Shorten the grammar comment and only rstrip the chunk-size line

Author: metsw24-max

Lib/http/client.py

@@ -158,10 +158,8 @@
 # to prevent http header injection.
 _contains_disallowed_method_pchar_re = re.compile('[\x00-\x1f]')
 
-# RFC 9112: Content-Length = 1*DIGIT and chunk-size = 1*HEXDIG.  int() is more
-# permissive (it accepts a leading sign, underscores, surrounding whitespace
-# and, in base 16, an "0x" prefix and non-ASCII digits), so the body-framing
-# values are matched against the grammar before being passed to int().
+# RFC 9112: Content-Length = 1*DIGIT and chunk-size = 1*HEXDIG.
+# int() is more permissive, so we match against the grammar before calling it.
 _is_legal_content_length = re.compile(r'[0-9]+').fullmatch
 _is_legal_chunk_size = re.compile(rb'[0-9a-fA-F]+').fullmatch
 
@@ -551,7 +549,7 @@ def _read_next_chunk_size(self):
         i = line.find(b";")
         if i >= 0:
             line = line[:i] # strip chunk-extensions
-        line = line.strip()
+        line = line.rstrip()
         try:
             if not _is_legal_chunk_size(line):
                 raise ValueError("invalid chunk size")

Lib/test/test_httplib.py

@@ -1334,9 +1334,10 @@ def test_malformed_content_length(self):
 
     def test_malformed_chunk_size(self):
         # RFC 9112: chunk-size = 1*HEXDIG.  Reject sizes that int(_, 16) accepts
-        # but the grammar forbids (a sign, an "0x" prefix or underscores).
+        # but the grammar forbids (a sign, an "0x" prefix, underscores or
+        # leading whitespace).
         start = 'HTTP/1.1 200 OK\r\nTransfer-Encoding: chunked\r\n\r\n'
-        for size in ('-5', '+5', '0x5', '1_f'):
+        for size in ('-5', '+5', '0x5', '1_f', ' 5'):
             with self.subTest(size=size):
                 sock = FakeSocket(start + '%s\r\nHELLO\r\n0\r\n\r\n' % size)
                 resp = client.HTTPResponse(sock, method="GET")