diff --git a/.gitignore b/.gitignore index de62e8f..46d0f92 100644 --- a/.gitignore +++ b/.gitignore @@ -1 +1,2 @@ /coreutils-[0-9.]*.tar.xz +/coreutils-[0-9.]*.tar.xz.sig diff --git a/coreutils-4.5.3-langinfo.patch b/coreutils-4.5.3-langinfo.patch deleted file mode 100644 index a8af3bd..0000000 --- a/coreutils-4.5.3-langinfo.patch +++ /dev/null @@ -1,20 +0,0 @@ -diff --git a/src/date.c b/src/date.c -index ddb011e..619a72b 100644 ---- a/src/date.c -+++ b/src/date.c -@@ -490,14 +490,7 @@ main (int argc, char **argv) - format = DATE_FMT_LANGINFO (); - if (! *format) - { -- /* Do not wrap the following literal format string with _(...). -- For example, suppose LC_ALL is unset, LC_TIME=POSIX, -- and LANG="ko_KR". In that case, POSIX says that LC_TIME -- determines the format and contents of date and time strings -- written by date, which means "date" must generate output -- using the POSIX locale; but adding _() would cause "date" -- to use a Korean translation of the format. */ -- format = "%a %b %e %H:%M:%S %Z %Y"; -+ format = dcgettext(NULL, N_("%a %b %e %H:%M:%S %Z %Y"), LC_TIME); - } - } - diff --git a/coreutils-6.10-manpages.patch b/coreutils-6.10-manpages.patch deleted file mode 100644 index 5f8bdb2..0000000 --- a/coreutils-6.10-manpages.patch +++ /dev/null @@ -1,14 +0,0 @@ -diff --git a/src/md5sum.c b/src/md5sum.c -index 8e21609..a857d62 100644 ---- a/src/md5sum.c -+++ b/src/md5sum.c -@@ -266,6 +266,9 @@ Print or check %s (%d-bit) checksums.\n\ - fputs (_("\ - -t, --text read in text mode (default)\n\ - "), stdout); -+ fputs (_("\ -+ Note: There is no difference between binary and text mode option on GNU system.\n\ -+"), stdout); - fputs (_("\ - \n\ - The following five options are useful only when verifying checksums:\n\ diff --git a/coreutils-8.2-uname-processortype.patch b/coreutils-8.2-uname-processortype.patch deleted file mode 100644 index ed01ab8..0000000 --- a/coreutils-8.2-uname-processortype.patch +++ /dev/null @@ -1,49 +0,0 @@ -diff --git a/src/uname.c b/src/uname.c -index 6371ca2..1ad8fd7 100644 ---- a/src/uname.c -+++ b/src/uname.c -@@ -300,13 +300,19 @@ main (int argc, char **argv) - - if (toprint & PRINT_PROCESSOR) - { -- char const *element = unknown; -+ char *element = unknown; - #if HAVE_SYSINFO && defined SI_ARCHITECTURE - { - static char processor[257]; - if (0 <= sysinfo (SI_ARCHITECTURE, processor, sizeof processor)) - element = processor; - } -+#else -+ { -+ static struct utsname u; -+ uname(&u); -+ element = u.machine; -+ } - #endif - #ifdef UNAME_PROCESSOR - if (element == unknown) -@@ -344,7 +350,7 @@ main (int argc, char **argv) - - if (toprint & PRINT_HARDWARE_PLATFORM) - { -- char const *element = unknown; -+ char *element = unknown; - #if HAVE_SYSINFO && defined SI_PLATFORM - { - static char hardware_platform[257]; -@@ -352,6 +358,14 @@ main (int argc, char **argv) - hardware_platform, sizeof hardware_platform)) - element = hardware_platform; - } -+#else -+ { -+ static struct utsname u; -+ uname(&u); -+ element = u.machine; -+ if(strlen(element)==4 && element[0]=='i' && element[2]=='8' && element[3]=='6') -+ element[1]='3'; -+ } - #endif - #ifdef UNAME_HARDWARE_PLATFORM - if (element == unknown) diff --git a/coreutils-8.25-DIR_COLORS.patch b/coreutils-8.25-DIR_COLORS.patch deleted file mode 100644 index 94923b0..0000000 --- a/coreutils-8.25-DIR_COLORS.patch +++ /dev/null @@ -1,692 +0,0 @@ -From a13bc34f1eeebdf8b87e4b5a570341bb77a62f76 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 - ---- - DIR_COLORS | 41 ++++--- - DIR_COLORS.256color | 302 ++++++++++++++++++++++++------------------------ - DIR_COLORS.lightbgcolor | 215 +++++++++++++++++----------------- - 3 files changed, 286 insertions(+), 272 deletions(-) - -diff --git a/DIR_COLORS b/DIR_COLORS -index d2ea453..27af9d7 100644 ---- a/DIR_COLORS -+++ b/DIR_COLORS -@@ -1,6 +1,10 @@ - # Configuration file for dircolors, a utility to help you set the - # LS_COLORS environment variable used by GNU ls with the --color option. - -+# This file goes in the /etc directory, and must be world readable. -+# You can copy this file to .dir_colors in your $HOME directory to override -+# the system defaults. -+ - # Copyright (C) 1996-2017 Free Software Foundation, Inc. - # Copying and distribution of this file, with or without modification, - # are permitted provided the copyright notice and this notice are preserved. -@@ -8,6 +12,9 @@ - # The keywords COLOR, OPTIONS, and EIGHTBIT (honored by the - # slackware version of dircolors) are recognized but ignored. - -+# For compatibility, the pattern "^COLOR.*none" is recognized as a way to -+# disable colorization. See https://bugzilla.redhat.com/1349579 for details. -+ - # Below are TERM entries, which can be a glob patterns, to match - # against the TERM environment variable to determine if it is colorizable. - TERM Eterm -@@ -56,7 +63,7 @@ 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;05;37;41 # ... and the files they point to - SETUID 37;41 # file that is setuid (u+s) - SETGID 30;43 # file that is setgid (g+s) - CAPABILITY 30;41 # file with capability -@@ -185,21 +192,21 @@ EXEC 01;32 - .ogx 01;35 - - # audio formats --.aac 00;36 --.au 00;36 --.flac 00;36 --.m4a 00;36 --.mid 00;36 --.midi 00;36 --.mka 00;36 --.mp3 00;36 --.mpc 00;36 --.ogg 00;36 --.ra 00;36 --.wav 00;36 -+.aac 01;36 -+.au 01;36 -+.flac 01;36 -+.m4a 01;36 -+.mid 01;36 -+.midi 01;36 -+.mka 01;36 -+.mp3 01;36 -+.mpc 01;36 -+.ogg 01;36 -+.ra 01;36 -+.wav 01;36 - - # https://wiki.xiph.org/MIME_Types_and_File_Extensions --.oga 00;36 --.opus 00;36 --.spx 00;36 --.xspf 00;36 -+.oga 01;36 -+.opus 01;36 -+.spx 01;36 -+.xspf 01;36 -diff --git a/DIR_COLORS.256color b/DIR_COLORS.256color -index d2ea453..74c34ba 100644 ---- a/DIR_COLORS.256color -+++ b/DIR_COLORS.256color -@@ -1,3 +1,9 @@ -+# Configuration file for the 256color ls utility -+ -+# This file goes in the /etc directory, and must be world readable. -+# You can copy this file to .dir_colors in your $HOME directory to override -+# the system defaults. -+ - # Configuration file for dircolors, a utility to help you set the - # LS_COLORS environment variable used by GNU ls with the --color option. - -@@ -8,32 +14,13 @@ - # The keywords COLOR, OPTIONS, and EIGHTBIT (honored by the - # slackware version of dircolors) are recognized but ignored. - -+# For compatibility, the pattern "^COLOR.*none" is recognized as a way to -+# disable colorization. See https://bugzilla.redhat.com/1349579 for details. -+ - # Below are TERM entries, which can be a glob patterns, to match - # against the TERM environment variable to determine if it is colorizable. --TERM Eterm --TERM ansi --TERM *color* --TERM con[0-9]*x[0-9]* --TERM cons25 --TERM console --TERM cygwin --TERM dtterm --TERM gnome --TERM hurd --TERM jfbterm --TERM konsole --TERM kterm --TERM linux --TERM linux-c --TERM mlterm --TERM putty --TERM rxvt* --TERM screen* --TERM st --TERM terminator --TERM tmux* --TERM vt100 --TERM xterm* -+TERM *256color* -+TERM rxvt-unicode256 - - # Below are the color init strings for the basic file types. A color init - # string consists of one or more of the following numeric codes: -@@ -43,29 +30,40 @@ TERM xterm* - # 30=black 31=red 32=green 33=yellow 34=blue 35=magenta 36=cyan 37=white - # Background color codes: - # 40=black 41=red 42=green 43=yellow 44=blue 45=magenta 46=cyan 47=white -+# Text color(256 colors mode) codes: -+# Valid syntax for text 256color is 38;5; , where color number -+# is number between 0 and 255. -+# You may find following command useful to search the best one for you: -+# for ((x=0; x<=255; x++));do echo -e "${x}:\033[38;5;${x}mcolor\033[000m";done -+# Background color(256 colors mode) codes: -+# Valid syntax for background 256color is 48;5; , where -+# color number is number between 0 and 255. -+# You may find following command useful to search the best one for you: -+# for ((x=0; x<=255; x++));do echo -e "${x}:\033[48;5;${x}mcolor\033[000m";done -+ - #NORMAL 00 # no color code at all - #FILE 00 # regular file: use no color at all - RESET 0 # reset to "normal" color --DIR 01;34 # directory --LINK 01;36 # symbolic link. (If you set this to 'target' instead of a -+DIR 38;5;33 # directory -+LINK 38;5;51 # symbolic link. (If you set this to 'target' instead of a - # numerical value, the color is as for the file pointed to.) - MULTIHARDLINK 00 # regular file with more than one link --FIFO 40;33 # pipe --SOCK 01;35 # socket --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 --SETUID 37;41 # file that is setuid (u+s) --SETGID 30;43 # file that is setgid (g+s) --CAPABILITY 30;41 # file with capability --STICKY_OTHER_WRITABLE 30;42 # dir that is sticky and other-writable (+t,o+w) --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 -+FIFO 40;38;5;11 # pipe -+SOCK 38;5;13 # socket -+DOOR 38;5;5 # door -+BLK 48;5;232;38;5;11 # block device driver -+CHR 48;5;232;38;5;3 # character device driver -+ORPHAN 48;5;232;38;5;9 # symlink to nonexistent file, or non-stat'able file ... -+MISSING 01;05;37;41 # ... and the files they point to -+SETUID 48;5;196;38;5;15 # file that is setuid (u+s) -+SETGID 48;5;11;38;5;16 # file that is setgid (g+s) -+CAPABILITY 48;5;196;38;5;226 # file with capability -+STICKY_OTHER_WRITABLE 48;5;10;38;5;16 # dir that is sticky and other-writable (+t,o+w) -+OTHER_WRITABLE 48;5;10;38;5;21 # dir that is other-writable (o+w) and not sticky -+STICKY 48;5;21;38;5;15 # dir with the sticky bit set (+t) and not other-writable - - # This is for files with execute permission: --EXEC 01;32 -+EXEC 38;5;40 - - # List any file extensions like '.gz' or '.tar' that you would like ls - # to colorize below. Put the extension, a space, and the color init string. -@@ -83,123 +81,123 @@ EXEC 01;32 - #.csh 01;32 - - # archives or compressed (bright red) --.tar 01;31 --.tgz 01;31 --.arc 01;31 --.arj 01;31 --.taz 01;31 --.lha 01;31 --.lz4 01;31 --.lzh 01;31 --.lzma 01;31 --.tlz 01;31 --.txz 01;31 --.tzo 01;31 --.t7z 01;31 --.zip 01;31 --.z 01;31 --.Z 01;31 --.dz 01;31 --.gz 01;31 --.lrz 01;31 --.lz 01;31 --.lzo 01;31 --.xz 01;31 --.zst 01;31 --.tzst 01;31 --.bz2 01;31 --.bz 01;31 --.tbz 01;31 --.tbz2 01;31 --.tz 01;31 --.deb 01;31 --.rpm 01;31 --.jar 01;31 --.war 01;31 --.ear 01;31 --.sar 01;31 --.rar 01;31 --.alz 01;31 --.ace 01;31 --.zoo 01;31 --.cpio 01;31 --.7z 01;31 --.rz 01;31 --.cab 01;31 --.wim 01;31 --.swm 01;31 --.dwm 01;31 --.esd 01;31 -+.tar 38;5;9 -+.tgz 38;5;9 -+.arc 38;5;9 -+.arj 38;5;9 -+.taz 38;5;9 -+.lha 38;5;9 -+.lz4 38;5;9 -+.lzh 38;5;9 -+.lzma 38;5;9 -+.tlz 38;5;9 -+.txz 38;5;9 -+.tzo 38;5;9 -+.t7z 38;5;9 -+.zip 38;5;9 -+.z 38;5;9 -+.Z 38;5;9 -+.dz 38;5;9 -+.gz 38;5;9 -+.lrz 38;5;9 -+.lz 38;5;9 -+.lzo 38;5;9 -+.xz 38;5;9 -+.zst 38;5;9 -+.tzst 38;5;9 -+.bz2 38;5;9 -+.bz 38;5;9 -+.tbz 38;5;9 -+.tbz2 38;5;9 -+.tz 38;5;9 -+.deb 38;5;9 -+.rpm 38;5;9 -+.jar 38;5;9 -+.war 38;5;9 -+.ear 38;5;9 -+.sar 38;5;9 -+.rar 38;5;9 -+.alz 38;5;9 -+.ace 38;5;9 -+.zoo 38;5;9 -+.cpio 38;5;9 -+.7z 38;5;9 -+.rz 38;5;9 -+.cab 38;5;9 -+.wim 38;5;9 -+.swm 38;5;9 -+.dwm 38;5;9 -+.esd 38;5;9 - - # image formats --.jpg 01;35 --.jpeg 01;35 --.mjpg 01;35 --.mjpeg 01;35 --.gif 01;35 --.bmp 01;35 --.pbm 01;35 --.pgm 01;35 --.ppm 01;35 --.tga 01;35 --.xbm 01;35 --.xpm 01;35 --.tif 01;35 --.tiff 01;35 --.png 01;35 --.svg 01;35 --.svgz 01;35 --.mng 01;35 --.pcx 01;35 --.mov 01;35 --.mpg 01;35 --.mpeg 01;35 --.m2v 01;35 --.mkv 01;35 --.webm 01;35 --.ogm 01;35 --.mp4 01;35 --.m4v 01;35 --.mp4v 01;35 --.vob 01;35 --.qt 01;35 --.nuv 01;35 --.wmv 01;35 --.asf 01;35 --.rm 01;35 --.rmvb 01;35 --.flc 01;35 --.avi 01;35 --.fli 01;35 --.flv 01;35 --.gl 01;35 --.dl 01;35 --.xcf 01;35 --.xwd 01;35 --.yuv 01;35 --.cgm 01;35 --.emf 01;35 -+.jpg 38;5;13 -+.jpeg 38;5;13 -+.mjpg 38;5;13 -+.mjpeg 38;5;13 -+.gif 38;5;13 -+.bmp 38;5;13 -+.pbm 38;5;13 -+.pgm 38;5;13 -+.ppm 38;5;13 -+.tga 38;5;13 -+.xbm 38;5;13 -+.xpm 38;5;13 -+.tif 38;5;13 -+.tiff 38;5;13 -+.png 38;5;13 -+.svg 38;5;13 -+.svgz 38;5;13 -+.mng 38;5;13 -+.pcx 38;5;13 -+.mov 38;5;13 -+.mpg 38;5;13 -+.mpeg 38;5;13 -+.m2v 38;5;13 -+.mkv 38;5;13 -+.webm 38;5;13 -+.ogm 38;5;13 -+.mp4 38;5;13 -+.m4v 38;5;13 -+.mp4v 38;5;13 -+.vob 38;5;13 -+.qt 38;5;13 -+.nuv 38;5;13 -+.wmv 38;5;13 -+.asf 38;5;13 -+.rm 38;5;13 -+.rmvb 38;5;13 -+.flc 38;5;13 -+.avi 38;5;13 -+.fli 38;5;13 -+.flv 38;5;13 -+.gl 38;5;13 -+.dl 38;5;13 -+.xcf 38;5;13 -+.xwd 38;5;13 -+.yuv 38;5;13 -+.cgm 38;5;13 -+.emf 38;5;13 - - # https://wiki.xiph.org/MIME_Types_and_File_Extensions --.ogv 01;35 --.ogx 01;35 -+.ogv 38;5;13 -+.ogx 38;5;13 - - # audio formats --.aac 00;36 --.au 00;36 --.flac 00;36 --.m4a 00;36 --.mid 00;36 --.midi 00;36 --.mka 00;36 --.mp3 00;36 --.mpc 00;36 --.ogg 00;36 --.ra 00;36 --.wav 00;36 -+.aac 38;5;45 -+.au 38;5;45 -+.flac 38;5;45 -+.m4a 38;5;45 -+.mid 38;5;45 -+.midi 38;5;45 -+.mka 38;5;45 -+.mp3 38;5;45 -+.mpc 38;5;45 -+.ogg 38;5;45 -+.ra 38;5;45 -+.wav 38;5;45 - - # https://wiki.xiph.org/MIME_Types_and_File_Extensions --.oga 00;36 --.opus 00;36 --.spx 00;36 --.xspf 00;36 -+.oga 38;5;45 -+.opus 38;5;45 -+.spx 38;5;45 -+.xspf 38;5;45 -diff --git a/DIR_COLORS.lightbgcolor b/DIR_COLORS.lightbgcolor -index d2ea453..95d6879 100644 ---- a/DIR_COLORS.lightbgcolor -+++ b/DIR_COLORS.lightbgcolor -@@ -1,3 +1,9 @@ -+# Configuration file for the color ls utility - modified for lighter backgrounds -+ -+# This file goes in the /etc directory, and must be world readable. -+# You can copy this file to .dir_colors in your $HOME directory to override -+# the system defaults. -+ - # Configuration file for dircolors, a utility to help you set the - # LS_COLORS environment variable used by GNU ls with the --color option. - -@@ -8,6 +14,9 @@ - # The keywords COLOR, OPTIONS, and EIGHTBIT (honored by the - # slackware version of dircolors) are recognized but ignored. - -+# For compatibility, the pattern "^COLOR.*none" is recognized as a way to -+# disable colorization. See https://bugzilla.redhat.com/1349579 for details. -+ - # Below are TERM entries, which can be a glob patterns, to match - # against the TERM environment variable to determine if it is colorizable. - TERM Eterm -@@ -46,17 +55,17 @@ TERM xterm* - #NORMAL 00 # no color code at all - #FILE 00 # regular file: use no color at all - RESET 0 # reset to "normal" color --DIR 01;34 # directory --LINK 01;36 # symbolic link. (If you set this to 'target' instead of a -+DIR 00;34 # directory -+LINK 00;36 # symbolic link. (If you set this to 'target' instead of a - # numerical value, the color is as for the file pointed to.) - MULTIHARDLINK 00 # regular file with more than one link - FIFO 40;33 # pipe --SOCK 01;35 # socket --DOOR 01;35 # door -+SOCK 00;35 # socket -+DOOR 00;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;05;37;41 # ... and the files they point to - SETUID 37;41 # file that is setuid (u+s) - SETGID 30;43 # file that is setgid (g+s) - CAPABILITY 30;41 # file with capability -@@ -65,7 +74,7 @@ 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 files with execute permission: --EXEC 01;32 -+EXEC 00;32 - - # List any file extensions like '.gz' or '.tar' that you would like ls - # to colorize below. Put the extension, a space, and the color init string. -@@ -82,107 +91,107 @@ EXEC 01;32 - #.sh 01;32 - #.csh 01;32 - -- # archives or compressed (bright red) --.tar 01;31 --.tgz 01;31 --.arc 01;31 --.arj 01;31 --.taz 01;31 --.lha 01;31 --.lz4 01;31 --.lzh 01;31 --.lzma 01;31 --.tlz 01;31 --.txz 01;31 --.tzo 01;31 --.t7z 01;31 --.zip 01;31 --.z 01;31 --.Z 01;31 --.dz 01;31 --.gz 01;31 --.lrz 01;31 --.lz 01;31 --.lzo 01;31 --.xz 01;31 --.zst 01;31 --.tzst 01;31 --.bz2 01;31 --.bz 01;31 --.tbz 01;31 --.tbz2 01;31 --.tz 01;31 --.deb 01;31 --.rpm 01;31 --.jar 01;31 --.war 01;31 --.ear 01;31 --.sar 01;31 --.rar 01;31 --.alz 01;31 --.ace 01;31 --.zoo 01;31 --.cpio 01;31 --.7z 01;31 --.rz 01;31 --.cab 01;31 --.wim 01;31 --.swm 01;31 --.dwm 01;31 --.esd 01;31 -+# archives or compressed (red) -+.tar 00;31 -+.tgz 00;31 -+.arc 00;31 -+.arj 00;31 -+.taz 00;31 -+.lha 00;31 -+.lz4 00;31 -+.lzh 00;31 -+.lzma 00;31 -+.tlz 00;31 -+.txz 00;31 -+.tzo 00;31 -+.t7z 00;31 -+.zip 00;31 -+.z 00;31 -+.Z 00;31 -+.dz 00;31 -+.gz 00;31 -+.lrz 00;31 -+.lz 00;31 -+.lzo 00;31 -+.xz 00;31 -+.zst 00;31 -+.tzst 00;31 -+.bz2 00;31 -+.bz 00;31 -+.tbz 00;31 -+.tbz2 00;31 -+.tz 00;31 -+.deb 00;31 -+.rpm 00;31 -+.jar 00;31 -+.war 00;31 -+.ear 00;31 -+.sar 00;31 -+.rar 00;31 -+.alz 00;31 -+.ace 00;31 -+.zoo 00;31 -+.cpio 00;31 -+.7z 00;31 -+.rz 00;31 -+.cab 00;31 -+.wim 00;31 -+.swm 00;31 -+.dwm 00;31 -+.esd 00;31 - - # image formats --.jpg 01;35 --.jpeg 01;35 --.mjpg 01;35 --.mjpeg 01;35 --.gif 01;35 --.bmp 01;35 --.pbm 01;35 --.pgm 01;35 --.ppm 01;35 --.tga 01;35 --.xbm 01;35 --.xpm 01;35 --.tif 01;35 --.tiff 01;35 --.png 01;35 --.svg 01;35 --.svgz 01;35 --.mng 01;35 --.pcx 01;35 --.mov 01;35 --.mpg 01;35 --.mpeg 01;35 --.m2v 01;35 --.mkv 01;35 --.webm 01;35 --.ogm 01;35 --.mp4 01;35 --.m4v 01;35 --.mp4v 01;35 --.vob 01;35 --.qt 01;35 --.nuv 01;35 --.wmv 01;35 --.asf 01;35 --.rm 01;35 --.rmvb 01;35 --.flc 01;35 --.avi 01;35 --.fli 01;35 --.flv 01;35 --.gl 01;35 --.dl 01;35 --.xcf 01;35 --.xwd 01;35 --.yuv 01;35 --.cgm 01;35 --.emf 01;35 -+.jpg 00;35 -+.jpeg 00;35 -+.mjpg 00;35 -+.mjpeg 00;35 -+.gif 00;35 -+.bmp 00;35 -+.pbm 00;35 -+.pgm 00;35 -+.ppm 00;35 -+.tga 00;35 -+.xbm 00;35 -+.xpm 00;35 -+.tif 00;35 -+.tiff 00;35 -+.png 00;35 -+.svg 00;35 -+.svgz 00;35 -+.mng 00;35 -+.pcx 00;35 -+.mov 00;35 -+.mpg 00;35 -+.mpeg 00;35 -+.m2v 00;35 -+.mkv 00;35 -+.webm 00;35 -+.ogm 00;35 -+.mp4 00;35 -+.m4v 00;35 -+.mp4v 00;35 -+.vob 00;35 -+.qt 00;35 -+.nuv 00;35 -+.wmv 00;35 -+.asf 00;35 -+.rm 00;35 -+.rmvb 00;35 -+.flc 00;35 -+.avi 00;35 -+.fli 00;35 -+.flv 00;35 -+.gl 00;35 -+.dl 00;35 -+.xcf 00;35 -+.xwd 00;35 -+.yuv 00;35 -+.cgm 00;35 -+.emf 00;35 - - # https://wiki.xiph.org/MIME_Types_and_File_Extensions --.ogv 01;35 --.ogx 01;35 -+.ogv 00;35 -+.ogx 00;35 - - # audio formats - .aac 00;36 --- -2.5.5 - diff --git a/coreutils-8.26-selinuxenable.patch b/coreutils-8.26-selinuxenable.patch new file mode 100644 index 0000000..d9b625a --- /dev/null +++ b/coreutils-8.26-selinuxenable.patch @@ -0,0 +1,26 @@ +From 6880c3dc9098b3337612850d1500b474aeb944ca Mon Sep 17 00:00:00 2001 +From: Kamil Dudka +Date: Tue, 29 Aug 2017 17:33:51 +0200 +Subject: [PATCH] require_selinux_(): use selinuxenabled(8) if available + +--- + init.cfg | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/init.cfg b/init.cfg +index af6b581..f887b3a 100644 +--- a/init.cfg ++++ b/init.cfg +@@ -114,6 +114,9 @@ require_selinux_() + grep 'selinuxfs$' /proc/filesystems > /dev/null \ + || skip_ "this system lacks SELinux support" + ++ # use the 'selinuxenabled' utility if available ++ selinuxenabled; [ $? = 1 ] && skip_ "SELinux is disabled" ++ + # Independent of whether SELinux is enabled system-wide, + # the current file system may lack SELinux support. + # Also the current build may have SELinux support disabled. +-- +2.9.5 + diff --git a/coreutils-8.27-CVE-2017-7476.patch b/coreutils-8.27-CVE-2017-7476.patch deleted file mode 100644 index 23fdb3f..0000000 --- a/coreutils-8.27-CVE-2017-7476.patch +++ /dev/null @@ -1,189 +0,0 @@ -From fc286e2b3af5b2ed9aec44b520265bb0968f1660 Mon Sep 17 00:00:00 2001 -From: =?UTF-8?q?P=C3=A1draig=20Brady?= -Date: Mon, 24 Apr 2017 01:43:36 -0700 -Subject: [PATCH 1/2] time_rz: fix heap buffer overflow vulnerability - -This issue has been assigned CVE-2017-7476 and was -detected with American Fuzzy Lop 2.41b run on the -coreutils date(1) program with ASAN enabled. - - ERROR: AddressSanitizer: heap-buffer-overflow on address 0x... - WRITE of size 8 at 0x60d00000cff8 thread T0 - #1 0x443020 in extend_abbrs lib/time_rz.c:88 - #2 0x443356 in save_abbr lib/time_rz.c:155 - #3 0x44393f in localtime_rz lib/time_rz.c:290 - #4 0x41e4fe in parse_datetime2 lib/parse-datetime.y:1798 - -A minimized reproducer is the following 120 byte TZ value, -which goes beyond the value of ABBR_SIZE_MIN (119) on x86_64. -Extend the aa...b portion to overwrite more of the heap. - - date -d $(printf 'TZ="aaa%020daaaaaab%089d"') - -localtime_rz and mktime_z were affected since commit 4bc76593. -parse_datetime was affected since commit 4e6e16b3f. - -* lib/time_rz.c (save_abbr): Rearrange the calculation determining -whether there is enough buffer space available. The rearrangement -ensures we're only dealing with positive numbers, thus avoiding -the problematic promotion of signed to unsigned causing an invalid -comparison when zone_copy is more than ABBR_SIZE_MIN bytes beyond -the start of the buffer. -* tests/test-parse-datetime.c (main): Add a test case written by -Paul Eggert, which overwrites enough of the heap so that -standard glibc will fail with "free(): invalid pointer" -without the patch applied. -Reported and analyzed at https://bugzilla.redhat.com/1444774 - -Upstream-commit: 94e01571507835ff59dd8ce2a0b56a4b566965a4 -Signed-off-by: Kamil Dudka ---- - gnulib-tests/test-parse-datetime.c | 16 ++++++++++++++++ - lib/time_rz.c | 15 +++++++++++++-- - 2 files changed, 29 insertions(+), 2 deletions(-) - -diff --git a/gnulib-tests/test-parse-datetime.c b/gnulib-tests/test-parse-datetime.c -index b42a51c..b6fe457 100644 ---- a/gnulib-tests/test-parse-datetime.c -+++ b/gnulib-tests/test-parse-datetime.c -@@ -432,5 +432,21 @@ main (int argc _GL_UNUSED, char **argv) - ASSERT ( parse_datetime (&result, "TZ=\"\\\\\"", &now)); - ASSERT ( parse_datetime (&result, "TZ=\"\\\"\"", &now)); - -+ /* Outlandishly-long time zone abbreviations should not cause problems. */ -+ { -+ static char const bufprefix[] = "TZ=\""; -+ enum { tzname_len = 2000 }; -+ static char const bufsuffix[] = "0\" 1970-01-01 01:02:03.123456789"; -+ enum { bufsize = sizeof bufprefix - 1 + tzname_len + sizeof bufsuffix }; -+ char buf[bufsize]; -+ memcpy (buf, bufprefix, sizeof bufprefix - 1); -+ memset (buf + sizeof bufprefix - 1, 'X', tzname_len); -+ strcpy (buf + bufsize - sizeof bufsuffix, bufsuffix); -+ ASSERT (parse_datetime (&result, buf, &now)); -+ LOG (buf, now, result); -+ ASSERT (result.tv_sec == 1 * 60 * 60 + 2 * 60 + 3 -+ && result.tv_nsec == 123456789); -+ } -+ - return 0; - } -diff --git a/lib/time_rz.c b/lib/time_rz.c -index adb9c1c..c41a8ef 100644 ---- a/lib/time_rz.c -+++ b/lib/time_rz.c -@@ -27,6 +27,7 @@ - #include - - #include -+#include - #include - #include - #include -@@ -35,6 +36,10 @@ - #include "flexmember.h" - #include "time-internal.h" - -+#ifndef SIZE_MAX -+# define SIZE_MAX ((size_t) -1) -+#endif -+ - #if !HAVE_TZSET - static void tzset (void) { } - #endif -@@ -43,7 +48,7 @@ static void tzset (void) { } - the largest "small" request for the GNU C library malloc. */ - enum { DEFAULT_MXFAST = 64 * sizeof (size_t) / 4 }; - --/* Minimum size of the ABBRS member of struct abbr. ABBRS is larger -+/* Minimum size of the ABBRS member of struct tm_zone. ABBRS is larger - only in the unlikely case where an abbreviation longer than this is - used. */ - enum { ABBR_SIZE_MIN = DEFAULT_MXFAST - offsetof (struct tm_zone, abbrs) }; -@@ -150,7 +155,13 @@ save_abbr (timezone_t tz, struct tm *tm) - if (! (*zone_copy || (zone_copy == tz->abbrs && tz->tz_is_set))) - { - size_t zone_size = strlen (zone) + 1; -- if (zone_size < tz->abbrs + ABBR_SIZE_MIN - zone_copy) -+ size_t zone_used = zone_copy - tz->abbrs; -+ if (SIZE_MAX - zone_used < zone_size) -+ { -+ errno = ENOMEM; -+ return false; -+ } -+ if (zone_used + zone_size < ABBR_SIZE_MIN) - extend_abbrs (zone_copy, zone, zone_size); - else - { --- -2.9.3 - - -From 9579f90484c71e5a22f32f35189192a82e47550e Mon Sep 17 00:00:00 2001 -From: =?UTF-8?q?P=C3=A1draig=20Brady?= -Date: Wed, 26 Apr 2017 20:51:39 -0700 -Subject: [PATCH 2/2] date,touch: test and document large TZ security issue - -Add a test for CVE-2017-7476 which was fixed in gnulib at: -http://git.sv.gnu.org/gitweb/?p=gnulib.git;a=commitdiff;h=94e01571 - -* tests/misc/date-tz.sh: Add a new test which overwrites enough -of the heap to trigger a segfault, even without ASAN enabled. -* tests/local.mk: Reference the new test. -* NEWS: Mention the bug fix. - -Upstream-commit: 9287ef2b1707e2a222f8ae776ce3785abcb16fba -Signed-off-by: Kamil Dudka ---- - tests/local.mk | 1 + - tests/misc/date-tz.sh | 26 ++++++++++++++++++++++++++ - 2 files changed, 27 insertions(+) - create mode 100755 tests/misc/date-tz.sh - -diff --git a/tests/local.mk b/tests/local.mk -index 9f1a853..ec0b414 100644 ---- a/tests/local.mk -+++ b/tests/local.mk -@@ -282,6 +282,7 @@ all_tests = \ - tests/misc/csplit-suppress-matched.pl \ - tests/misc/date-debug.sh \ - tests/misc/date-sec.sh \ -+ tests/misc/date-tz.sh \ - tests/misc/dircolors.pl \ - tests/misc/dirname.pl \ - tests/misc/env-null.sh \ -diff --git a/tests/misc/date-tz.sh b/tests/misc/date-tz.sh -new file mode 100755 -index 0000000..3fe1579 ---- /dev/null -+++ b/tests/misc/date-tz.sh -@@ -0,0 +1,26 @@ -+#!/bin/sh -+# Verify TZ processing. -+ -+# Copyright (C) 2017 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_ date -+ -+# coreutils-8.27 would overwrite the heap with large TZ values -+tz_long=$(printf '%2000s' | tr ' ' a) -+date -d "TZ=\"${tz_long}0\" 2017" || fail=1 -+ -+Exit $fail --- -2.9.3 - diff --git a/coreutils-8.27-date-debug-test.patch b/coreutils-8.27-date-debug-test.patch deleted file mode 100644 index a8def7b..0000000 --- a/coreutils-8.27-date-debug-test.patch +++ /dev/null @@ -1,50 +0,0 @@ -From ee2017f191f1ad177405fbd8816df0a55127804a Mon Sep 17 00:00:00 2001 -From: Paul Eggert -Date: Thu, 9 Mar 2017 23:59:05 -0800 -Subject: [PATCH] tests: port to tzdb-2017a - -Problem reported by Bernhard Voelker in: -http://lists.gnu.org/archive/html/coreutils/2017-03/msg00026.html -* tests/misc/date-debug.sh: Port test to tzdb 2017a, -and future-proof the America/Belize test. - -Upstream-commit: 612086660bab9bf981894da146550e9101224b17 -Signed-off-by: Kamil Dudka ---- - tests/misc/date-debug.sh | 9 +++++---- - 1 file changed, 5 insertions(+), 4 deletions(-) - -diff --git a/tests/misc/date-debug.sh b/tests/misc/date-debug.sh -index 48f4605..8e0b2af 100755 ---- a/tests/misc/date-debug.sh -+++ b/tests/misc/date-debug.sh -@@ -52,10 +52,11 @@ date: output timezone: +09:00 (set from TZ="Asia/Tokyo" environment value) - date: final: 661095000.000000000 (epoch-seconds) - date: final: (Y-M-D) 1990-12-13 13:30:00 (UTC0) - date: final: (Y-M-D) 1990-12-13 22:30:00 (output timezone TZ=+09:00) --Thu Dec 13 07:30:00 CST 1990 -+Thu Dec 13 07:30:00 -0600 1990 - EOF - --TZ=America/Belize date --debug -d "$in1" >out1 2>&1 || fail=1 -+TZ=America/Belize date --debug -d "$in1" +'%a %b %e %T %z %Y' >out1 2>&1 || -+ fail=1 - - compare exp1 out1 || fail=1 - -@@ -94,10 +95,10 @@ date: output timezone: -05:00 (set from TZ="America/Lima" environment value) - date: final: 1.000000000 (epoch-seconds) - date: final: (Y-M-D) 1970-01-01 00:00:01 (UTC0) - date: final: (Y-M-D) 1969-12-31 19:00:01 (output timezone TZ=-05:00) --Wed Dec 31 19:00:01 PET 1969 -+Wed Dec 31 19:00:01 -0500 1969 - EOF - --TZ=America/Lima date --debug -d "$in3" >out3 2>&1 || fail=1 -+TZ=America/Lima date --debug -d "$in3" +'%a %b %e %T %z %Y' >out3 2>&1 || fail=1 - compare exp3 out3 || fail=1 - - ## --- -2.9.3 - diff --git a/coreutils-8.27-ptx-int-overflow.patch b/coreutils-8.27-ptx-int-overflow.patch deleted file mode 100644 index 897c2ad..0000000 --- a/coreutils-8.27-ptx-int-overflow.patch +++ /dev/null @@ -1,547 +0,0 @@ -From 7408a9758924a1ccbabf9fcab401a31ef1b7c755 Mon Sep 17 00:00:00 2001 -From: Paul Eggert -Date: Thu, 17 Aug 2017 12:02:16 -0700 -Subject: [PATCH] ptx: fix some integer overflow bugs -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -Problem reported by Lukas Zachar at: -http://bugzilla.redhat.com/1482445 -* src/ptx.c (line_width, gap_size, maximum_word_length) -(reference_max_width, half_line_width, before_max_width) -(keyafter_max_width, truncation_string_length, compare_words) -(compare_occurs, search_table, find_occurs_in_text, print_spaces) -(fix_output_parameters, define_all_fields): -Use ptrdiff_t, not int, for object offsets and sizes. -(WORD, OCCURS): Use ptrdiff_t, not short int. -(WORD_TABLE, number_of_occurs, generate_all_output): -Prefer ptrdiff_t to size_t where either will do. -(total_line_count, file_line_count, OCCURS, fix_output_parameters) -(define_all_fields): -Use intmax_t, not int, for line counts. -(DELTA): Remove. All uses changed. -(OCCURS, find_occurs_in_text, fix_output_parameters): -Use int, not size_t, for file indexes. -(tail_truncation, before_truncation, keyafter_truncation) -(head_truncation, search_table, define_all_fields) -(generate_all_output): -Use bool for booleans. -(digest_word_file, find_occurs_in_text): -Use x2nrealloc instead of checking for overflow by hand. -(find_occurs_in_text, fix_output_parameters, define_all_fields): -Omit unnecessary cast. -(fix_output_parameters): Don’t assume integers fit in 11 digits. -(fix_output_parameters, define_all_fields): -Use sprintf return value rather than calling strlen. -(define_all_fields): Do not rely on sprintf to generate a string -that may contain more than INT_MAX bytes. -(main): Use xstrtoimax, not xstrtoul. -Use xnmalloc to catch integer overflow. - -Upstream-commit: 1d9765a764790cc68ec52c16d7ccbf633c404f0e -Signed-off-by: Kamil Dudka ---- - src/ptx.c | 194 +++++++++++++++++++++++++++++--------------------------------- - 1 file changed, 91 insertions(+), 103 deletions(-) - -diff --git a/src/ptx.c b/src/ptx.c -index c0c9733..2aababf 100644 ---- a/src/ptx.c -+++ b/src/ptx.c -@@ -59,9 +59,9 @@ - /* Global definitions. */ - - /* FIXME: There are many unchecked integer overflows in this file, -- that will cause this command to misbehave given large inputs or -- options. Many of the "int" values below should be "size_t" or -- something else like that. */ -+ and in theory they could cause this command to have undefined -+ behavior given large inputs or options. This command should -+ diagnose any such overflow and exit. */ - - /* Program options. */ - -@@ -77,8 +77,8 @@ static bool gnu_extensions = true; /* trigger all GNU extensions */ - static bool auto_reference = false; /* refs are 'file_name:line_number:' */ - static bool input_reference = false; /* refs at beginning of input lines */ - static bool right_reference = false; /* output refs after right context */ --static int line_width = 72; /* output line width in characters */ --static int gap_size = 3; /* number of spaces between output fields */ -+static ptrdiff_t line_width = 72; /* output line width in characters */ -+static ptrdiff_t gap_size = 3; /* number of spaces between output fields */ - static const char *truncation_string = "/"; - /* string used to mark line truncations */ - static const char *macro_name = "xx"; /* macro name for roff or TeX output */ -@@ -105,8 +105,8 @@ static struct regex_data context_regex; /* end of context */ - static struct regex_data word_regex; /* keyword */ - - /* A BLOCK delimit a region in memory of arbitrary size, like the copy of a -- whole file. A WORD is something smaller, its length should fit in a -- short integer. A WORD_TABLE may contain several WORDs. */ -+ whole file. A WORD is similar, except it is intended for smaller regions. -+ A WORD_TABLE may contain several WORDs. */ - - typedef struct - { -@@ -118,7 +118,7 @@ BLOCK; - typedef struct - { - char *start; /* pointer to beginning of region */ -- short int size; /* length of the region */ -+ ptrdiff_t size; /* length of the region */ - } - WORD; - -@@ -126,7 +126,7 @@ typedef struct - { - WORD *start; /* array of WORDs */ - size_t alloc; /* allocated length */ -- size_t length; /* number of used entries */ -+ ptrdiff_t length; /* number of used entries */ - } - WORD_TABLE; - -@@ -149,10 +149,10 @@ static struct re_registers word_regs; - static char word_fastmap[CHAR_SET_SIZE]; - - /* Maximum length of any word read. */ --static int maximum_word_length; -+static ptrdiff_t maximum_word_length; - - /* Maximum width of any reference used. */ --static int reference_max_width; -+static ptrdiff_t reference_max_width; - - /* Ignore and Only word tables. */ - -@@ -162,9 +162,9 @@ static WORD_TABLE only_table; /* table of words to select */ - /* Source text table, and scanning macros. */ - - static int number_input_files; /* number of text input files */ --static int total_line_count; /* total number of lines seen so far */ -+static intmax_t total_line_count; /* total number of lines seen so far */ - static const char **input_file_name; /* array of text input file names */ --static int *file_line_count; /* array of 'total_line_count' values at end */ -+static intmax_t *file_line_count; /* array of line count values at end */ - - static BLOCK *text_buffers; /* files to study */ - -@@ -219,20 +219,18 @@ static BLOCK *text_buffers; /* files to study */ - - When automatic references are used, the 'reference' value is the - overall line number in all input files read so far, in this case, it -- is of type (int). When input references are used, the 'reference' -+ is of type intmax_t. When input references are used, the 'reference' - value indicates the distance between the keyword beginning and the -- start of the reference field, it is of type (DELTA) and usually -+ start of the reference field, and it fits in ptrdiff_t and is usually - negative. */ - --typedef short int DELTA; /* to hold displacement within one context */ -- - typedef struct - { - WORD key; /* description of the keyword */ -- DELTA left; /* distance to left context start */ -- DELTA right; /* distance to right context end */ -- int reference; /* reference descriptor */ -- size_t file_index; /* corresponding file */ -+ ptrdiff_t left; /* distance to left context start */ -+ ptrdiff_t right; /* distance to right context end */ -+ intmax_t reference; /* reference descriptor */ -+ int file_index; /* corresponding file */ - } - OCCURS; - -@@ -241,7 +239,7 @@ OCCURS; - - static OCCURS *occurs_table[1]; /* all words retained from the read text */ - static size_t occurs_alloc[1]; /* allocated size of occurs_table */ --static size_t number_of_occurs[1]; /* number of used slots in occurs_table */ -+static ptrdiff_t number_of_occurs[1]; /* number of used slots in occurs_table */ - - - /* Communication among output routines. */ -@@ -249,10 +247,17 @@ static size_t number_of_occurs[1]; /* number of used slots in occurs_table */ - /* Indicate if special output processing is requested for each character. */ - static char edited_flag[CHAR_SET_SIZE]; - --static int half_line_width; /* half of line width, reference excluded */ --static int before_max_width; /* maximum width of before field */ --static int keyafter_max_width; /* maximum width of keyword-and-after field */ --static int truncation_string_length;/* length of string that flags truncation */ -+/* Half of line width, reference excluded. */ -+static ptrdiff_t half_line_width; -+ -+/* Maximum width of before field. */ -+static ptrdiff_t before_max_width; -+ -+/* Maximum width of keyword-and-after field. */ -+static ptrdiff_t keyafter_max_width; -+ -+/* Length of string that flags truncation. */ -+static ptrdiff_t truncation_string_length; - - /* When context is limited by lines, wraparound may happen on final output: - the 'head' pointer gives access to some supplementary left context which -@@ -261,16 +266,16 @@ static int truncation_string_length;/* length of string that flags truncation */ - beginning of the output line. */ - - static BLOCK tail; /* tail field */ --static int tail_truncation; /* flag truncation after the tail field */ -+static bool tail_truncation; /* flag truncation after the tail field */ - - static BLOCK before; /* before field */ --static int before_truncation; /* flag truncation before the before field */ -+static bool before_truncation; /* flag truncation before the before field */ - - static BLOCK keyafter; /* keyword-and-after field */ --static int keyafter_truncation; /* flag truncation after the keyafter field */ -+static bool keyafter_truncation; /* flag truncation after the keyafter field */ - - static BLOCK head; /* head field */ --static int head_truncation; /* flag truncation before the head field */ -+static bool head_truncation; /* flag truncation before the head field */ - - static BLOCK reference; /* reference field for input reference mode */ - -@@ -540,8 +545,8 @@ compare_words (const void *void_first, const void *void_second) - { - #define first ((const WORD *) void_first) - #define second ((const WORD *) void_second) -- int length; /* minimum of two lengths */ -- int counter; /* cursor in words */ -+ ptrdiff_t length; /* minimum of two lengths */ -+ ptrdiff_t counter; /* cursor in words */ - int value; /* value of comparison */ - - length = first->size < second->size ? first->size : second->size; -@@ -567,7 +572,7 @@ compare_words (const void *void_first, const void *void_second) - } - } - -- return first->size - second->size; -+ return first->size < second->size ? -1 : first->size > second->size; - #undef first - #undef second - } -@@ -586,21 +591,21 @@ compare_occurs (const void *void_first, const void *void_second) - int value; - - value = compare_words (&first->key, &second->key); -- return value == 0 ? first->key.start - second->key.start : value; -+ return (value ? value -+ : first->key.start < second->key.start ? -1 -+ : first->key.start > second->key.start); - #undef first - #undef second - } - --/*------------------------------------------------------------. --| Return !0 if WORD appears in TABLE. Uses a binary search. | --`------------------------------------------------------------*/ -+/* True if WORD appears in TABLE. Uses a binary search. */ - --static int _GL_ATTRIBUTE_PURE -+static bool _GL_ATTRIBUTE_PURE - search_table (WORD *word, WORD_TABLE *table) - { -- int lowest; /* current lowest possible index */ -- int highest; /* current highest possible index */ -- int middle; /* current middle index */ -+ ptrdiff_t lowest; /* current lowest possible index */ -+ ptrdiff_t highest; /* current highest possible index */ -+ ptrdiff_t middle; /* current middle index */ - int value; /* value from last comparison */ - - lowest = 0; -@@ -614,9 +619,9 @@ search_table (WORD *word, WORD_TABLE *table) - else if (value > 0) - lowest = middle + 1; - else -- return 1; -+ return true; - } -- return 0; -+ return false; - } - - /*---------------------------------------------------------------------. -@@ -713,14 +718,8 @@ digest_word_file (const char *file_name, WORD_TABLE *table) - if (cursor > word_start) - { - if (table->length == table->alloc) -- { -- if ((SIZE_MAX / sizeof *table->start - 1) / 2 < table->alloc) -- xalloc_die (); -- table->alloc = table->alloc * 2 + 1; -- table->start = xrealloc (table->start, -- table->alloc * sizeof *table->start); -- } -- -+ table->start = x2nrealloc (table->start, &table->alloc, -+ sizeof *table->start); - table->start[table->length].start = word_start; - table->start[table->length].size = cursor - word_start; - table->length++; -@@ -744,13 +743,13 @@ digest_word_file (const char *file_name, WORD_TABLE *table) - `----------------------------------------------------------------------*/ - - static void --find_occurs_in_text (size_t file_index) -+find_occurs_in_text (int file_index) - { - char *cursor; /* for scanning the source text */ - char *scan; /* for scanning the source text also */ - char *line_start; /* start of the current input line */ - char *line_scan; /* newlines scanned until this point */ -- int reference_length; /* length of reference in input mode */ -+ ptrdiff_t reference_length; /* length of reference in input mode */ - WORD possible_key; /* possible key, to ease searches */ - OCCURS *occurs_cursor; /* current OCCURS under construction */ - -@@ -946,16 +945,9 @@ find_occurs_in_text (size_t file_index) - where it will be constructed. */ - - if (number_of_occurs[0] == occurs_alloc[0]) -- { -- if ((SIZE_MAX / sizeof *occurs_table[0] - 1) / 2 -- < occurs_alloc[0]) -- xalloc_die (); -- occurs_alloc[0] = occurs_alloc[0] * 2 + 1; -- occurs_table[0] = -- xrealloc (occurs_table[0], -- occurs_alloc[0] * sizeof *occurs_table[0]); -- } -- -+ occurs_table[0] = x2nrealloc (occurs_table[0], -+ &occurs_alloc[0], -+ sizeof *occurs_table[0]); - occurs_cursor = occurs_table[0] + number_of_occurs[0]; - - /* Define the reference field, if any. */ -@@ -990,8 +982,7 @@ find_occurs_in_text (size_t file_index) - of the reference. The reference position is simply the - value of 'line_start'. */ - -- occurs_cursor->reference -- = (DELTA) (line_start - possible_key.start); -+ occurs_cursor->reference = line_start - possible_key.start; - if (reference_length > reference_max_width) - reference_max_width = reference_length; - } -@@ -1023,11 +1014,9 @@ find_occurs_in_text (size_t file_index) - `-----------------------------------------*/ - - static void --print_spaces (int number) -+print_spaces (ptrdiff_t number) - { -- int counter; -- -- for (counter = number; counter > 0; counter--) -+ for (ptrdiff_t counter = number; counter > 0; counter--) - putchar (' '); - } - -@@ -1200,10 +1189,9 @@ print_field (BLOCK field) - static void - fix_output_parameters (void) - { -- size_t file_index; /* index in text input file arrays */ -- int line_ordinal; /* line ordinal value for reference */ -- char ordinal_string[12]; /* edited line ordinal for reference */ -- int reference_width; /* width for the whole reference */ -+ int file_index; /* index in text input file arrays */ -+ intmax_t line_ordinal; /* line ordinal value for reference */ -+ ptrdiff_t reference_width; /* width for the whole reference */ - int character; /* character ordinal */ - const char *cursor; /* cursor in some constant strings */ - -@@ -1219,15 +1207,15 @@ fix_output_parameters (void) - line_ordinal = file_line_count[file_index] + 1; - if (file_index > 0) - line_ordinal -= file_line_count[file_index - 1]; -- sprintf (ordinal_string, "%d", line_ordinal); -- reference_width = strlen (ordinal_string); -+ char ordinal_string[INT_BUFSIZE_BOUND (intmax_t)]; -+ reference_width = sprintf (ordinal_string, "%"PRIdMAX, line_ordinal); - if (input_file_name[file_index]) - reference_width += strlen (input_file_name[file_index]); - if (reference_width > reference_max_width) - reference_max_width = reference_width; - } - reference_max_width++; -- reference.start = xmalloc ((size_t) reference_max_width + 1); -+ reference.start = xmalloc (reference_max_width + 1); - } - - /* If the reference appears to the left of the output line, reserve some -@@ -1355,14 +1343,14 @@ fix_output_parameters (void) - static void - define_all_fields (OCCURS *occurs) - { -- int tail_max_width; /* allowable width of tail field */ -- int head_max_width; /* allowable width of head field */ -+ ptrdiff_t tail_max_width; /* allowable width of tail field */ -+ ptrdiff_t head_max_width; /* allowable width of head field */ - char *cursor; /* running cursor in source text */ - char *left_context_start; /* start of left context */ - char *right_context_end; /* end of right context */ - char *left_field_start; /* conservative start for 'head'/'before' */ - const char *file_name; /* file name for reference */ -- int line_ordinal; /* line ordinal for reference */ -+ intmax_t line_ordinal; /* line ordinal for reference */ - const char *buffer_start; /* start of buffered file for this occurs */ - const char *buffer_end; /* end of buffered file for this occurs */ - -@@ -1435,7 +1423,7 @@ define_all_fields (OCCURS *occurs) - before_truncation = cursor > left_context_start; - } - else -- before_truncation = 0; -+ before_truncation = false; - - SKIP_WHITE (before.start, buffer_end); - -@@ -1468,11 +1456,11 @@ define_all_fields (OCCURS *occurs) - - if (tail.end > tail.start) - { -- keyafter_truncation = 0; -+ keyafter_truncation = false; - tail_truncation = truncation_string && tail.end < right_context_end; - } - else -- tail_truncation = 0; -+ tail_truncation = false; - - SKIP_WHITE_BACKWARDS (tail.end, tail.start); - } -@@ -1483,7 +1471,7 @@ define_all_fields (OCCURS *occurs) - - tail.start = NULL; - tail.end = NULL; -- tail_truncation = 0; -+ tail_truncation = false; - } - - /* 'head' could not take more columns than what has been left in the right -@@ -1506,12 +1494,12 @@ define_all_fields (OCCURS *occurs) - - if (head.end > head.start) - { -- before_truncation = 0; -+ before_truncation = false; - head_truncation = (truncation_string - && head.start > left_context_start); - } - else -- head_truncation = 0; -+ head_truncation = false; - - SKIP_WHITE (head.start, head.end); - } -@@ -1522,7 +1510,7 @@ define_all_fields (OCCURS *occurs) - - head.start = NULL; - head.end = NULL; -- head_truncation = 0; -+ head_truncation = false; - } - - if (auto_reference) -@@ -1540,8 +1528,8 @@ define_all_fields (OCCURS *occurs) - if (occurs->file_index > 0) - line_ordinal -= file_line_count[occurs->file_index - 1]; - -- sprintf (reference.start, "%s:%d", file_name, line_ordinal); -- reference.end = reference.start + strlen (reference.start); -+ char *file_end = stpcpy (reference.start, file_name); -+ reference.end = file_end + sprintf (file_end, ":%"PRIdMAX, line_ordinal); - } - else if (input_reference) - { -@@ -1549,7 +1537,7 @@ define_all_fields (OCCURS *occurs) - /* Reference starts at saved position for reference and extends right - until some white space is met. */ - -- reference.start = keyafter.start + (DELTA) occurs->reference; -+ reference.start = keyafter.start + occurs->reference; - reference.end = reference.start; - SKIP_NON_WHITE (reference.end, right_context_end); - } -@@ -1753,7 +1741,7 @@ output_one_dumb_line (void) - static void - generate_all_output (void) - { -- size_t occurs_index; /* index of keyword entry being processed */ -+ ptrdiff_t occurs_index; /* index of keyword entry being processed */ - OCCURS *occurs_cursor; /* current keyword entry being processed */ - - /* The following assignments are useful to provide default values in case -@@ -1762,11 +1750,11 @@ generate_all_output (void) - - tail.start = NULL; - tail.end = NULL; -- tail_truncation = 0; -+ tail_truncation = false; - - head.start = NULL; - head.end = NULL; -- head_truncation = 0; -+ head_truncation = false; - - /* Loop over all keyword occurrences. */ - -@@ -1946,12 +1934,12 @@ main (int argc, char **argv) - - case 'g': - { -- unsigned long int tmp_ulong; -- if (xstrtoul (optarg, NULL, 0, &tmp_ulong, NULL) != LONGINT_OK -- || ! (0 < tmp_ulong && tmp_ulong <= INT_MAX)) -+ intmax_t tmp; -+ if (! (xstrtoimax (optarg, NULL, 0, &tmp, NULL) == LONGINT_OK -+ && 0 < tmp && tmp <= PTRDIFF_MAX)) - die (EXIT_FAILURE, 0, _("invalid gap width: %s"), - quote (optarg)); -- gap_size = tmp_ulong; -+ gap_size = tmp; - break; - } - -@@ -1973,12 +1961,12 @@ main (int argc, char **argv) - - case 'w': - { -- unsigned long int tmp_ulong; -- if (xstrtoul (optarg, NULL, 0, &tmp_ulong, NULL) != LONGINT_OK -- || ! (0 < tmp_ulong && tmp_ulong <= INT_MAX)) -+ intmax_t tmp; -+ if (! (xstrtoimax (optarg, NULL, 0, &tmp, NULL) == LONGINT_OK -+ && 0 < tmp && tmp <= PTRDIFF_MAX)) - die (EXIT_FAILURE, 0, _("invalid line width: %s"), - quote (optarg)); -- line_width = tmp_ulong; -+ line_width = tmp; - break; - } - -@@ -2045,9 +2033,9 @@ main (int argc, char **argv) - else if (gnu_extensions) - { - number_input_files = argc - optind; -- input_file_name = xmalloc (number_input_files * sizeof *input_file_name); -- file_line_count = xmalloc (number_input_files * sizeof *file_line_count); -- text_buffers = xmalloc (number_input_files * sizeof *text_buffers); -+ input_file_name = xnmalloc (number_input_files, sizeof *input_file_name); -+ file_line_count = xnmalloc (number_input_files, sizeof *file_line_count); -+ text_buffers = xnmalloc (number_input_files, sizeof *text_buffers); - - for (file_index = 0; file_index < number_input_files; file_index++) - { --- -2.9.5 - diff --git a/coreutils-8.27-runcon-doc.patch b/coreutils-8.27-runcon-doc.patch deleted file mode 100644 index 41c0a8a..0000000 --- a/coreutils-8.27-runcon-doc.patch +++ /dev/null @@ -1,33 +0,0 @@ -From 76be8a7f9eb717b3d47009eb25d39fe7139a2c2d Mon Sep 17 00:00:00 2001 -From: Sebastian Kisela -Date: Tue, 30 May 2017 09:29:32 +0200 -Subject: [PATCH] doc: mention `setpriv --no-new-privs` feature in runcon info - -upstream commit: 6ebaf8195000d6d3590a2eac13f13b158e325452 ---- - doc/coreutils.texi | 9 ++++++++- - 1 file changed, 8 insertions(+), 1 deletion(-) - -diff --git a/doc/coreutils.texi b/doc/coreutils.texi -index 68df075..e16e885 100644 ---- a/doc/coreutils.texi -+++ b/doc/coreutils.texi -@@ -16583,7 +16583,14 @@ are interpreted as arguments to the command. - With neither @var{context} nor @var{command}, print the current - security context. - --The program accepts the following options. Also see @ref{Common options}. -+@cindex restricted security context -+@cindex NO_NEW_PRIVS -+Note also the @command{setpriv} command which can be used to set the -+NO_NEW_PRIVS bit using @command{setpriv --no-new-privs runcon ...}, -+thus disallowing usage of a security context with more privileges -+than the process would normally have. -+ -+@command{runcon} accepts the following options. Also see @ref{Common options}. - - @table @samp - --- -2.9.4 - diff --git a/coreutils-8.27-tail-inotify-recreate.patch b/coreutils-8.27-tail-inotify-recreate.patch deleted file mode 100644 index 1a63655..0000000 --- a/coreutils-8.27-tail-inotify-recreate.patch +++ /dev/null @@ -1,168 +0,0 @@ -From ba5fe2d4b8b6a8366f48b1ad1f97fe26c9089b53 Mon Sep 17 00:00:00 2001 -From: Sebastian Kisela -Date: Wed, 5 Apr 2017 09:40:41 +0200 -Subject: [PATCH] tail: revert to polling if a followed directory is replaced - -* src/tail.c (tail_forever_inotify): Add the IN_DELETE_SELF flag when -creating watch for the parent directory. After the parent directory -is removed, an event is caught and then we switch from inotify to -polling mode. Till now, inotify has always frozen because it waited for -an event from a watched dir, which has been already deleted and was not -added again. -* tests/tail-2/inotify-dir-recreate.sh: Add a test case. -* tests/local.mk: Reference the new test. -Fixes http://bugs.gnu.org/26363 -Reported at https://bugzilla.redhat.com/1283760 - -Upstream-commit: ba5fe2d4b8b6a8366f48b1ad1f97fe26c9089b53 - ---- - src/tail.c | 22 +++++++++- - tests/local.mk | 1 + - tests/tail-2/inotify-dir-recreate.sh | 82 ++++++++++++++++++++++++++++++++++++ - 4 files changed, 107 insertions(+), 1 deletion(-) - create mode 100755 tests/tail-2/inotify-dir-recreate.sh - -diff --git a/src/tail.c b/src/tail.c -index d1552d4..6328fe0 100644 ---- a/src/tail.c -+++ b/src/tail.c -@@ -1457,7 +1457,8 @@ tail_forever_inotify (int wd, struct File_spec *f, size_t n_files, - In that case the same watch descriptor is returned. */ - f[i].parent_wd = inotify_add_watch (wd, dirlen ? f[i].name : ".", - (IN_CREATE | IN_DELETE -- | IN_MOVED_TO | IN_ATTRIB)); -+ | IN_MOVED_TO | IN_ATTRIB -+ | IN_DELETE_SELF)); - - f[i].name[dirlen] = prev; - -@@ -1628,6 +1629,25 @@ tail_forever_inotify (int wd, struct File_spec *f, size_t n_files, - ev = void_ev; - evbuf_off += sizeof (*ev) + ev->len; - -+ /* If a directory is deleted, IN_DELETE_SELF is emitted -+ with ev->name of length 0. -+ We need to catch it, otherwise it would wait forever, -+ as wd for directory becomes inactive. Revert to polling now. */ -+ if ((ev->mask & IN_DELETE_SELF) && ! ev->len) -+ { -+ for (i = 0; i < n_files; i++) -+ { -+ if (ev->wd == f[i].parent_wd) -+ { -+ hash_free (wd_to_name); -+ error (0, 0, -+ _("directory containing watched file was removed")); -+ errno = 0; /* we've already diagnosed enough errno detail. */ -+ return true; -+ } -+ } -+ } -+ - if (ev->len) /* event on ev->name in watched directory. */ - { - size_t j; -diff --git a/tests/local.mk b/tests/local.mk -index 3fe9ba8..e890c9a 100644 ---- a/tests/local.mk -+++ b/tests/local.mk -@@ -176,6 +176,7 @@ all_tests = \ - tests/tail-2/descriptor-vs-rename.sh \ - tests/tail-2/inotify-rotate.sh \ - tests/tail-2/inotify-rotate-resources.sh \ -+ tests/tail-2/inotify-dir-recreate.sh \ - tests/chmod/no-x.sh \ - tests/chgrp/basic.sh \ - tests/rm/dangling-symlink.sh \ -diff --git a/tests/tail-2/inotify-dir-recreate.sh b/tests/tail-2/inotify-dir-recreate.sh -new file mode 100755 -index 0000000..eaa8422 ---- /dev/null -+++ b/tests/tail-2/inotify-dir-recreate.sh -@@ -0,0 +1,82 @@ -+#!/bin/sh -+# Makes sure, inotify will switch to polling mode if directory -+# of the watched file was removed and recreated. -+# (...instead of getting stuck forever) -+ -+# Copyright (C) 2006-2017 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_ tail -+ -+ -+# Terminate any background tail process -+cleanup_() { kill $pid 2>/dev/null && wait $pid; } -+ -+cleanup_fail_ () -+{ -+ warn_ $1 -+ cleanup_ -+ fail=1 -+} -+ -+# $check_re - string to be found -+# $check_f - file to be searched -+check_tail_output_ () -+{ -+ local delay="$1" -+ grep $check_re $check_f > /dev/null || -+ { sleep $delay ; return 1; } -+} -+ -+grep_timeout_ () -+{ -+ check_re="$1" -+ check_f="$2" -+ retry_delay_ check_tail_output_ .1 5 -+} -+ -+# Prepare the file to be watched -+mkdir dir && echo 'inotify' > dir/file || framework_failure_ -+ -+#tail must print content of the file to stdout, verify -+timeout 60 tail -F dir/file &>out & pid=$! -+grep_timeout_ 'inotify' 'out' || -+{ cleanup_fail_ 'file to be tailed does not exist'; } -+ -+# Remove the directory, should get the message about the deletion -+rm -r dir || framework_failure_ -+grep_timeout_ 'polling' 'out' || -+{ cleanup_fail_ 'tail did not switch to polling mode'; } -+ -+# Recreate the dir, must get a message about recreation -+mkdir dir && touch dir/file || framework_failure_ -+grep_timeout_ 'appeared' 'out' || -+{ cleanup_fail_ 'previously removed file did not appear'; } -+ -+cleanup_ -+ -+# Expected result for the whole process -+cat <<\EOF > exp || framework_failure_ -+inotify -+tail: 'dir/file' has become inaccessible: No such file or directory -+tail: directory containing watched file was removed -+tail: inotify cannot be used, reverting to polling -+tail: 'dir/file' has appeared; following new file -+EOF -+ -+compare exp out || fail=1 -+ -+Exit $fail --- -2.9.3 - diff --git a/coreutils-8.27.tar.xz.sig b/coreutils-8.27.tar.xz.sig deleted file mode 100644 index 7555c00..0000000 --- a/coreutils-8.27.tar.xz.sig +++ /dev/null @@ -1,16 +0,0 @@ ------BEGIN PGP SIGNATURE----- - -iQIcBAABAgAGBQJYwOwaAAoJEN9v2XEwYDfZQrUP/RdXj/ug35e+u+VD1ts9/b8n -7JihJmxngEZQAJECNTMbJ7mNj6DhpMY0Jg/Hwg7zJT28T6QDeS1Iuk3Id4uM5eFa -CgHKAZumntSMTkQdNvnCEFEIqu+L8BtBYGcOaw66wAFNFw3jdJUUs2sOST2r46jR -N7aY9oARKJuHfgTZ2BI2zL0Q+poXM1O0k/U+BScE6c139zJsbg+1uM9kGVtJWPkM -EPLFWkbTgjYnt+qEFrDlWL0YFOS42sgR7P1sVfBC1nAu5lwgzPy62OtGv9WCEBhm -3+PRNZ0KLW8CKp06llG/0bG4QwssWs6p/vPwrRGeAg6pKsRNN1ni27AnDThiPgvz -YbBLgU+EZj1HuibvYArHXNKY2+O5ZC3nYU6bdAffl3TAtrGFA1ncZXGiFD5UgOQ2 -V9Q38S41FUEwKGtf9tWGCRTxrb4FQ1CDzJglV9vHKetn4mgH/HpEG/q07k4RNW5d -ikfrS0xFxbqtLjlY3UqvtkrFyVQFY093ozsP7fKsq53JAtEWc3YvXR8UCbliU+gV -5qug0REBQafe9EAyH+oq0dzD2BZ3KtFcjtKI/2UzAf3idcyygsHgcEPQObqI8BfD -NscEMjdFY7+Zh5w2shQlyq4xr2aI2nXCX3+AMcS/6Yfg6W6fBvgIjtmXBrQsbWpV -DBcx50TVDa/ERBX1+FI1 -=skPR ------END PGP SIGNATURE----- diff --git a/coreutils-8.32-DIR_COLORS.patch b/coreutils-8.32-DIR_COLORS.patch new file mode 100644 index 0000000..37ce3e6 --- /dev/null +++ b/coreutils-8.32-DIR_COLORS.patch @@ -0,0 +1,100 @@ +From bca11e30e8a6281a8cbddc9fb196dd86ab09c955 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 + +--- + DIR_COLORS | 9 ++++++++- + DIR_COLORS.lightbgcolor | 21 +++++++++++++++------ + 2 files changed, 23 insertions(+), 7 deletions(-) + +diff --git a/DIR_COLORS b/DIR_COLORS +index 540f6cd..b4785b6 100644 +--- a/DIR_COLORS ++++ b/DIR_COLORS +@@ -1,3 +1,7 @@ ++# This file goes in the /etc directory, and must be world readable. ++# You can override the system defaults by making a copy of this file ++# as ~/.dir_colors ++ + # Configuration file for dircolors, a utility to help you set the + # LS_COLORS environment variable used by GNU ls with the --color option. + +@@ -11,6 +15,9 @@ + + # Global config options can be specified before TERM or COLORTERM entries + ++# For compatibility, the pattern "^COLOR.*none" is recognized as a way to ++# disable colorization. See https://bugzilla.redhat.com/1349579 for details. ++ + # =================================================================== + # Terminal filters + # =================================================================== +@@ -70,7 +77,7 @@ 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) +diff --git a/DIR_COLORS.lightbgcolor b/DIR_COLORS.lightbgcolor +index e3b0ec3..39a0a4c 100644 +--- a/DIR_COLORS.lightbgcolor ++++ b/DIR_COLORS.lightbgcolor +@@ -1,3 +1,9 @@ ++# Configuration file for the color ls utility - modified for lighter backgrounds ++ ++# This file goes in the /etc directory, and must be world readable. ++# You can override the system defaults by making a copy of this file ++# as ~/.dir_colors ++ + # Configuration file for dircolors, a utility to help you set the + # LS_COLORS environment variable used by GNU ls with the --color option. + +@@ -11,6 +17,9 @@ + + # Global config options can be specified before TERM or COLORTERM entries + ++# For compatibility, the pattern "^COLOR.*none" is recognized as a way to ++# disable colorization. See https://bugzilla.redhat.com/1349579 for details. ++ + # =================================================================== + # Terminal filters + # =================================================================== +@@ -60,17 +69,17 @@ TERM xterm* + #NORMAL 00 # no color code at all + #FILE 00 # regular file: use no color at all + RESET 0 # reset to "normal" color +-DIR 01;34 # directory +-LINK 01;36 # symbolic link. (If you set this to 'target' instead of a ++DIR 00;34 # directory ++LINK 00;36 # symbolic link. (If you set this to 'target' instead of a + # numerical value, the color is as for the file pointed to.) + MULTIHARDLINK 00 # regular file with more than one link + FIFO 40;33 # pipe +-SOCK 01;35 # socket +-DOOR 01;35 # door ++SOCK 00;35 # socket ++DOOR 00;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) +@@ -79,7 +88,7 @@ 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: +-EXEC 01;32 ++EXEC 00;32 + + # =================================================================== + # File extension attributes +-- +2.49.0 + diff --git a/coreutils-8.4-mkdir-modenote.patch b/coreutils-8.4-mkdir-modenote.patch deleted file mode 100644 index 51a129e..0000000 --- a/coreutils-8.4-mkdir-modenote.patch +++ /dev/null @@ -1,13 +0,0 @@ -diff --git a/doc/coreutils.texi b/doc/coreutils.texi -index 400e135..47e4480 100644 ---- a/doc/coreutils.texi -+++ b/doc/coreutils.texi -@@ -10074,6 +10074,8 @@ incorrect. @xref{Directory Setuid and Setgid}, for how the - set-user-ID and set-group-ID bits of directories are inherited unless - overridden in this way. - -+Note: The @option{--mode},@option{-m} option only applies to the right-most directories listed on the command line. When combined with @option{--parents}, @option{-p} option, any parent directories are created with @samp{u+wx} modified by umask. -+ - @item -p - @itemx --parents - @opindex -p diff --git a/coreutils-8.5-dircolors.patch b/coreutils-8.5-dircolors.patch deleted file mode 100644 index 8707c0a..0000000 --- a/coreutils-8.5-dircolors.patch +++ /dev/null @@ -1,13 +0,0 @@ -diff -urNp coreutils-8.5-orig/src/dircolors.hin coreutils-8.5/src/dircolors.hin ---- coreutils-8.5-orig/src/dircolors.hin 2010-04-20 21:52:04.000000000 +0200 -+++ coreutils-8.5/src/dircolors.hin 2010-07-22 16:18:41.978036926 +0200 -@@ -127,6 +127,9 @@ EXEC 01;32 - .deb 01;31 - .rpm 01;31 - .jar 01;31 -+.war 01;31 -+.ear 01;31 -+.sar 01;31 - .rar 01;31 - .ace 01;31 - .zoo 01;31 diff --git a/coreutils-9.9-fix-cut-test-aarch64.patch b/coreutils-9.9-fix-cut-test-aarch64.patch new file mode 100644 index 0000000..600f87b --- /dev/null +++ b/coreutils-9.9-fix-cut-test-aarch64.patch @@ -0,0 +1,28 @@ +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 new file mode 100644 index 0000000..82e3899 --- /dev/null +++ b/coreutils-9.9-gnulib-c23.patch @@ -0,0 +1,169 @@ +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-colorls.csh b/coreutils-colorls.csh index f631762..66ec2fa 100755 --- a/coreutils-colorls.csh +++ b/coreutils-colorls.csh @@ -15,11 +15,6 @@ alias l. 'ls -d .*' set COLORS=/etc/DIR_COLORS if ($?TERM) then - if ( -e "/etc/DIR_COLORS.256color" ) then - if ( "`/usr/bin/tput colors`" == "256" ) then - set COLORS=/etc/DIR_COLORS.256color - endif - endif if ( -e "/etc/DIR_COLORS.$TERM" ) then set COLORS="/etc/DIR_COLORS.$TERM" endif diff --git a/coreutils-colorls.sh b/coreutils-colorls.sh index ac92268..5162f1e 100755 --- a/coreutils-colorls.sh +++ b/coreutils-colorls.sh @@ -22,10 +22,6 @@ if [ -z "$USER_LS_COLORS" ]; then [ -z "$COLORS" ] && [ -e "/etc/DIR_COLORS.$TERM" ] && \ COLORS="/etc/DIR_COLORS.$TERM" - [ -z "$COLORS" ] && [ -e "/etc/DIR_COLORS.256color" ] && \ - [ "x`/usr/bin/tty -s && /usr/bin/tput colors 2>/dev/null`" = "x256" ] && \ - COLORS="/etc/DIR_COLORS.256color" - [ -z "$COLORS" ] && [ -e "/etc/DIR_COLORS" ] && \ COLORS="/etc/DIR_COLORS" diff --git a/coreutils-df-direct.patch b/coreutils-df-direct.patch index a69d896..341ee2c 100644 --- a/coreutils-df-direct.patch +++ b/coreutils-df-direct.patch @@ -1,8 +1,20 @@ +From 91be1a584108a6a3d96f64382bbf206c4213b3db 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 + +--- + doc/coreutils.texi | 7 ++++++ + src/df.c | 34 ++++++++++++++++++++++++++-- + tests/df/direct.sh | 55 ++++++++++++++++++++++++++++++++++++++++++++++ + 3 files changed, 94 insertions(+), 2 deletions(-) + create mode 100755 tests/df/direct.sh + diff --git a/doc/coreutils.texi b/doc/coreutils.texi -index a507280..400e135 100644 +index b420606..0ccb368 100644 --- a/doc/coreutils.texi +++ b/doc/coreutils.texi -@@ -11303,6 +11303,13 @@ some systems (notably SunOS), doing this yields more up to date results, +@@ -12597,6 +12597,13 @@ 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. @@ -15,12 +27,12 @@ index a507280..400e135 100644 + @item --total @opindex --total - @cindex grand total of disk size, usage and available space + @cindex grand total of file system size, usage and available space diff --git a/src/df.c b/src/df.c -index 8f760db..a7385fd 100644 +index 75e638c..ef9f0a7 100644 --- a/src/df.c +++ b/src/df.c -@@ -120,6 +120,9 @@ static bool print_type; +@@ -121,6 +121,9 @@ static bool print_type; /* If true, print a grand total at the end. */ static bool print_grand_total; @@ -30,7 +42,7 @@ index 8f760db..a7385fd 100644 /* Grand total data. */ static struct fs_usage grand_fsu; -@@ -247,13 +250,15 @@ enum +@@ -248,13 +251,15 @@ enum NO_SYNC_OPTION = CHAR_MAX + 1, SYNC_OPTION, TOTAL_OPTION, @@ -41,16 +53,16 @@ index 8f760db..a7385fd 100644 static struct option const long_options[] = { - {"all", no_argument, NULL, 'a'}, - {"block-size", required_argument, NULL, 'B'}, -+ {"direct", no_argument, NULL, DIRECT_OPTION}, - {"inodes", no_argument, NULL, 'i'}, - {"human-readable", no_argument, NULL, 'h'}, - {"si", no_argument, NULL, 'H'}, -@@ -509,7 +514,10 @@ get_header (void) - for (col = 0; col < ncolumns; col++) + {"all", no_argument, nullptr, 'a'}, + {"block-size", required_argument, nullptr, 'B'}, ++ {"direct", no_argument, nullptr, DIRECT_OPTION}, + {"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++) { - char *cell = NULL; + char *cell; - char const *header = _(columns[col]->caption); + char const *header = (columns[col]->field == TARGET_FIELD + && direct_statfs)? @@ -59,7 +71,7 @@ index 8f760db..a7385fd 100644 if (columns[col]->field == SIZE_FIELD && (header_mode == DEFAULT_MODE -@@ -1397,6 +1405,19 @@ get_point (const char *point, const struct stat *statp) +@@ -1446,6 +1454,17 @@ get_point (char const *point, const struct stat *statp) static void get_entry (char const *name, struct stat const *statp) { @@ -67,19 +79,17 @@ index 8f760db..a7385fd 100644 + { + char *resolved = canonicalize_file_name (name); + if (resolved) -+ { -+ char *mp = find_mount_point (name, statp); -+ get_dev (NULL, mp, resolved, NULL, NULL, false, false, NULL, false); -+ free(mp); -+ free (resolved); -+ return; -+ } ++ { ++ get_dev (NULL, resolved, name, NULL, NULL, false, false, NULL, false); ++ free (resolved); ++ return; ++ } + } + if ((S_ISBLK (statp->st_mode) || S_ISCHR (statp->st_mode)) - && get_disk (name)) + && get_device (name)) return; -@@ -1467,6 +1488,7 @@ or all file systems by default.\n\ +@@ -1516,6 +1535,7 @@ 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\ @@ -87,7 +97,7 @@ index 8f760db..a7385fd 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); -@@ -1557,6 +1579,9 @@ main (int argc, char **argv) +@@ -1610,6 +1630,9 @@ main (int argc, char **argv) xstrtol_fatal (e, oi, c, long_options, optarg); } break; @@ -97,14 +107,14 @@ index 8f760db..a7385fd 100644 case 'i': if (header_mode == OUTPUT_MODE) { -@@ -1653,6 +1678,13 @@ main (int argc, char **argv) +@@ -1706,6 +1729,13 @@ main (int argc, char **argv) } } + if (direct_statfs && show_local_fs) + { + error (0, 0, _("options --direct and --local (-l) are mutually " -+ "exclusive")); ++ "exclusive")); + usage (EXIT_FAILURE); + } + @@ -112,7 +122,7 @@ index 8f760db..a7385fd 100644 { if (posix_format) diff --git a/tests/df/direct.sh b/tests/df/direct.sh -new file mode 100644 +new file mode 100755 index 0000000..8e4cfb8 --- /dev/null +++ b/tests/df/direct.sh @@ -172,3 +182,6 @@ index 0000000..8e4cfb8 +compare file_out file_exp || fail=1 + +Exit $fail +-- +2.52.0 + diff --git a/coreutils-getgrouplist.patch b/coreutils-getgrouplist.patch deleted file mode 100644 index 5b35f42..0000000 --- a/coreutils-getgrouplist.patch +++ /dev/null @@ -1,86 +0,0 @@ -diff --git a/lib/getugroups.c b/lib/getugroups.c -index 299bae6..8ece29b 100644 ---- a/lib/getugroups.c -+++ b/lib/getugroups.c -@@ -19,6 +19,9 @@ - - #include - -+/* We do not need this code if getgrouplist(3) is available. */ -+#ifndef HAVE_GETGROUPLIST -+ - #include "getugroups.h" - - #include -@@ -126,3 +129,4 @@ getugroups (int maxcount, gid_t *grouplist, char const *username, - } - - #endif /* HAVE_GRP_H */ -+#endif /* have getgrouplist */ -diff --git a/lib/mgetgroups.c b/lib/mgetgroups.c -index 76474c2..0a9d221 100644 ---- a/lib/mgetgroups.c -+++ b/lib/mgetgroups.c -@@ -121,9 +121,17 @@ mgetgroups (char const *username, gid_t gid, gid_t **groups) - /* else no username, so fall through and use getgroups. */ - #endif - -- max_n_groups = (username -- ? getugroups (0, NULL, username, gid) -- : getgroups (0, NULL)); -+ if (!username) -+ max_n_groups = getgroups(0, NULL); -+ else -+ { -+#ifdef HAVE_GETGROUPLIST -+ max_n_groups = 0; -+ getgrouplist (username, gid, NULL, &max_n_groups); -+#else -+ max_n_groups = getugroups (0, NULL, username, gid); -+#endif -+ } - - /* If we failed to count groups because there is no supplemental - group support, then return an array containing just GID. -@@ -145,10 +153,25 @@ mgetgroups (char const *username, gid_t gid, gid_t **groups) - if (g == NULL) - return -1; - -- ng = (username -- ? getugroups (max_n_groups, g, username, gid) -- : getgroups (max_n_groups - (gid != (gid_t) -1), -- g + (gid != (gid_t) -1))); -+ if (!username) -+ ng = getgroups (max_n_groups - (gid != (gid_t)-1), g + (gid != (gid_t)-1)); -+ else -+ { -+#ifdef HAVE_GETGROUPLIST -+ int e; -+ ng = max_n_groups; -+ while ((e = getgrouplist (username, gid, g, &ng)) == -1 -+ && ng > max_n_groups) -+ { -+ max_n_groups = ng; -+ g = xrealloc (g, max_n_groups * sizeof (GETGROUPS_T)); -+ } -+ if (e == -1) -+ ng = -1; -+#else -+ ng = getugroups (max_n_groups, g, username, gid); -+#endif -+ } - - if (ng < 0) - { -diff --git a/m4/jm-macros.m4 b/m4/jm-macros.m4 -index 62777c7..5180243 100644 ---- a/m4/jm-macros.m4 -+++ b/m4/jm-macros.m4 -@@ -82,6 +82,7 @@ AC_DEFUN([coreutils_MACROS], - fchown - fchmod - ftruncate -+ getgrouplist - iswspace - mkfifo - mbrlen diff --git a/coreutils-i18n-cut-old.patch b/coreutils-i18n-cut-old.patch deleted file mode 100644 index 7fcc8ff..0000000 --- a/coreutils-i18n-cut-old.patch +++ /dev/null @@ -1,565 +0,0 @@ -diff --git a/src/cut.c b/src/cut.c -index 7ab6be4..022d0ad 100644 ---- a/src/cut.c -+++ b/src/cut.c -@@ -28,6 +28,11 @@ - #include - #include - #include -+ -+/* Get mbstate_t, mbrtowc(). */ -+#if HAVE_WCHAR_H -+# include -+#endif - #include "system.h" - - #include "error.h" -@@ -38,6 +43,18 @@ - - #include "set-fields.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 -+ - /* The official name of this program (e.g., no 'g' prefix). */ - #define PROGRAM_NAME "cut" - -@@ -54,6 +71,52 @@ - } \ - while (0) - -+/* Refill the buffer BUF to get a multibyte character. */ -+#define REFILL_BUFFER(BUF, BUFPOS, BUFLEN, STREAM) \ -+ do \ -+ { \ -+ if (BUFLEN < MB_LEN_MAX && !feof (STREAM) && !ferror (STREAM)) \ -+ { \ -+ memmove (BUF, BUFPOS, BUFLEN); \ -+ BUFLEN += fread (BUF + BUFLEN, sizeof(char), BUFSIZ, STREAM); \ -+ BUFPOS = BUF; \ -+ } \ -+ } \ -+ while (0) -+ -+/* Get wide character on BUFPOS. BUFPOS is not included after that. -+ If byte sequence is not valid as a character, CONVFAIL is true. Otherwise false. */ -+#define GET_NEXT_WC_FROM_BUFFER(WC, BUFPOS, BUFLEN, MBLENGTH, STATE, CONVFAIL) \ -+ do \ -+ { \ -+ mbstate_t state_bak; \ -+ \ -+ if (BUFLEN < 1) \ -+ { \ -+ WC = WEOF; \ -+ break; \ -+ } \ -+ \ -+ /* Get a wide character. */ \ -+ CONVFAIL = false; \ -+ state_bak = STATE; \ -+ MBLENGTH = mbrtowc ((wchar_t *)&WC, BUFPOS, BUFLEN, &STATE); \ -+ \ -+ switch (MBLENGTH) \ -+ { \ -+ case (size_t)-1: \ -+ case (size_t)-2: \ -+ CONVFAIL = true; \ -+ STATE = state_bak; \ -+ /* Fall througn. */ \ -+ \ -+ case 0: \ -+ MBLENGTH = 1; \ -+ break; \ -+ } \ -+ } \ -+ while (0) -+ - - /* Pointer inside RP. When checking if a byte or field is selected - by a finite range, we check if it is between CURRENT_RP.LO -@@ -61,6 +124,9 @@ - CURRENT_RP.HI then we make CURRENT_RP to point to the next range pair. */ - static struct field_range_pair *current_rp; - -+/* Length of the delimiter given as argument to -d. */ -+size_t delimlen; -+ - /* This buffer is used to support the semantics of the -s option - (or lack of same) when the specified field list includes (does - not include) the first field. In both of those cases, the entire -@@ -77,15 +143,25 @@ enum operating_mode - { - undefined_mode, - -- /* Output characters that are in the given bytes. */ -+ /* Output bytes that are at the given positions. */ - byte_mode, - -+ /* Output characters that are at the given positions. */ -+ character_mode, -+ - /* Output the given delimiter-separated fields. */ - field_mode - }; - - static enum operating_mode operating_mode; - -+/* If nonzero, when in byte mode, don't split multibyte characters. */ -+static int byte_mode_character_aware; -+ -+/* If nonzero, the function for single byte locale is work -+ if this program runs on multibyte locale. */ -+static int force_singlebyte_mode; -+ - /* If true do not output lines containing no delimiter characters. - Otherwise, all such lines are printed. This option is valid only - with field mode. */ -@@ -97,6 +173,9 @@ static bool complement; - - /* The delimiter character for field mode. */ - static unsigned char delim; -+#if HAVE_WCHAR_H -+static wchar_t wcdelim; -+#endif - - /* The delimiter for each line/record. */ - static unsigned char line_delim = '\n'; -@@ -164,7 +243,7 @@ Print selected parts of lines from each FILE to standard output.\n\ - -f, --fields=LIST select only these fields; also print any line\n\ - that contains no delimiter character, unless\n\ - the -s option is specified\n\ -- -n (ignored)\n\ -+ -n with -b: don't split multibyte characters\n\ - "), stdout); - fputs (_("\ - --complement complement the set of selected bytes, characters\n\ -@@ -280,6 +359,82 @@ cut_bytes (FILE *stream) - } - } - -+#if HAVE_MBRTOWC -+/* This function is in use for the following case. -+ -+ 1. Read from the stream STREAM, printing to standard output any selected -+ characters. -+ -+ 2. Read from stream STREAM, printing to standard output any selected bytes, -+ without splitting multibyte characters. */ -+ -+static void -+cut_characters_or_cut_bytes_no_split (FILE *stream) -+{ -+ size_t idx; /* number of bytes or characters in the line so far. */ -+ char buf[MB_LEN_MAX + BUFSIZ]; /* For spooling a read byte sequence. */ -+ char *bufpos; /* Next read position of BUF. */ -+ size_t buflen; /* The length of the byte sequence in 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 of the stream. */ -+ bool convfail = false; /* true, when conversion failed. Otherwise false. */ -+ /* Whether to begin printing delimiters between ranges for the current line. -+ Set after we've begun printing data corresponding to the first range. */ -+ bool print_delimiter = false; -+ -+ idx = 0; -+ buflen = 0; -+ bufpos = buf; -+ memset (&state, '\0', sizeof(mbstate_t)); -+ -+ current_rp = frp; -+ -+ while (1) -+ { -+ REFILL_BUFFER (buf, bufpos, buflen, stream); -+ -+ GET_NEXT_WC_FROM_BUFFER (wc, bufpos, buflen, mblength, state, convfail); -+ (void) convfail; /* ignore unused */ -+ -+ if (wc == WEOF) -+ { -+ if (idx > 0) -+ putchar (line_delim); -+ break; -+ } -+ else if (wc == line_delim) -+ { -+ putchar (line_delim); -+ idx = 0; -+ print_delimiter = false; -+ current_rp = frp; -+ } -+ else -+ { -+ next_item (&idx); -+ if (print_kth (idx)) -+ { -+ if (output_delimiter_specified) -+ { -+ if (print_delimiter && is_range_start_index (idx)) -+ { -+ fwrite (output_delimiter_string, sizeof (char), -+ output_delimiter_length, stdout); -+ } -+ print_delimiter = true; -+ } -+ fwrite (bufpos, mblength, sizeof(char), stdout); -+ } -+ } -+ -+ buflen -= mblength; -+ bufpos += mblength; -+ } -+} -+#endif -+ - /* Read from stream STREAM, printing to standard output any selected fields. */ - - static void -@@ -425,13 +580,211 @@ cut_fields (FILE *stream) - } - } - -+#if HAVE_MBRTOWC -+static void -+cut_fields_mb (FILE *stream) -+{ -+ int c; -+ size_t field_idx; -+ int found_any_selected_field; -+ int buffer_first_field; -+ int empty_input; -+ char buf[MB_LEN_MAX + BUFSIZ]; /* For spooling a read byte sequence. */ -+ char *bufpos; /* Next read position of BUF. */ -+ size_t buflen; /* The length of the byte sequence in buf. */ -+ wint_t wc = 0; /* 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 of the stream. */ -+ bool convfail = false; /* true, when conversion failed. Otherwise false. */ -+ -+ current_rp = frp; -+ -+ found_any_selected_field = 0; -+ field_idx = 1; -+ bufpos = buf; -+ buflen = 0; -+ memset (&state, '\0', sizeof(mbstate_t)); -+ -+ c = getc (stream); -+ empty_input = (c == EOF); -+ if (c != EOF) -+ { -+ ungetc (c, stream); -+ wc = 0; -+ } -+ else -+ wc = WEOF; -+ -+ /* To support the semantics of the -s flag, we may have to buffer -+ all of the first field to determine whether it is `delimited.' -+ But that is unnecessary if all non-delimited lines must be printed -+ and the first field has been selected, or if non-delimited lines -+ must be suppressed and the first field has *not* been selected. -+ That is because a non-delimited line has exactly one field. */ -+ buffer_first_field = (suppress_non_delimited ^ !print_kth (1)); -+ -+ while (1) -+ { -+ if (field_idx == 1 && buffer_first_field) -+ { -+ int len = 0; -+ -+ while (1) -+ { -+ REFILL_BUFFER (buf, bufpos, buflen, stream); -+ -+ GET_NEXT_WC_FROM_BUFFER -+ (wc, bufpos, buflen, mblength, state, convfail); -+ -+ if (wc == WEOF) -+ break; -+ -+ field_1_buffer = xrealloc (field_1_buffer, len + mblength); -+ memcpy (field_1_buffer + len, bufpos, mblength); -+ len += mblength; -+ buflen -= mblength; -+ bufpos += mblength; -+ -+ if (!convfail && (wc == line_delim || wc == wcdelim)) -+ break; -+ } -+ -+ if (len <= 0 && wc == WEOF) -+ break; -+ -+ /* If the first field extends to the end of line (it is not -+ delimited) and we are printing all non-delimited lines, -+ print this one. */ -+ if (convfail || (!convfail && wc != wcdelim)) -+ { -+ if (suppress_non_delimited) -+ { -+ /* Empty. */ -+ } -+ else -+ { -+ fwrite (field_1_buffer, sizeof (char), len, stdout); -+ /* Make sure the output line is newline terminated. */ -+ if (convfail || (!convfail && wc != line_delim)) -+ putchar (line_delim); -+ } -+ continue; -+ } -+ -+ if (print_kth (1)) -+ { -+ /* Print the field, but not the trailing delimiter. */ -+ fwrite (field_1_buffer, sizeof (char), len - 1, stdout); -+ found_any_selected_field = 1; -+ } -+ next_item (&field_idx); -+ } -+ -+ if (wc != WEOF) -+ { -+ if (print_kth (field_idx)) -+ { -+ if (found_any_selected_field) -+ { -+ fwrite (output_delimiter_string, sizeof (char), -+ output_delimiter_length, stdout); -+ } -+ found_any_selected_field = 1; -+ } -+ -+ while (1) -+ { -+ REFILL_BUFFER (buf, bufpos, buflen, stream); -+ -+ GET_NEXT_WC_FROM_BUFFER -+ (wc, bufpos, buflen, mblength, state, convfail); -+ -+ if (wc == WEOF) -+ break; -+ else if (!convfail && (wc == wcdelim || wc == line_delim)) -+ { -+ buflen -= mblength; -+ bufpos += mblength; -+ break; -+ } -+ -+ if (print_kth (field_idx)) -+ fwrite (bufpos, mblength, sizeof(char), stdout); -+ -+ buflen -= mblength; -+ bufpos += mblength; -+ } -+ } -+ -+ if ((!convfail || wc == line_delim) && buflen < 1) -+ wc = WEOF; -+ -+ if (!convfail && wc == wcdelim) -+ next_item (&field_idx); -+ else if (wc == WEOF || (!convfail && wc == line_delim)) -+ { -+ if (found_any_selected_field -+ || (!empty_input && !(suppress_non_delimited && field_idx == 1))) -+ putchar (line_delim); -+ if (wc == WEOF) -+ break; -+ field_idx = 1; -+ current_rp = frp; -+ found_any_selected_field = 0; -+ } -+ } -+} -+#endif -+ - static void - cut_stream (FILE *stream) - { -- if (operating_mode == byte_mode) -- cut_bytes (stream); -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1 && !force_singlebyte_mode) -+ { -+ switch (operating_mode) -+ { -+ case byte_mode: -+ if (byte_mode_character_aware) -+ cut_characters_or_cut_bytes_no_split (stream); -+ else -+ cut_bytes (stream); -+ break; -+ -+ case character_mode: -+ cut_characters_or_cut_bytes_no_split (stream); -+ break; -+ -+ case field_mode: -+ if (delimlen == 1) -+ { -+ /* Check if we have utf8 multibyte locale, so we can use this -+ optimization because of uniqueness of characters, which is -+ not true for e.g. SJIS */ -+ char * loc = setlocale(LC_CTYPE, NULL); -+ if (loc && (strstr (loc, "UTF-8") || strstr (loc, "utf-8") || -+ strstr (loc, "UTF8") || strstr (loc, "utf8"))) -+ { -+ cut_fields (stream); -+ break; -+ } -+ } -+ cut_fields_mb (stream); -+ break; -+ -+ default: -+ abort (); -+ } -+ } - else -- cut_fields (stream); -+#endif -+ { -+ if (operating_mode == field_mode) -+ cut_fields (stream); -+ else -+ cut_bytes (stream); -+ } - } - - /* Process file FILE to standard output. -@@ -483,6 +836,7 @@ main (int argc, char **argv) - bool ok; - bool delim_specified = false; - char *spec_list_string IF_LINT ( = NULL); -+ char mbdelim[MB_LEN_MAX + 1]; - - initialize_main (&argc, &argv); - set_program_name (argv[0]); -@@ -505,7 +859,6 @@ main (int argc, char **argv) - switch (optc) - { - case 'b': -- case 'c': - /* Build the byte list. */ - if (operating_mode != undefined_mode) - FATAL_ERROR (_("only one type of list may be specified")); -@@ -513,6 +866,14 @@ main (int argc, char **argv) - spec_list_string = optarg; - break; - -+ case 'c': -+ /* Build the character list. */ -+ if (operating_mode != undefined_mode) -+ FATAL_ERROR (_("only one type of list may be specified")); -+ operating_mode = character_mode; -+ spec_list_string = optarg; -+ break; -+ - case 'f': - /* Build the field list. */ - if (operating_mode != undefined_mode) -@@ -524,10 +885,38 @@ main (int argc, char **argv) - case 'd': - /* New delimiter. */ - /* Interpret -d '' to mean 'use the NUL byte as the delimiter.' */ -- if (optarg[0] != '\0' && optarg[1] != '\0') -- FATAL_ERROR (_("the delimiter must be a single character")); -- delim = optarg[0]; -- delim_specified = true; -+ { -+#if HAVE_MBRTOWC -+ if(MB_CUR_MAX > 1) -+ { -+ mbstate_t state; -+ -+ memset (&state, '\0', sizeof(mbstate_t)); -+ delimlen = mbrtowc (&wcdelim, optarg, strnlen(optarg, MB_LEN_MAX), &state); -+ -+ if (delimlen == (size_t)-1 || delimlen == (size_t)-2) -+ ++force_singlebyte_mode; -+ else -+ { -+ delimlen = (delimlen < 1) ? 1 : delimlen; -+ if (wcdelim != L'\0' && *(optarg + delimlen) != '\0') -+ FATAL_ERROR (_("the delimiter must be a single character")); -+ memcpy (mbdelim, optarg, delimlen); -+ mbdelim[delimlen] = '\0'; -+ if (delimlen == 1) -+ delim = *optarg; -+ } -+ } -+ -+ if (MB_CUR_MAX <= 1 || force_singlebyte_mode) -+#endif -+ { -+ if (optarg[0] != '\0' && optarg[1] != '\0') -+ FATAL_ERROR (_("the delimiter must be a single character")); -+ delim = (unsigned char) optarg[0]; -+ } -+ delim_specified = true; -+ } - break; - - case OUTPUT_DELIMITER_OPTION: -@@ -540,6 +929,7 @@ main (int argc, char **argv) - break; - - case 'n': -+ byte_mode_character_aware = 1; - break; - - case 's': -@@ -579,15 +969,34 @@ main (int argc, char **argv) - | (complement ? SETFLD_COMPLEMENT : 0) ); - - if (!delim_specified) -- delim = '\t'; -+ { -+ delim = '\t'; -+#ifdef HAVE_MBRTOWC -+ wcdelim = L'\t'; -+ mbdelim[0] = '\t'; -+ mbdelim[1] = '\0'; -+ delimlen = 1; -+#endif -+ } - - if (output_delimiter_string == NULL) - { -- static char dummy[2]; -- dummy[0] = delim; -- dummy[1] = '\0'; -- output_delimiter_string = dummy; -- output_delimiter_length = 1; -+#ifdef HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1 && !force_singlebyte_mode) -+ { -+ output_delimiter_string = xstrdup(mbdelim); -+ output_delimiter_length = delimlen; -+ } -+ -+ if (MB_CUR_MAX <= 1 || force_singlebyte_mode) -+#endif -+ { -+ static char dummy[2]; -+ dummy[0] = delim; -+ dummy[1] = '\0'; -+ output_delimiter_string = dummy; -+ output_delimiter_length = 1; -+ } - } - - if (optind == argc) diff --git a/coreutils-i18n-cut.patch b/coreutils-i18n-cut.patch deleted file mode 100644 index f4015d1..0000000 --- a/coreutils-i18n-cut.patch +++ /dev/null @@ -1,587 +0,0 @@ -(sb) lin18nux/lsb compliance - cut - not stable enough, not applied - ---- coreutils-8.24/src/cut.c 2015-06-26 19:05:22.000000000 +0200 -+++ cut.c 2016-01-15 10:15:04.863804121 +0100 -@@ -28,6 +28,11 @@ - #include - #include - #include -+ -+#include -+#include -+#include -+ - #include "system.h" - - #include "error.h" -@@ -61,25 +66,16 @@ - CURRENT_RP.HI then we make CURRENT_RP to point to the next range pair. */ - static struct field_range_pair *current_rp; - --/* This buffer is used to support the semantics of the -s option -- (or lack of same) when the specified field list includes (does -- not include) the first field. In both of those cases, the entire -- first field must be read into this buffer to determine whether it -- is followed by a delimiter or a newline before any of it may be -- output. Otherwise, cut_fields can do the job without using this -- buffer. */ --static char *field_1_buffer; -- --/* The number of bytes allocated for FIELD_1_BUFFER. */ --static size_t field_1_bufsize; -- - enum operating_mode - { - undefined_mode, - -- /* Output characters that are in the given bytes. */ -+ /* Output the given bytes. */ - byte_mode, - -+ /* Output characters that are in the given positions . */ -+ char_mode, -+ - /* Output the given delimiter-separated fields. */ - field_mode - }; -@@ -91,12 +87,16 @@ static enum operating_mode operating_mode; - with field mode. */ - static bool suppress_non_delimited; - -+/* Unless true, we do not recognize multibyte characters in byte-splitting -+ mode. */ -+static bool no_break_mb_chars; -+ - /* If true, print all bytes, characters, or fields _except_ - those that were specified. */ - static bool complement; - - /* The delimiter character for field mode. */ --static unsigned char delim; -+static mbf_char_t delim; - - /* The delimiter for each line/record. */ - static unsigned char line_delim = '\n'; -@@ -109,7 +109,7 @@ static size_t output_delimiter_length; - - /* The output field separator string. Defaults to the 1-character - string consisting of the input delimiter. */ --static char *output_delimiter_string; -+static char const *output_delimiter_string; - - /* True if we have ever read standard input. */ - static bool have_read_stdin; -@@ -164,7 +164,7 @@ Print selected parts of lines from each FILE to standard output.\n\ - -f, --fields=LIST select only these fields; also print any line\n\ - that contains no delimiter character, unless\n\ - the -s option is specified\n\ -- -n (ignored)\n\ -+ -n with -b, don't split multibyte characters\n\ - "), stdout); - fputs (_("\ - --complement complement the set of selected bytes, characters\n\ -@@ -211,6 +211,12 @@ next_item (size_t *item_idx) - current_rp++; - } - -+static inline void -+next_item_n (size_t *item_idx, size_t n) -+{ -+ while (n-- > 0) -+ next_item (item_idx); -+} - /* Return nonzero if the K'th field or byte is printable. */ - - static inline bool -@@ -219,6 +225,15 @@ print_kth (size_t k) - return current_rp->lo <= k; - } - -+/* The lo and hi params should be used for the current characters byte position -+ * and byte size, respectively. */ -+static inline bool -+rp_intersect (size_t lo, size_t hi) -+{ -+ return ((current_rp->lo <= lo && current_rp->hi >= lo) -+ || (current_rp->lo <= hi && current_rp->hi >= hi)); -+} -+ - /* Return nonzero if K'th byte is the beginning of a range. */ - - static inline bool -@@ -281,23 +296,215 @@ cut_bytes (FILE *stream) - } - - /* Read from stream STREAM, printing to standard output any selected fields. */ -+extern ssize_t -+mb_getndelim2 (mbf_char_t **lineptr, size_t *linesize, size_t nmax, -+ mbf_char_t delim1, mbf_char_t delim2, mb_file_t *stream) -+{ -+/* The maximum value that getndelim2 can return without suffering from -+ overflow problems, either internally (because of pointer -+ subtraction overflow) or due to the API (because of ssize_t). */ -+#define GETNDELIM2_MAXIMUM (PTRDIFF_MAX < SSIZE_MAX ? PTRDIFF_MAX : SSIZE_MAX) -+ -+/* Try to add at least this many bytes when extending the buffer. -+ MIN_CHUNK must be no greater than GETNDELIM2_MAXIMUM. */ -+#define MIN_CHUNK 64 -+ size_t nchars_avail; /* Allocated but unused chars in *LINEPTR. */ -+ mbf_char_t *read_pos; /* Where we're reading into *LINEPTR. */ -+ ssize_t chars_stored = -1; -+ mbf_char_t *ptr = *lineptr; -+ size_t size = *linesize; -+ bool found_delimiter; -+ -+ if (!ptr) -+ { -+ size = nmax < MIN_CHUNK ? nmax : MIN_CHUNK; -+ ptr = malloc (size * sizeof (mbf_char_t)); -+ if (!ptr) -+ return -1; -+ } -+ -+ if (size < 0) -+ goto done; -+ -+ nchars_avail = size; -+ read_pos = ptr; -+ -+ if (nchars_avail == 0 && nmax <= size) -+ goto done; -+ -+ /* Normalize delimiters, since memchr2 doesn't handle EOF. */ -+ if (mb_iseof (delim1)) -+ mb_copy (&delim1, &delim2); -+ else if (mb_iseof (delim2)) -+ mb_copy (&delim2, &delim1); -+ -+ flockfile (stream); -+ -+ found_delimiter = false; -+ do -+ { -+ /* Here always ptr + size == read_pos + nchars_avail. -+ Also nchars_avail > 0 || size < nmax. */ -+ -+ mbf_char_t c IF_LINT (= 0); -+ { -+ mbf_getc (c, *stream); -+ if (mb_iseof (c)) -+ { -+ /* Return partial line, if any. */ -+ if (read_pos == ptr) -+ goto unlock_done; -+ else -+ break; -+ } -+ if (mb_equal (c, delim1) || mb_equal (c, delim2)) -+ found_delimiter = true; -+ } -+ -+ /* We always want at least one byte left in the buffer, since we -+ always (unless we get an error while reading the first byte) -+ NUL-terminate the line buffer. */ -+ -+ if (!nchars_avail) -+ { -+ /* Grow size proportionally, not linearly, to avoid O(n^2) -+ running time. */ -+ size_t newsize = size < MIN_CHUNK ? size + MIN_CHUNK : 2 * size; -+ mbf_char_t *newptr; -+ -+ /* Respect nmax. This handles possible integer overflow. */ -+ if (! (size < newsize && newsize <= nmax)) -+ newsize = nmax; -+ -+ if (GETNDELIM2_MAXIMUM < newsize) -+ { -+ size_t newsizemax = GETNDELIM2_MAXIMUM + 1; -+ if (size == newsizemax) -+ goto unlock_done; -+ newsize = newsizemax; -+ } -+ nchars_avail = newsize - (read_pos - ptr); -+ newptr = realloc (ptr, newsize * sizeof (mbf_char_t)); -+ if (!newptr) -+ goto unlock_done; -+ ptr = newptr; -+ size = newsize; -+ read_pos = size - nchars_avail + ptr; -+ } -+ -+ /* Here, if size < nmax, nchars_avail >= buffer_len + 1. -+ If size == nmax, nchars_avail > 0. */ -+ -+ if (1 < nchars_avail--) -+ { -+ mb_copy(read_pos++, &c); -+ } -+ -+ } -+ while (!found_delimiter); -+ -+ chars_stored = (read_pos - ptr); -+ -+ unlock_done: -+ funlockfile (stream); -+ -+ done: -+ *lineptr = ptr; -+ *linesize = size; -+ return chars_stored; -+} -+ -+static void -+cut_chars (FILE *stream) -+{ -+ size_t char_idx; /* Number of chars in the line so far. */ -+ bool print_delimiter; -+ mbf_char_t c; -+ mb_file_t mbf; -+ -+ print_delimiter = false; -+ char_idx = 0; -+ current_rp = frp; -+ -+ mbf_init (mbf, stream); -+ while (true) -+ { -+ mbf_getc (c, mbf); -+ -+ if (mb_iseq (c, line_delim)) -+ { -+ putc (line_delim, stdout); -+ char_idx = 0; -+ print_delimiter = false; -+ current_rp = frp; -+ } -+ else if (mb_iseof (c)) -+ { -+ if (char_idx > 0) -+ putc (line_delim, stdout); -+ break; -+ } -+ else -+ { -+ /* Forward by one byte. */ -+ next_item (&char_idx); -+ -+ /* Check if the current characters byte range is within -+ * the argument list. */ -+ if (rp_intersect (char_idx, char_idx + mb_len (c) - 1)) -+ { -+ if (output_delimiter_specified) -+ { -+ if (print_delimiter && is_range_start_index (char_idx)) -+ { -+ fwrite (output_delimiter_string, sizeof (char), -+ output_delimiter_length, stdout); -+ } -+ print_delimiter = true; -+ } -+ mb_putc (c, stdout); -+ } -+ -+ /* Byte mode with multibyte characters uncut (-b -n). */ -+ if (no_break_mb_chars) -+ /* Forward by an additional byte_length (c) - 1. */ -+ next_item_n (&char_idx, mb_len (c) - 1); -+ } -+ } -+} - - static void - cut_fields (FILE *stream) - { -- int c; -+ -+ /* This buffer is used to support the semantics of the -s option -+ (or lack of same) when the specified field list includes (does -+ not include) the first field. In both of those cases, the entire -+ first field must be read into this buffer to determine whether it -+ is followed by a delimiter or a newline before any of it may be -+ output. Otherwise, cut_fields can do the job without using this -+ buffer. */ -+ mbf_char_t *field_1_buffer = 0; -+ /* The number of bytes allocated for FIELD_1_BUFFER. */ -+ size_t field_1_bufsize; -+ -+ -+ mbf_char_t c, d; -+ mb_file_t mbf; - size_t field_idx = 1; - bool found_any_selected_field = false; - bool buffer_first_field; - - current_rp = frp; - -- c = getc (stream); -- if (c == EOF) -+ mbf_init (mbf, stream); -+ mbf_getc (c, mbf); -+ if (mb_iseof (c)) - return; - -- ungetc (c, stream); -- c = 0; -+ mbf_ungetc (c, mbf); -+ mb_setascii (&c, 0); -+ mb_copy (&d, &delim); - - /* To support the semantics of the -s flag, we may have to buffer - all of the first field to determine whether it is 'delimited.' -@@ -312,10 +519,14 @@ cut_fields (FILE *stream) - if (field_idx == 1 && buffer_first_field) - { - ssize_t len; -- size_t n_bytes; -+ size_t n_chars; -+ mbf_char_t nl; -+ mb_setascii (&nl, line_delim); -+ -+ len = mb_getndelim2 (&field_1_buffer, &field_1_bufsize, -+ GETNLINE_NO_LIMIT, d, nl, &mbf); -+ - -- len = getndelim2 (&field_1_buffer, &field_1_bufsize, 0, -- GETNLINE_NO_LIMIT, delim, line_delim, stream); - if (len < 0) - { - free (field_1_buffer); -@@ -325,15 +536,15 @@ cut_fields (FILE *stream) - xalloc_die (); - } - -- n_bytes = len; -- assert (n_bytes != 0); -+ n_chars = len; -+ //assert (n_chars != 0); - -- c = 0; -+ mb_setascii (&c, 0); - - /* If the first field extends to the end of line (it is not - delimited) and we are printing all non-delimited lines, - print this one. */ -- if (to_uchar (field_1_buffer[n_bytes - 1]) != delim) -+ if (!mb_equal (field_1_buffer[n_chars - 1], d)) - { - if (suppress_non_delimited) - { -@@ -341,26 +552,30 @@ cut_fields (FILE *stream) - } - else - { -- fwrite (field_1_buffer, sizeof (char), n_bytes, stdout); -+ for (int i = 0; i < n_chars; ++i) -+ mb_putc (field_1_buffer[i], stdout); -+ - /* Make sure the output line is newline terminated. */ -- if (field_1_buffer[n_bytes - 1] != line_delim) -+ if (!mb_iseq (field_1_buffer[n_chars - 1], line_delim)) - putchar (line_delim); -- c = line_delim; -+ mb_setascii (&c, line_delim); - } - continue; - } - if (print_kth (1)) - { - /* Print the field, but not the trailing delimiter. */ -- fwrite (field_1_buffer, sizeof (char), n_bytes - 1, stdout); -+ for (int i = 0; i < n_chars - 1; ++i) -+ mb_putc (field_1_buffer[i], stdout); - - /* With -d$'\n' don't treat the last '\n' as a delimiter. */ -- if (delim == line_delim) -+ if (mb_iseq (d, line_delim)) - { -- int last_c = getc (stream); -- if (last_c != EOF) -+ mbf_char_t last_c; -+ mbf_getc (last_c, mbf); -+ if (!mb_iseof (last_c)) - { -- ungetc (last_c, stream); -+ mbf_ungetc (last_c, mbf); - found_any_selected_field = true; - } - } -@@ -370,7 +585,8 @@ cut_fields (FILE *stream) - next_item (&field_idx); - } - -- int prev_c = c; -+ mbf_char_t prev_c; -+ mb_copy (&prev_c, &c); - - if (print_kth (field_idx)) - { -@@ -381,42 +597,46 @@ cut_fields (FILE *stream) - } - found_any_selected_field = true; - -- while ((c = getc (stream)) != delim && c != line_delim && c != EOF) -+ mbf_getc (c, mbf); -+ while (!mb_equal (c, d) && !mb_iseq (c, line_delim) && !mb_iseof (c)) - { -- putchar (c); -- prev_c = c; -+ mb_putc (c, stdout); -+ mb_copy (&prev_c, &c); -+ mbf_getc (c, mbf); - } - } - else - { -- while ((c = getc (stream)) != delim && c != line_delim && c != EOF) -+ mbf_getc (c, mbf); -+ while (!mb_equal (c, d) && !mb_iseq (c, line_delim) && !mb_iseof (c)) - { -- prev_c = c; -+ mb_copy (&prev_c, &c); -+ mbf_getc (c, mbf); - } - } - - /* With -d$'\n' don't treat the last '\n' as a delimiter. */ -- if (delim == line_delim && c == delim) -+ if (mb_iseq (d, line_delim) && mb_equal (c, d)) - { -- int last_c = getc (stream); -- if (last_c != EOF) -- ungetc (last_c, stream); -+ mbf_char_t last_c; -+ mbf_getc (last_c, mbf); -+ if (!mb_iseof (last_c)) -+ mbf_ungetc (last_c, mbf); - else -- c = last_c; -+ mb_copy (&c, &last_c); - } - -- if (c == delim) -+ if (mb_equal (c, d)) - next_item (&field_idx); -- else if (c == line_delim || c == EOF) -+ else if (mb_iseq (c, line_delim) || mb_iseof (c)) - { - if (found_any_selected_field - || !(suppress_non_delimited && field_idx == 1)) - { -- if (c == line_delim || prev_c != line_delim -- || delim == line_delim) -+ if (mb_iseq (c, line_delim) || !mb_iseq (prev_c, line_delim) || mb_iseq (d, line_delim)) - putchar (line_delim); - } -- if (c == EOF) -+ if (mb_iseof (c)) - break; - field_idx = 1; - current_rp = frp; -@@ -429,7 +649,14 @@ static void - cut_stream (FILE *stream) - { - if (operating_mode == byte_mode) -- cut_bytes (stream); -+ { -+ if (no_break_mb_chars) -+ cut_chars (stream); -+ else -+ cut_bytes (stream); -+ } -+ else if (operating_mode == char_mode) -+ cut_chars (stream); - else - cut_fields (stream); - } -@@ -483,6 +710,7 @@ main (int argc, char **argv) - bool ok; - bool delim_specified = false; - char *spec_list_string IF_LINT ( = NULL); -+ mbi_iterator_t iter; - - initialize_main (&argc, &argv); - set_program_name (argv[0]); -@@ -496,8 +724,10 @@ main (int argc, char **argv) - - /* By default, all non-delimited lines are printed. */ - suppress_non_delimited = false; -+ /* Default behaviour for -b, unless -n is also specified. */ -+ no_break_mb_chars = false; - -- delim = '\0'; -+ mb_setascii (&delim, '\0'); - have_read_stdin = false; - - while ((optc = getopt_long (argc, argv, "b:c:d:f:nsz", longopts, NULL)) != -1) -@@ -505,7 +735,6 @@ main (int argc, char **argv) - switch (optc) - { - case 'b': -- case 'c': - /* Build the byte list. */ - if (operating_mode != undefined_mode) - FATAL_ERROR (_("only one type of list may be specified")); -@@ -513,6 +742,14 @@ main (int argc, char **argv) - spec_list_string = optarg; - break; - -+ case 'c': -+ /* Build the char list. */ -+ if (operating_mode != undefined_mode) -+ FATAL_ERROR (_("only one type of list may be specified")); -+ operating_mode = char_mode; -+ spec_list_string = optarg; -+ break; -+ - case 'f': - /* Build the field list. */ - if (operating_mode != undefined_mode) -@@ -524,9 +761,17 @@ main (int argc, char **argv) - case 'd': - /* New delimiter. */ - /* Interpret -d '' to mean 'use the NUL byte as the delimiter.' */ -- if (optarg[0] != '\0' && optarg[1] != '\0') -+ mbi_init (iter, optarg, strlen (optarg)); -+ if (!mbi_avail (iter)) -+ mb_setascii (&delim, '\0'); -+ else -+ { -+ mb_copy (&delim, &mbi_cur (iter)); -+ -+ mbi_advance (iter); -+ if (mbi_avail (iter)) - FATAL_ERROR (_("the delimiter must be a single character")); -- delim = optarg[0]; -+ } - delim_specified = true; - break; - -@@ -540,6 +785,7 @@ main (int argc, char **argv) - break; - - case 'n': -+ no_break_mb_chars = true; - break; - - case 's': -@@ -579,15 +825,12 @@ main (int argc, char **argv) - | (complement ? SETFLD_COMPLEMENT : 0) ); - - if (!delim_specified) -- delim = '\t'; -+ mb_setascii (&delim, '\t'); - - if (output_delimiter_string == NULL) - { -- static char dummy[2]; -- dummy[0] = delim; -- dummy[1] = '\0'; -- output_delimiter_string = dummy; -- output_delimiter_length = 1; -+ output_delimiter_string = mb_ptr (delim); -+ output_delimiter_length = mb_len (delim); - } - - if (optind == argc) diff --git a/coreutils-i18n-expand-unexpand.patch b/coreutils-i18n-expand-unexpand.patch deleted file mode 100644 index b5f571f..0000000 --- a/coreutils-i18n-expand-unexpand.patch +++ /dev/null @@ -1,848 +0,0 @@ -From e87ab5b991b08092a7e07af82b3ec822a8604151 Mon Sep 17 00:00:00 2001 -From: Ondrej Oprala -Date: Wed, 5 Aug 2015 09:15:09 +0200 -Subject: [PATCH] expand,unexpand: add multibyte support -MIME-Version: 1.0 -Content-Type: text/plain; charset=UTF-8 -Content-Transfer-Encoding: 8bit - -* NEWS: Mention the changes. -* bootstrap.conf: Add mbfile to the list of modules. -* configure.ac: Properly initialize mbfile. -* src/expand.c (expand): Iterate over multibyte characters properly. -* src/unexpand.c (unexpand): Iterate over multibyte characters -properly. -* tests/local.mk: Add new tests. -* tests/{expand,unexpand}/mb.sh: New tests. - -Co-authored-by: Pádraig Brady ---- - bootstrap.conf | 1 + - configure.ac | 2 + - lib/mbfile.c | 3 + - lib/mbfile.h | 255 +++++++++++++++++++++++++++++++++++++++++++++++++++ - m4/mbfile.m4 | 14 +++ - src/expand.c | 43 +++++---- - src/unexpand.c | 54 +++++++---- - tests/expand/mb.sh | 98 ++++++++++++++++++++ - tests/local.mk | 2 + - tests/unexpand/mb.sh | 97 ++++++++++++++++++++ - 10 files changed, 535 insertions(+), 34 deletions(-) - create mode 100644 lib/mbfile.c - create mode 100644 lib/mbfile.h - create mode 100644 m4/mbfile.m4 - create mode 100755 tests/expand/mb.sh - create mode 100755 tests/unexpand/mb.sh - -diff --git a/bootstrap.conf b/bootstrap.conf -index 8a0ff31..a1c78b2 100644 ---- a/bootstrap.conf -+++ b/bootstrap.conf -@@ -152,6 +152,7 @@ gnulib_modules=" - maintainer-makefile - malloc-gnu - manywarnings -+ mbfile - mbrlen - mbrtowc - mbsalign -diff --git a/configure.ac b/configure.ac -index 1e74b36..24c9725 100644 ---- a/configure.ac -+++ b/configure.ac -@@ -427,6 +427,8 @@ fi - # I'm leaving it here for now. This whole thing needs to be modernized... - gl_WINSIZE_IN_PTEM - -+gl_MBFILE -+ - gl_HEADER_TIOCGWINSZ_IN_TERMIOS_H - - if test $gl_cv_sys_tiocgwinsz_needs_termios_h = no && \ -diff --git a/lib/mbfile.c b/lib/mbfile.c -new file mode 100644 -index 0000000..b0a468e ---- /dev/null -+++ b/lib/mbfile.c -@@ -0,0 +1,3 @@ -+#include -+#define MBFILE_INLINE _GL_EXTERN_INLINE -+#include "mbfile.h" -diff --git a/lib/mbfile.h b/lib/mbfile.h -new file mode 100644 -index 0000000..11f1b12 ---- /dev/null -+++ b/lib/mbfile.h -@@ -0,0 +1,255 @@ -+/* Multibyte character I/O: macros for multi-byte encodings. -+ Copyright (C) 2001, 2005, 2009-2015 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 . */ -+ -+/* Written by Mitsuru Chinen -+ and Bruno Haible . */ -+ -+/* The macros in this file implement multi-byte character input from a -+ stream. -+ -+ mb_file_t -+ is the type for multibyte character input stream, usable for variable -+ declarations. -+ -+ mbf_char_t -+ is the type for multibyte character or EOF, usable for variable -+ declarations. -+ -+ mbf_init (mbf, stream) -+ initializes the MB_FILE for reading from stream. -+ -+ mbf_getc (mbc, mbf) -+ reads the next multibyte character from mbf and stores it in mbc. -+ -+ mb_iseof (mbc) -+ returns true if mbc represents the EOF value. -+ -+ Here are the function prototypes of the macros. -+ -+ extern void mbf_init (mb_file_t mbf, FILE *stream); -+ extern void mbf_getc (mbf_char_t mbc, mb_file_t mbf); -+ extern bool mb_iseof (const mbf_char_t mbc); -+ */ -+ -+#ifndef _MBFILE_H -+#define _MBFILE_H 1 -+ -+#include -+#include -+#include -+#include -+ -+/* Tru64 with Desktop Toolkit C has a bug: must be included before -+ . -+ BSD/OS 4.1 has a bug: and must be included before -+ . */ -+#include -+#include -+#include -+ -+#include "mbchar.h" -+ -+#ifndef _GL_INLINE_HEADER_BEGIN -+ #error "Please include config.h first." -+#endif -+_GL_INLINE_HEADER_BEGIN -+#ifndef MBFILE_INLINE -+# define MBFILE_INLINE _GL_INLINE -+#endif -+ -+struct mbfile_multi { -+ FILE *fp; -+ bool eof_seen; -+ bool have_pushback; -+ mbstate_t state; -+ unsigned int bufcount; -+ char buf[MBCHAR_BUF_SIZE]; -+ struct mbchar pushback; -+}; -+ -+MBFILE_INLINE void -+mbfile_multi_getc (struct mbchar *mbc, struct mbfile_multi *mbf) -+{ -+ size_t bytes; -+ -+ /* 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; -+ } -+ -+ /* Before using mbrtowc, we need at least one byte. */ -+ if (mbf->bufcount == 0) -+ { -+ int c = getc (mbf->fp); -+ if (c == EOF) -+ { -+ mbf->eof_seen = true; -+ goto eof; -+ } -+ mbf->buf[0] = (unsigned char) c; -+ mbf->bufcount++; -+ } -+ -+ /* Handle most ASCII characters quickly, without calling mbrtowc(). */ -+ if (mbf->bufcount == 1 && mbsinit (&mbf->state) && is_basic (mbf->buf[0])) -+ { -+ /* These characters are part of the basic character set. ISO C 99 -+ guarantees that their wide character code is identical to their -+ char code. */ -+ mbc->wc = mbc->buf[0] = mbf->buf[0]; -+ mbc->wc_valid = true; -+ mbc->ptr = &mbc->buf[0]; -+ mbc->bytes = 1; -+ mbf->bufcount = 0; -+ return; -+ } -+ -+ /* Use mbrtowc on an increasing number of bytes. Read only as many bytes -+ from mbf->fp as needed. This is needed to give reasonable interactive -+ behaviour when mbf->fp is connected to an interactive tty. */ -+ for (;;) -+ { -+ /* We don't know whether the 'mbrtowc' function updates the state when -+ it returns -2, - this is the ISO C 99 and glibc-2.2 behaviour - or -+ not - amended ANSI C, glibc-2.1 and Solaris 2.7 behaviour. We -+ don't have an autoconf test for this, yet. -+ The new behaviour would allow us to feed the bytes one by one into -+ mbrtowc. But the old behaviour forces us to feed all bytes since -+ the end of the last character into mbrtowc. Since we want to retry -+ with more bytes when mbrtowc returns -2, we must backup the state -+ before calling mbrtowc, because implementations with the new -+ behaviour will clobber it. */ -+ mbstate_t backup_state = mbf->state; -+ -+ bytes = mbrtowc (&mbc->wc, &mbf->buf[0], mbf->bufcount, &mbf->state); -+ -+ if (bytes == (size_t) -1) -+ { -+ /* An invalid multibyte sequence was encountered. */ -+ /* Return a single byte. */ -+ bytes = 1; -+ mbc->wc_valid = false; -+ break; -+ } -+ else if (bytes == (size_t) -2) -+ { -+ /* An incomplete multibyte character. */ -+ mbf->state = backup_state; -+ if (mbf->bufcount == MBCHAR_BUF_SIZE) -+ { -+ /* An overlong incomplete multibyte sequence was encountered. */ -+ /* Return a single byte. */ -+ bytes = 1; -+ mbc->wc_valid = false; -+ break; -+ } -+ else -+ { -+ /* Read one more byte and retry mbrtowc. */ -+ int c = getc (mbf->fp); -+ if (c == EOF) -+ { -+ /* An incomplete multibyte character at the end. */ -+ mbf->eof_seen = true; -+ bytes = mbf->bufcount; -+ mbc->wc_valid = false; -+ break; -+ } -+ mbf->buf[mbf->bufcount] = (unsigned char) c; -+ mbf->bufcount++; -+ } -+ } -+ else -+ { -+ if (bytes == 0) -+ { -+ /* A null wide character was encountered. */ -+ bytes = 1; -+ assert (mbf->buf[0] == '\0'); -+ assert (mbc->wc == 0); -+ } -+ mbc->wc_valid = true; -+ break; -+ } -+ } -+ -+ /* Return the multibyte sequence mbf->buf[0..bytes-1]. */ -+ mbc->ptr = &mbc->buf[0]; -+ memcpy (&mbc->buf[0], &mbf->buf[0], bytes); -+ mbc->bytes = bytes; -+ -+ mbf->bufcount -= bytes; -+ if (mbf->bufcount > 0) -+ { -+ /* It's not worth calling memmove() for so few bytes. */ -+ unsigned int count = mbf->bufcount; -+ char *p = &mbf->buf[0]; -+ -+ do -+ { -+ *p = *(p + bytes); -+ p++; -+ } -+ while (--count > 0); -+ } -+ return; -+ -+eof: -+ /* An mbchar_t with bytes == 0 is used to indicate EOF. */ -+ mbc->ptr = NULL; -+ mbc->bytes = 0; -+ mbc->wc_valid = false; -+ return; -+} -+ -+MBFILE_INLINE void -+mbfile_multi_ungetc (const struct mbchar *mbc, struct mbfile_multi *mbf) -+{ -+ mb_copy (&mbf->pushback, mbc); -+ mbf->have_pushback = true; -+} -+ -+typedef struct mbfile_multi mb_file_t; -+ -+typedef mbchar_t mbf_char_t; -+ -+#define mbf_init(mbf, stream) \ -+ ((mbf).fp = (stream), \ -+ (mbf).eof_seen = false, \ -+ (mbf).have_pushback = false, \ -+ memset (&(mbf).state, '\0', sizeof (mbstate_t)), \ -+ (mbf).bufcount = 0) -+ -+#define mbf_getc(mbc, mbf) mbfile_multi_getc (&(mbc), &(mbf)) -+ -+#define mbf_ungetc(mbc, mbf) mbfile_multi_ungetc (&(mbc), &(mbf)) -+ -+#define mb_iseof(mbc) ((mbc).bytes == 0) -+ -+#ifndef _GL_INLINE_HEADER_BEGIN -+ #error "Please include config.h first." -+#endif -+_GL_INLINE_HEADER_BEGIN -+ -+#endif /* _MBFILE_H */ -diff --git a/m4/mbfile.m4 b/m4/mbfile.m4 -new file mode 100644 -index 0000000..8589902 ---- /dev/null -+++ b/m4/mbfile.m4 -@@ -0,0 +1,14 @@ -+# mbfile.m4 serial 7 -+dnl Copyright (C) 2005, 2008-2015 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 mbfile.h -+dnl From Bruno Haible. -+ -+AC_DEFUN([gl_MBFILE], -+[ -+ AC_REQUIRE([AC_TYPE_MBSTATE_T]) -+ : -+]) -diff --git a/src/expand.c b/src/expand.c -index 9fa2e10..380e020 100644 ---- a/src/expand.c -+++ b/src/expand.c -@@ -37,6 +37,9 @@ - #include - #include - #include -+ -+#include -+ - #include "system.h" - #include "die.h" - #include "xstrndup.h" -@@ -100,19 +103,19 @@ expand (void) - { - /* Input stream. */ - FILE *fp = next_file (NULL); -+ mb_file_t mbf; -+ mbf_char_t c; - - if (!fp) - return; - -+ mbf_init (mbf, fp); -+ - while (true) - { -- /* Input character, or EOF. */ -- int c; -- - /* If true, perform translations. */ - bool convert = true; - -- - /* The following variables have valid values only when CONVERT - is true: */ - -@@ -122,17 +125,23 @@ expand (void) - /* Index in TAB_LIST of next tab stop to examine. */ - size_t tab_index = 0; - -- - /* Convert a line of text. */ - - do - { -- while ((c = getc (fp)) < 0 && (fp = next_file (fp))) -- continue; -+ do { -+ mbf_getc (c, mbf); -+ if (mb_iseof (c)) -+ { -+ mbf_init (mbf, fp = next_file (fp)); -+ continue; -+ } -+ } -+ while (false); - - if (convert) - { -- if (c == '\t') -+ if (mb_iseq (c, '\t')) - { - /* Column the next input tab stop is on. */ - uintmax_t next_tab_column; -@@ -151,32 +160,34 @@ expand (void) - if (putchar (' ') < 0) - die (EXIT_FAILURE, errno, _("write error")); - -- c = ' '; -+ mb_setascii (&c, ' '); - } -- else if (c == '\b') -+ else if (mb_iseq (c, '\b')) - { - /* Go back one column, and force recalculation of the - next tab stop. */ - column -= !!column; - tab_index -= !!tab_index; - } -- else -+ /* A leading control character could make us trip over. */ -+ else if (!mb_iscntrl (c)) - { -- column++; -+ column += mb_width (c); - if (!column) - die (EXIT_FAILURE, 0, _("input line is too long")); - } - -- convert &= convert_entire_line || !! isblank (c); -+ convert &= convert_entire_line || mb_isblank (c); - } - -- if (c < 0) -+ if (mb_iseof (c)) - return; - -- if (putchar (c) < 0) -+ mb_putc (c, stdout); -+ if (ferror (stdout)) - die (EXIT_FAILURE, errno, _("write error")); - } -- while (c != '\n'); -+ while (!mb_iseq (c, '\n')); - } - } - -diff --git a/src/unexpand.c b/src/unexpand.c -index 7801274..569a7ee 100644 ---- a/src/unexpand.c -+++ b/src/unexpand.c -@@ -38,6 +38,9 @@ - #include - #include - #include -+ -+#include -+ - #include "system.h" - #include "die.h" - #include "xstrndup.h" -@@ -107,11 +110,12 @@ unexpand (void) - { - /* Input stream. */ - FILE *fp = next_file (NULL); -+ mb_file_t mbf; - - /* The array of pending blanks. In non-POSIX locales, blanks can - include characters other than spaces, so the blanks must be - stored, not merely counted. */ -- char *pending_blank; -+ mbf_char_t *pending_blank; - - if (!fp) - return; -@@ -119,12 +123,14 @@ unexpand (void) - /* 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 = xmalloc (max_column_width); -+ pending_blank = xmalloc (max_column_width * sizeof (mbf_char_t)); -+ -+ mbf_init (mbf, fp); - - while (true) - { - /* Input character, or EOF. */ -- int c; -+ mbf_char_t c; - - /* If true, perform translations. */ - bool convert = true; -@@ -158,12 +164,19 @@ unexpand (void) - - do - { -- while ((c = getc (fp)) < 0 && (fp = next_file (fp))) -- continue; -+ do { -+ mbf_getc (c, mbf); -+ if (mb_iseof (c)) -+ { -+ mbf_init (mbf, fp = next_file (fp)); -+ continue; -+ } -+ } -+ while (false); - - if (convert) - { -- bool blank = !! isblank (c); -+ bool blank = mb_isblank (c); - - if (blank) - { -@@ -180,16 +193,16 @@ unexpand (void) - if (next_tab_column < column) - die (EXIT_FAILURE, 0, _("input line is too long")); - -- if (c == '\t') -+ if (mb_iseq (c, '\t')) - { - column = next_tab_column; - - if (pending) -- pending_blank[0] = '\t'; -+ mb_setascii (&pending_blank[0], '\t'); - } - else - { -- column++; -+ column += mb_width (c); - - if (! (prev_blank && column == next_tab_column)) - { -@@ -197,13 +210,14 @@ unexpand (void) - will be replaced by tabs. */ - if (column == next_tab_column) - one_blank_before_tab_stop = true; -- pending_blank[pending++] = c; -+ mb_copy (&pending_blank[pending++], &c); - prev_blank = true; - continue; - } - - /* Replace the pending blanks by a tab or two. */ -- pending_blank[0] = c = '\t'; -+ mb_setascii (&c, '\t'); -+ mb_setascii (&pending_blank[0], '\t'); - } - - /* Discard pending blanks, unless it was a single -@@ -211,7 +225,7 @@ unexpand (void) - pending = one_blank_before_tab_stop; - } - } -- else if (c == '\b') -+ else if (mb_iseq (c, '\b')) - { - /* Go back one column, and force recalculation of the - next tab stop. */ -@@ -221,7 +235,7 @@ unexpand (void) - } - else - { -- column++; -+ column += mb_width (c); - if (!column) - die (EXIT_FAILURE, 0, _("input line is too long")); - } -@@ -229,8 +243,11 @@ unexpand (void) - if (pending) - { - if (pending > 1 && one_blank_before_tab_stop) -- pending_blank[0] = '\t'; -- if (fwrite (pending_blank, 1, pending, stdout) != pending) -+ mb_setascii (&pending_blank[0], '\t'); -+ -+ for (int n = 0; n < pending; ++n) -+ mb_putc (pending_blank[n], stdout); -+ if (ferror (stdout)) - die (EXIT_FAILURE, errno, _("write error")); - pending = 0; - one_blank_before_tab_stop = false; -@@ -240,16 +257,17 @@ unexpand (void) - convert &= convert_entire_line || blank; - } - -- if (c < 0) -+ if (mb_iseof (c)) - { - free (pending_blank); - return; - } - -- if (putchar (c) < 0) -+ mb_putc (c, stdout); -+ if (ferror (stdout)) - die (EXIT_FAILURE, errno, _("write error")); - } -- while (c != '\n'); -+ while (!mb_iseq (c, '\n')); - } - } - -diff --git a/tests/expand/mb.sh b/tests/expand/mb.sh -new file mode 100755 -index 0000000..7971e18 ---- /dev/null -+++ b/tests/expand/mb.sh -@@ -0,0 +1,98 @@ -+#!/bin/sh -+ -+# Copyright (C) 2012-2015 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_ expand -+ -+export LC_ALL=en_US.UTF-8 -+ -+#input containing multibyte characters -+cat <<\EOF > in || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+EOF -+env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_ -+ -+cat <<\EOF > exp || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+expand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+#test characters with display widths != 1 -+env printf '12345678 -+e\t|ascii(1) -+\u00E9\t|composed(1) -+e\u0301\t|decomposed(1) -+\u3000\t|ideo-space(2) -+\uFF0D\t|full-hypen(2) -+' > in || framework_failure_ -+ -+env printf '12345678 -+e |ascii(1) -+\u00E9 |composed(1) -+e\u0301 |decomposed(1) -+\u3000 |ideo-space(2) -+\uFF0D |full-hypen(2) -+' > exp || framework_failure_ -+ -+expand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+#shouldn't fail with "input line too long" -+#when a line starts with a control character -+env printf '\n' > in || framework_failure_ -+ -+expand < in > out || fail=1 -+compare in out > /dev/null 2>&1 || fail=1 -+ -+#non-Unicode characters interspersed between Unicode ones -+env printf '12345678 -+\t\xFF| -+\xFF\t| -+\t\xFFä| -+ä\xFF\t| -+\tä\xFF| -+\xFF\tä| -+äbcdef\xFF\t| -+' > in || framework_failure_ -+ -+env printf '12345678 -+ \xFF| -+\xFF | -+ \xFFä| -+ä\xFF | -+ ä\xFF| -+\xFF ä| -+äbcdef\xFF | -+' > exp || framework_failure_ -+ -+expand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+exit $fail -diff --git a/tests/local.mk b/tests/local.mk -index 192f776..8053397 100644 ---- a/tests/local.mk -+++ b/tests/local.mk -@@ -544,6 +544,7 @@ all_tests = \ - tests/du/threshold.sh \ - tests/du/trailing-slash.sh \ - tests/du/two-args.sh \ -+ tests/expand/mb.sh \ - tests/id/gnu-zero-uids.sh \ - tests/id/no-context.sh \ - tests/id/context.sh \ -@@ -684,6 +685,7 @@ all_tests = \ - tests/touch/read-only.sh \ - tests/touch/relative.sh \ - tests/touch/trailing-slash.sh \ -+ tests/unexpand/mb.sh \ - $(all_root_tests) - - # See tests/factor/create-test.sh. -diff --git a/tests/unexpand/mb.sh b/tests/unexpand/mb.sh -new file mode 100755 -index 0000000..60d4c1a ---- /dev/null -+++ b/tests/unexpand/mb.sh -@@ -0,0 +1,97 @@ -+#!/bin/sh -+ -+# Copyright (C) 2012-2015 Free Software Foundation, Inc. -+ -+# This program is free software: you can redistribute it and/or modify -+# it under the terms of the GNU General Public License as published by -+# the Free Software Foundation, either version 3 of the License, or -+# (at your option) any later version. -+ -+# This program is distributed in the hope that it will be useful, -+# but WITHOUT ANY WARRANTY; without even the implied warranty of -+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -+# GNU General Public License for more details. -+ -+# You should have received a copy of the GNU General Public License -+# along with this program. If not, see . -+ -+. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src -+print_ver_ unexpand -+ -+export LC_ALL=en_US.UTF-8 -+ -+#input containing multibyte characters -+cat > in <<\EOF -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+cat > exp <<\EOF -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+unexpand -a < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+#test characters with a display width larger than 1 -+ -+env printf '12345678 -+e |ascii(1) -+\u00E9 |composed(1) -+e\u0301 |decomposed(1) -+\u3000 |ideo-space(2) -+\uFF0D |full-hypen(2) -+' > in || framework_failure_ -+ -+env printf '12345678 -+e\t|ascii(1) -+\u00E9\t|composed(1) -+e\u0301\t|decomposed(1) -+\u3000\t|ideo-space(2) -+\uFF0D\t|full-hypen(2) -+' > exp || framework_failure_ -+ -+unexpand -a < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+#test input where a blank of width > 1 is not being substituted -+in="$(LC_ALL=en_US.UTF-8 printf ' \u3000 ö ü ß')" -+exp=' 　 ö ü ß' -+ -+unexpand -a < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+#non-Unicode characters interspersed between Unicode ones -+env printf '12345678 -+ \xFF| -+\xFF | -+ \xFFä| -+ä\xFF | -+ ä\xFF| -+\xFF ä| -+äbcdef\xFF | -+' > in || framework_failure_ -+ -+env printf '12345678 -+\t\xFF| -+\xFF\t| -+\t\xFFä| -+ä\xFF\t| -+\tä\xFF| -+\xFF\tä| -+äbcdef\xFF\t| -+' > exp || framework_failure_ -+ -+unexpand -a < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 --- -2.7.4 - diff --git a/coreutils-i18n-fix-unexpand.patch b/coreutils-i18n-fix-unexpand.patch deleted file mode 100644 index f0c347c..0000000 --- a/coreutils-i18n-fix-unexpand.patch +++ /dev/null @@ -1,28 +0,0 @@ -From 02424bfcd719bbaa695f4e1c3ef17ad91b0d23c0 Mon Sep 17 00:00:00 2001 -From: Lubomir Rintel -Date: Thu, 28 Jan 2016 20:57:22 +0100 -Subject: [PATCH] unexpand: fix blank line handling - - echo '' |./src/unexpand -a - -Really? ---- - src/unexpand.c | 2 +- - 1 file changed, 1 insertion(+), 1 deletion(-) - -diff --git a/src/unexpand.c b/src/unexpand.c -index 569a7ee..3bbbd66 100644 ---- a/src/unexpand.c -+++ b/src/unexpand.c -@@ -233,7 +233,7 @@ unexpand (void) - next_tab_column = column; - tab_index -= !!tab_index; - } -- else -+ else if (!mb_iseq (c, '\n')) - { - column += mb_width (c); - if (!column) --- -2.7.4 - diff --git a/coreutils-i18n-fix2-expand-unexpand.patch b/coreutils-i18n-fix2-expand-unexpand.patch deleted file mode 100644 index b34d7b7..0000000 --- a/coreutils-i18n-fix2-expand-unexpand.patch +++ /dev/null @@ -1,108 +0,0 @@ -diff --git a/src/expand.c b/src/expand.c -index 380e020..310b349 100644 ---- a/src/expand.c -+++ b/src/expand.c -@@ -129,15 +129,19 @@ expand (void) - - do - { -- do { -+ while (true) { - mbf_getc (c, mbf); -- if (mb_iseof (c)) -+ if ((mb_iseof (c)) && (fp = next_file (fp))) - { -- mbf_init (mbf, fp = next_file (fp)); -+ mbf_init (mbf, fp); - continue; - } -+ else -+ { -+ break; -+ } - } -- while (false); -+ - - if (convert) - { -diff --git a/src/unexpand.c b/src/unexpand.c -index 3bbbd66..863a90a 100644 ---- a/src/unexpand.c -+++ b/src/unexpand.c -@@ -164,15 +164,19 @@ unexpand (void) - - do - { -- do { -+ while (true) { - mbf_getc (c, mbf); -- if (mb_iseof (c)) -+ if ((mb_iseof (c)) && (fp = next_file (fp))) - { -- mbf_init (mbf, fp = next_file (fp)); -+ mbf_init (mbf, fp); - continue; - } -+ else -+ { -+ break; -+ } - } -- while (false); -+ - - if (convert) - { -diff --git a/tests/expand/mb.sh b/tests/expand/mb.sh -index 7971e18..031be7a 100755 ---- a/tests/expand/mb.sh -+++ b/tests/expand/mb.sh -@@ -44,6 +44,20 @@ EOF - expand < in > out || fail=1 - compare exp out > /dev/null 2>&1 || fail=1 - -+#multiple files as an input -+cat <<\EOF >> exp || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+expand ./in ./in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ - #test characters with display widths != 1 - env printf '12345678 - e\t|ascii(1) -diff --git a/tests/unexpand/mb.sh b/tests/unexpand/mb.sh -index 60d4c1a..8d75652 100755 ---- a/tests/unexpand/mb.sh -+++ b/tests/unexpand/mb.sh -@@ -44,6 +44,22 @@ EOF - unexpand -a < in > out || fail=1 - compare exp out > /dev/null 2>&1 || fail=1 - -+ -+#multiple files as an input -+cat >> exp <<\EOF -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+ -+unexpand -a ./in ./in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ - #test characters with a display width larger than 1 - - env printf '12345678 diff --git a/coreutils-i18n-fold-newline.patch b/coreutils-i18n-fold-newline.patch deleted file mode 100644 index f7286ef..0000000 --- a/coreutils-i18n-fold-newline.patch +++ /dev/null @@ -1,80 +0,0 @@ -From ff424639fe863cbd6963add1a79b97290c1606c6 Mon Sep 17 00:00:00 2001 -From: rpm-build -Date: Fri, 3 Feb 2017 12:26:53 +0100 -Subject: [PATCH] fold.c: preserve new-lines in mutlibyte text - ---- - src/fold.c | 49 ++++++++++++++++++++++++------------------------- - 1 file changed, 24 insertions(+), 25 deletions(-) - -diff --git a/src/fold.c b/src/fold.c -index d23edd5..8c232a7 100644 ---- a/src/fold.c -+++ b/src/fold.c -@@ -342,39 +342,38 @@ fold_multibyte_text (FILE *istream, size_t width, int *saved_errno) - } - - rescan: -- if (operating_mode == byte_mode) /* byte mode */ -+ 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 */ -+ else /* column mode */ - { -- if (convfail) -- increment = 1; -- else -+ switch (wc) - { -- switch (wc) -- { -- case L'\n': -- fwrite (line_out, sizeof(char), offset_out, stdout); -- START_NEW_LINE; -- continue; -+ case L'\b': -+ increment = (column > 0) ? -1 : 0; -+ break; - -- case L'\b': -- increment = (column > 0) ? -1 : 0; -- break; -+ case L'\r': -+ increment = -1 * column; -+ break; - -- case L'\r': -- increment = -1 * column; -- break; -+ case L'\t': -+ increment = 8 - column % 8; -+ break; - -- case L'\t': -- increment = 8 - column % 8; -- break; -- -- default: -- increment = wcwidth (wc); -- increment = (increment < 0) ? 0 : increment; -- } -+ default: -+ increment = wcwidth (wc); -+ increment = (increment < 0) ? 0 : increment; - } - } - --- -2.7.4 - diff --git a/coreutils-i18n-sort-human.patch b/coreutils-i18n-sort-human.patch deleted file mode 100644 index 6752493..0000000 --- a/coreutils-i18n-sort-human.patch +++ /dev/null @@ -1,35 +0,0 @@ -From 3976ef5a20369d8b490907ab2cba2d617305a5e0 Mon Sep 17 00:00:00 2001 -From: Kamil Dudka -Date: Mon, 30 May 2016 16:19:20 +0200 -Subject: [PATCH] sort: do not use static array 'blanks' in human_numcompare() - -... because the array is not initialized with MB locales. Note this is -rather a conservative fix. I plan to do more cleanup of the i18n patch -in Fedora to prevent mistakes like this in future updates of coreutils. ---- - src/sort.c | 8 +++----- - 1 file changed, 3 insertions(+), 5 deletions(-) - -diff --git a/src/sort.c b/src/sort.c -index 9e07ad8..e47b039 100644 ---- a/src/sort.c -+++ b/src/sort.c -@@ -2304,12 +2304,10 @@ find_unit_order (char const *number) - < K/k < M < G < T < P < E < Z < Y */ - - static int --human_numcompare (char const *a, char const *b) -+human_numcompare (char *a, char *b) - { -- while (blanks[to_uchar (*a)]) -- a++; -- while (blanks[to_uchar (*b)]) -- b++; -+ skipblanks(&a, a + strlen(a)); -+ skipblanks(&b, b + strlen(b)); - - int diff = find_unit_order (a) - find_unit_order (b); - return (diff ? diff : strnumcmp (a, b, decimal_point, thousands_sep)); --- -2.5.5 - diff --git a/coreutils-i18n-un-expand-BOM.patch b/coreutils-i18n-un-expand-BOM.patch deleted file mode 100644 index 2ccdcca..0000000 --- a/coreutils-i18n-un-expand-BOM.patch +++ /dev/null @@ -1,456 +0,0 @@ -From 7a7c776a4e228d180e74614fd8c8afcad5d4bdf7 Mon Sep 17 00:00:00 2001 -From: Jakub Martisko -Date: Thu, 7 Jul 2016 12:53:26 +0200 -Subject: [PATCH] coreutils-i18n-un-expand-BOM.patch - ---- - src/expand-common.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++++++ - src/expand-common.h | 12 ++++++ - src/expand.c | 45 +++++++++++++++++++- - src/unexpand.c | 43 ++++++++++++++++++- - tests/expand/mb.sh | 71 ++++++++++++++++++++++++++++++++ - tests/unexpand/mb.sh | 59 ++++++++++++++++++++++++++ - 6 files changed, 342 insertions(+), 2 deletions(-) - -diff --git a/src/expand-common.c b/src/expand-common.c -index 4657e46..97cbb09 100644 ---- a/src/expand-common.c -+++ b/src/expand-common.c -@@ -18,6 +18,7 @@ - - #include - #include -+#include - #include "system.h" - #include "die.h" - #include "error.h" -@@ -105,6 +106,119 @@ set_extend_size (uintmax_t tabval) - return ok; - } - -+extern int -+set_utf_locale (void) -+{ -+ /*try using some predefined locale */ -+ const char* predef_locales[] = {"C.UTF8","en_US.UTF8","en_GB.UTF8"}; -+ -+ const int predef_locales_count=3; -+ for (int i=0;ibufcount=0; -+ if (c == 0xEF) -+ { -+ c=fgetc(fp); -+ } -+ else -+ { -+ if (c != EOF) -+ { -+ ungetc(c,fp); -+ } -+ return false; -+ } -+ -+ if (c == 0xBB) -+ { -+ c=fgetc(fp); -+ } -+ else -+ { -+ if ( c!= EOF ) -+ { -+ mbf->buf[0]=(unsigned char) 0xEF; -+ mbf->bufcount=1; -+ ungetc(c,fp); -+ return false; -+ } -+ else -+ { -+ ungetc(0xEF,fp); -+ return false; -+ } -+ } -+ if (c == 0xBF) -+ { -+ mbf->bufcount=0; -+ return true; -+ } -+ else -+ { -+ if (c != EOF) -+ { -+ mbf->buf[0]=(unsigned char) 0xEF; -+ mbf->buf[1]=(unsigned char) 0xBB; -+ mbf->bufcount=2; -+ ungetc(c,fp); -+ return false; -+ } -+ else -+ { -+ mbf->buf[0]=(unsigned char) 0xEF; -+ mbf->bufcount=1; -+ ungetc(0xBB,fp); -+ return false; -+ } -+ } -+ return false; -+} -+ -+extern void -+print_bom(void) -+{ -+ putc (0xEF, stdout); -+ putc (0xBB, stdout); -+ putc (0xBF, stdout); -+} -+ - /* Add the comma or blank separated list of tab stops STOPS - to the list of tab stops. */ - extern void -diff --git a/src/expand-common.h b/src/expand-common.h -index 8cb2079..763bfda 100644 ---- a/src/expand-common.h -+++ b/src/expand-common.h -@@ -34,6 +34,18 @@ extern size_t max_column_width; - /* The desired exit status. */ - extern int exit_status; - -+extern int -+set_utf_locale (void); -+ -+extern bool -+check_utf_locale(void); -+ -+extern bool -+check_bom(FILE* fp, mb_file_t *mbf); -+ -+extern void -+print_bom(void); -+ - /* Add tab stop TABVAL to the end of 'tab_list'. */ - extern void - add_tab_stop (uintmax_t tabval); -diff --git a/src/expand.c b/src/expand.c -index 310b349..4136824 100644 ---- a/src/expand.c -+++ b/src/expand.c -@@ -105,11 +105,33 @@ expand (void) - FILE *fp = next_file (NULL); - mb_file_t mbf; - mbf_char_t c; -+ /* True if the starting locale is utf8. */ -+ bool using_utf_locale; -+ -+ /* True if the first file contains BOM header. */ -+ bool found_bom; -+ using_utf_locale=check_utf_locale(); - - 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) -+ { -+ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale")); -+ } -+ } -+ -+ -+ if (found_bom == true) -+ { -+ print_bom(); -+ } - - while (true) - { -@@ -134,6 +156,27 @@ expand (void) - if ((mb_iseof (c)) && (fp = next_file (fp))) - { - mbf_init (mbf, fp); -+ if (fp!=NULL) -+ { -+ if (check_bom(fp,&mbf)==true) -+ { -+ /*Not the first file - check BOM header*/ -+ if (using_utf_locale==false && found_bom==false) -+ { -+ /*BOM header in subsequent file but not in the first one. */ -+ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); -+ } -+ } -+ else -+ { -+ if(using_utf_locale==false && found_bom==true) -+ { -+ /*First file conatined BOM header - locale was switched to UTF -+ /*all subsequent files should contain BOM. */ -+ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); -+ } -+ } -+ } - continue; - } - else -diff --git a/src/unexpand.c b/src/unexpand.c -index 863a90a..5681b58 100644 ---- a/src/unexpand.c -+++ b/src/unexpand.c -@@ -116,16 +116,36 @@ unexpand (void) - include characters other than spaces, so the blanks must be - stored, not merely counted. */ - mbf_char_t *pending_blank; -+ /* True if the starting locale is utf8. */ -+ bool using_utf_locale; -+ -+ /* True if the first file contains BOM header. */ -+ bool found_bom; -+ using_utf_locale=check_utf_locale(); - - 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) -+ { -+ 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 = xmalloc (max_column_width * sizeof (mbf_char_t)); - -- mbf_init (mbf, fp); -+ if (found_bom == true) -+ { -+ print_bom(); -+ } - - while (true) - { -@@ -169,6 +189,27 @@ unexpand (void) - if ((mb_iseof (c)) && (fp = next_file (fp))) - { - mbf_init (mbf, fp); -+ if (fp!=NULL) -+ { -+ if (check_bom(fp,&mbf)==true) -+ { -+ /*Not the first file - check BOM header*/ -+ if (using_utf_locale==false && found_bom==false) -+ { -+ /*BOM header in subsequent file but not in the first one. */ -+ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); -+ } -+ } -+ else -+ { -+ if(using_utf_locale==false && found_bom==true) -+ { -+ /*First file conatined BOM header - locale was switched to UTF -+ /*all subsequent files should contain BOM. */ -+ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); -+ } -+ } -+ } - continue; - } - else -diff --git a/tests/expand/mb.sh b/tests/expand/mb.sh -index 031be7a..1621c84 100755 ---- a/tests/expand/mb.sh -+++ b/tests/expand/mb.sh -@@ -109,4 +109,75 @@ env printf '12345678 - expand < in > out || fail=1 - compare exp out > /dev/null 2>&1 || fail=1 - -+ -+ -+#BOM header test 1 -+printf "\xEF\xBB\xBF" > in; cat <<\EOF >> in || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+EOF -+env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_ -+ -+printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+ -+expand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LANG=C expand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LC_ALL=C expand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+ -+printf '\xEF\xBB\xBF' > in1; cat <<\EOF >> in1 || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+EOF -+env printf ' äöü\t. öüä. \tä xx\n' >> in1 || framework_failure_ -+ -+ -+printf '\xEF\xBB\xBF' > exp; cat <<\EOF >> exp || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+expand in1 in1 > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LANG=C expand in1 in1 > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LC_ALL=C expand in1 in1 > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ - exit $fail -diff --git a/tests/unexpand/mb.sh b/tests/unexpand/mb.sh -index 8d75652..9d4ee3e 100755 ---- a/tests/unexpand/mb.sh -+++ b/tests/unexpand/mb.sh -@@ -111,3 +111,62 @@ env printf '12345678 - - unexpand -a < in > out || fail=1 - compare exp out > /dev/null 2>&1 || fail=1 -+ -+#BOM header test 1 -+printf "\xEF\xBB\xBF" > in; cat <<\EOF >> in || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_ -+ -+printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+unexpand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LANG=C unexpand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LC_ALL=C unexpand < in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+ -+printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_ -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+1234567812345678123456781 -+. . . . -+a b c d -+. . . . -+ä ö ü ß -+. . . . -+ äöü . öüä. ä xx -+EOF -+ -+ -+unexpand in in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LANG=C unexpand in in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 -+ -+LC_ALL=C unexpand in in > out || fail=1 -+compare exp out > /dev/null 2>&1 || fail=1 --- -2.9.3 - diff --git a/coreutils-i18n.patch b/coreutils-i18n.patch index ab5d8dc..83579e9 100644 --- a/coreutils-i18n.patch +++ b/coreutils-i18n.patch @@ -1,39 +1,80 @@ -From 29117b2d07af00f4d4b87cf778e4294588ab1a83 Mon Sep 17 00:00:00 2001 -From: Kamil Dudka -Date: Thu, 1 Dec 2016 15:10:04 +0100 +From a81b096084524e9aeef5e8b81fc829eb9efec581 Mon Sep 17 00:00:00 2001 +From: rpm-build +Date: Wed, 30 Aug 2023 17:19:58 +0200 Subject: [PATCH] coreutils-i18n.patch -TODO: merge upstream --- + bootstrap.conf | 2 + + configure.ac | 6 + lib/linebuffer.h | 8 + - src/fold.c | 308 ++++++++++++++++-- - src/join.c | 359 ++++++++++++++++++--- - src/pr.c | 443 ++++++++++++++++++++++--- - src/sort.c | 764 +++++++++++++++++++++++++++++++++++++++++--- - src/uniq.c | 265 ++++++++++++++- + lib/mbfile.c | 20 + + lib/mbfile.h | 283 +++++++++++++ + m4/mbfile.m4 | 16 + + src/cut.c | 508 +++++++++++++++++++++-- + src/expand-common.c | 114 ++++++ + src/expand-common.h | 12 + + src/expand.c | 90 +++- + src/local.mk | 4 +- + src/pr.c | 443 ++++++++++++++++++-- + src/sort.c | 791 +++++++++++++++++++++++++++++++++--- + src/unexpand.c | 101 ++++- + tests/Coreutils.pm | 3 + + tests/expand/mb.sh | 183 +++++++++ tests/i18n/sort.sh | 29 ++ - tests/local.mk | 2 + - tests/misc/cut.pl | 7 +- - tests/misc/expand.pl | 42 +++ - tests/misc/fold.pl | 50 ++- - tests/misc/join.pl | 50 +++ - tests/misc/sort-mb-tests.sh | 45 +++ - tests/misc/sort-merge.pl | 42 +++ - tests/misc/sort.pl | 40 ++- - tests/misc/unexpand.pl | 39 +++ - tests/misc/uniq.pl | 55 ++++ + tests/local.mk | 4 + + tests/misc/expand.pl | 42 ++ + tests/misc/sort-mb-tests.sh | 45 ++ + tests/misc/unexpand.pl | 39 ++ tests/pr/pr-tests.pl | 49 +++ - 18 files changed, 2435 insertions(+), 162 deletions(-) + tests/sort/sort-merge.pl | 42 ++ + tests/sort/sort.pl | 40 +- + tests/unexpand/mb.sh | 172 ++++++++ + 25 files changed, 2879 insertions(+), 167 deletions(-) + create mode 100644 lib/mbfile.c + create mode 100644 lib/mbfile.h + create mode 100644 m4/mbfile.m4 + create mode 100644 tests/expand/mb.sh create mode 100644 tests/i18n/sort.sh create mode 100644 tests/misc/sort-mb-tests.sh + create mode 100644 tests/unexpand/mb.sh +diff --git a/bootstrap.conf b/bootstrap.conf +index ec68ac8..ec2fbbe 100644 +--- a/bootstrap.conf ++++ b/bootstrap.conf +@@ -171,6 +171,8 @@ gnulib_modules=" + malloc-gnu + manywarnings + mbbuf ++ mbchar ++ mbfile + mbrlen + mbrtoc32 + mbrtowc +diff --git a/configure.ac b/configure.ac +index 5e99ef3..ac07577 100644 +--- a/configure.ac ++++ b/configure.ac +@@ -465,6 +465,12 @@ fi + # I'm leaving it here for now. This whole thing needs to be modernized... + gl_WINSIZE_IN_PTEM + ++gl_MBFILE ++dnl Do not use gl_MODULE_INDICATOR([mbfile]) here: we don't want 'struct mbchar' ++dnl to have a different size in lib/ than in tests/. ++AC_DEFINE([GNULIB_MBFILE], [1], ++ [Define to 1 if the gnulib module 'mbfile' is in use.]) ++ + gl_HEADER_TIOCGWINSZ_IN_TERMIOS_H + + if test $gl_cv_sys_tiocgwinsz_needs_termios_h = no && \ diff --git a/lib/linebuffer.h b/lib/linebuffer.h -index 64181af..9b8fe5a 100644 +index ca56f80..509b7e6 100644 --- a/lib/linebuffer.h +++ b/lib/linebuffer.h -@@ -21,6 +21,11 @@ +@@ -27,6 +27,11 @@ extern "C" { + #endif - # include +/* Get mbstate_t. */ +# if HAVE_WCHAR_H @@ -43,9 +84,9 @@ index 64181af..9b8fe5a 100644 /* A 'struct linebuffer' holds a line of text. */ struct linebuffer -@@ -28,6 +33,9 @@ struct linebuffer - size_t size; /* Allocated. */ - size_t length; /* Used. */ +@@ -34,6 +39,9 @@ struct linebuffer + idx_t size; /* Allocated. */ + idx_t length; /* Used. */ char *buffer; +# if HAVE_WCHAR_H + mbstate_t state; @@ -53,32 +94,365 @@ index 64181af..9b8fe5a 100644 }; /* Initialize linebuffer LINEBUFFER for use. */ -diff --git a/src/fold.c b/src/fold.c -index 8cd0d6b..d23edd5 100644 ---- a/src/fold.c -+++ b/src/fold.c -@@ -22,12 +22,34 @@ +diff --git a/lib/mbfile.c b/lib/mbfile.c +new file mode 100644 +index 0000000..f4e3e77 +--- /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. ++ ++ 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 3 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 MBFILE_INLINE _GL_EXTERN_INLINE ++#include "mbfile.h" +diff --git a/lib/mbfile.h b/lib/mbfile.h +new file mode 100644 +index 0000000..c852f31 +--- /dev/null ++++ b/lib/mbfile.h +@@ -0,0 +1,283 @@ ++/* Multibyte character I/O: macros for multi-byte encodings. ++ Copyright (C) 2001, 2005, 2009-2025 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 3 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 Mitsuru Chinen ++ and Bruno Haible . */ ++ ++/* The macros in this file implement multi-byte character input from a ++ stream. ++ ++ mb_file_t ++ is the type for multibyte character input stream, usable for variable ++ declarations. ++ ++ mbf_char_t ++ is the type for multibyte character or EOF, usable for variable ++ declarations. ++ ++ mbf_init (mbf, stream) ++ initializes the MB_FILE for reading from stream. ++ ++ mbf_getc (mbc, mbf) ++ reads the next multibyte character from mbf and stores it in mbc. ++ ++ mb_iseof (mbc) ++ returns true if mbc represents the EOF value. ++ ++ Here are the function prototypes of the macros. ++ ++ extern void mbf_init (mb_file_t mbf, FILE *stream); ++ extern void mbf_getc (mbf_char_t mbc, mb_file_t mbf); ++ extern bool mb_iseof (const mbf_char_t mbc); ++ */ ++ ++#ifndef _MBFILE_H ++#define _MBFILE_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 ++#include ++#include ++#include ++ ++#include "mbchar.h" ++ ++_GL_INLINE_HEADER_BEGIN ++#ifndef MBFILE_INLINE ++# 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 */ ++ mbstate_t state; ++ unsigned int bufcount; ++ char buf[MBCHAR_BUF_SIZE]; ++ struct mbchar pushback[MBFILE_MAX_PUSHBACK]; ++}; ++ ++MBFILE_INLINE void ++mbfile_multi_getc (struct mbchar *mbc, struct mbfile_multi *mbf) ++{ ++ 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; ++ ++ new_bufcount = mbf->bufcount; ++ ++ /* If mbf->state is not in an initial state, some more 32-bit wide character ++ may be hiding in the state. We need to call mbrtoc32 again. */ ++ #if GNULIB_MBRTOC32_REGULAR ++ assert (mbsinit (&mbf->state)); ++ #else ++ if (mbsinit (&mbf->state)) ++ #endif ++ { ++ /* Before using mbrtoc32, we need at least one byte. */ ++ if (new_bufcount == 0) ++ { ++ int c = getc (mbf->fp); ++ if (c == EOF) ++ { ++ mbf->eof_seen = true; ++ goto eof; ++ } ++ mbf->buf[0] = (unsigned char) c; ++ new_bufcount++; ++ } ++ ++ /* Handle most ASCII characters quickly, without calling mbrtoc32(). */ ++ if (new_bufcount == 1 && is_basic (mbf->buf[0])) ++ { ++ /* These characters are part of the POSIX portable character set. ++ For most of them, namely those in the ISO C basic character set, ++ ISO C 99 guarantees that their wide character code is identical to ++ their char code. For the few other ones, this is the case as well, ++ in all locale encodings that are in use. The 32-bit wide character ++ code is the same as well. */ ++ mbc->wc = mbc->buf[0] = mbf->buf[0]; ++ mbc->wc_valid = true; ++ mbc->ptr = &mbc->buf[0]; ++ mbc->bytes = 1; ++ mbf->bufcount = 0; ++ return; ++ } ++ } ++ ++ /* Use mbrtoc32 on an increasing number of bytes. Read only as many bytes ++ from mbf->fp as needed. This is needed to give reasonable interactive ++ behaviour when mbf->fp is connected to an interactive tty. */ ++ for (;;) ++ { ++ /* Feed the bytes one by one into mbrtoc32. */ ++ bytes = mbrtoc32 (&mbc->wc, &mbf->buf[mbf->bufcount], new_bufcount - mbf->bufcount, &mbf->state); ++ ++ if (bytes == (size_t) -1) ++ { ++ /* An invalid multibyte sequence was encountered. */ ++ mbf->bufcount = new_bufcount; ++ /* Return a single byte. */ ++ bytes = 1; ++ mbc->wc_valid = false; ++ /* Allow the next invocation to continue from a sane state. */ ++ mbszero (&mbf->state); ++ break; ++ } ++ else if (bytes == (size_t) -2) ++ { ++ /* An incomplete multibyte character. */ ++ mbf->bufcount = new_bufcount; ++ if (mbf->bufcount == MBCHAR_BUF_SIZE) ++ { ++ /* An overlong incomplete multibyte sequence was encountered. */ ++ /* Return a single byte. */ ++ bytes = 1; ++ mbc->wc_valid = false; ++ break; ++ } ++ else ++ { ++ /* Read one more byte and retry mbrtoc32. */ ++ int c = getc (mbf->fp); ++ if (c == EOF) ++ { ++ /* An incomplete multibyte character at the end. */ ++ mbf->eof_seen = true; ++ bytes = new_bufcount; ++ mbc->wc_valid = false; ++ break; ++ } ++ mbf->buf[new_bufcount] = (unsigned char) c; ++ new_bufcount++; ++ } ++ } ++ else ++ { ++ #if !GNULIB_MBRTOC32_REGULAR ++ if (bytes == (size_t) -3) ++ { ++ /* The previous multibyte sequence produced an additional 32-bit ++ wide character. */ ++ mbf->bufcount = new_bufcount; ++ bytes = 0; ++ } ++ else ++ #endif ++ { ++ bytes = mbf->bufcount + bytes; ++ mbf->bufcount = new_bufcount; ++ if (bytes == 0) ++ { ++ /* A null 32-bit wide character was encountered. */ ++ bytes = 1; ++ assert (mbf->buf[0] == '\0'); ++ assert (mbc->wc == 0); ++ } ++ } ++ mbc->wc_valid = true; ++ break; ++ } ++ } ++ ++ /* Return the multibyte sequence mbf->buf[0..bytes-1]. */ ++ mbc->ptr = &mbc->buf[0]; ++ memcpy (&mbc->buf[0], &mbf->buf[0], bytes); ++ mbc->bytes = bytes; ++ ++ mbf->bufcount -= bytes; ++ if (mbf->bufcount > 0) ++ { ++ /* It's not worth calling memmove() for so few bytes. */ ++ unsigned int count = mbf->bufcount; ++ char *p = &mbf->buf[0]; ++ ++ do ++ { ++ *p = *(p + bytes); ++ p++; ++ } ++ while (--count > 0); ++ } ++ return; ++ ++eof: ++ /* An mbchar_t with bytes == 0 is used to indicate EOF. */ ++ mbc->ptr = NULL; ++ mbc->bytes = 0; ++ mbc->wc_valid = false; ++ return; ++} ++ ++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++; ++} ++ ++typedef struct mbfile_multi mb_file_t; ++ ++typedef mbchar_t mbf_char_t; ++ ++#define mbf_init(mbf, stream) \ ++ ((mbf).fp = (stream), \ ++ (mbf).eof_seen = false, \ ++ (mbf).pushback_count = 0, \ ++ mbszero (&(mbf).state), \ ++ (mbf).bufcount = 0) ++ ++#define mbf_getc(mbc, mbf) mbfile_multi_getc (&(mbc), &(mbf)) ++ ++#define mbf_ungetc(mbc, mbf) mbfile_multi_ungetc (&(mbc), &(mbf)) ++ ++#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 +new file mode 100644 +index 0000000..1d126e0 +--- /dev/null ++++ b/m4/mbfile.m4 +@@ -0,0 +1,16 @@ ++# mbfile.m4 ++# serial 7 ++dnl Copyright (C) 2005, 2008-2025 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. ++ ++AC_DEFUN([gl_MBFILE], ++[ ++ AC_REQUIRE([AC_TYPE_MBSTATE_T]) ++ : ++]) +diff --git a/src/cut.c b/src/cut.c +index f0effb9..36479d6 100644 +--- a/src/cut.c ++++ b/src/cut.c +@@ -27,6 +27,11 @@ + #include #include #include - -+/* Get mbstate_t, mbrtowc(), wcwidth(). */ ++ ++/* Get mbstate_t, mbrtowc(). */ +#if HAVE_WCHAR_H +# include +#endif -+ -+/* Get iswprint(), iswblank(), wcwidth(). */ -+#if HAVE_WCTYPE_H -+# include -+#endif -+ #include "system.h" - #include "die.h" - #include "error.h" - #include "fadvise.h" - #include "xdectoint.h" + + #include "assure.h" +@@ -35,6 +40,18 @@ + + #include "set-fields.h" +/* MB_LEN_MAX is incorrectly defined to be 1 in at least one GCC -+ installation; work around this configuration error. */ ++ installation; work around this configuration error. */ +#if !defined MB_LEN_MAX || MB_LEN_MAX < 2 +# undef MB_LEN_MAX +# define MB_LEN_MAX 16 @@ -89,870 +463,965 @@ index 8cd0d6b..d23edd5 100644 +# 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). */ -@@ -35,20 +57,41 @@ + #define PROGRAM_NAME "cut" - #define AUTHORS proper_name ("David MacKenzie") +@@ -51,6 +68,52 @@ + } \ + while (0) -+#define FATAL_ERROR(Message) \ -+ do \ -+ { \ -+ error (0, 0, (Message)); \ -+ usage (2); \ -+ } \ ++/* Refill the buffer BUF to get a multibyte character. */ ++#define REFILL_BUFFER(BUF, BUFPOS, BUFLEN, STREAM) \ ++ do \ ++ { \ ++ if (BUFLEN < MB_LEN_MAX && !feof (STREAM) && !ferror (STREAM)) \ ++ { \ ++ memmove (BUF, BUFPOS, BUFLEN); \ ++ BUFLEN += fread (BUF + BUFLEN, sizeof(char), BUFSIZ, STREAM); \ ++ BUFPOS = BUF; \ ++ } \ ++ } \ + while (0) + ++/* Get wide character on BUFPOS. BUFPOS is not included after that. ++ If byte sequence is not valid as a character, CONVFAIL is true. Otherwise false. */ ++#define GET_NEXT_WC_FROM_BUFFER(WC, BUFPOS, BUFLEN, MBLENGTH, STATE, CONVFAIL) \ ++ do \ ++ { \ ++ mbstate_t state_bak; \ ++ \ ++ if (BUFLEN < 1) \ ++ { \ ++ WC = WEOF; \ ++ break; \ ++ } \ ++ \ ++ /* Get a wide character. */ \ ++ CONVFAIL = false; \ ++ state_bak = STATE; \ ++ MBLENGTH = mbrtowc ((wchar_t *)&WC, BUFPOS, BUFLEN, &STATE); \ ++ \ ++ switch (MBLENGTH) \ ++ { \ ++ case (size_t)-1: \ ++ case (size_t)-2: \ ++ CONVFAIL = true; \ ++ STATE = state_bak; \ ++ /* Fall througn. */ \ ++ \ ++ case 0: \ ++ MBLENGTH = 1; \ ++ break; \ ++ } \ ++ } \ ++ while (0) ++ + + /* Pointer inside RP. When checking if a byte or field is selected + by a finite range, we check if it is between CURRENT_RP.LO +@@ -58,6 +121,9 @@ + CURRENT_RP.HI then we make CURRENT_RP to point to the next range pair. */ + static struct field_range_pair *current_rp; + ++/* Length of the delimiter given as argument to -d. */ ++size_t delimlen; ++ + /* This buffer is used to support the semantics of the -s option + (or lack of same) when the specified field list includes (does + not include) the first field. In both of those cases, the entire +@@ -70,6 +136,29 @@ static char *field_1_buffer; + /* The number of bytes allocated for FIELD_1_BUFFER. */ + static size_t field_1_bufsize; + +enum operating_mode -+{ -+ /* Fold texts by columns that are at the given positions. */ -+ column_mode, ++ { ++ undefined_mode, + -+ /* Fold texts by bytes that are at the given positions. */ -+ byte_mode, ++ /* Output bytes that are at the given positions. */ ++ byte_mode, + -+ /* Fold texts by characters that are at the given positions. */ -+ character_mode, -+}; ++ /* Output characters that are at the given positions. */ ++ character_mode, ++ ++ /* Output the given delimiter-separated fields. */ ++ field_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, when in byte mode, don't split multibyte characters. */ ++static int byte_mode_character_aware; ++ ++/* If nonzero, the function for single byte locale is work ++ if this program runs on multibyte locale. */ ++static int force_singlebyte_mode; ++ + /* If true, do not output lines containing no delimiter characters. + Otherwise, all such lines are printed. This option is valid only + with field mode. */ +@@ -81,10 +170,16 @@ static bool complement; --/* If nonzero, count bytes, not column positions. */ --static bool count_bytes; + /* The delimiter character for field mode. */ + static unsigned char delim; ++#if HAVE_WCHAR_H ++static wchar_t wcdelim; ++#endif + + /* The delimiter for each line/record. */ + static unsigned char line_delim = '\n'; + ++/* True if the --output-delimiter=STRING option was specified. */ ++static bool output_delimiter_specified; ++ + /* The length of output_delimiter_string. */ + static size_t output_delimiter_length; + +@@ -92,9 +187,6 @@ static size_t output_delimiter_length; + string consisting of the input delimiter. */ + static char *output_delimiter_string; + +-/* The output delimiter string contents, if the default. */ +-static char output_delimiter_default[1]; - - /* If nonzero, at least one of the files we read was standard input. */ + /* True if we have ever read 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, NULL, 'b'}, -+ {"characters", no_argument, NULL, 'c'}, - {"spaces", no_argument, NULL, 's'}, - {"width", required_argument, NULL, 'w'}, - {GETOPT_HELP_OPTION_DECL}, -@@ -76,6 +119,7 @@ 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\ +@@ -148,7 +240,7 @@ Print selected parts of lines from each FILE to standard output.\n\ + -f, --fields=LIST select only these fields; also print any line\n\ + that contains no delimiter character, unless\n\ + the -s option is specified\n\ +- -n (ignored)\n\ ++ -n with -b: don't split multibyte characters\n\ "), stdout); -@@ -93,7 +137,7 @@ 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') - { -@@ -116,30 +160,14 @@ 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 = NULL; - 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 == NULL) -- { -- error (0, errno, "%s", quotef (filename)); -- return false; -- } - - fadvise (istream, FADVISE_SEQUENTIAL); - -@@ -169,6 +197,15 @@ 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) + fputs (_("\ + --complement complement the set of selected bytes, characters\n\ +@@ -252,7 +344,7 @@ cut_bytes (FILE *stream) + next_item (&byte_idx); + if (print_kth (byte_idx)) + { +- if (output_delimiter_string != output_delimiter_default) ++ if (output_delimiter_specified) { -@@ -215,11 +252,221 @@ fold_file (char const *filename, size_t width) - line_out[offset_out++] = c; + if (print_delimiter && is_range_start_index (byte_idx)) + { +@@ -271,6 +363,82 @@ cut_bytes (FILE *stream) } + } -- saved_errno = errno; -+ *saved_errno = errno; - - if (offset_out) - fwrite (line_out, sizeof (char), (size_t) offset_out, stdout); - -+} -+ +#if HAVE_MBRTOWC ++/* This function is in use for the following case. ++ ++ 1. Read from the stream STREAM, printing to standard output any selected ++ characters. ++ ++ 2. Read from stream STREAM, printing to standard output any selected bytes, ++ without splitting multibyte characters. */ ++ +static void -+fold_multibyte_text (FILE *istream, size_t width, int *saved_errno) ++cut_characters_or_cut_bytes_no_split (FILE *stream) +{ ++ uintmax_t idx; /* number of bytes or characters in the line so far. */ + 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. */ ++ char *bufpos; /* Next read position of BUF. */ ++ size_t buflen; /* The length of the byte sequence in 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. */ ++ mbstate_t state; /* State of the stream. */ ++ bool convfail = false; /* true, when conversion failed. Otherwise false. */ ++ /* Whether to begin printing delimiters between ranges for the current line. ++ Set after we've begun printing data corresponding to the first range. */ ++ bool print_delimiter = false; + -+ 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; ++ idx = 0; ++ buflen = 0; ++ bufpos = buf; + memset (&state, '\0', sizeof(mbstate_t)); + -+ for (;; bufpos += mblength, buflen -= mblength) ++ current_rp = frp; ++ ++ while (1) + { -+ if (buflen < MB_LEN_MAX && !feof (istream) && !ferror (istream)) ++ REFILL_BUFFER (buf, bufpos, buflen, stream); ++ ++ GET_NEXT_WC_FROM_BUFFER (wc, bufpos, buflen, mblength, state, convfail); ++ (void) convfail; /* ignore unused */ ++ ++ if (wc == WEOF) + { -+ 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; ++ if (idx > 0) ++ putchar (line_delim); + break; + } -+ -+rescan: -+ if (operating_mode == byte_mode) /* byte mode */ -+ increment = mblength; -+ else if (operating_mode == character_mode) /* character mode */ -+ increment = 1; -+ else /* column mode */ ++ else if (wc == line_delim) + { -+ if (convfail) -+ increment = 1; -+ else ++ putchar (line_delim); ++ idx = 0; ++ print_delimiter = false; ++ current_rp = frp; ++ } ++ else ++ { ++ next_item (&idx); ++ if (print_kth (idx)) + { -+ switch (wc) ++ if (output_delimiter_specified) + { -+ case L'\n': -+ fwrite (line_out, sizeof(char), offset_out, stdout); -+ START_NEW_LINE; -+ continue; -+ -+ 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 (print_delimiter && is_range_start_index (idx)) ++ { ++ fwrite (output_delimiter_string, sizeof (char), ++ output_delimiter_length, stdout); ++ } ++ print_delimiter = true; + } ++ fwrite (bufpos, mblength, sizeof(char), stdout); + } + } + -+ 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; -+ } ++ buflen -= mblength; ++ bufpos += mblength; + } -+ -+ *saved_errno = errno; -+ -+ 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 1; -+ } -+ -+ /* Define how ISTREAM is being folded. */ + /* Read from stream STREAM, printing to standard output any selected fields. */ + + static void +@@ -433,11 +601,218 @@ cut_fields (FILE *stream) + } + } + +-/* Process file FILE to standard output, using CUT_STREAM. +#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ fold_multibyte_text (istream, width, &saved_errno); ++static void ++cut_fields_mb (FILE *stream) ++{ ++ int c; ++ uintmax_t field_idx; ++ int found_any_selected_field; ++ int buffer_first_field; ++ int empty_input; ++ char buf[MB_LEN_MAX + BUFSIZ]; /* For spooling a read byte sequence. */ ++ char *bufpos; /* Next read position of BUF. */ ++ size_t buflen; /* The length of the byte sequence in buf. */ ++ wint_t wc = 0; /* 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 of the stream. */ ++ bool convfail = false; /* true, when conversion failed. Otherwise false. */ ++ ++ current_rp = frp; ++ ++ found_any_selected_field = 0; ++ field_idx = 1; ++ bufpos = buf; ++ buflen = 0; ++ memset (&state, '\0', sizeof(mbstate_t)); ++ ++ c = getc (stream); ++ empty_input = (c == EOF); ++ if (c != EOF) ++ { ++ ungetc (c, stream); ++ wc = 0; ++ } ++ else ++ wc = WEOF; ++ ++ /* To support the semantics of the -s flag, we may have to buffer ++ all of the first field to determine whether it is `delimited.' ++ But that is unnecessary if all non-delimited lines must be printed ++ and the first field has been selected, or if non-delimited lines ++ must be suppressed and the first field has *not* been selected. ++ That is because a non-delimited line has exactly one field. */ ++ buffer_first_field = (suppress_non_delimited ^ !print_kth (1)); ++ ++ while (1) ++ { ++ if (field_idx == 1 && buffer_first_field) ++ { ++ int len = 0; ++ ++ while (1) ++ { ++ REFILL_BUFFER (buf, bufpos, buflen, stream); ++ ++ GET_NEXT_WC_FROM_BUFFER ++ (wc, bufpos, buflen, mblength, state, convfail); ++ ++ if (wc == WEOF) ++ break; ++ ++ field_1_buffer = xrealloc (field_1_buffer, len + mblength); ++ memcpy (field_1_buffer + len, bufpos, mblength); ++ len += mblength; ++ buflen -= mblength; ++ bufpos += mblength; ++ ++ if (!convfail && (wc == line_delim || wc == wcdelim)) ++ break; ++ } ++ ++ if (len <= 0 && wc == WEOF) ++ break; ++ ++ /* If the first field extends to the end of line (it is not ++ delimited) and we are printing all non-delimited lines, ++ print this one. */ ++ if (convfail || (!convfail && wc != wcdelim)) ++ { ++ if (suppress_non_delimited) ++ { ++ /* Empty. */ ++ } ++ else ++ { ++ fwrite (field_1_buffer, sizeof (char), len, stdout); ++ /* Make sure the output line is newline terminated. */ ++ if (convfail || (!convfail && wc != line_delim)) ++ putchar (line_delim); ++ } ++ continue; ++ } ++ ++ if (print_kth (1)) ++ { ++ /* Print the field, but not the trailing delimiter. */ ++ fwrite (field_1_buffer, sizeof (char), len - 1, stdout); ++ found_any_selected_field = 1; ++ } ++ next_item (&field_idx); ++ } ++ ++ if (wc != WEOF) ++ { ++ if (print_kth (field_idx)) ++ { ++ if (found_any_selected_field) ++ { ++ fwrite (output_delimiter_string, sizeof (char), ++ output_delimiter_length, stdout); ++ } ++ found_any_selected_field = 1; ++ } ++ ++ while (1) ++ { ++ REFILL_BUFFER (buf, bufpos, buflen, stream); ++ ++ GET_NEXT_WC_FROM_BUFFER ++ (wc, bufpos, buflen, mblength, state, convfail); ++ ++ if (wc == WEOF) ++ break; ++ else if (!convfail && (wc == wcdelim || wc == line_delim)) ++ { ++ buflen -= mblength; ++ bufpos += mblength; ++ break; ++ } ++ ++ if (print_kth (field_idx)) ++ fwrite (bufpos, mblength, sizeof(char), stdout); ++ ++ buflen -= mblength; ++ bufpos += mblength; ++ } ++ } ++ ++ if ((!convfail || wc == line_delim) && buflen < 1) ++ wc = WEOF; ++ ++ if (!convfail && wc == wcdelim) ++ next_item (&field_idx); ++ else if (wc == WEOF || (!convfail && wc == line_delim)) ++ { ++ if (found_any_selected_field ++ || (!empty_input && !(suppress_non_delimited && field_idx == 1))) ++ putchar (line_delim); ++ if (wc == WEOF) ++ break; ++ field_idx = 1; ++ current_rp = frp; ++ found_any_selected_field = 0; ++ } ++ } ++} ++#endif ++ ++static void ++cut_stream (FILE *stream) ++{ ++#if HAVE_MBRTOWC ++ if (MB_CUR_MAX > 1 && !force_singlebyte_mode) ++ { ++ switch (operating_mode) ++ { ++ case byte_mode: ++ if (byte_mode_character_aware) ++ cut_characters_or_cut_bytes_no_split (stream); ++ else ++ cut_bytes (stream); ++ break; ++ ++ case character_mode: ++ cut_characters_or_cut_bytes_no_split (stream); ++ break; ++ ++ case field_mode: ++ if (delimlen == 1) ++ { ++ /* Check if we have utf8 multibyte locale, so we can use this ++ optimization because of uniqueness of characters, which is ++ not true for e.g. SJIS */ ++ char * loc = setlocale(LC_CTYPE, NULL); ++ if (loc && (strstr (loc, "UTF-8") || strstr (loc, "utf-8") || ++ strstr (loc, "UTF8") || strstr (loc, "utf8"))) ++ { ++ cut_fields (stream); ++ break; ++ } ++ } ++ cut_fields_mb (stream); ++ break; ++ ++ default: ++ abort (); ++ } ++ } + else +#endif -+ fold_text (istream, width, &saved_errno); ++ { ++ if (operating_mode == field_mode) ++ cut_fields (stream); ++ else ++ cut_bytes (stream); ++ } ++} + - if (ferror (istream)) - { - error (0, saved_errno, "%s", quotef (filename)); -@@ -252,7 +499,8 @@ main (int argc, char **argv) ++/* Process file FILE to standard output. + Return true if successful. */ + + static bool +-cut_file (char const *file, void (*cut_stream) (FILE *)) ++cut_file (char const *file) + { + FILE *stream; + +@@ -482,8 +857,8 @@ main (int argc, char **argv) + int optc; + bool ok; + bool delim_specified = false; +- bool byte_mode = false; +- char *spec_list_string = nullptr; ++ char *spec_list_string IF_LINT ( = nullptr); ++ char mbdelim[MB_LEN_MAX + 1]; + + initialize_main (&argc, &argv); + set_program_name (argv[0]); +@@ -493,6 +868,8 @@ 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; ++ operating_mode = undefined_mode; ++ + /* By default, all non-delimited lines are printed. */ + suppress_non_delimited = false; - while ((optc = getopt_long (argc, argv, shortopts, longopts, NULL)) != -1) - { -@@ -261,7 +509,15 @@ main (int argc, char **argv) +@@ -505,35 +882,77 @@ 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")); + case 'b': +- case 'c': + /* Build the byte list. */ +- byte_mode = true; +- FALLTHROUGH; ++ if (operating_mode != undefined_mode) ++ FATAL_ERROR (_("only one type of list may be specified")); + operating_mode = byte_mode; ++ spec_list_string = optarg; + break; + + case 'c': -+ if (operating_mode != column_mode) -+ FATAL_ERROR (_("only one way of folding may be specified")); ++ /* Build the character list. */ ++ if (operating_mode != undefined_mode) ++ FATAL_ERROR (_("only one type of list may be specified")); + operating_mode = character_mode; ++ spec_list_string = optarg; ++ break; ++ + case 'f': + /* Build the field list. */ +- if (spec_list_string) +- FATAL_ERROR (_("only one list may be specified")); ++ if (operating_mode != undefined_mode) ++ FATAL_ERROR (_("only one type of list may be specified")); ++ operating_mode = field_mode; + spec_list_string = optarg; break; - case 's': /* Break at word boundaries. */ -diff --git a/src/join.c b/src/join.c -index 98b461c..9990f38 100644 ---- a/src/join.c -+++ b/src/join.c -@@ -22,19 +22,33 @@ - #include - #include - -+/* Get mbstate_t, mbrtowc(), mbrtowc(), wcwidth(). */ -+#if HAVE_WCHAR_H -+# include + case 'd': + /* New delimiter. */ + /* Interpret -d '' to mean 'use the NUL byte as the delimiter.' */ +- if (optarg[0] != '\0' && optarg[1] != '\0') +- FATAL_ERROR (_("the delimiter must be a single character")); +- delim = optarg[0]; +- delim_specified = true; ++ { ++#if HAVE_MBRTOWC ++ if(MB_CUR_MAX > 1) ++ { ++ mbstate_t state; ++ ++ memset (&state, '\0', sizeof(mbstate_t)); ++ delimlen = mbrtowc (&wcdelim, optarg, strnlen(optarg, MB_LEN_MAX), &state); ++ ++ if (delimlen == (size_t)-1 || delimlen == (size_t)-2) ++ ++force_singlebyte_mode; ++ else ++ { ++ delimlen = (delimlen < 1) ? 1 : delimlen; ++ if (wcdelim != L'\0' && *(optarg + delimlen) != '\0') ++ FATAL_ERROR (_("the delimiter must be a single character")); ++ memcpy (mbdelim, optarg, delimlen); ++ mbdelim[delimlen] = '\0'; ++ if (delimlen == 1) ++ delim = *optarg; ++ } ++ } ++ ++ if (MB_CUR_MAX <= 1 || force_singlebyte_mode) +#endif -+ -+/* Get iswblank(), towupper. */ -+#if HAVE_WCTYPE_H -+# include -+#endif -+ - #include "system.h" - #include "die.h" - #include "error.h" - #include "fadvise.h" - #include "hard-locale.h" - #include "linebuffer.h" --#include "memcasecmp.h" - #include "quote.h" - #include "stdio--.h" - #include "xmemcoll.h" - #include "xstrtol.h" - #include "argmatch.h" ++ { ++ if (optarg[0] != '\0' && optarg[1] != '\0') ++ FATAL_ERROR (_("the delimiter must be a single character")); ++ delim = (unsigned char) optarg[0]; ++ } ++ delim_specified = true; ++ } + break; -+/* 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 -+ - /* The official name of this program (e.g., no 'g' prefix). */ - #define PROGRAM_NAME "join" + case OUTPUT_DELIMITER_OPTION: ++ output_delimiter_specified = true; + /* Interpret --output-delimiter='' to mean + 'use the NUL byte as the delimiter.' */ + output_delimiter_length = (optarg[0] == '\0' + ? 1 : strlen (optarg)); +- output_delimiter_string = optarg; ++ output_delimiter_string = xstrdup (optarg); + break; -@@ -136,10 +150,12 @@ static struct outlist outlist_head; - /* Last element in 'outlist', where a new element can be added. */ - static struct outlist *outlist_end = &outlist_head; + case 'n': ++ byte_mode_character_aware = 1; + break; --/* Tab character separating fields. If negative, fields are separated -- by any nonempty string of blanks, otherwise by exactly one -- tab character whose value (when cast to unsigned char) equals TAB. */ --static int tab = -1; -+/* Tab character separating fields. If NULL, fields are separated -+ by any nonempty string of blanks. */ -+static char *tab = NULL; -+ -+/* The number of bytes used for tab. */ -+static size_t tablen = 0; - - /* If nonzero, check that the input is correctly ordered. */ - static enum -@@ -276,13 +292,14 @@ xfields (struct line *line) - if (ptr == lim) - return; - -- if (0 <= tab && tab != '\n') -+ if (tab != NULL) - { -+ unsigned char t = tab[0]; - char *sep; -- for (; (sep = memchr (ptr, tab, lim - ptr)) != NULL; ptr = sep + 1) -+ for (; (sep = memchr (ptr, t, lim - ptr)) != NULL; ptr = sep + 1) - extract_field (line, ptr, sep - ptr); + case 's': +@@ -555,40 +974,57 @@ main (int argc, char **argv) + } } -- else if (tab < 0) -+ else + +- if (!spec_list_string) ++ if (operating_mode == undefined_mode) + FATAL_ERROR (_("you must specify a list of bytes, characters, or fields")); + +- if (byte_mode) +- { +- if (delim_specified) +- FATAL_ERROR (_("an input delimiter may be specified only\ ++ if (delim_specified && operating_mode != field_mode) ++ FATAL_ERROR (_("an input delimiter may be specified only\ + when operating on fields")); + +- if (suppress_non_delimited) +- FATAL_ERROR (_("suppressing non-delimited lines makes sense\n\ ++ if (suppress_non_delimited && operating_mode != field_mode) ++ FATAL_ERROR (_("suppressing non-delimited lines makes sense\n\ + \tonly when operating on fields")); +- } + + set_fields (spec_list_string, +- ((byte_mode ? SETFLD_ERRMSG_USE_POS : 0) +- | (complement ? SETFLD_COMPLEMENT : 0))); ++ ( (operating_mode == field_mode) ? 0 : SETFLD_ERRMSG_USE_POS) ++ | (complement ? SETFLD_COMPLEMENT : 0) ); + + if (!delim_specified) +- delim = '\t'; ++ { ++ delim = '\t'; ++#ifdef HAVE_MBRTOWC ++ wcdelim = L'\t'; ++ mbdelim[0] = '\t'; ++ mbdelim[1] = '\0'; ++ delimlen = 1; ++#endif ++ } + + if (output_delimiter_string == nullptr) { - /* Skip leading blanks before the first field. */ - while (field_sep (*ptr)) -@@ -306,6 +323,147 @@ xfields (struct line *line) - extract_field (line, ptr, lim - ptr); +- output_delimiter_default[0] = delim; +- output_delimiter_string = output_delimiter_default; +- output_delimiter_length = 1; ++#ifdef HAVE_MBRTOWC ++ if (MB_CUR_MAX > 1 && !force_singlebyte_mode) ++ { ++ output_delimiter_string = xstrdup(mbdelim); ++ output_delimiter_length = delimlen; ++ } ++ ++ if (MB_CUR_MAX <= 1 || force_singlebyte_mode) ++#endif ++ { ++ static char dummy[2]; ++ dummy[0] = delim; ++ dummy[1] = '\0'; ++ output_delimiter_string = dummy; ++ output_delimiter_length = 1; ++ } + } + +- void (*cut_stream) (FILE *) = byte_mode ? cut_bytes : cut_fields; + if (optind == argc) +- ok = cut_file ("-", cut_stream); ++ ok = cut_file ("-"); + else + for (ok = true; optind < argc; optind++) +- ok &= cut_file (argv[optind], cut_stream); ++ ok &= cut_file (argv[optind]); + + + if (have_read_stdin && fclose (stdin) == EOF) +diff --git a/src/expand-common.c b/src/expand-common.c +index 14dd804..0d8eaaa 100644 +--- a/src/expand-common.c ++++ b/src/expand-common.c +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + #include "system.h" + #include "c-ctype.h" + #include "fadvise.h" +@@ -132,6 +133,119 @@ set_increment_size (colno tabval) + return ok; } -+#if HAVE_MBRTOWC -+static void -+xfields_multibyte (struct line *line) ++extern int ++set_utf_locale (void) +{ -+ char *ptr = line->buf.buffer; -+ char const *lim = ptr + line->buf.length - 1; -+ wchar_t wc = 0; -+ size_t mblength = 1; -+ mbstate_t state, state_bak; ++ /*try using some predefined locale */ ++ const char* predef_locales[] = {"C.UTF8","en_US.UTF8","en_GB.UTF8"}; + -+ memset (&state, 0, sizeof (mbstate_t)); -+ -+ if (ptr >= lim) -+ return; -+ -+ if (tab != NULL) -+ { -+ char *sep = ptr; -+ for (; ptr < lim; ptr = sep + mblength) -+ { -+ sep = ptr; -+ while (sep < lim) -+ { -+ state_bak = state; -+ mblength = mbrtowc (&wc, sep, lim - sep + 1, &state); -+ -+ if (mblength == (size_t)-1 || mblength == (size_t)-2) -+ { -+ mblength = 1; -+ state = state_bak; -+ } -+ mblength = (mblength < 1) ? 1 : mblength; -+ -+ if (mblength == tablen && !memcmp (sep, tab, mblength)) -+ break; -+ else -+ { -+ sep += mblength; -+ continue; -+ } -+ } -+ -+ if (sep >= lim) -+ break; -+ -+ extract_field (line, ptr, sep - ptr); -+ } -+ } -+ else -+ { -+ /* Skip leading blanks before the first field. */ -+ while(ptr < lim) -+ { -+ state_bak = state; -+ mblength = mbrtowc (&wc, ptr, lim - ptr + 1, &state); -+ -+ if (mblength == (size_t)-1 || mblength == (size_t)-2) ++ const int predef_locales_count=3; ++ for (int i=0;i= lim) -+ return; -+ -+ state_bak = state; -+ mblength = mbrtowc (&wc, sep, lim - sep + 1, &state); -+ if (mblength == (size_t)-1 || mblength == (size_t)-2) -+ { -+ mblength = 1; -+ state = state_bak; -+ break; -+ } -+ mblength = (mblength < 1) ? 1 : mblength; -+ -+ ptr = sep + mblength; -+ while (ptr < lim) -+ { -+ state_bak = state; -+ mblength = mbrtowc (&wc, ptr, lim - ptr + 1, &state); -+ if (mblength == (size_t)-1 || mblength == (size_t)-2) -+ { -+ mblength = 1; -+ state = state_bak; -+ break; -+ } -+ mblength = (mblength < 1) ? 1 : mblength; -+ -+ if (!iswblank (wc) && wc != '\n') -+ break; -+ -+ ptr += mblength; -+ } -+ } -+ while (ptr < lim); -+ } -+ -+ extract_field (line, ptr, lim - ptr); ++ else if (i==predef_locales_count-1) ++ { ++ return 1; ++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale")); ++ } ++ } ++ return 0; +} -+#endif + - static void - freeline (struct line *line) - { -@@ -327,56 +485,133 @@ keycmp (struct line const *line1, struct line const *line2, - size_t jf_1, size_t jf_2) - { - /* Start of field to compare in each file. */ -- char *beg1; -- char *beg2; -- -- size_t len1; -- size_t len2; /* Length of fields to compare. */ -+ char *beg[2]; -+ char *copy[2]; -+ size_t len[2]; /* Length of fields to compare. */ - int diff; -+ int i, j; -+ int mallocd = 0; - - if (jf_1 < line1->nfields) - { -- beg1 = line1->fields[jf_1].beg; -- len1 = line1->fields[jf_1].len; -+ beg[0] = line1->fields[jf_1].beg; -+ len[0] = line1->fields[jf_1].len; - } - else - { -- beg1 = NULL; -- len1 = 0; -+ beg[0] = NULL; -+ len[0] = 0; - } - - if (jf_2 < line2->nfields) - { -- beg2 = line2->fields[jf_2].beg; -- len2 = line2->fields[jf_2].len; -+ beg[1] = line2->fields[jf_2].beg; -+ len[1] = line2->fields[jf_2].len; - } - else - { -- beg2 = NULL; -- len2 = 0; -+ beg[1] = NULL; -+ len[1] = 0; - } - -- if (len1 == 0) -- return len2 == 0 ? 0 : -1; -- if (len2 == 0) -+ if (len[0] == 0) -+ return len[1] == 0 ? 0 : -1; -+ if (len[1] == 0) - return 1; - - if (ignore_case) - { -- /* FIXME: ignore_case does not work with NLS (in particular, -- with multibyte chars). */ -- diff = memcasecmp (beg1, beg2, MIN (len1, len2)); -+#ifdef HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ { -+ size_t mblength; -+ wchar_t wc, uwc; -+ mbstate_t state, state_bak; ++extern bool ++check_utf_locale(void) ++{ ++ char* locale = setlocale (LC_CTYPE , NULL); ++ if (locale == NULL) ++ { ++ return false; ++ } ++ else if (strcasestr(locale, "utf8") == NULL && strcasestr(locale, "utf-8") == NULL) ++ { ++ return false; ++ } ++ return true; ++} + -+ memset (&state, '\0', sizeof (mbstate_t)); -+ -+ for (i = 0; i < 2; i++) -+ { -+ mallocd = 1; -+ copy[i] = xmalloc (len[i] + 1); -+ memset (copy[i], '\0',len[i] + 1); -+ -+ for (j = 0; j < MIN (len[0], len[1]);) -+ { -+ state_bak = state; -+ mblength = mbrtowc (&wc, beg[i] + j, len[i] - j, &state); -+ -+ switch (mblength) -+ { -+ case (size_t) -1: -+ case (size_t) -2: -+ state = state_bak; -+ /* Fall through */ -+ case 0: -+ mblength = 1; -+ break; -+ -+ default: -+ uwc = towupper (wc); -+ -+ if (uwc != wc) -+ { -+ mbstate_t state_wc; -+ size_t mblen; -+ -+ memset (&state_wc, '\0', sizeof (mbstate_t)); -+ mblen = wcrtomb (copy[i] + j, uwc, &state_wc); -+ assert (mblen != (size_t)-1); -+ } -+ else -+ memcpy (copy[i] + j, beg[i] + j, mblength); -+ } -+ j += mblength; -+ } -+ copy[i][j] = '\0'; -+ } -+ } -+ else -+#endif -+ { -+ for (i = 0; i < 2; i++) -+ { -+ mallocd = 1; -+ copy[i] = xmalloc (len[i] + 1); -+ -+ for (j = 0; j < MIN (len[0], len[1]); j++) -+ copy[i][j] = toupper (beg[i][j]); -+ -+ copy[i][j] = '\0'; -+ } -+ } - } - else - { -- if (hard_LC_COLLATE) -- return xmemcoll (beg1, len1, beg2, len2); -- diff = memcmp (beg1, beg2, MIN (len1, len2)); -+ copy[0] = beg[0]; -+ copy[1] = beg[1]; - } - -+ if (hard_LC_COLLATE) -+ { -+ diff = xmemcoll ((char *) copy[0], len[0], (char *) copy[1], len[1]); -+ -+ if (mallocd) -+ for (i = 0; i < 2; i++) -+ free (copy[i]); -+ -+ return diff; -+ } -+ diff = memcmp (copy[0], copy[1], MIN (len[0], len[1])); -+ -+ if (mallocd) -+ for (i = 0; i < 2; i++) -+ free (copy[i]); ++extern bool ++check_bom(FILE* fp, mb_file_t *mbf) ++{ ++ int c; + + - if (diff) - return diff; -- return len1 < len2 ? -1 : len1 != len2; -+ return len[0] - len[1]; - } - - /* Check that successive input lines PREV and CURRENT from input file -@@ -468,6 +703,11 @@ get_line (FILE *fp, struct line **linep, int which) - } - ++line_no[which - 1]; - -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ xfields_multibyte (line); ++ c=fgetc(fp); ++ ++ /*test BOM header of the first file */ ++ mbf->bufcount=0; ++ if (c == 0xEF) ++ { ++ c=fgetc(fp); ++ } + else -+#endif - xfields (line); - - if (prevline[which - 1]) -@@ -567,21 +807,28 @@ prfield (size_t n, struct line const *line) - - /* Output all the fields in line, other than the join field. */ - -+#define PUT_TAB_CHAR \ -+ do \ -+ { \ -+ (tab != NULL) ? \ -+ fwrite(tab, sizeof(char), tablen, stdout) : putchar (' '); \ -+ } \ -+ while (0) ++ { ++ if (c != EOF) ++ { ++ ungetc(c,fp); ++ } ++ return false; ++ } + - static void - prfields (struct line const *line, size_t join_field, size_t autocount) ++ if (c == 0xBB) ++ { ++ c=fgetc(fp); ++ } ++ else ++ { ++ if ( c!= EOF ) ++ { ++ mbf->buf[0]=(unsigned char) 0xEF; ++ mbf->bufcount=1; ++ ungetc(c,fp); ++ return false; ++ } ++ else ++ { ++ ungetc(0xEF,fp); ++ return false; ++ } ++ } ++ if (c == 0xBF) ++ { ++ mbf->bufcount=0; ++ return true; ++ } ++ else ++ { ++ if (c != EOF) ++ { ++ mbf->buf[0]=(unsigned char) 0xEF; ++ mbf->buf[1]=(unsigned char) 0xBB; ++ mbf->bufcount=2; ++ ungetc(c,fp); ++ return false; ++ } ++ else ++ { ++ mbf->buf[0]=(unsigned char) 0xEF; ++ mbf->bufcount=1; ++ ungetc(0xBB,fp); ++ return false; ++ } ++ } ++ return false; ++} ++ ++extern void ++print_bom(void) ++{ ++ putc (0xEF, stdout); ++ putc (0xBB, stdout); ++ putc (0xBF, stdout); ++} ++ + /* Add the comma or blank separated list of tab stops STOPS + to the list of tab stops. */ + extern void +diff --git a/src/expand-common.h b/src/expand-common.h +index 46ef4e3..e19469b 100644 +--- a/src/expand-common.h ++++ b/src/expand-common.h +@@ -29,6 +29,18 @@ extern idx_t max_column_width; + /* The desired exit status. */ + extern int exit_status; + ++extern int ++set_utf_locale (void); ++ ++extern bool ++check_utf_locale(void); ++ ++extern bool ++check_bom(FILE* fp, mb_file_t *mbf); ++ ++extern void ++print_bom(void); ++ + /* Add tab stop TABVAL to the end of 'tab_list'. */ + extern void + add_tab_stop (colno tabval); +diff --git a/src/expand.c b/src/expand.c +index 5ec7ce9..65ac315 100644 +--- a/src/expand.c ++++ b/src/expand.c +@@ -38,6 +38,9 @@ + #include + #include + #include ++ ++#include ++ + #include "system.h" + #include "expand-common.h" + +@@ -96,19 +99,41 @@ expand (void) { - size_t i; - size_t nfields = autoformat ? autocount : line->nfields; -- char output_separator = tab < 0 ? ' ' : tab; + /* Input stream. */ + FILE *fp = next_file (nullptr); ++ mb_file_t mbf; ++ mbf_char_t c; ++ /* True if the starting locale is utf8. */ ++ bool using_utf_locale; ++ ++ /* True if the first file contains BOM header. */ ++ bool found_bom; ++ using_utf_locale=check_utf_locale(); - for (i = 0; i < join_field && i < nfields; ++i) + if (!fp) + return; ++ mbf_init (mbf, fp); ++ found_bom=check_bom(fp,&mbf); + +- while (true) ++ if (using_utf_locale == false && found_bom == true) ++ { ++ /*try using some predefined locale */ ++ ++ if (set_utf_locale () != 0) { -- putchar (output_separator); -+ PUT_TAB_CHAR; - prfield (i, line); - } - for (i = join_field + 1; i < nfields; ++i) - { -- putchar (output_separator); -+ PUT_TAB_CHAR; - prfield (i, line); - } - } -@@ -592,7 +839,6 @@ static void - prjoin (struct line const *line1, struct line const *line2) - { - const struct outlist *outlist; -- char output_separator = tab < 0 ? ' ' : tab; - size_t field; - struct line const *line; +- /* Input character, or EOF. */ +- int c; ++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale")); ++ } ++ } ++ ++ ++ if (found_bom == true) ++ { ++ print_bom(); ++ } -@@ -626,7 +872,7 @@ prjoin (struct line const *line1, struct line const *line2) - o = o->next; - if (o == NULL) - break; -- putchar (output_separator); -+ PUT_TAB_CHAR; - } - putchar (eolchar); - } -@@ -1104,20 +1350,43 @@ main (int argc, char **argv) ++ while (true) ++ { + /* If true, perform translations. */ + bool convert = true; - case 't': - { -- unsigned char newtab = optarg[0]; -+ char *newtab = NULL; -+ size_t newtablen; -+ newtab = xstrdup (optarg); -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) +- + /* The following variables have valid values only when CONVERT + is true: */ + +@@ -118,17 +143,48 @@ expand (void) + /* Index in TAB_LIST of next tab stop to examine. */ + idx_t tab_index = 0; + +- + /* Convert a line of text. */ + + do + { +- while ((c = getc (fp)) < 0 && (fp = next_file (fp))) +- continue; ++ while (true) { ++ mbf_getc (c, mbf); ++ if ((mb_iseof (c)) && (fp = next_file (fp))) + { -+ mbstate_t state; -+ -+ memset (&state, 0, sizeof (mbstate_t)); -+ newtablen = mbrtowc (NULL, newtab, -+ strnlen (newtab, MB_LEN_MAX), -+ &state); -+ if (newtablen == (size_t) 0 -+ || newtablen == (size_t) -1 -+ || newtablen == (size_t) -2) -+ newtablen = 1; ++ mbf_init (mbf, fp); ++ if (fp!=NULL) ++ { ++ if (check_bom(fp,&mbf)==true) ++ { ++ /*Not the first file - check BOM header*/ ++ if (using_utf_locale==false && found_bom==false) ++ { ++ /*BOM header in subsequent file but not in the first one. */ ++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); ++ } ++ } ++ else ++ { ++ if(using_utf_locale==false && found_bom==true) ++ { ++ /*First file conatined BOM header - locale was switched to UTF ++ *all subsequent files should contain BOM. */ ++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); ++ } ++ } ++ } ++ continue; + } + else -+#endif -+ newtablen = 1; - if (! newtab) -- newtab = '\n'; /* '' => process the whole line. */ -+ newtab = (char*)"\n"; /* '' => process the whole line. */ - else if (optarg[1]) - { -- if (STREQ (optarg, "\\0")) -- newtab = '\0'; -- else -- die (EXIT_FAILURE, 0, _("multi-character tab %s"), -- quote (optarg)); -+ if (newtablen == 1 && newtab[1]) -+ { -+ if (STREQ (newtab, "\\0")) -+ newtab[0] = '\0'; -+ } -+ } -+ if (tab != NULL && strcmp (tab, newtab)) + { -+ free (newtab); -+ die (EXIT_FAILURE, 0, _("incompatible tabs")); - } -- if (0 <= tab && tab != newtab) -- die (EXIT_FAILURE, 0, _("incompatible tabs")); - tab = newtab; -+ tablen = newtablen; - } - break; ++ break; ++ } ++ } ++ + if (convert) + { +- if (c == '\t') ++ if (mb_iseq (c, '\t')) + { + /* Column the next input tab stop is on. */ + bool last_tab; +@@ -139,31 +195,33 @@ expand (void) + if (putchar (' ') < 0) + write_error (); + +- c = ' '; ++ mb_setascii (&c, ' '); + } +- else if (c == '\b') ++ else if (mb_iseq (c, '\b')) + { + /* Go back one column, and force recalculation of the + next tab stop. */ + column -= !!column; + tab_index -= !!tab_index; + } +- else ++ /* 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))) + error (EXIT_FAILURE, 0, _("input line is too long")); + } + +- convert &= convert_entire_line || !! isblank (c); ++ convert &= convert_entire_line || !! mb_isblank (c); + } + +- if (c < 0) ++ if (mb_iseof (c)) + return; + +- if (putchar (c) < 0) ++ mb_putc (c, stdout); ++ if (ferror (stdout)) + write_error (); + } +- while (c != '\n'); ++ while (!mb_iseq (c, '\n')); + } + } + +diff --git a/src/local.mk b/src/local.mk +index a8ad6b4..b0e61ec 100644 +--- a/src/local.mk ++++ b/src/local.mk +@@ -490,8 +490,8 @@ src_base32_CPPFLAGS = -DBASE_TYPE=32 $(AM_CPPFLAGS) + src_basenc_SOURCES = src/basenc.c + src_basenc_CPPFLAGS = -DBASE_TYPE=42 $(AM_CPPFLAGS) + +-src_expand_SOURCES = src/expand.c src/expand-common.c +-src_unexpand_SOURCES = src/unexpand.c src/expand-common.c ++src_expand_SOURCES = src/expand.c src/expand-common.c lib/mbfile.c lib/mbchar.c ++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 diff --git a/src/pr.c b/src/pr.c -index 26f221f..633f50e 100644 +index 10b8c52..079c86c 100644 --- a/src/pr.c +++ b/src/pr.c -@@ -311,6 +311,24 @@ - +@@ -312,6 +312,24 @@ + #include #include #include + @@ -974,10 +1443,10 @@ index 26f221f..633f50e 100644 +#endif + #include "system.h" - #include "die.h" - #include "error.h" -@@ -324,6 +342,18 @@ - #include "xstrtol.h" + #include "c-ctype.h" + #include "fadvise.h" +@@ -325,6 +343,18 @@ + #include "xstrtol-error.h" #include "xdectoint.h" +/* Some systems, like BeOS, have multibyte encodings but lack mbstate_t. */ @@ -995,7 +1464,7 @@ index 26f221f..633f50e 100644 /* The official name of this program (e.g., no 'g' prefix). */ #define PROGRAM_NAME "pr" -@@ -416,7 +446,20 @@ struct COLUMN +@@ -417,7 +447,20 @@ struct COLUMN typedef struct COLUMN COLUMN; @@ -1017,9 +1486,9 @@ index 26f221f..633f50e 100644 static bool read_line (COLUMN *p); static bool print_page (void); static bool print_stored (COLUMN *p); -@@ -428,6 +471,7 @@ static void add_line_number (COLUMN *p); - static void getoptnum (const char *n_str, int min, int *num, - const char *errfmt); +@@ -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); static void getoptarg (char *arg, char switch_char, char *character, + int *character_length, int *character_width, int *number); @@ -1032,7 +1501,7 @@ index 26f221f..633f50e 100644 -static void print_char (char c); static void cleanup (void); static void print_sep_string (void); - static void separator_string (const char *optarg_S); + static void separator_string (char const *optarg_S); @@ -453,7 +496,7 @@ static COLUMN *column_vector; we store the leftmost columns contiguously in buff. To print a line from buff, get the index of the first character @@ -1086,7 +1555,7 @@ index 26f221f..633f50e 100644 static char *column_separator = (char *) " "; static char *line_separator = (char *) "\t"; -@@ -851,6 +904,13 @@ separator_string (const char *optarg_S) +@@ -852,6 +905,13 @@ separator_string (char const *optarg_S) integer_overflow (); col_sep_length = len; col_sep_string = optarg_S; @@ -1100,7 +1569,7 @@ index 26f221f..633f50e 100644 } int -@@ -875,6 +935,21 @@ main (int argc, char **argv) +@@ -876,6 +936,21 @@ main (int argc, char **argv) atexit (close_stdout); @@ -1122,7 +1591,7 @@ index 26f221f..633f50e 100644 n_files = 0; file_names = (argc > 1 ? xnmalloc (argc - 1, sizeof (char *)) -@@ -951,8 +1026,12 @@ main (int argc, char **argv) +@@ -952,8 +1027,12 @@ main (int argc, char **argv) break; case 'e': if (optarg) @@ -1137,7 +1606,7 @@ index 26f221f..633f50e 100644 /* Could check tab width > 0. */ untabify_input = true; break; -@@ -965,8 +1044,12 @@ main (int argc, char **argv) +@@ -966,8 +1045,12 @@ main (int argc, char **argv) break; case 'i': if (optarg) @@ -1152,7 +1621,7 @@ index 26f221f..633f50e 100644 /* Could check tab width > 0. */ tabify_output = true; break; -@@ -984,8 +1067,8 @@ main (int argc, char **argv) +@@ -986,8 +1069,8 @@ main (int argc, char **argv) case 'n': numbered_lines = true; if (optarg) @@ -1163,7 +1632,7 @@ index 26f221f..633f50e 100644 break; case 'N': skip_count = false; -@@ -1010,6 +1093,7 @@ main (int argc, char **argv) +@@ -1013,6 +1096,7 @@ main (int argc, char **argv) /* Reset an additional input of -s, -S dominates -s */ col_sep_string = ""; col_sep_length = 0; @@ -1171,7 +1640,7 @@ index 26f221f..633f50e 100644 use_col_separator = true; if (optarg) separator_string (optarg); -@@ -1166,10 +1250,45 @@ getoptnum (const char *n_str, int min, int *num, const char *err) +@@ -1168,7 +1252,8 @@ getoptnum (char const *n_str, int min, char const *err) a number. */ static void @@ -1179,7 +1648,12 @@ index 26f221f..633f50e 100644 +getoptarg (char *arg, char switch_char, char *character, int *character_length, + int *character_width, int *number) { - if (!ISDIGIT (*arg)) + if (!*arg) + { +@@ -1177,7 +1262,41 @@ getoptarg (char *arg, char switch_char, char *character, int *number) + } + + if (!c_isdigit (*arg)) - *character = *arg++; + { +#ifdef HAVE_MBRTOWC @@ -1219,7 +1693,7 @@ index 26f221f..633f50e 100644 if (*arg) { long int tmp_long; -@@ -1191,6 +1310,11 @@ static void +@@ -1206,6 +1325,11 @@ static void init_parameters (int number_of_files) { int chars_used_by_number = 0; @@ -1231,7 +1705,7 @@ index 26f221f..633f50e 100644 lines_per_body = lines_per_page - lines_per_header - lines_per_footer; if (lines_per_body <= 0) -@@ -1228,7 +1352,7 @@ init_parameters (int number_of_files) +@@ -1243,7 +1367,7 @@ init_parameters (int number_of_files) else col_sep_string = column_separator; @@ -1240,7 +1714,7 @@ index 26f221f..633f50e 100644 use_col_separator = true; } /* It's rather pointless to define a TAB separator with column -@@ -1258,11 +1382,11 @@ init_parameters (int number_of_files) +@@ -1275,11 +1399,11 @@ 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. */ @@ -1254,16 +1728,16 @@ index 26f221f..633f50e 100644 /* The number is part of the column width unless we are printing files in parallel. */ -@@ -1271,7 +1395,7 @@ init_parameters (int number_of_files) +@@ -1288,7 +1412,7 @@ init_parameters (int number_of_files) } int sep_chars, useful_chars; -- if (INT_MULTIPLY_WRAPV (columns - 1, col_sep_length, &sep_chars)) -+ if (INT_MULTIPLY_WRAPV (columns - 1, col_sep_width, &sep_chars)) +- if (ckd_mul (&sep_chars, columns - 1, col_sep_length)) ++ if (ckd_mul (&sep_chars, columns - 1, col_sep_width)) sep_chars = INT_MAX; - if (INT_SUBTRACT_WRAPV (chars_per_line - chars_used_by_number, sep_chars, - &useful_chars)) -@@ -1294,7 +1418,7 @@ init_parameters (int number_of_files) + if (ckd_sub (&useful_chars, chars_per_line - chars_used_by_number, + sep_chars)) +@@ -1311,7 +1435,7 @@ 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); @@ -1272,7 +1746,7 @@ index 26f221f..633f50e 100644 } /* Open the necessary files, -@@ -1402,7 +1526,7 @@ init_funcs (void) +@@ -1417,7 +1541,7 @@ init_funcs (void) /* Enlarge p->start_position of first column to use the same form of padding_not_printed with all columns. */ @@ -1281,7 +1755,7 @@ index 26f221f..633f50e 100644 /* This loop takes care of all but the rightmost column. */ -@@ -1436,7 +1560,7 @@ init_funcs (void) +@@ -1451,7 +1575,7 @@ init_funcs (void) } else { @@ -1290,7 +1764,7 @@ index 26f221f..633f50e 100644 h_next = h + chars_per_column; } } -@@ -1727,9 +1851,9 @@ static void +@@ -1751,9 +1875,9 @@ static void align_column (COLUMN *p) { padding_not_printed = p->start_position; @@ -1302,9 +1776,9 @@ index 26f221f..633f50e 100644 padding_not_printed = ANYWHERE; } -@@ -2004,13 +2128,13 @@ store_char (char c) +@@ -2030,13 +2154,13 @@ store_char (char c) /* May be too generous. */ - buff = X2REALLOC (buff, &buff_allocated); + buff = xpalloc (buff, &buff_allocated, 1, -1, sizeof *buff); } - buff[buff_current++] = c; + buff[buff_current++] = (unsigned char) c; @@ -1318,7 +1792,7 @@ index 26f221f..633f50e 100644 char *s; int num_width; -@@ -2027,22 +2151,24 @@ add_line_number (COLUMN *p) +@@ -2053,22 +2177,24 @@ 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. */ @@ -1347,7 +1821,7 @@ index 26f221f..633f50e 100644 output_position = POS_AFTER_TAB (chars_per_output_tab, output_position); } -@@ -2203,7 +2329,7 @@ print_white_space (void) +@@ -2227,7 +2353,7 @@ print_white_space (void) while (goal - h_old > 1 && (h_new = POS_AFTER_TAB (chars_per_output_tab, h_old)) <= goal) { @@ -1356,7 +1830,7 @@ index 26f221f..633f50e 100644 h_old = h_new; } while (++h_old <= goal) -@@ -2223,6 +2349,7 @@ print_sep_string (void) +@@ -2247,6 +2373,7 @@ print_sep_string (void) { char const *s = col_sep_string; int l = col_sep_length; @@ -1364,7 +1838,7 @@ index 26f221f..633f50e 100644 if (separators_not_printed <= 0) { -@@ -2234,6 +2361,7 @@ print_sep_string (void) +@@ -2258,6 +2385,7 @@ print_sep_string (void) { for (; separators_not_printed > 0; --separators_not_printed) { @@ -1372,7 +1846,7 @@ index 26f221f..633f50e 100644 while (l-- > 0) { /* 3 types of sep_strings: spaces only, spaces and chars, -@@ -2247,12 +2375,15 @@ print_sep_string (void) +@@ -2271,12 +2399,15 @@ print_sep_string (void) } else { @@ -1389,7 +1863,7 @@ index 26f221f..633f50e 100644 /* sep_string ends with some spaces */ if (spaces_not_printed > 0) print_white_space (); -@@ -2280,7 +2411,7 @@ print_clump (COLUMN *p, int n, char *clump) +@@ -2307,7 +2438,7 @@ print_clump (COLUMN *p, int n, char *clump) required number of tabs and spaces. */ static void @@ -1398,7 +1872,7 @@ index 26f221f..633f50e 100644 { if (tabify_output) { -@@ -2304,6 +2435,74 @@ print_char (char c) +@@ -2331,6 +2462,74 @@ print_char (char c) putchar (c); } @@ -1473,7 +1947,7 @@ index 26f221f..633f50e 100644 /* Skip to page PAGE before printing. PAGE may be larger than total number of pages. */ -@@ -2483,9 +2682,9 @@ read_line (COLUMN *p) +@@ -2507,9 +2706,9 @@ read_line (COLUMN *p) align_empty_cols = false; } @@ -1485,8 +1959,8 @@ index 26f221f..633f50e 100644 padding_not_printed = ANYWHERE; } -@@ -2555,7 +2754,7 @@ print_stored (COLUMN *p) - int i; +@@ -2578,7 +2777,7 @@ print_stored (COLUMN *p) + COLUMN *q; int line = p->current_line++; - char *first = &buff[line_vector[line]]; @@ -1494,7 +1968,7 @@ index 26f221f..633f50e 100644 /* FIXME UMR: Uninitialized memory read: * This is occurring while in: -@@ -2567,7 +2766,7 @@ print_stored (COLUMN *p) +@@ -2590,7 +2789,7 @@ print_stored (COLUMN *p) xmalloc [xmalloc.c:94] init_store_cols [pr.c:1648] */ @@ -1503,7 +1977,7 @@ index 26f221f..633f50e 100644 pad_vertically = true; -@@ -2586,9 +2785,9 @@ print_stored (COLUMN *p) +@@ -2610,9 +2809,9 @@ print_stored (COLUMN *p) } } @@ -1515,7 +1989,7 @@ index 26f221f..633f50e 100644 padding_not_printed = ANYWHERE; } -@@ -2601,8 +2800,8 @@ print_stored (COLUMN *p) +@@ -2625,8 +2824,8 @@ print_stored (COLUMN *p) if (spaces_not_printed == 0) { output_position = p->start_position + end_vector[line]; @@ -1526,7 +2000,7 @@ index 26f221f..633f50e 100644 } return true; -@@ -2621,7 +2820,7 @@ print_stored (COLUMN *p) +@@ -2645,7 +2844,7 @@ print_stored (COLUMN *p) number of characters is 1.) */ static int @@ -1535,7 +2009,7 @@ index 26f221f..633f50e 100644 { unsigned char uc = c; char *s = clump_buff; -@@ -2631,10 +2830,10 @@ char_to_clump (char c) +@@ -2655,10 +2854,10 @@ char_to_clump (char c) int chars; int chars_per_c = 8; @@ -1548,7 +2022,7 @@ index 26f221f..633f50e 100644 { width = TAB_WIDTH (chars_per_c, input_position); -@@ -2715,6 +2914,164 @@ char_to_clump (char c) +@@ -2739,6 +2938,164 @@ char_to_clump (char c) return chars; } @@ -1714,13 +2188,14 @@ index 26f221f..633f50e 100644 looking for more options and printing the next batch of files. diff --git a/src/sort.c b/src/sort.c -index 6d2eec5..f189a0d 100644 +index 05d00cc..eb51f20 100644 --- a/src/sort.c +++ b/src/sort.c -@@ -29,6 +29,14 @@ +@@ -30,6 +30,15 @@ #include #include - #include + #include ++ +#if HAVE_WCHAR_H +# include +#endif @@ -1731,10 +2206,10 @@ index 6d2eec5..f189a0d 100644 + #include "system.h" #include "argmatch.h" - #include "die.h" -@@ -165,14 +173,39 @@ static int decimal_point; - /* Thousands separator; if -1, then there isn't one. */ - static int thousands_sep; + #include "assure.h" +@@ -160,14 +169,39 @@ static int thousands_sep; + /* We currently ignore multi-byte grouping chars. */ + static bool thousands_sep_ignored; +/* True if -f is specified. */ +static bool folding; @@ -1773,9 +2248,9 @@ index 6d2eec5..f189a0d 100644 /* The kind of blanks for '-b' to skip in various options. */ enum blanktype { bl_start, bl_end, bl_both }; -@@ -346,13 +379,11 @@ static bool reverse; - they were read if all keys compare equal. */ - static bool stable; +@@ -344,13 +378,11 @@ static bool stable; + /* An int value outside char range. */ + enum { NON_CHAR = CHAR_MAX + 1 }; -/* If TAB has this value, blanks separate fields. */ -enum { TAB_DEFAULT = CHAR_MAX + 1 }; @@ -1790,9 +2265,9 @@ index 6d2eec5..f189a0d 100644 /* Flag to remove consecutive duplicate lines from the output. Only the last of a sequence of equal lines will be output. */ -@@ -811,6 +842,46 @@ reap_all (void) - reap (-1); - } +@@ -386,6 +418,46 @@ struct tempnode + static struct tempnode *volatile temphead; + static struct tempnode *volatile *temptail = &temphead; +/* Function pointers. */ +static void @@ -1837,7 +2312,7 @@ index 6d2eec5..f189a0d 100644 /* Clean up any remaining temporary files. */ static void -@@ -1255,7 +1326,7 @@ zaptemp (char const *name) +@@ -1343,7 +1415,7 @@ zaptemp (char const *name) free (node); } @@ -1846,7 +2321,7 @@ index 6d2eec5..f189a0d 100644 static int struct_month_cmp (void const *m1, void const *m2) -@@ -1270,7 +1341,7 @@ struct_month_cmp (void const *m1, void const *m2) +@@ -1358,7 +1430,7 @@ struct_month_cmp (void const *m1, void const *m2) /* Initialize the character class tables. */ static void @@ -1855,7 +2330,7 @@ index 6d2eec5..f189a0d 100644 { size_t i; -@@ -1282,7 +1353,7 @@ inittables (void) +@@ -1370,7 +1442,7 @@ inittables (void) fold_toupper[i] = toupper (i); } @@ -1864,7 +2339,7 @@ index 6d2eec5..f189a0d 100644 /* If we're not in the "C" locale, read different names for months. */ if (hard_LC_TIME) { -@@ -1364,6 +1435,84 @@ specify_nmerge (int oi, char c, char const *s) +@@ -1450,6 +1522,84 @@ specify_nmerge (int oi, char c, char const *s) xstrtol_fatal (e, oi, c, long_options, s); } @@ -1949,7 +2424,7 @@ index 6d2eec5..f189a0d 100644 /* Specify the amount of main memory to use when sorting. */ static void specify_sort_size (int oi, char c, char const *s) -@@ -1597,7 +1746,7 @@ buffer_linelim (struct buffer const *buf) +@@ -1676,7 +1826,7 @@ buffer_linelim (struct buffer const *buf) by KEY in LINE. */ static char * @@ -1958,7 +2433,7 @@ index 6d2eec5..f189a0d 100644 { char *ptr = line->text, *lim = ptr + line->length - 1; size_t sword = key->sword; -@@ -1606,10 +1755,10 @@ begfield (struct line const *line, struct keyfield const *key) +@@ -1685,10 +1835,10 @@ begfield (struct line const *line, struct keyfield const *key) /* The leading field separator itself is included in a field when -t is absent. */ @@ -1971,7 +2446,7 @@ index 6d2eec5..f189a0d 100644 ++ptr; if (ptr < lim) ++ptr; -@@ -1635,11 +1784,70 @@ begfield (struct line const *line, struct keyfield const *key) +@@ -1718,12 +1868,71 @@ begfield (struct line const *line, struct keyfield const *key) return ptr; } @@ -2037,13 +2512,14 @@ index 6d2eec5..f189a0d 100644 /* Return the limit of (a pointer to the first character after) the field in LINE specified by KEY. */ + ATTRIBUTE_PURE static char * -limfield (struct line const *line, struct keyfield const *key) -+limfield_uni (const struct line *line, const struct keyfield *key) ++limfield_uni (struct line const *line, struct keyfield const *key) { char *ptr = line->text, *lim = ptr + line->length - 1; size_t eword = key->eword, echar = key->echar; -@@ -1654,10 +1862,10 @@ limfield (struct line const *line, struct keyfield const *key) +@@ -1738,10 +1947,10 @@ 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. */ @@ -2056,7 +2532,7 @@ index 6d2eec5..f189a0d 100644 ++ptr; if (ptr < lim && (eword || echar)) ++ptr; -@@ -1703,10 +1911,10 @@ limfield (struct line const *line, struct keyfield const *key) +@@ -1787,10 +1996,10 @@ limfield (struct line const *line, struct keyfield const *key) */ /* Make LIM point to the end of (one byte past) the current field. */ @@ -2069,12 +2545,12 @@ index 6d2eec5..f189a0d 100644 if (newlim) lim = newlim; } -@@ -1737,6 +1945,130 @@ limfield (struct line const *line, struct keyfield const *key) +@@ -1825,6 +2034,130 @@ limfield (struct line const *line, struct keyfield const *key) return ptr; } +#if HAVE_MBRTOWC -+static char * ++static char * _GL_ATTRIBUTE_PURE +limfield_mb (const struct line *line, const struct keyfield *key) +{ + char *ptr = line->text, *lim = ptr + line->length - 1; @@ -2200,7 +2676,7 @@ index 6d2eec5..f189a0d 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 -@@ -1823,8 +2155,22 @@ fillbuf (struct buffer *buf, FILE *fp, char const *file) +@@ -1911,8 +2244,22 @@ fillbuf (struct buffer *buf, FILE *fp, char const *file) else { if (key->skipsblanks) @@ -2225,16 +2701,32 @@ index 6d2eec5..f189a0d 100644 line->keybeg = line_start; } } -@@ -1974,7 +2320,7 @@ human_numcompare (char const *a, char const *b) - hideously fast. */ +@@ -2050,12 +2397,10 @@ find_unit_order (char const *number) + ATTRIBUTE_PURE + static int +-human_numcompare (char const *a, char const *b) ++human_numcompare (char *a, char *b) + { +- while (blanks[to_uchar (*a)]) +- a++; +- while (blanks[to_uchar (*b)]) +- b++; ++ skipblanks(&a, a + strlen(a)); ++ skipblanks(&b, b + strlen(b)); + + 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) + + ATTRIBUTE_PURE static int -numcompare (char const *a, char const *b) +numcompare_uni (const char *a, const char *b) { while (blanks[to_uchar (*a)]) a++; -@@ -1984,6 +2330,25 @@ numcompare (char const *a, char const *b) +@@ -2077,6 +2422,25 @@ numcompare (char const *a, char const *b) return strnumcmp (a, b, decimal_point, thousands_sep); } @@ -2257,10 +2749,10 @@ index 6d2eec5..f189a0d 100644 +} +#endif /* HAV_EMBRTOWC */ + - /* Work around a problem whereby the long double value returned by glibc's - strtold ("NaN", ...) contains uninitialized bits: clear all bytes of - A and B before calling strtold. FIXME: remove this function once -@@ -2034,7 +2399,7 @@ general_numcompare (char const *sa, char const *sb) + static int + nan_compare (long double a, long double b) + { +@@ -2118,7 +2482,7 @@ general_numcompare (char const *sa, char const *sb) Return 0 if the name in S is not recognized. */ static int @@ -2269,7 +2761,7 @@ index 6d2eec5..f189a0d 100644 { size_t lo = 0; size_t hi = MONTHS_PER_YEAR; -@@ -2310,15 +2675,14 @@ debug_key (struct line const *line, struct keyfield const *key) +@@ -2457,15 +2821,14 @@ debug_key (struct line const *line, struct keyfield const *key) char saved = *lim; *lim = '\0'; @@ -2287,7 +2779,7 @@ index 6d2eec5..f189a0d 100644 else if (key->general_numeric) ignore_value (strtold (beg, &tighter_lim)); else if (key->numeric || key->human_numeric) -@@ -2452,7 +2816,7 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) +@@ -2611,7 +2974,7 @@ 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 */ @@ -2296,8 +2788,58 @@ index 6d2eec5..f189a0d 100644 && ((!key->skipsblanks && !implicit_skip) || (!key->skipsblanks && key->schar) || (!key->skipeblanks && key->echar))) -@@ -2510,11 +2874,87 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) - error (0, 0, _("option '-r' only applies to last-resort comparison")); +@@ -2659,9 +3022,9 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) + bool number_locale_warned = false; + if (basic_numeric_field_span) + { +- if (tab == TAB_DEFAULT +- ? thousands_sep != NON_CHAR && (isblank (to_uchar (thousands_sep))) +- : tab == thousands_sep) ++ if (tab_length ++ ? tab[0] == thousands_sep ++ : thousands_sep != NON_CHAR && (isblank (to_uchar (thousands_sep)))) + { + error (0, 0, + _("field separator %s is treated as a " +@@ -2672,9 +3035,9 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) + } + if (basic_numeric_field_span || general_numeric_field_span) + { +- if (tab == TAB_DEFAULT +- ? thousands_sep != NON_CHAR && (isblank (to_uchar (decimal_point))) +- : tab == decimal_point) ++ if (tab_length ++ ? tab[0] == decimal_point ++ : thousands_sep != NON_CHAR && (isblank (to_uchar (decimal_point)))) + { + error (0, 0, + _("field separator %s is treated as a " +@@ -2682,19 +3045,19 @@ key_warnings (struct keyfield const *gkey, bool gkey_only) + quote (((char []) {decimal_point, 0}))); + number_locale_warned = true; + } +- else if (tab == '-') ++ else if (tab_length && tab[0] == '-') + { + error (0, 0, + _("field separator %s is treated as a " + "minus sign in numbers"), +- quote (((char []) {tab, 0}))); ++ quote (((char []) {tab[0], 0}))); + } +- else if (general_numeric_field_span && tab == '+') ++ else if (general_numeric_field_span && tab_length && tab[0] == '+') + { + error (0, 0, + _("field separator %s is treated as a " + "plus sign in numbers"), +- quote (((char []) {tab, 0}))); ++ quote (((char []) {tab[0], 0}))); + } + } + +@@ -2746,11 +3109,87 @@ diff_reversed (int diff, bool reversed) + return reversed ? _GL_CMP (0, diff) : diff; } +#if HAVE_MBRTOWC @@ -2385,17 +2927,17 @@ index 6d2eec5..f189a0d 100644 { struct keyfield *key = keylist; -@@ -2599,7 +3039,7 @@ keycompare (struct line const *a, struct line const *b) +@@ -2831,7 +3270,7 @@ keycompare (struct line const *a, struct line const *b) else if (key->human_numeric) diff = human_numcompare (ta, tb); else if (key->month) -- diff = getmonth (ta, NULL) - getmonth (tb, NULL); -+ diff = getmonth (ta, tlena, NULL) - getmonth (tb, tlenb, NULL); +- diff = getmonth (ta, nullptr) - getmonth (tb, nullptr); ++ diff = getmonth (ta, tlena, nullptr) - getmonth (tb, tlenb, nullptr); else if (key->random) diff = compare_random (ta, tlena, tb, tlenb); else if (key->version) -@@ -2715,6 +3155,211 @@ keycompare (struct line const *a, struct line const *b) - return key->reverse ? -diff : diff; +@@ -2941,6 +3380,211 @@ keycompare (struct line const *a, struct line const *b) + return diff_reversed (diff, key->reverse); } +#if HAVE_MBRTOWC @@ -2606,16 +3148,16 @@ index 6d2eec5..f189a0d 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. */ -@@ -2742,7 +3387,7 @@ compare (struct line const *a, struct line const *b) +@@ -2968,7 +3612,7 @@ compare (struct line const *a, struct line const *b) diff = - NONZERO (blen); else if (blen == 0) diff = 1; - else if (hard_LC_COLLATE) + else if (hard_LC_COLLATE && !folding) { - /* Note xmemcoll0 is a performance enhancement as + /* xmemcoll0 is a performance enhancement as it will not unconditionally write '\0' after the -@@ -4139,6 +4784,7 @@ set_ordering (char const *s, struct keyfield *key, enum blanktype blanktype) +@@ -4340,6 +4984,7 @@ set_ordering (char const *s, struct keyfield *key, enum blanktype blanktype) break; case 'f': key->translate = fold_toupper; @@ -2623,7 +3165,7 @@ index 6d2eec5..f189a0d 100644 break; case 'g': key->general_numeric = true; -@@ -4218,7 +4864,7 @@ main (int argc, char **argv) +@@ -4419,7 +5064,7 @@ main (int argc, char **argv) initialize_exit_failure (SORT_FAILURE); hard_LC_COLLATE = hard_locale (LC_COLLATE); @@ -2632,8 +3174,8 @@ index 6d2eec5..f189a0d 100644 hard_LC_TIME = hard_locale (LC_TIME); #endif -@@ -4239,6 +4885,29 @@ main (int argc, char **argv) - thousands_sep = -1; +@@ -4442,6 +5087,29 @@ main (int argc, char **argv) + thousands_sep = NON_CHAR; } +#if HAVE_MBRTOWC @@ -2662,7 +3204,7 @@ index 6d2eec5..f189a0d 100644 have_read_stdin = false; inittables (); -@@ -4513,13 +5182,34 @@ main (int argc, char **argv) +@@ -4717,13 +5385,34 @@ main (int argc, char **argv) case 't': { @@ -2672,7 +3214,7 @@ index 6d2eec5..f189a0d 100644 + size_t newtab_length = 1; + strncpy (newtab, optarg, MB_LEN_MAX); + if (! newtab[0]) - die (SORT_FAILURE, 0, _("empty tab")); + error (SORT_FAILURE, 0, _("empty tab")); - if (optarg[1]) +#if HAVE_MBRTOWC + if (MB_CUR_MAX > 1) @@ -2695,429 +3237,433 @@ index 6d2eec5..f189a0d 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 -@@ -4530,9 +5220,11 @@ main (int argc, char **argv) - quote (optarg)); +@@ -4734,9 +5423,11 @@ main (int argc, char **argv) + quote (optarg)); } } - if (tab != TAB_DEFAULT && tab != newtab) + if (tab_length && (tab_length != newtab_length + || memcmp (tab, newtab, tab_length) != 0)) - die (SORT_FAILURE, 0, _("incompatible tabs")); + error (SORT_FAILURE, 0, _("incompatible tabs")); - tab = newtab; + memcpy (tab, newtab, newtab_length); + tab_length = newtab_length; } break; -@@ -4770,12 +5462,10 @@ main (int argc, char **argv) - sort (files, nfiles, outfile, nthreads); - } - --#ifdef lint - if (files_from) - readtokens0_free (&tok); - else - free (files); --#endif - - if (have_read_stdin && fclose (stdin) == EOF) - sort_die (_("close failed"), "-"); -diff --git a/src/uniq.c b/src/uniq.c -index 87a0c93..9f755d9 100644 ---- a/src/uniq.c -+++ b/src/uniq.c -@@ -21,6 +21,17 @@ +diff --git a/src/unexpand.c b/src/unexpand.c +index ff234d7..7c36ef6 100644 +--- a/src/unexpand.c ++++ b/src/unexpand.c +@@ -39,6 +39,9 @@ + #include #include #include - -+/* Get mbstate_t, mbrtowc(). */ -+#if HAVE_WCHAR_H -+# include -+#endif + -+/* Get isw* functions. */ -+#if HAVE_WCTYPE_H -+# include -+#endif -+#include ++#include + #include "system.h" - #include "argmatch.h" - #include "linebuffer.h" -@@ -32,9 +43,21 @@ - #include "stdio--.h" - #include "xmemcoll.h" - #include "xstrtol.h" --#include "memcasecmp.h" -+#include "xmemcoll.h" - #include "quote.h" + #include "expand-common.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 -+# 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 -+ -+ - /* The official name of this program (e.g., no 'g' prefix). */ - #define PROGRAM_NAME "uniq" - -@@ -144,6 +167,10 @@ enum - GROUP_OPTION = CHAR_MAX + 1 - }; - -+/* Function pointers. */ -+static char * -+(*find_field) (struct linebuffer *line); -+ - static struct option const longopts[] = +@@ -105,24 +108,46 @@ unexpand (void) { - {"count", no_argument, NULL, 'c'}, -@@ -260,7 +287,7 @@ size_opt (char const *opt, char const *msgid) - return a pointer to the beginning of the line's field to be compared. */ + /* Input stream. */ + FILE *fp = next_file (nullptr); ++ mb_file_t mbf; - static char * _GL_ATTRIBUTE_PURE --find_field (struct linebuffer const *line) -+find_field_uni (struct linebuffer *line) - { - size_t count; - char const *lp = line->buffer; -@@ -280,6 +307,83 @@ find_field (struct linebuffer const *line) - return line->buffer + i; - } + /* The array of pending blanks. In non-POSIX locales, blanks can + include characters other than spaces, so the blanks must be + stored, not merely counted. */ +- char *pending_blank; ++ mbf_char_t *pending_blank; ++ /* True if the starting locale is utf8. */ ++ bool using_utf_locale; ++ ++ /* True if the first file contains BOM header. */ ++ bool found_bom; ++ using_utf_locale=check_utf_locale(); -+#if HAVE_MBRTOWC + if (!fp) + return; + ++ mbf_init (mbf, fp); ++ found_bom=check_bom(fp,&mbf); + -+# define MBCHAR_TO_WCHAR(WC, MBLENGTH, LP, POS, SIZE, STATEP, CONVFAIL) \ -+ do \ -+ { \ -+ mbstate_t state_bak; \ -+ \ -+ CONVFAIL = 0; \ -+ state_bak = *STATEP; \ -+ \ -+ MBLENGTH = mbrtowc (&WC, LP + POS, SIZE - POS, STATEP); \ -+ \ -+ switch (MBLENGTH) \ -+ { \ -+ case (size_t)-2: \ -+ case (size_t)-1: \ -+ *STATEP = state_bak; \ -+ CONVFAIL++; \ -+ /* Fall through */ \ -+ case 0: \ -+ MBLENGTH = 1; \ -+ } \ -+ } \ -+ while (0) -+ -+static char * -+find_field_multi (struct linebuffer *line) -+{ -+ size_t count; -+ char *lp = line->buffer; -+ size_t size = line->length - 1; -+ size_t pos; -+ size_t mblength; -+ wchar_t wc; -+ mbstate_t *statep; -+ int convfail = 0; -+ -+ pos = 0; -+ statep = &(line->state); -+ -+ /* skip fields. */ -+ for (count = 0; count < skip_fields && pos < size; count++) ++ if (using_utf_locale == false && found_bom == true) + { -+ while (pos < size) ++ /* Try using some predefined locale */ ++ if (set_utf_locale () != 0) + { -+ MBCHAR_TO_WCHAR (wc, mblength, lp, pos, size, statep, convfail); -+ -+ if (convfail || !(iswblank (wc) || wc == '\n')) -+ { -+ pos += mblength; -+ break; -+ } -+ pos += mblength; -+ } -+ -+ while (pos < size) -+ { -+ MBCHAR_TO_WCHAR (wc, mblength, lp, pos, size, statep, convfail); -+ -+ if (!convfail && (iswblank (wc) || wc == '\n')) -+ break; -+ -+ pos += mblength; ++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale")); + } + } + -+ /* skip fields. */ -+ for (count = 0; count < skip_chars && pos < size; count++) -+ { -+ MBCHAR_TO_WCHAR (wc, mblength, lp, pos, size, statep, convfail); -+ pos += mblength; -+ } + /* 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)); + -+ return lp + pos; -+} -+#endif -+ - /* Return false if two strings OLD and NEW match, true if not. - OLD and NEW point not to the beginnings of the lines - but rather to the beginnings of the fields to compare. -@@ -288,6 +392,8 @@ find_field (struct linebuffer const *line) - static bool - different (char *old, char *new, size_t oldlen, size_t newlen) - { -+ char *copy_old, *copy_new; -+ - if (check_chars < oldlen) - oldlen = check_chars; - if (check_chars < newlen) -@@ -295,15 +401,104 @@ different (char *old, char *new, size_t oldlen, size_t newlen) ++ if (found_bom == true) ++ print_bom(); - if (ignore_case) + while (true) { -- /* FIXME: This should invoke strcoll somehow. */ -- return oldlen != newlen || memcasecmp (old, new, oldlen); -+ size_t i; + /* Input character, or EOF. */ +- int c; ++ mbf_char_t c; + + /* If true, perform translations. */ + bool convert = true; +@@ -156,12 +181,44 @@ unexpand (void) + + do + { +- while ((c = getc (fp)) < 0 && (fp = next_file (fp))) +- continue; ++ while (true) { ++ mbf_getc (c, mbf); ++ if ((mb_iseof (c)) && (fp = next_file (fp))) ++ { ++ mbf_init (mbf, fp); ++ if (fp!=NULL) ++ { ++ if (check_bom(fp,&mbf)==true) ++ { ++ /*Not the first file - check BOM header*/ ++ if (using_utf_locale==false && found_bom==false) ++ { ++ /*BOM header in subsequent file but not in the first one. */ ++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); ++ } ++ } ++ else ++ { ++ if(using_utf_locale==false && found_bom==true) ++ { ++ /*First file conatined BOM header - locale was switched to UTF ++ *all subsequent files should contain BOM. */ ++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header")); ++ } ++ } ++ } ++ continue; ++ } ++ else ++ { ++ break; ++ } ++ } + -+ copy_old = xmalloc (oldlen + 1); -+ copy_new = xmalloc (oldlen + 1); + + if (convert) + { +- bool blank = !! isblank (c); ++ bool blank = mb_isblank (c); + + if (blank) + { +@@ -175,16 +232,16 @@ unexpand (void) + + if (convert) + { +- if (c == '\t') ++ if (mb_iseq (c, '\t')) + { + column = next_tab_column; + + if (pending) +- pending_blank[0] = '\t'; ++ mb_setascii (&pending_blank[0], '\t'); + } + else + { +- column++; ++ column += mb_width (c); + + if (! (prev_blank && column == next_tab_column)) + { +@@ -192,13 +249,14 @@ unexpand (void) + will be replaced by tabs. */ + if (column == next_tab_column) + one_blank_before_tab_stop = true; +- pending_blank[pending++] = c; ++ mb_copy (&pending_blank[pending++], &c); + prev_blank = true; + continue; + } + + /* Replace the pending blanks by a tab or two. */ +- pending_blank[0] = c = '\t'; ++ mb_setascii (&c, '\t'); ++ mb_setascii (&pending_blank[0], '\t'); + } + + /* Discard pending blanks, unless it was a single +@@ -206,7 +264,7 @@ unexpand (void) + pending = one_blank_before_tab_stop; + } + } +- else if (c == '\b') ++ else if (mb_iseq (c, '\b')) + { + /* Go back one column, and force recalculation of the + next tab stop. */ +@@ -216,16 +274,20 @@ unexpand (void) + } + else + { +- column++; +- if (!column) ++ const uintmax_t orig_column = column; ++ column += mb_width (c); ++ if (column < orig_column) + error (EXIT_FAILURE, 0, _("input line is too long")); + } + + if (pending) + { + if (pending > 1 && one_blank_before_tab_stop) +- pending_blank[0] = '\t'; +- if (fwrite (pending_blank, 1, pending, stdout) != pending) ++ mb_setascii (&pending_blank[0], '\t'); + -+ for (i = 0; i < oldlen; i++) -+ { -+ copy_old[i] = toupper (old[i]); -+ copy_new[i] = toupper (new[i]); -+ } -+ bool rc = xmemcoll (copy_old, oldlen, copy_new, newlen); -+ free (copy_old); -+ free (copy_new); -+ return rc; ++ for (int n = 0; n < pending; ++n) ++ mb_putc (pending_blank[n], stdout); ++ if (ferror (stdout)) + write_error (); + pending = 0; + one_blank_before_tab_stop = false; +@@ -235,16 +297,17 @@ unexpand (void) + convert &= convert_entire_line || blank; + } + +- if (c < 0) ++ if (mb_iseof (c)) + { + free (pending_blank); + return; + } + +- if (putchar (c) < 0) ++ mb_putc (c, stdout); ++ if (ferror (stdout)) + write_error (); + } +- while (c != '\n'); ++ while (!mb_iseq (c, '\n')); } -- else if (hard_LC_COLLATE) -- return xmemcoll (old, oldlen, new, newlen) != 0; - else -- return oldlen != newlen || memcmp (old, new, oldlen); -+ { -+ copy_old = (char *)old; -+ copy_new = (char *)new; -+ } -+ -+ return xmemcoll (copy_old, oldlen, copy_new, newlen); -+ } -+#if HAVE_MBRTOWC -+static int -+different_multi (const char *old, const char *new, size_t oldlen, size_t newlen, mbstate_t oldstate, mbstate_t newstate) -+{ -+ size_t i, j, chars; -+ const char *str[2]; -+ char *copy[2]; -+ size_t len[2]; -+ mbstate_t state[2]; -+ size_t mblength; -+ wchar_t wc, uwc; -+ mbstate_t state_bak; -+ -+ str[0] = old; -+ str[1] = new; -+ len[0] = oldlen; -+ len[1] = newlen; -+ state[0] = oldstate; -+ state[1] = newstate; -+ -+ for (i = 0; i < 2; i++) -+ { -+ copy[i] = xmalloc (len[i] + 1); -+ memset (copy[i], '\0', len[i] + 1); -+ -+ for (j = 0, chars = 0; j < len[i] && chars < check_chars; chars++) -+ { -+ state_bak = state[i]; -+ mblength = mbrtowc (&wc, str[i] + j, len[i] - j, &(state[i])); -+ -+ switch (mblength) -+ { -+ case (size_t)-1: -+ case (size_t)-2: -+ state[i] = state_bak; -+ /* Fall through */ -+ case 0: -+ mblength = 1; -+ break; -+ -+ default: -+ if (ignore_case) -+ { -+ uwc = towupper (wc); -+ -+ if (uwc != wc) -+ { -+ mbstate_t state_wc; -+ size_t mblen; -+ -+ memset (&state_wc, '\0', sizeof(mbstate_t)); -+ mblen = wcrtomb (copy[i] + j, uwc, &state_wc); -+ assert (mblen != (size_t)-1); -+ } -+ else -+ memcpy (copy[i] + j, str[i] + j, mblength); -+ } -+ else -+ memcpy (copy[i] + j, str[i] + j, mblength); -+ } -+ j += mblength; -+ } -+ copy[i][j] = '\0'; -+ len[i] = j; -+ } -+ int rc = xmemcoll (copy[0], len[0], copy[1], len[1]); -+ free (copy[0]); -+ free (copy[1]); -+ return rc; -+ -+} -+#endif -+ - /* Output the line in linebuffer LINE to standard output - provided that the switches say it should be output. - MATCH is true if the line matches the previous line. -@@ -367,19 +562,38 @@ check_file (const char *infile, const char *outfile, char delimiter) - char *prevfield IF_LINT ( = NULL); - size_t prevlen IF_LINT ( = 0); - bool first_group_printed = false; -+#if HAVE_MBRTOWC -+ mbstate_t prevstate; -+ -+ memset (&prevstate, '\0', sizeof (mbstate_t)); -+#endif - - while (!feof (stdin)) +diff --git a/tests/Coreutils.pm b/tests/Coreutils.pm +index b55fb9d..ac80f49 100644 +--- a/tests/Coreutils.pm ++++ b/tests/Coreutils.pm +@@ -269,6 +269,9 @@ sub run_tests ($$$$$) + # Yes, this is an arbitrary limit. If it causes trouble, + # consider removing it. + my $max = 30; ++ # The downstream i18n multi-byte tests have a "-mb" suffix. ++ # Therefore add 3 to the maximum test name length. ++ $max += 3; + if ($max < length $test_name) { - char *thisfield; - size_t thislen; - bool new_group; -+#if HAVE_MBRTOWC -+ mbstate_t thisstate; -+#endif - - if (readlinebuffer_delim (thisline, stdin, delimiter) == 0) - break; - - thisfield = find_field (thisline); - thislen = thisline->length - 1 - (thisfield - thisline->buffer); -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ { -+ thisstate = thisline->state; - -+ new_group = (prevline->length == 0 -+ || different_multi (thisfield, prevfield, -+ thislen, prevlen, -+ thisstate, prevstate)); -+ } -+ else -+#endif - new_group = (prevline->length == 0 - || different (thisfield, prevfield, thislen, prevlen)); - -@@ -397,6 +611,10 @@ check_file (const char *infile, const char *outfile, char delimiter) - SWAP_LINES (prevline, thisline); - prevfield = thisfield; - prevlen = thislen; -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ prevstate = thisstate; -+#endif - first_group_printed = true; - } - } -@@ -409,17 +627,26 @@ check_file (const char *infile, const char *outfile, char delimiter) - size_t prevlen; - uintmax_t match_count = 0; - bool first_delimiter = true; -+#if HAVE_MBRTOWC -+ mbstate_t prevstate; -+#endif - - if (readlinebuffer_delim (prevline, stdin, delimiter) == 0) - goto closefiles; - prevfield = find_field (prevline); - prevlen = prevline->length - 1 - (prevfield - prevline->buffer); -+#if HAVE_MBRTOWC -+ prevstate = prevline->state; -+#endif - - while (!feof (stdin)) - { - bool match; - char *thisfield; - size_t thislen; -+#if HAVE_MBRTOWC -+ mbstate_t thisstate = thisline->state; -+#endif - if (readlinebuffer_delim (thisline, stdin, delimiter) == 0) - { - if (ferror (stdin)) -@@ -428,6 +655,14 @@ check_file (const char *infile, const char *outfile, char delimiter) - } - thisfield = find_field (thisline); - thislen = thisline->length - 1 - (thisfield - thisline->buffer); -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ { -+ match = !different_multi (thisfield, prevfield, -+ thislen, prevlen, thisstate, prevstate); -+ } -+ else -+#endif - match = !different (thisfield, prevfield, thislen, prevlen); - match_count += match; - -@@ -460,6 +695,9 @@ check_file (const char *infile, const char *outfile, char delimiter) - SWAP_LINES (prevline, thisline); - prevfield = thisfield; - prevlen = thislen; -+#if HAVE_MBRTOWC -+ prevstate = thisstate; -+#endif - if (!match) - match_count = 0; - } -@@ -506,6 +744,19 @@ main (int argc, char **argv) - - atexit (close_stdout); - -+#if HAVE_MBRTOWC -+ if (MB_CUR_MAX > 1) -+ { -+ find_field = find_field_multi; -+ } -+ else -+#endif -+ { -+ find_field = find_field_uni; -+ } + warn "$program_name: $test_name: test name is too long (> $max)\n"; +diff --git a/tests/expand/mb.sh b/tests/expand/mb.sh +new file mode 100644 +index 0000000..dd6007c +--- /dev/null ++++ b/tests/expand/mb.sh +@@ -0,0 +1,183 @@ ++#!/bin/sh ++ ++# Copyright (C) 2012-2015 Free Software Foundation, Inc. ++ ++# This program is free software: you can redistribute it and/or modify ++# it under the terms of the GNU General Public License as published by ++# the Free Software Foundation, either version 3 of the License, or ++# (at your option) any later version. ++ ++# This program is distributed in the hope that it will be useful, ++# but WITHOUT ANY WARRANTY; without even the implied warranty of ++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++# GNU General Public License for more details. ++ ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . ++ ++. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src ++print_ver_ expand ++ ++export LC_ALL=en_US.UTF-8 ++ ++#input containing multibyte characters ++cat <<\EOF > in || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++EOF ++env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_ ++ ++cat <<\EOF > exp || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++ ++expand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++#multiple files as an input ++cat <<\EOF >> exp || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++ ++expand ./in ./in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++#test characters with display widths != 1 ++env printf '12345678 ++e\t|ascii(1) ++\u00E9\t|composed(1) ++e\u0301\t|decomposed(1) ++\u3000\t|ideo-space(2) ++\uFF0D\t|full-hypen(2) ++' > in || framework_failure_ ++ ++env printf '12345678 ++e |ascii(1) ++\u00E9 |composed(1) ++e\u0301 |decomposed(1) ++\u3000 |ideo-space(2) ++\uFF0D |full-hypen(2) ++' > exp || framework_failure_ ++ ++expand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++#shouldn't fail with "input line too long" ++#when a line starts with a control character ++env printf '\n' > in || framework_failure_ ++ ++expand < in > out || fail=1 ++compare in out > /dev/null 2>&1 || fail=1 ++ ++#non-Unicode characters interspersed between Unicode ones ++env printf '12345678 ++\t\xFF| ++\xFF\t| ++\t\xFFä| ++ä\xFF\t| ++\tä\xFF| ++\xFF\tä| ++äbcdef\xFF\t| ++' > in || framework_failure_ ++ ++env printf '12345678 ++ \xFF| ++\xFF | ++ \xFFä| ++ä\xFF | ++ ä\xFF| ++\xFF ä| ++äbcdef\xFF | ++' > exp || framework_failure_ ++ ++expand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 + + + - skip_chars = 0; - skip_fields = 0; - check_chars = SIZE_MAX; ++#BOM header test 1 ++printf "\xEF\xBB\xBF" > in; cat <<\EOF >> in || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++EOF ++env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_ ++ ++printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++ ++ ++expand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LANG=C expand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LC_ALL=C expand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++ ++printf '\xEF\xBB\xBF' > in1; cat <<\EOF >> in1 || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++EOF ++env printf ' äöü\t. öüä. \tä xx\n' >> in1 || framework_failure_ ++ ++ ++printf '\xEF\xBB\xBF' > exp; cat <<\EOF >> exp || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++ ++expand in1 in1 > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LANG=C expand in1 in1 > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LC_ALL=C expand in1 in1 > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++exit $fail diff --git a/tests/i18n/sort.sh b/tests/i18n/sort.sh new file mode 100644 index 0000000..26c95de @@ -3154,46 +3700,36 @@ index 0000000..26c95de + +Exit $fail diff --git a/tests/local.mk b/tests/local.mk -index 568944e..192f776 100644 +index 53fc53e..0148422 100644 --- a/tests/local.mk +++ b/tests/local.mk -@@ -352,6 +352,8 @@ all_tests = \ - tests/misc/sort-discrim.sh \ - tests/misc/sort-files0-from.pl \ - tests/misc/sort-float.sh \ +@@ -412,6 +412,8 @@ all_tests = \ + tests/sort/sort-field-limit.sh \ + tests/sort/sort-files0-from.pl \ + tests/sort/sort-float.sh \ + tests/misc/sort-mb-tests.sh \ + tests/i18n/sort.sh \ - tests/misc/sort-h-thousands-sep.sh \ - tests/misc/sort-merge.pl \ - tests/misc/sort-merge-fdlimit.sh \ -diff --git a/tests/misc/cut.pl b/tests/misc/cut.pl -index f6f8a56..b426a80 100755 ---- a/tests/misc/cut.pl -+++ b/tests/misc/cut.pl -@@ -23,9 +23,11 @@ use strict; - # Turn off localization of executable's output. - @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3; + tests/sort/sort-h-thousands-sep.sh \ + tests/sort/sort-merge.pl \ + tests/sort/sort-merge-fdlimit.sh \ +@@ -618,6 +620,7 @@ all_tests = \ + tests/du/threshold.sh \ + tests/du/trailing-slash.sh \ + tests/du/two-args.sh \ ++ tests/expand/mb.sh \ + tests/id/gnu-zero-uids.sh \ + tests/id/no-context.sh \ + tests/id/context.sh \ +@@ -774,6 +777,7 @@ all_tests = \ + tests/touch/read-only.sh \ + tests/touch/relative.sh \ + tests/touch/trailing-slash.sh \ ++ tests/unexpand/mb.sh \ + $(all_root_tests) --my $mb_locale = $ENV{LOCALE_FR_UTF8}; -+my $mb_locale; -+# uncommented enable multibyte paths -+$mb_locale = $ENV{LOCALE_FR_UTF8}; - ! defined $mb_locale || $mb_locale eq 'none' -- and $mb_locale = 'C'; -+ and $mb_locale = 'C'; - - my $prog = 'cut'; - my $try = "Try '$prog --help' for more information.\n"; -@@ -240,6 +242,7 @@ if ($mb_locale ne 'C') - my @new_t = @$t; - my $test_name = shift @new_t; - -+ next if ($test_name =~ "newline-[12][0-9]"); - push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; - } - push @Tests, @new; + # See tests/factor/create-test.sh. diff --git a/tests/misc/expand.pl b/tests/misc/expand.pl -index 8a9cad1..9293e39 100755 +index 4b07210..68b9ea1 100755 --- a/tests/misc/expand.pl +++ b/tests/misc/expand.pl @@ -27,6 +27,15 @@ my $prog = 'expand'; @@ -3212,8 +3748,8 @@ index 8a9cad1..9293e39 100755 my @Tests = ( ['t1', '--tabs=3', {IN=>"a\tb"}, {OUT=>"a b"}], -@@ -152,6 +161,8 @@ my @Tests = - ['trail9', '--tab=1,2 -t/5',{IN=>"\ta\tb\tc"}, {OUT=>" a b c"}], +@@ -168,6 +177,8 @@ my @Tests = + # Test errors + # FIXME: The following tests contain ‘quoting’ specific to LC_MESSAGES @@ -3221,7 +3757,7 @@ index 8a9cad1..9293e39 100755 ['e1', '--tabs="a"', {IN=>''}, {OUT=>''}, {EXIT=>1}, {ERR => "$prog: tab size contains invalid character(s): 'a'\n"}], ['e2', "-t $UINTMAX_OFLOW", {IN=>''}, {OUT=>''}, {EXIT=>1}, -@@ -168,6 +179,37 @@ my @Tests = +@@ -184,6 +195,37 @@ my @Tests = {ERR => "$prog: '/' specifier not at start of number: '/'\n"}], ); @@ -3259,149 +3795,6 @@ index 8a9cad1..9293e39 100755 my $save_temps = $ENV{DEBUG}; my $verbose = $ENV{VERBOSE}; -diff --git a/tests/misc/fold.pl b/tests/misc/fold.pl -index 7b192b4..76f073f 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/join.pl b/tests/misc/join.pl -index 4d399d8..07f2823 100755 ---- a/tests/misc/join.pl -+++ b/tests/misc/join.pl -@@ -25,6 +25,15 @@ my $limits = getlimits (); - - my $prog = 'join'; - -+my $try = "Try \`$prog --help' for more information.\n"; -+my $inval = "$prog: invalid byte, character or field list\n$try"; -+ -+my $mb_locale; -+#Comment out next line to disable multibyte tests -+$mb_locale = $ENV{LOCALE_FR_UTF8}; -+! defined $mb_locale || $mb_locale eq 'none' -+ and $mb_locale = 'C'; -+ - my $delim = chr 0247; - sub t_subst ($) - { -@@ -329,8 +338,49 @@ foreach my $t (@tv) - push @Tests, $new_ent; - } - -+# Add _POSIX2_VERSION=199209 to the environment of each test -+# that uses an old-style option like +1. -+if ($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 join 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; -+ } -+ #Adjust the output some error messages including test_name for mb -+ if (grep {ref $_ eq 'HASH' && exists $_->{ERR}} -+ (@new_t)) -+ { -+ my $sub2 = {ERR_SUBST => "s/$test_name-mb/$test_name/"}; -+ push @new_t, $sub2; -+ push @$t, $sub2; -+ } -+ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; -+ } -+ push @Tests, @new; -+ } -+ - @Tests = triple_test \@Tests; - -+#skip invalid-j-mb test, it is failing because of the format -+@Tests = grep {$_->[0] ne 'invalid-j-mb'} @Tests; -+ - my $save_temps = $ENV{DEBUG}; - my $verbose = $ENV{VERBOSE}; - diff --git a/tests/misc/sort-mb-tests.sh b/tests/misc/sort-mb-tests.sh new file mode 100644 index 0000000..11836ba @@ -3453,10 +3846,136 @@ index 0000000..11836ba +compare exp out || { fail=1; cat out; } + +Exit $fail -diff --git a/tests/misc/sort-merge.pl b/tests/misc/sort-merge.pl -index 23f6ed2..402a987 100755 ---- a/tests/misc/sort-merge.pl -+++ b/tests/misc/sort-merge.pl +diff --git a/tests/misc/unexpand.pl b/tests/misc/unexpand.pl +index bb7469c..c1dec95 100755 +--- a/tests/misc/unexpand.pl ++++ b/tests/misc/unexpand.pl +@@ -27,6 +27,14 @@ my $limits = getlimits (); + + my $prog = 'unexpand'; + ++# comment out next line to disable multibyte tests ++my $mb_locale = $ENV{LOCALE_FR_UTF8}; ++! defined $mb_locale || $mb_locale eq 'none' ++ and $mb_locale = 'C'; ++ ++my $try = "Try \`$prog --help' for more information.\n"; ++my $inval = "$prog: invalid byte, character or field list\n$try"; ++ + my @Tests = + ( + ['a1', {IN=> ' 'x 1 ."y\n"}, {OUT=> ' 'x 1 ."y\n"}], +@@ -132,6 +140,37 @@ my @Tests = + ['ts2', '-t5,8', {IN=>"x\t \t y\n"}, {OUT=>"x\t\t y\n"}], + ); + ++if ($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 unexpand 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, $sub; ++ } ++ next if ($test_name =~ 'b-1'); ++ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; ++ } ++ push @Tests, @new; ++ } ++ ++@Tests = triple_test \@Tests; ++ + my $save_temps = $ENV{DEBUG}; + my $verbose = $ENV{VERBOSE}; + +diff --git a/tests/pr/pr-tests.pl b/tests/pr/pr-tests.pl +index 60e6106..3c64a08 100755 +--- a/tests/pr/pr-tests.pl ++++ b/tests/pr/pr-tests.pl +@@ -24,6 +24,15 @@ use strict; + my $prog = 'pr'; + my $normalize_strerror = "s/': .*/'/"; + ++my $mb_locale; ++#Uncomment the following line to enable multibyte tests ++$mb_locale = $ENV{LOCALE_FR_UTF8}; ++! defined $mb_locale || $mb_locale eq 'none' ++ and $mb_locale = 'C'; ++ ++my $try = "Try \`$prog --help' for more information.\n"; ++my $inval = "$prog: invalid byte, character or field list\n$try"; ++ + my @tv = ( + + # -b option is no longer an official option. But it's still working to +@@ -515,8 +524,48 @@ push @Tests, + {IN=>"x\tx\tx\tx\tx\nx\tx\tx\tx\tx\n"}, + {OUT=>"x\tx\tx\tx\tx\tx\tx\tx\tx\tx\n"} ]; + ++# Add _POSIX2_VERSION=199209 to the environment of each test ++# that uses an old-style option like +1. ++if ($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 pr 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, $sub; ++ } ++ #temporarily skip some failing tests ++ next if ($test_name =~ "col-0" or $test_name =~ "col-inval" or $test_name =~ "asan1"); ++ push @new, ["$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}; + +diff --git a/tests/sort/sort-merge.pl b/tests/sort/sort-merge.pl +index a3204d3..40942a5 100755 +--- a/tests/sort/sort-merge.pl ++++ b/tests/sort/sort-merge.pl @@ -26,6 +26,15 @@ my $prog = 'sort'; # Turn off localization of executable's output. @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3; @@ -3513,10 +4032,10 @@ index 23f6ed2..402a987 100755 my $save_temps = $ENV{DEBUG}; my $verbose = $ENV{VERBOSE}; -diff --git a/tests/misc/sort.pl b/tests/misc/sort.pl -index c3e7f8e..6ecd3ff 100755 ---- a/tests/misc/sort.pl -+++ b/tests/misc/sort.pl +diff --git a/tests/sort/sort.pl b/tests/sort/sort.pl +index 5fa9d52..a66952a 100755 +--- a/tests/sort/sort.pl ++++ b/tests/sort/sort.pl @@ -24,10 +24,15 @@ my $prog = 'sort'; # Turn off localization of executable's output. @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3; @@ -3534,7 +4053,7 @@ index c3e7f8e..6ecd3ff 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 '-'. -@@ -423,6 +428,38 @@ foreach my $t (@Tests) +@@ -428,6 +433,38 @@ foreach my $t (@Tests) } } @@ -3573,7 +4092,7 @@ index c3e7f8e..6ecd3ff 100755 @Tests = triple_test \@Tests; # Remember that triple_test creates from each test with exactly one "IN" -@@ -432,6 +469,7 @@ foreach my $t (@Tests) +@@ -437,6 +474,7 @@ 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; @@ -3581,208 +4100,184 @@ index c3e7f8e..6ecd3ff 100755 my $save_temps = $ENV{DEBUG}; my $verbose = $ENV{VERBOSE}; -diff --git a/tests/misc/unexpand.pl b/tests/misc/unexpand.pl -index 6ba6d40..de86723 100755 ---- a/tests/misc/unexpand.pl -+++ b/tests/misc/unexpand.pl -@@ -27,6 +27,14 @@ my $limits = getlimits (); - - my $prog = 'unexpand'; - -+# comment out next line to disable multibyte tests -+my $mb_locale = $ENV{LOCALE_FR_UTF8}; -+! defined $mb_locale || $mb_locale eq 'none' -+ and $mb_locale = 'C'; +diff --git a/tests/unexpand/mb.sh b/tests/unexpand/mb.sh +new file mode 100644 +index 0000000..8a82d74 +--- /dev/null ++++ b/tests/unexpand/mb.sh +@@ -0,0 +1,172 @@ ++#!/bin/sh + -+my $try = "Try \`$prog --help' for more information.\n"; -+my $inval = "$prog: invalid byte, character or field list\n$try"; ++# Copyright (C) 2012-2015 Free Software Foundation, Inc. + - my @Tests = - ( - ['a1', {IN=> ' 'x 1 ."y\n"}, {OUT=> ' 'x 1 ."y\n"}], -@@ -128,6 +136,37 @@ my @Tests = - ['ts2', '-t5,8', {IN=>"x\t \t y\n"}, {OUT=>"x\t\t y\n"}], - ); - -+if ($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; ++# 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. + -+ # Depending on whether unexpand 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, $sub; -+ } -+ next if ($test_name =~ 'b-1'); -+ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; -+ } -+ push @Tests, @new; -+ } ++# 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. + -+@Tests = triple_test \@Tests; ++# You should have received a copy of the GNU General Public License ++# along with this program. If not, see . + - my $save_temps = $ENV{DEBUG}; - my $verbose = $ENV{VERBOSE}; - -diff --git a/tests/misc/uniq.pl b/tests/misc/uniq.pl -index f028036..8eaf59a 100755 ---- a/tests/misc/uniq.pl -+++ b/tests/misc/uniq.pl -@@ -23,9 +23,17 @@ my $limits = getlimits (); - my $prog = 'uniq'; - my $try = "Try '$prog --help' for more information.\n"; - -+my $inval = "$prog: invalid byte, character or field list\n$try"; ++. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src ++print_ver_ unexpand + - # Turn off localization of executable's output. - @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3; - -+my $mb_locale; -+#Comment out next line to disable multibyte tests -+$mb_locale = $ENV{LOCALE_FR_UTF8}; -+! defined $mb_locale || $mb_locale eq 'none' -+ and $mb_locale = 'C'; ++export LC_ALL=en_US.UTF-8 + - # When possible, create a "-z"-testing variant of each test. - sub add_z_variants($) - { -@@ -262,6 +270,53 @@ foreach my $t (@Tests) - and push @$t, {ENV=>'_POSIX2_VERSION=199209'}; - } - -+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; ++#input containing multibyte characters ++cat > in <<\EOF ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF + -+ # Depending on whether uniq 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, $sub; -+ } -+ # In test #145, replace the each ‘...’ by '...'. -+ if ($test_name =~ "145") -+ { -+ my $sub = { ERR_SUBST => "s/‘([^’]+)’/'\$1'/g"}; -+ push @new_t, $sub; -+ push @$t, $sub; -+ } -+ next if ( $test_name =~ "schar" -+ or $test_name =~ "^obs-plus" -+ or $test_name =~ "119"); -+ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; -+ } -+ push @Tests, @new; -+ } ++cat > exp <<\EOF ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF + -+# Remember that triple_test creates from each test with exactly one "IN" -+# file two more tests (.p and .r suffix on name) corresponding to reading -+# input from a file and from a pipe. The pipe-reading test would fail -+# due to a race condition about 1 in 20 times. -+# Remove the IN_PIPE version of the "output-is-input" test above. -+# The others aren't susceptible because they have three inputs each. ++unexpand -a < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 + -+@Tests = grep {$_->[0] ne 'output-is-input.p'} @Tests; + - @Tests = add_z_variants \@Tests; - @Tests = triple_test \@Tests; - -diff --git a/tests/pr/pr-tests.pl b/tests/pr/pr-tests.pl -index ec3980a..136657d 100755 ---- a/tests/pr/pr-tests.pl -+++ b/tests/pr/pr-tests.pl -@@ -24,6 +24,15 @@ use strict; - my $prog = 'pr'; - my $normalize_strerror = "s/': .*/'/"; - -+my $mb_locale; -+#Uncomment the following line to enable multibyte tests -+$mb_locale = $ENV{LOCALE_FR_UTF8}; -+! defined $mb_locale || $mb_locale eq 'none' -+ and $mb_locale = 'C'; ++#multiple files as an input ++cat >> exp <<\EOF ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF + -+my $try = "Try \`$prog --help' for more information.\n"; -+my $inval = "$prog: invalid byte, character or field list\n$try"; + - my @tv = ( - - # -b option is no longer an official option. But it's still working to -@@ -474,8 +483,48 @@ push @Tests, - {IN=>{2=>"a\n"}}, - {OUT=>"a\t\t\t\t \t\t\ta\n"} ]; - -+# Add _POSIX2_VERSION=199209 to the environment of each test -+# that uses an old-style option like +1. -+if ($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; ++unexpand -a ./in ./in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 + -+ # Depending on whether pr 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, $sub; -+ } -+ #temporarily skip some failing tests -+ next if ($test_name =~ "col-0" or $test_name =~ "col-inval" or $test_name =~ "asan1"); -+ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}]; -+ } -+ push @Tests, @new; -+ } ++#test characters with a display width larger than 1 + - @Tests = triple_test \@Tests; - -+# Remember that triple_test creates from each test with exactly one "IN" -+# file two more tests (.p and .r suffix on name) corresponding to reading -+# input from a file and from a pipe. The pipe-reading test would fail -+# due to a race condition about 1 in 20 times. -+# Remove the IN_PIPE version of the "output-is-input" test above. -+# The others aren't susceptible because they have three inputs each. -+@Tests = grep {$_->[0] ne 'output-is-input.p'} @Tests; ++env printf '12345678 ++e |ascii(1) ++\u00E9 |composed(1) ++e\u0301 |decomposed(1) ++\u3000 |ideo-space(2) ++\uFF0D |full-hypen(2) ++' > in || framework_failure_ + - my $save_temps = $ENV{DEBUG}; - my $verbose = $ENV{VERBOSE}; - ++env printf '12345678 ++e\t|ascii(1) ++\u00E9\t|composed(1) ++e\u0301\t|decomposed(1) ++\u3000\t|ideo-space(2) ++\uFF0D\t|full-hypen(2) ++' > exp || framework_failure_ ++ ++unexpand -a < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++#test input where a blank of width > 1 is not being substituted ++in="$(LC_ALL=en_US.UTF-8 printf ' \u3000 ö ü ß')" ++exp=' 　 ö ü ß' ++ ++unexpand -a < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++#non-Unicode characters interspersed between Unicode ones ++env printf '12345678 ++ \xFF| ++\xFF | ++ \xFFä| ++ä\xFF | ++ ä\xFF| ++\xFF ä| ++äbcdef\xFF | ++' > in || framework_failure_ ++ ++env printf '12345678 ++\t\xFF| ++\xFF\t| ++\t\xFFä| ++ä\xFF\t| ++\tä\xFF| ++\xFF\tä| ++äbcdef\xFF\t| ++' > exp || framework_failure_ ++ ++unexpand -a < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++#BOM header test 1 ++printf "\xEF\xBB\xBF" > in; cat <<\EOF >> in || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_ ++ ++printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++ ++unexpand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LANG=C unexpand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LC_ALL=C unexpand < in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++ ++printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_ ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++1234567812345678123456781 ++. . . . ++a b c d ++. . . . ++ä ö ü ß ++. . . . ++ äöü . öüä. ä xx ++EOF ++ ++ ++unexpand in in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LANG=C unexpand in in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 ++ ++LC_ALL=C unexpand in in > out || fail=1 ++compare exp out > /dev/null 2>&1 || fail=1 -- -2.7.4 +2.52.0 diff --git a/coreutils-keyring.gpg b/coreutils-keyring.gpg new file mode 100644 index 0000000..003a885 --- /dev/null +++ b/coreutils-keyring.gpg @@ -0,0 +1,312 @@ +Release GPG keyring of coreutils group. + +-----BEGIN PGP PUBLIC KEY BLOCK----- + +mQINBE58fE4BEADGS6VzDkx2OOQMPQedsmBtRs3S5sz9tzO51EwkS779js3Sjt96 +KlQM0SbwtbUxOFor42LRXJKUU9T/Jl3v3+onASvoHAUcuAL15WAhnY9cuQeFOvZP +/iy0I1+bV0CILrz364T6vL614obnBBdTg8ZqSZM+csRlpGwXJiuY6mkrsPLXakxA +35n/nAgQOcQPj36CuuvpCH4JKPkzklwUMqueDzXkYMNSdWmVnI+ZSfDmeiwzAbFY +tE5uGW+c3DzD98RGCLt3FLr86n24IDlaTZSsaWbTJVsur9s4sbp6rST3pspDSQYF +ShhJ5aqqEYIvPp5kXj2CZJjOFBnIkn+0aDSps+XrnZjJn/f8f9lIAg0/0JjmytHY +yopo6HFZMdtOvklmnsIuJ/fdyk7761+necYHf5dopVuv29PSu62+A/gnKGfGaqtY +AjXFfsiLp/+iTQ+LNV4hWFbFKHHZOn4G194pWl6nY1gArwQKPZ5p6uy5EXgiNPRs +C1CcuVZNJp1RiayhTI68uuI+cldBU6N7+yZKGhjDUQKjIZ3eDB8X7vsCC9S1GgvX +Hcv8mjcMcHtnoC0w0FiW35JYtAu9mY4+uQhoRPTyPHh+ufX+OdKf7q5BKCppY1r7 +HF1VRFKjSybhEwMeGBdj1EEY413/A8ynpgpHLosPT36n8HtAWUGu+TadZQARAQAB +tCFQw6FkcmFpZyBCcmFkeSA8UEBkcmFpZ0JyYWR5LmNvbT6JAjsEEwECACUCGwMG +CwkIBwMCBhUIAgkKCwQWAgMBAh4BAheABQJOfIDXAhkBAAoJEN9v2XEwYDfZ4AEP +/jr6zmXUVhNiVCtqiHqc4jOs1OPC51iEcMUwpeaEEWHq17uMMIqz+nd8B7CAyjzw +FJIW4gtwPS3uTsXR2+KOl1VnMS5O/M9suyG5eM+fpCWkzyTC1He/1M9iaRMGY8u2 +wOjZoeY40QFN5fvL/BuC8GLBefI0rTzMaYO0WFlVWTpaemj4pL1Z4JoQdmR49H6O +qI155jfsXuv2VWjN1NoYT8w3FEugc7rdNWe4dmscU5H54JEQMuFd34X7Ja2S9YnQ +OdqO/nVQGm3te2X6ElOBoA68HyuXcEozf0KgKkcPrBEV/tjQrzn5Mc7jOgeCDDV3 +7MFwBZUi+z69jjOc85tNYf/FHRfUFnBLPC1HrOIlrraaqydPfvHBRTybTJVhXlQW +b9kqfrT1HU8UGfwP+5cwTy2WjZecxvozZakYBO4cdcmsSNE5jM8Tp7EU7ktxPXg1 +IQwZ8sEFJN6HRhRVmhK1FyR1hrwdcvfYrFmoYbyWUCW1RNuGw3RXdjXjGSl6VxzC +vrWXjeiMyLQQ7l7IneFaIPV22quPi/NVJbNeT5DqKa58kYgEVASfZVZkL7S3PJvj +fEqhw5jTi3l84AHtYNNo95UXWQQCWhpYjZ3q61satme++Eth552VAGP+JK4634mj +vVViYmWAnjs0efSN9yCOWKDKBONviW5WGZwi7MVtgF6uiQIcBBMBCAAGBQJOhIiA +AAoJEH/Z/MsAC+7uW3YP/RJlgRTkRa8t0t4oK06zg+jSMMQ3ZFsiipQEBMzJfCXy +C9pG+gU/mgcOoqnpxY6iA9ufY0dLOJYhMPsSLtrkjwMAIU54UY+WRpaTcXB+5Zma +1OoA/Oh6wcZHy61PEUkSfoiQ8vtXhzqQn7PAUbi7ds5ecn0hy8E6KKEEysFt+Say +zrINiCeO3wr6LUqUtpxdo8JGaHhdXGZsk5OMARnYlC/rzZxFKsie3+FKO7KNFoNr +edIElFKdx6b7r4CXqfK9XpZr8SaM+f3wh8mBCK4W2Re50/6inHAnTYwW0octwr0b +AtlHOY2myauBdj+19IWntZnhoKxuhVPLaEoG8j26k+LIP6h8fB8GoRh5oUarLiCk +fahDRNY/bPFtBnsE6Co5OTTy41CFkGX0JbguTpL0uPQxygIKz7x29P509fMpq5t8 +z0hcVYJ5/cXiNjFLid2JsWugKAWe5k53E7qQKR+jLSvPtZ2oOHAMUzu6hOnwDY4Q +5r+j6t81tFAlS6P4fcpVU+alUwvVNdXc6MSkfmK9ahumjYnLKy0uo242U1wuBZgN +adr6pFxKrMiC/0PVJz+ZQOZU4OUt/t4E9KpyUEasfOl1z4r+q+6dZffRbrP5CCIQ +M6A01GRbEufrcXjgYnmaDncV8JnmLbHOoZ8WF+xczywFg45ULSt0N5ZiS/BbatuO +iEYEExECAAYFAlE+Z4wACgkQFg9ft4s9SAbl2ACgqTFvvpXJzTpZrKrisKY2i9RR +dNsAoJt0xI/urG+JIn5kUJobcPsZtY62iQIcBBMBAgAGBQJRY/sdAAoJEGiHnitP +7eG+NrgP/iKO5+3ytwRYwwbtQNROUQSbLwpUN2N3S3XH9lRV2NGEx5nx9Yn0l22w +gRMbULeFk4S1Ak3mR16D/mlnfPMyVqrJotp/E4rkK5OzjIsy58vL6B4PLgut2Xlw +Clg+XklxkQDfT4m/QtLGJYOnx/AjBn6ABu2zD4FWsn7hIMdXDq9bpr9IT96iqd1P +MYogglYK5OBFIGefjf+Sut7i3vuwJcjuNdL79tIbn5yple96EOL6eoHSRv5ndcoS +mxHtmin0lVeQ1ajoBETNh/E6/yItZNtc7BKbttYF/tN0GYpQB+dcCeiXLAOJ9n/2 +ET0gAWMP+kHzdcl3mdfw+KiZOK0gak0cu6LW+3GGAXXZkFYh7I70Y7K0wYNNgy3W +rzlISbAeC0zKOzpJJ2eQWJAs13FyinUPEyKRorRSubajbhJzHa4t3SwevR9DExnG +DL23UWreDO4ElDbvT3MzMA7ifaVSLFR/Rxu/6xsK1lPs2NygmGpdDnPjJung9CTa +1yyadMi3Cfgggu5IuUaKtzW61lbD8sMXqLRoFIIkZjcQagS/ybGeKIAedCE6pqMh +MViSIVi2G/F1wVaahfhjvaj87yYPxUuHq4hHwx2RE1EjP66a1IoR4key/eZDWfHi +th2VeeaVnma12NTl1GzfaEig3mzgtB7lM50/qJ7ml+MeE5agga7oiQIcBBABCgAG +BQJVfds0AAoJECFMgsI2H9co0u0QAK+EhLBUwJJ1XfuheL8pXSJ7FxaicSPk9dKL +Fbhc2oIAItqGSAsBRncYH8jYAPSwtCq1whATbyPgoEDm5G8KQEdAZ4bA6mhXw7Nj +UgHtkbnm1bIbavM/lhZLdNi+H0ZV4w5G4e47/zMLbwK84ZhiArRdklq58200CmPB +qNnfaxRxxkJBA6Bn6Cnv0FUSRvHUlSXgOw+pZXGNFZpzi50d38L1na7iCxrfyxH1 +sS3Nhn3zTf8BCKDcCVyP8UeBP9Fb2+fYJ/f3/KN0C12Hnbqc9WsYvFSYWq6u+I8/ +GP0oQohe3Fv5S1VEHWB1feCNmvVtV50J7hukTBojERhC07Z+2T5G2aw1Cc4zxkOA +uwOBTzuij53sErn5o+hca/pJTlXz8jJ8OxSFY8FT1QGVlLAN10yl9mDsdnZb2VSn +bQdqYG/qfbdC2cm2rCrhcKFpierXURLr14UC1O7tbDmLFYXDxvQfjtj9GSo4NHrK +wlTvfHi+3x6fGyx+Auulcjt65A5kQ3mycOc5paZhTdIKhS5mFdQoKw1Sg6RPiRIy +OH5fx8ob6I7gN+bcuX3r8KCH1FcIiyZd3WsVQlI1EfnpujkFo1O2xDVpm/D9IjAO +MRqKTtnHbCjaPUrsRRysAharr47YuzQUYGaMmIJfSN3kP4U2OukYmVFSUpxrlNep +M7LGQsmdiQIzBBMBCAAdFiEEP0srMOiHNvRbOiwMIhOnPE4lafEFAlimlJcACgkQ +IhOnPE4lafEZRA//bTNw4mi9B04yacqaFlJ5f3i9v0fWnsSXNEkW5wslhbjoD8Ab +PpVNrrw7Jm0YTFNa5TtnNc7fcnHNNfsL0LbtCfdrZOTm7vZstFJrASHam7La5655 +RgvTbozSWuuYrfLyKAituRmhJyv3ntpP9K6yUAAuJjxR3ny1sn8KNIFX7g49emlC +k5eIEujcmaVJp1l8wbnf/jioKr6QeXz0cxWUUFXolR0AUt8Vy11V+qRQb9Iw902y +2gmbMun4HjYEtCtm+eY9TRD5jY7hCHTYTFEfWITnGIRDyHyLIS9a0xql3W3EyWO0 +JkHNIm1ajqbuUp4IIxoZmIxNmEmW3aS8rsuIY1P0zXjj6j+GcRX8lZJOIhieBfWk +ku6dZwwtv9wF3K1UQzFwRsERqiwj4CAwlUy4um1eLOcjx6ge7Ub67FQCihx0VEpO +jnngjQN4clth8YM5nst/+lOFsZb/k2SHqTnpdE9pFl39aij5Y7nAI6xZL8xyM+CG +9tcFMXBrmyZAmD83v0N2PyjWuLAyY2b2SSYhOXIVfonHYSfuGw27yvn6mQ0jICZu +vdeZQASYgBAohMDXOgDgKdL6g143d96tQST72RflXAxoKTbblKK0kqxZnfdRIja6 +MTLstYJUNwWQsSD7bwcY8wnTXPK5TpPtBH4q0sjkjd1ZNNAQvbbowTlZ/smJAjME +EwEKAB0WIQQSG9otSstjYWs2eg5Y4Rux5BTZrQUCWKj25AAKCRBY4Rux5BTZrY/1 +EACrnMsYUnN9sc9qhy67pAMPy5QaGsYY5IMOnQlTcjXYrBRBx0kEWhiMrX4USqRK +Yj51J5U/6MIyeFbmDMaGrUQ/Ba9GxxjOnYAUri5S7lvtuYZGYsQqQc4ORgNCSRAQ +GMiB5Q+3oWbkaoads3ezhcE+R7/0HrqgxgCRg5mzTx6up5vrkBN8kbI6BIpgoPBy +AzTOul/EIkJuBYHg4IPt9dWOmbFbJyxMJg7kNwTS65GypIEiMeQXK4VzcdB6jr2L +Ju77Ia+pWyzKpq323swdRZtM/hHrGJrwJDbdKMfWxoWf9e8cqvO5hIM2mzchHCQ8 +7OQSnb3JIsHQIPHCxeaxzMOS1smRNbYu4/yY/MRcWaNiScuoMJqI0gVWd+XIScwE +PSGyKlncV8moki4pFNkseaLw3MEQDoxqf9TtxXnEB7ZduvR/UcELUB85lVjNnoiy +GjrcagTZ4jDISxADvqBP+a02GsY28dLOk6smqPPwezbVWqV+ABPeQ+bgPd313MGl +a22s72O4/nXzzt0rNgmgEIqMy0OkgmxAUBCSfcQp88HEnk/roHsUV4iYwAks2cOp +CDriBnwjIywK+hVq0r8nuBNRQt0P/Yp75ZITffPRrOLVXvA8D7tV+kIm1GrjDbIZ +OFCNpAUCHXv/cXPeUvHsSd9hmyjGbNN3UzpxhykiDF9GWYkBHAQTAQgABgUCWKaB +cAAKCRCZRTN/KIg+y2JSCADAOSj2N7T8PriPsuGbRWehb2zvfjQ1C/IiDIWf6s7F +QuEjfg4NuWUJ2rPl2bYFey2yzSx7Ld0yNNdzSRxng6QADHUHYAneQi2WuGlyA06P +DDfFERlWRv6JZgnL9R7rWHB+RAa6DnPPgpxifABv9RR4caU+8uAP24KHRxCQXPx7 +LfB8hi+G8G3UYbuLnO5FTTuCObjjSh50h8qEt0f5y65R4kDDA40/L26POJNsHc5u +EE9rZlh0c4AqmakRSmH83+Q6XRWOtn/zPggj85ir0gsxLAezZG/OtuAyXW+rOC0L +RJDJ3JaiScUC3xewY5L/7jgg9aTcvuwxKoLBIaHOYtJQiQIzBBMBCgAdFiEE+ymK +u+HQChyPpNwfqLUfXoAyzOQFAlimepMACgkQqLUfXoAyzOQokg/8CqbMll42B+nG +VDdSNFCNjhjhKYctR/aZa2th7iDRwsTFuqSVHbywRL0XrkI0YOOJU57V56fBY7Uh +kfOKc6oeL7EXxpox8ehMToWMOcLSvi37EGMmlGLXokM9bN1gxfdFIrZr1Ji1kBYX +hvSj2Fxxi2NGRp0uy+IIOa0vB29u2xHi6GWk8U8MBMn0UcP6H053Kk6tMsMDEhF2 +rSYGpvKFSWywuFuELosSS6jG73+6pg9fMWBTDYQyWFH8YRA9AlpxWxT29gcKaftM +SBIz86Svh3PZ7qOEDVxh+yWAQTVUTVuGzUSleDDuJt75QLSt+ZERS9iezodB6EOb +AZr6canAJGmDwmjPTLwS0E3U197QW6encv3qUSA0Sb/QyAzr5007d2PzkIk6wJq3 +SxBdBRqCjAyR0VxZr2kE1Yr3t5rI3MOFsVWIKIpmkLzmCSPuUGFTvOZHlYVaTOKI +x5ge8d9smXdHjpSF0iGl45e0u1UMDsiU9dpo++ygdZWAnMI12Md5MO+K2uB4gLk8 +Njln1duZ0MQP9M6swkiIwH6jig3BkRCIAIWCNhbScBWJ79+HKD4Swk92+vTKDFRV +lrD8TQlQSbS69Lbon4/v+NwgcpHRTigY5TZZ6s4DXBUl8OIkXDs2LHeboTvm2Zu8 +gX+uWujFHr0nJmvwI1P/ih3kYoEFqLuJAjMEEwEKAB0WIQS7Pk4P+lsqogxkAaHa +lBBIg4QoJgUCWKeHnwAKCRDalBBIg4QoJv+gD/9AygNKRsaxJ19u0wyLifpGOsi2 +a6mlmwZkLLYhomeC82iV4+7EeI++QFhLc+KlRNZtkQld9rmihbcJo9UOfqTwwG/W +bzSF/Ed0GSFzPtS6HDjVPTn7qiKQoeat/e6g+VmYoK765wLknj75Tq0jPltX0/Yl +78s0ZwMI+HhirTBreOS6AVPlS8wFD4ywe64PN/YjgePAEfiIEiYICXmwGUHjPBgK +a50z9VuVs3TRLo+b00N73YDEW8tlpouhETQuL8hAYhjGgivHss0DRnuB5fNe6FgN +vwretguK3uknup1vrvVvDXOUOIdI1UksplrJvDbjYrFJB+L4VSbyGk7Kl6oSGKiz +YRF7gM4I+hpXlVWSKVxEdUlA9F6KPm3iqM5ld6K3Q6rDuppO/2BaqlBhinR+Z3bJ +TLtM1uKh0IgyGUstEkML/kjF9wJcCC+z7ZmW0k2CdA9JyMiHDQdVblxZpUI//Yge +gA4P32X1OofAFX2oXua88qehbEY2uYk3OFsR3bJwbTn40bJkxE8072IpBozYzskg +14Q/xnUxXkIL1wqLU1GPi9l+kbuh2+8yAdlz799x7De/uZhk8IwOOC5H+2oLp+vd +iRXDLKU1sDBiVFRJb9kosvUj7S/a15My1eqOSVP5Fa0GbXNw7ndvcpybMoFqbVSC +lzjlN2OgZuXYEl2PU4kCMwQQAQgAHRYhBH/Z1lK/X9LsXxORsHmPHjXLTTipBQJY +qndrAAoJEHmPHjXLTTip6uUP/j3RieBfyGnau1a4KClaXlPGHxlu9M1fFw+aRqV7 +r8ALWuQzsKlh8QlPEWhtqkty0BFXAhzRMYJd3G/5j9kaoS9NAeNpJpbZd9Gz25ZN +k+3PCkww4XthvKNY/ONwnwGuelLpIbwa25+f7Oct55tthkyM2TWXlwkRVNpeMNhk +uUkP4+gFnpvtzUTFqwYtaEtNY3UFw1CjmcA5xTGL6pIg2FKf6m1YyJJkDLpU2/pB +Ca8Mk/A9wQZ/9+M/l8goNq05vsQsp8nlh9zo1XpwWYBq3OwPQKDt4d6rAwU+zMHC +XI5MP5B2g2Pj+M5bQMNOxa4sLw71ALaCYETeHHi24Kp/ZhOWsUomwc+v7t5gApAk +6gjxbGklMWhdJuk2I+lv796J4cFI4VZpTXAygMSnnlo+GoMiqTz0C9eElZlp8z/Z +yy9g88Z8fBoAY1SmrroaxLOvlFKRG92xhd+JUh0kj72loB+Fozg5HV1OqkF6c2us +w3XCoIcht87TxmZWPTXqXdPXrStS74g59vrVyGvsNN2hG/l4dPGZSEV63Kn2eiti +Of3JPYJcy0iQpBBnhhKQwPVNgWso7NxsNsVYOUZCDeSoCFEvrdUFSr6q26IBBLcw +itnF/KEX3MyJLGr1BjDF9KqdP3+YL5Eqrq1Zn7LtyAbC2Odo4KY6vOT3SRrSkBRH +RRq4iQIcBBMBAgAGBQJYrLQ2AAoJEPaR/VwUa1eD1d8P/1qcubzbb/p4jpnrZsXW +i6+CAeJuA2f2qyBJtdVPhiz2swSHMNIlhVWh20w4892yv7Mgafj6i3Zoben088Bd +BTvCUOXRtkepCSTLTg1fTa/l3a2vNxLyK3LT6Xf8KuY5lXTH+XWn7vG/N4T6jyd2 +MQLP9VUltRkk7aNarIZvoYMd6/JVqKVhvxg42UZmcjke3PFKiHMIHBVSGBu3W1Mx +TDNgVZqTJlsqvfShwoBjPPYLBpSVZKHKgjirsDkZTS+ufpVmt2rzlujeVyC6y5f4 +subOde/pxGnTT+sMJENe/3uJxjUIy07xyXKBRnhpPxXbpTafZCcVc688er0CLRW2 +JsL9aEmEM0FV6HlnvW4ivoW1v9mSevAxe+KvgCO2cU2+HFqN/tCtxnr8rZ2HIpf8 +00cTpdvIn7wibGP9jfwMisD2Mugx28eLrZ+1sNaRLwVmroedjo9NJr2BiyPozOEN +lGX8V/RxQLaQfiHwyuKVpxA8rlx5evvtDE2d31ekVtdLXtN+GmCymnPhu1KbD5Mq ++Xk+yj1t8tdMD+SiFclz1uVeAOGpX5u7GMIsy4W8yoB5JlrwrsFot6UBaVZjAVHB +XTdMvBGsfxmimO7d0p2tBFJ1QV2lAafVhVIklCT8zXk4McqqtWxXIKWEB9dfIpbD +/A5MPtu7X91BTISC7SmRdBjViQGcBBMBCAAGBQJYrnXHAAoJEBzIdvEMrJ+JDgAM +AJyHN3j+g47bSERRxLevoRybp8/BoRfK/OjcLRxhOru4prOAiJEfNo77IbG9Quz3 +aBn7vRDh44BxXIR/NjI6kM3hsN40BBDVwfeFEFGKciV3cjCBqlqnhwt4MV6iDoGQ +1CkTm4LZQvtjQN26PAXUxxl/GO39vze3a8z3QP9BatZ+KrLOp2u7pOkwHNkY3Anb +/H0AUq0fH2Dq5omDJB8R54jlHc3/ZrLvujCVAmEuTPxK6LGl5xg4TaBtYeUgIki8 +A9iwrcFgh9OjgAuG1PFs+6RroE+nVPm/ZPDJ5l45ZHR4qQB52qp2lxf745PlSHj7 +23d6ASx/I8mDZ7bPqk2aCKXGQqkZ31b+I+Ut2ru2nEW6JAna26kgBMhNrINqLNxO +qPXjZHqZHG1amvlTAwGpAgeW5WBPvNjFn1WNPB1+9vCPTSwkWLR8dnzy46Rsfohk +RAGFtQjdccBxaikRHuUlIUI32M0WjKCP/sy5nVLQKrX9xqkOj+mSblmbS+u8cmIH +0rQiUMOhZHJhaWcgQnJhZHkgPHBicmFkeUByZWRoYXQuY29tPokCHwQwAQIACQUC +Vp+cpgIdIAAKCRDfb9lxMGA32UftD/9jYqsCfNAzb0vhDOaU1AchzaQa1pIKEjoL +6d4AMeXFSBpMi4nYJpN+rmM8DAzcbenBcSoIqecdfENp3mY+hI8mYdnMiVpldsro +EAl/SDxY6//pPd0Dnmoe6sNodBB2uwHxhQi9ubz72iWX5WiKP8+OUAj91cLMl9nK +IYfcHy3iinSRqT02JP33DGDwsHCoAMmp59g6AHnf0sjCtZEtK79MtKiKTkUdMazP +VGs81x1jCO2kvvmy0fDZxkGuyso0inae2hsaMSqqoga5lC0jQanFIXSEkLZgJglj +LmiWPO0IGHPFth/e//51atGUmpdd2ufQ/QVoxSnQKRFQ98eO/SQ75bO5vbE8dGv8 +oX9S3M9NjKOY9VnXC/JDyMXt2aMDs9tqSo22lJuT2Wq20wM5hlszxKI7c9QphnuH +yPNtszzXo1+5/UEuCNIQoe59MoscGmx7GN5WvlENaixGg7tzpZ+wdftN7BUcpJfC +gsEQurHzPEIomlszp3xraX0G84plClas13Ie8CIVM7UPbF0Cwx6XwhryjaDTkq3f ++mjQXtNJQk487q8cc9dxplslXiDqBYVngV+oDKOjrqc5PXSQm2M8EYRn9SXuFnT8 +iF5SkuFYtgOEj3KNZ04ZB1I7AQebylS2LGwWan8yWJSAs22eR9urWBVpmre6GUGZ +fo7YBdOvbLQiUMOhZHJhaWcgQnJhZHkgPHBpeGVsYmVhdEBnbnUub3JnPokCOAQT +AQIAIgUCTnyAtAIbAwYLCQgHAwIGFQgCCQoLBBYCAwECHgECF4AACgkQ32/ZcTBg +N9moHg/+Mjq/O1RnNg7kdUjRK1wOflym7itgE8kq4G55EJvLSxo6wIgd7ZKUj+cv +X+iXQpGRc3bicpNTsKcW6EjDtyg+VCSWD7qJ3EtwxVf9mN3bIqWSVwP0k8kc1N+t +p+L+/9jve+h7Hf7rXZoNo+l9h0/AIIr9YyM2r1VtiAsMNCfD/Ssvc5Yx4fZHR+2V +kOLeVb2lqdYVe7ZrXDt8qkdBHMCtxm+9jaY3pZVDFKk19NeI74Vzr9+mYn0I0OZS +0capUuG7+a+FGI1Dx2jn8uL+x4eLDdI3vvr/vGWparikBExGq1pAKWm5gBF10CDP +4nx9+5hzjPipvCuQerRnjL3FQyXa6E/GpCp4Mk7SdB4zML1CmnYUzz4n0TcV5aFi +yaMQPk5TByxzYXWUqjFJzFwmU0z8Oy/d64ZMGLyAxCly6gBc/AmXzsUhg2hJB3nG +3JRw2WmpOIeOdYn6S3onfAFT1tGo7kWNIWYxX5fT7qAHVlnAmgjz+zvfB8Hwq/B0 +FDZPzgwYX4LeRMCj9VDspoCVnaMd4rWqbH2lKUU/k0SFRt3iAqjvT6WPbJIDtEF0 +ifU2R79laaZZU5rbYWZC52AfO7NdLP+7uwxtPYyOdP/4s0HS0e8WDuykdZbTaC9K +HbIiKMW9YXQJRo6YupWJWOpFpPkvx9ttcQQ7C5s8YFjVR/96dYKJAhwEEwEIAAYF +Ak6EiIAACgkQf9n8ywAL7u5OexAAjb2+LR8Pa80t3ooladI3Q1icII1hvfb6C+KB +lzm0d8nMNqcjpPdkbppcVmjqbF3xw70uMnT9m1Y5NGMzJEZiNv6VWT3/m+VJ/aih +ci/lccUA46pL6Edxw2F/l6ftEOcPRAefNvszCQPNSVHPoQ1m+HuweVgYs9by6s6E +FFCG8BbqxpAxGxaByoq7ZtlxfMAjKHSPCJSJQTntj5dz79+K+eI8i6bMP8isPBvu +HAT8ZJ8mn2kQTEpuMIyCl6GTEigKimwq21tebB666Kv7wwS/nwCzceqyPshlrXQp +YYWoKfLd4SrC1z99//H93/IkN9dZfDJaWvMOlgO+/Tjnlr0tnVsIafnYaOA7Pb4c +QAx/tbPeiSH3QyRQw4wD2T1CaoLGPLaS4aOCjJXbNBPk+44suO0gUkU8duBwyK0p +fjFAJQJnJnVEsqWDh0KustQW3jdPvlqEe1eWmhnivXnmtvBk4U2BPkOG/NC9+r3n +xIWnrRhINWZLT85wM47WtQ2l5BRK71UKrgZDixOIbAR4H54FLa+vrwub6JjpOrQM +MYaxA/aiEv5byP38nWVvWRSaFDC+QpPyOHLnzBSoxaAHvm8bsNR+4KALcL4zyrUm ++qqQWbaOpikgBDhYyI/qteW6REZunofpkrpXZbyE+oFUxn7Vwz1ivEkiYPrEhTWr +HomA9eSIRgQTEQIABgUCUT5njAAKCRAWD1+3iz1IBic4AJ0VP0N+M3OHLK84zhnb +r7NV/OsepwCghhSEutr+LFoP8SIDFZGyGwWNZkWJAhwEEwECAAYFAlFj+x0ACgkQ +aIeeK0/t4b4XvBAAnQEaY8PFnZgegqdsNakq1gLr433h3WwQBGzba9CHhElS7VdF +c3+VnZ031zRXFFMWSFOovvQpyuRNsuGvgmvlr93+/OgP2jBZbgPFZy0B0KaTpvuE +3LD2XyPINajejIVJTMwNIuD2TTxz+zqRcdie4ExOdSmWHmjGNVCt2W7Xf2ZX18ex +FdH8jOVKtI2Hdm0YdfgNrfbcSLVgGr5MJMvaifsgGyQkPS/iDXVvLZxmSJiloupJ +ZfXrCcw5mzd8qodWwC7VJbZWIYkUBo5ir+tFAr1GuxD8D1l2U1RA3jRIgsmjd2CD +S6eKOmBXR3UVxFypOkHqfsHlST2vzTpvWGhzeQXAbo5ahjtI6m2c5mn6Tvb0V6BA +o6Fjw1id/iOWmfUSyI9byZkC7HJD/68jgvFha5eXixSo7v66MFptGl9B3sWG0gf5 +iSMbIj4EFzuBySv905kmXJ9VXnawQWalNC7n5JvJkIwAMC6bNU7aO84+9K7kh7bo +rGaBkiYfD5W09BgTipJAEgq5cVKLOGKaN47DhSszu3QAXl6Wk/VL/RTJfzWWGU13 +nZ7UY7f2uavA30mHOznAn+2v1GnMwq6ZhCQt2Y37YgDowBSR2PrFFZJOzZJhd6GN +5XWjq6A4QKZouIK19zRAA2Zsvi1TNDzUw01qGT4i+hsxPKXgEbp883D/ZMuJAhwE +EAEKAAYFAlV92zQACgkQIUyCwjYf1yjk7w/9FyPk/VEJsUYvG6Oap8Qh+bwCQRRm +vApZKVurqkMAXntN93GbCudWyPdt5igZDQf7CAHobvkUrn4fIGSMAUu6jmy7qoFf +AnGNKDMWLVYIUi5T/Sb5WCoV6DGpRJ46MjEkbplbnvQyemVsUVQLkB5GrnkO1WRV +UCk3vnsgSqrJ7B9HyLHAjsbEgm3L2OWe+1Nz9+Evg7etyVHyLLN5N2pMK3/ZMHKf +42p9SEh5x6JL9YlcxW6EseOnoy64MHDvVvnXnuUWxuTEsEpytvRXlJ7SkG+2lLcn +nbPNPY3zWfjOEI7j8RvXQJGU3FKt7NZNMGe/jdjq5nF1R5QtilRBnpVFboVmkWNN +/eiOT1Xy9/PEZKe0GUHLLh2t2ffI2du4FPKKmZ3i8sl2VTh70okKEO8zxTohs+7h +1bff6XgIFCqzpzVoiIMHLloN/Qxr27lywFzu42UISXIJBW34nSzJ1SUkaVdAdkE8 +TtXEk0xHmMkATTWTwDHoWmp0E2QcVugFpUlw85Dj1FkFNf6IvwaMw0wpE9aP9IKM +oPmKuarKzC1PUiGqm8o66Oh8I/ycQVv70VgvazeUY1f0GXV/49nT9tyj988/XKAT +T3OkyHmZIE0Q3HLlSK98bN1ddlVn35IABE7LSa9aJWN2QTOU0pw6D1Gc7pRD9smT +HAxs4LUP8TXOkGWJAjMEEwEIAB0WIQQ/Sysw6Ic29Fs6LAwiE6c8TiVp8QUCWKaU +mQAKCRAiE6c8TiVp8bY1D/476x3jkMpbkhg5wd6YlVH33kvxocqaMEdt9jIMj/Xr +xJbMZKQgHBAESf6XiIYqLRZOsIcdi8k/0goaqP+HENnUj/lK/vBii8P7Qtcct8F5 +55UEDC6GWCFaqEZn0l2qgbHjGWcwh8toq+NZ5VniPyhQErm3b7dToauqE7sOoibm +/RpkfwxNmtySd/nmmyanP4Q27AgZ7Csq8h68P1wiVTAnOuBJ28CW1z5XsJ5YRTq8 +ae/6kJs7g9eRoDtMkUr516EYmui10khYFUaZ87KjpsTXpgfiHUTtbbW73yGBdqwM +QD/s10UUCrlv7j8gJ1V8Z5NRSda8kwDyeorziwD+sfGIuxK86Q7NA5tjP9QY5tJA +m+yxgiwcv56XL12p7G82L3WRDujVm4pDs5NGFRGQNsmkb1T9DEFQMOnsBgVWH4sl +sjPsN51YNs/wHmu0jOv3CBbVDJAELxjqIroTZuT1yjG1xV5maPTqppMr3+gT16eR +SZ2nBy4ev8rYM4N4K9EEBjcbXWLNQOYeger1vz5S0bEzUuGeHY4ahMNB+dRTf1eN +UjRlhSzddlWpoNMbb1+PlYwtcTEIfh2vs2iJEbhZhuETVFye2RmBQ+MQ6oXDGEcg +fwbwrbyW0X+Z9KPIDhTRMrdXJiBui5RvQ1AxAuQ3sZglw/xySSvztqf5InRrt1lE +N4kCMwQTAQoAHRYhBBIb2i1Ky2NhazZ6DljhG7HkFNmtBQJYqPbkAAoJEFjhG7Hk +FNmt9cgP/2owqkabfUTz1Gf5BZn8cWlcZT0ePFJuXqceoyZfPj4VhwKSyRiXEu2U +LGi75TSUp1ESok6w3KG7chq2GoH2EITysqUhpcroOTAT5qjWGwf1WEP/zEYrmQb2 +ayFRBHdcoNNgRnJVd2HB7FlHF6fg5aPrM3P7o8ajYDneYSDwubajN2xnUsFV8yYv +liNV8DtFOsX2AHSf9ipsF3P5ArsjRJoMI6Z/PgZuECRiya8qzbxZoIZGgT+khcvC +SwxsX6YXmNImwhGpugUnSrjvBPdiyN4CilTOdaiEqPLwFDpFWEkByx3ewfJYfBfH +EOzTdSgtPEXJB0Xxb7ge5fpBtFunI45bPRwRIT6EM29WcYWwCp12HCTt4N2LHwu6 +h+JL3ikFucgtJsSO68h/oId7THD24ft4UpIfBR0zZ0/i+ier3SAB/gN0xE4Hpy4Q +YNcl9rkt/ApuHX2hQqcN8woUhGV9HV4n07Z6FIqs3qSj+o4w2hV5xaEqOiVoKdMC +p7DCECjR5ACmhvtLTI8ddS/2rXPK/8Kttg4e74LysK5WOSbCiX7M+GjNIuVh7aA8 +BVR7hLjQ1CRAu/c0/m6EsTEViHuNZjX4deJo/c70kWLbP5UVN9yXrJjwVXwBOz1O +XiZzzJCl+ICT2fu8K2P7nL4yqkSAuMZHz1sQxzIvLs8hjbMYbdqMiQIzBBMBCgAd +FiEE+ymKu+HQChyPpNwfqLUfXoAyzOQFAlimepUACgkQqLUfXoAyzOTxgA/7BZpk +HIlTGVobZ3drVXXLRVdydLbypAJ2d6KU37hY1xuCM1bQ36H/hQKtHBgdTVc87IvB +0iZTKfwxPHBloK4MBDl0zj0Nz+Y6OK5oaUccDCSIDyBuMnkwu+U3O94mWoftQZuB +FH9urpElmgLftknKE1PMsPT2PVEpLVKX82yXo28+aAhXjcO7W/FYQhHX5vqPZmjC +uJGS2DZJHUjF0Vem1Eh2a200+t47JfFSMRSFBm2S4Z1Bo5UUjSk83yJ66tCynJ3x +D5vhMTWJXRLhZd7DXjjPBMrp6MqDElL8tNF1w86Bk4kIwX/hMre6c0/+4b5rJBwF +mjRkAwfk/YLJPz5dfoMiTf0kqj93F86BKDnYZNQ4L0Yn1QWWKJSEf55ldmxvaxwz +ZE3NpOALdBwkG7yjhttsHIe5kpWgluxcuYTvWpX7KGIZnt1qSl+Cv0VAOY7eo2Zl +KTtpqAQeFqtCZL0tcLxj2Ce8LqViuraKGxNKi13FtpS74W4DgseXv8tnhdy0uqlP +gRQ2WCHpUhXUlU/KaXtXXmS6oRFnCzXikYXzH5ZFTHzNthg1gO5Fk3y2B+5eL71V +SHDeIpi0jTpiO3Mav6AtVlw6QRXXfn61cdF1M37k1XA5lFPb+ifkV0sF/rkFE5NL +r0NAFqcwB3CE7K0fgOidFhdnH9zi+qcfCiyMjpGJAjMEEwEKAB0WIQS7Pk4P+lsq +ogxkAaHalBBIg4QoJgUCWKeHoQAKCRDalBBIg4QoJnzFD/wNhcOyJURvQtQXcys2 +bSw93rubuZO2OUpIgs6CCcZgCKt4sES9Xv9Qt2qRdk6GBgnlsTdTfwDWEDla1NYf ++/894Kf+3dLhaiTmYkWVh3UhysE6rihKZ5SHeriNCFCyaOvflOfpGQn20TX17I04 +fLBPQ2tZLIZYELpHHr5OXDm0YiBR+1Rc7mj80cTdw2+1vNa1p2r72n2GzKz76Yl4 +BI7dWud4GAEW26yrwF3VtdGFacRcDsjSM5rR5pxREY2WGzONCCD1yuaJUqk8Q+QK +8g/2PybkAUJpzmNzWqgsn8FhPESfObl2FPuIbxIjR+N531QGeU4HcH62zJeJjCdR +XxJk+k1VRP7SIIg310q6J4WiHa6LU79BVTFEV/0gyHh8psLpySr6nJN9TAImdekd +2+BN6xdWcub6/JJTdJgg+g/VuD+2vUm9zPtcP7nnpadqen6k2pobiDfuGepa4k7s +1jdgSoyKdgntJNBEpBCCx/fQQeXlR6kcscjUP1aMa+XIgpeZhyKTWWcGfbzsf58u +YYOP2nMn1GvPvoKcW4AfbPui14eNh3m3hQ3numJKBZGLzBASJsdc10CkOJzLq448 +nhdJTp8ZLRGYl9mEbpVuHNrYQnxYe67OtGS9Nv/DlAJXR4fUiX/Yq/Z+w5zz7HMK +Pbu/XhRIZcfJWgmRkgr3DSwGdIkCMwQQAQgAHRYhBH/Z1lK/X9LsXxORsHmPHjXL +TTipBQJYqndrAAoJEHmPHjXLTTip1XkP/R2nPYovKt4/ytjOMRDfO7XSzpUn2d0g +hmKRn0MHe21n3IjBzDG+BapdTMQCOc4Ucs1UicPV2lxRD8TQa8hh1MYCp9gkZ0Hx +I9R4q8StipyPLq7B5TQJ4tsHqT4Vc8reuxRInV/2XZ6gdr412v9dsK08o9lYri59 +mv5YJaxZmdov5555oK0ieMAbIRXiSqSsONcA4ph/MPXpVRXZvmu8+IhKJZbAd0cw +iOhjTU8z0qCBcU4vYB0nxwp2AWbQG4QDpk5lTp40Tn7A1dL1XUbiXsK9h2jAF5zn +Rssb+drhNeafoqYfVRsB2ObZPhfqD9nq6isbj1ocDU1nQLOrFdYu1o9+JgMFs6F5 +NvavG7RY4RdVLlXDQuoMiX5e1PyGsBgLliy4Tz5gogKtqzm40nV0573pcEkUR7Um +rNEzEuPoC8PFr7W8lYEHx70Yhql6IZ7rGXKDQNBWLp4drmPKajhdH8xPOKn1Tocr +qdL8hkzWh6wqLcSzwhgR14/bjCZDj3AJr6bRdAAbcE1xqWt86XiJRM0upe0j/Q7E +s2eUybhUb/YPSe++llkUsePqvLGMSY2nUN1lwHST1/yI1gjJ0qTSdrHUDd/V1KkU +SY8CL122N61FoSAEy2Tk4hVNrSNEM0DUuYXaEFZFazJT5/QwfmCaE7lBFzHFRQFs +mbsPONxL6qjFiQIcBBMBAgAGBQJYrLRFAAoJEPaR/VwUa1eDkbsQAKFy6zUg6GQz +i3pSqoaWvwCh0rdQzlQJ0Rr+1k70AnGvGnPmtFpceT8AHsJkzfhH4AetZLYeuOpf +FlcMca9267VdyWgwInob8fcvAURW1ZN4qn8MvNPOBXudj5W5+8XowWmDES4qNr1/ +2Oj4IgHDlMRgUYhsql0ybYarpfZdRxxKKj3ZW4B55Qqds2mG1w40zTSeW9ErXQvJ +EYkqFsAhEme0Ii+tKP1oM/qRrHuCfKiQw8Zc99v0uU19KbdD2B8sCsBfgkIJpGny +6ne8BuNAJRDJa4JhzyRu0Aw7f+U/ewn4T+GYdzgsqnsqH6nEwEabeHUtEsChXxZp +7mu9nSww8fJUEgHuTonr/w8UcMtB7HVwhQ1/AuFxzaQx7uKkyU+uyJaElZ3LD30O +f20p9Z0v6LXpyiqxBUUytoPCsBtRi2aPQKvNmnkPbtH4P45nz0Nc7CVaWM3tvAGR +53WQMxowHcek/J3mtNVprhG1gn5V+NnF/a5cjVqGxQbs/G7lhqZXYBNeflW3mUFx +7DaO5C5KcqjJBN1h9W6a48qh0sqyIbuBFlWJFNdizV0eMi1ypsHXKSZcl7SZ7PB2 +QGMVLg6VW0RneL7zzpoaLHaey97bxeccP721rA0/6w5qCE+qlTUXgV5sZSXJkj9M +wwpVQWwqa6q/cG0G7iFCxbD+OPZ3/9jZiQGcBBMBCAAGBQJYrnXJAAoJEBzIdvEM +rJ+J7Q4MAKz8ITE6nKeltOLAJF3xHNNcvyIHFLcOF2BI4bJTinMS7hFwEM3tg8+s +fnClHe7Lu/YpJdtqJ+jz8+nZMEF9tpS49C4bA8sPDyBHVqBi75xivKDSchnogPql +jctZF6NWbOt3Bf21DqbJFnrrtg/aEDrHQIDdXZUIKM66artlELC1XmFUnzfUBYNB +vksoPD+ehG9Im4ugC5kQCGxMNDjHXGyw+DzSm5n+hyEtkjnOPq1x2uPaELrHweMZ +c06ivHndOBp3vU2EgkyuCvRebc4OLu94RSel/ANv2VRdt3ryRQrW5tqxQJhEwPLW +fWqNTmR3vZhuUrY5Bk/R6Spn+iNJE1qCUutbB89aIeT9KMV5Dl0Zes4gdK7PLnLJ +5rjEMoVvJ1Tdl4LUToKZk+7el+2jEMZpkv5jnXkeRqMZAB584wWVOA7+7pKDUGL4 +r7RJByaBz6wRFCGmSJ5DIZQ8HKSeF1ikCwUHqVDYfAWmlyR/t7ZH3ZgUT1ezi67/ +PLQrM9JPbLkCDQROfHxOARAA5hb6RwSG2oH8LMWk6rmPthWH5IBE8yw4InTPpsA8 +V7LyFlNUOH+BuHI8mTpTHk4aRfg3h8wxqw9VfnncWN/H69Y6bhgYp8XZ37esQjPr +kujaQ7QaLp9EB++96AvF+5pTvf1eBlkhprMXUolw/D3UpGnC6uXW2iCjKEjt4HGU +G/nJQum9U9fcmZJWrtKFOW8NK/DVJ3iIdh2RmR+DceBDXUJF2qL9DEQvhEDAO5uY +glC8CwYdHwbdQaWjgLyDMWjr65SQZGbYJ1e+ZxPGGpucfQR89lylNaZwIg/HkFgU +bIvGnezleSwfO93ayQ34HVtpecr14TMG/jouh85xCsbsX7znnTLtCKzti+EkWRXa +NV0D+FvaPKo4jv440vgQZajcPzD9tbYWUfylpg83URVaQqZZglg1gLPU166vkB4V +/ov6nBjQ+Z6YxJsGvgPVhfBZth8IrckFUINyH5JKAAcwPZBtKR0QfUSHW+SxHer4 +DMLHpsjO39wHO9CIk4EcbLYUJwoEYlFpcnNWNYBwjLqAWXuMA+mE2fX/+NoMY1/c +rOZ46y3dLq0zJfD+LBgORx10j1fFaAj9j36pg43DUewZSwLtBhlYJ/SExW0Rz0xU +MU+C/4EJjy7+3ycLV+M8gnJGVwp2+z1H1ESe5bH6hSgARqQ4pOfP9sbM7sNX/y17 +KMEAEQEAAYkCHwQYAQIACQUCTnx8TgIbDAAKCRDfb9lxMGA32aBIEADAGhbCehSj +Wv8SEw9gUpN+slmIDBnZ7uqQgXjWO5OnG2TrSJyPNAwfk6ESY6JeoGuiASL3EpqD +vRTVsIvDzzqhNBwVa+mi/q3lof9yNs74dmJYsH0P20+9lVzNfWATWUDA4cVYBvON +BloCK1cVvn9zqFvfjFBcRbZskcvMBVPxO2Fv4xAzX+omPDfCnweY8G7i71Z8Nnl/ +HVkSZMI9uXrtcde00oISHf5xUebJdx96dxnUCDLPUwPiIxxYN44KvIl3cnIB5qwu +BV8F2XXUtBdxZDJexqsCIoAD3rhRoWq6E2fRJKeqt/4TmxwjsJ8ZODp+ilXhqRe/ +shHttoOvbo5QBZNZMujxkqxXeu+j2E3Ry5mSiGX1SewwbT1iUppwGI15Uwhthhrc +PwbtWxxIyzPBU6awwlrTrYxNTB1n7WM99gcQctLWZpWnEaoAnEmIEcPjnM+c2NRw +UJmE/C5h9intY4fOa2a8hpUPx6UbMkfPl0bkIA2cduvQtAFKy/G/Jm4H+0trSmrD +c+o+rl7v9sMJ9wKkMUdAcqUgNP0TEHzDPbzvztcKBCLnNLoUTKNIN4eNJjMGk8Si +/OgiN1NKkuVz7I3i916mVxxlFjKEyLYU4tYYXsbB+ZJy4dTP/YWHbQulJYLgju6Z +ELphkzjc6eM3CaOZ73u4GVXotheeUabUHQ== +=drvb +-----END PGP PUBLIC KEY BLOCK----- \ No newline at end of file diff --git a/coreutils-python3.patch b/coreutils-python3.patch new file mode 100644 index 0000000..447fdbc --- /dev/null +++ b/coreutils-python3.patch @@ -0,0 +1,65 @@ +From 8927d505ecb5334f09c48ef98ef1f464f581d0f7 Mon Sep 17 00:00:00 2001 +From: rpm-build +Date: Tue, 2 Apr 2024 14:11:26 +0100 +Subject: [PATCH] coreutils-python3.patch + +--- + init.cfg | 4 ++-- + tests/d_type-check | 2 +- + tests/du/move-dir-while-traversing.sh | 6 +++--- + 3 files changed, 6 insertions(+), 6 deletions(-) + +diff --git a/init.cfg b/init.cfg +index ac05f7b..26d9516 100644 +--- a/init.cfg ++++ b/init.cfg +@@ -601,10 +601,10 @@ seek_data_capable_() + # Skip the current test if "." lacks d_type support. + require_dirent_d_type_() + { +- python < /dev/null \ ++ python3 < /dev/null \ + || skip_ python missing: assuming no d_type support + +- python "$abs_srcdir"/tests/d_type-check \ ++ python3 "$abs_srcdir"/tests/d_type-check \ + || skip_ requires d_type support + } + +diff --git a/tests/d_type-check b/tests/d_type-check +index 1a2f76f..42d3924 100644 +--- a/tests/d_type-check ++++ b/tests/d_type-check +@@ -1,4 +1,4 @@ +-#!/usr/bin/python ++#!/usr/bin/python3 + # Exit 0 if "." and "./tempfile" have useful d_type information, else 1. + # 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 +--- a/tests/du/move-dir-while-traversing.sh ++++ b/tests/du/move-dir-while-traversing.sh +@@ -21,8 +21,8 @@ print_ver_ du + require_trap_signame_ + + # We use a python-inotify script, so... +-python -m pyinotify -h > /dev/null \ +- || skip_ 'python inotify package not installed' ++python3 -m pyinotify -h > /dev/null \ ++ || skip_ 'python3 inotify package not installed' + + # Move a directory "up" while du is processing its sub-directories. + # While du is processing a hierarchy .../B/C/D/... this script +@@ -33,7 +33,7 @@ python -m pyinotify -h > /dev/null \ + # rename syscall before du finishes processing the subtree under D/. + + cat <<'EOF' > inotify-watch-for-dir-access.py +-#!/usr/bin/env python ++#!/usr/bin/env python3 + import pyinotify as pn + import os,sys + +-- +2.51.0 + diff --git a/coreutils-selinux.patch b/coreutils-selinux.patch deleted file mode 100644 index 8274a23..0000000 --- a/coreutils-selinux.patch +++ /dev/null @@ -1,120 +0,0 @@ -diff --git a/man/chcon.x b/man/chcon.x -index 8c1ff6f..c84fb96 100644 ---- a/man/chcon.x -+++ b/man/chcon.x -@@ -1,4 +1,4 @@ - [NAME] --chcon \- change file security context -+chcon \- change file SELinux security context - [DESCRIPTION] - .\" Add any additional description here -diff --git a/man/runcon.x b/man/runcon.x -index d2df13e..5c5f5d8 100644 ---- a/man/runcon.x -+++ b/man/runcon.x -@@ -1,5 +1,5 @@ - [NAME] --runcon \- run command with specified security context -+runcon \- run command with specified SELinux security context - [DESCRIPTION] - Run COMMAND with completely-specified CONTEXT, or with current or - transitioned security context modified by one or more of LEVEL, -diff --git a/src/cp.c b/src/cp.c -index 1b528c6..25dbb88 100644 ---- a/src/cp.c -+++ b/src/cp.c -@@ -203,6 +203,9 @@ Copy SOURCE to DEST, or multiple SOURCE(s) to DIRECTORY.\n\ - all\n\ - "), stdout); - fputs (_("\ -+ -c deprecated, same as --preserve=context\n\ -+"), stdout); -+ fputs (_("\ - --no-preserve=ATTR_LIST don't preserve the specified attributes\n\ - --parents use full source file name under DIRECTORY\n\ - "), stdout); -@@ -929,7 +932,7 @@ 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, NULL)) - != -1) - { -@@ -977,6 +980,17 @@ 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 ) { -+ (void) 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/doc/coreutils.texi b/doc/coreutils.texi -index 47e4480..cff2ead 100644 ---- a/doc/coreutils.texi -+++ b/doc/coreutils.texi -@@ -8083,6 +8083,11 @@ done - exit $fail - @end example - -+@item -c -+@cindex SELinux security context information, preserving -+Preserve SELinux security context of the original files if possible. -+Some file systems don't support storing of SELinux security context. -+ - @item --copy-contents - @cindex directories, copying recursively - @cindex copying directories recursively -diff --git a/src/install.c b/src/install.c -index d79d597..437889a 100644 ---- a/src/install.c -+++ b/src/install.c -@@ -673,7 +673,7 @@ In the 4th form, create all components of the given DIRECTORY(ies).\n\ - -v, --verbose print the name of each directory as it is created\n\ - "), stdout); - fputs (_("\ -- --preserve-context preserve SELinux security context\n\ -+ -P, --preserve-context preserve SELinux security context (-P deprecated)\n\ - -Z set SELinux security context of destination\n\ - file and each created directory to default type\n\ - --context[=CTX] like -Z, or if CTX is specified then set the\n\ -@@ -824,7 +824,7 @@ 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, - NULL)) != -1) - { - switch (optc) -@@ -885,6 +885,8 @@ 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) - { -@@ -892,6 +894,10 @@ main (int argc, char **argv) - "this kernel is not SELinux-enabled")); - break; - } -+ if ( x.set_security_context ) { -+ (void) 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; diff --git a/coreutils.spec b/coreutils.spec index 9265112..6712263 100644 --- a/coreutils.spec +++ b/coreutils.spec @@ -1,11 +1,15 @@ Summary: A set of basic GNU tools commonly used in shell scripts Name: coreutils -Version: 8.27 -Release: 16%{?dist} -License: GPLv3+ -Group: System Environment/Base +Version: 9.9 +Release: 2%{?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/ Source0: https://ftp.gnu.org/gnu/%{name}/%{name}-%{version}.tar.xz +Source1: https://ftp.gnu.org/gnu/%{name}/%{name}-%{version}.tar.xz.sig +# From https://savannah.gnu.org/project/release-gpgkeys.php?group=coreutils&download=1 +# which is linked as project keyring on https://savannah.gnu.org/projects/coreutils +Source2: coreutils-keyring.gpg Source50: supported_utils Source105: coreutils-colorls.sh Source106: coreutils-colorls.csh @@ -13,136 +17,86 @@ Source106: coreutils-colorls.csh # do not make coreutils-single depend on /usr/bin/coreutils %global __requires_exclude ^%{_bindir}/coreutils$ -# upstream patches -Patch1: coreutils-8.27-date-debug-test.patch - -# date, touch: fix out-of-bounds write via large TZ variable (CVE-2017-7476) -Patch2: coreutils-8.27-CVE-2017-7476.patch - -# tail: revert to polling if a followed directory is replaced (#1283760) -Patch3: coreutils-8.27-tail-inotify-recreate.patch - -# doc: mention `setpriv --no-new-privs` feature in runcon info -Patch4: coreutils-8.27-runcon-doc.patch - -# ptx: fix a possible crash caused by integer overflow (#1482445) -Patch5: coreutils-8.27-ptx-int-overflow.patch - # disable the test-lock gnulib test prone to deadlock Patch100: coreutils-8.26-test-lock.patch -#add note about no difference between binary/text mode on Linux - md5sum manpage -Patch101: coreutils-6.10-manpages.patch -# downstream changes to default DIR_COLORS -Patch102: coreutils-8.25-DIR_COLORS.patch -#do display processor type for uname -p/-i based on uname(2) syscall -Patch103: coreutils-8.2-uname-processortype.patch -#df --direct -Patch104: coreutils-df-direct.patch -#add note about mkdir --mode behaviour into info documentation(#610559) -Patch107: coreutils-8.4-mkdir-modenote.patch +# require_selinux_(): use selinuxenabled(8) if available +Patch101: coreutils-8.26-selinuxenable.patch -# sh-utils -#add info about TZ envvar to date manpage -Patch703: sh-utils-2.0.11-dateman.patch -Patch713: coreutils-4.5.3-langinfo.patch +# downstream changes to default DIR_COLORS +Patch102: coreutils-8.32-DIR_COLORS.patch + +# use python3 in tests +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 + +# 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 # (sb) lin18nux/lsb compliance - multibyte functionality patch Patch800: coreutils-i18n.patch -# (sb) lin18nux/lsb compliance - expand/unexpand -Patch801: coreutils-i18n-expand-unexpand.patch -# i18n patch for cut - old version - used -Patch804: coreutils-i18n-cut-old.patch -# The unexpand patch above is not correct. Sent to the patch authors -Patch803: coreutils-i18n-fix-unexpand.patch -#(un)expand - allow multiple files on input - broken by patch 801 -Patch805: coreutils-i18n-fix2-expand-unexpand.patch -#(un)expand - test BOM headers -Patch806: coreutils-i18n-un-expand-BOM.patch -# make 'sort -h' work for arbitrary column even when using UTF-8 locales -Patch807: coreutils-i18n-sort-human.patch -# fold: preserve new-lines in mutlibyte text (#1418505) -Patch808: coreutils-i18n-fold-newline.patch - -#getgrouplist() patch from Ulrich Drepper. -Patch908: coreutils-getgrouplist.patch - -#SELINUX Patch - implements Redhat changes -#(upstream did some SELinux implementation unlike with RedHat patch) -Patch950: coreutils-selinux.patch Conflicts: filesystem < 3 + # To avoid clobbering installs Conflicts: coreutils-single -Provides: /bin/basename -Provides: /bin/cat -Provides: /bin/chgrp -Provides: /bin/chmod -Provides: /bin/chown -Provides: /bin/cp -Provides: /bin/cut -Provides: /bin/date -Provides: /bin/dd -Provides: /bin/df -Provides: /bin/echo -Provides: /bin/env -Provides: /bin/false -Provides: /bin/ln -Provides: /bin/ls -Provides: /bin/mkdir -Provides: /bin/mknod -Provides: /bin/mktemp -Provides: /bin/mv -Provides: /bin/nice -Provides: /bin/pwd -Provides: /bin/readlink -Provides: /bin/rm -Provides: /bin/rmdir -Provides: /bin/sleep -Provides: /bin/sort -Provides: /bin/stty -Provides: /bin/sync -Provides: /bin/touch -Provides: /bin/true -Provides: /bin/uname BuildRequires: attr BuildRequires: autoconf BuildRequires: automake -BuildRequires: bison +BuildRequires: gcc BuildRequires: gettext-devel BuildRequires: gmp-devel +BuildRequires: hostname BuildRequires: libacl-devel BuildRequires: libattr-devel BuildRequires: libcap-devel BuildRequires: libselinux-devel +BuildRequires: libselinux-utils +BuildRequires: make BuildRequires: openssl-devel BuildRequires: strace +BuildRequires: systemd-devel BuildRequires: texinfo +# For gpg verification of source tarball +BuildRequires: gnupg2 + +# test-only dependencies +BuildRequires: acl +BuildRequires: gdb +BuildRequires: perl-interpreter +BuildRequires: perl(FileHandle) +BuildRequires: python3 +BuildRequires: tzdata +%ifarch %valgrind_arches +BuildRequires: valgrind +%endif + +%if 0%{?fedora} +BuildRequires: perl(Expect) +BuildRequires: python3-inotify +%endif + %if 23 < 0%{?fedora} || 7 < 0%{?rhel} # needed by i18n test-cases BuildRequires: glibc-langpack-en +BuildRequires: glibc-langpack-fr +BuildRequires: glibc-langpack-ko +BuildRequires: glibc-langpack-sv %endif Requires: %{name}-common = %{version}-%{release} -Requires: ncurses -Provides: bundled(gnulib) Provides: coreutils-full = %{version}-%{release} -Provides: fileutils = %{version}-%{release} -Provides: sh-utils = %{version}-%{release} -Provides: stat = %{version}-%{release} -Provides: textutils = %{version}-%{release} - -#old mktemp package had epoch 3, so we have to use 4 for coreutils -Provides: mktemp = 4:%{version}-%{release} -Obsoletes: mktemp < 4:%{version}-%{release} - -Obsoletes: fileutils <= 4.1.9 -Obsoletes: sh-utils <= 2.0.12 -Obsoletes: stat <= 3.3 -Obsoletes: textutils <= 2.0.21 +Provides: bundled(gnulib) Obsoletes: %{name} < 8.24-100 %description @@ -153,6 +107,8 @@ the old GNU fileutils, sh-utils, and textutils packages. Summary: coreutils multicall binary Suggests: coreutils-common Provides: coreutils = %{version}-%{release} +Provides: coreutils%{?_isa} = %{version}-%{release} +Provides: bundled(gnulib) # To avoid clobbering installs Conflicts: coreutils < 8.24-100 # Note RPM doesn't support separate buildroots for %files @@ -168,19 +124,35 @@ packaged as a single multicall binary. # yum obsoleting rules explained at: # https://bugzilla.redhat.com/show_bug.cgi?id=1107973#c7 Obsoletes: %{name} < 8.24-100 -Requires(preun): /sbin/install-info -Requires(post): /sbin/install-info + +# 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 + Summary: coreutils common optional components %description common Optional though recommended components, including documentation and translations. %prep +%{gpgverify} --keyring='%{SOURCE2}' --signature='%{SOURCE1}' --data='%{SOURCE0}' %autosetup -N -# will be modified by coreutils-8.25-DIR_COLORS.patch -tee DIR_COLORS{,.256color,.lightbgcolor} /dev/null -# git add DIR_COLORS{,.256color,.lightbgcolor} +# will be regenerated in the build directories +rm -f src/fs.h + +# will be further modified by coreutils-8.32-DIR_COLORS.patch +sed src/dircolors.hin \ + -e 's| 00;36$| 01;36|' \ + > DIR_COLORS +sed src/dircolors.hin \ + -e 's| 01;31$| 00;31|' \ + -e 's| 01;35$| 00;35|' \ + > DIR_COLORS.lightbgcolor + +# git add DIR_COLORS{,.lightbgcolor} # git commit -m "clone DIR_COLORS before patching" # apply all patches @@ -190,18 +162,36 @@ tee DIR_COLORS{,.256color,.lightbgcolor} /dev/null find tests -name '*.sh' -perm 0644 -print -exec chmod 0755 '{}' '+' (echo "<<< done") 2>/dev/null +# FIXME: Force a newer gettext version to workaround `autoreconf -i` errors +# with coreutils 9.6 and bundled gettext 0.19.2 from gettext-common-devel. +sed -i "s/0.19.2/$(rpm -q --queryformat '%%{VERSION}\n' gettext-devel)/" bootstrap.conf configure.ac + autoreconf -fiv %build export CFLAGS="$RPM_OPT_FLAGS -fno-strict-aliasing -fpic" + +# Upstream suggests to build with -Dlint for static analyzers: +# https://lists.gnu.org/archive/html/coreutils/2018-06/msg00110.html +# ... and even for production binary RPMs: +# https://lists.gnu.org/archive/html/bug-gnulib/2020-05/msg00130.html +# There is currently no measurable performance drop or other known downside. +CFLAGS="$CFLAGS -Dlint" + +# make mknod work again in chroot without /proc being mounted (#1811038) +export ac_cv_func_lchmod="no" + +# needed for out-of-tree build +%global _configure ../configure + %{expand:%%global optflags %{optflags} -D_GNU_SOURCE=1} for type in separate single; do - mkdir $type && \ - (cd $type && ln -s ../configure || exit 1 + mkdir -p $type && \ + (cd $type || exit $? if test $type = 'single'; then config_single='--enable-single-binary' config_single="$config_single --without-openssl" # smaller/slower sha*sum - config_single="$config_single --without-gmp" # expr/factor machine ints + config_single="$config_single --without-libgmp" # expr/factor machine ints else config_single='--with-openssl' # faster sha*sum fi @@ -209,9 +199,14 @@ 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 all %{?_smp_mflags}) + %make_build all V=1 + + # make sure that parse-datetime.{c,y} ends up in debuginfo (#1555079) + ln -fv ../lib/parse-datetime.{c,y} . + ) done # Get the list of supported utilities @@ -231,14 +226,20 @@ for type in separate single; do fi (cd $type && make DESTDIR=$RPM_BUILD_ROOT/$subdir $install) +%if "%{_sbindir}" != "%{_bindir}" # chroot was in /usr/sbin : - mkdir -p $RPM_BUILD_ROOT/$subdir/{%{_bindir},%{_sbindir}} + mkdir -p $RPM_BUILD_ROOT/$subdir/%_sbindir mv $RPM_BUILD_ROOT/$subdir/{%_bindir,%_sbindir}/chroot +%endif # Move multicall variants to *.single. # RemovePathPostfixes will strip that later. if test $type = 'single'; then - for dir in %{_bindir} %{_sbindir} %{_libexecdir}/%{name}; do + for dir in %{_bindir} \ +%if "%{_sbindir}" != "%{_bindir}" +%{_sbindir} \ +%endif +%{_libexecdir}/%{name}; do for bin in $RPM_BUILD_ROOT/%{_libexecdir}/%{name}/$dir/*; do basebin=$(basename $bin) mv $bin $RPM_BUILD_ROOT/$dir/$basebin.single @@ -248,8 +249,7 @@ for type in separate single; do done mkdir -p $RPM_BUILD_ROOT%{_sysconfdir}/profile.d -install -p -c -m644 DIR_COLORS{,.256color,.lightbgcolor} \ - $RPM_BUILD_ROOT%{_sysconfdir} +install -p -c -m644 DIR_COLORS{,.lightbgcolor} $RPM_BUILD_ROOT%{_sysconfdir} install -p -c -m644 %SOURCE105 $RPM_BUILD_ROOT%{_sysconfdir}/profile.d/colorls.sh install -p -c -m644 %SOURCE106 $RPM_BUILD_ROOT%{_sysconfdir}/profile.d/colorls.csh @@ -260,18 +260,6 @@ grep LC_TIME %name.lang | cut -d'/' -f1-6 | sed -e 's/) /) %%dir /g' >>%name.lan # (sb) Deal with Installed (but unpackaged) file(s) found rm -f $RPM_BUILD_ROOT%{_infodir}/dir -%preun common -if [ $1 = 0 ]; then - if [ -f %{_infodir}/%{name}.info.gz ]; then - /sbin/install-info --delete %{_infodir}/%{name}.info.gz %{_infodir}/dir || : - fi -fi - -%post common -if [ -f %{_infodir}/%{name}.info.gz ]; then - /sbin/install-info %{_infodir}/%{name}.info.gz %{_infodir}/dir || : -fi - %files -f supported_utils %exclude %{_bindir}/*.single %dir %{_libexecdir}/coreutils @@ -279,7 +267,9 @@ fi %files single %{_bindir}/*.single +%if "%{_sbindir}" != "%{_bindir}" %{_sbindir}/chroot.single +%endif %dir %{_libexecdir}/coreutils %{_libexecdir}/coreutils/*.so.single # duplicate the license because coreutils-common does not need to be installed @@ -296,6 +286,373 @@ fi %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 +- 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) + +* Wed Aug 21 2024 Lukáš Zaoral - 9.5-8 +- add missing systemd-devel buildrequires + +* Wed Jul 17 2024 Fedora Release Engineering - 9.5-7 +- Rebuilt for https://fedoraproject.org/wiki/Fedora_41_Mass_Rebuild + +* Mon Jul 15 2024 Lukáš Zaoral - 9.5-6 +- Rebuilt for the bin-sbin merge + +* Mon Jul 15 2024 Sohum Mendon - 9.5-5 +- fix incorrect exit status when fold is called with a non-existent file + +* Tue Jul 09 2024 Zbigniew Jędrzejewski-Szmek - 9.5-4 +- Rebuilt for the bin-sbin merge + +* Thu Jul 04 2024 Lukáš Zaoral - 9.5-3 +- do not buildrequire perl(Expect) on ELN + +* Tue Jun 04 2024 Lukáš Zaoral - 9.5-2 +- enable LTO on ppc64le + +* Tue Apr 02 2024 Lukáš Zaoral - 9.5-1 +- rebase to latest upstream version (rhbz#2272063) +- sync i18n patch with SUSE (Kudos to Berny Völker!) +- add some test dependencies to execute additional part of the upstream test-suite + +* Mon Jan 29 2024 Lukáš Zaoral - 9.4-6 +- fix tail on kernels with 64k page sizes (RHEL-22866) + +* Wed Jan 24 2024 Fedora Release Engineering - 9.4-5 +- Rebuilt for https://fedoraproject.org/wiki/Fedora_40_Mass_Rebuild + +* Fri Jan 19 2024 Fedora Release Engineering - 9.4-4 +- Rebuilt for https://fedoraproject.org/wiki/Fedora_40_Mass_Rebuild + +* Thu Jan 18 2024 Lukáš Zaoral - 9.4-3 +- fix compilation on i686 + +* Thu Jan 18 2024 Lukáš Zaoral - 9.4-2 +- fix buffer overflow in split (CVE-2024-0684) + +* Fri Sep 15 2023 Lukáš Zaoral - 9.4-1 +- new upstream release 9.4 (#2235759) +- enable integration with systemd +- fix the license field + +* Wed Jul 19 2023 Fedora Release Engineering - 9.3-2 +- Rebuilt for https://fedoraproject.org/wiki/Fedora_39_Mass_Rebuild + +* Tue Apr 18 2023 Kamil Dudka - 9.3-1 +- remove obsolete Provides for absolute paths +- new upstream release 9.3 + +* Tue Apr 11 2023 Lukáš Zaoral - 9.2-4 +- migrate to SPDX license format + +* Fri Mar 24 2023 Kamil Dudka - 9.2-3 +- copy: fix --reflink=auto to fallback in more cases (#2180056) +- cksum: fix reporting of failed checks (#2180056) + +* Wed Mar 22 2023 Kamil Dudka - 9.2-2 +- coreutils-getgrouplist.patch: drop a patch no longer needed + +* Wed Mar 22 2023 Kamil Dudka - 9.2-1 +- new upstream release 9.2 + +* Thu Jan 19 2023 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_38_Mass_Rebuild + +* Mon Jan 02 2023 Kamil Dudka - 9.1-10 +- drop obsolete downstream-only extension of date(1) man page +- undocument downstream SELinux options deprecated since 2009 + +* Mon Jan 02 2023 Kamil Dudka - 9.1-9 +- basic support for checking NFSv4 ACLs (#2137866) + +* Mon Sep 19 2022 Kamil Dudka - 9.1-8 +- remove obsolete extension of mkdir(1) info documentation + +* Tue Aug 23 2022 Kamil Dudka - 9.1-7 +- remove non-upstream patch for uname -i/-p (#548834) + +* Mon Aug 08 2022 Kamil Dudka - 9.1-6 +- improve wording of a comment in /etc/DIR_COLORS (#2112593) + +* Mon Aug 08 2022 Kamil Dudka - 9.1-5 +- improve handling of control characters in unexpand (#2112870) + +* Mon Aug 01 2022 Kamil Dudka - 9.1-4 +- prevent unexpand from failing on control characters (#2112870) + +* Wed Jul 20 2022 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_37_Mass_Rebuild + +* Sat Apr 23 2022 Pádraig Brady - 9.1-2 +- make simple backups in correct dir; broken in 9.1 + +* Tue Apr 19 2022 Kamil Dudka - 9.1-1 +- new upstream release 9.1 + +* Mon Mar 21 2022 Kamil Dudka - 9.0-5 +- ls, stat: avoid triggering automounts (#2044981) + +* Tue Mar 01 2022 Kamil Dudka - 9.0-4 +- make `df --direct` work again (#2058686) + +* Wed Jan 19 2022 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_36_Mass_Rebuild + +* Mon Oct 04 2021 Kamil Dudka - 9.0-2 +- chmod: fix exit status when ignoring symlinks + +* Sun Sep 26 2021 Kamil Dudka - 9.0-1 +- new upstream release 9.0 + +* Tue Sep 14 2021 Sahana Prasad +- Rebuilt with OpenSSL 3.0.0 + +* Wed Jul 21 2021 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_35_Mass_Rebuild + +* Wed Jul 07 2021 Kamil Dudka - 8.32-30 +- df: fix duplicated remote entries due to bind mounts (#1979814) + +* Thu Jul 01 2021 Kamil Dudka - 8.32-28 +- tail: fix stack out-of-bounds write with --follow + +* Tue Jun 08 2021 Kamil Dudka - 8.32-27 +- mountlist: recognize fuse.portal as dummy file system (#1913358) + +* Mon May 17 2021 Kamil Dudka - 8.32-26 +- cp: pick additional copy_file_range()-related fixes from upstream + +* Mon May 03 2021 Kamil Dudka - 8.32-24 +- copy: ensure we enforce --reflink=never (#1956080) + +* Tue Apr 27 2021 Kamil Dudka - 8.32-23 +- copy: do not refuse to copy a swap file + +* Fri Apr 09 2021 Kamil Dudka - 8.32-22 +- weaken the dependency on glibc-doc to reduce minimal installations +- drop the last use of ncurses no longer needed (#1830318) +- utimens: fix confusing arg type in internal func + +* Fri Mar 26 2021 Kamil Dudka - 8.32-21 +- hostname,ln: fix memory leaks detected by Coverity + +* Wed Mar 24 2021 Kamil Dudka - 8.32-20 +- cp: use copy_file_range if available + +* Thu Feb 18 2021 Kamil Dudka - 8.32-19 +- stat: add support for the exfat file system (#1921427) + +* Wed Feb 03 2021 Kamil Dudka - 8.32-18 +- make coreutils-common recommend glibc-doc for info doc refs (#959597) + +* Tue Feb 02 2021 Kamil Dudka - 8.32-17 +- ls: fix crash printing SELinux context for unstatable files (#1921249) +- split: fix --number=K/N to output correct part of file (#1921246) +- expr: fix invalid read with unmatched \(...\) (#1919775) + +* Tue Jan 26 2021 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_34_Mass_Rebuild + +* Tue Dec 08 2020 Kamil Dudka - 8.32-15 +- rm: do not skip files upon failure to remove an empty dir (#1905481) + +* Tue Nov 03 2020 Kamil Dudka - 8.32-14 +- df,stat,tail: recognize more file system types + +* Wed Oct 14 2020 Kamil Dudka - 8.32-13 +- make the %%build section idempotent + +* Mon Aug 17 2020 Kamil Dudka - 8.32-12 +- do not install /etc/DIR_COLORS.256color (#1830318) + +* Thu Jul 30 2020 Kamil Dudka - 8.32-11 +- cp: default to --reflink=auto (#1861108) + +* Mon Jul 27 2020 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_33_Mass_Rebuild + +* Fri Jul 24 2020 Kamil Dudka - 8.32-9 +- disable -flto on ppc64le to make test-float pass (#1789115) + +* Mon Jul 13 2020 Tom Stellard - 8.32-8 +- Use make macros +- https://fedoraproject.org/wiki/Changes/UseMakeBuildInstallMacro + +* Fri Jun 26 2020 James Cassell - 8.32-7 +- move ncurses to -common package since it's needed for colorls.sh +- make ncurses optional + +* Fri May 15 2020 Kamil Dudka - 8.32-6 +- compile with -Dlint to enable optional initialization and cleanup code + +* Thu Apr 23 2020 Kamil Dudka - 8.32-5 +- du: simplify leaf optimization for XFS (#1823247) + +* Fri Apr 17 2020 Tom Stellard - 8.32-4 +- Fix missing inline function definition + +* Wed Mar 11 2020 Kamil Dudka - 8.32-3 +- uniq: remove collation handling as required by newer POSIX + +* Mon Mar 09 2020 Kamil Dudka - 8.32-2 +- make mknod work again in chroot without /proc being mounted (#1811038) +- ls: restore 8.31 behavior on removed directories + +* Thu Mar 05 2020 Kamil Dudka - 8.32-1 +- new upstream release 8.32 + +* Tue Feb 11 2020 Kamil Dudka - 8.31-10 +- make upstream test-suite work with root privileges (#1800597) + +* Wed Feb 05 2020 Kamil Dudka - 8.31-9 +- use upstream fix the cp/proc-short-read test + +* Thu Jan 30 2020 Kamil Dudka - 8.31-8 +- skip a test that relies on /proc/kallsyms having immutable content + +* Tue Jan 28 2020 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_32_Mass_Rebuild + +* Thu Oct 17 2019 Kamil Dudka - 8.31-6 +- temporarily disable the use of statx (#1760300) + +* Fri Oct 11 2019 Kamil Dudka - 8.31-5 +- use statx instead of stat when available (#1760300) + +* Wed Jul 24 2019 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_31_Mass_Rebuild + +* Tue Jul 16 2019 Kamil Dudka - 8.31-3 +- disable flashing in ls colors for broken symbolic links (#1728986) + +* Mon Mar 18 2019 Kamil Dudka - 8.31-2 +- fix formatting of sha512sum(1) man page (#1688740) + +* Mon Mar 11 2019 Kamil Dudka - 8.31-1 +- new upstream release 8.31 + +* Thu Jan 31 2019 Fedora Release Engineering +- Rebuilt for https://fedoraproject.org/wiki/Fedora_30_Mass_Rebuild + +* Wed Nov 07 2018 Kamil Dudka - 8.30-8 +- sync: fix open() fallback bug +- fix implicit declaration warning in coreutils-getgrouplist.patch + +* Sat Nov 03 2018 Kevin Fenzi - 8.30-7 +- Also remove Requires pre/post used by info scriptlets. + +* Sat Nov 03 2018 Kevin Fenzi - 8.30-6 +- Remove no longer needed info scriptlets + +* Thu Oct 11 2018 Kamil Dudka - 8.30-5 +- fix heap-based buffer overflow in vasnprintf() (CVE-2018-17942) + +* Thu Jul 12 2018 Fedora Release Engineering - 8.30-4 +- Rebuilt for https://fedoraproject.org/wiki/Fedora_29_Mass_Rebuild + +* Tue Jul 10 2018 Kamil Dudka - 8.30-3 +- rename gnulib's renameat2 to renameatu to avoid clash with glibc (#1598518) + +* Wed Jul 04 2018 Kamil Dudka - 8.30-2 +- sync i18n patches with Suse (patch by Bernhard Voelker) + +* Mon Jul 02 2018 Kamil Dudka - 8.30-1 +- new upstream release 8.30 + +* Wed May 30 2018 Kamil Dudka - 8.29-12 +- add provides to coreutils-single to make it a drop-in replacement + +* Mon May 28 2018 Kamil Dudka - 8.29-11 +- ls: increase the allowed abmon width from 5 to 12 (#1577872) +- date, ls: pick strftime fixes from glibc to improve locale support (#1577872) + +* Fri Apr 20 2018 Kamil Dudka - 8.29-10 +- fix crash caused by mistakenly enabled leaf optimization (#1558249) + +* Fri Mar 23 2018 Kamil Dudka - 8.29-9 +- make it possible to install the latest available Adobe Reader RPM for Linux + +* Mon Mar 19 2018 Kamil Dudka - 8.29-8 +- drop BR for bison, which is not used during the build + +* Fri Mar 16 2018 Kamil Dudka - 8.29-7 +- make sure that parse-datetime.{c,y} ends up in debuginfo (#1555079) + +* Tue Mar 06 2018 Kamil Dudka - 8.29-6 +- fix build failure with glibc-2.28 + +* Mon Feb 26 2018 Igor Gnatenko - 8.29-5 +- Remove /bin/* Provides + +* Mon Feb 19 2018 Kamil Dudka - 8.29-4 +- add explicit BR for the gcc compiler + +* Wed Feb 07 2018 Fedora Release Engineering - 8.29-3 +- Rebuilt for https://fedoraproject.org/wiki/Fedora_28_Mass_Rebuild + +* Tue Jan 23 2018 Kamil Dudka - 8.29-2 +- doc: warn about following symlinks recursively in chown/chgrp (CVE-2017-18018) +- mv -n: do not overwrite the destination + +* Tue Jan 02 2018 Kamil Dudka - 8.29-1 +- new upstream release 8.29 + +* Tue Nov 07 2017 Igor Gnatenko - 8.28-2 +- Remove very old Provides (mktemp, sh-utils, textwrap, fileutils, stat) + +* Mon Sep 04 2017 Kamil Dudka - 8.28-1 +- new upstream release 8.28 + * Tue Aug 22 2017 Ville Skyttä - 8.27-16 - Own the %%{_libexecdir}/coreutils dir diff --git a/rh_i18n_wip.tar.gz b/rh_i18n_wip.tar.gz deleted file mode 100644 index 24b7cdc..0000000 Binary files a/rh_i18n_wip.tar.gz and /dev/null differ diff --git a/sh-utils-2.0.11-dateman.patch b/sh-utils-2.0.11-dateman.patch deleted file mode 100644 index 60cdaa6..0000000 --- a/sh-utils-2.0.11-dateman.patch +++ /dev/null @@ -1,12 +0,0 @@ -diff -urNp coreutils-5.97-orig/man/date.x coreutils-5.97/man/date.x ---- coreutils-5.97-orig/man/date.x 1999-11-02 15:07:36.000000000 +0100 -+++ coreutils-5.97/man/date.x 2008-10-15 10:13:31.000000000 +0200 -@@ -11,3 +11,8 @@ calendar date, time of day, time zone, day of week, relative time, - relative date, and numbers. An empty string indicates the beginning - of the day. The date string format is more complex than is easily - documented here but is fully described in the info documentation. -+[ENVIRONMENT] -+.TP -+TZ -+Specifies the timezone, unless overridden by command line parameters. -+If neither is specified, the setting from /etc/localtime is used. diff --git a/sources b/sources index 2566cf4..0952ab1 100644 --- a/sources +++ b/sources @@ -1 +1,2 @@ -SHA512 (coreutils-8.27.tar.xz) = abf3280aaa54e9bd5851df0eda2af1de1017ca174633e52d1e592455d46ea0e99812dda46d2f320e979553cef271485d8818c595bba6ed31264511a511c93679 +SHA512 (coreutils-9.9.tar.xz.sig) = 0a3dfdfa6b4234e2e1d42142269f959bdf3cf8f6605a50270a27eff84dd22588f182121f7dd3eeb04be45f5109d02690215065b3d3b43882874d0e165a1435d0 +SHA512 (coreutils-9.9.tar.xz) = e7b0e59f7732d2c098ea4934014f470248bd5c4764210e9200a698010a8e3b95bbb26e543f0cd73ed5a4b8e1f8cda932c73f39954d68175e4deaa47526610c65 diff --git a/supported_utils b/supported_utils index 8105ccf..6db4fb5 100644 --- a/supported_utils +++ b/supported_utils @@ -1,6 +1,7 @@ %{_bindir}/arch %{_bindir}/b2sum %{_bindir}/basename +%{_bindir}/basenc %{_bindir}/cat %{_bindir}/chgrp %{_bindir}/chmod diff --git a/upstream-key.gpg b/upstream-key.gpg deleted file mode 100644 index dc6dc1d..0000000 --- a/upstream-key.gpg +++ /dev/null @@ -1,123 +0,0 @@ ------BEGIN PGP PUBLIC KEY BLOCK----- -Version: GnuPG v1.4.6 (GNU/Linux) - -mQGiBDftyYoRBACvICTt5AWe7kdbRtJ37IZ+ED5tBA/IbISfqUPO+HmL/J9JSfkV -QHbdQR5dj5mrU6BY5YOY7L4KOS6lH3AgvsZ/NhkDBraBPgnMkpDqFb7z4keCIebb -AmlcBL2VQNTo0Lczo319YoZ+UaNH53OddlBY944qBTa0AlcJuS1SgEp7pwCg+CUj -4SjVzqZh5lgPTS0bnYvF/n0D/iItZ7WAm37KW+9UjArWZD6NO+mVMNq4GWmhcSBD -uyJOZFxFQWXdFRdM9sNO7lkWYVCxpXyFzmQcBzdrAt+zx/3QadEbduGAqEKAROQU -gSDlMITWGK97/Cadn1YRSDcGKNlJX9jlJvt5Q/xh+CnJ8HTwO0PF9A5N/phFuMMB -UH0pA/0e5eIBsr2Wvxy39+nGnNv5b+5tHkGXSSHKyI7+zOdIBTtRQO7lwTG9ioKg -/yMqb9NCSf4GdyZiFJsQ+TWoSyk1bvFHt7YUOhTeii7Zgbk7Due2q+b9KzzyH/r2 -kf+fLh0lgiy/LfBhvsfO8M9dji3XDyZpBLRO6gda9M9NqzEfgbQfSmltIE1leWVy -aW5nIDxqaW1AbWV5ZXJpbmcubmV0PohGBBARAgAGBQI9TvsUAAoJENoowjp5/0R0 -NTIAn2qpRF9QVupw/gz4UN5d5MKurlOMAKDNXKfXzWClHRq5ufCdwZead3WMMYhG -BBARAgAGBQJCk1gpAAoJEIvYLm8wuUtcqlIAn0KbOC5YSkgqhfhM1uRlHnvHB74A -AJ4qbzrkw7iitd1CH1eoMoFiP5CI14hGBBARAgAGBQJDYmg2AAoJELk/YMa1xM4T -ct0AoJIkdqI6dhTUDOVwiZRxaCKVYaoNAJsG8I+OPhhRhe7ZgN5iN3xlRfkhTohG -BBARAgAGBQJECHuEAAoJEFQUZr6xLcGbUyQAnRmg070gGrZ5E4ZPJRqL/DUoB7hN -AKCj7uAIpcRdrBAQW8PKiOWcPRvxjohGBBIRAgAGBQI/bJ2IAAoJEA6nVrUUSEP1 -QXoAoJ6dMlvbJUep2l5N8G0XFmRyxTrIAJ0bn5IYu7RMxqI0vv6DHn2VgEQLeohG -BBIRAgAGBQI/vFVMAAoJENKUXDvBNlC2gtYAn1zlWvzZaC2lxRXuW7fMWpB/5uVJ -AJ9RFEFFzl8BktsnskYJUIvrx5zVL4hGBBMRAgAGBQI/UFjyAAoJEDhZwDsuI25H -z80An0G2Xm22lMc7ThGGgKeovGP0GzPIAKCHFH2aY2Dv6XOYomNB1yvW7MU0ZIhG -BBMRAgAGBQI/cfsiAAoJEA3cqjJ41SZOmcoAoKulkHQ6TUVORoSN77UYtrdCKy0I -AKC5qT7peM0Jd6I9wPLwc7Fc65xraIhGBBMRAgAGBQJAmOELAAoJEAu1FKXQbtaf -ysgAoL7Zl3BSH+/F9ouPCXkduzIywdx9AJ9OevRoJwxpER+SwSiLnw9Q7fVmcYhX -BBMRAgAXBQI66oJOBQsHCgMEAxUDAgMWAgECF4AACgkQ/dLerNMzy6HlawCg5UXJ -LGWj9P0SuJKcGm+mqKb1J2MAn3YrgB3duqFNs/yS4mvxM74TzI5miFoEExECABoF -CwcKAwQDFQMCAxYCAQIXgAIZAQUCOuqCTwAKCRD90t6s0zPLoaVVAJ0UZOyi+B+q -cNTEDSDrc3Oc1MzZrQCg0UONeu4Dv4N5ZLI6lZBMZETaCmKIXwQTEQIAFwUCOuqC -TgULBwoDBAMVAwIDFgIBAheAABIJEP3S3qzTM8uhB2VHUEcAAQHlawCg5UXJLGWj -9P0SuJKcGm+mqKb1J2MAn3YrgB3duqFNs/yS4mvxM74TzI5miGIEExECABoFCwcK -AwQDFQMCAxYCAQIXgAIZAQUCOuqCTwASCRD90t6s0zPLoQdlR1BHAAEBpVUAnRRk -7KL4H6pw1MQNIOtzc5zUzNmtAKDRQ4167gO/g3lksjqVkExkRNoKYrQfSmltIE1l -eWVyaW5nIDxtZXllcmluZ0BnbnUub3JnPohGBBARAgAGBQJCk1gsAAoJEIvYLm8w -uUtcHS0AoIO9LsaLdn6aH3fskRVZ4qhpRBXbAJ0drV2s3abBKhkhUui7kpF87MTD -+4hGBBARAgAGBQJDYmg8AAoJELk/YMa1xM4TdT4Ani/0ORxwCzqGT0+BG2thzbO7 -aFkuAKCoKP+u6WhYYOBdEcaM6T5QLN56H4hGBBARAgAGBQJECHuHAAoJEFQUZr6x -LcGbrKEAoLef0BqLLpNGhAFJKSAvWEWOiGcxAJ9w7F7MtsDoegKeQ44yYiPX5jEu -5ohGBBIRAgAGBQI/bJ2IAAoJEA6nVrUUSEP13sUAn3IWX1RWnH50v+DZKcqzCaSA -oqHbAKCVvtirU/A3FJLnuyIBv+lguddi2IhGBBIRAgAGBQI/vFVRAAoJENKUXDvB -NlC2D68AnAzm1iw0YSQ1GuPaU3lG8n72p5EBAJ4pNBP+RFWjvZSfcUYhZAFhq8CB -QYhGBBMRAgAGBQI/cfslAAoJEA3cqjJ41SZO8asAnRsJcSER+vpIIzM/et8PakIC -ZJxsAJ9LjdnHkb+Zr9YDXzKXu6OTiJvIh4hGBBMRAgAGBQJAmOEOAAoJEAu1FKXQ -btafLL8AoJask7aB+OfOQgS/kMlKXAA25Hl3AKC/3XJeRRR0ze508VcIhx7EhYVV -84heBBMRAgAeBQI/UFjBAhsDBgsJCAcDAgMVAgMDFgIBAh4BAheAAAoJEP3S3qzT -M8uh8gwAoLfqQt7QgzavHlD44LxmAXovm5t0AJ4m8EQC+N9oJyODmpLbfQKNL6pq -zohmBBMRAgAeBQI/UFjBAhsDBgsJCAcDAgMVAgMDFgIBAh4BAheAABIJEP3S3qzT -M8uhB2VHUEcAAQHyDACgt+pC3tCDNq8eUPjgvGYBei+bm3QAnibwRAL432gnI4Oa -ktt9Ao0vqmrOtCFKaW0gTWV5ZXJpbmcgPG1leWVyaW5nQHBvYm94LmNvbT6IRgQQ -EQIABgUCQpNYLAAKCRCL2C5vMLlLXP7FAKCodISH72q8e30TxLwdoOh7hDjehACf -U97FCEOWICQaEI2BvOzGzn6yrO6IRgQQEQIABgUCQ2JoPAAKCRC5P2DGtcTOE0Gk -AJ43felw+/nxzJ7DVJYZ0tbASZ3BcACeNf2nXMkqkwrBZZ9DDMUGQ6tIB3GIRgQQ -EQIABgUCRAh7hwAKCRBUFGa+sS3Bm1nUAJ0foaMmGWqugETz37RZ2XpCfdQIlQCe -N50WxYPBxrGGmhhGOVbji1uhVSmIRgQSEQIABgUCP2ydiAAKCRAOp1a1FEhD9T73 -AJ4/51C6L0lHrX77DFXVJrB02yybsACgi/9TewF7HaF3x8fdMEZxsRK1HR+IRgQS -EQIABgUCP7xVUQAKCRDSlFw7wTZQtvjnAJ9FM83LyrTs2Dk/T7kOcSFTfjXqegCe -OlpOQ/sB4EtoHxrTSCy3OhToVsmIRgQTEQIABgUCP1BY+wAKCRA4WcA7LiNuR5yI -AJ9F3RsjjwtYX2rSx+j5o4+y4Dyl9wCfVR9uTBDLDP3kOaDrTT/H9XHTf6uIRgQT -EQIABgUCP3H7JQAKCRAN3KoyeNUmTv4eAJ9rCBUUXWYFUrjUayOenPULMW1BhACg -ncwdeTN+SGy8lX3zoo1vdNv+vTKIRgQTEQIABgUCQJjhDgAKCRALtRSl0G7WnyNP -AJ9Gn9yRup0zePUPMex36fX94o+i8wCggdDgtpKjzcaQ83o8VBiemFeiss+IXAQT -EQIAHAUCPjpzhwIbAwQLBwMCAxUCAwMWAgECHgECF4AACgkQ/dLerNMzy6FG5gCg -99D5pDqSRuZP2QJAT8LNiCZlRGgAn25OTXbNlHkM+gYFj0fyo+Ikj+T5iGQEExEC -ABwFAj46c4cCGwMECwcDAgMVAgMDFgIBAh4BAheAABIJEP3S3qzTM8uhB2VHUEcA -AQFG5gCg99D5pDqSRuZP2QJAT8LNiCZlRGgAn25OTXbNlHkM+gYFj0fyo+Ikj+T5 -tCJKaW0gTWV5ZXJpbmcgPG1leWVyaW5nQGFzY2VuZC5jb20+iEYEEBECAAYFAkKT -WCwACgkQi9gubzC5S1zwAQCgnPUCCl1g6eJdI5ZViACDiaaULAAAn19sIyQmkiaU -45QVcDtYuQTNSh/QiEYEEBECAAYFAkNiaDwACgkQuT9gxrXEzhP+igCfc526l8n/ -q8zVhIe9NonG+jVlrEoAnRXKebriKwmvVSdqbY8khlbJjB/ziEYEEBECAAYFAkQI -e4cACgkQVBRmvrEtwZs2owCgwzEOLdyXa2JGA/xkpBluqa8/UyMAnjZyxESMAj/A -2rUg3IvgtBmaetE4iEYEEhECAAYFAj+8VVEACgkQ0pRcO8E2ULaqIQCfQlbRoDOL -Hv+9YVxPgD8yhwFB850AnRTmAG4Z57YD92s4o1ne9sgaufmdiEYEExECAAYFAj9Q -WPsACgkQOFnAOy4jbkfOoQCgwfC1mkANwR+vv9TVlYkmoZ6wNL8An0dql+uy5ic1 -YpyKfV7g7MMuEMDwiEYEExECAAYFAj9x+yUACgkQDdyqMnjVJk6QCwCglS7PPvFR -HoOZxl7XgpVbAK6vZQgAniVxncBgSu06lmsDNHiJpiDMIZkkiEYEExECAAYFAkCY -4Q4ACgkQC7UUpdBu1p+QqwCeNzsozeUjiCFQBBiR+gCBnvZhQqgAnj4ImXyp45hs -fc3dZHP3qB1Ws5UjiFUEExECABUFAjftyYoDCwoDAxUDAgMWAgECF4AACgkQ/dLe -rNMzy6HnugCePkbs7JcEo0837WNqdoGf2WXL3vIAoK0cStFCa4zj4FV/SoG9cDZP -JOzfiF0EExECABUFAjftyYoDCwoDAxUDAgMWAgECF4AAEgkQ/dLerNMzy6EHZUdQ -RwABAee6AJ4+RuzslwSjTzftY2p2gZ/ZZcve8gCgrRxK0UJrjOPgVX9Kgb1wNk8k -7N+0IkppbSBNZXllcmluZyA8bWV5ZXJpbmdAbHVjZW50LmNvbT6IRQQTEQIABgUC -QJjhDgAKCRALtRSl0G7Wn/YLAJdAhf8twtaImmHzRT7eaUIf0b4+AJ9hRfAjWrRp -UF5cW5AzZsVwEW7Vc4hGBBARAgAGBQJCk1gsAAoJEIvYLm8wuUtceyMAoJGYrqPm -T+ThNBRLt5aIq/p3yBHmAJ0V0tEMjdIafWlY6IDZkst2VXBPFohGBBARAgAGBQJD -Ymg8AAoJELk/YMa1xM4TTxEAnAtkRTdyDNdPn5kW3HMKcQp9S02vAJ9wiBJbBeaB -jGcQ4zoafo0vw8ZMi4hGBBARAgAGBQJECHuHAAoJEFQUZr6xLcGbZi4AoK2Th3Pi -pC+CWdYDCA9qNa+uUkHsAKCHUU/oOSEqvjEHoYs22RZzVGbbVohGBBIRAgAGBQI/ -vFVRAAoJENKUXDvBNlC2qQ0An3hiEeuqRgzbuY6YLqiA9FH0GHEEAJ4j2O8AjZFq -Vc8RL32KA6nuwfJ28ohGBBMRAgAGBQI/UFj7AAoJEDhZwDsuI25HPicAoJOlcGaT -t5dvksbBg00BNCyZl8odAJ0UCIFlFzzB/x050scZKMrvquc2T4hGBBMRAgAGBQI/ -cfslAAoJEA3cqjJ41SZO5mQAoLTvGtjJxspvgEg3z3T/q6iI/FdxAJ4wgnqQjRvm -AHAWMibcDupPA10u+ohVBBMRAgAVBQI37e/HAwsKAwMVAwIDFgIBAheAAAoJEP3S -3qzTM8uh8vAAn23cUtWPdFr4wIwUNo9bsY1CUHMNAKCoHS3nayqM/WUfihcZJoOs -kQA22ohdBBMRAgAVBQI37e/HAwsKAwMVAwIDFgIBAheAABIJEP3S3qzTM8uhB2VH -UEcAAQHy8ACfbdxS1Y90WvjAjBQ2j1uxjUJQcw0AoKgdLedrKoz9ZR+KFxkmg6yR -ADbatCdKaW0gTWV5ZXJpbmcgPG1leWVyaW5nQG5hLW5ldC5vcm5sLmdvdj6IRgQQ -EQIABgUCPU77FAAKCRDaKMI6ef9EdBjQAJ41hqQaE3W2dHgN9otb7fL0n6U1YACg -kI9DvFQ1YmpLI8jdGwbDxDodAeOIRgQQEQIABgUCQpNYLAAKCRCL2C5vMLlLXMrg -AJ90LwV+nd+U4GEvzYixFvksHvtFGgCggD3NDeGXlgUhPB+nqyBq2QKfZxKIRgQQ -EQIABgUCQ2JoPAAKCRC5P2DGtcTOE4WfAJ4uxTyLyO4NCBk/IlTM0NAKLFHJgwCc -DP0YQC0oDm5uJ8/ZIkl0MUrzKXGIRgQQEQIABgUCRAh7hwAKCRBUFGa+sS3BmyTW -AJ4+X1CGNorq+Nme5tTIVskgYKH7wQCcD7UpPt2+r+NcGSYftkKk3O8R8TKIRgQS -EQIABgUCP7xVUQAKCRDSlFw7wTZQtolWAJ98yLyyC6jzrF/YG5kqeGqHSNdKtQCd -EdCDkGG09QJX8gFfZ/r8lWlflj+IRgQTEQIABgUCP1BY+wAKCRA4WcA7LiNuR4mz -AKC/1XBB9cBCs8X/KvoLLQP75q0i2QCbBb0UoVSUYgsdETzujbTwg+0HLseIRgQT -EQIABgUCP3H7JQAKCRAN3KoyeNUmTql1AJsEhcfoOC2U4JjHR6rWzqinaIxcNgCg -lmdHMQ3L8zCfNzD7lehquPy2P0eIRgQTEQIABgUCQJjhDgAKCRALtRSl0G7Wn+1r -AJ4nUVrAEtL+XBp2UU1QmVCxa7lcSwCfT8ds7xZ++aZomPK2Xvz230WnUsGIVQQT -EQIAFQUCN+3v9gMLCgMDFQMCAxYCAQIXgAAKCRD90t6s0zPLocAwAKCJ4wBEND4W -mzs6Sp47mWBsp96HRACfTH+SGkDfLqgkZ7JgEgzSDKGl4TyIXQQTEQIAFQUCN+3v -9gMLCgMDFQMCAxYCAQIXgAASCRD90t6s0zPLoQdlR1BHAAEBwDAAoInjAEQ0Phab -OzpKnjuZYGyn3odEAJ9Mf5IaQN8uqCRnsmASDNIMoaXhPLkBDQQ37cmSEAQAx3xz -BZlJikWJaiZGru3cEKYYnRFp8No2b4jhBwY9nKn8UIxuY5aQN4ka/k81wqjlC6cT -wn5R7kg2ha8eGXpwYhKGwn5MGvIxqfoj2tsQ76uluTowHA4seoavi7RGEDzm4Vpt -8Nua8krrZ2QPtLA86gkzL1QG5Bbv/o2Ldx8HHNcAAwcEAKcK2tj2X8RPgUarczXv -rdXMteeSFnI7fagbLpEfaTI2xa1ADLg5UO4M9Erz9m6k6xV6loxcBB9H5Ljm9GWf -el4T4p1lwzi3Lu5hKzIiFs+5vsy+fyEai4e5f6v9Ww3Q3Ec6UZpPZGyN+PDPlZxe -rf3ZIMogSGrrEBhprhLHReudiE4EGBECAAYFAjftyZIAEgkQ/dLerNMzy6EHZUdQ -RwABAQXiAKCilmALgD6mhccl4ISaUB5LfW74BQCgqd7wIfbV2+NKqf1Yuj75sryW -Ke4= -=zRdO ------END PGP PUBLIC KEY BLOCK-----