80 lines
2.9 KiB
Python
80 lines
2.9 KiB
Python
|
"""Byte hashes already proved the stored files are all distinct. This compares
|
||
|
|
their TEXT so we can say whether the stored resignation letter is simply an
|
||
|
|
older render of the same letter the user just attached.
|
||
|
|
"""
|
||
|
|
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"]
|
||
|
|
|
||
|
|
LOCAL = {
|
||
|
|
"LOCAL: UFC - Shareholders Resolution Director Sune Resigned.pdf":
|
||
|
|
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.pdf":
|
||
|
|
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 = [
|
||
|
|
("STORED resolution.signed_letter", "pbc_266170881", "e0dbxprazb70rqx", "corrected_v2_avwpnq7o93.pdf"),
|
||
|
|
("STORED resignation.letter", "ysterbaard_director_resignations", "8cfie18uhgy0n0o",
|
||
|
|
"resignation_letter_the_ultimate_fuel_company_1jk8t34nf3.pdf"),
|
||
|
|
("STORED resignation.signature", "ysterbaard_director_resignations", "8cfie18uhgy0n0o",
|
||
|
|
"tbde1evt2m6_8mz8kutpki.pdf"),
|
||
|
|
]
|
||
|
|
|
||
|
|
|
||
|
|
def text_of(b: bytes) -> str:
|
||
|
|
try:
|
||
|
|
r = PdfReader(io.BytesIO(b))
|
||
|
|
return "\n".join((p.extract_text() or "") for p in r.pages)
|
||
|
|
except Exception as e:
|
||
|
|
return f"<<unreadable: {e}>>"
|
||
|
|
|
||
|
|
|
||
|
|
def norm(s: str) -> str:
|
||
|
|
return " ".join(s.split()).lower()
|
||
|
|
|
||
|
|
|
||
|
|
texts = {}
|
||
|
|
for label, path in LOCAL.items():
|
||
|
|
b = Path(path).read_bytes()
|
||
|
|
texts[label] = (norm(text_of(b)), len(b))
|
||
|
|
print(f"{label}\n {len(b):>8} B chars={len(texts[label][0])}")
|
||
|
|
|
||
|
|
print()
|
||
|
|
for label, col, rid, fname in STORED:
|
||
|
|
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()
|
||
|
|
texts[label] = (norm(text_of(b)), len(b))
|
||
|
|
print(f"{label}\n {len(b):>8} B chars={len(texts[label][0])}")
|
||
|
|
|
||
|
|
print("\n=== TEXT SIMILARITY (fraction of the shorter text found in the longer) ===")
|
||
|
|
import difflib
|
||
|
|
|
||
|
|
labels = list(texts)
|
||
|
|
for i in range(len(labels)):
|
||
|
|
for j in range(i + 1, len(labels)):
|
||
|
|
a, b = texts[labels[i]][0], texts[labels[j]][0]
|
||
|
|
if not a or not b:
|
||
|
|
continue
|
||
|
|
ratio = difflib.SequenceMatcher(None, a, b).ratio()
|
||
|
|
print(f" {ratio * 100:5.1f}% {labels[i]} <-> {labels[j]}")
|
||
|
|
|
||
|
|
print("\n=== FIRST 400 CHARS OF EACH ===")
|
||
|
|
for label in labels:
|
||
|
|
t = texts[label][0]
|
||
|
|
print(f"\n--- {label}\n{t[:400]}")
|