"""Decisive test: does a file contain embedded signature IMAGES?

Text extraction can't tell a signed scan from a blank template — both have the
same text layer. Embedded image XObjects can: a scanned signature leaves an
image where the template has bare underscores.
"""
import io
import urllib.parse
import urllib.request
from pathlib import Path
from pypdf import PdfReader

JEI = Path(r"C:\Users\SJ\.minimax-agent\projects\JEI")
env = {}
for line in (JEI / ".env.local").read_text(encoding="utf-8").splitlines():
    line = line.strip()
    if line and not line.startswith("#") and "=" in line:
        k, v = line.split("=", 1)
        env[k.strip()] = v.strip().strip('"').strip("'")
PB = env.get("NEXT_PUBLIC_PB_URL") or env["PB_URL"]
TOK = env["PB_TOKEN"]

FILES = [
    ("LOCAL  UFC - Shareholders Resolution ... (attached)",
     None,
     r"C:\Users\SJ\.minimax\v2\assets\2026\10\12\13-41-56-012-asset_20261012-134156-012_a0299b3ae338_88b7c484-UFC - Shareholders Resolution Director Sune Resigned.pdf"),
    ("LOCAL  UFC - Sune Resignation Letter (attached)",
     None,
     r"C:\Users\SJ\.minimax\v2\assets\2026\10\12\13-41-56-017-asset_20261012-134156-017_9aec1b4380ba_261a3e6b-UFC - Sune Resignation Letter.pdf"),
    ("STORED resolution.signed_letter", ("pbc_266170881", "e0dbxprazb70rqx", "corrected_v2_avwpnq7o93.pdf"), None),
    ("STORED resignation.letter", ("ysterbaard_director_resignations", "8cfie18uhgy0n0o",
     "resignation_letter_the_ultimate_fuel_company_1jk8t34nf3.pdf"), None),
    ("STORED resignation.signature", ("ysterbaard_director_resignations", "8cfie18uhgy0n0o",
     "tbde1evt2m6_8mz8kutpki.pdf"), None),
]


def count_images(reader) -> int:
    n = 0
    for page in reader.pages:
        try:
            n += len(page.images)
        except Exception:
            pass
    return n


def has_annot_sig(reader) -> int:
    n = 0
    for page in reader.pages:
        try:
            for a in page.get("/Annots") or []:
                obj = a.get_object()
                if obj.get("/Subtype") == "/Widget" or obj.get("/FT") == "/Sig":
                    n += 1
        except Exception:
            pass
    return n


for label, pb, path in FILES:
    if pb:
        col, rid, fname = pb
        url = f"{PB}/api/files/{col}/{rid}/{urllib.parse.quote(fname)}"
        req = urllib.request.Request(url, headers={"Authorization": TOK})
        with urllib.request.urlopen(req, timeout=120) as r:
            b = r.read()
    else:
        b = Path(path).read_bytes()

    rd = PdfReader(io.BytesIO(b))
    imgs = count_images(rd)
    sigs = has_annot_sig(rd)
    # Look for signature-ish words in the text layer
    txt = " ".join((p.extract_text() or "") for p in rd.pages).lower()
    markers = []
    for m in ("approved by", "signed at", "signature", "signed"):
        if m in txt:
            markers.append(m)
    print(f"{label}")
    print(f"    size={len(b):>8} B  pages={len(rd.pages)}  images={imgs}  digital-sig-widgets={sigs}")
    print(f"    text markers present: {markers}")
    print()

print("VERDICT: images==0 on every file => none of these contain a scanned")
print("signature; all are blank templates with signature lines only.")