2026-06-19 08:43:56 +02:00
|
|
|
#!/usr/bin/env python3
|
|
|
|
|
"""Local CONNECT proxy + self-signed HTTPS origin for the issue #85 test.
|
|
|
|
|
|
|
|
|
|
Starts a TLS origin server and an HTTP proxy that honours CONNECT, on ephemeral
|
|
|
|
|
ports. Every request line the proxy receives (and any Proxy-Authorization) is
|
2026-06-19 09:28:50 +02:00
|
|
|
appended to the proxy log; every header the origin receives over the tunnel is
|
|
|
|
|
appended to the origin log. That lets the test assert both that an https crawl
|
|
|
|
|
tunneled through the proxy and that proxy credentials never leaked to the origin.
|
2026-06-19 08:43:56 +02:00
|
|
|
|
2026-06-19 09:28:50 +02:00
|
|
|
Proxy modes (argv[3], default "ok"):
|
|
|
|
|
ok - honour CONNECT and tunnel to the origin
|
|
|
|
|
flood - answer 200 then stream headers forever with no blank line, to exercise
|
|
|
|
|
the client's bound on the proxy response (must not hang the crawl)
|
|
|
|
|
|
|
|
|
|
Usage: proxy-https-server.py <cert.pem> <logdir> [mode]
|
2026-06-19 08:43:56 +02:00
|
|
|
Prints "ORIGIN <port>", "PROXY <port>", then "ready" (one per line) on stdout.
|
|
|
|
|
"""
|
2026-07-16 18:01:30 +02:00
|
|
|
import os
|
2026-06-19 08:43:56 +02:00
|
|
|
import sys
|
|
|
|
|
|
2026-07-16 18:01:30 +02:00
|
|
|
# python3 -P (PYTHONSAFEPATH) drops the script's own directory from sys.path
|
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
|
|
|
|
|
|
|
|
|
|
import proxytestlib # noqa: E402
|
2026-06-19 08:43:56 +02:00
|
|
|
|
Share the proxy test servers' duplicated code in proxytestlib.py
proxy-https-server.py (#85) and proxy-connect-server.py (#564) were ~90% identical: the CONNECT proxy, the relay and the origin were copies, differing only in the origin body, the TLS wrap and the argv shape. The common half moves to tests/proxytestlib.py, leaving each server as a docstring plus a serve() call (153 and 152 lines become 32 and 33). socks5-server.py reuses the relay too, but keeps its own origin, which is specialized for keep-alive reuse and subpages.
Behavior-preserving except that the shared origin always logs the request line, which previously only proxy-connect-server.py did. That is harmless for #85, whose origin-log assertion only checks that no Proxy-Authorization arrives. Tests 13, 52 and 57 pass unchanged, the full suite is identical at 101 pass / 7 skip, and the new module ships in the release tarball.
2026-07-16 17:30:41 +02:00
|
|
|
ORIGIN_BODY = b"<html><body>ORIGIN-PAGE-85</body></html>"
|
2026-06-19 08:43:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
2026-06-19 09:28:50 +02:00
|
|
|
certfile, logdir = sys.argv[1], sys.argv[2]
|
|
|
|
|
mode = sys.argv[3] if len(sys.argv) > 3 else "ok"
|
Share the proxy test servers' duplicated code in proxytestlib.py
proxy-https-server.py (#85) and proxy-connect-server.py (#564) were ~90% identical: the CONNECT proxy, the relay and the origin were copies, differing only in the origin body, the TLS wrap and the argv shape. The common half moves to tests/proxytestlib.py, leaving each server as a docstring plus a serve() call (153 and 152 lines become 32 and 33). socks5-server.py reuses the relay too, but keeps its own origin, which is specialized for keep-alive reuse and subpages.
Behavior-preserving except that the shared origin always logs the request line, which previously only proxy-connect-server.py did. That is harmless for #85, whose origin-log assertion only checks that no Proxy-Authorization arrives. Tests 13, 52 and 57 pass unchanged, the full suite is identical at 101 pass / 7 skip, and the new module ships in the release tarball.
2026-07-16 17:30:41 +02:00
|
|
|
proxytestlib.serve(logdir, ORIGIN_BODY, 443, mode, certfile=certfile)
|
2026-06-19 08:43:56 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
|
main()
|
