curses: do not initialize LC_ALL to user settings (issue6358)

701341f57ceb moved the setlocale() call to right before curses was used. This
didn’t fully solve the problem it was supposed to solve (locale-dependent
functions, like date formatting/parsing and str methods on Python 2), but only
postponed it.

Initializing LC_CTYPE seems to be sufficient for curses to work correctly.
Therefore LC_CTYPE is set while curses is used and reset afterwards. Some
locale-dependent str methods might behave differently on Python 2 while curses
is used, but that shouldn’d be a problem.

hgext/histedit.py

@@ -201,7 +201,6 b' except ImportError:'
     termios = None
 
 import functools
-import locale
 import os
 import struct
 
@@ -1710,11 +1709,8 b' def _chistedit(ui, repo, freeargs, opts)'
         ctxs = []
         for i, r in enumerate(revs):
             ctxs.append(histeditrule(ui, repo[r], i))
-        # Curses requires setting the locale or it will default to the C
-        # locale. This sets the locale to the user's default system
-        # locale.
-        locale.setlocale(locale.LC_ALL, '')
-        rc = curses.wrapper(functools.partial(_chisteditmain, repo, ctxs))
+        with util.with_lc_ctype():
+            rc = curses.wrapper(functools.partial(_chisteditmain, repo, ctxs))
         curses.echo()
         curses.endwin()
         if rc is False:

mercurial/crecord.py

@@ -10,7 +10,6 b''
 
 from __future__ import absolute_import
 
-import locale
 import os
 import re
 import signal
@@ -574,14 +573,12 b' def chunkselector(ui, headerlist, operat'
     """
     ui.write(_(b'starting interactive selection\n'))
     chunkselector = curseschunkselector(headerlist, ui, operation)
-    # This is required for ncurses to display non-ASCII characters in
-    # default user locale encoding correctly.  --immerrr
-    locale.setlocale(locale.LC_ALL, '')
     origsigtstp = sentinel = object()
     if util.safehasattr(signal, b'SIGTSTP'):
         origsigtstp = signal.getsignal(signal.SIGTSTP)
     try:
-        curses.wrapper(chunkselector.main)
+        with util.with_lc_ctype():
+            curses.wrapper(chunkselector.main)
         if chunkselector.initexc is not None:
             raise chunkselector.initexc
         # ncurses does not restore signal handler for SIGTSTP

mercurial/util.py

@@ -22,6 +22,7 b' import errno'
 import gc
 import hashlib
 import itertools
+import locale
 import mmap
 import os
 import platform as pyplatform
@@ -3626,3 +3627,32 b' def uvarintdecodestream(fh):'
         if not (byte & 0x80):
             return result
         shift += 7
+
+
+# Passing the '' locale means that the locale should be set according to the
+# user settings (environment variables).
+# Python sometimes avoids setting the global locale settings. When interfacing
+# with C code (e.g. the curses module or the Subversion bindings), the global
+# locale settings must be initialized correctly. Python 2 does not initialize
+# the global locale settings on interpreter startup. Python 3 sometimes
+# initializes LC_CTYPE, but not consistently at least on Windows. Therefore we
+# explicitly initialize it to get consistent behavior if it's not already
+# initialized. Since CPython commit 177d921c8c03d30daa32994362023f777624b10d,
+# LC_CTYPE is always initialized. If we require Python 3.8+, we should re-check
+# if we can remove this code.
[e-mail]
+def with_lc_ctype():
+    oldloc = locale.setlocale(locale.LC_CTYPE, None)
+    if oldloc == 'C':
+        try:
+            try:
+                locale.setlocale(locale.LC_CTYPE, '')
+            except locale.Error:
+                # The likely case is that the locale from the environment
+                # variables is unknown.
+                pass
+            yield
+        finally:
+            locale.setlocale(locale.LC_CTYPE, oldloc)
+    else:
+        yield