"""S1 真值：Word 最后保存时记录的页数。DOCX 读 docProps/app.xml 的 <Pages>，旧版 DOC 读 OLE SummaryInformation 的 PIDSI_PAGECOUNT。"""
import json, re, sys, zipfile, pathlib
sys.path.insert(0, str(pathlib.Path(__file__).resolve().parent.parent))
import olefile
from common import IDS, sample_file, sniff

OUT = pathlib.Path(__file__).parent / "out"
rows = {}
for sid in IDS:
    f = sample_file(sid)
    kind = sniff(f)
    info = {"kind": kind, "pages": None, "app": None, "ole_objects": 0}
    if kind == "docx":
        with zipfile.ZipFile(f) as z:
            names = z.namelist()
            if "docProps/app.xml" in names:
                app = z.read("docProps/app.xml").decode("utf-8", "replace")
                m = re.search(r"<Pages>(\d+)</Pages>", app)
                info["pages"] = int(m.group(1)) if m else None
                a = re.search(r"<Application>([^<]*)</Application>", app)
                info["app"] = a.group(1) if a else None
            info["ole_objects"] = sum(1 for n in names if n.startswith("word/embeddings/"))
            info["has_ole_xml"] = b"<o:OLEObject" in z.read("word/document.xml")
    elif kind == "doc":
        ole = olefile.OleFileIO(str(f))
        meta = ole.get_metadata()
        info["pages"] = meta.num_pages
        info["app"] = (meta.creating_application or b"").decode("gbk", "replace") if isinstance(meta.creating_application, bytes) else meta.creating_application
        info["ole_objects"] = sum(1 for e in ole.listdir() if e and e[0] == "ObjectPool")
    rows[sid] = info
    print(sid, info)
(OUT / "truth.json").write_text(json.dumps(rows, ensure_ascii=False, indent=1))