changeset 50820:9ed281bbf864 stable

hgweb: encode WSGI environment using the ISO-8859-1 codec The WSGI specification (PEP 3333) specifies that on Python 3 all strings passed by the server must be of type str with code points encodable using the ISO 8859-1 codec. For some reason, I introduced a bug in 2632c1ed8f34 by applying the reverse change. Maybe I got confused because PEP 3333 says that arbitrary operating system environment variables may be contained in the WSGI environment and therefore we need to handle the WSGI environment variables like we would handle operating system environment variables. The bug mentioned in the previous paragraph and fixed by this changeset manifested e.g. in the path of the URL being encoded in the wrong way. Browsers encode non-ASCII bytes with the percent-encoding. WSGI servers will decode the percent-encoded bytes and pass them to the application as strings where each byte is mapped to the corresponding code point with the same ordinal (i.e. it is decoded using the ISO-8859-1 codec). Mercurial uses the bytes type for these strings (which makes much more sense), so we need to encode it again using the ISO-8859-1 codec. If we use another codec, it can result in nonsense.
author Manuel Jacob <me@manueljacob.de>
date Mon, 07 Aug 2023 23:12:02 +0200
parents 04d5cde28a7f
children 28c0fcff24e5
files mercurial/hgweb/request.py tests/test-wsgirequest.py
diffstat 2 files changed, 4 insertions(+), 18 deletions(-) [+]
line wrap: on
line diff
--- a/mercurial/hgweb/request.py	Mon Aug 07 11:05:43 2023 +0200
+++ b/mercurial/hgweb/request.py	Mon Aug 07 23:12:02 2023 +0200
@@ -11,7 +11,6 @@
 
 from ..thirdparty import attr
 from .. import (
-    encoding,
     error,
     pycompat,
     util,
@@ -167,13 +166,7 @@
     def tobytes(s):
         if not isinstance(s, str):
             return s
-        if pycompat.iswindows:
-            # This is what mercurial.encoding does for os.environ on
-            # Windows.
-            return encoding.strtolocal(s)
-        else:
-            # This is what is documented to be used for os.environ on Unix.
-            return pycompat.fsencode(s)
+        return s.encode('iso8859-1')
 
     env = {tobytes(k): tobytes(v) for k, v in env.items()}
 
--- a/tests/test-wsgirequest.py	Mon Aug 07 11:05:43 2023 +0200
+++ b/tests/test-wsgirequest.py	Mon Aug 07 23:12:02 2023 +0200
@@ -500,16 +500,9 @@
         self.assertEqual(r.reponame, b'repo')
 
     def testenvencoding(self):
-        if pycompat.iswindows:
-            # On Windows, we can't generally know which non-ASCII characters
-            # are supported.
-            r = parse(DEFAULT_ENV, extra={'foo': 'bar'})
-            self.assertEqual(r.rawenv[b'foo'], b'bar')
-        else:
-            # Unix is byte-based. Therefore we test all possible bytes.
-            b = b''.join(pycompat.bytechr(i) for i in range(256))
-            r = parse(DEFAULT_ENV, extra={'foo': pycompat.fsdecode(b)})
-            self.assertEqual(r.rawenv[b'foo'], b)
+        b = b''.join(pycompat.bytechr(i) for i in range(256))
+        r = parse(DEFAULT_ENV, extra={'foo': b.decode('iso8859-1')})
+        self.assertEqual(r.rawenv[b'foo'], b)
 
 
 if __name__ == '__main__':