From: Gregory P. Smith <greg@krypto.org>
Date: Mon, 5 Dec 2022 22:27:55 +0000 (-0800)
Subject: gh-100001: Also escape \s in http.server log messages. (#100038)
X-Git-Tag: v3.12.0a3~8
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=7e29398407dbd53b714702abb89aa2fd7baca48a;p=thirdparty%2FPython%2Fcpython.git

gh-100001: Also escape \s in http.server log messages. (#100038)

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.
---

diff --git a/Lib/http/server.py b/Lib/http/server.py
index 3b5bd9eb0129..8acabff605e7 100644
--- a/Lib/http/server.py
+++ b/Lib/http/server.py
@@ -566,6 +566,7 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):
     # 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.
diff --git a/Lib/test/test_httpservers.py b/Lib/test/test_httpservers.py
index b0e2d713e3de..ca078862cca6 100644
--- a/Lib/test/test_httpservers.py
+++ b/Lib/test/test_httpservers.py
@@ -1000,6 +1000,7 @@ class BaseHTTPRequestHandlerTestCase(unittest.TestCase):
             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.
@@ -1008,6 +1009,7 @@ class BaseHTTPRequestHandlerTestCase(unittest.TestCase):
         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')
diff --git a/Misc/NEWS.d/next/Library/2022-12-05-13-40-15.gh-issue-100001.78ReYp.rst b/Misc/NEWS.d/next/Library/2022-12-05-13-40-15.gh-issue-100001.78ReYp.rst
new file mode 100644
index 000000000000..e305352c7a55
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2022-12-05-13-40-15.gh-issue-100001.78ReYp.rst
@@ -0,0 +1,5 @@
+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.