[PATCH 2 of 2 stable] hgweb: encode WSGI environment like OS environment

[Manuel Jacob]

# HG changeset patch
# User Manuel Jacob <me at manueljacob.de>
# Date 1593049567 -7200
#      Thu Jun 25 03:46:07 2020 +0200
# Branch stable
# Node ID c115cca2d19d55c2538def5c95a68ceff597f45d
# Parent  8f730a30fb20a104bbf5665e1f7d0d4e4aaedf6f
# EXP-Topic cgi_env_encoding
hgweb: encode WSGI environment like OS environment

Previously, the WSGI environment keys and values were encoded using latin-1.
This resulted in a crash if a WSGI environment key or value could not be encoded
using latin-1.

On Unix, the OS environment is byte-based. Therefore we should do the reverse of
what Python does for os.environ.

On Windows, there’s no native byte-based OS environment. Therefore we should do
the same as what mercurial.encoding does with the OS environment.

diff --git a/mercurial/hgweb/request.py b/mercurial/hgweb/request.py
--- a/mercurial/hgweb/request.py
+++ b/mercurial/hgweb/request.py
@@ -8,10 +8,13 @@
 
 from __future__ import absolute_import
 
+import sys
+
 # import wsgiref.validate
 
 from ..thirdparty import attr
 from .. import (
+    encoding,
     error,
     pycompat,
     util,
@@ -162,10 +165,18 @@
     # strings on Python 3 must be between \00000-\000FF. We deal with bytes
     # in Mercurial, so mass convert string keys and values to bytes.
     if pycompat.ispy3:
+        fsencoding = sys.getfilesystemencoding()
+
         def tobytes(s):
             if not isinstance(s, str):
                 return s
-            return s.encode('latin-1')
+            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 s.encode(fsencoding, 'surrogateescape')
+
         env = {tobytes(k): tobytes(v) for k, v in pycompat.iteritems(env)}
 
     # Some hosting solutions are emulating hgwebdir, and dispatching directly
diff --git a/tests/test-wsgirequest.py b/tests/test-wsgirequest.py
--- a/tests/test-wsgirequest.py
+++ b/tests/test-wsgirequest.py
@@ -3,7 +3,7 @@
 import unittest
 
 from mercurial.hgweb import request as requestmod
-from mercurial import error
+from mercurial import error, pycompat
 
 DEFAULT_ENV = {
     'REQUEST_METHOD': 'GET',
@@ -432,6 +432,18 @@
         self.assertEqual(r.dispatchpath, b'path1/path2')
         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)
+
 
 if __name__ == '__main__':
     import silenttestrunner