# https://en.wikipedia.org/wiki/List_of_Unicode_characters#Control_codes
_control_char_table = str.maketrans(
{c: fr'\x{c:02x}' for c in itertools.chain(range(0x20), range(0x7f,0xa0))})
+ _control_char_table[ord('\\')] = r'\\'
def log_message(self, format, *args):
"""Log an arbitrary message.
log_message(self.handler, '/\033bar\000\033')
log_message(self.handler, '/spam %s.', 'a')
log_message(self.handler, '/spam %s.', '\033\x7f\x9f\xa0beans')
+ log_message(self.handler, '"GET /foo\\b"ar\007 HTTP/1.0"')
stderr = fake_stderr.getvalue()
self.assertNotIn('\033', stderr) # non-printable chars are caught.
self.assertNotIn('\000', stderr) # non-printable chars are caught.
self.assertIn(r'/\x1bbar\x00\x1b', lines[1])
self.assertIn('/spam a.', lines[2])
self.assertIn('/spam \\x1b\\x7f\\x9f\xa0beans.', lines[3])
+ self.assertIn(r'"GET /foo\\b"ar\x07 HTTP/1.0"', lines[4])
def test_http_1_1(self):
result = self.send_typical_request(b'GET / HTTP/1.1\r\n\r\n')
--- /dev/null
+Also \ escape \s in the http.server BaseHTTPRequestHandler.log_message so
+that it is technically possible to parse the line and reconstruct what the
+original data was. Without this a \xHH is ambiguious as to if it is a hex
+replacement we put in or the characters r"\x" came through in the original
+request line.