gh-100001: Omit control characters in http.server stderr logs. (#100002)

Replace control characters in http.server.BaseHTTPRequestHandler.log_message with an escaped \xHH sequence to avoid causing problems for the terminal the output is printed to.

1 files changed, 10 insertions, 1 deletions

diff --git a/Lib/http/server.py b/Lib/http/server.py
index 8aee31b..3b5bd9e 100644
--- a/Lib/http/server.py
+++ b/Lib/http/server.py
@@ -93,6 +93,7 @@ import email.utils
 import html
 import http.client
 import io
+import itertools
 import mimetypes
 import os
 import posixpath
@@ -562,6 +563,10 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):
 
         self.log_message(format, *args)
 
+    # 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))})
+
     def log_message(self, format, *args):
         """Log an arbitrary message.
 
@@ -577,12 +582,16 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):
         The client ip and current date/time are prefixed to
         every message.
 
+        Unicode control characters are replaced with escaped hex
+        before writing the output to stderr.
+
         """
 
+        message = format % args
         sys.stderr.write("%s - - [%s] %s\n" %
                          (self.address_string(),
                           self.log_date_time_string(),
-                          format%args))
+                          message.translate(self._control_char_table)))
 
     def version_string(self):
         """Return the server software version string."""