[gentoo-portage-dev] [PATCH] pym/portage/util/locale.py: add a C module to check locale

[Anthony G. Basile]

From: "Anthony G. Basile" <blueness@g.o>

The current method to check for the system locale is to use python's
ctype.util.find_library() to construct a full library path to the
system libc.so which is then passed to ctypes.CDLL().  However,
this gets bogged down in implementation dependant details and
fails with musl.

We work around this design flaw in ctypes with a small python module
written in C called 'portage_c_check_locale', and only fall back on
the current ctype-based check when this module is not available.

Since this is the first python module written in C included in portage,
as a side effect, we introduce the machinary for future modules in
setup.py.

X-Gentoo-bug: 571444
X-Gentoo-bug-url: https://bugs.gentoo.org/show_bug.cgi?id=571444
---
 pym/portage/util/locale.py |  36 +++++++++---
 setup.py                   |   9 ++-
 src/check_locale.c         | 139 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 174 insertions(+), 10 deletions(-)
 create mode 100644 src/check_locale.c

diff --git a/pym/portage/util/locale.py b/pym/portage/util/locale.py
index 2a15ea1..ed97f61 100644
--- a/pym/portage/util/locale.py
+++ b/pym/portage/util/locale.py
@@ -30,17 +30,17 @@ locale_categories = (
 _check_locale_cache = {}
 
 
-def _check_locale(silent):
+def _ctypes_check_locale():
 	"""
-	The inner locale check function.
+	Check for locale using ctypes.
 	"""
 
 	libc_fn = find_library("c")
 	if libc_fn is None:
-		return None
+		return (None, "")
 	libc = LoadLibrary(libc_fn)
 	if libc is None:
-		return None
+		return (None, "")
 
 	lc = list(range(ord('a'), ord('z')+1))
 	uc = list(range(ord('A'), ord('Z')+1))
@@ -48,9 +48,6 @@ def _check_locale(silent):
 	ruc = [libc.toupper(c) for c in lc]
 
 	if lc != rlc or uc != ruc:
-		if silent:
-			return False
-
 		msg = ("WARNING: The LC_CTYPE variable is set to a locale " +
 			"that specifies transformation between lowercase " +
 			"and uppercase ASCII characters that is different than " +
@@ -71,11 +68,32 @@ def _check_locale(silent):
 			msg.extend([
 				"  %s -> %s" % (chars(uc), chars(rlc)),
 				"  %28s: %s" % ('expected', chars(lc))])
+		return (False, msg)
+
+	return (True, "")
+
+
+def _check_locale(silent):
+	"""
+	The inner locale check function.
+	"""
+
+	try:
+		from portage_c_check_locale import _c_check_locale
+		(ret, msg) = _c_check_locale()
+	except ImportError:
+		writemsg_level("!!! Unable to import portage_c_check_locale\n",
+			level=logging.WARNING, noiselevel=-1)
+		(ret, msg) = _ctypes_check_locale()
+
+	if ret:
+		return True
+
+	if not silent:
 		writemsg_level("".join(["!!! %s\n" % l for l in msg]),
 			level=logging.ERROR, noiselevel=-1)
-		return False
 
-	return True
+	return False
 
 
 def check_locale(silent=False, env=None):
diff --git a/setup.py b/setup.py
index b066fae..ed353a3 100755
--- a/setup.py
+++ b/setup.py
@@ -4,7 +4,7 @@
 
 from __future__ import print_function
 
-from distutils.core import setup, Command
+from distutils.core import setup, Command, Extension
 from distutils.command.build import build
 from distutils.command.build_scripts import build_scripts
 from distutils.command.clean import clean
@@ -41,6 +41,11 @@ x_scripts = {
 	],
 }
 
+x_c_helpers = {
+	'portage_c_check_locale' : [
+		'src/check_locale.c'
+	],
+}
 
 class x_build(build):
 	""" Build command with extra build_man call. """
@@ -636,6 +641,8 @@ setup(
 		['$sysconfdir/portage/repo.postsync.d', ['cnf/repo.postsync.d/example']],
 	],
 
+	ext_modules = [Extension(name=n, sources=m) for n, m in x_c_helpers.items()],
+
 	cmdclass = {
 		'build': x_build,
 		'build_man': build_man,
diff --git a/src/check_locale.c b/src/check_locale.c
new file mode 100644
index 0000000..a995028
--- /dev/null
+++ b/src/check_locale.c
@@ -0,0 +1,139 @@
+/* Copyright 2005-2015 Gentoo Foundation
+ * Distributed under the terms of the GNU General Public License v2
+ */
+
+#include <Python.h>
+#include <ctype.h>
+#include <string.h>
+
+static PyObject * portage_c_check_locale(PyObject *, PyObject *);
+
+static PyMethodDef CheckLocaleMethods[] = {
+	{"_c_check_locale", portage_c_check_locale, METH_NOARGS, "Check the system locale."},
+	{NULL, NULL, 0, NULL}
+};
+
+#if PY_MAJOR_VERSION >= 3
+static struct PyModuleDef moduledef = {
+	PyModuleDef_HEAD_INIT,
+	"portage_c_check_locale",						/* m_name */
+	"Module for checking the system locale for portage",		/* m_doc */
+	-1,								/* m_size */
+	CheckLocaleMethods,						/* m_methods */
+	NULL,								/* m_reload */
+	NULL,								/* m_traverse */
+	NULL,								/* m_clear */
+	NULL,								/* m_free */
+};
+#endif
+
+static PyObject *LocaleError;
+
+PyMODINIT_FUNC
+#if PY_MAJOR_VERSION >= 3
+PyInit_portage_c_check_locale(void)
+#else
+initportage_c_check_locale(void)
+#endif
+{
+	PyObject *m;
+
+#if PY_MAJOR_VERSION >= 3
+	m = PyModule_Create(&moduledef);
+#else
+	m = Py_InitModule("portage_c_check_locale", CheckLocaleMethods);
+#endif
+
+	if (m == NULL)
+#if PY_MAJOR_VERSION >= 3
+		return NULL;
+#else
+		return;
+#endif
+
+	LocaleError = PyErr_NewException("locale.LocaleError", NULL, NULL);
+	Py_INCREF(LocaleError);
+	PyModule_AddObject(m, "LocaleError", LocaleError);
+
+#if PY_MAJOR_VERSION >= 3
+	return m;
+#else
+	return;
+#endif
+}
+
+
+static void
+error_msg(char msg[], int c[], int rc[], int ac[])
+{
+	int i, p;
+
+	strcat(msg, "  ");
+	p = strlen(msg);
+	for (i = 'a'; i <= 'z'; i++)
+		msg[p++] = c[i-'a'];
+
+	strcat(msg, " -> ");
+	p = strlen(msg);
+	for (i = 'a'; i <= 'z'; i++)
+		msg[p++] = rc[i-'a'];
+	strcat(msg, "\n");
+
+	strcat(msg, "                      expected: ");
+	p = strlen(msg);
+	for (i = 'a'; i <= 'z'; i++)
+		msg[p++] = ac[i-'a'];
+	strcat(msg, "\n\n");
+}
+
+
+static PyObject *
+portage_c_check_locale(PyObject *self, PyObject *args)
+{
+	int i, upper = 1, lower = 1;
+	int lc[26], uc[26], rlc[26], ruc[26];
+	char msg[1024];
+
+	memset(msg, 0, 1024);
+
+	for (i = 'a'; i <= 'z'; i++) {
+		lc[i-'a'] = i;
+		ruc[i-'a'] = toupper(i);
+	}
+
+	for (i = 'A'; i <= 'Z'; i++) {
+		uc[i-'A'] = i;
+		rlc[i-'A'] = tolower(i);
+	}
+
+	for (i = 'a'; i <= 'z'; i++)
+		if(lc[i-'a'] != rlc[i-'a']) {
+			lower = 0;
+			break;
+		}
+
+	for (i = 'A'; i <= 'Z'; i++)
+		if(uc[i-'A'] != ruc[i-'A']) {
+			upper = 0;
+			break;
+		}
+
+	if (lower == 0 || upper == 0) {
+		strcpy(msg,
+			"WARNING: The LC_CTYPE variable is set to a locale that specifies\n"
+			"transformation between lowercase and uppercase ASCII characters that\n"
+			"is different than the one specified by POSIX locale. This can break\n"
+			"ebuilds and cause issues in programs that rely on the common character\n"
+			"conversion scheme.  Please consider enabling another locale (such as\n"
+			"en_US.UTF-8) in /etc/locale.gen and setting it as LC_CTYPE in make.conf.\n\n"
+		);
+
+		if (lower == 0)
+			error_msg(msg, lc, ruc, uc);
+
+		if (upper == 0)
+			error_msg(msg, uc, rlc, lc);
+	}
+
+	return Py_BuildValue("is", lower && upper, msg);
+}
-- 
2.7.3