about summary refs log tree commit diff
path: root/wcsmbs
diff options
context:
space:
mode:
authorJoseph Myers <joseph@codesourcery.com>2015-11-23 08:50:53 +0000
committerJoseph Myers <joseph@codesourcery.com>2015-11-23 08:50:53 +0000
commitf5eee5c72b2ab56f3faf4f46729fe82805efde68 (patch)
tree5835c3e294687c8019b6396ffef2fc758ecf4d66 /wcsmbs
parentf549f0bcba7196a2afc51657c536bbc131a7c544 (diff)
downloadglibc-f5eee5c72b2ab56f3faf4f46729fe82805efde68.tar.gz
glibc-f5eee5c72b2ab56f3faf4f46729fe82805efde68.tar.xz
glibc-f5eee5c72b2ab56f3faf4f46729fe82805efde68.zip
Fix strtol in Turkish locales (bug 19242).
The implementations of strtol and related functions use
locale-specific conversions to upper case before determining whether a
character is a valid letter in the argument.  This means that in
Turkish locales such as tr_TR.UTF-8 and tr_TR.ISO-8859-9, "i" is
interpreted as not being a valid number, when if the base passed to
strtol is 19 or more it should be interpreted as the number 18.

ISO C explicitly says "The letters from a (or A) through z (or Z) are
ascribed the values 10 through 35", so clearly intends the standard
ASCII letters (otherwise you wouldn't generally have exactly 26
letters to ascribe such values) (whereas white-space must be
identified according to the locale).  In particular, 'i' and 'I' must
be understood to be in that sequence.

This patch makes the code do the case conversions and classification
in the C locale; the user's locale remains used for whitespace testing
(explicitly correct according to ISO C).  Note that the way the code
worked, the only non-ASCII letter that would previously have been
accepted would have been the Turkish 'ı' (dotless 'i'), because the
uppercase version of that in Turkish locales is 'I'.  This patch means
that will no longer be accepted, which seems appropriate.

Tested for x86_64 and x86.

	[BZ #19242]
	* stdlib/strtol_l.c (ISALPHA): Use _nl_C_locobj_ptr for locale.
	(TOUPPER): Likewise.
	* stdlib/tst-strtol-locale-main.c: New file.
	* stdlib/tst-strtol-locale.c: Likewise.
	* stdlib/Makefile (tests): Add tst-strtol-locale.
	[$(run-built-tests) = yes] (LOCALES): Add tr_TR.ISO-8859-9.
	[$(run-built-tests) = yes] ($(objpfx)tst-strtol-locale.out):
	Depend on $(gen-locales).
	* wcsmbs/tst-wcstol-locale.c: New file.
	* wcsmbs/Makefile (tests): Add tst-wcstol-locale.
	[$(run-built-tests) = yes] (LOCALES): Add tr_TR.UTF-8 and
	tr_TR.ISO-8859-9.
	[$(run-built-tests) = yes] ($(objpfx)tst-wcstol-locale.out):
	Depend on $(gen-locales).
Diffstat (limited to 'wcsmbs')
-rw-r--r--wcsmbs/Makefile6
-rw-r--r--wcsmbs/tst-wcstol-locale.c25
2 files changed, 29 insertions, 2 deletions
diff --git a/wcsmbs/Makefile b/wcsmbs/Makefile
index f333fa873e..c1bb9375b7 100644
--- a/wcsmbs/Makefile
+++ b/wcsmbs/Makefile
@@ -47,13 +47,14 @@ strop-tests :=  wcscmp wcsncmp wmemcmp wcslen wcschr wcsrchr wcscpy wcsnlen \
 		wcscspn wmemchr wmemset
 tests := tst-wcstof wcsmbs-tst1 tst-wcsnlen tst-btowc tst-mbrtowc \
 	 tst-wcrtomb tst-wcpncpy tst-mbsrtowcs tst-wchar-h tst-mbrtowc2 \
-	 tst-c16c32-1 wcsatcliff $(addprefix test-,$(strop-tests))
+	 tst-c16c32-1 wcsatcliff tst-wcstol-locale \
+	 $(addprefix test-,$(strop-tests))
 
 include ../Rules
 
 ifeq ($(run-built-tests),yes)
 LOCALES := de_DE.ISO-8859-1 de_DE.UTF-8 en_US.ANSI_X3.4-1968 hr_HR.ISO-8859-2 \
-	   ja_JP.EUC-JP zh_TW.EUC-TW
+	   ja_JP.EUC-JP zh_TW.EUC-TW tr_TR.UTF-8 tr_TR.ISO-8859-9
 include ../gen-locales.mk
 
 $(objpfx)tst-btowc.out: $(gen-locales)
@@ -62,6 +63,7 @@ $(objpfx)tst-mbrtowc.out: $(gen-locales)
 $(objpfx)tst-mbrtowc2.out: $(gen-locales)
 $(objpfx)tst-wcrtomb.out: $(gen-locales)
 $(objpfx)wcsmbs-tst1.out: $(gen-locales)
+$(objpfx)tst-wcstol-locale.out: $(gen-locales)
 endif
 
 CFLAGS-wcwidth.c = -I../wctype
diff --git a/wcsmbs/tst-wcstol-locale.c b/wcsmbs/tst-wcstol-locale.c
new file mode 100644
index 0000000000..ea27e8e660
--- /dev/null
+++ b/wcsmbs/tst-wcstol-locale.c
@@ -0,0 +1,25 @@
+/* Test strtol functions work with all ASCII letters in Turkish
+   locales (bug 19242).  Wide string version.
+   Copyright (C) 2015 Free Software Foundation, Inc.
+   This file is part of the GNU C Library.
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library; if not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#define CHAR wchar_t
+#define SFMT "L\"%ls\""
+#define FNPFX wcsto
+#define L_(C) L ## C
+
+#include "../stdlib/tst-strtol-locale-main.c"