diff --git a/coreutils-8.32-DIR_COLORS.patch b/coreutils-8.32-DIR_COLORS.patch index 37ce3e6..ee037bf 100644 --- a/coreutils-8.32-DIR_COLORS.patch +++ b/coreutils-8.32-DIR_COLORS.patch @@ -1,4 +1,4 @@ -From bca11e30e8a6281a8cbddc9fb196dd86ab09c955 Mon Sep 17 00:00:00 2001 +From c7b13f5e1a7ad012c510a8bdd5a8943ab4b55833 Mon Sep 17 00:00:00 2001 From: Kamil Dudka Date: Fri, 17 Jun 2016 16:58:18 +0200 Subject: [PATCH] downstream changes to default DIR_COLORS @@ -9,7 +9,7 @@ Subject: [PATCH] downstream changes to default DIR_COLORS 2 files changed, 23 insertions(+), 7 deletions(-) diff --git a/DIR_COLORS b/DIR_COLORS -index 540f6cd..b4785b6 100644 +index b465771..ad42b09 100644 --- a/DIR_COLORS +++ b/DIR_COLORS @@ -1,3 +1,7 @@ @@ -30,17 +30,17 @@ index 540f6cd..b4785b6 100644 # =================================================================== # Terminal filters # =================================================================== -@@ -70,7 +77,7 @@ DOOR 01;35 # door +@@ -69,7 +76,7 @@ DOOR 01;35 # door BLK 40;33;01 # block device driver CHR 40;33;01 # character device driver ORPHAN 40;31;01 # symlink to nonexistent file, or non-stat'able file ... -MISSING 00 # ... and the files they point to +MISSING 01;37;41 # ... and the files they point to - SETUID 37;41 # regular file that is setuid (u+s) - SETGID 30;43 # regular file that is setgid (g+s) - CAPABILITY 00 # regular file with capability (very expensive to lookup) + SETUID 37;41 # file that is setuid (u+s) + SETGID 30;43 # file that is setgid (g+s) + CAPABILITY 00 # file with capability (very expensive to lookup) diff --git a/DIR_COLORS.lightbgcolor b/DIR_COLORS.lightbgcolor -index e3b0ec3..39a0a4c 100644 +index eab6258..1627b63 100644 --- a/DIR_COLORS.lightbgcolor +++ b/DIR_COLORS.lightbgcolor @@ -1,3 +1,9 @@ @@ -63,7 +63,7 @@ index e3b0ec3..39a0a4c 100644 # =================================================================== # Terminal filters # =================================================================== -@@ -60,17 +69,17 @@ TERM xterm* +@@ -59,17 +68,17 @@ TERM xterm* #NORMAL 00 # no color code at all #FILE 00 # regular file: use no color at all RESET 0 # reset to "normal" color @@ -83,18 +83,18 @@ index e3b0ec3..39a0a4c 100644 ORPHAN 40;31;01 # symlink to nonexistent file, or non-stat'able file ... -MISSING 00 # ... and the files they point to +MISSING 01;37;41 # ... and the files they point to - SETUID 37;41 # regular file that is setuid (u+s) - SETGID 30;43 # regular file that is setgid (g+s) - CAPABILITY 00 # regular file with capability (very expensive to lookup) -@@ -79,7 +88,7 @@ OTHER_WRITABLE 34;42 # dir that is other-writable (o+w) and not sticky + SETUID 37;41 # file that is setuid (u+s) + SETGID 30;43 # file that is setgid (g+s) + CAPABILITY 00 # file with capability (very expensive to lookup) +@@ -78,7 +87,7 @@ OTHER_WRITABLE 34;42 # dir that is other-writable (o+w) and not sticky STICKY 37;44 # dir with the sticky bit set (+t) and not other-writable - # This is for regular files with execute permission: + # This is for files with execute permission: -EXEC 01;32 +EXEC 00;32 # =================================================================== # File extension attributes -- -2.49.0 +2.34.1 diff --git a/coreutils-9.9-fix-cut-test-aarch64.patch b/coreutils-9.9-fix-cut-test-aarch64.patch deleted file mode 100644 index 600f87b..0000000 --- a/coreutils-9.9-fix-cut-test-aarch64.patch +++ /dev/null @@ -1,28 +0,0 @@ -From 95044cb5eaea83d02f768feb5ab79fcf5e6ad782 Mon Sep 17 00:00:00 2001 -From: =?UTF-8?q?P=C3=A1draig=20Brady?= -Date: Mon, 22 Dec 2025 17:12:48 +0000 -Subject: [PATCH] tests: avoid false failure due to ulimit on aarch64 - -* tests/cut/cut-huge-range.sh: Add an extra 1MiB headroom, -which was seen with aarch64. -Reported at https://bugzilla.redhat.com/2424302 - -Cherry-picked-by: Lukáš Zaoral -Upstream-commit: 95044cb5eaea83d02f768feb5ab79fcf5e6ad782 ---- - tests/cut/cut-huge-range.sh | 1 + - 1 file changed, 1 insertion(+) - -diff --git a/tests/cut/cut-huge-range.sh b/tests/cut/cut-huge-range.sh -index 4bd1b129d8..98d7e8f0b9 100755 ---- a/tests/cut/cut-huge-range.sh -+++ b/tests/cut/cut-huge-range.sh -@@ -22,6 +22,7 @@ getlimits_ - - vm=$(get_min_ulimit_v_ returns_ 0 cut -b1 /dev/null) \ - || skip_ 'shell lacks ulimit, or ASAN enabled' -+vm=$(($vm+1000)) # https://bugzilla.redhat.com/2424302 - - # Ensure we can cut up to our sentinel value. - # Don't use expr to subtract one, - diff --git a/coreutils-9.9-gnulib-c23.patch b/coreutils-9.9-gnulib-c23.patch deleted file mode 100644 index 82e3899..0000000 --- a/coreutils-9.9-gnulib-c23.patch +++ /dev/null @@ -1,169 +0,0 @@ -From 891761bca1aa78336e5b18c121075b6e4696c5d4 Mon Sep 17 00:00:00 2001 -From: Paul Eggert -Date: Sun, 23 Nov 2025 00:50:40 -0800 -Subject: [PATCH] Port to C23 qualifier-generic fns like strchr -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -This ports Gnulib to strict C23 platforms that reject code -like ‘char *q = strchr (P, 'x');’ when P is a pointer to const, -because in C23 strchr is a qualifier-generic function so -strchr (P, 'x') returns char const *. -This patch does not attempt to do the following two things, -which might be useful in the future: -1. When compiling on non-C23 platforms, check user code for -portability to platforms that define qualifier-generic functions. -2. Port Gnulib to platforms that have qualifier-generic functions -not listed in the C23 standard, e.g., strchrnul. I don’t know -of any such platforms. -* lib/mbschr.c (mbschr): -* lib/memchr2.c (memchr2): -Port to C23, where functions like strchr are qualifier-generic. -* lib/c++defs.h (_GL_FUNCDECL_SYS_NAME): New macro. -* lib/c++defs.h (_GL_FUNCDECL_SYS): -* lib/stdlib.in.h (bsearch): -Use it, to prevent C23 names like strchr from acting like macros. -* lib/string.in.h (memchr, strchr, strpbrk, strrchr): -Do not #undef when GNULIB_POSIXCHECK is defined, as this could -cause conforming C23 code to fail to conform. It’s not clear why -_GL_WARN_ON_USE_CXX; perhaps it was needed but isn’t any more? -But for now, limit the removal of #undef to these four functions -where #undeffing is clearly undesirable in C23. -* lib/wchar.in.h (wmemchr): Parenthesize function name in decl, -to prevent it from acting like a macro. - -Cherry-picked-by: Lukáš Zaoral -Upstream-commit: df17f4f37ed3ca373d23ad42eae51122bdb96626 ---- - lib/c++defs.h | 12 +++++++++++- - lib/mbschr.c | 2 +- - lib/memchr2.c | 2 +- - lib/stdlib.in.h | 6 +++--- - lib/string.in.h | 4 ---- - lib/wchar.in.h | 2 +- - 6 files changed, 17 insertions(+), 11 deletions(-) - -diff --git a/lib/c++defs.h b/lib/c++defs.h -index b77979a..7384457 100644 ---- a/lib/c++defs.h -+++ b/lib/c++defs.h -@@ -127,6 +127,16 @@ - #define _GL_FUNCDECL_RPL_1(rpl_func,rettype,parameters,...) \ - _GL_EXTERN_C_FUNC __VA_ARGS__ rettype rpl_func parameters - -+/* _GL_FUNCDECL_SYS_NAME (func) expands to plain func if C++, and to -+ parenthsized func otherwise. Parenthesization is needed in C23 if -+ the function is like strchr and so is a qualifier-generic macro -+ that expands to something more complicated. */ -+#ifdef __cplusplus -+# define _GL_FUNCDECL_SYS_NAME(func) func -+#else -+# define _GL_FUNCDECL_SYS_NAME(func) (func) -+#endif -+ - /* _GL_FUNCDECL_SYS (func, rettype, parameters, [attributes]); - declares the system function, named func, with the given prototype, - consisting of return type, parameters, and attributes. -@@ -139,7 +149,7 @@ - _GL_FUNCDECL_SYS (posix_openpt, int, (int flags), _GL_ATTRIBUTE_NODISCARD); - */ - #define _GL_FUNCDECL_SYS(func,rettype,parameters,...) \ -- _GL_EXTERN_C_FUNC __VA_ARGS__ rettype func parameters -+ _GL_EXTERN_C_FUNC __VA_ARGS__ rettype _GL_FUNCDECL_SYS_NAME (func) parameters - - /* _GL_CXXALIAS_RPL (func, rettype, parameters); - declares a C++ alias called GNULIB_NAMESPACE::func -diff --git a/lib/mbschr.c b/lib/mbschr.c -index c9e14b5..6582134 100644 ---- a/lib/mbschr.c -+++ b/lib/mbschr.c -@@ -65,5 +65,5 @@ mbschr (const char *string, int c) - return NULL; - } - else -- return strchr (string, c); -+ return (char *) strchr (string, c); - } -diff --git a/lib/memchr2.c b/lib/memchr2.c -index 7493823..d7724ae 100644 ---- a/lib/memchr2.c -+++ b/lib/memchr2.c -@@ -55,7 +55,7 @@ memchr2 (void const *s, int c1_in, int c2_in, size_t n) - c2 = (unsigned char) c2_in; - - if (c1 == c2) -- return memchr (s, c1, n); -+ return (void *) memchr (s, c1, n); - - /* Handle the first few bytes by reading one byte at a time. - Do this until VOID_PTR is aligned on a longword boundary. */ -diff --git a/lib/stdlib.in.h b/lib/stdlib.in.h -index bef0aaa..fd0e1e0 100644 ---- a/lib/stdlib.in.h -+++ b/lib/stdlib.in.h -@@ -224,9 +224,9 @@ _GL_INLINE_HEADER_BEGIN - - /* Declarations for ISO C N3322. */ - #if defined __GNUC__ && __GNUC__ >= 15 && !defined __clang__ --_GL_EXTERN_C void *bsearch (const void *__key, -- const void *__base, size_t __nmemb, size_t __size, -- int (*__compare) (const void *, const void *)) -+_GL_EXTERN_C void *_GL_FUNCDECL_SYS_NAME (bsearch) -+ (const void *__key, const void *__base, size_t __nmemb, size_t __size, -+ int (*__compare) (const void *, const void *)) - _GL_ATTRIBUTE_NONNULL_IF_NONZERO (2, 3) _GL_ARG_NONNULL ((5)); - _GL_EXTERN_C void qsort (void *__base, size_t __nmemb, size_t __size, - int (*__compare) (const void *, const void *)) -diff --git a/lib/string.in.h b/lib/string.in.h -index fdcdd21..8b56acf 100644 ---- a/lib/string.in.h -+++ b/lib/string.in.h -@@ -409,7 +409,6 @@ _GL_CXXALIASWARN1 (memchr, void const *, - _GL_CXXALIASWARN (memchr); - # endif - #elif defined GNULIB_POSIXCHECK --# undef memchr - /* Assume memchr is always declared. */ - _GL_WARN_ON_USE (memchr, "memchr has platform-specific bugs - " - "use gnulib module memchr for portability" ); -@@ -674,7 +673,6 @@ _GL_WARN_ON_USE (stpncpy, "stpncpy is unportable - " - #if defined GNULIB_POSIXCHECK - /* strchr() does not work with multibyte strings if the locale encoding is - GB18030 and the character to be searched is a digit. */ --# undef strchr - /* Assume strchr is always declared. */ - _GL_WARN_ON_USE_CXX (strchr, - const char *, char *, (const char *, int), -@@ -981,7 +979,6 @@ _GL_CXXALIASWARN (strpbrk); - Even in this simple case, it does not work with multibyte strings if the - locale encoding is GB18030 and one of the characters to be searched is a - digit. */ --# undef strpbrk - _GL_WARN_ON_USE_CXX (strpbrk, - const char *, char *, (const char *, const char *), - "strpbrk cannot work correctly on character strings " -@@ -1011,7 +1008,6 @@ _GL_WARN_ON_USE (strspn, "strspn cannot work correctly on character strings " - #if defined GNULIB_POSIXCHECK - /* strrchr() does not work with multibyte strings if the locale encoding is - GB18030 and the character to be searched is a digit. */ --# undef strrchr - /* Assume strrchr is always declared. */ - _GL_WARN_ON_USE_CXX (strrchr, - const char *, char *, (const char *, int), -diff --git a/lib/wchar.in.h b/lib/wchar.in.h -index ab602a2..6be4515 100644 ---- a/lib/wchar.in.h -+++ b/lib/wchar.in.h -@@ -301,7 +301,7 @@ _GL_EXTERN_C int wcsncmp (const wchar_t *__s1, const wchar_t *__s2, size_t __n) - _GL_ATTRIBUTE_NONNULL_IF_NONZERO (1, 3) - _GL_ATTRIBUTE_NONNULL_IF_NONZERO (2, 3); - # ifndef __cplusplus --_GL_EXTERN_C wchar_t *wmemchr (const wchar_t *__s, wchar_t __wc, size_t __n) -+_GL_EXTERN_C wchar_t *(wmemchr) (const wchar_t *__s, wchar_t __wc, size_t __n) - _GL_ATTRIBUTE_NONNULL_IF_NONZERO (1, 3); - # endif - _GL_EXTERN_C wchar_t *wmemset (wchar_t *__s, wchar_t __wc, size_t __n) --- -2.52.0 - diff --git a/coreutils-CVE-2025-5278.patch b/coreutils-CVE-2025-5278.patch new file mode 100644 index 0000000..af81286 --- /dev/null +++ b/coreutils-CVE-2025-5278.patch @@ -0,0 +1,107 @@ +From 701a9bdbf78f869e0fb778ed5aede00e42517add Mon Sep 17 00:00:00 2001 +From: Pádraig Brady +Date: Tue, 20 May 2025 16:03:44 +0100 +Subject: [PATCH] sort: fix buffer under-read (CWE-127) + +* src/sort.c (begfield): Check pointer adjustment +to avoid Out-of-range pointer offset (CWE-823). +(limfield): Likewise. +* tests/sort/sort-field-limit.sh: Add a new test, +which triggers with ASAN or Valgrind. +* tests/local.mk: Reference the new test. +Fixes https://bugs.gnu.org/78507 + +(cherry picked from commit 8c9602e3a145e9596dc1a63c6ed67865814b6633) +--- + src/sort.c | 12 ++++++++++-- + tests/local.mk | 1 + + tests/sort/sort-field-limit.sh | 35 ++++++++++++++++++++++++++++++++++ + 3 files changed, 46 insertions(+), 2 deletions(-) + create mode 100755 tests/sort/sort-field-limit.sh + +diff --git a/src/sort.c b/src/sort.c +index b10183b..7af1a25 100644 +--- a/src/sort.c ++++ b/src/sort.c +@@ -1644,7 +1644,11 @@ begfield (struct line const *line, struct keyfield const *key) + ++ptr; + + /* Advance PTR by SCHAR (if possible), but no further than LIM. */ +- ptr = MIN (lim, ptr + schar); ++ size_t remaining_bytes = lim - ptr; ++ if (schar < remaining_bytes) ++ ptr += schar; ++ else ++ ptr = lim; + + return ptr; + } +@@ -1746,7 +1750,11 @@ limfield (struct line const *line, struct keyfield const *key) + ++ptr; + + /* Advance PTR by ECHAR (if possible), but no further than LIM. */ +- ptr = MIN (lim, ptr + echar); ++ size_t remaining_bytes = lim - ptr; ++ if (echar < remaining_bytes) ++ ptr += echar; ++ else ++ ptr = lim; + } + + return ptr; +diff --git a/tests/local.mk b/tests/local.mk +index 4da6756..642d225 100644 +--- a/tests/local.mk ++++ b/tests/local.mk +@@ -388,6 +388,7 @@ all_tests = \ + tests/sort/sort-debug-keys.sh \ + tests/sort/sort-debug-warn.sh \ + tests/sort/sort-discrim.sh \ ++ tests/sort/sort-field-limit.sh \ + tests/sort/sort-files0-from.pl \ + tests/sort/sort-float.sh \ + tests/sort/sort-h-thousands-sep.sh \ +diff --git a/tests/sort/sort-field-limit.sh b/tests/sort/sort-field-limit.sh +new file mode 100755 +index 0000000..52d8e1d +--- /dev/null ++++ b/tests/sort/sort-field-limit.sh +@@ -0,0 +1,35 @@ ++#!/bin/sh ++# From 7.2-9.7, this would trigger an out of bounds mem read ++ ++# Copyright (C) 2025 Free Software Foundation, Inc. ++ ++# This program is free software: you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation, either version 3 of the License, or ++# (at your option) any later version. ++ ++# This program 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 General Public License for more details. ++ ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src ++print_ver_ sort ++getlimits_ ++ ++# This issue triggers with valgrind or ASAN ++valgrind --error-exitcode=1 sort --version 2>/dev/null && ++ VALGRIND='valgrind --error-exitcode=1' ++ ++{ printf '%s\n' aa bb; } > in || framework_failure_ ++ ++_POSIX2_VERSION=200809 $VALGRIND sort +0.${SIZE_MAX}R in > out || fail=1 ++compare in out || fail=1 ++ ++_POSIX2_VERSION=200809 $VALGRIND sort +1 -1.${SIZE_MAX}R in > out || fail=1 ++compare in out || fail=1 ++ ++Exit $fail +-- +2.49.0 + diff --git a/coreutils-df-direct.patch b/coreutils-df-direct.patch index 341ee2c..f29a065 100644 --- a/coreutils-df-direct.patch +++ b/coreutils-df-direct.patch @@ -1,4 +1,4 @@ -From 91be1a584108a6a3d96f64382bbf206c4213b3db Mon Sep 17 00:00:00 2001 +From f072852456c545bd89296bc88cf59ccd63287a68 Mon Sep 17 00:00:00 2001 From: Kamil Dudka Date: Mon, 29 Mar 2010 17:20:34 +0000 Subject: [PATCH] coreutils-df-direct.patch @@ -11,10 +11,10 @@ Subject: [PATCH] coreutils-df-direct.patch create mode 100755 tests/df/direct.sh diff --git a/doc/coreutils.texi b/doc/coreutils.texi -index b420606..0ccb368 100644 +index 8f7f43e..230f1f1 100644 --- a/doc/coreutils.texi +++ b/doc/coreutils.texi -@@ -12597,6 +12597,13 @@ some systems (notably Solaris), doing this yields more up to date results, +@@ -12427,6 +12427,13 @@ some systems (notably Solaris), doing this yields more up to date results, but in general this option makes @command{df} much slower, especially when there are many or very busy file systems. @@ -29,7 +29,7 @@ index b420606..0ccb368 100644 @opindex --total @cindex grand total of file system size, usage and available space diff --git a/src/df.c b/src/df.c -index 75e638c..ef9f0a7 100644 +index 994f0e3..ceee209 100644 --- a/src/df.c +++ b/src/df.c @@ -121,6 +121,9 @@ static bool print_type; @@ -42,7 +42,7 @@ index 75e638c..ef9f0a7 100644 /* Grand total data. */ static struct fs_usage grand_fsu; -@@ -248,13 +251,15 @@ enum +@@ -247,13 +250,15 @@ enum NO_SYNC_OPTION = CHAR_MAX + 1, SYNC_OPTION, TOTAL_OPTION, @@ -59,10 +59,10 @@ index 75e638c..ef9f0a7 100644 {"inodes", no_argument, nullptr, 'i'}, {"human-readable", no_argument, nullptr, 'h'}, {"si", no_argument, nullptr, 'H'}, -@@ -571,7 +576,10 @@ get_header (void) - for (idx_t col = 0; col < ncolumns; col++) +@@ -574,7 +579,10 @@ get_header (void) + for (col = 0; col < ncolumns; col++) { - char *cell; + char *cell = nullptr; - char const *header = _(columns[col]->caption); + char const *header = (columns[col]->field == TARGET_FIELD + && direct_statfs)? @@ -71,7 +71,7 @@ index 75e638c..ef9f0a7 100644 if (columns[col]->field == SIZE_FIELD && (header_mode == DEFAULT_MODE -@@ -1446,6 +1454,17 @@ get_point (char const *point, const struct stat *statp) +@@ -1471,6 +1479,17 @@ get_point (char const *point, const struct stat *statp) static void get_entry (char const *name, struct stat const *statp) { @@ -89,7 +89,7 @@ index 75e638c..ef9f0a7 100644 if ((S_ISBLK (statp->st_mode) || S_ISCHR (statp->st_mode)) && get_device (name)) return; -@@ -1516,6 +1535,7 @@ or all file systems by default.\n\ +@@ -1541,6 +1560,7 @@ or all file systems by default.\n\ -B, --block-size=SIZE scale sizes by SIZE before printing them; e.g.,\n\ '-BM' prints sizes in units of 1,048,576 bytes;\n\ see SIZE format below\n\ @@ -97,7 +97,7 @@ index 75e638c..ef9f0a7 100644 -h, --human-readable print sizes in powers of 1024 (e.g., 1023M)\n\ -H, --si print sizes in powers of 1000 (e.g., 1.1G)\n\ "), stdout); -@@ -1610,6 +1630,9 @@ main (int argc, char **argv) +@@ -1631,6 +1651,9 @@ main (int argc, char **argv) xstrtol_fatal (e, oi, c, long_options, optarg); } break; @@ -107,7 +107,7 @@ index 75e638c..ef9f0a7 100644 case 'i': if (header_mode == OUTPUT_MODE) { -@@ -1706,6 +1729,13 @@ main (int argc, char **argv) +@@ -1727,6 +1750,13 @@ main (int argc, char **argv) } } @@ -183,5 +183,5 @@ index 0000000..8e4cfb8 + +Exit $fail -- -2.52.0 +2.44.0 diff --git a/coreutils-i18n.patch b/coreutils-i18n.patch index 83579e9..81df920 100644 --- a/coreutils-i18n.patch +++ b/coreutils-i18n.patch @@ -1,4 +1,4 @@ -From a81b096084524e9aeef5e8b81fc829eb9efec581 Mon Sep 17 00:00:00 2001 +From 3ca26b2b340953a0193409c1153801775d61e352 Mon Sep 17 00:00:00 2001 From: rpm-build Date: Wed, 30 Aug 2023 17:19:58 +0200 Subject: [PATCH] coreutils-i18n.patch @@ -7,31 +7,39 @@ Subject: [PATCH] coreutils-i18n.patch bootstrap.conf | 2 + configure.ac | 6 + lib/linebuffer.h | 8 + + lib/mbchar.c | 23 ++ + lib/mbchar.h | 373 +++++++++++++++++ lib/mbfile.c | 20 + - lib/mbfile.h | 283 +++++++++++++ - m4/mbfile.m4 | 16 + + lib/mbfile.h | 267 ++++++++++++ + m4/mbchar.m4 | 13 + + m4/mbfile.m4 | 14 + src/cut.c | 508 +++++++++++++++++++++-- src/expand-common.c | 114 ++++++ src/expand-common.h | 12 + src/expand.c | 90 +++- + src/fold.c | 311 ++++++++++++-- src/local.mk | 4 +- src/pr.c | 443 ++++++++++++++++++-- - src/sort.c | 791 +++++++++++++++++++++++++++++++++--- - src/unexpand.c | 101 ++++- + src/sort.c | 792 +++++++++++++++++++++++++++++++++--- + src/unexpand.c | 102 ++++- tests/Coreutils.pm | 3 + tests/expand/mb.sh | 183 +++++++++ tests/i18n/sort.sh | 29 ++ tests/local.mk | 4 + tests/misc/expand.pl | 42 ++ + tests/misc/fold.pl | 50 ++- tests/misc/sort-mb-tests.sh | 45 ++ tests/misc/unexpand.pl | 39 ++ tests/pr/pr-tests.pl | 49 +++ tests/sort/sort-merge.pl | 42 ++ tests/sort/sort.pl | 40 +- tests/unexpand/mb.sh | 172 ++++++++ - 25 files changed, 2879 insertions(+), 167 deletions(-) + 30 files changed, 3604 insertions(+), 196 deletions(-) + create mode 100644 lib/mbchar.c + create mode 100644 lib/mbchar.h create mode 100644 lib/mbfile.c create mode 100644 lib/mbfile.h + create mode 100644 m4/mbchar.m4 create mode 100644 m4/mbfile.m4 create mode 100644 tests/expand/mb.sh create mode 100644 tests/i18n/sort.sh @@ -39,23 +47,23 @@ Subject: [PATCH] coreutils-i18n.patch create mode 100644 tests/unexpand/mb.sh diff --git a/bootstrap.conf b/bootstrap.conf -index ec68ac8..ec2fbbe 100644 +index 126e1e8..b4ccebf 100644 --- a/bootstrap.conf +++ b/bootstrap.conf -@@ -171,6 +171,8 @@ gnulib_modules=" +@@ -163,6 +163,8 @@ gnulib_modules=" + maintainer-makefile malloc-gnu manywarnings - mbbuf + mbchar + mbfile mbrlen mbrtoc32 mbrtowc diff --git a/configure.ac b/configure.ac -index 5e99ef3..ac07577 100644 +index 9cb6ee1..1131ce3 100644 --- a/configure.ac +++ b/configure.ac -@@ -465,6 +465,12 @@ fi +@@ -504,6 +504,12 @@ fi # I'm leaving it here for now. This whole thing needs to be modernized... gl_WINSIZE_IN_PTEM @@ -69,12 +77,12 @@ index 5e99ef3..ac07577 100644 if test $gl_cv_sys_tiocgwinsz_needs_termios_h = no && \ diff --git a/lib/linebuffer.h b/lib/linebuffer.h -index ca56f80..509b7e6 100644 +index ae0d55d..5bf5350 100644 --- a/lib/linebuffer.h +++ b/lib/linebuffer.h -@@ -27,6 +27,11 @@ extern "C" { - #endif - +@@ -22,6 +22,11 @@ + # include "idx.h" + # include +/* Get mbstate_t. */ +# if HAVE_WCHAR_H @@ -84,7 +92,7 @@ index ca56f80..509b7e6 100644 /* A 'struct linebuffer' holds a line of text. */ struct linebuffer -@@ -34,6 +39,9 @@ struct linebuffer +@@ -29,6 +34,9 @@ struct linebuffer idx_t size; /* Allocated. */ idx_t length; /* Used. */ char *buffer; @@ -94,14 +102,422 @@ index ca56f80..509b7e6 100644 }; /* Initialize linebuffer LINEBUFFER for use. */ +diff --git a/lib/mbchar.c b/lib/mbchar.c +new file mode 100644 +index 0000000..d94b7c3 +--- /dev/null ++++ b/lib/mbchar.c +@@ -0,0 +1,23 @@ ++/* Copyright (C) 2001, 2006, 2009-2024 Free Software Foundation, Inc. ++ ++ This file 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. ++ ++ This file 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 this program. If not, see . */ ++ ++ ++#include ++ ++#define MBCHAR_INLINE _GL_EXTERN_INLINE ++ ++#include ++ ++#include "mbchar.h" +diff --git a/lib/mbchar.h b/lib/mbchar.h +new file mode 100644 +index 0000000..c06ef11 +--- /dev/null ++++ b/lib/mbchar.h +@@ -0,0 +1,373 @@ ++/* Multibyte character data type. ++ Copyright (C) 2001, 2005-2007, 2009-2024 Free Software Foundation, Inc. ++ ++ This file 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. ++ ++ This file 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 this program. If not, see . */ ++ ++/* Written by Bruno Haible . */ ++ ++/* A multibyte character is a short subsequence of a char* string, ++ representing a single 32-bit wide character. ++ ++ We use multibyte characters instead of 32-bit wide characters because ++ of the following goals: ++ 1) correct multibyte handling, i.e. operate according to the LC_CTYPE ++ locale, ++ 2) ease of maintenance, i.e. the maintainer needs not know all details ++ of the ISO C 99 standard, ++ 3) don't fail grossly if the input is not in the encoding set by the ++ locale, because often different encodings are in use in the same ++ countries (ISO-8859-1/UTF-8, EUC-JP/Shift_JIS, ...), ++ 4) fast in the case of ASCII characters. ++ ++ Multibyte characters are only accessed through the mb* macros. ++ ++ mb_ptr (mbc) ++ return a pointer to the beginning of the multibyte sequence. ++ ++ mb_len (mbc) ++ returns the number of bytes occupied by the multibyte sequence. ++ Always > 0. ++ ++ mb_iseq (mbc, sc) ++ returns true if mbc is the standard ASCII character sc. ++ ++ mb_isnul (mbc) ++ returns true if mbc is the nul character. ++ ++ mb_cmp (mbc1, mbc2) ++ returns a positive, zero, or negative value depending on whether mbc1 ++ sorts after, same or before mbc2. ++ ++ mb_casecmp (mbc1, mbc2) ++ returns a positive, zero, or negative value depending on whether mbc1 ++ sorts after, same or before mbc2, modulo upper/lowercase conversion. ++ ++ mb_equal (mbc1, mbc2) ++ returns true if mbc1 and mbc2 are equal. ++ ++ mb_caseequal (mbc1, mbc2) ++ returns true if mbc1 and mbc2 are equal modulo upper/lowercase conversion. ++ ++ mb_isalnum (mbc) ++ returns true if mbc is alphanumeric. ++ ++ mb_isalpha (mbc) ++ returns true if mbc is alphabetic. ++ ++ mb_isascii(mbc) ++ returns true if mbc is plain ASCII. ++ ++ mb_isblank (mbc) ++ returns true if mbc is a blank. ++ ++ mb_iscntrl (mbc) ++ returns true if mbc is a control character. ++ ++ mb_isdigit (mbc) ++ returns true if mbc is a decimal digit. ++ ++ mb_isgraph (mbc) ++ returns true if mbc is a graphic character. ++ ++ mb_islower (mbc) ++ returns true if mbc is lowercase. ++ ++ mb_isprint (mbc) ++ returns true if mbc is a printable character. ++ ++ mb_ispunct (mbc) ++ returns true if mbc is a punctuation character. ++ ++ mb_isspace (mbc) ++ returns true if mbc is a space character. ++ ++ mb_isupper (mbc) ++ returns true if mbc is uppercase. ++ ++ mb_isxdigit (mbc) ++ returns true if mbc is a hexadecimal digit. ++ ++ mb_width (mbc) ++ returns the number of columns on the output device occupied by mbc. ++ Always >= 0. ++ ++ mb_putc (mbc, stream) ++ outputs mbc on stream, a byte oriented FILE stream opened for output. ++ ++ mb_setascii (&mbc, sc) ++ assigns the standard ASCII character sc to mbc. ++ (Only available if the 'mbfile' module is in use.) ++ ++ mb_copy (&destmbc, &srcmbc) ++ copies srcmbc to destmbc. ++ ++ Here are the function prototypes of the macros. ++ ++ extern const char * mb_ptr (const mbchar_t mbc); ++ extern size_t mb_len (const mbchar_t mbc); ++ extern bool mb_iseq (const mbchar_t mbc, char sc); ++ extern bool mb_isnul (const mbchar_t mbc); ++ extern int mb_cmp (const mbchar_t mbc1, const mbchar_t mbc2); ++ extern int mb_casecmp (const mbchar_t mbc1, const mbchar_t mbc2); ++ extern bool mb_equal (const mbchar_t mbc1, const mbchar_t mbc2); ++ extern bool mb_caseequal (const mbchar_t mbc1, const mbchar_t mbc2); ++ extern bool mb_isalnum (const mbchar_t mbc); ++ extern bool mb_isalpha (const mbchar_t mbc); ++ extern bool mb_isascii (const mbchar_t mbc); ++ extern bool mb_isblank (const mbchar_t mbc); ++ extern bool mb_iscntrl (const mbchar_t mbc); ++ extern bool mb_isdigit (const mbchar_t mbc); ++ extern bool mb_isgraph (const mbchar_t mbc); ++ extern bool mb_islower (const mbchar_t mbc); ++ extern bool mb_isprint (const mbchar_t mbc); ++ extern bool mb_ispunct (const mbchar_t mbc); ++ extern bool mb_isspace (const mbchar_t mbc); ++ extern bool mb_isupper (const mbchar_t mbc); ++ extern bool mb_isxdigit (const mbchar_t mbc); ++ extern int mb_width (const mbchar_t mbc); ++ extern void mb_putc (const mbchar_t mbc, FILE *stream); ++ extern void mb_setascii (mbchar_t *new, char sc); ++ extern void mb_copy (mbchar_t *new, const mbchar_t *old); ++ */ ++ ++#ifndef _MBCHAR_H ++#define _MBCHAR_H 1 ++ ++/* This file uses _GL_INLINE_HEADER_BEGIN, _GL_INLINE. */ ++#if !_GL_CONFIG_H_INCLUDED ++ #error "Please include config.h first." ++#endif ++ ++#include ++#include ++ ++_GL_INLINE_HEADER_BEGIN ++#ifndef MBCHAR_INLINE ++# define MBCHAR_INLINE _GL_INLINE ++#endif ++ ++/* The longest multibyte characters, nowadays, are 4 bytes long. ++ Regardless of the values of MB_CUR_MAX and MB_LEN_MAX. */ ++#define MBCHAR_BUF_SIZE 4 ++ ++struct mbchar ++{ ++ const char *ptr; /* pointer to current character */ ++ size_t bytes; /* number of bytes of current character, > 0 */ ++ bool wc_valid; /* true if wc is a valid 32-bit wide character */ ++ char32_t wc; /* if wc_valid: the current character */ ++#if defined GNULIB_MBFILE ++ char buf[MBCHAR_BUF_SIZE]; /* room for the bytes, used for file input only */ ++#endif ++}; ++ ++/* EOF (not a real character) is represented with bytes = 0 and ++ wc_valid = false. */ ++ ++typedef struct mbchar mbchar_t; ++ ++/* Access the current character. */ ++#define mb_ptr(mbc) ((mbc).ptr) ++#define mb_len(mbc) ((mbc).bytes) ++ ++/* Comparison of characters. */ ++#define mb_iseq(mbc, sc) ((mbc).wc_valid && (mbc).wc == (sc)) ++#define mb_isnul(mbc) ((mbc).wc_valid && (mbc).wc == 0) ++#define mb_cmp(mbc1, mbc2) \ ++ ((mbc1).wc_valid \ ++ ? ((mbc2).wc_valid \ ++ ? _GL_CMP ((mbc1).wc, (mbc2).wc) \ ++ : -1) \ ++ : ((mbc2).wc_valid \ ++ ? 1 \ ++ : (mbc1).bytes == (mbc2).bytes \ ++ ? memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) \ ++ : (mbc1).bytes < (mbc2).bytes \ ++ ? (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) > 0 ? 1 : -1) \ ++ : (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc2).bytes) >= 0 ? 1 : -1))) ++#define mb_casecmp(mbc1, mbc2) \ ++ ((mbc1).wc_valid \ ++ ? ((mbc2).wc_valid \ ++ ? _GL_CMP (c32tolower ((mbc1).wc), c32tolower ((mbc2).wc)) \ ++ : -1) \ ++ : ((mbc2).wc_valid \ ++ ? 1 \ ++ : (mbc1).bytes == (mbc2).bytes \ ++ ? memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) \ ++ : (mbc1).bytes < (mbc2).bytes \ ++ ? (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) > 0 ? 1 : -1) \ ++ : (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc2).bytes) >= 0 ? 1 : -1))) ++#define mb_equal(mbc1, mbc2) \ ++ ((mbc1).wc_valid && (mbc2).wc_valid \ ++ ? (mbc1).wc == (mbc2).wc \ ++ : (mbc1).bytes == (mbc2).bytes \ ++ && memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) == 0) ++#define mb_caseequal(mbc1, mbc2) \ ++ ((mbc1).wc_valid && (mbc2).wc_valid \ ++ ? c32tolower ((mbc1).wc) == c32tolower ((mbc2).wc) \ ++ : (mbc1).bytes == (mbc2).bytes \ ++ && memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) == 0) ++ ++/* , classification. */ ++#define mb_isascii(mbc) \ ++ ((mbc).wc_valid && (mbc).wc >= 0 && (mbc).wc <= 127) ++#define mb_isalnum(mbc) ((mbc).wc_valid && c32isalnum ((mbc).wc)) ++#define mb_isalpha(mbc) ((mbc).wc_valid && c32isalpha ((mbc).wc)) ++#define mb_isblank(mbc) ((mbc).wc_valid && c32isblank ((mbc).wc)) ++#define mb_iscntrl(mbc) ((mbc).wc_valid && c32iscntrl ((mbc).wc)) ++#define mb_isdigit(mbc) ((mbc).wc_valid && c32isdigit ((mbc).wc)) ++#define mb_isgraph(mbc) ((mbc).wc_valid && c32isgraph ((mbc).wc)) ++#define mb_islower(mbc) ((mbc).wc_valid && c32islower ((mbc).wc)) ++#define mb_isprint(mbc) ((mbc).wc_valid && c32isprint ((mbc).wc)) ++#define mb_ispunct(mbc) ((mbc).wc_valid && c32ispunct ((mbc).wc)) ++#define mb_isspace(mbc) ((mbc).wc_valid && c32isspace ((mbc).wc)) ++#define mb_isupper(mbc) ((mbc).wc_valid && c32isupper ((mbc).wc)) ++#define mb_isxdigit(mbc) ((mbc).wc_valid && c32isxdigit ((mbc).wc)) ++ ++/* Extra function. */ ++ ++/* Unprintable characters appear as a small box of width 1. */ ++#define MB_UNPRINTABLE_WIDTH 1 ++ ++MBCHAR_INLINE int ++mb_width_aux (char32_t wc) ++{ ++ int w = c32width (wc); ++ /* For unprintable characters, arbitrarily return 0 for control characters ++ and MB_UNPRINTABLE_WIDTH otherwise. */ ++ return (w >= 0 ? w : c32iscntrl (wc) ? 0 : MB_UNPRINTABLE_WIDTH); ++} ++ ++#define mb_width(mbc) \ ++ ((mbc).wc_valid ? mb_width_aux ((mbc).wc) : MB_UNPRINTABLE_WIDTH) ++ ++/* Output. */ ++#define mb_putc(mbc, stream) fwrite ((mbc).ptr, 1, (mbc).bytes, (stream)) ++ ++#if defined GNULIB_MBFILE ++/* Assignment. */ ++# define mb_setascii(mbc, sc) \ ++ ((mbc)->ptr = (mbc)->buf, (mbc)->bytes = 1, (mbc)->wc_valid = 1, \ ++ (mbc)->wc = (mbc)->buf[0] = (sc)) ++#endif ++ ++/* Copying a character. */ ++MBCHAR_INLINE void ++mb_copy (mbchar_t *new_mbc, const mbchar_t *old_mbc) ++{ ++#if defined GNULIB_MBFILE ++ if (old_mbc->ptr == &old_mbc->buf[0]) ++ { ++ memcpy (&new_mbc->buf[0], &old_mbc->buf[0], old_mbc->bytes); ++ new_mbc->ptr = &new_mbc->buf[0]; ++ } ++ else ++#endif ++ new_mbc->ptr = old_mbc->ptr; ++ new_mbc->bytes = old_mbc->bytes; ++ if ((new_mbc->wc_valid = old_mbc->wc_valid)) ++ new_mbc->wc = old_mbc->wc; ++} ++ ++ ++/* is_basic(c) tests whether the single-byte character c is ++ - in the ISO C "basic character set" or is one of '@', '$', and '`' ++ which ISO C 23 § 5.2.1.1.(1) guarantees to be single-byte and in ++ practice are safe to treat as basic in the execution character set, ++ or ++ - in the POSIX "portable character set", which ++ ++ equally guarantees to be single-byte. ++ This is a convenience function, and is in this file only to share code ++ between mbiter.h, mbuiter.h, and mbfile.h. */ ++#if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \ ++ && ('$' == 36) && ('%' == 37) && ('&' == 38) && ('\'' == 39) \ ++ && ('(' == 40) && (')' == 41) && ('*' == 42) && ('+' == 43) \ ++ && (',' == 44) && ('-' == 45) && ('.' == 46) && ('/' == 47) \ ++ && ('0' == 48) && ('1' == 49) && ('2' == 50) && ('3' == 51) \ ++ && ('4' == 52) && ('5' == 53) && ('6' == 54) && ('7' == 55) \ ++ && ('8' == 56) && ('9' == 57) && (':' == 58) && (';' == 59) \ ++ && ('<' == 60) && ('=' == 61) && ('>' == 62) && ('?' == 63) \ ++ && ('@' == 64) && ('A' == 65) && ('B' == 66) && ('C' == 67) \ ++ && ('D' == 68) && ('E' == 69) && ('F' == 70) && ('G' == 71) \ ++ && ('H' == 72) && ('I' == 73) && ('J' == 74) && ('K' == 75) \ ++ && ('L' == 76) && ('M' == 77) && ('N' == 78) && ('O' == 79) \ ++ && ('P' == 80) && ('Q' == 81) && ('R' == 82) && ('S' == 83) \ ++ && ('T' == 84) && ('U' == 85) && ('V' == 86) && ('W' == 87) \ ++ && ('X' == 88) && ('Y' == 89) && ('Z' == 90) && ('[' == 91) \ ++ && ('\\' == 92) && (']' == 93) && ('^' == 94) && ('_' == 95) \ ++ && ('`' == 96) && ('a' == 97) && ('b' == 98) && ('c' == 99) \ ++ && ('d' == 100) && ('e' == 101) && ('f' == 102) && ('g' == 103) \ ++ && ('h' == 104) && ('i' == 105) && ('j' == 106) && ('k' == 107) \ ++ && ('l' == 108) && ('m' == 109) && ('n' == 110) && ('o' == 111) \ ++ && ('p' == 112) && ('q' == 113) && ('r' == 114) && ('s' == 115) \ ++ && ('t' == 116) && ('u' == 117) && ('v' == 118) && ('w' == 119) \ ++ && ('x' == 120) && ('y' == 121) && ('z' == 122) && ('{' == 123) \ ++ && ('|' == 124) && ('}' == 125) && ('~' == 126) ++/* The character set is ISO-646, not EBCDIC. */ ++# define IS_BASIC_ASCII 1 ++ ++/* All locale encodings (see localcharset.h) map the characters 0x00..0x7F ++ to U+0000..U+007F, like ASCII, except for ++ CP864 different mapping of '%' ++ SHIFT_JIS different mappings of 0x5C, 0x7E ++ JOHAB different mapping of 0x5C ++ However, these characters in the range 0x20..0x7E are in the ISO C ++ "basic character set" and in the POSIX "portable character set", which ++ ISO C and POSIX guarantee to be single-byte. Thus, locales with these ++ encodings are not POSIX compliant. And they are most likely not in use ++ any more (as of 2023). */ ++# define is_basic(c) ((unsigned char) (c) < 0x80) ++ ++#else ++ ++MBCHAR_INLINE bool ++is_basic (char c) ++{ ++ switch (c) ++ { ++ case '\0': ++ case '\007': case '\010': ++ case '\t': case '\n': case '\v': case '\f': case '\r': ++ case ' ': case '!': case '"': case '#': case '$': case '%': ++ case '&': case '\'': case '(': case ')': case '*': ++ case '+': case ',': case '-': case '.': case '/': ++ case '0': case '1': case '2': case '3': case '4': ++ case '5': case '6': case '7': case '8': case '9': ++ case ':': case ';': case '<': case '=': case '>': ++ case '?': case '@': ++ case 'A': case 'B': case 'C': case 'D': case 'E': ++ case 'F': case 'G': case 'H': case 'I': case 'J': ++ case 'K': case 'L': case 'M': case 'N': case 'O': ++ case 'P': case 'Q': case 'R': case 'S': case 'T': ++ case 'U': case 'V': case 'W': case 'X': case 'Y': ++ case 'Z': ++ case '[': case '\\': case ']': case '^': case '_': case '`': ++ case 'a': case 'b': case 'c': case 'd': case 'e': ++ case 'f': case 'g': case 'h': case 'i': case 'j': ++ case 'k': case 'l': case 'm': case 'n': case 'o': ++ case 'p': case 'q': case 'r': case 's': case 't': ++ case 'u': case 'v': case 'w': case 'x': case 'y': ++ case 'z': case '{': case '|': case '}': case '~': ++ return 1; ++ default: ++ return 0; ++ } ++} ++ ++#endif ++ ++_GL_INLINE_HEADER_END ++ ++#endif /* _MBCHAR_H */ diff --git a/lib/mbfile.c b/lib/mbfile.c new file mode 100644 -index 0000000..f4e3e77 +index 0000000..8d2957b --- /dev/null +++ b/lib/mbfile.c @@ -0,0 +1,20 @@ +/* Multibyte character I/O: macros for multi-byte encodings. -+ Copyright (C) 2012-2025 Free Software Foundation, Inc. ++ Copyright (C) 2012-2023 Free Software Foundation, Inc. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as @@ -122,12 +538,12 @@ index 0000000..f4e3e77 +#include "mbfile.h" diff --git a/lib/mbfile.h b/lib/mbfile.h new file mode 100644 -index 0000000..c852f31 +index 0000000..ad61c19 --- /dev/null +++ b/lib/mbfile.h -@@ -0,0 +1,283 @@ +@@ -0,0 +1,267 @@ +/* Multibyte character I/O: macros for multi-byte encodings. -+ Copyright (C) 2001, 2005, 2009-2025 Free Software Foundation, Inc. ++ Copyright (C) 2001, 2005, 2009-2023 Free Software Foundation, Inc. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as @@ -182,7 +598,6 @@ index 0000000..c852f31 + +#include +#include -+#include +#include +#include + @@ -193,22 +608,14 @@ index 0000000..c852f31 +# define MBFILE_INLINE _GL_INLINE +#endif + -+#ifdef __cplusplus -+extern "C" { -+#endif -+ -+ -+/* Guarantee two characters of pushback. */ -+#define MBFILE_MAX_PUSHBACK 2 -+ +struct mbfile_multi { + FILE *fp; + bool eof_seen; -+ unsigned int pushback_count; /* <= MBFILE_MAX_PUSHBACK */ ++ bool have_pushback; + mbstate_t state; + unsigned int bufcount; + char buf[MBCHAR_BUF_SIZE]; -+ struct mbchar pushback[MBFILE_MAX_PUSHBACK]; ++ struct mbchar pushback; +}; + +MBFILE_INLINE void @@ -217,19 +624,19 @@ index 0000000..c852f31 + unsigned int new_bufcount; + size_t bytes; + -+ /* Return character pushed back, if there is one. */ -+ if (mbf->pushback_count > 0) -+ { -+ mb_copy (mbc, &mbf->pushback[mbf->pushback_count - 1]); -+ mbf->pushback_count--; -+ return; -+ } -+ + /* If EOF has already been seen, don't use getc. This matters if + mbf->fp is connected to an interactive tty. */ + if (mbf->eof_seen) + goto eof; + ++ /* Return character pushed back, if there is one. */ ++ if (mbf->have_pushback) ++ { ++ mb_copy (mbc, &mbf->pushback); ++ mbf->have_pushback = false; ++ return; ++ } ++ + new_bufcount = mbf->bufcount; + + /* If mbf->state is not in an initial state, some more 32-bit wide character @@ -378,10 +785,8 @@ index 0000000..c852f31 +MBFILE_INLINE void +mbfile_multi_ungetc (const struct mbchar *mbc, struct mbfile_multi *mbf) +{ -+ if (mbf->pushback_count == MBFILE_MAX_PUSHBACK) -+ abort (); -+ mb_copy (&mbf->pushback[mbf->pushback_count], mbc); -+ mbf->pushback_count++; ++ mb_copy (&mbf->pushback, mbc); ++ mbf->have_pushback = true; +} + +typedef struct mbfile_multi mb_file_t; @@ -391,7 +796,7 @@ index 0000000..c852f31 +#define mbf_init(mbf, stream) \ + ((mbf).fp = (stream), \ + (mbf).eof_seen = false, \ -+ (mbf).pushback_count = 0, \ ++ (mbf).have_pushback = false, \ + mbszero (&(mbf).state), \ + (mbf).bufcount = 0) + @@ -401,27 +806,39 @@ index 0000000..c852f31 + +#define mb_iseof(mbc) ((mbc).bytes == 0) + -+ -+#ifdef __cplusplus -+} -+#endif -+ +_GL_INLINE_HEADER_END + +#endif /* _MBFILE_H */ -diff --git a/m4/mbfile.m4 b/m4/mbfile.m4 +diff --git a/m4/mbchar.m4 b/m4/mbchar.m4 new file mode 100644 -index 0000000..1d126e0 +index 0000000..471e8c4 --- /dev/null -+++ b/m4/mbfile.m4 -@@ -0,0 +1,16 @@ -+# mbfile.m4 -+# serial 7 -+dnl Copyright (C) 2005, 2008-2025 Free Software Foundation, Inc. ++++ b/m4/mbchar.m4 +@@ -0,0 +1,13 @@ ++# mbchar.m4 serial 9 ++dnl Copyright (C) 2005-2007, 2009-2024 Free Software Foundation, Inc. ++dnl This file is free software; the Free Software Foundation ++dnl gives unlimited permission to copy and/or distribute it, ++dnl with or without modifications, as long as this notice is preserved. ++ ++dnl autoconf tests required for use of mbchar.m4 ++dnl From Bruno Haible. ++ ++AC_DEFUN([gl_MBCHAR], ++[ ++ AC_REQUIRE([AC_USE_SYSTEM_EXTENSIONS]) ++]) +diff --git a/m4/mbfile.m4 b/m4/mbfile.m4 +new file mode 100644 +index 0000000..83068a9 +--- /dev/null ++++ b/m4/mbfile.m4 +@@ -0,0 +1,14 @@ ++# mbfile.m4 serial 7 ++dnl Copyright (C) 2005, 2008-2023 Free Software Foundation, Inc. +dnl This file is free software; the Free Software Foundation +dnl gives unlimited permission to copy and/or distribute it, +dnl with or without modifications, as long as this notice is preserved. -+dnl This file is offered as-is, without any warranty. + +dnl autoconf tests required for use of mbfile.h +dnl From Bruno Haible. @@ -432,7 +849,7 @@ index 0000000..1d126e0 + : +]) diff --git a/src/cut.c b/src/cut.c -index f0effb9..36479d6 100644 +index 061e09c..6d10425 100644 --- a/src/cut.c +++ b/src/cut.c @@ -27,6 +27,11 @@ @@ -1092,7 +1509,7 @@ index f0effb9..36479d6 100644 if (have_read_stdin && fclose (stdin) == EOF) diff --git a/src/expand-common.c b/src/expand-common.c -index 14dd804..0d8eaaa 100644 +index c95998d..d4386fe 100644 --- a/src/expand-common.c +++ b/src/expand-common.c @@ -19,6 +19,7 @@ @@ -1101,9 +1518,9 @@ index 14dd804..0d8eaaa 100644 #include +#include #include "system.h" - #include "c-ctype.h" #include "fadvise.h" -@@ -132,6 +133,119 @@ set_increment_size (colno tabval) + #include "quote.h" +@@ -123,6 +124,119 @@ set_increment_size (uintmax_t tabval) return ok; } @@ -1224,10 +1641,10 @@ index 14dd804..0d8eaaa 100644 to the list of tab stops. */ extern void diff --git a/src/expand-common.h b/src/expand-common.h -index 46ef4e3..e19469b 100644 +index 1a57108..6025652 100644 --- a/src/expand-common.h +++ b/src/expand-common.h -@@ -29,6 +29,18 @@ extern idx_t max_column_width; +@@ -25,6 +25,18 @@ extern size_t max_column_width; /* The desired exit status. */ extern int exit_status; @@ -1245,9 +1662,9 @@ index 46ef4e3..e19469b 100644 + /* Add tab stop TABVAL to the end of 'tab_list'. */ extern void - add_tab_stop (colno tabval); + add_tab_stop (uintmax_t tabval); diff --git a/src/expand.c b/src/expand.c -index 5ec7ce9..65ac315 100644 +index a6176a9..60b1b8e 100644 --- a/src/expand.c +++ b/src/expand.c @@ -38,6 +38,9 @@ @@ -1308,7 +1725,7 @@ index 5ec7ce9..65ac315 100644 @@ -118,17 +143,48 @@ expand (void) /* Index in TAB_LIST of next tab stop to examine. */ - idx_t tab_index = 0; + size_t tab_index = 0; - /* Convert a line of text. */ @@ -1358,8 +1775,8 @@ index 5ec7ce9..65ac315 100644 + if (mb_iseq (c, '\t')) { /* Column the next input tab stop is on. */ - bool last_tab; -@@ -139,31 +195,33 @@ expand (void) + uintmax_t next_tab_column; +@@ -147,32 +203,34 @@ expand (void) if (putchar (' ') < 0) write_error (); @@ -1378,13 +1795,14 @@ index 5ec7ce9..65ac315 100644 + /* A leading control character could make us trip over. */ + else if (!mb_iscntrl (c)) { -- if (ckd_add (&column, column, 1)) -+ if (ckd_add (&column, column, mb_width (c))) +- column++; ++ column += mb_width (c); + if (!column) error (EXIT_FAILURE, 0, _("input line is too long")); } - convert &= convert_entire_line || !! isblank (c); -+ convert &= convert_entire_line || !! mb_isblank (c); ++ convert &= convert_entire_line || mb_isblank (c); } - if (c < 0) @@ -1401,11 +1819,414 @@ index 5ec7ce9..65ac315 100644 } } +diff --git a/src/fold.c b/src/fold.c +index 941ad11..bdc466d 100644 +--- a/src/fold.c ++++ b/src/fold.c +@@ -23,10 +23,32 @@ + #include + #include + ++/* Get mbstate_t, mbrtowc(), wcwidth(). */ ++#if HAVE_WCHAR_H ++# include ++#endif ++ ++/* Get iswprint(), iswblank(), wcwidth(). */ ++#if HAVE_WCTYPE_H ++# include ++#endif ++ + #include "system.h" + #include "fadvise.h" + #include "xdectoint.h" + ++/* MB_LEN_MAX is incorrectly defined to be 1 in at least one GCC ++ installation; work around this configuration error. */ ++#if !defined MB_LEN_MAX || MB_LEN_MAX < 2 ++# undef MB_LEN_MAX ++# define MB_LEN_MAX 16 ++#endif ++ ++/* Some systems, like BeOS, have multibyte encodings but lack mbstate_t. */ ++#if HAVE_MBRTOWC && defined mbstate_t ++# define mbrtowc(pwc, s, n, ps) (mbrtowc) (pwc, s, n, 0) ++#endif ++ + #define TAB_WIDTH 8 + + /* The official name of this program (e.g., no 'g' prefix). */ +@@ -34,20 +56,41 @@ + + #define AUTHORS proper_name ("David MacKenzie") + ++#define FATAL_ERROR(Message) \ ++ do \ ++ { \ ++ error (0, 0, (Message)); \ ++ usage (2); \ ++ } \ ++ while (0) ++ ++enum operating_mode ++{ ++ /* Fold texts by columns that are at the given positions. */ ++ column_mode, ++ ++ /* Fold texts by bytes that are at the given positions. */ ++ byte_mode, ++ ++ /* Fold texts by characters that are at the given positions. */ ++ character_mode, ++}; ++ ++/* The argument shows current mode. (Default: column_mode) */ ++static enum operating_mode operating_mode; ++ + /* If nonzero, try to break on whitespace. */ + static bool break_spaces; + +-/* If nonzero, count bytes, not column positions. */ +-static bool count_bytes; +- + /* If nonzero, at least one of the files we read was standard input. */ + static bool have_read_stdin; + +-static char const shortopts[] = "bsw:0::1::2::3::4::5::6::7::8::9::"; ++static char const shortopts[] = "bcsw:0::1::2::3::4::5::6::7::8::9::"; + + static struct option const longopts[] = + { + {"bytes", no_argument, nullptr, 'b'}, ++ {"characters", no_argument, nullptr, 'c'}, + {"spaces", no_argument, nullptr, 's'}, + {"width", required_argument, nullptr, 'w'}, + {GETOPT_HELP_OPTION_DECL}, +@@ -75,6 +118,7 @@ Wrap input lines in each FILE, writing to standard output.\n\ + + fputs (_("\ + -b, --bytes count bytes rather than columns\n\ ++ -c, --characters count characters rather than columns\n\ + -s, --spaces break at spaces\n\ + -w, --width=WIDTH use WIDTH columns instead of 80\n\ + "), stdout); +@@ -92,7 +136,7 @@ Wrap input lines in each FILE, writing to standard output.\n\ + static size_t + adjust_column (size_t column, char c) + { +- if (!count_bytes) ++ if (operating_mode != byte_mode) + { + if (c == '\b') + { +@@ -115,30 +159,14 @@ adjust_column (size_t column, char c) + to stdout, with maximum line length WIDTH. + Return true if successful. */ + +-static bool +-fold_file (char const *filename, size_t width) ++static void ++fold_text (FILE *istream, size_t width, int *saved_errno) + { +- FILE *istream; + int c; + size_t column = 0; /* Screen column where next char will go. */ + size_t offset_out = 0; /* Index in 'line_out' for next char. */ + static char *line_out = nullptr; + static size_t allocated_out = 0; +- int saved_errno; +- +- if (STREQ (filename, "-")) +- { +- istream = stdin; +- have_read_stdin = true; +- } +- else +- istream = fopen (filename, "r"); +- +- if (istream == nullptr) +- { +- error (0, errno, "%s", quotef (filename)); +- return false; +- } + + fadvise (istream, FADVISE_SEQUENTIAL); + +@@ -168,6 +196,15 @@ fold_file (char const *filename, size_t width) + bool found_blank = false; + size_t logical_end = offset_out; + ++ /* If LINE_OUT has no wide character, ++ put a new wide character in LINE_OUT ++ if column is bigger than width. */ ++ if (offset_out == 0) ++ { ++ line_out[offset_out++] = c; ++ continue; ++ } ++ + /* Look for the last blank. */ + while (logical_end) + { +@@ -214,13 +251,224 @@ fold_file (char const *filename, size_t width) + line_out[offset_out++] = c; + } + +- saved_errno = errno; ++ *saved_errno = errno; + if (!ferror (istream)) +- saved_errno = 0; ++ *saved_errno = 0; + + if (offset_out) + fwrite (line_out, sizeof (char), (size_t) offset_out, stdout); + ++} ++ ++#if HAVE_MBRTOWC ++static void ++fold_multibyte_text (FILE *istream, size_t width, int *saved_errno) ++{ ++ char buf[MB_LEN_MAX + BUFSIZ]; /* For spooling a read byte sequence. */ ++ size_t buflen = 0; /* The length of the byte sequence in buf. */ ++ char *bufpos = buf; /* Next read position of BUF. */ ++ wint_t wc; /* A gotten wide character. */ ++ size_t mblength; /* The byte size of a multibyte character which shows ++ as same character as WC. */ ++ mbstate_t state, state_bak; /* State of the stream. */ ++ int convfail = 0; /* 1, when conversion is failed. Otherwise 0. */ ++ ++ static char *line_out = NULL; ++ size_t offset_out = 0; /* Index in `line_out' for next char. */ ++ static size_t allocated_out = 0; ++ ++ int increment; ++ size_t column = 0; ++ ++ size_t last_blank_pos; ++ size_t last_blank_column; ++ int is_blank_seen; ++ int last_blank_increment = 0; ++ int is_bs_following_last_blank; ++ size_t bs_following_last_blank_num; ++ int is_cr_after_last_blank; ++ ++#define CLEAR_FLAGS \ ++ do \ ++ { \ ++ last_blank_pos = 0; \ ++ last_blank_column = 0; \ ++ is_blank_seen = 0; \ ++ is_bs_following_last_blank = 0; \ ++ bs_following_last_blank_num = 0; \ ++ is_cr_after_last_blank = 0; \ ++ } \ ++ while (0) ++ ++#define START_NEW_LINE \ ++ do \ ++ { \ ++ putchar ('\n'); \ ++ column = 0; \ ++ offset_out = 0; \ ++ CLEAR_FLAGS; \ ++ } \ ++ while (0) ++ ++ CLEAR_FLAGS; ++ memset (&state, '\0', sizeof(mbstate_t)); ++ ++ for (;; bufpos += mblength, buflen -= mblength) ++ { ++ if (buflen < MB_LEN_MAX && !feof (istream) && !ferror (istream)) ++ { ++ memmove (buf, bufpos, buflen); ++ buflen += fread (buf + buflen, sizeof(char), BUFSIZ, istream); ++ bufpos = buf; ++ } ++ ++ if (buflen < 1) ++ break; ++ ++ /* Get a wide character. */ ++ state_bak = state; ++ mblength = mbrtowc ((wchar_t *)&wc, bufpos, buflen, &state); ++ ++ switch (mblength) ++ { ++ case (size_t)-1: ++ case (size_t)-2: ++ convfail++; ++ state = state_bak; ++ /* Fall through. */ ++ ++ case 0: ++ mblength = 1; ++ break; ++ } ++ ++rescan: ++ if (convfail) ++ increment = 1; ++ else if (wc == L'\n') ++ { ++ /* preserve newline */ ++ fwrite (line_out, sizeof(char), offset_out, stdout); ++ START_NEW_LINE; ++ continue; ++ } ++ else if (operating_mode == byte_mode) /* byte mode */ ++ increment = mblength; ++ else if (operating_mode == character_mode) /* character mode */ ++ increment = 1; ++ else /* column mode */ ++ { ++ switch (wc) ++ { ++ case L'\b': ++ increment = (column > 0) ? -1 : 0; ++ break; ++ ++ case L'\r': ++ increment = -1 * column; ++ break; ++ ++ case L'\t': ++ increment = 8 - column % 8; ++ break; ++ ++ default: ++ increment = wcwidth (wc); ++ increment = (increment < 0) ? 0 : increment; ++ } ++ } ++ ++ if (column + increment > width && break_spaces && last_blank_pos) ++ { ++ fwrite (line_out, sizeof(char), last_blank_pos, stdout); ++ putchar ('\n'); ++ ++ offset_out = offset_out - last_blank_pos; ++ column = column - last_blank_column + ((is_cr_after_last_blank) ++ ? last_blank_increment : bs_following_last_blank_num); ++ memmove (line_out, line_out + last_blank_pos, offset_out); ++ CLEAR_FLAGS; ++ goto rescan; ++ } ++ ++ if (column + increment > width && column != 0) ++ { ++ fwrite (line_out, sizeof(char), offset_out, stdout); ++ START_NEW_LINE; ++ goto rescan; ++ } ++ ++ if (allocated_out < offset_out + mblength) ++ { ++ line_out = X2REALLOC (line_out, &allocated_out); ++ } ++ ++ memcpy (line_out + offset_out, bufpos, mblength); ++ offset_out += mblength; ++ column += increment; ++ ++ if (is_blank_seen && !convfail && wc == L'\r') ++ is_cr_after_last_blank = 1; ++ ++ if (is_bs_following_last_blank && !convfail && wc == L'\b') ++ ++bs_following_last_blank_num; ++ else ++ is_bs_following_last_blank = 0; ++ ++ if (break_spaces && !convfail && iswblank (wc)) ++ { ++ last_blank_pos = offset_out; ++ last_blank_column = column; ++ is_blank_seen = 1; ++ last_blank_increment = increment; ++ is_bs_following_last_blank = 1; ++ bs_following_last_blank_num = 0; ++ is_cr_after_last_blank = 0; ++ } ++ } ++ ++ *saved_errno = errno; ++ if (!ferror (istream)) ++ *saved_errno = 0; ++ ++ if (offset_out) ++ fwrite (line_out, sizeof (char), (size_t) offset_out, stdout); ++ ++} ++#endif ++ ++/* Fold file FILENAME, or standard input if FILENAME is "-", ++ to stdout, with maximum line length WIDTH. ++ Return 0 if successful, 1 if an error occurs. */ ++ ++static bool ++fold_file (char const *filename, size_t width) ++{ ++ FILE *istream; ++ int saved_errno; ++ ++ if (STREQ (filename, "-")) ++ { ++ istream = stdin; ++ have_read_stdin = 1; ++ } ++ else ++ istream = fopen (filename, "r"); ++ ++ if (istream == NULL) ++ { ++ error (0, errno, "%s", filename); ++ return false; ++ } ++ ++ /* Define how ISTREAM is being folded. */ ++#if HAVE_MBRTOWC ++ if (MB_CUR_MAX > 1) ++ fold_multibyte_text (istream, width, &saved_errno); ++ else ++#endif ++ fold_text (istream, width, &saved_errno); ++ + if (STREQ (filename, "-")) + clearerr (istream); + else if (fclose (istream) != 0 && !saved_errno) +@@ -251,7 +499,8 @@ main (int argc, char **argv) + + atexit (close_stdout); + +- break_spaces = count_bytes = have_read_stdin = false; ++ operating_mode = column_mode; ++ break_spaces = have_read_stdin = false; + + while ((optc = getopt_long (argc, argv, shortopts, longopts, nullptr)) != -1) + { +@@ -260,7 +509,15 @@ main (int argc, char **argv) + switch (optc) + { + case 'b': /* Count bytes rather than columns. */ +- count_bytes = true; ++ if (operating_mode != column_mode) ++ FATAL_ERROR (_("only one way of folding may be specified")); ++ operating_mode = byte_mode; ++ break; ++ ++ case 'c': ++ if (operating_mode != column_mode) ++ FATAL_ERROR (_("only one way of folding may be specified")); ++ operating_mode = character_mode; + break; + + case 's': /* Break at word boundaries. */ diff --git a/src/local.mk b/src/local.mk -index a8ad6b4..b0e61ec 100644 +index 96ee941..8fdb8fc 100644 --- a/src/local.mk +++ b/src/local.mk -@@ -490,8 +490,8 @@ src_base32_CPPFLAGS = -DBASE_TYPE=32 $(AM_CPPFLAGS) +@@ -450,8 +450,8 @@ src_base32_CPPFLAGS = -DBASE_TYPE=32 $(AM_CPPFLAGS) src_basenc_SOURCES = src/basenc.c src_basenc_CPPFLAGS = -DBASE_TYPE=42 $(AM_CPPFLAGS) @@ -1415,9 +2236,9 @@ index a8ad6b4..b0e61ec 100644 +src_unexpand_SOURCES = src/unexpand.c src/expand-common.c lib/mbfile.c lib/mbchar.c src_wc_SOURCES = src/wc.c - if USE_AVX512_WC_LINECOUNT + if USE_AVX2_WC_LINECOUNT diff --git a/src/pr.c b/src/pr.c -index 10b8c52..079c86c 100644 +index 09c6fa8..7552b62 100644 --- a/src/pr.c +++ b/src/pr.c @@ -312,6 +312,24 @@ @@ -1443,9 +2264,9 @@ index 10b8c52..079c86c 100644 +#endif + #include "system.h" - #include "c-ctype.h" #include "fadvise.h" -@@ -325,6 +343,18 @@ + #include "hard-locale.h" +@@ -324,6 +342,18 @@ #include "xstrtol-error.h" #include "xdectoint.h" @@ -1464,7 +2285,7 @@ index 10b8c52..079c86c 100644 /* The official name of this program (e.g., no 'g' prefix). */ #define PROGRAM_NAME "pr" -@@ -417,7 +447,20 @@ struct COLUMN +@@ -416,7 +446,20 @@ struct COLUMN typedef struct COLUMN COLUMN; @@ -1486,9 +2307,9 @@ index 10b8c52..079c86c 100644 static bool read_line (COLUMN *p); static bool print_page (void); static bool print_stored (COLUMN *p); -@@ -428,6 +471,7 @@ static void pad_across_to (int position); - static void add_line_number (COLUMN *p); - static int getoptnum (char const *n_str, int min, char const *errfmt); +@@ -428,6 +471,7 @@ static void add_line_number (COLUMN *p); + static void getoptnum (char const *n_str, int min, int *num, + char const *errfmt); static void getoptarg (char *arg, char switch_char, char *character, + int *character_length, int *character_width, int *number); @@ -1621,7 +2442,7 @@ index 10b8c52..079c86c 100644 /* Could check tab width > 0. */ tabify_output = true; break; -@@ -986,8 +1069,8 @@ main (int argc, char **argv) +@@ -985,8 +1068,8 @@ main (int argc, char **argv) case 'n': numbered_lines = true; if (optarg) @@ -1632,7 +2453,7 @@ index 10b8c52..079c86c 100644 break; case 'N': skip_count = false; -@@ -1013,6 +1096,7 @@ main (int argc, char **argv) +@@ -1011,6 +1094,7 @@ main (int argc, char **argv) /* Reset an additional input of -s, -S dominates -s */ col_sep_string = ""; col_sep_length = 0; @@ -1640,7 +2461,7 @@ index 10b8c52..079c86c 100644 use_col_separator = true; if (optarg) separator_string (optarg); -@@ -1168,7 +1252,8 @@ getoptnum (char const *n_str, int min, char const *err) +@@ -1165,7 +1249,8 @@ getoptnum (char const *n_str, int min, int *num, char const *err) a number. */ static void @@ -1650,10 +2471,10 @@ index 10b8c52..079c86c 100644 { if (!*arg) { -@@ -1177,7 +1262,41 @@ getoptarg (char *arg, char switch_char, char *character, int *number) +@@ -1174,7 +1259,41 @@ getoptarg (char *arg, char switch_char, char *character, int *number) } - if (!c_isdigit (*arg)) + if (!ISDIGIT (*arg)) - *character = *arg++; + { +#ifdef HAVE_MBRTOWC @@ -1693,7 +2514,7 @@ index 10b8c52..079c86c 100644 if (*arg) { long int tmp_long; -@@ -1206,6 +1325,11 @@ static void +@@ -1203,6 +1322,11 @@ static void init_parameters (int number_of_files) { int chars_used_by_number = 0; @@ -1705,7 +2526,7 @@ index 10b8c52..079c86c 100644 lines_per_body = lines_per_page - lines_per_header - lines_per_footer; if (lines_per_body <= 0) -@@ -1243,7 +1367,7 @@ init_parameters (int number_of_files) +@@ -1240,7 +1364,7 @@ init_parameters (int number_of_files) else col_sep_string = column_separator; @@ -1714,7 +2535,7 @@ index 10b8c52..079c86c 100644 use_col_separator = true; } /* It's rather pointless to define a TAB separator with column -@@ -1275,11 +1399,11 @@ init_parameters (int number_of_files) +@@ -1272,11 +1396,11 @@ init_parameters (int number_of_files) + TAB_WIDTH (chars_per_input_tab, chars_per_number); */ /* Estimate chars_per_text without any margin and keep it constant. */ @@ -1728,7 +2549,7 @@ index 10b8c52..079c86c 100644 /* The number is part of the column width unless we are printing files in parallel. */ -@@ -1288,7 +1412,7 @@ init_parameters (int number_of_files) +@@ -1285,7 +1409,7 @@ init_parameters (int number_of_files) } int sep_chars, useful_chars; @@ -1737,7 +2558,7 @@ index 10b8c52..079c86c 100644 sep_chars = INT_MAX; if (ckd_sub (&useful_chars, chars_per_line - chars_used_by_number, sep_chars)) -@@ -1311,7 +1435,7 @@ init_parameters (int number_of_files) +@@ -1308,7 +1432,7 @@ init_parameters (int number_of_files) We've to use 8 as the lower limit, if we use chars_per_default_tab = 8 to expand a tab which is not an input_tab-char. */ free (clump_buff); @@ -1746,7 +2567,7 @@ index 10b8c52..079c86c 100644 } /* Open the necessary files, -@@ -1417,7 +1541,7 @@ init_funcs (void) +@@ -1414,7 +1538,7 @@ init_funcs (void) /* Enlarge p->start_position of first column to use the same form of padding_not_printed with all columns. */ @@ -1755,7 +2576,7 @@ index 10b8c52..079c86c 100644 /* This loop takes care of all but the rightmost column. */ -@@ -1451,7 +1575,7 @@ init_funcs (void) +@@ -1448,7 +1572,7 @@ init_funcs (void) } else { @@ -1764,7 +2585,7 @@ index 10b8c52..079c86c 100644 h_next = h + chars_per_column; } } -@@ -1751,9 +1875,9 @@ static void +@@ -1745,9 +1869,9 @@ static void align_column (COLUMN *p) { padding_not_printed = p->start_position; @@ -1776,9 +2597,9 @@ index 10b8c52..079c86c 100644 padding_not_printed = ANYWHERE; } -@@ -2030,13 +2154,13 @@ store_char (char c) +@@ -2021,13 +2145,13 @@ store_char (char c) /* May be too generous. */ - buff = xpalloc (buff, &buff_allocated, 1, -1, sizeof *buff); + buff = X2REALLOC (buff, &buff_allocated); } - buff[buff_current++] = c; + buff[buff_current++] = (unsigned char) c; @@ -1792,7 +2613,7 @@ index 10b8c52..079c86c 100644 char *s; int num_width; -@@ -2053,22 +2177,24 @@ add_line_number (COLUMN *p) +@@ -2044,22 +2168,24 @@ add_line_number (COLUMN *p) /* Tabification is assumed for multiple columns, also for n-separators, but 'default n-separator = TAB' hasn't been given priority over equal column_width also specified by POSIX. */ @@ -1821,7 +2642,7 @@ index 10b8c52..079c86c 100644 output_position = POS_AFTER_TAB (chars_per_output_tab, output_position); } -@@ -2227,7 +2353,7 @@ print_white_space (void) +@@ -2218,7 +2344,7 @@ print_white_space (void) while (goal - h_old > 1 && (h_new = POS_AFTER_TAB (chars_per_output_tab, h_old)) <= goal) { @@ -1830,7 +2651,7 @@ index 10b8c52..079c86c 100644 h_old = h_new; } while (++h_old <= goal) -@@ -2247,6 +2373,7 @@ print_sep_string (void) +@@ -2238,6 +2364,7 @@ print_sep_string (void) { char const *s = col_sep_string; int l = col_sep_length; @@ -1838,7 +2659,7 @@ index 10b8c52..079c86c 100644 if (separators_not_printed <= 0) { -@@ -2258,6 +2385,7 @@ print_sep_string (void) +@@ -2249,6 +2376,7 @@ print_sep_string (void) { for (; separators_not_printed > 0; --separators_not_printed) { @@ -1846,7 +2667,7 @@ index 10b8c52..079c86c 100644 while (l-- > 0) { /* 3 types of sep_strings: spaces only, spaces and chars, -@@ -2271,12 +2399,15 @@ print_sep_string (void) +@@ -2262,12 +2390,15 @@ print_sep_string (void) } else { @@ -1863,7 +2684,7 @@ index 10b8c52..079c86c 100644 /* sep_string ends with some spaces */ if (spaces_not_printed > 0) print_white_space (); -@@ -2307,7 +2438,7 @@ print_clump (COLUMN *p, int n, char *clump) +@@ -2295,7 +2426,7 @@ print_clump (COLUMN *p, int n, char *clump) required number of tabs and spaces. */ static void @@ -1872,7 +2693,7 @@ index 10b8c52..079c86c 100644 { if (tabify_output) { -@@ -2331,6 +2462,74 @@ print_char (char c) +@@ -2319,6 +2450,74 @@ print_char (char c) putchar (c); } @@ -1947,7 +2768,7 @@ index 10b8c52..079c86c 100644 /* Skip to page PAGE before printing. PAGE may be larger than total number of pages. */ -@@ -2507,9 +2706,9 @@ read_line (COLUMN *p) +@@ -2495,9 +2694,9 @@ read_line (COLUMN *p) align_empty_cols = false; } @@ -1959,7 +2780,7 @@ index 10b8c52..079c86c 100644 padding_not_printed = ANYWHERE; } -@@ -2578,7 +2777,7 @@ print_stored (COLUMN *p) +@@ -2566,7 +2765,7 @@ print_stored (COLUMN *p) COLUMN *q; int line = p->current_line++; @@ -1968,7 +2789,7 @@ index 10b8c52..079c86c 100644 /* FIXME UMR: Uninitialized memory read: * This is occurring while in: -@@ -2590,7 +2789,7 @@ print_stored (COLUMN *p) +@@ -2578,7 +2777,7 @@ print_stored (COLUMN *p) xmalloc [xmalloc.c:94] init_store_cols [pr.c:1648] */ @@ -1977,7 +2798,7 @@ index 10b8c52..079c86c 100644 pad_vertically = true; -@@ -2610,9 +2809,9 @@ print_stored (COLUMN *p) +@@ -2598,9 +2797,9 @@ print_stored (COLUMN *p) } } @@ -1989,7 +2810,7 @@ index 10b8c52..079c86c 100644 padding_not_printed = ANYWHERE; } -@@ -2625,8 +2824,8 @@ print_stored (COLUMN *p) +@@ -2613,8 +2812,8 @@ print_stored (COLUMN *p) if (spaces_not_printed == 0) { output_position = p->start_position + end_vector[line]; @@ -2000,7 +2821,7 @@ index 10b8c52..079c86c 100644 } return true; -@@ -2645,7 +2844,7 @@ print_stored (COLUMN *p) +@@ -2633,7 +2832,7 @@ print_stored (COLUMN *p) number of characters is 1.) */ static int @@ -2009,7 +2830,7 @@ index 10b8c52..079c86c 100644 { unsigned char uc = c; char *s = clump_buff; -@@ -2655,10 +2854,10 @@ char_to_clump (char c) +@@ -2643,10 +2842,10 @@ char_to_clump (char c) int chars; int chars_per_c = 8; @@ -2022,7 +2843,7 @@ index 10b8c52..079c86c 100644 { width = TAB_WIDTH (chars_per_c, input_position); -@@ -2739,6 +2938,164 @@ char_to_clump (char c) +@@ -2727,6 +2926,164 @@ char_to_clump (char c) return chars; } @@ -2188,14 +3009,13 @@ index 10b8c52..079c86c 100644 looking for more options and printing the next batch of files. diff --git a/src/sort.c b/src/sort.c -index 05d00cc..eb51f20 100644 +index 0963419..dea9457 100644 --- a/src/sort.c +++ b/src/sort.c -@@ -30,6 +30,15 @@ +@@ -29,6 +29,14 @@ + #include #include #include - #include -+ +#if HAVE_WCHAR_H +# include +#endif @@ -2207,7 +3027,7 @@ index 05d00cc..eb51f20 100644 #include "system.h" #include "argmatch.h" #include "assure.h" -@@ -160,14 +169,39 @@ static int thousands_sep; +@@ -157,14 +165,39 @@ static int thousands_sep; /* We currently ignore multi-byte grouping chars. */ static bool thousands_sep_ignored; @@ -2248,7 +3068,7 @@ index 05d00cc..eb51f20 100644 /* The kind of blanks for '-b' to skip in various options. */ enum blanktype { bl_start, bl_end, bl_both }; -@@ -344,13 +378,11 @@ static bool stable; +@@ -341,13 +374,11 @@ static bool stable; /* An int value outside char range. */ enum { NON_CHAR = CHAR_MAX + 1 }; @@ -2265,9 +3085,9 @@ index 05d00cc..eb51f20 100644 /* Flag to remove consecutive duplicate lines from the output. Only the last of a sequence of equal lines will be output. */ -@@ -386,6 +418,46 @@ struct tempnode - static struct tempnode *volatile temphead; - static struct tempnode *volatile *temptail = &temphead; +@@ -804,6 +835,46 @@ reap_all (void) + reap (-1); + } +/* Function pointers. */ +static void @@ -2312,7 +3132,7 @@ index 05d00cc..eb51f20 100644 /* Clean up any remaining temporary files. */ static void -@@ -1343,7 +1415,7 @@ zaptemp (char const *name) +@@ -1271,7 +1342,7 @@ zaptemp (char const *name) free (node); } @@ -2321,7 +3141,7 @@ index 05d00cc..eb51f20 100644 static int struct_month_cmp (void const *m1, void const *m2) -@@ -1358,7 +1430,7 @@ struct_month_cmp (void const *m1, void const *m2) +@@ -1286,7 +1357,7 @@ struct_month_cmp (void const *m1, void const *m2) /* Initialize the character class tables. */ static void @@ -2330,7 +3150,7 @@ index 05d00cc..eb51f20 100644 { size_t i; -@@ -1370,7 +1442,7 @@ inittables (void) +@@ -1298,7 +1369,7 @@ inittables (void) fold_toupper[i] = toupper (i); } @@ -2339,7 +3159,7 @@ index 05d00cc..eb51f20 100644 /* If we're not in the "C" locale, read different names for months. */ if (hard_LC_TIME) { -@@ -1450,6 +1522,84 @@ specify_nmerge (int oi, char c, char const *s) +@@ -1380,6 +1451,84 @@ specify_nmerge (int oi, char c, char const *s) xstrtol_fatal (e, oi, c, long_options, s); } @@ -2424,7 +3244,7 @@ index 05d00cc..eb51f20 100644 /* Specify the amount of main memory to use when sorting. */ static void specify_sort_size (int oi, char c, char const *s) -@@ -1676,7 +1826,7 @@ buffer_linelim (struct buffer const *buf) +@@ -1611,7 +1760,7 @@ buffer_linelim (struct buffer const *buf) by KEY in LINE. */ static char * @@ -2433,7 +3253,7 @@ index 05d00cc..eb51f20 100644 { char *ptr = line->text, *lim = ptr + line->length - 1; size_t sword = key->sword; -@@ -1685,10 +1835,10 @@ begfield (struct line const *line, struct keyfield const *key) +@@ -1620,10 +1769,10 @@ begfield (struct line const *line, struct keyfield const *key) /* The leading field separator itself is included in a field when -t is absent. */ @@ -2446,7 +3266,7 @@ index 05d00cc..eb51f20 100644 ++ptr; if (ptr < lim) ++ptr; -@@ -1718,12 +1868,71 @@ begfield (struct line const *line, struct keyfield const *key) +@@ -1653,12 +1802,71 @@ begfield (struct line const *line, struct keyfield const *key) return ptr; } @@ -2519,7 +3339,7 @@ index 05d00cc..eb51f20 100644 { char *ptr = line->text, *lim = ptr + line->length - 1; size_t eword = key->eword, echar = key->echar; -@@ -1738,10 +1947,10 @@ limfield (struct line const *line, struct keyfield const *key) +@@ -1673,10 +1881,10 @@ limfield (struct line const *line, struct keyfield const *key) 'beginning' is the first character following the delimiting TAB. Otherwise, leave PTR pointing at the first 'blank' character after the preceding field. */ @@ -2532,7 +3352,7 @@ index 05d00cc..eb51f20 100644 ++ptr; if (ptr < lim && (eword || echar)) ++ptr; -@@ -1787,10 +1996,10 @@ limfield (struct line const *line, struct keyfield const *key) +@@ -1722,10 +1930,10 @@ limfield (struct line const *line, struct keyfield const *key) */ /* Make LIM point to the end of (one byte past) the current field. */ @@ -2545,7 +3365,7 @@ index 05d00cc..eb51f20 100644 if (newlim) lim = newlim; } -@@ -1825,6 +2034,130 @@ limfield (struct line const *line, struct keyfield const *key) +@@ -1760,6 +1968,130 @@ limfield (struct line const *line, struct keyfield const *key) return ptr; } @@ -2676,7 +3496,7 @@ index 05d00cc..eb51f20 100644 /* Fill BUF reading from FP, moving buf->left bytes from the end of buf->buf to the beginning first. If EOF is reached and the file wasn't terminated by a newline, supply one. Set up BUF's line -@@ -1911,8 +2244,22 @@ fillbuf (struct buffer *buf, FILE *fp, char const *file) +@@ -1846,8 +2178,22 @@ fillbuf (struct buffer *buf, FILE *fp, char const *file) else { if (key->skipsblanks) @@ -2701,7 +3521,7 @@ index 05d00cc..eb51f20 100644 line->keybeg = line_start; } } -@@ -2050,12 +2397,10 @@ find_unit_order (char const *number) +@@ -1985,12 +2331,10 @@ find_unit_order (char const *number) ATTRIBUTE_PURE static int @@ -2717,7 +3537,7 @@ index 05d00cc..eb51f20 100644 int diff = find_unit_order (a) - find_unit_order (b); return (diff ? diff : strnumcmp (a, b, decimal_point, thousands_sep)); -@@ -2067,7 +2412,7 @@ human_numcompare (char const *a, char const *b) +@@ -2002,7 +2346,7 @@ human_numcompare (char const *a, char const *b) ATTRIBUTE_PURE static int @@ -2726,7 +3546,7 @@ index 05d00cc..eb51f20 100644 { while (blanks[to_uchar (*a)]) a++; -@@ -2077,6 +2422,25 @@ numcompare (char const *a, char const *b) +@@ -2012,6 +2356,25 @@ numcompare (char const *a, char const *b) return strnumcmp (a, b, decimal_point, thousands_sep); } @@ -2752,7 +3572,7 @@ index 05d00cc..eb51f20 100644 static int nan_compare (long double a, long double b) { -@@ -2118,7 +2482,7 @@ general_numcompare (char const *sa, char const *sb) +@@ -2053,7 +2416,7 @@ general_numcompare (char const *sa, char const *sb) Return 0 if the name in S is not recognized. */ static int @@ -2761,7 +3581,7 @@ index 05d00cc..eb51f20 100644 { size_t lo = 0; size_t hi = MONTHS_PER_YEAR; -@@ -2457,15 +2821,14 @@ debug_key (struct line const *line, struct keyfield const *key) +@@ -2380,15 +2743,14 @@ debug_key (struct line const *line, struct keyfield const *key) char saved = *lim; *lim = '\0'; @@ -2779,7 +3599,7 @@ index 05d00cc..eb51f20 100644 else if (key->general_numeric) ignore_value (strtold (beg, &tighter_lim)); else if (key->numeric || key->human_numeric) -@@ -2611,7 +2974,7 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) +@@ -2534,7 +2896,7 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) /* Warn about significant leading blanks. */ bool implicit_skip = key_numeric (key) || key->month; bool line_offset = key->eword == 0 && key->echar != 0; /* -k1.x,1.y */ @@ -2788,7 +3608,7 @@ index 05d00cc..eb51f20 100644 && ((!key->skipsblanks && !implicit_skip) || (!key->skipsblanks && key->schar) || (!key->skipeblanks && key->echar))) -@@ -2659,9 +3022,9 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) +@@ -2582,9 +2944,9 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) bool number_locale_warned = false; if (basic_numeric_field_span) { @@ -2801,7 +3621,7 @@ index 05d00cc..eb51f20 100644 { error (0, 0, _("field separator %s is treated as a " -@@ -2672,9 +3035,9 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) +@@ -2595,9 +2957,9 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) } if (basic_numeric_field_span || general_numeric_field_span) { @@ -2814,7 +3634,7 @@ index 05d00cc..eb51f20 100644 { error (0, 0, _("field separator %s is treated as a " -@@ -2682,19 +3045,19 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) +@@ -2605,19 +2967,19 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) quote (((char []) {decimal_point, 0}))); number_locale_warned = true; } @@ -2838,8 +3658,17 @@ index 05d00cc..eb51f20 100644 } } -@@ -2746,11 +3109,87 @@ diff_reversed (int diff, bool reversed) - return reversed ? _GL_CMP (0, diff) : diff; +@@ -2628,7 +2990,7 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) + { + error (0, 0, + _("%snumbers use %s as a decimal point in this locale"), +- tab == decimal_point ? "" : _("note "), ++ (tab_length && tab[0] == decimal_point) ? "" : _("note "), + quote (((char []) {decimal_point, 0}))); + + } +@@ -2670,11 +3032,87 @@ diff_reversed (int diff, bool reversed) + return reversed ? (diff < 0) - (diff > 0) : diff; } +#if HAVE_MBRTOWC @@ -2927,7 +3756,7 @@ index 05d00cc..eb51f20 100644 { struct keyfield *key = keylist; -@@ -2831,7 +3270,7 @@ keycompare (struct line const *a, struct line const *b) +@@ -2755,7 +3193,7 @@ keycompare (struct line const *a, struct line const *b) else if (key->human_numeric) diff = human_numcompare (ta, tb); else if (key->month) @@ -2936,7 +3765,7 @@ index 05d00cc..eb51f20 100644 else if (key->random) diff = compare_random (ta, tlena, tb, tlenb); else if (key->version) -@@ -2941,6 +3380,211 @@ keycompare (struct line const *a, struct line const *b) +@@ -2865,6 +3303,211 @@ keycompare (struct line const *a, struct line const *b) return diff_reversed (diff, key->reverse); } @@ -3148,7 +3977,7 @@ index 05d00cc..eb51f20 100644 /* Compare two lines A and B, returning negative, zero, or positive depending on whether A compares less than, equal to, or greater than B. */ -@@ -2968,7 +3612,7 @@ compare (struct line const *a, struct line const *b) +@@ -2892,7 +3535,7 @@ compare (struct line const *a, struct line const *b) diff = - NONZERO (blen); else if (blen == 0) diff = 1; @@ -3157,7 +3986,7 @@ index 05d00cc..eb51f20 100644 { /* xmemcoll0 is a performance enhancement as it will not unconditionally write '\0' after the -@@ -4340,6 +4984,7 @@ set_ordering (char const *s, struct keyfield *key, enum blanktype blanktype) +@@ -4280,6 +4923,7 @@ set_ordering (char const *s, struct keyfield *key, enum blanktype blanktype) break; case 'f': key->translate = fold_toupper; @@ -3165,7 +3994,7 @@ index 05d00cc..eb51f20 100644 break; case 'g': key->general_numeric = true; -@@ -4419,7 +5064,7 @@ main (int argc, char **argv) +@@ -4359,7 +5003,7 @@ main (int argc, char **argv) initialize_exit_failure (SORT_FAILURE); hard_LC_COLLATE = hard_locale (LC_COLLATE); @@ -3174,7 +4003,7 @@ index 05d00cc..eb51f20 100644 hard_LC_TIME = hard_locale (LC_TIME); #endif -@@ -4442,6 +5087,29 @@ main (int argc, char **argv) +@@ -4382,6 +5026,29 @@ main (int argc, char **argv) thousands_sep = NON_CHAR; } @@ -3204,7 +4033,7 @@ index 05d00cc..eb51f20 100644 have_read_stdin = false; inittables (); -@@ -4717,13 +5385,34 @@ main (int argc, char **argv) +@@ -4652,13 +5319,34 @@ main (int argc, char **argv) case 't': { @@ -3237,13 +4066,13 @@ index 05d00cc..eb51f20 100644 +#endif + if (newtab_length == 1 && optarg[1]) { - if (streq (optarg, "\\0")) + if (STREQ (optarg, "\\0")) - newtab = '\0'; + newtab[0] = '\0'; else { /* Provoke with 'sort -txx'. Complain about -@@ -4734,9 +5423,11 @@ main (int argc, char **argv) +@@ -4669,9 +5357,11 @@ main (int argc, char **argv) quote (optarg)); } } @@ -3258,7 +4087,7 @@ index 05d00cc..eb51f20 100644 break; diff --git a/src/unexpand.c b/src/unexpand.c -index ff234d7..7c36ef6 100644 +index aca67dd..f79c808 100644 --- a/src/unexpand.c +++ b/src/unexpand.c @@ -39,6 +39,9 @@ @@ -3271,7 +4100,7 @@ index ff234d7..7c36ef6 100644 #include "system.h" #include "expand-common.h" -@@ -105,24 +108,46 @@ unexpand (void) +@@ -105,24 +108,47 @@ unexpand (void) { /* Input stream. */ FILE *fp = next_file (nullptr); @@ -3291,27 +4120,28 @@ index ff234d7..7c36ef6 100644 if (!fp) return; - + mbf_init (mbf, fp); + found_bom=check_bom(fp,&mbf); + + if (using_utf_locale == false && found_bom == true) ++ { ++ /*try using some predefined locale */ + ++ if (set_utf_locale () != 0) + { -+ /* Try using some predefined locale */ -+ if (set_utf_locale () != 0) -+ { -+ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale")); -+ } ++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale")); + } -+ ++ } /* The worst case is a non-blank character, then one blank, then a tab stop, then MAX_COLUMN_WIDTH - 1 blanks, then a non-blank; so allocate MAX_COLUMN_WIDTH bytes to store the blanks. */ -- pending_blank = ximalloc (max_column_width); -+ pending_blank = ximalloc (max_column_width * sizeof (mbf_char_t)); +- pending_blank = xmalloc (max_column_width); ++ pending_blank = xmalloc (max_column_width * sizeof (mbf_char_t)); + + if (found_bom == true) ++ { + print_bom(); ++ } while (true) { @@ -3321,7 +4151,7 @@ index ff234d7..7c36ef6 100644 /* If true, perform translations. */ bool convert = true; -@@ -156,12 +181,44 @@ unexpand (void) +@@ -156,12 +182,44 @@ unexpand (void) do { @@ -3369,10 +4199,10 @@ index ff234d7..7c36ef6 100644 if (blank) { -@@ -175,16 +232,16 @@ unexpand (void) +@@ -178,16 +236,16 @@ unexpand (void) + if (next_tab_column < column) + error (EXIT_FAILURE, 0, _("input line is too long")); - if (convert) - { - if (c == '\t') + if (mb_iseq (c, '\t')) { @@ -3389,7 +4219,7 @@ index ff234d7..7c36ef6 100644 if (! (prev_blank && column == next_tab_column)) { -@@ -192,13 +249,14 @@ unexpand (void) +@@ -195,13 +253,14 @@ unexpand (void) will be replaced by tabs. */ if (column == next_tab_column) one_blank_before_tab_stop = true; @@ -3406,7 +4236,7 @@ index ff234d7..7c36ef6 100644 } /* Discard pending blanks, unless it was a single -@@ -206,7 +264,7 @@ unexpand (void) +@@ -209,7 +268,7 @@ unexpand (void) pending = one_blank_before_tab_stop; } } @@ -3415,7 +4245,7 @@ index ff234d7..7c36ef6 100644 { /* Go back one column, and force recalculation of the next tab stop. */ -@@ -216,16 +274,20 @@ unexpand (void) +@@ -219,16 +278,20 @@ unexpand (void) } else { @@ -3440,7 +4270,7 @@ index ff234d7..7c36ef6 100644 write_error (); pending = 0; one_blank_before_tab_stop = false; -@@ -235,16 +297,17 @@ unexpand (void) +@@ -238,16 +301,17 @@ unexpand (void) convert &= convert_entire_line || blank; } @@ -3462,7 +4292,7 @@ index ff234d7..7c36ef6 100644 } diff --git a/tests/Coreutils.pm b/tests/Coreutils.pm -index b55fb9d..ac80f49 100644 +index 18e7bea..24a141b 100644 --- a/tests/Coreutils.pm +++ b/tests/Coreutils.pm @@ -269,6 +269,9 @@ sub run_tests ($$$$$) @@ -3700,10 +4530,10 @@ index 0000000..26c95de + +Exit $fail diff --git a/tests/local.mk b/tests/local.mk -index 53fc53e..0148422 100644 +index 0b18ec9..7c6d089 100644 --- a/tests/local.mk +++ b/tests/local.mk -@@ -412,6 +412,8 @@ all_tests = \ +@@ -388,6 +388,8 @@ all_tests = \ tests/sort/sort-field-limit.sh \ tests/sort/sort-files0-from.pl \ tests/sort/sort-float.sh \ @@ -3712,7 +4542,7 @@ index 53fc53e..0148422 100644 tests/sort/sort-h-thousands-sep.sh \ tests/sort/sort-merge.pl \ tests/sort/sort-merge-fdlimit.sh \ -@@ -618,6 +620,7 @@ all_tests = \ +@@ -591,6 +593,7 @@ all_tests = \ tests/du/threshold.sh \ tests/du/trailing-slash.sh \ tests/du/two-args.sh \ @@ -3720,7 +4550,7 @@ index 53fc53e..0148422 100644 tests/id/gnu-zero-uids.sh \ tests/id/no-context.sh \ tests/id/context.sh \ -@@ -774,6 +777,7 @@ all_tests = \ +@@ -747,6 +750,7 @@ all_tests = \ tests/touch/read-only.sh \ tests/touch/relative.sh \ tests/touch/trailing-slash.sh \ @@ -3729,7 +4559,7 @@ index 53fc53e..0148422 100644 # See tests/factor/create-test.sh. diff --git a/tests/misc/expand.pl b/tests/misc/expand.pl -index 4b07210..68b9ea1 100755 +index 11f3fc4..d609a2c 100755 --- a/tests/misc/expand.pl +++ b/tests/misc/expand.pl @@ -27,6 +27,15 @@ my $prog = 'expand'; @@ -3795,6 +4625,79 @@ index 4b07210..68b9ea1 100755 my $save_temps = $ENV{DEBUG}; my $verbose = $ENV{VERBOSE}; +diff --git a/tests/misc/fold.pl b/tests/misc/fold.pl +index 00b4362..7d51bea 100755 +--- a/tests/misc/fold.pl ++++ b/tests/misc/fold.pl +@@ -20,9 +20,18 @@ use strict; + + (my $program_name = $0) =~ s|.*/||; + ++my $prog = 'fold'; ++my $try = "Try \`$prog --help' for more information.\n"; ++my $inval = "$prog: invalid byte, character or field list\n$try"; ++ + # Turn off localization of executable's output. + @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3; + ++# uncommented to enable multibyte paths ++my $mb_locale = $ENV{LOCALE_FR_UTF8}; ++! defined $mb_locale || $mb_locale eq 'none' ++ and $mb_locale = 'C'; ++ + my @Tests = + ( + ['s1', '-w2 -s', {IN=>"a\t"}, {OUT=>"a\n\t"}], +@@ -31,9 +40,48 @@ my @Tests = + ['s4', '-w4 -s', {IN=>"abc ef\n"}, {OUT=>"abc \nef\n"}], + ); + ++# Add _POSIX2_VERSION=199209 to the environment of each test ++# that uses an old-style option like +1. ++if ($mb_locale ne 'C') ++ { ++ # Duplicate each test vector, appending "-mb" to the test name and ++ # inserting {ENV => "LC_ALL=$mb_locale"} in the copy, so that we ++ # provide coverage for the distro-added multi-byte code paths. ++ my @new; ++ foreach my $t (@Tests) ++ { ++ my @new_t = @$t; ++ my $test_name = shift @new_t; ++ ++ # Depending on whether fold is multi-byte-patched, ++ # it emits different diagnostics: ++ # non-MB: invalid byte or field list ++ # MB: invalid byte, character or field list ++ # Adjust the expected error output accordingly. ++ if (grep {ref $_ eq 'HASH' && exists $_->{ERR} && $_->{ERR} eq $inval} ++ (@new_t)) ++ { ++ my $sub = {ERR_SUBST => 's/, character//'}; ++ push @new_t, $sub; ++ push @$t, $sub; ++ } ++ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; ++ } ++ push @Tests, @new; ++ } ++ ++@Tests = triple_test \@Tests; ++ ++# Remember that triple_test creates from each test with exactly one "IN" ++# file two more tests (.p and .r suffix on name) corresponding to reading ++# input from a file and from a pipe. The pipe-reading test would fail ++# due to a race condition about 1 in 20 times. ++# Remove the IN_PIPE version of the "output-is-input" test above. ++# The others aren't susceptible because they have three inputs each. ++@Tests = grep {$_->[0] ne 'output-is-input.p'} @Tests; ++ + my $save_temps = $ENV{DEBUG}; + my $verbose = $ENV{VERBOSE}; + +-my $prog = 'fold'; + my $fail = run_tests ($program_name, $prog, \@Tests, $save_temps, $verbose); + exit $fail; diff --git a/tests/misc/sort-mb-tests.sh b/tests/misc/sort-mb-tests.sh new file mode 100644 index 0000000..11836ba @@ -3847,7 +4750,7 @@ index 0000000..11836ba + +Exit $fail diff --git a/tests/misc/unexpand.pl b/tests/misc/unexpand.pl -index bb7469c..c1dec95 100755 +index 76bcbd4..59eb819 100755 --- a/tests/misc/unexpand.pl +++ b/tests/misc/unexpand.pl @@ -27,6 +27,14 @@ my $limits = getlimits (); @@ -3865,7 +4768,7 @@ index bb7469c..c1dec95 100755 my @Tests = ( ['a1', {IN=> ' 'x 1 ."y\n"}, {OUT=> ' 'x 1 ."y\n"}], -@@ -132,6 +140,37 @@ my @Tests = +@@ -128,6 +136,37 @@ my @Tests = ['ts2', '-t5,8', {IN=>"x\t \t y\n"}, {OUT=>"x\t\t y\n"}], ); @@ -3904,7 +4807,7 @@ index bb7469c..c1dec95 100755 my $verbose = $ENV{VERBOSE}; diff --git a/tests/pr/pr-tests.pl b/tests/pr/pr-tests.pl -index 60e6106..3c64a08 100755 +index 6b34e0b..34b4aeb 100755 --- a/tests/pr/pr-tests.pl +++ b/tests/pr/pr-tests.pl @@ -24,6 +24,15 @@ use strict; @@ -3973,7 +4876,7 @@ index 60e6106..3c64a08 100755 my $verbose = $ENV{VERBOSE}; diff --git a/tests/sort/sort-merge.pl b/tests/sort/sort-merge.pl -index a3204d3..40942a5 100755 +index 89eed0c..b855d73 100755 --- a/tests/sort/sort-merge.pl +++ b/tests/sort/sort-merge.pl @@ -26,6 +26,15 @@ my $prog = 'sort'; @@ -4033,7 +4936,7 @@ index a3204d3..40942a5 100755 my $verbose = $ENV{VERBOSE}; diff --git a/tests/sort/sort.pl b/tests/sort/sort.pl -index 5fa9d52..a66952a 100755 +index d49f65f..ebba925 100755 --- a/tests/sort/sort.pl +++ b/tests/sort/sort.pl @@ -24,10 +24,15 @@ my $prog = 'sort'; @@ -4053,7 +4956,7 @@ index 5fa9d52..a66952a 100755 # Since each test is run with a file name and with redirected stdin, # the name in the diagnostic is either the file name or "-". # Normalize each diagnostic to use '-'. -@@ -428,6 +433,38 @@ foreach my $t (@Tests) +@@ -423,6 +428,38 @@ foreach my $t (@Tests) } } @@ -4092,7 +4995,7 @@ index 5fa9d52..a66952a 100755 @Tests = triple_test \@Tests; # Remember that triple_test creates from each test with exactly one "IN" -@@ -437,6 +474,7 @@ foreach my $t (@Tests) +@@ -432,6 +469,7 @@ foreach my $t (@Tests) # Remove the IN_PIPE version of the "output-is-input" test above. # The others aren't susceptible because they have three inputs each. @Tests = grep {$_->[0] ne 'output-is-input.p'} @Tests; @@ -4279,5 +5182,5 @@ index 0000000..8a82d74 +LC_ALL=C unexpand in in > out || fail=1 +compare exp out > /dev/null 2>&1 || fail=1 -- -2.52.0 +2.49.0 diff --git a/coreutils-nproc-affinity-1.patch b/coreutils-nproc-affinity-1.patch new file mode 100644 index 0000000..8748d4e --- /dev/null +++ b/coreutils-nproc-affinity-1.patch @@ -0,0 +1,55 @@ +commit 45c2456a56337ebcafe0dd9faa2bd995ccbc3357 +Author: Florian Weimer +Date: Mon Nov 11 14:05:53 2024 +0100 + + nproc: Use affinity mask even on systems with more than 1024 CPUs. + + * lib/nproc.c (num_processors_via_affinity_mask): Retry + with larger affinity masks if CPU_ALLOC_SIZE is available. + +diff --git a/lib/nproc.c b/lib/nproc.c +index 92a07e8289..48bc3d06fa 100644 +--- a/lib/nproc.c ++++ b/lib/nproc.c +@@ -20,6 +20,7 @@ + #include + #include "nproc.h" + ++#include + #include + #include + #include +@@ -124,6 +125,33 @@ num_processors_via_affinity_mask (void) + return count; + } + } ++#elif HAVE_SCHED_GETAFFINITY_LIKE_GLIBC \ ++ && defined CPU_ALLOC_SIZE /* glibc >= 2.6 */ ++ { ++ unsigned int alloc_count = 1024; ++ while (1) ++ { ++ cpu_set_t *set = CPU_ALLOC (alloc_count); ++ if (set == NULL) ++ return 0; ++ unsigned int size = CPU_ALLOC_SIZE (alloc_count); ++ if (sched_getaffinity (0, size, set) == 0) ++ { ++ unsigned int count = CPU_COUNT_S (size, set); ++ CPU_FREE (set); ++ return count; ++ } ++ if (errno != EINVAL) ++ { ++ CPU_FREE (set); ++ return 0; ++ } ++ CPU_FREE (set); ++ alloc_count *= 2; ++ if (alloc_count == 0) ++ return 0; ++ } ++ } + #elif HAVE_SCHED_GETAFFINITY_LIKE_GLIBC /* glibc >= 2.3.4 */ + { + cpu_set_t set; diff --git a/coreutils-nproc-affinity-2.patch b/coreutils-nproc-affinity-2.patch new file mode 100644 index 0000000..aeca09c --- /dev/null +++ b/coreutils-nproc-affinity-2.patch @@ -0,0 +1,64 @@ +commit ee0bc695303775da5026091a65e8ec2b764f4a26 +Author: Bruno Haible +Date: Mon Nov 11 15:40:52 2024 +0100 + + nproc: Use affinity mask even in out-of-memory situations. + + * lib/nproc.c (num_processors_via_affinity_mask): Use a stack-allocated + cpu_set_t as fallback. Add comments. + +diff --git a/lib/nproc.c b/lib/nproc.c +index 48bc3d06fa..0b5898d88f 100644 +--- a/lib/nproc.c ++++ b/lib/nproc.c +@@ -125,15 +125,25 @@ num_processors_via_affinity_mask (void) + return count; + } + } +-#elif HAVE_SCHED_GETAFFINITY_LIKE_GLIBC \ +- && defined CPU_ALLOC_SIZE /* glibc >= 2.6 */ ++#elif HAVE_SCHED_GETAFFINITY_LIKE_GLIBC /* glibc >= 2.3.4 */ ++ /* There are two ways to use the sched_getaffinity() function: ++ - With a statically-sized cpu_set_t. ++ - With a dynamically-sized cpu_set_t. ++ Documentation: ++ ++ ++ The second way has the advantage that it works on systems with more than ++ 1024 CPUs. The first way has the advantage that it works also when memory ++ is tight. */ ++# if defined CPU_ALLOC_SIZE /* glibc >= 2.6 */ + { + unsigned int alloc_count = 1024; +- while (1) ++ for (;;) + { + cpu_set_t *set = CPU_ALLOC (alloc_count); + if (set == NULL) +- return 0; ++ /* Out of memory. */ ++ break; + unsigned int size = CPU_ALLOC_SIZE (alloc_count); + if (sched_getaffinity (0, size, set) == 0) + { +@@ -143,16 +153,19 @@ num_processors_via_affinity_mask (void) + } + if (errno != EINVAL) + { ++ /* Some other error. */ + CPU_FREE (set); + return 0; + } + CPU_FREE (set); ++ /* Retry with some larger cpu_set_t. */ + alloc_count *= 2; + if (alloc_count == 0) ++ /* Integer overflow. Avoid an endless loop. */ + return 0; + } + } +-#elif HAVE_SCHED_GETAFFINITY_LIKE_GLIBC /* glibc >= 2.3.4 */ ++# endif + { + cpu_set_t set; + diff --git a/coreutils-prereq-CVE-2025-5278.patch b/coreutils-prereq-CVE-2025-5278.patch new file mode 100644 index 0000000..1abc6a3 --- /dev/null +++ b/coreutils-prereq-CVE-2025-5278.patch @@ -0,0 +1,42 @@ +From bfbb3ec7f798b179d7fa7b42673e068b18048899 Mon Sep 17 00:00:00 2001 +From: Paul Eggert +Date: Sat, 3 Aug 2024 22:31:20 -0700 +Subject: shuf: fix randomness bug + +Problem reported by Daniel Carpenter . +* gl/lib/randread.c (randread_new): Fill the ISAAC buffer +instead of storing at most BYTES_BOUND bytes into it. + +(cherry picked from commit bfbb3ec7f798b179d7fa7b42673e068b18048899) +--- + gl/lib/randread.c | 12 +++++++++++- + 1 file changed, 11 insertions(+), 1 deletion(-) + +diff --git a/lib/randread.c b/lib/randread.c +index cbee224bb..43c0cf09f 100644 +--- a/lib/randread.c ++++ b/lib/randread.c +@@ -189,9 +189,19 @@ randread_new (char const *name, size_t bytes_bound) + setvbuf (source, s->buf.c, _IOFBF, MIN (sizeof s->buf.c, bytes_bound)); + else + { ++ /* Fill the ISAAC buffer. Although it is tempting to read at ++ most BYTES_BOUND bytes, this is incorrect for two reasons. ++ First, BYTES_BOUND is just an estimate. ++ Second, even if the estimate is correct ++ ISAAC64 poorly randomizes when BYTES_BOUND is small ++ and just the first few bytes of s->buf.isaac.state.m ++ are random while the other bytes are all zero. See: ++ Aumasson J-P. On the pseudo-random generator ISAAC. ++ Cryptology ePrint Archive. 2006;438. ++ . */ + s->buf.isaac.buffered = 0; + if (! get_nonce (s->buf.isaac.state.m, +- MIN (sizeof s->buf.isaac.state.m, bytes_bound))) ++ sizeof s->buf.isaac.state.m)) + { + int e = errno; + randread_free_body (s); +-- +2.49.0 + diff --git a/coreutils-python3.patch b/coreutils-python3.patch index 447fdbc..98fc642 100644 --- a/coreutils-python3.patch +++ b/coreutils-python3.patch @@ -1,4 +1,4 @@ -From 8927d505ecb5334f09c48ef98ef1f464f581d0f7 Mon Sep 17 00:00:00 2001 +From cef9cccce395cd80cd5ac42a4fe6c3909be1c0b5 Mon Sep 17 00:00:00 2001 From: rpm-build Date: Tue, 2 Apr 2024 14:11:26 +0100 Subject: [PATCH] coreutils-python3.patch @@ -10,10 +10,10 @@ Subject: [PATCH] coreutils-python3.patch 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/init.cfg b/init.cfg -index ac05f7b..26d9516 100644 +index b06965a..08413ee 100644 --- a/init.cfg +++ b/init.cfg -@@ -601,10 +601,10 @@ seek_data_capable_() +@@ -581,10 +581,10 @@ seek_data_capable_() # Skip the current test if "." lacks d_type support. require_dirent_d_type_() { @@ -37,7 +37,7 @@ index 1a2f76f..42d3924 100644 # Intended to exit 0 only on Linux/GNU systems. import os diff --git a/tests/du/move-dir-while-traversing.sh b/tests/du/move-dir-while-traversing.sh -index adf482b..cf9214a 100755 +index 830a69e..7344ddf 100755 --- a/tests/du/move-dir-while-traversing.sh +++ b/tests/du/move-dir-while-traversing.sh @@ -21,8 +21,8 @@ print_ver_ du @@ -61,5 +61,5 @@ index adf482b..cf9214a 100755 import os,sys -- -2.51.0 +2.44.0 diff --git a/coreutils-selinux.patch b/coreutils-selinux.patch new file mode 100644 index 0000000..a31c3af --- /dev/null +++ b/coreutils-selinux.patch @@ -0,0 +1,87 @@ +From 78970c915b8556fcec4622e948a37dd8e34efe6d Mon Sep 17 00:00:00 2001 +From: rpm-build +Date: Wed, 30 Aug 2023 17:19:58 +0200 +Subject: [PATCH] coreutils-selinux.patch + +--- + src/cp.c | 19 ++++++++++++++++++- + src/install.c | 12 +++++++++++- + 2 files changed, 29 insertions(+), 2 deletions(-) + +diff --git a/src/cp.c b/src/cp.c +index 28b0217..897379f 100644 +--- a/src/cp.c ++++ b/src/cp.c +@@ -997,7 +997,7 @@ main (int argc, char **argv) + selinux_enabled = (0 < is_selinux_enabled ()); + cp_option_init (&x); + +- while ((c = getopt_long (argc, argv, "abdfHilLnprst:uvxPRS:TZ", ++ while ((c = getopt_long (argc, argv, "abcdfHilLnprst:uvxPRS:TZ", + long_opts, nullptr)) + != -1) + { +@@ -1049,6 +1049,23 @@ main (int argc, char **argv) + copy_contents = true; + break; + ++ case 'c': ++ fprintf (stderr, "%s: warning: option '-c' is deprecated," ++ " please use '--preserve=context' instead\n", argv[0]); ++ if (x.set_security_context) ++ { ++ fprintf (stderr, ++ "%s: cannot force target context and preserve it\n", ++ argv[0]); ++ exit (1); ++ } ++ else if (selinux_enabled) ++ { ++ x.preserve_security_context = true; ++ x.require_preserve_context = true; ++ } ++ break; ++ + case 'd': + x.preserve_links = true; + x.dereference = DEREF_NEVER; +diff --git a/src/install.c b/src/install.c +index accd0fd..b686fe9 100644 +--- a/src/install.c ++++ b/src/install.c +@@ -807,7 +807,7 @@ main (int argc, char **argv) + dir_arg = false; + umask (0); + +- while ((optc = getopt_long (argc, argv, "bcCsDdg:m:o:pt:TvS:Z", long_options, ++ while ((optc = getopt_long (argc, argv, "bcCsDdg:m:o:pPt:TvS:Z", long_options, + nullptr)) + != -1) + { +@@ -872,6 +872,9 @@ main (int argc, char **argv) + no_target_directory = true; + break; + ++ case 'P': ++ fprintf (stderr, "%s: warning: option '-P' is deprecated," ++ " please use '--preserve-context' instead\n", argv[0]); + case PRESERVE_CONTEXT_OPTION: + if (! selinux_enabled) + { +@@ -879,6 +882,13 @@ main (int argc, char **argv) + "this kernel is not SELinux-enabled")); + break; + } ++ if (x.set_security_context) ++ { ++ fprintf (stderr, ++ "%s: cannot force target context and preserve it\n", ++ argv[0]); ++ exit (1); ++ } + x.preserve_security_context = true; + use_default_selinux_context = false; + break; +-- +2.44.0 + diff --git a/coreutils.spec b/coreutils.spec index 6712263..21e6427 100644 --- a/coreutils.spec +++ b/coreutils.spec @@ -1,7 +1,7 @@ Summary: A set of basic GNU tools commonly used in shell scripts Name: coreutils -Version: 9.9 -Release: 2%{?dist} +Version: 9.5 +Release: 12%{?dist} # some used parts of gnulib are under various variants of LGPL License: GPL-3.0-or-later AND GFDL-1.3-no-invariants-or-later AND LGPL-2.1-or-later AND LGPL-3.0-or-later Url: https://www.gnu.org/software/coreutils/ @@ -32,17 +32,22 @@ Patch103: coreutils-python3.patch # df --direct Patch104: coreutils-df-direct.patch -# gnulib C23 support -# https://github.com/coreutils/gnulib/commit/df17f4f37ed3ca373d23ad42eae51122bdb96626 -Patch105: coreutils-9.9-gnulib-c23.patch +# https://bugzilla.redhat.com/show_bug.cgi?id=2325167 +Patch105: coreutils-nproc-affinity-1.patch +Patch106: coreutils-nproc-affinity-2.patch -# fix cut test failure on aarch64 rawhide (rhbz#2424302) -# https://github.com/coreutils/coreutils/commit/95044cb5eaea83d02f768feb5ab79fcf5e6ad782 -Patch106: coreutils-9.9-fix-cut-test-aarch64.patch +# sort: fix buffer under-read (CVE-2025-5278) +# * CVE test prereq: https://cgit.git.savannah.gnu.org/cgit/coreutils.git/patch/?id=bfbb3ec7f798b179d7fa7b42673e068b18048899 +# * CVE fix: https://cgit.git.savannah.gnu.org/cgit/coreutils.git/patch/?id=8c9602e3a145e9596dc1a63c6ed67865814b6633 +Patch107: coreutils-prereq-CVE-2025-5278.patch +Patch108: coreutils-CVE-2025-5278.patch # (sb) lin18nux/lsb compliance - multibyte functionality patch Patch800: coreutils-i18n.patch +# downstream SELinux options deprecated since 2009 +Patch950: coreutils-selinux.patch + Conflicts: filesystem < 3 # To avoid clobbering installs @@ -63,7 +68,6 @@ BuildRequires: libselinux-utils BuildRequires: make BuildRequires: openssl-devel BuildRequires: strace -BuildRequires: systemd-devel BuildRequires: texinfo # For gpg verification of source tarball @@ -125,9 +129,6 @@ packaged as a single multicall binary. # https://bugzilla.redhat.com/show_bug.cgi?id=1107973#c7 Obsoletes: %{name} < 8.24-100 -# Gnulib translations are maintained seprately since coreutils 9.6 (#2393892) -Requires: gnulib-l10n - # info doc refers to "Specifying the Time Zone" from glibc-doc (#959597) Suggests: glibc-doc @@ -162,10 +163,6 @@ sed src/dircolors.hin \ find tests -name '*.sh' -perm 0644 -print -exec chmod 0755 '{}' '+' (echo "<<< done") 2>/dev/null -# FIXME: Force a newer gettext version to workaround `autoreconf -i` errors -# with coreutils 9.6 and bundled gettext 0.19.2 from gettext-common-devel. -sed -i "s/0.19.2/$(rpm -q --queryformat '%%{VERSION}\n' gettext-devel)/" bootstrap.conf configure.ac - autoreconf -fiv %build @@ -199,7 +196,6 @@ for type in separate single; do --cache-file=../config.cache \ --enable-install-program=arch \ --enable-no-install-program=kill,uptime \ - --enable-systemd \ --with-tty-group \ DEFAULT_POSIX2_VERSION=200112 alternative=199209 || : %make_build all V=1 @@ -286,58 +282,17 @@ rm -f $RPM_BUILD_ROOT%{_infodir}/dir %license COPYING %changelog -* Tue Jan 13 2026 Lukáš Zaoral - 9.9-2 -- fix cut test failure on aarch64 rawhide (rhbz#2424302) - -* Wed Nov 26 2025 Lukáš Zaoral - 9.9-1 -- rebase to latest upstream release (rhbz#2413803) - -* Mon Sep 29 2025 Lukáš Zaoral - 9.8-3 -- require gnulib-l10n for translations of gnulib messages (rhbz#2393892) - -* Thu Sep 25 2025 Lukáš Zaoral - 9.8-2 -- tail: fix tailing larger number of lines in regular files (rhbz#2398008) - -* Wed Sep 24 2025 Lukáš Zaoral - 9.8-1 -- rebase to latest upstream release (rhbz#2397467) -- remove downstream patch for selinux options deprecated since 2009 - -* Wed Jul 23 2025 Fedora Release Engineering - 9.7-5 -- Rebuilt for https://fedoraproject.org/wiki/Fedora_43_Mass_Rebuild - -* Mon Jun 30 2025 Lukáš Zaoral - 9.7-4 -- stty: add support for arbitrary baud rates (rhbz#2375439) - -* Wed May 28 2025 Lukáš Zaoral - 9.7-3 +* Wed May 28 2025 Lukáš Zaoral - 9.5-12 - sort: fix buffer under-read (CVE-2025-5278) -* Mon May 19 2025 Lukáš Zaoral - 9.7-2 -- cp/mv: do not fail when copying of trivial NFSv4 ACLs fails (rhbz#2363149) - -* Wed Apr 09 2025 Lukáš Zaoral - 9.7-1 -- rebase to latest upstream release (rhbz#2358624) - -* Tue Feb 25 2025 Lukáš Zaoral - 9.6-2 -- fix 'who -m' with guessed tty names (rhbz#2343998) - -* Mon Jan 20 2025 Lukáš Zaoral - 9.6-1 -- rebase to latest upstream version (rhbz#2338620) -- sync i18n patch with SUSE (Kudos to Berny Völker!) - -* Thu Jan 16 2025 Fedora Release Engineering - 9.5-13 -- Rebuilt for https://fedoraproject.org/wiki/Fedora_42_Mass_Rebuild - -* Sun Jan 12 2025 Zbigniew Jędrzejewski-Szmek - 9.5-12 -- Rebuilt for the bin-sbin merge (2nd attempt) - * Wed Nov 13 2024 Florian Weimer - 9.5-11 - Affinity mask handling in nproc for large CPU counts (rhbz#2325167) * Fri Sep 27 2024 Lukáš Zaoral - 9.5-10 - fix fold -b with UTF8 locale (RHEL-60295) -* Tue Aug 27 2024 Lukáš Zaoral - 9.5-9 -- show web sessions in who output (rhbz#2307847) +* Mon Aug 26 2024 Lukáš Zaoral - 9.5-9 +- disable integration with systemd (rhbz#2307847) * Wed Aug 21 2024 Lukáš Zaoral - 9.5-8 - add missing systemd-devel buildrequires diff --git a/sources b/sources index 0952ab1..d9dc6c9 100644 --- a/sources +++ b/sources @@ -1,2 +1,2 @@ -SHA512 (coreutils-9.9.tar.xz.sig) = 0a3dfdfa6b4234e2e1d42142269f959bdf3cf8f6605a50270a27eff84dd22588f182121f7dd3eeb04be45f5109d02690215065b3d3b43882874d0e165a1435d0 -SHA512 (coreutils-9.9.tar.xz) = e7b0e59f7732d2c098ea4934014f470248bd5c4764210e9200a698010a8e3b95bbb26e543f0cd73ed5a4b8e1f8cda932c73f39954d68175e4deaa47526610c65 +SHA512 (coreutils-9.5.tar.xz) = 2ca0deac4dc10a80fd0c6fd131252e99d457fd03b7bd626a6bc74fe5a0529c0a3d48ce1f5da1d3b3a7a150a1ce44f0fbb6b68a6ac543dfd5baa3e71f5d65401c +SHA512 (coreutils-9.5.tar.xz.sig) = 029997e0f4ee64e561853cff7c8a124f58cc891598595b44c4a46f9813b4b71c9d677464bc8a26d294e9971832f4b87c23777fea4fac6e8e30f06ad93b9957d5