); val = json.loads((OUT / sys.argv[2]).read_text())
sents = {}
for f in OUT.glob("S*-sentences.json"):
    for s in json.loads(f.read_text()):
        sents[s["id"]] = s
tab_cache, stat = {}, collections.defaultdict(lambda: [0, 0])
for r in val["results"]:
    s = sents[r["id"]]; sid = r["id"].split(":")[0]; key = (sid, s["page"])
    if key not in tab_cache:
        with pdfplumber.open(pdf_dir / f"{sid}.pdf") as pdf:
            pg = pdf.pages[s["page"] - 1]
            tab_cache[key] = ([t.bbox for t in pg.find_tables()], pg.height)
    tables, h = tab_cache[key]
    x0, top, x1, bottom = s["quads"][0]
    if top < 0.09 * h or bottom > 0.92 * h:
        cls = "页眉页脚带"
    elif any(tx0 - 1 <= x0 and top >= tt - 1 and x1 <= tx1 + 1 and bottom <= tb + 1 for tx0, tt, tx1, tb in tables):
        cls = "表格内"
    else:
        cls = "正文"
    stat[cls][0] += r["in_docx_ignoring_autonumber"]; stat[cls][1] += 1
print({k: f"{ok}/{n} = {ok / n:.1%}" for k, (ok, n) in stat.items()})