diff --git a/scripts/fetch-pdf-test-fonts.py b/scripts/fetch-pdf-test-fonts.py index 821a5e74..5da6d9cd 100644 --- a/scripts/fetch-pdf-test-fonts.py +++ b/scripts/fetch-pdf-test-fonts.py @@ -4,13 +4,28 @@ import argparse import hashlib import json +import os from pathlib import Path +import tempfile import time import urllib.error +import urllib.parse import urllib.request +class _HttpsOnlyRedirectHandler(urllib.request.HTTPRedirectHandler): + def redirect_request(self, req, fp, code, msg, headers, newurl): + if urllib.parse.urlsplit(newurl).scheme != "https": + raise ValueError("refusing to follow a non-HTTPS redirect") + return super().redirect_request(req, fp, code, msg, headers, newurl) + + +urllib.request.install_opener(urllib.request.build_opener(_HttpsOnlyRedirectHandler)) + + def fetch(url): + if urllib.parse.urlsplit(url).scheme != "https": + raise ValueError("refusing to fetch a non-HTTPS URL") for attempt in range(3): try: with urllib.request.urlopen(url, timeout=60) as response: @@ -42,14 +57,26 @@ def main(): name, url, digest = fixture["name"], fixture["source"], fixture["sha256"] if Path(name).name != name or name in ("", ".", "..") or not url.startswith("https://"): raise ValueError("invalid fixture name or source") - path = destination / name + path = (destination / name).resolve() + if path.parent != destination: + raise ValueError(f"fixture path escapes destination: {name}") if path.is_file() and hashlib.sha256(path.read_bytes()).hexdigest() == digest: print(f"Verified {name}") continue data = fetch(url) if len(data) > 16 * 1024 * 1024 or hashlib.sha256(data).hexdigest() != digest: raise ValueError(f"fixture size or SHA-256 mismatch: {name}") - path.write_bytes(data) + fd, tmp = tempfile.mkstemp(dir=destination, prefix=f".{name}.", suffix=".tmp") + try: + with os.fdopen(fd, "wb") as handle: + handle.write(data) + os.replace(tmp, destination / name) + except BaseException: + try: + os.unlink(tmp) + except OSError: + pass + raise print(f"Fetched and verified {name}")