glibc/stdlib/tst-strtod-nan-locale.c

26 lines
1 KiB
C
Raw Normal View History

Fix strtod ("NAN(I)") in Turkish locales (bug 19266). The implementations of strtod and related functions use locale-specific conversions to lower case when parsing the contents of a string NAN(n-char-sequence_opt). This has the consequence that NAN(I) is not treated as being of that form (only the initial NAN part is accepted). The syntax of n-char-sequence directly maps to the ASCII letters, digits and underscore as in identifiers, so it is unambiguous that all ASCII letters must be accepted in all locales. This patch, relative to a tree with <https://sourceware.org/ml/libc-alpha/2015-11/msg00258.html> (pending review) applied and depending on that patch, fixes this problem by checking directly for ASCII letters. This will have the side effect of no longer accepting 'İ' (dotted 'I') inside NAN() in Turkish locales, which seems appropriate (that letter wouldn't have been interpreted as having any meaning in the NaN payload anyway, as not acceptable to strtoull). Tested for x86_64 and x86. [BZ #19266] * stdlib/strtod_l.c (____STRTOF_INTERNAL): Check directly for upper case and lower case letters inside NAN(), not using TOLOWER. * stdlib/tst-strtod-nan-locale-main.c: New file. * stdlib/tst-strtod-nan-locale.c: Likewise. * stdlib/Makefile (tests): Add tst-strtod-nan-locale. [$(run-built-tests) = yes] ($(objpfx)tst-strtod-nan-locale.out): Depend on $(gen-locales). ($(objpfx)tst-strtod-nan-locale): Depend on $(libm). * wcsmbs/tst-wcstod-nan-locale.c: New file. * wcsmbs/Makefile (tests): Add tst-wcstod-nan-locale. [$(run-built-tests) = yes] ($(objpfx)tst-wcstod-nan-locale.out): Depend on $(gen-locales). ($(objpfx)tst-wcstod-nan-locale): Depend on $(libm).
2015-11-24 23:21:59 +01:00
/* Test strtod functions work with all ASCII letters in NAN(...) in
Turkish locales (bug 19266). Narrow string version.
Copyright (C) 2015-2022 Free Software Foundation, Inc.
Fix strtod ("NAN(I)") in Turkish locales (bug 19266). The implementations of strtod and related functions use locale-specific conversions to lower case when parsing the contents of a string NAN(n-char-sequence_opt). This has the consequence that NAN(I) is not treated as being of that form (only the initial NAN part is accepted). The syntax of n-char-sequence directly maps to the ASCII letters, digits and underscore as in identifiers, so it is unambiguous that all ASCII letters must be accepted in all locales. This patch, relative to a tree with <https://sourceware.org/ml/libc-alpha/2015-11/msg00258.html> (pending review) applied and depending on that patch, fixes this problem by checking directly for ASCII letters. This will have the side effect of no longer accepting 'İ' (dotted 'I') inside NAN() in Turkish locales, which seems appropriate (that letter wouldn't have been interpreted as having any meaning in the NaN payload anyway, as not acceptable to strtoull). Tested for x86_64 and x86. [BZ #19266] * stdlib/strtod_l.c (____STRTOF_INTERNAL): Check directly for upper case and lower case letters inside NAN(), not using TOLOWER. * stdlib/tst-strtod-nan-locale-main.c: New file. * stdlib/tst-strtod-nan-locale.c: Likewise. * stdlib/Makefile (tests): Add tst-strtod-nan-locale. [$(run-built-tests) = yes] ($(objpfx)tst-strtod-nan-locale.out): Depend on $(gen-locales). ($(objpfx)tst-strtod-nan-locale): Depend on $(libm). * wcsmbs/tst-wcstod-nan-locale.c: New file. * wcsmbs/Makefile (tests): Add tst-wcstod-nan-locale. [$(run-built-tests) = yes] ($(objpfx)tst-wcstod-nan-locale.out): Depend on $(gen-locales). ($(objpfx)tst-wcstod-nan-locale): Depend on $(libm).
2015-11-24 23:21:59 +01:00
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 07:40:42 +02:00
<https://www.gnu.org/licenses/>. */
Fix strtod ("NAN(I)") in Turkish locales (bug 19266). The implementations of strtod and related functions use locale-specific conversions to lower case when parsing the contents of a string NAN(n-char-sequence_opt). This has the consequence that NAN(I) is not treated as being of that form (only the initial NAN part is accepted). The syntax of n-char-sequence directly maps to the ASCII letters, digits and underscore as in identifiers, so it is unambiguous that all ASCII letters must be accepted in all locales. This patch, relative to a tree with <https://sourceware.org/ml/libc-alpha/2015-11/msg00258.html> (pending review) applied and depending on that patch, fixes this problem by checking directly for ASCII letters. This will have the side effect of no longer accepting 'İ' (dotted 'I') inside NAN() in Turkish locales, which seems appropriate (that letter wouldn't have been interpreted as having any meaning in the NaN payload anyway, as not acceptable to strtoull). Tested for x86_64 and x86. [BZ #19266] * stdlib/strtod_l.c (____STRTOF_INTERNAL): Check directly for upper case and lower case letters inside NAN(), not using TOLOWER. * stdlib/tst-strtod-nan-locale-main.c: New file. * stdlib/tst-strtod-nan-locale.c: Likewise. * stdlib/Makefile (tests): Add tst-strtod-nan-locale. [$(run-built-tests) = yes] ($(objpfx)tst-strtod-nan-locale.out): Depend on $(gen-locales). ($(objpfx)tst-strtod-nan-locale): Depend on $(libm). * wcsmbs/tst-wcstod-nan-locale.c: New file. * wcsmbs/Makefile (tests): Add tst-wcstod-nan-locale. [$(run-built-tests) = yes] ($(objpfx)tst-wcstod-nan-locale.out): Depend on $(gen-locales). ($(objpfx)tst-wcstod-nan-locale): Depend on $(libm).
2015-11-24 23:21:59 +01:00
#define CHAR char
#define SFMT "\"%s\""
#define FNPFX strto
#define L_(C) C
#include <tst-strtod-nan-locale-main.c>