[PATCH] encoding: improve handling of buggy getpreferredencoding() on Mac OS X

[Dan Villiom Podlaski Christiansen]

# HG changeset patch
# User Dan Villiom Podlaski Christiansen <danchr at gmail.com>
# Date 1281742254 -7200
# Node ID ec4a47b5db217863cd175e1e0aea51e4d7c17444
# Parent  22cef2ef536169892e9a9c4380b5f0f9c17dbf39
encoding: improve handling of buggy getpreferredencoding() on Mac OS X

Prior to version 2.7, calling locale.getpreferredencoding() would
always return 'mac-roman' on Mac OS X. Previously, this was handled by
a call to locale.setlocale(). Unfortunately, Python 2.6.5 and older
have a bug where isspace() would incorrectly report True for 0x85 and
0xa0 after such a call.

In order to fix this, we replace the previous _encodingfixup mapping
to an _encodingfixers mapping. Rather than mapping encodings to their
replacement, it maps them to a function returning the
replacement. This allows us to provide an simplified implementation of
getpreferredencoding() which extracts the expected encoding and
restores the locale.

This fix is based on a patch originally submitted by Martijn Pieters
as well as feedback from Brodie Rao.

diff --git a/mercurial/encoding.py b/mercurial/encoding.py
--- a/mercurial/encoding.py
+++ b/mercurial/encoding.py
@@ -8,21 +8,41 @@
 import error
 import sys, unicodedata, locale, os
 
-_encodingfixup = {'646': 'ascii', 'ANSI_X3.4-1968': 'ascii'}
+def _getpreferredencoding():
+    '''
+    On darwin, getpreferredencoding ignores the locale environment and
+    always returns mac-roman. http://bugs.python.org/issue6202 fixes this
+    for Python 2.7 and up. This is the same corrected code for earlier
+    Python versions.
+
+    However, we can't use a version check for this method, as some distributions 
+    patch Python to fix this. Instead, we use it as a 'fixer' for the mac-roman
+    encoding, as it is unlikely that this encoding is the actually expected.
+    '''
+    try:
+        locale.CODESET
+    except AttributeError:
+        # Fall back to parsing environment variables :-(
+        return locale.getdefaultlocale()[1]
+
+    oldloc = locale.setlocale(locale.LC_CTYPE)
+    locale.setlocale(locale.LC_CTYPE, "")
+    result = locale.nl_langinfo(locale.CODESET)
+    locale.setlocale(locale.LC_CTYPE, oldloc)
+
+    return result
+
+_encodingfixers = {
+    '646': lambda: 'ascii',
+    'ANSI_X3.4-1968': lambda: 'ascii',
+    'mac-roman': _getpreferredencoding
+}
 
 try:
     encoding = os.environ.get("HGENCODING")
-    if sys.platform == 'darwin' and not encoding:
-        # On darwin, getpreferredencoding ignores the locale environment and
-        # always returns mac-roman. We override this if the environment is
-        # not C (has been customized by the user).
-        lc = locale.setlocale(locale.LC_CTYPE, '')
-        if lc == 'UTF-8':
-            locale.setlocale(locale.LC_CTYPE, 'en_US.UTF-8')
-        encoding = locale.getlocale()[1]
     if not encoding:
         encoding = locale.getpreferredencoding() or 'ascii'
-        encoding = _encodingfixup.get(encoding, encoding)
+        encoding = _encodingfixers.get(encoding, lambda: encoding)()
 except locale.Error:
     encoding = 'ascii'
 encodingmode = os.environ.get("HGENCODINGMODE", "strict")