Compare commits

..

1 Commits

Author SHA1 Message Date
Xavier Roche
5f7f4deb63 Gate INTsys on HTS_LFS, not the never-defined LFS_FLAG
LFS_FLAG is an AC_SUBST make variable holding the -D large-file flags; it is
never itself a preprocessor macro, so "#ifdef LFS_FLAG" was always false and
INTsys stayed int on POSIX. HTS_LFS is the AC_DEFINE that config.h carries,
and htsglobal.h already includes config.h before this point.

No live bug either way: every INTsys use site holds a bounded length (cache
strings, a recv length), never a file offset. INTsys appears in no struct
field or function signature, so nothing in the ABI moves, and INTsysP tracks
the typedef so the cache text stays identical decimal digits.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Xavier Roche <roche@httrack.com>
2026-07-16 10:18:21 +02:00
6 changed files with 266 additions and 160 deletions

View File

@@ -323,11 +323,9 @@ typedef int64_t TStamp;
#define LLintP "%" PRId64
/* Integer type for file offsets/sizes passed to the C library; INTsysP is its
printf conversion. FIXME: LFS_FLAG is a configure make variable, never a C
macro, so this test is dead and INTsys stays int on POSIX despite large-file
support (the real macro is HTS_LFS). Widening it there is an installed-header
type change, so it is left alone here. */
#if defined(LFS_FLAG) || defined(_MSC_VER)
printf conversion. HTS_LFS is the large-file macro: LFS_FLAG is a configure
make variable carrying the -D flags, never itself defined. */
#if defined(HTS_LFS) || defined(_MSC_VER)
typedef LLint INTsys;
#define INTsysP LLintP

View File

@@ -3,7 +3,6 @@
# silently drop it from the dist tarball and break "make distcheck".
EXTRA_DIST = $(TESTS) crawl-test.sh run-all-tests.sh check-network.sh \
proxy-https-server.py socks5-server.py proxy-connect-server.py \
proxytestlib.py \
local-crawl.sh local-server.py testlib.sh server.crt server.key \
server-root/simple/basic.html server-root/simple/link.html \
server-root/stripquery/index.html server-root/stripquery/a.html \

View File

@@ -16,17 +16,136 @@ Proxy modes (argv[2], default "ok"):
Usage: proxy-connect-server.py <logdir> [mode]
Prints "ORIGIN <port>", "PROXY <port>", then "ready" (one per line) on stdout.
"""
import http.server
import os
import socket
import socketserver
import sys
import proxytestlib
import threading
ORIGIN_BODY = b"<html><body>ORIGIN-PAGE-564</body></html>"
PROXY_LOG = "proxy.log"
ORIGIN_LOG = "origin-headers.log"
def make_origin(logdir):
class Origin(http.server.BaseHTTPRequestHandler):
def do_GET(self):
with open(os.path.join(logdir, ORIGIN_LOG), "a") as handle:
handle.write(self.requestline + "\n")
for key in self.headers.keys():
handle.write(key + "\n")
self.send_response(200)
self.send_header("Content-Type", "text/html")
self.send_header("Content-Length", str(len(ORIGIN_BODY)))
self.end_headers()
self.wfile.write(ORIGIN_BODY)
def log_message(self, *args):
pass
return Origin
def start_origin(logdir):
httpd = socketserver.TCPServer(("127.0.0.1", 0), make_origin(logdir))
port = httpd.socket.getsockname()[1]
threading.Thread(target=httpd.serve_forever, daemon=True).start()
return port
def pipe(src, dst):
try:
while True:
data = src.recv(65536)
if not data:
break
dst.sendall(data)
except OSError:
pass
finally:
for sock in (src, dst):
try:
sock.shutdown(socket.SHUT_RDWR)
except OSError:
pass
def handle_client(conn, logdir, mode):
rfile = conn.makefile("rb")
request_line = rfile.readline().decode("latin-1").strip()
auth = None
while True:
line = rfile.readline().decode("latin-1")
if line in ("\r\n", "\n", ""):
break
key, _, value = line.partition(":")
if key.strip().lower() == "proxy-authorization":
auth = value.strip()
with open(os.path.join(logdir, PROXY_LOG), "a") as handle:
handle.write(request_line + "\n")
if auth is not None:
handle.write("AUTH " + auth + "\n")
parts = request_line.split()
# CONNECT-only: reject the classic absolute-URI form a normal proxy accepts
if not (len(parts) >= 2 and parts[0] == "CONNECT"):
conn.sendall(b"HTTP/1.0 501 Not Implemented\r\n\r\n")
conn.close()
return
if mode == "flood":
# 200, then an endless header stream with no terminating blank line: the
# client must bound this and give up, not hang.
try:
conn.sendall(b"HTTP/1.0 200 Connection established\r\n")
while True:
conn.sendall(b"X-Pad: 0123456789\r\n")
except OSError:
pass
conn.close()
return
host, _, port = parts[1].partition(":")
try:
upstream = socket.create_connection((host, int(port or 80)))
except OSError:
conn.sendall(b"HTTP/1.0 502 Bad Gateway\r\n\r\n")
conn.close()
return
conn.sendall(b"HTTP/1.0 200 Connection established\r\n\r\n")
threading.Thread(target=pipe, args=(conn, upstream), daemon=True).start()
pipe(upstream, conn)
def start_proxy(logdir, mode):
srv = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
srv.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
srv.bind(("127.0.0.1", 0))
srv.listen(16)
port = srv.getsockname()[1]
def serve():
while True:
conn, _ = srv.accept()
threading.Thread(
target=handle_client, args=(conn, logdir, mode), daemon=True
).start()
threading.Thread(target=serve, daemon=True).start()
return port
def main():
logdir = sys.argv[1]
mode = sys.argv[2] if len(sys.argv) > 2 else "ok"
proxytestlib.serve(logdir, ORIGIN_BODY, 80, mode)
for name in (PROXY_LOG, ORIGIN_LOG):
open(os.path.join(logdir, name), "w").close()
origin_port = start_origin(logdir)
proxy_port = start_proxy(logdir, mode)
# Keep the port lines the caller parses LF: Windows would emit \r\n.
sys.stdout.reconfigure(newline="\n")
print("ORIGIN %d" % origin_port, flush=True)
print("PROXY %d" % proxy_port, flush=True)
print("ready", flush=True)
threading.Event().wait()
if __name__ == "__main__":

View File

@@ -15,17 +15,138 @@ Proxy modes (argv[3], default "ok"):
Usage: proxy-https-server.py <cert.pem> <logdir> [mode]
Prints "ORIGIN <port>", "PROXY <port>", then "ready" (one per line) on stdout.
"""
import http.server
import os
import socket
import socketserver
import ssl
import sys
import proxytestlib
import threading
ORIGIN_BODY = b"<html><body>ORIGIN-PAGE-85</body></html>"
PROXY_LOG = "proxy.log"
ORIGIN_LOG = "origin-headers.log"
def make_origin(logdir):
class Origin(http.server.BaseHTTPRequestHandler):
def do_GET(self):
with open(os.path.join(logdir, ORIGIN_LOG), "a") as handle:
for key in self.headers.keys():
handle.write(key + "\n")
self.send_response(200)
self.send_header("Content-Type", "text/html")
self.send_header("Content-Length", str(len(ORIGIN_BODY)))
self.end_headers()
self.wfile.write(ORIGIN_BODY)
def log_message(self, *args):
pass
return Origin
def start_origin(certfile, logdir):
httpd = socketserver.TCPServer(("127.0.0.1", 0), make_origin(logdir))
ctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
ctx.load_cert_chain(certfile)
httpd.socket = ctx.wrap_socket(httpd.socket, server_side=True)
port = httpd.socket.getsockname()[1]
threading.Thread(target=httpd.serve_forever, daemon=True).start()
return port
def pipe(src, dst):
try:
while True:
data = src.recv(65536)
if not data:
break
dst.sendall(data)
except OSError:
pass
finally:
for sock in (src, dst):
try:
sock.shutdown(socket.SHUT_RDWR)
except OSError:
pass
def handle_client(conn, logdir, mode):
rfile = conn.makefile("rb")
request_line = rfile.readline().decode("latin-1").strip()
auth = None
while True:
line = rfile.readline().decode("latin-1")
if line in ("\r\n", "\n", ""):
break
key, _, value = line.partition(":")
if key.strip().lower() == "proxy-authorization":
auth = value.strip()
with open(os.path.join(logdir, PROXY_LOG), "a") as handle:
handle.write(request_line + "\n")
if auth is not None:
handle.write("AUTH " + auth + "\n")
parts = request_line.split()
if not (len(parts) >= 2 and parts[0] == "CONNECT"):
conn.sendall(b"HTTP/1.0 501 Not Implemented\r\n\r\n")
conn.close()
return
if mode == "flood":
# 200, then an endless header stream with no terminating blank line: the
# client must bound this and give up, not hang.
try:
conn.sendall(b"HTTP/1.0 200 Connection established\r\n")
while True:
conn.sendall(b"X-Pad: 0123456789\r\n")
except OSError:
pass
conn.close()
return
host, _, port = parts[1].partition(":")
try:
upstream = socket.create_connection((host, int(port or 443)))
except OSError:
conn.sendall(b"HTTP/1.0 502 Bad Gateway\r\n\r\n")
conn.close()
return
conn.sendall(b"HTTP/1.0 200 Connection established\r\n\r\n")
threading.Thread(target=pipe, args=(conn, upstream), daemon=True).start()
pipe(upstream, conn)
def start_proxy(logdir, mode):
srv = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
srv.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
srv.bind(("127.0.0.1", 0))
srv.listen(16)
port = srv.getsockname()[1]
def serve():
while True:
conn, _ = srv.accept()
threading.Thread(
target=handle_client, args=(conn, logdir, mode), daemon=True
).start()
threading.Thread(target=serve, daemon=True).start()
return port
def main():
certfile, logdir = sys.argv[1], sys.argv[2]
mode = sys.argv[3] if len(sys.argv) > 3 else "ok"
proxytestlib.serve(logdir, ORIGIN_BODY, 443, mode, certfile=certfile)
for name in (PROXY_LOG, ORIGIN_LOG):
open(os.path.join(logdir, name), "w").close()
origin_port = start_origin(certfile, logdir)
proxy_port = start_proxy(logdir, mode)
# Keep the port lines the caller parses LF: Windows would emit \r\n.
sys.stdout.reconfigure(newline="\n")
print("ORIGIN %d" % origin_port, flush=True)
print("PROXY %d" % proxy_port, flush=True)
print("ready", flush=True)
threading.Event().wait()
if __name__ == "__main__":

View File

@@ -1,146 +0,0 @@
#!/usr/bin/env python3
"""Shared helpers for the local proxy test servers.
A CONNECT proxy in front of an origin, as used by proxy-https-server.py (TLS
origin, #85) and proxy-connect-server.py (plain origin, #564). socks5-server.py
reuses the relay only; its origin is specialised for keep-alive reuse.
Importable because Python puts the running script's directory on sys.path.
"""
import http.server
import os
import socket
import socketserver
import ssl
import sys
import threading
PROXY_LOG = "proxy.log"
ORIGIN_LOG = "origin-headers.log"
def pipe(src, dst):
"""Relay bytes one way until EOF, then tear both ends down."""
try:
while True:
data = src.recv(65536)
if not data:
break
dst.sendall(data)
except OSError:
pass
finally:
for sock in (src, dst):
try:
sock.shutdown(socket.SHUT_RDWR)
except OSError:
pass
def make_origin(logdir, body):
class Origin(http.server.BaseHTTPRequestHandler):
def do_GET(self):
# the request line proves origin-form vs absolute-URI (#564)
with open(os.path.join(logdir, ORIGIN_LOG), "a") as handle:
handle.write(self.requestline + "\n")
for key in self.headers.keys():
handle.write(key + "\n")
self.send_response(200)
self.send_header("Content-Type", "text/html")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def log_message(self, *args):
pass
return Origin
def start_origin(logdir, body, certfile=None):
"""Serve body on an ephemeral port, over TLS when certfile is given."""
httpd = socketserver.TCPServer(("127.0.0.1", 0), make_origin(logdir, body))
if certfile is not None:
ctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
ctx.load_cert_chain(certfile)
httpd.socket = ctx.wrap_socket(httpd.socket, server_side=True)
port = httpd.socket.getsockname()[1]
threading.Thread(target=httpd.serve_forever, daemon=True).start()
return port
def handle_client(conn, logdir, mode, default_port):
rfile = conn.makefile("rb")
request_line = rfile.readline().decode("latin-1").strip()
auth = None
while True:
line = rfile.readline().decode("latin-1")
if line in ("\r\n", "\n", ""):
break
key, _, value = line.partition(":")
if key.strip().lower() == "proxy-authorization":
auth = value.strip()
with open(os.path.join(logdir, PROXY_LOG), "a") as handle:
handle.write(request_line + "\n")
if auth is not None:
handle.write("AUTH " + auth + "\n")
parts = request_line.split()
# CONNECT-only: reject the classic absolute-URI form a normal proxy accepts
if not (len(parts) >= 2 and parts[0] == "CONNECT"):
conn.sendall(b"HTTP/1.0 501 Not Implemented\r\n\r\n")
conn.close()
return
if mode == "flood":
# 200, then endless headers with no blank line: the client must not hang
try:
conn.sendall(b"HTTP/1.0 200 Connection established\r\n")
while True:
conn.sendall(b"X-Pad: 0123456789\r\n")
except OSError:
pass
conn.close()
return
host, _, port = parts[1].partition(":")
try:
# default_port only backstops a portless CONNECT; httrack sends host:port
upstream = socket.create_connection((host, int(port or default_port)))
except OSError:
conn.sendall(b"HTTP/1.0 502 Bad Gateway\r\n\r\n")
conn.close()
return
conn.sendall(b"HTTP/1.0 200 Connection established\r\n\r\n")
threading.Thread(target=pipe, args=(conn, upstream), daemon=True).start()
pipe(upstream, conn)
def start_proxy(logdir, mode, default_port):
srv = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
srv.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
srv.bind(("127.0.0.1", 0))
srv.listen(16)
port = srv.getsockname()[1]
def accept_loop():
while True:
conn, _ = srv.accept()
threading.Thread(
target=handle_client,
args=(conn, logdir, mode, default_port),
daemon=True,
).start()
threading.Thread(target=accept_loop, daemon=True).start()
return port
def serve(logdir, origin_body, default_port, mode="ok", certfile=None):
"""Start the origin+proxy pair, announce both ports, then block forever."""
for name in (PROXY_LOG, ORIGIN_LOG):
open(os.path.join(logdir, name), "w").close()
origin_port = start_origin(logdir, origin_body, certfile)
proxy_port = start_proxy(logdir, mode, default_port)
# Keep the port lines the caller parses LF: Windows would emit \r\n.
sys.stdout.reconfigure(newline="\n")
print("ORIGIN %d" % origin_port, flush=True)
print("PROXY %d" % proxy_port, flush=True)
print("ready", flush=True)
threading.Event().wait()

View File

@@ -16,8 +16,6 @@ import struct
import sys
import threading
from proxytestlib import pipe
# The one name the proxy answers for; a .invalid TLD never resolves (RFC 6761),
# so a locally-resolving client could not reach us -- success proves remote DNS.
REMOTE_HOST = b"socks-origin.invalid"
@@ -87,6 +85,23 @@ def recvn(conn, n):
return buf
def pipe(src, dst):
try:
while True:
data = src.recv(65536)
if not data:
break
dst.sendall(data)
except OSError:
pass
finally:
for sock in (src, dst):
try:
sock.shutdown(socket.SHUT_RDWR)
except OSError:
pass
def log(logdir, line):
with open(os.path.join(logdir, SOCKS_LOG), "a") as handle:
handle.write(line + "\n")