[gentoo-portage-dev] [PATCH 1/2] Warn if LC_CTYPE does not transform ASCII chars like POSIX

[Michał Górny]

Output a warning if LC_CTYPE is set to a value that causes libc
toupper() and/or tolower() conversions not apply correctly to printable
ASCII characters.
---
 pym/_emerge/actions.py     |  3 +++
 pym/portage/util/locale.py | 63 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)
 create mode 100644 pym/portage/util/locale.py

diff --git a/pym/_emerge/actions.py b/pym/_emerge/actions.py
index 7f1cb59..e03e8d4 100644
--- a/pym/_emerge/actions.py
+++ b/pym/_emerge/actions.py
@@ -27,6 +27,7 @@ portage.proxy.lazyimport.lazyimport(globals(),
 	'portage.debug',
 	'portage.news:count_unread_news,display_news_notifications',
 	'portage.util._get_vm_info:get_vm_info',
+	'portage.util.locale:check_locale',
 	'portage.emaint.modules.sync.sync:SyncRepos',
 	'_emerge.chk_updated_cfg_files:chk_updated_cfg_files',
 	'_emerge.help:help@emerge_help',
@@ -2467,6 +2468,8 @@ def validate_ebuild_environment(trees):
 		for line in textwrap.wrap(msg, 65):
 			out.ewarn(line)
 
+	check_locale()
+
 def check_procfs():
 	procfs_path = '/proc'
 	if platform.system() not in ("Linux",) or \
diff --git a/pym/portage/util/locale.py b/pym/portage/util/locale.py
new file mode 100644
index 0000000..6919ceb
--- /dev/null
+++ b/pym/portage/util/locale.py
@@ -0,0 +1,63 @@
+#-*- coding:utf-8 -*-
+# Copyright 2015 Gentoo Foundation
+# Distributed under the terms of the GNU General Public License v2
+"""
+Function to check whether the current used LC_CTYPE handles case
+transformations of ASCII characters in a way compatible with the POSIX
+locale.
+get_ro_checker().
+"""
+from __future__ import unicode_literals
+
+import logging
+import textwrap
+
+from portage.util import writemsg_level
+from portage.util._ctypes import find_library, LoadLibrary
+
+
+def check_locale():
+	"""
+	Check whether the locale is sane. Returns True if it is, prints
+	warning and returns False if it is not. Returns None if the check
+	can not be executed due to platform limitations.
+	"""
+
+	libc_fn = find_library("c")
+	if libc_fn is None:
+		return None
+	libc = LoadLibrary(libc_fn)
+	if libc is None:
+		return None
+
+	lc = list(range(ord('a'), ord('z')+1))
+	uc = list(range(ord('A'), ord('Z')+1))
+	rlc = [libc.tolower(c) for c in uc]
+	ruc = [libc.toupper(c) for c in lc]
+
+	if lc != rlc or uc != ruc:
+		msg = ("WARNING: The LC_CTYPE variable is set to a locale " +
+			"that specifies transformation between lowercase " +
+			"and uppercase ASCII characters that is different than " +
+			"the one specified by POSIX locale. This can break " +
+			"ebuilds and cause issues in programs that rely on " +
+			"the common character conversion scheme. " +
+			"Please consider enabling another locale (such as " +
+			"en_US.UTF-8) in /etc/locale.gen and setting it " +
+			"as LC_CTYPE in make.conf.")
+		msg = [l for l in textwrap.wrap(msg, 70)]
+		msg.append("")
+		chars = lambda l: ''.join(chr(x) for x in l)
+		if uc != ruc:
+			msg.extend([
+				"  %s -> %s" % (chars(lc), chars(ruc)),
+				"  %28s: %s" % ('expected', chars(uc))])
+		if lc != rlc:
+			msg.extend([
+				"  %s -> %s" % (chars(uc), chars(rlc)),
+				"  %28s: %s" % ('expected', chars(lc))])
+		writemsg_level("".join(["!!! %s\n" % l for l in msg]),
+			level=logging.ERROR, noiselevel=-1)
+		return False
+
+	return True
-- 
2.6.3