version 9.1

* NEWS: Record release date.

.github/ISSUE_TEMPLATE.txt

@@ -68,7 +68,7 @@ When sending messages to coreutils@gnu.org or bug-coreutils@gnu.org :
 
 
 <!--
-Copyright (C) 2017-2021 Free Software Foundation, Inc.
+Copyright (C) 2017-2022 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

.github/PULL_REQUEST_TEMPLATE.txt

@@ -88,7 +88,7 @@ in this matter.
 
 
 <!--
-Copyright (C) 2017-2021 Free Software Foundation, Inc.
+Copyright (C) 2017-2022 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

.gitignore

@@ -106,6 +106,7 @@
 /lib/sys/
 /lib/termios.h
 /lib/time.h
+/lib/unictype
 /lib/unistd.h
 /lib/unistr
 /lib/unistr.h

.prev-version

@@ -1 +1 @@
-8.32
+9.0

.vg-suppressions

@@ -1,6 +1,6 @@
 # Suppress valgrind diagnostics we don't care about.
 
-# Copyright (C) 2003-2021 Free Software Foundation, Inc.
+# Copyright (C) 2003-2022 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

HACKING

@@ -617,7 +617,7 @@ and root only tests, is to follow these steps (requires lcov to be installed):
   xdg-open doc/coverage/index.html
 
 ========================================================================
-Copyright (C) 2009-2021 Free Software Foundation, Inc.
+Copyright (C) 2009-2022 Free Software Foundation, Inc.
 
 Permission is granted to copy, distribute and/or modify this document
 under the terms of the GNU Free Documentation License, Version 1.3 or

Makefile.am

@@ -1,6 +1,6 @@
 # Make coreutils.					-*-Makefile-*-
 
-# Copyright (C) 1990-2021 Free Software Foundation, Inc.
+# Copyright (C) 1990-2022 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
@@ -93,7 +93,7 @@ dist-hook: gen-ChangeLog
 	$(AM_V_at)touch $(distdir)/doc/constants.texi \
 	  $(distdir)/doc/coreutils.info
 
-gen_start_ver = 8.25
+gen_start_ver = 8.27
 .PHONY: gen-ChangeLog
 gen-ChangeLog:
 	$(AM_V_GEN)if test -d .git; then				\

NEWS

@@ -1,5 +1,134 @@
 GNU coreutils NEWS                                    -*- outline -*-
 
+* Noteworthy changes in release 9.1 (2022-04-15) [stable]
+
+** Bug fixes
+
+  chmod -R no longer exits with error status when encountering symlinks.
+  All files would be processed correctly, but the exit status was incorrect.
+  [bug introduced in coreutils-9.0]
+
+  If 'cp -Z A B' checks B's status and some other process then removes B,
+  cp no longer creates B with a too-generous SELinux security context
+  before adjusting it to the correct value.
+  [bug introduced in coreutils-8.17]
+
+  'cp --preserve=ownership A B' no longer ignores the umask when creating B.
+  Also, 'cp --preserve-xattr A B' is less likely to temporarily chmod u+w B.
+  [bug introduced in coreutils-6.7]
+
+  On macOS, 'cp A B' no longer miscopies when A is in an APFS file system
+  and B is in some other file system.
+  [bug introduced in coreutils-9.0]
+
+  On macOS, fmt no longer corrupts multi-byte characters
+  by misdetecting their component bytes as spaces.
+  [This bug was present in "the beginning".]
+
+  'id xyz' now uses the name 'xyz' to determine groups, instead of xyz's uid.
+  [bug introduced in coreutils-8.22]
+
+  'ls -v' and 'sort -V' no longer mishandle corner cases like "a..a" vs "a.+"
+  or lines containing NULs.  Their behavior now matches the documentation
+  for file names like ".m4" that consist entirely of an extension,
+  and the documentation has been clarified for unusual cases.
+  [bug introduced in coreutils-7.0]
+
+  On macOS, 'mv A B' no longer fails with "Operation not supported"
+  when A and B are in the same tmpfs file system.
+  [bug introduced in coreutils-9.0]
+
+  'mv -T --backup=numbered A B/' no longer miscalculates the backup number
+  for B when A is a directory, possibly inflooping.
+  [bug introduced in coreutils-6.3]
+
+** Changes in behavior
+
+  cat now uses the copy_file_range syscall if available, when doing
+  simple copies between regular files.  This may be more efficient, by avoiding
+  user space copies, and possibly employing copy offloading or reflinking.
+
+  chown and chroot now warn about usages like "chown root.root f",
+  which have the nonstandard and long-obsolete "." separator that
+  causes problems on platforms where user names contain ".".
+  Applications should use ":" instead of ".".
+
+  cksum no longer allows abbreviated algorithm names,
+  so that forward compatibility and robustness is improved.
+
+  date +'%-N' now suppresses excess trailing digits, instead of always
+  padding them with zeros to 9 digits.  It uses clock_getres and
+  clock_gettime to infer the clock resolution.
+
+  dd conv=fsync now synchronizes output even after a write error,
+  and similarly for dd conv=fdatasync.
+
+  dd now counts bytes instead of blocks if a block count ends in "B".
+  For example, 'dd count=100KiB' now copies 100 KiB of data, not
+  102,400 blocks of data.  The flags count_bytes, skip_bytes and
+  seek_bytes are therefore obsolescent and are no longer documented,
+  though they still work.
+
+  ls no longer colors files with capabilities by default, as file-based
+  capabilties are very rarely used, and lookup increases processing per file by
+  about 30%.  It's best to use getcap [-r] to identify files with capabilities.
+
+  ls no longer tries to automount files, reverting to the behavior
+  before the statx() call was introduced in coreutils-8.32.
+
+  stat no longer tries to automount files by default, reverting to the
+  behavior before the statx() call was introduced in coreutils-8.32.
+  Only `stat --cached=never` will continue to automount files.
+
+  timeout --foreground --kill-after=... will now exit with status 137
+  if the kill signal was sent, which is consistent with the behavior
+  when the --foreground option is not specified.  This allows users to
+  distinguish if the command was more forcefully terminated.
+
+** New Features
+
+  dd now supports the aliases iseek=N for skip=N, and oseek=N for seek=N,
+  like FreeBSD and other operating systems.
+
+  dircolors takes a new --print-ls-colors option to display LS_COLORS
+  entries, on separate lines, colored according to the entry color code.
+
+  dircolors will now also match COLORTERM in addition to TERM environment
+  variables.  The default config will apply colors with any COLORTERM set.
+
+** Improvements
+
+  cp, mv, and install now use openat-like syscalls when copying to a directory.
+  This avoids some race conditions and should be more efficient.
+
+  On macOS, cp creates a copy-on-write clone if source and destination
+  are regular files on the same APFS file system, the destination does
+  not already exist, and cp is preserving mode and timestamps (e.g.,
+  'cp -p', 'cp -a').
+
+  The new 'date' option --resolution outputs the timestamp resolution.
+
+  With conv=fdatasync or conv=fsync, dd status=progress now reports
+  any extra final progress just before synchronizing output data,
+  since synchronizing can take a long time.
+
+  printf now supports printing the numeric value of multi-byte characters.
+
+  sort --debug now diagnoses issues with --field-separator characters
+  that conflict with characters possibly used in numbers.
+
+  'tail -f file | filter' now exits on Solaris when filter exits.
+
+  root invoked coreutils, that are built and run in single binary mode,
+  now adjust /proc/$pid/cmdline to be more specific to the utility
+  being run, rather than using the general "coreutils" binary name.
+
+** Build-related
+
+  AIX builds no longer fail because some library functions are not found.
+  [bug introduced in coreutils-8.32]
+
+
 * Noteworthy changes in release 9.0 (2021-09-24) [stable]
 
 ** Bug fixes
@@ -3016,7 +3145,7 @@ GNU coreutils NEWS                                    -*- outline -*-
   install accepts a new option --strip-program to specify the program used to
   strip binaries.
 
-  ls now colorizes files with capabilities if libcap is available
+  ls now colors names of files with capabilities if libcap is available.
 
   ls -v now uses filevercmp function as sort predicate (instead of strverscmp)
 
@@ -5289,7 +5418,7 @@ packages, see ./old/*/NEWS.
 
 ========================================================================
 
-Copyright (C) 2001-2021 Free Software Foundation, Inc.
+Copyright (C) 2001-2022 Free Software Foundation, Inc.
 
 Permission is granted to copy, distribute and/or modify this document
 under the terms of the GNU Free Documentation License, Version 1.3 or

README

@@ -232,7 +232,7 @@ the address on the last line of --help output.
 
 ========================================================================
 
-Copyright (C) 1998-2021 Free Software Foundation, Inc.
+Copyright (C) 1998-2022 Free Software Foundation, Inc.
 
 Permission is granted to copy, distribute and/or modify this document
 under the terms of the GNU Free Documentation License, Version 1.3 or

README-hacking

@@ -1,34 +1,45 @@
--*- outline -*-
+Building from a Git repository				-*- outline -*-
 
 These notes intend to help people working on the checked-out sources.
 These requirements do not apply when building from a distribution tarball.
-See also HACKING for more detailed contribution guidelines.
+If this package has a file HACKING, please also read that file for
+more detailed contribution guidelines.
 
 * Requirements
 
-We've opted to keep only the highest-level sources in the GIT repository.
-This eases our maintenance burden, (fewer merges etc.), but imposes more
+We've opted to keep only the highest-level sources in the Git repository.
+This eases our maintenance burden (fewer merges etc.), but imposes more
 requirements on anyone wishing to build from the just-checked-out sources.
-Note the requirements to build the released archive are much less and
-are just the requirements of the standard ./configure && make procedure.
+(The requirements to build from a release are much less and are just
+the requirements of the standard './configure && make' procedure.)
 Specific development tools and versions will be checked for and listed by
 the bootstrap script.  See README-prereq for specific notes on obtaining
 these prerequisite tools.
 
 Valgrind <http://valgrind.org/> is also highly recommended, if
-Valgrind supports your architecture. See also README-valgrind.
+Valgrind supports your architecture.  See also README-valgrind
+(if present).
 
 While building from a just-cloned source tree may require installing a
-few prerequisites, later, a plain 'git pull && make' should be sufficient.
+few prerequisites, later, a plain 'git pull && make' typically suffices.
 
-* First GIT checkout
+* First Git checkout
 
 You can get a copy of the source repository like this:
 
-        $ git clone git://git.sv.gnu.org/coreutils
-        $ cd coreutils
+        $ git clone git://git.sv.gnu.org/<packagename>
+        $ cd <packagename>
 
-As an optional step, if you already have a copy of the gnulib git
+where '<packagename>' stands for 'coreutils' or whatever other package
+you are building.
+
+To use the most-recent Gnulib (as opposed to the Gnulib version that
+the package last synchronized to), do this next:
+
+        $ git submodule foreach git pull origin master
+        $ git commit -m 'build: update gnulib submodule to latest' gnulib
+
+As an optional step, if you already have a copy of the Gnulib Git
 repository, then you can use it as a reference to reduce download
 time and file system space requirements:
 
@@ -39,20 +50,14 @@ which are extracted from other source packages:
 
         $ ./bootstrap
 
-To use the most-recent gnulib (as opposed to the gnulib version that
-the package last synchronized to), do this next:
-
-        $ git submodule foreach git pull origin master
-        $ git commit -m 'build: update gnulib submodule to latest' gnulib
-
 And there you are!  Just
 
-        $ ./configure --quiet #[--enable-gcc-warnings] [*]
+        $ ./configure --quiet #[--disable-gcc-warnings] [*]
         $ make
         $ make check
 
 At this point, there should be no difference between your local copy,
-and the GIT master copy:
+and the Git master copy:
 
         $ git diff
 
@@ -60,12 +65,15 @@ should output no difference.
 
 Enjoy!
 
-[*] The --enable-gcc-warnings option is useful only with glibc
-and with a very recent version of gcc.  You'll probably also have
-to use recent system headers.  If you configure with this option,
-and spot a problem, please be sure to send the report to the bug
-reporting address of this package, and not to that of gnulib, even
-if the problem seems to originate in a gnulib-provided file.
+[*] By default GCC warnings are enabled when building from Git.
+If you get warnings with recent GCC and Glibc with default
+configure-time options, please report the warnings to the bug
+reporting address of this package instead of to bug-gnulib,
+even if the problem seems to originate in a Gnulib-provided file.
+If you get warnings with other configurations, you can run
+'./configure --disable-gcc-warnings' or 'make WERROR_CFLAGS='
+to build quietly or verbosely, respectively.
+-----
 
 * Submitting patches
 
@@ -93,7 +101,7 @@ each program.  One way to do this is to use vc-dwim
 
 -----
 
-Copyright (C) 2002-2021 Free Software Foundation, Inc.
+Copyright (C) 2002-2022 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

README-prereq

@@ -1,65 +1,41 @@
 This gives some notes on obtaining the tools required for development.
-I.e., the tools checked for by the bootstrap script and include:
+These tools can be used by the 'bootstrap' and 'configure' scripts,
+as well as by 'make'.  They include:
 
-- Autoconf  <https://www.gnu.org/software/autoconf/>
-- Automake  <https://www.gnu.org/software/automake/>
-- Bison     <https://www.gnu.org/software/bison/>
-- Gettext   <https://www.gnu.org/software/gettext/>
-- Git       <https://git-scm.com/>
-- Gperf     <https://www.gnu.org/software/gperf/>
-- Gzip      <https://www.gnu.org/software/gzip/>
-- Perl      <https://www.cpan.org/>
-- Rsync     <https://rsync.samba.org/>
-- Tar       <https://www.gnu.org/software/tar/>
-- Texinfo   <https://www.gnu.org/software/texinfo/>
+- Autoconf   <https://www.gnu.org/software/autoconf/>
+- Automake   <https://www.gnu.org/software/automake/>
+- Bison      <https://www.gnu.org/software/bison/>
+- Gettext    <https://www.gnu.org/software/gettext/>
+- Git        <https://git-scm.com/>
+- Gperf      <https://www.gnu.org/software/gperf/>
+- Gzip       <https://www.gnu.org/software/gzip/>
+- Help2man   <https://www.gnu.org/software/help2man/>
+- M4         <https://www.gnu.org/software/m4/>
+- Make       <https://www.gnu.org/software/make/>
+- Perl       <https://www.cpan.org/>
+- Tar        <https://www.gnu.org/software/tar/>
+- Texinfo    <https://www.gnu.org/software/texinfo/>
+- Wget       <http://www.gnu.org/software/wget/>
+- XZ Utils   <https://tukaani.org/xz/>
 
-Note please try to install/build official packages for your system.
-If these programs are not available use the following instructions
-to build them and install the results into a directory that you will
-then use when building this package.
+It is generally better to use official packages for your system.
+If a package is not officially available you can build it from source
+and install it into a directory that you can then use to build this
+package.  If some packages are available but are too old, install the
+too-old versions first as they may be needed to build newer versions.
 
-Even if the official version of a package for your system is too old,
-please install it, as it may be required to build the newer versions.
-The examples below install into $HOME/coreutils/deps/, so if you are
-going to follow these instructions, first ensure that your $PATH is
-set correctly by running this command:
+Here is an example of how to build a program from source.  This
+example is for Autoconf; a similar approach should work for the other
+developer prerequisites.  This example assumes Autoconf 2.71; it
+should be OK to use a later version of Autoconf, if available.
 
-  prefix=$HOME/coreutils/deps
+  prefix=$HOME/prefix   # (or wherever else you choose)
   export PATH=$prefix/bin:$PATH
-
-* autoconf *
-
-  # Note Autoconf 2.62 or newer is needed to build automake-1.11.2
-  # but we specify 2.64 here as that's what coreutils requires.
-  # Please use the latest stable release version as indicated by git tags.
-  git clone --depth=1 git://git.sv.gnu.org/autoconf.git
-  cd autoconf
-  git pull --tags
-  git checkout v2.64
-  autoreconf -vi
+  wget https://ftp.gnu.org/pub/gnu/autoconf/autoconf-2.71.tar.gz
+  gzip -d <autoconf-2.71.tar.gz | tar xf -
+  cd autoconf-2.71
   ./configure --prefix=$prefix
   make install
 
-* automake *
-
-  # Note help2man is required to build automake fully
-  git clone git://git.sv.gnu.org/automake.git
-  cd automake
-  git checkout v1.11.2
-  ./bootstrap
-  ./configure --prefix=$prefix
-  make install
-
-This package uses XZ utils (successor to LZMA) to create
-a compressed distribution tarball.  Using this feature of Automake
-requires version 1.10a or newer, as well as the xz program itself.
-
-* xz *
-
-  git clone https://git.tukaani.org/xz.git
-  cd xz
-  ./autogen.sh
-  ./configure --prefix=$prefix
-  make install
-
-Now you can build this package as described in README-hacking.
+Once the prerequisites are installed, you can build this package as
+described in README-hacking.

README-valgrind

@@ -1,7 +1,7 @@
 #! /bin/bash
 # Convert this package for use with valgrind.
 
-# Copyright (C) 2002-2021 Free Software Foundation, Inc.
+# Copyright (C) 2002-2022 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

THANKS.in

@@ -641,7 +641,6 @@ Ulrich Hermisson                    ulrich_hermisson@hotmail.com
 Urs Thuermann                       urs@isnogud.escape.de
 Uwe H. Steinfeld                    usteinfeld@gmx.net
 Vesselin Atanasov                   vesselin@bgnet.bg
-Ville Skyttä                        ville.skytta@iki.fi
 Vin Shelton                         acs@alumni.princeton.edu
 Vineet Chadha                       chadha@acis.ufl.edu
 Vitali Lovich                       vlovich@gmail.com

TODO

@@ -143,7 +143,7 @@ pr's use of nstrftime can make it malloc a very large (up to SIZE_MAX) buffer
 
 -----
 
-Copyright (C) 2002-2021 Free Software Foundation, Inc.
+Copyright (C) 2002-2022 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

bootstrap

@@ -1,10 +1,10 @@
 #! /bin/sh
 # Print a version string.
-scriptversion=2021-04-11.09; # UTC
+scriptversion=2022-03-21.01; # UTC
 
 # Bootstrap this package from checked-out sources.
 
-# Copyright (C) 2003-2021 Free Software Foundation, Inc.
+# Copyright (C) 2003-2022 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
@@ -313,6 +313,116 @@ find_tool ()
   eval "export $find_tool_envvar"
 }
 
+# Strip blank and comment lines to leave significant entries.
+gitignore_entries() {
+  sed '/^#/d; /^$/d' "$@"
+}
+
+# If $STR is not already on a line by itself in $FILE, insert it at the start.
+# Entries are inserted at the start of the ignore list to ensure existing
+# entries starting with ! are not overridden.  Such entries support
+# whitelisting exceptions after a more generic blacklist pattern.
+insert_if_absent() {
+  file=$1
+  str=$2
+  test -f $file || touch $file
+  test -r $file || die "Error: failed to read ignore file: $file"
+  duplicate_entries=$(gitignore_entries $file | sort | uniq -d)
+  if [ "$duplicate_entries" ] ; then
+    die "Error: Duplicate entries in $file: " $duplicate_entries
+  fi
+  linesold=$(gitignore_entries $file | wc -l)
+  linesnew=$( { echo "$str"; cat $file; } | gitignore_entries | sort -u | wc -l)
+  if [ $linesold != $linesnew ] ; then
+    { echo "$str" | cat - $file > $file.bak && mv $file.bak $file; } \
+      || die "insert_if_absent $file $str: failed"
+  fi
+}
+
+# Adjust $PATTERN for $VC_IGNORE_FILE and insert it with
+# insert_if_absent.
+insert_vc_ignore() {
+  vc_ignore_file="$1"
+  pattern="$2"
+  case $vc_ignore_file in
+  *.gitignore)
+    # A .gitignore entry that does not start with '/' applies
+    # recursively to subdirectories, so prepend '/' to every
+    # .gitignore entry.
+    pattern=$(echo "$pattern" | sed s,^,/,);;
+  esac
+  insert_if_absent "$vc_ignore_file" "$pattern"
+}
+
+symlink_to_dir()
+{
+  src=$1/$2
+  dst=${3-$2}
+
+  test -f "$src" && {
+
+    # If the destination directory doesn't exist, create it.
+    # This is required at least for "lib/uniwidth/cjk.h".
+    dst_dir=$(dirname "$dst")
+    if ! test -d "$dst_dir"; then
+      mkdir -p "$dst_dir"
+
+      # If we've just created a directory like lib/uniwidth,
+      # tell version control system(s) it's ignorable.
+      # FIXME: for now, this does only one level
+      parent=$(dirname "$dst_dir")
+      for dot_ig in x $vc_ignore; do
+        test $dot_ig = x && continue
+        ig=$parent/$dot_ig
+        insert_vc_ignore $ig "${dst_dir##*/}"
+      done
+    fi
+
+    if $copy; then
+      {
+        test ! -h "$dst" || {
+          echo "$me: rm -f $dst" &&
+          rm -f "$dst"
+        }
+      } &&
+      test -f "$dst" &&
+      cmp -s "$src" "$dst" || {
+        echo "$me: cp -fp $src $dst" &&
+        cp -fp "$src" "$dst"
+      }
+    else
+      # Leave any existing symlink alone, if it already points to the source,
+      # so that broken build tools that care about symlink times
+      # aren't confused into doing unnecessary builds.  Conversely, if the
+      # existing symlink's timestamp is older than the source, make it afresh,
+      # so that broken tools aren't confused into skipping needed builds.  See
+      # <https://lists.gnu.org/r/bug-gnulib/2011-05/msg00326.html>.
+      test -h "$dst" &&
+      src_ls=$(ls -diL "$src" 2>/dev/null) && set $src_ls && src_i=$1 &&
+      dst_ls=$(ls -diL "$dst" 2>/dev/null) && set $dst_ls && dst_i=$1 &&
+      test "$src_i" = "$dst_i" &&
+      both_ls=$(ls -dt "$src" "$dst") &&
+      test "X$both_ls" = "X$dst$nl$src" || {
+        dot_dots=
+        case $src in
+        /*) ;;
+        *)
+          case /$dst/ in
+          *//* | */../* | */./* | /*/*/*/*/*/)
+             die "invalid symlink calculation: $src -> $dst";;
+          /*/*/*/*/)    dot_dots=../../../;;
+          /*/*/*/)      dot_dots=../../;;
+          /*/*/)        dot_dots=../;;
+          esac;;
+        esac
+
+        echo "$me: ln -fs $dot_dots$src $dst" &&
+        ln -fs "$dot_dots$src" "$dst"
+      }
+    fi
+  }
+}
+
 # Override the default configuration, if necessary.
 # Make sure that bootstrap.conf is sourced from the current directory
 # if we were invoked as "sh bootstrap".
@@ -375,47 +485,6 @@ if test -n "$checkout_only_file" && test ! -r "$checkout_only_file"; then
   die "Bootstrapping from a non-checked-out distribution is risky."
 fi
 
-# Strip blank and comment lines to leave significant entries.
-gitignore_entries() {
-  sed '/^#/d; /^$/d' "$@"
-}
-
-# If $STR is not already on a line by itself in $FILE, insert it at the start.
-# Entries are inserted at the start of the ignore list to ensure existing
-# entries starting with ! are not overridden.  Such entries support
-# whitelisting exceptions after a more generic blacklist pattern.
-insert_if_absent() {
-  file=$1
-  str=$2
-  test -f $file || touch $file
-  test -r $file || die "Error: failed to read ignore file: $file"
-  duplicate_entries=$(gitignore_entries $file | sort | uniq -d)
-  if [ "$duplicate_entries" ] ; then
-    die "Error: Duplicate entries in $file: " $duplicate_entries
-  fi
-  linesold=$(gitignore_entries $file | wc -l)
-  linesnew=$( { echo "$str"; cat $file; } | gitignore_entries | sort -u | wc -l)
-  if [ $linesold != $linesnew ] ; then
-    { echo "$str" | cat - $file > $file.bak && mv $file.bak $file; } \
-      || die "insert_if_absent $file $str: failed"
-  fi
-}
-
-# Adjust $PATTERN for $VC_IGNORE_FILE and insert it with
-# insert_if_absent.
-insert_vc_ignore() {
-  vc_ignore_file="$1"
-  pattern="$2"
-  case $vc_ignore_file in
-  *.gitignore)
-    # A .gitignore entry that does not start with '/' applies
-    # recursively to subdirectories, so prepend '/' to every
-    # .gitignore entry.
-    pattern=$(echo "$pattern" | sed s,^,/,);;
-  esac
-  insert_if_absent "$vc_ignore_file" "$pattern"
-}
-
 # Die if there is no AC_CONFIG_AUX_DIR($build_aux) line in configure.ac.
 found_aux_dir=no
 grep '^[	 ]*AC_CONFIG_AUX_DIR(\['"$build_aux"'\])' configure.ac \
@@ -694,9 +763,26 @@ if $use_gnulib; then
       shallow=
       if test -z "$GNULIB_REVISION"; then
         git clone -h 2>&1 | grep -- --depth > /dev/null && shallow='--depth 2'
+        git clone $shallow ${GNULIB_URL:-$default_gnulib_url} "$gnulib_path" \
+          || cleanup_gnulib
+      else
+        git fetch -h 2>&1 | grep -- --depth > /dev/null && shallow='--depth 2'
+        mkdir -p "$gnulib_path"
+        # Only want a shallow checkout of $GNULIB_REVISION, but git does not
+        # support cloning by commit hash. So attempt a shallow fetch by commit
+        # hash to minimize the amount of data downloaded and changes needed to
+        # be processed, which can drastically reduce download and processing
+        # time for checkout. If the fetch by commit fails, a shallow fetch can
+        # not be performed because we do not know what the depth of the commit
+        # is without fetching all commits. So fallback to fetching all commits.
+        git -C "$gnulib_path" init
+        git -C "$gnulib_path" remote add origin \
+            ${GNULIB_URL:-$default_gnulib_url}
+        git -C "$gnulib_path" fetch $shallow origin "$GNULIB_REVISION" \
+          || git -C "$gnulib_path" fetch origin \
+          || cleanup_gnulib
+        git -C "$gnulib_path" reset --hard FETCH_HEAD
       fi
-      git clone $shallow ${GNULIB_URL:-$default_gnulib_url} "$gnulib_path" \
-        || cleanup_gnulib
 
       trap - 1 2 13 15
     fi
@@ -813,75 +899,6 @@ case $SKIP_PO in
   fi;;
 esac
 
-symlink_to_dir()
-{
-  src=$1/$2
-  dst=${3-$2}
-
-  test -f "$src" && {
-
-    # If the destination directory doesn't exist, create it.
-    # This is required at least for "lib/uniwidth/cjk.h".
-    dst_dir=$(dirname "$dst")
-    if ! test -d "$dst_dir"; then
-      mkdir -p "$dst_dir"
-
-      # If we've just created a directory like lib/uniwidth,
-      # tell version control system(s) it's ignorable.
-      # FIXME: for now, this does only one level
-      parent=$(dirname "$dst_dir")
-      for dot_ig in x $vc_ignore; do
-        test $dot_ig = x && continue
-        ig=$parent/$dot_ig
-        insert_vc_ignore $ig "${dst_dir##*/}"
-      done
-    fi
-
-    if $copy; then
-      {
-        test ! -h "$dst" || {
-          echo "$me: rm -f $dst" &&
-          rm -f "$dst"
-        }
-      } &&
-      test -f "$dst" &&
-      cmp -s "$src" "$dst" || {
-        echo "$me: cp -fp $src $dst" &&
-        cp -fp "$src" "$dst"
-      }
-    else
-      # Leave any existing symlink alone, if it already points to the source,
-      # so that broken build tools that care about symlink times
-      # aren't confused into doing unnecessary builds.  Conversely, if the
-      # existing symlink's timestamp is older than the source, make it afresh,
-      # so that broken tools aren't confused into skipping needed builds.  See
-      # <https://lists.gnu.org/r/bug-gnulib/2011-05/msg00326.html>.
-      test -h "$dst" &&
-      src_ls=$(ls -diL "$src" 2>/dev/null) && set $src_ls && src_i=$1 &&
-      dst_ls=$(ls -diL "$dst" 2>/dev/null) && set $dst_ls && dst_i=$1 &&
-      test "$src_i" = "$dst_i" &&
-      both_ls=$(ls -dt "$src" "$dst") &&
-      test "X$both_ls" = "X$dst$nl$src" || {
-        dot_dots=
-        case $src in
-        /*) ;;
-        *)
-          case /$dst/ in
-          *//* | */../* | */./* | /*/*/*/*/*/)
-             die "invalid symlink calculation: $src -> $dst";;
-          /*/*/*/*/)    dot_dots=../../../;;
-          /*/*/*/)      dot_dots=../../;;
-          /*/*/)        dot_dots=../;;
-          esac;;
-        esac
-
-        echo "$me: ln -fs $dot_dots$src $dst" &&
-        ln -fs "$dot_dots$src" "$dst"
-      }
-    fi
-  }
-}
-
 version_controlled_file() {
   parent=$1
   file=$2
@@ -1093,7 +1110,7 @@ bootstrap_epilogue
 
 echo "$0: done.  Now you can run './configure'."
 
-# Local variables:
+# Local Variables:
 # eval: (add-hook 'before-save-hook 'time-stamp)
 # time-stamp-start: "scriptversion="
 # time-stamp-format: "%:y-%02m-%02d.%02H"

bootstrap.conf

@@ -1,6 +1,6 @@
 # Bootstrap configuration.
 
-# Copyright (C) 2006-2021 Free Software Foundation, Inc.
+# Copyright (C) 2006-2022 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
@@ -26,13 +26,16 @@ avoided_gnulib_modules='
 gnulib_modules="
   $avoided_gnulib_modules
   acl
+  alignalloc
   alignof
   alloca
   announce-gen
   areadlink-with-size
+  areadlinkat-with-size
   argmatch
   argv-iter
   assert
+  attribute
   autobuild
   backupfile
   backup-rename
@@ -79,6 +82,8 @@ gnulib_modules="
   faccessat
   fadvise
   fchdir
+  fchmodat
+  fchownat
   fclose
   fcntl
   fcntl-safer
@@ -118,6 +123,7 @@ gnulib_modules="
   getpass-gnu
   gettext-h
   gettime
+  gettime-res
   getugroups
   getusershell
   git-version-gen
@@ -172,7 +178,9 @@ gnulib_modules="
   mkancesdirs
   mkdir
   mkdir-p
+  mkdirat
   mkfifo
+  mkfifoat
   mknod
   mkostemp
   mkstemp
@@ -181,7 +189,6 @@ gnulib_modules="
   mountlist
   mpsort
   netinet_in
-  non-recursive-gnulib-prefix-hack
   nproc
   nstrftime
   obstack
@@ -240,7 +247,6 @@ gnulib_modules="
   stat-macros
   stat-size
   stat-time
-  statat
   stdbool
   stdlib-safer
   stpcpy
@@ -256,6 +262,7 @@ gnulib_modules="
   sys_resource
   sys_stat
   sys_wait
+  targetdir
   tempname
   termios
   time_rz
@@ -276,6 +283,7 @@ gnulib_modules="
   userspec
   utimecmp
   utimens
+  utimensat
   vasprintf-posix
   vc-list-files
   verify
@@ -287,6 +295,7 @@ gnulib_modules="
   winsz-ioctl
   winsz-termios
   write-any-file
+  xalignalloc
   xalloc
   xbinary-io
   xdectoint
@@ -338,7 +347,7 @@ XGETTEXT_OPTIONS=$XGETTEXT_OPTIONS'\\\
 '
 
 gnulib_tool_option_extras="--tests-base=gnulib-tests --with-tests --symlink\
- --makefile-name=gnulib.mk
+ --makefile-name=gnulib.mk --automake-subdir
 "
 
 # Build prerequisites
@@ -372,9 +381,6 @@ bootstrap_post_import_hook ()
     && chmod a-w $tmp-1 $tmp-2 \
     && mv -f $tmp-1 $m4f && mv -f $tmp-2 $mkf)
 
-  # Massage lib/gnulib.mk before using it later in the bootstrapping process.
-  build-aux/prefix-gnulib-mk --lib-name=$gnulib_name lib/$gnulib_mk
-
   # Regenerate src/single-binary.mk
   (mkf=src/single-binary.mk tmp=single-binary.tmp \
     && rm -f $mkf $tmp \

cfg.mk

@@ -1,5 +1,5 @@
 # Customize maint.mk                           -*- makefile -*-
-# Copyright (C) 2003-2021 Free Software Foundation, Inc.
+# Copyright (C) 2003-2022 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
@@ -49,7 +49,7 @@ export VERBOSE = yes
 # 4914152 9e
 export XZ_OPT = -8e
 
-old_NEWS_hash = ad874c61dc38785cb432159b725fc3de
+old_NEWS_hash = 612bad626bf28b1847ad0114cb2cd6fe
 
 # Add an exemption for sc_makefile_at_at_check.
 _makefile_at_at_check_exceptions = ' && !/^cu_install_prog/ && !/dynamic-dep/'
@@ -192,7 +192,7 @@ sc_prohibit_quotes_notation:
 # Files in src/ should quote all strings in error() output, so that
 # unexpected input chars like \r etc. don't corrupt the error.
 # In edge cases this can be avoided by putting the format string
-# on a separate line to the following arguments.
+# on a separate line to the arguments, or the arguments in parenthesis.
 sc_error_quotes:
 	@cd $(srcdir)/src && GIT_PAGER= git grep -n 'error *(.*%s.*, [^(]*);$$'\
 	  *.c | grep -v ', q' \
@@ -236,7 +236,7 @@ sc_error_shell_always_quotes:
 # to the compiler that it doesn't return.
 sc_die_EXIT_FAILURE:
 	@cd $(srcdir)/src && GIT_PAGER= git grep -E \
-	    'error \(.*_(FAILURE|INVALID)' \
+	    'error \([^?]*EXIT_' \
 	  && { echo '$(ME): '"Use die() instead of error" 1>&2; \
 	       exit 1; }  \
 	  || :
@@ -441,12 +441,6 @@ sc_prohibit_operator_at_end_of_line:
 	halt='found operator at end of line'				\
 	  $(_sc_search_regexp)
 
-# Don't use "readlink" or "readlinkat" directly
-sc_prohibit_readlink:
-	@prohibit='\<readlink(at)? \('					\
-	halt='do not use readlink(at); use via xreadlink or areadlink*'	\
-	  $(_sc_search_regexp)
-
 # Don't use address of "stat" or "lstat" functions
 sc_prohibit_stat_macro_address:
 	@prohibit='\<l?stat '':|&l?stat\>'				\
@@ -839,7 +833,7 @@ exclude_file_name_regexp--sc_bindtextdomain = \
 exclude_file_name_regexp--sc_trailing_blank = \
   ^(tests/pr/|gl/.*\.diff$$|man/help2man)
 exclude_file_name_regexp--sc_system_h_headers = \
-  ^src/((die|system|copy|find-mount-point)\.h|make-prime-list\.c)$$
+  ^src/((die|system|copy|chown-core|find-mount-point)\.h|make-prime-list\.c)$$
 
 _src = (crctab|false|lbracket|ls-(dir|ls|vdir)|tac-pipe|uname-(arch|uname))
 _gl_src = (xdecto.max|cl-strtold)

configure.ac

@@ -1,7 +1,7 @@
 # -*- autoconf -*-
 # Process this file with autoconf to produce a configure script.
 
-# Copyright (C) 1991-2021 Free Software Foundation, Inc.
+# Copyright (C) 1991-2022 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
@@ -64,11 +64,7 @@ gl_INIT
 coreutils_MACROS
 
 # The test suite needs to know if we have a working perl.
-# FIXME: this is suboptimal.  Ideally, we would be able to call gl_PERL
-# with an ACTION-IF-NOT-FOUND argument ...
-cu_have_perl=yes
-case $PERL in *"/missing "*) cu_have_perl=no;; esac
-AM_CONDITIONAL([HAVE_PERL], [test $cu_have_perl = yes])
+AM_CONDITIONAL([HAVE_PERL], [test "$gl_cv_prog_perl" != no])
 
 # gl_GCC_VERSION_IFELSE([major], [minor], [run-if-found], [run-if-not-found])
 # ------------------------------------------------
@@ -88,6 +84,50 @@ AC_DEFUN([gl_GCC_VERSION_IFELSE],
   ]
 )
 
+AC_ARG_ENABLE([single-binary],
+  [AS_HELP_STRING([--enable-single-binary=[shebangs|symlinks]],
+     [Compile all the tools in a single binary, reducing the overall size.
+      When compiled this way, shebangs (default when enabled) or symlinks are
+      installed for each tool that points to the single binary.])],
+  [gl_single_binary=no ;
+   case $enableval in
+     yes) gl_single_binary=shebangs ;;
+     no|shebangs|symlinks) gl_single_binary=$enableval ;;
+     *)      AC_MSG_ERROR([bad value $enableval for single-binary option.
+                           Options are: symlinks, shebangs, no.]) ;;
+   esac],
+  [gl_single_binary=no]
+)
+AC_ARG_ENABLE([single-binary-exceptions],
+  [AS_HELP_STRING([--enable-single-binary-exceptions=PROG_LIST],
+     [When used with --enable-single-binary, exclude the PROG_LIST from
+      it, so these programs are compiled as separated files
+      (comma-separated, default none))])],
+  [gl_single_binary_exceptions=$enableval],
+  [gl_single_binary_exceptions=]
+)
+if test "$gl_single_binary" = 'symlinks'; then
+  if ! test "`echo ls | sed \"$program_transform_name\"`" = 'ls'; then
+    AC_MSG_ERROR([program name transformations are not currently supported
+                  with --enable-single-binary=symlinks.])
+  fi
+fi
+AM_CONDITIONAL([SINGLE_BINARY], [test "$gl_single_binary" != no])
+
+AC_ARG_ENABLE([bold-man-page-references],
+  [AS_HELP_STRING([--disable-bold-man-page-references],
+     [When generating man pages, do not apply bold style around any
+      references like name(1) etc.])],
+  [gl_bold_manpages=yes ;
+   case $enableval in
+     no|yes) gl_bold_manpages=$enableval ;;
+     *)      AC_MSG_ERROR([bad value $enableval for bold-man-page-references.
+                           Options are: yes, no.]) ;;
+   esac],
+  [gl_bold_manpages=yes]
+)
+AM_CONDITIONAL([BOLD_MAN_REFS], [test "$gl_bold_manpages" != no])
+
 AC_ARG_ENABLE([gcc-warnings],
   [AS_HELP_STRING([--enable-gcc-warnings@<:@=TYPE@:>@],
     [control generation of GCC warnings.  The TYPE 'no' disables
@@ -150,9 +190,14 @@ if test $gl_gcc_warnings != no; then
   nw="$nw -Wmissing-format-attribute" # copy.c
   nw="$nw -Wunsafe-loop-optimizations" # a few src/*.c
   nw="$nw -Winline"                 # system.h's readdir_ignoring_dot_and_dotdot
-  nw="$nw -Wsuggest-attribute=format" # warns about copy.c and factor.c
   nw="$nw -Wvector-operation-performance" # warns about randperm.c
 
+  # Suppress noreturn warnings with single binaries; otherwise
+  # GCC complains about the renamed 'main' not being declared noreturn
+  # because 'main_exit' calls 'exit' when linting.
+  if test "$gl_single_binary" != no; then
+    nw="$nw -Wsuggest-attribute=noreturn"
+  fi
 
   # Using -Wstrict-overflow is a pain, but the alternative is worse.
   # For an example, see the code that provoked this report:
@@ -224,42 +269,13 @@ if test $gl_gcc_warnings != no; then
   nw="$nw -Wstrict-prototypes"
   # It's not worth being this picky about test programs.
   nw="$nw -Wsuggest-attribute=const"
+  nw="$nw -Wsuggest-attribute=format"
   nw="$nw -Wsuggest-attribute=pure"
   gl_MANYWARN_COMPLEMENT([GNULIB_TEST_WARN_CFLAGS],
                          [$GNULIB_WARN_CFLAGS], [$nw])
   AC_SUBST([GNULIB_TEST_WARN_CFLAGS])
 fi
 
-AC_ARG_ENABLE([single-binary],
-  [AS_HELP_STRING([--enable-single-binary=[shebangs|symlinks]],
-     [Compile all the tools in a single binary, reducing the overall size.
-      When compiled this way, shebangs (default when enabled) or symlinks are
-      installed for each tool that points to the single binary.])],
-  [gl_single_binary=no ;
-   case $enableval in
-     yes) gl_single_binary=shebangs ;;
-     no|shebangs|symlinks) gl_single_binary=$enableval ;;
-     *)      AC_MSG_ERROR([bad value $enableval for single-binary option.
-                           Options are: symlinks, shebangs, no.]) ;;
-   esac],
-  [gl_single_binary=no]
-)
-AC_ARG_ENABLE([single-binary-exceptions],
-  [AS_HELP_STRING([--enable-single-binary-exceptions=PROG_LIST],
-     [When used with --enable-single-binary, exclude the PROG_LIST from
-      it, so these programs are compiled as separated files
-      (comma-separated, default none))])],
-  [gl_single_binary_exceptions=$enableval],
-  [gl_single_binary_exceptions=]
-)
-if test "$gl_single_binary" = 'symlinks'; then
-  if ! test "`echo ls | sed \"$program_transform_name\"`" = 'ls'; then
-    AC_MSG_ERROR([program name transformations are not currently supported
-                  with --enable-single-binary=symlinks.])
-  fi
-fi
-AM_CONDITIONAL([SINGLE_BINARY], [test "$gl_single_binary" != no])
-
 AC_FUNC_FORK
 
 optional_bin_progs=
@@ -320,6 +336,9 @@ if test $utils_cv_localtime_cache = yes; then
   AC_DEFINE([LOCALTIME_CACHE], [1], [FIXME])
 fi
 
+# macOS >= 10.12
+AC_CHECK_FUNCS([fclonefileat])
+
 # Assume that if getattrat exists, it's compatible with Solaris 11.
 AC_CHECK_FUNCS([getattrat])
 if test $ac_cv_func_getattrat = yes; then

doc/coreutils.texi

@@ -145,7 +145,7 @@
 This manual documents version @value{VERSION} of the GNU core
 utilities, including the standard programs for text and file manipulation.
 
-Copyright @copyright{} 1994--2021 Free Software Foundation, Inc.
+Copyright @copyright{} 1994--2022 Free Software Foundation, Inc.
 
 @quotation
 Permission is granted to copy, distribute and/or modify this document
@@ -300,7 +300,7 @@ Operating on characters
 
 @command{tr}: Translate, squeeze, and/or delete characters
 
-* Character sets::               Specifying sets of characters
+* Character arrays::             Specifying arrays of characters
 * Translating::                  Changing one set of characters to another
 * Squeezing and deleting::       Removing characters
 
@@ -498,9 +498,9 @@ Date input formats
 Version sorting order
 
 * Version sort overview::
-* Implementation Details::
-* Differences from the official Debian Algorithm::
-* Advanced Topics::
+* Version sort implementation::
+* Differences from Debian version sort::
+* Advanced version sort topics::
 
 Opening the software toolbox
 
@@ -3554,7 +3554,8 @@ file once for each repeat.
 @item /@var{regexp}/[@var{offset}]
 Create an output file containing the current line up to (but not
 including) the next line of the input file that contains a match for
-@var{regexp}.  The optional @var{offset} is an integer.
+@var{regexp}.  The optional @var{offset} is an integer, that can
+be preceded by @samp{+} or @samp{-}.
 If it is given, the input up to (but not including) the
 matching line plus or minus @var{offset} is put into the output file,
 and the line after that begins the next section of input.
@@ -3990,7 +3991,7 @@ Output extra information to stderr, like the checksum implementation being used.
 
 @item --untagged
 @opindex --untagged
-Output using the original coreutils format used by the other
+Output using the original Coreutils format used by the other
 standalone checksum utilities like @command{md5sum} for example.
 This format has the checksum at the start of the line, and may be
 more amenable to further processing by other utilities,
@@ -6887,7 +6888,7 @@ These commands operate on individual characters.
 Synopsis:
 
 @example
-tr [@var{option}]@dots{} @var{set1} [@var{set2}]
+tr [@var{option}]@dots{} @var{string1} [@var{string2}]
 @end example
 
 @command{tr} copies standard input to standard output, performing
@@ -6904,9 +6905,11 @@ delete characters,
 delete characters, then squeeze repeated characters from the result.
 @end itemize
 
-The @var{set1} and (if given) @var{set2} arguments define ordered
-sets of characters, referred to below as @var{set1} and @var{set2}.  These
-sets are the characters of the input that @command{tr} operates on.
+The @var{string1} and @var{string2} operands define arrays of
+characters @var{array1} and @var{array2}.  By default @var{array1}
+lists input characters that @command{tr} operates on, and @var{array2}
+lists corresponding translations.  In some cases the second operand is
+omitted.
 
 The program accepts the following options.  Also see @ref{Common options}.
 Options must precede operands.
@@ -6919,34 +6922,29 @@ Options must precede operands.
 @opindex -c
 @opindex -C
 @opindex --complement
-This option replaces @var{set1} with its
-complement (all of the characters that are not in @var{set1}).
-Currently @command{tr} fully supports only single-byte characters.
-Eventually it will support multibyte characters; when it does, the
-@option{-C} option will cause it to complement the set of characters,
-whereas @option{-c} will cause it to complement the set of values.
-This distinction will matter only when some values are not characters,
-and this is possible only in locales using multibyte encodings when
-the input contains encoding errors.
+Instead of @var{array1}, use its complement (all characters not
+specified by @var{string1}), in ascending order.  Use this option with
+caution in multibyte locales where its meaning is not always clear
+or portable; see @ref{Character arrays}.
 
 @item -d
 @itemx --delete
 @opindex -d
 @opindex --delete
-Delete characters in @var{set1}, do not translate
+Delete characters in @var{array1}; do not translate.
 
 @item -s
 @itemx --squeeze-repeats
 @opindex -s
 @opindex --squeeze-repeats
 Replace each sequence of a repeated character that is listed in
-the last specified @var{set}, with a single occurrence of that character.
+the last specified @var{array}, with a single occurrence of that character.
 
 @item -t
 @itemx --truncate-set1
 @opindex -t
 @opindex --truncate-set1
-First truncate @var{set1} to length of @var{set2}.
+Truncate @var{array1} to the length of @var{array2}.
 
 @end table
 
@@ -6954,23 +6952,41 @@ First truncate @var{set1} to length of @var{set2}.
 @exitstatus
 
 @menu
-* Character sets::              Specifying sets of characters.
-* Translating::                 Changing one set of characters to another.
+* Character arrays::            Specifying arrays of characters.
+* Translating::                 Changing characters to other characters.
 * Squeezing and deleting::      Removing characters.
 @end menu
 
 
-@node Character sets
-@subsection Specifying sets of characters
+@node Character arrays
+@subsection Specifying arrays of characters
 
-@cindex specifying sets of characters
+@cindex arrays of characters in @command{tr}
 
-The format of the @var{set1} and @var{set2} arguments resembles
-the format of regular expressions; however, they are not regular
-expressions, only lists of characters.  Most characters simply
-represent themselves in these strings, but the strings can contain
-the shorthands listed below, for convenience.  Some of them can be
-used only in @var{set1} or @var{set2}, as noted below.
+The @var{string1} and @var{string2} operands are not regular
+expressions, even though they may look similar.  Instead, they
+merely represent arrays of characters.  As a GNU extension to POSIX,
+an empty string operand represents an empty array of characters.
+
+The interpretation of @var{string1} and @var{string2} depends on locale.
+GNU @command{tr} fully supports only safe single-byte locales,
+where each possible input byte represents a single character.
+Unfortunately, this means GNU @command{tr} will not handle commands
+like @samp{tr $'\u7530' $'\u68EE'} the way you might expect,
+since (assuming a UTF-8 encoding) this is equivalent to
+@samp{tr '\347\224\260' '\346\243\256'} and GNU @command{tr} will
+simply transliterate all @samp{\347} bytes to @samp{\346} bytes, etc.
+POSIX does not clearly specify the behavior of @command{tr} in locales
+where characters are represented by byte sequences instead of by
+individual bytes, or where data might contain invalid bytes that are
+encoding errors.  To avoid problems in this area, you can run
+@command{tr} in a safe single-byte locale by using a shell command
+like @samp{LC_ALL=C tr} instead of plain @command{tr}.
+
+Although most characters simply represent themselves in @var{string1}
+and @var{string2}, the strings can contain shorthands listed below,
+for convenience.  Some shorthands can be used only in @var{string1} or
+@var{string2}, as noted below.
 
 @table @asis
 
@@ -6981,38 +6997,42 @@ The following backslash escape sequences are recognized:
 
 @table @samp
 @item \a
-Control-G.
+Bell (BEL, Control-G).
 @item \b
-Control-H.
+Backspace (BS, Control-H).
 @item \f
-Control-L.
+Form feed (FF, Control-L).
 @item \n
-Control-J.
+Newline (LF, Control-J).
 @item \r
-Control-M.
+Carriage return (CR, Control-M).
 @item \t
-Control-I.
+Tab (HT, Control-I).
 @item \v
-Control-K.
+Vertical tab (VT, Control-K).
 @item \@var{ooo}
-The 8-bit character with the value given by @var{ooo}, which is 1 to 3
-octal digits.  Note that @samp{\400} is interpreted as the two-byte
-sequence, @samp{\040} @samp{0}.
+The eight-bit byte with the value given by @var{ooo}, which is the longest
+sequence of one to three octal digits following the backslash.
+For portability, @var{ooo} should represent a value that fits in eight bits.
+As a GNU extension to POSIX, if the value would not fit, then only the
+first two digits of @var{ooo} are used, e.g., @samp{\400}
+is equivalent to @samp{\0400} and represents a two-byte sequence.
 @item \\
 A backslash.
 @end table
 
-While a backslash followed by a character not listed above is
-interpreted as that character, the backslash also effectively
-removes any special significance, so it is useful to escape
-@samp{[}, @samp{]}, @samp{*}, and @samp{-}.
+It is an error if no character follows an unescaped backslash.
+As a GNU extension, a backslash followed by a character not listed
+above is interpreted as that character, removing any special
+significance; this can be used to escape the characters
+@samp{[} and @samp{-} when they would otherwise be special.
 
 @item Ranges
 @cindex ranges
 
-The notation @samp{@var{m}-@var{n}} expands to all of the characters
+The notation @samp{@var{m}-@var{n}} expands to the characters
 from @var{m} through @var{n}, in ascending order.  @var{m} should
-collate before @var{n}; if it doesn't, an error results.  As an example,
+not collate after @var{n}; if it does, an error results.  As an example,
 @samp{0-9} is the same as @samp{0123456789}.
 
 GNU @command{tr} does not support the System V syntax that uses square
@@ -7022,38 +7042,37 @@ to themselves.  However, they should be avoided because they sometimes
 behave unexpectedly.  For example, @samp{tr -d '[0-9]'} deletes brackets
 as well as digits.
 
-Many historically common and even accepted uses of ranges are not
+Many historically common and even accepted uses of ranges are not fully
 portable.  For example, on EBCDIC hosts using the @samp{A-Z}
 range will not do what most would expect because @samp{A} through @samp{Z}
 are not contiguous as they are in ASCII@.
-If you can rely on a POSIX compliant version of @command{tr}, then
-the best way to work around this is to use character classes (see below).
+One way to work around this is to use character classes (see below).
 Otherwise, it is most portable (and most ugly) to enumerate the members
 of the ranges.
 
 @item Repeated characters
 @cindex repeated characters
 
-The notation @samp{[@var{c}*@var{n}]} in @var{set2} expands to @var{n}
+The notation @samp{[@var{c}*@var{n}]} in @var{string2} expands to @var{n}
 copies of character @var{c}.  Thus, @samp{[y*6]} is the same as
 @samp{yyyyyy}.  The notation @samp{[@var{c}*]} in @var{string2} expands
-to as many copies of @var{c} as are needed to make @var{set2} as long as
-@var{set1}.  If @var{n} begins with @samp{0}, it is interpreted in
-octal, otherwise in decimal.
+to as many copies of @var{c} as are needed to make @var{array2} as long as
+@var{array1}.  If @var{n} begins with @samp{0}, it is interpreted in
+octal, otherwise in decimal.  A zero-valued @var{n} is treated as if
+it were absent.
 
 @item Character classes
 @cindex character classes
 
-The notation @samp{[:@var{class}:]} expands to all of the characters in
-the (predefined) class @var{class}.  The characters expand in no
-particular order, except for the @code{upper} and @code{lower} classes,
-which expand in ascending order.  When the @option{--delete} (@option{-d})
+The notation @samp{[:@var{class}:]} expands to all characters in
+the (predefined) class @var{class}.  When the @option{--delete} (@option{-d})
 and @option{--squeeze-repeats} (@option{-s}) options are both given, any
-character class can be used in @var{set2}.  Otherwise, only the
+character class can be used in @var{string2}.  Otherwise, only the
 character classes @code{lower} and @code{upper} are accepted in
-@var{set2}, and then only if the corresponding character class
+@var{string2}, and then only if the corresponding character class
 (@code{upper} and @code{lower}, respectively) is specified in the same
-relative position in @var{set1}.  Doing this specifies case conversion.
+relative position in @var{string1}.  Doing this specifies case conversion.
+Except for case conversion, a class's characters appear in no particular order.
 The class names are given below; an error results when an invalid class
 name is given.
 
@@ -7099,10 +7118,13 @@ Hexadecimal digits.
 @item Equivalence classes
 @cindex equivalence classes
 
-The syntax @samp{[=@var{c}=]} expands to all of the characters that are
-equivalent to @var{c}, in no particular order.  Equivalence classes are
-a relatively recent invention intended to support non-English alphabets.
-But there seems to be no standard way to define them or determine their
+The syntax @samp{[=@var{c}=]} expands to all characters equivalent to
+@var{c}, in no particular order.  These equivalence classes are
+allowed in @var{string2} only when @option{--delete} (@option{-d}) and
+@option{--squeeze-repeats} @option{-s} are both given.
+
+Although equivalence classes are intended to support non-English alphabets,
+there seems to be no standard way to define them or determine their
 contents.  Therefore, they are not fully implemented in GNU @command{tr};
 each character's equivalence class consists only of that character,
 which is of no particular use.
@@ -7115,13 +7137,14 @@ which is of no particular use.
 
 @cindex translating characters
 
-@command{tr} performs translation when @var{set1} and @var{set2} are
+@command{tr} performs translation when @var{string1} and @var{string2} are
 both given and the @option{--delete} (@option{-d}) option is not given.
-@command{tr} translates each character of its input that is in @var{set1}
-to the corresponding character in @var{set2}.  Characters not in
-@var{set1} are passed through unchanged.  When a character appears more
-than once in @var{set1} and the corresponding characters in @var{set2}
-are not all the same, only the final one is used.  For example, these
+@command{tr} translates each character of its input that is in @var{array1}
+to the corresponding character in @var{array2}.  Characters not in
+@var{array1} are passed through unchanged.
+
+As a GNU extension to POSIX, when a character appears more than once
+in @var{array1}, only the final instance is used.  For example, these
 two commands are equivalent:
 
 @example
@@ -7139,17 +7162,17 @@ tr '[:lower:]' '[:upper:]'
 @end example
 
 @noindent
-But note that using ranges like @code{a-z} above is not portable.
+However, ranges like @code{a-z} are not portable outside the C locale.
 
-When @command{tr} is performing translation, @var{set1} and @var{set2}
-typically have the same length.  If @var{set1} is shorter than
-@var{set2}, the extra characters at the end of @var{set2} are ignored.
+When @command{tr} is performing translation, @var{array1} and @var{array2}
+typically have the same length.  If @var{array1} is shorter than
+@var{array2}, the extra characters at the end of @var{array2} are ignored.
 
-On the other hand, making @var{set1} longer than @var{set2} is not
+On the other hand, making @var{array1} longer than @var{array2} is not
 portable; POSIX says that the result is undefined.  In this situation,
-BSD @command{tr} pads @var{set2} to the length of @var{set1} by repeating
-the last character of @var{set2} as many times as necessary.  System V
-@command{tr} truncates @var{set1} to the length of @var{set2}.
+BSD @command{tr} pads @var{array2} to the length of @var{array1} by repeating
+the last character of @var{array2} as many times as necessary.  System V
+@command{tr} truncates @var{array1} to the length of @var{array2}.
 
 By default, GNU @command{tr} handles this case like BSD @command{tr}.
 When the @option{--truncate-set1} (@option{-t}) option is given,
@@ -7165,13 +7188,12 @@ tr -cs A-Za-z0-9 '\012'
 
 @noindent
 because it converts only zero bytes (the first element in the
-complement of @var{set1}), rather than all non-alphanumerics, to
+complement of @var{array1}), rather than all non-alphanumerics, to
 newlines.
 
 @noindent
 By the way, the above idiom is not portable because it uses ranges, and
-it assumes that the octal code for newline is 012.
-Assuming a POSIX compliant @command{tr}, here is a better
+it assumes that the octal code for newline is 012.  Here is a better
 way to write it:
 
 @example
@@ -7187,20 +7209,20 @@ tr -cs '[:alnum:]' '[\n*]'
 @cindex removing characters
 
 When given just the @option{--delete} (@option{-d}) option, @command{tr}
-removes any input characters that are in @var{set1}.
+removes any input characters that are in @var{array1}.
 
 When given just the @option{--squeeze-repeats} (@option{-s}) option
 and not translating, @command{tr} replaces each input sequence of a
-repeated character that is in @var{set1} with a single occurrence of
+repeated character that is in @var{array1} with a single occurrence of
 that character.
 
 When given both @option{--delete} and @option{--squeeze-repeats}, @command{tr}
-first performs any deletions using @var{set1}, then squeezes repeats
-from any remaining characters using @var{set2}.
+first performs any deletions using @var{array1}, then squeezes repeats
+from any remaining characters using @var{array2}.
 
 The @option{--squeeze-repeats} option may also be used when translating,
 in which case @command{tr} first performs translation, then squeezes
-repeats from any remaining characters using @var{set2}.
+repeats from any remaining characters using @var{array2}.
 
 Here are some examples to illustrate various combinations of options:
 
@@ -7224,7 +7246,7 @@ tr -cs '[:alnum:]' '[\n*]'
 
 @item
 Convert each sequence of repeated newlines to a single newline.
-I.e., delete blank lines:
+I.e., delete empty lines:
 
 @example
 tr -s '\n'
@@ -7278,16 +7300,6 @@ Or you can use @samp{--} to terminate option processing:
 tr -d -- -axM
 @end example
 
-More generally, use the character class notation @code{[=c=]}
-with @samp{-} (or any other character) in place of the @samp{c}:
-
-@example
-tr -d '[=-=]axM'
-@end example
-
-Note how single quotes are used in the above example to protect the
-square brackets from interpretation by a shell.
-
 @end itemize
 
 
@@ -8109,7 +8121,7 @@ may be omitted, or one of:
 @end itemize
 Specifying @option{--color} and no @var{when} is equivalent to
 @option{--color=always}.
-If piping a colorized listing through a pager like @command{less},
+If piping a colored listing through a pager like @command{less},
 use the pager's @option{-R} option to pass the color codes to the terminal.
 
 @vindex LS_COLORS
@@ -8238,14 +8250,6 @@ List files horizontally, with as many as will fit on each line,
 separated by @samp{, } (a comma and a space),
 and with no other information.
 
-@item --zero
-@opindex --zero
-@outputNUL
-This option is incompatible with the @option{--dired} (@option{-D}) option.
-This option also implies the options @option{--show-control-chars},
-@option{-1}, @option{--color=none}, and
-@option{--quoting-style=literal} (@option{-N}).
-
 @item -p
 @itemx --indicator-style=slash
 @opindex -p
@@ -8287,6 +8291,14 @@ is 80.  With a @var{cols} value of @samp{0}, there is no limit on
 the length of the output line, and that single output line will
 be delimited with spaces, not tabs.
 
+@item --zero
+@opindex --zero
+@outputNUL
+This option is incompatible with the @option{--dired} (@option{-D}) option.
+This option also implies the options @option{--show-control-chars},
+@option{-1}, @option{--color=none}, and
+@option{--quoting-style=literal} (@option{-N}).
+
 @end table
 
 
@@ -8624,6 +8636,12 @@ Print the (compiled-in) default color configuration database.  This
 output is itself a valid configuration file, and is fairly descriptive
 of the possibilities.
 
+@item --print-ls-colors
+@opindex --print-ls-colors
+@cindex printing ls colors
+Print the LS_COLORS entries on separate lines,
+each colored as per the color they represent.
+
 @end table
 
 @exitstatus
@@ -9148,9 +9166,8 @@ option, and overrides the @option{--preserve=all} and @option{-a} options.
 @pindex dd
 @cindex converting while copying a file
 
-@command{dd} copies a file (from standard input to standard output, by
-default) with a changeable I/O block size, while optionally performing
-conversions on it.  Synopses:
+@command{dd} copies input to output with a changeable I/O block size,
+while optionally performing conversions on the data.  Synopses:
 
 @example
 dd [@var{operand}]@dots{}
@@ -9158,7 +9175,43 @@ dd @var{option}
 @end example
 
 The only options are @option{--help} and @option{--version}.
-@xref{Common options}.  @command{dd} accepts the following operands,
+@xref{Common options}.
+
+By default, @command{dd} copies standard input to standard output.
+To copy, @command{dd} repeatedly does the following steps in order:
+
+@enumerate
+@item
+Read an input block.
+
+@item
+If converting via @samp{sync}, pad as needed to meet the input block size.
+Pad with spaces if converting via @samp{block} or @samp{unblock}, NUL
+bytes otherwise.
+
+@item
+If @samp{bs=} is given and no conversion mentioned in steps (4) or (5)
+is given, output the data as a single block and skip all remaining steps.
+
+@item
+If the @samp{swab} conversion is given, swap each pair of input bytes.
+If the input data length is odd, preserve the last input byte
+(since there is nothing to swap it with).
+
+@item
+If any of the conversions @samp{swab}, @samp{block}, @samp{unblock},
+@samp{lcase}, @samp{ucase}, @samp{ascii}, @samp{ebcdic} and @samp{ibm}
+are given, do these conversions.  These conversions operate
+independently of input blocking, and might deal with records that span
+block boundaries.
+
+@item
+Aggregate the resulting data into output blocks of the specified size,
+and output each output block in turn.  Do not pad the last output block;
+it can be shorter than usual.
+@end enumerate
+
+@command{dd} accepts the following operands,
 whose syntax was inspired by the DD (data definition) statement of
 OS/360 JCL.
 
@@ -9171,8 +9224,7 @@ Read from @var{file} instead of standard input.
 @item of=@var{file}
 @opindex of
 Write to @var{file} instead of standard output.  Unless
-@samp{conv=notrunc} is given, @command{dd} truncates @var{file} to zero
-bytes (or the size specified with @samp{seek=}).
+@samp{conv=notrunc} is given, truncate @var{file} before writing it.
 
 @item ibs=@var{bytes}
 @opindex ibs
@@ -9212,28 +9264,37 @@ When converting variable-length records to fixed-length ones
 use @var{bytes} as the fixed record length.
 
 @item skip=@var{n}
+@itemx iseek=@var{n}
 @opindex skip
+@opindex iseek
 Skip @var{n} @samp{ibs}-byte blocks in the input file before copying.
-If @samp{iflag=skip_bytes} is specified, @var{n} is interpreted
+If @var{n} ends in the letter @samp{B}, interpret @var{n}
 as a byte count rather than a block count.
+(@samp{B} and the @samp{iseek=} spelling are GNU extensions to POSIX.)
 
 @item seek=@var{n}
+@itemx oseek=@var{n}
 @opindex seek
-Skip @var{n} @samp{obs}-byte blocks in the output file before copying.
-if @samp{oflag=seek_bytes} is specified, @var{n} is interpreted
+@opindex oseek
+Skip @var{n} @samp{obs}-byte blocks in the output file before
+truncating or copying.
+If @var{n} ends in the letter @samp{B}, interpret @var{n}
 as a byte count rather than a block count.
+(@samp{B} and the @samp{oseek=} spelling are GNU extensions to POSIX.)
 
 @item count=@var{n}
 @opindex count
 Copy @var{n} @samp{ibs}-byte blocks from the input file, instead
 of everything until the end of the file.
-if @samp{iflag=count_bytes} is specified, @var{n} is interpreted
-as a byte count rather than a block count.
-Note if the input may return short reads as could be the case
+If @var{n} ends in the letter @samp{B},
+interpret @var{n} as a byte count rather than a block count;
+this is a GNU extension to POSIX.
+If short reads occur, as could be the case
 when reading from a pipe for example, @samp{iflag=fullblock}
-will ensure that @samp{count=} corresponds to complete input blocks
-rather than the traditional POSIX specified behavior of counting
-input read operations.
+ensures that @samp{count=} counts complete input blocks
+rather than input read operations.
+As an extension to POSIX, @samp{count=0} copies zero blocks
+instead of copying all blocks.
 
 @item status=@var{level}
 @opindex status
@@ -9279,6 +9340,8 @@ An additional line like @samp{1 truncated record} or @samp{10
 truncated records} is output after the @samp{records out} line if
 @samp{conv=block} processing truncated one or more input records.
 
+The @samp{status=} operand is a GNU extension to POSIX.
+
 @item conv=@var{conversion}[,@var{conversion}]@dots{}
 @opindex conv
 Convert the file as specified by the @var{conversion} argument(s).
@@ -9326,6 +9389,8 @@ Remove any trailing spaces in each @samp{cbs}-sized input block,
 and append a newline.
 
 The @samp{block} and @samp{unblock} conversions are mutually exclusive.
+If you use either of these conversions, you should also use the
+@samp{cbs=} operand.
 
 @item lcase
 @opindex lcase@r{, converting to}
@@ -9351,12 +9416,12 @@ Similarly, when the output is a device rather than a file,
 NUL input blocks are not copied, and therefore this conversion
 is most useful with virtual or pre zeroed devices.
 
+The @samp{sparse} conversion is a GNU extension to POSIX.
+
 @item swab
 @opindex swab @r{(byte-swapping)}
 @cindex byte-swapping
-Swap every pair of input bytes.  GNU @command{dd}, unlike others, works
-when an odd number of bytes are read---the last byte is simply copied
-(since there is nothing to swap it with).
+Swap every pair of input bytes.
 
 @item sync
 @opindex sync @r{(padding with ASCII NULs)}
@@ -9381,7 +9446,8 @@ output file itself.
 @cindex creating output file, avoiding
 Do not create the output file; the output file must already exist.
 
-The @samp{excl} and @samp{nocreat} conversions are mutually exclusive.
+The @samp{excl} and @samp{nocreat} conversions are mutually exclusive,
+and are GNU extensions to POSIX.
 
 @item notrunc
 @opindex notrunc
@@ -9396,14 +9462,18 @@ Continue after read errors.
 @item fdatasync
 @opindex fdatasync
 @cindex synchronized data writes, before finishing
-Synchronize output data just before finishing.  This forces a physical
-write of output data.
+Synchronize output data just before finishing,
+even if there were write errors.
+This forces a physical write of output data.
+This conversion is a GNU extension to POSIX.
 
 @item fsync
 @opindex fsync
 @cindex synchronized data and metadata writes, before finishing
-Synchronize output data and metadata just before finishing.  This
-forces a physical write of output data and metadata.
+Synchronize output data and metadata just before finishing,
+even if there were write errors.
+This forces a physical write of output data and metadata.
+This conversion is a GNU extension to POSIX.
 
 @end table
 
@@ -9417,8 +9487,7 @@ argument(s).  (No spaces around any comma(s).)
 Access the output file using the flags specified by the @var{flag}
 argument(s).  (No spaces around any comma(s).)
 
-Here are the flags.  Not every flag is supported on every operating
-system.
+Here are the flags.
 
 @table @samp
 
@@ -9559,30 +9628,10 @@ as they may return short reads. In that case,
 this flag is needed to ensure that a @samp{count=} argument is
 interpreted as a block count rather than a count of read operations.
 
-@item count_bytes
-@opindex count_bytes
-Interpret the @samp{count=} operand as a byte count,
-rather than a block count, which allows specifying
-a length that is not a multiple of the I/O block size.
-This flag can be used only with @code{iflag}.
-
-@item skip_bytes
-@opindex skip_bytes
-Interpret the @samp{skip=} operand as a byte count,
-rather than a block count, which allows specifying
-an offset that is not a multiple of the I/O block size.
-This flag can be used only with @code{iflag}.
-
-@item seek_bytes
-@opindex seek_bytes
-Interpret the @samp{seek=} operand as a byte count,
-rather than a block count, which allows specifying
-an offset that is not a multiple of the I/O block size.
-This flag can be used only with @code{oflag}.
-
 @end table
 
-These flags are not supported on all systems, and @samp{dd} rejects
+These flags are all GNU extensions to POSIX.
+They are not supported on all systems, and @samp{dd} rejects
 attempts to use them when they are not supported.  When reading from
 standard input or writing to standard output, the @samp{nofollow} and
 @samp{noctty} flags should not be specified, and the other flags
@@ -9591,34 +9640,42 @@ affected file descriptors, even after @command{dd} exits.
 
 @end table
 
+The behavior of @command{dd} is unspecified if operands other than
+@samp{conv=}, @samp{iflag=}, @samp{oflag=}, and @samp{status=} are
+specified more than once.
+
 @cindex multipliers after numbers
 The numeric-valued strings above (@var{n} and @var{bytes})
+are unsigned decimal integers that
 can be followed by a multiplier: @samp{b}=512, @samp{c}=1,
 @samp{w}=2, @samp{x@var{m}}=@var{m}, or any of the
 standard block size suffixes like @samp{k}=1024 (@pxref{Block size}).
+These multipliers are GNU extensions to POSIX, except that
+POSIX allows @var{bytes} to be followed by @samp{k}, @samp{b}, and
+@samp{x@var{m}}.
+Block sizes (i.e., specified by @var{bytes} strings) must be nonzero.
 
 Any block size you specify via @samp{bs=}, @samp{ibs=}, @samp{obs=}, @samp{cbs=}
 should not be too large---values larger than a few megabytes
 are generally wasteful or (as in the gigabyte..exabyte case) downright
 counterproductive or error-inducing.
 
-To process data that is at an offset or size that is not a
-multiple of the I/O@ block size, you can use the @samp{skip_bytes},
-@samp{seek_bytes} and @samp{count_bytes} flags.  Alternatively
-the traditional method of separate @command{dd} invocations can be used.
+To process data with offset or size that is not a multiple of the I/O
+block size, you can use a numeric string @var{n} that ends in the
+letter @samp{B}.
 For example, the following shell commands copy data
-in 512 KiB blocks between a flash drive and a tape, but do not save
-or restore a 1 MiB area at the start of the flash drive:
+in 1 MiB blocks between a flash drive and a tape, but do not save
+or restore a 512-byte area at the start of the flash drive:
 
 @example
 flash=/dev/sda
 tape=/dev/st0
 
-# Copy all but the initial 1 MiB from flash to tape.
-(dd bs=1M skip=1 count=0 && dd bs=512k) <$flash >$tape
+# Copy all but the initial 512 bytes from flash to tape.
+dd if=$flash iseek=512B bs=1MiB of=$tape
 
-# Copy from tape back to flash, leaving initial 1 MiB alone.
-(dd bs=1M seek=1 count=0 && dd bs=512k) <$tape >$flash
+# Copy from tape back to flash, leaving initial 512 bytes alone.
+dd if=$tape bs=1MiB of=$flash oseek=512B
 @end example
 
 @cindex ddrescue
@@ -9739,8 +9796,8 @@ The program accepts the following options.  Also see @ref{Common options}.
 @itemx --compare
 @opindex -C
 @opindex --compare
-Compare each pair of source and destination files, and if the destination has
-identical content and any specified owner, group, permissions, and possibly
+Compare content of source and destination files, and if there would be no
+change to the destination content, owner, group, permissions, and possibly
 SELinux context, then do not modify the destination at all.
 Note this option is best used in conjunction with @option{--user},
 @option{--group} and @option{--mode} options, lest @command{install}
@@ -11261,7 +11318,8 @@ or group ID, then you may specify it with a leading @samp{+}.
 Some older scripts may still use @samp{.} in place of the @samp{:} separator.
 POSIX 1003.1-2001 (@pxref{Standards conformance}) does not
 require support for that, but for backward compatibility GNU
-@command{chown} supports @samp{.} so long as no ambiguity results.
+@command{chown} supports @samp{.} so long as no ambiguity results,
+although it issues a warning and support may be removed in future versions.
 New scripts should avoid the use of @samp{.} because it is not
 portable, and because it has undesirable results if the entire
 @var{owner@samp{.}group} happens to identify a user whose name
@@ -11609,7 +11667,7 @@ The program accepts the following options.  Also see @ref{Common options}.
 @opindex -c
 @opindex --changes
 Verbosely describe the action for each @var{file} whose permissions
-actually changes.
+actually change.
 
 @item -f
 @itemx --silent
@@ -12550,6 +12608,7 @@ Always read the already cached attributes if available.
 
 @item never
 Always sychronize with the latest file system attributes.
+This also mounts automounted files.
 
 @item default
 Leave the caching behavior to the underlying file system.
@@ -12896,6 +12955,13 @@ echo [@var{option}]@dots{} [@var{string}]@dots{}
 
 @mayConflictWithShellBuiltIn{echo}
 
+Due to historical and backwards compatibility reasons, certain bare option-like
+strings cannot be passed to @command{echo} as non-option arguments.
+It is therefore not advisable to use @command{echo} for printing unknown or
+variable arguments.  The @command{printf} command is recommended as a more
+portable and flexible replacement for tasks historically performed by
+@command{echo}.  @xref{printf invocation}.
+
 The program accepts the following options.  Also see @ref{Common options}.
 Options must precede operands, and the normally-special argument
 @samp{--} has no special meaning and is treated like any other
@@ -12961,13 +13027,15 @@ If the @env{POSIXLY_CORRECT} environment variable is set, then when
 option-like arguments instead of treating them as options.  For
 example, @code{echo -ne hello} outputs @samp{-ne hello} instead of
 plain @samp{hello}.  Also backslash escapes are always enabled.
+Note to echo the string @samp{-n}, one of the characters
+can be escaped in either octal or hexadecimal representation.
+For example, @code{echo -e '\x2dn'}.
 
 POSIX does not require support for any options, and says
 that the behavior of @command{echo} is implementation-defined if any
-@var{string} contains a backslash or if the first argument is
-@option{-n}.  Portable programs can use the @command{printf} command
-if they need to omit trailing newlines or output control characters or
-backslashes.  @xref{printf invocation}.
+@var{string} contains a backslash or if the first argument is @option{-n}.
+Portable programs should use the @command{printf} command instead.
+@xref{printf invocation}.
 
 @exitstatus
 
@@ -13383,7 +13451,7 @@ True if @var{file} exists and has its @dfn{sticky} bit set.
 @item -r @var{file}
 @opindex -r
 @cindex readable file check
-True if @var{file} exists and read permission is granted.
+True if @var{file} exists and the user has read access.
 
 @item -u @var{file}
 @opindex -u
@@ -13393,12 +13461,12 @@ True if @var{file} exists and has its set-user-ID bit set.
 @item -w @var{file}
 @opindex -w
 @cindex writable file check
-True if @var{file} exists and write permission is granted.
+True if @var{file} exists and the user has write access.
 
 @item -x @var{file}
 @opindex -x
 @cindex executable file check
-True if @var{file} exists and execute permission is granted
+True if @var{file} exists and the user has execute access
 (or search permission, if it is a directory).
 
 @item -O @var{file}
@@ -13910,11 +13978,11 @@ If a file being written to does not already exist, it is created.  If a
 file being written to already exists, the data it previously contained
 is overwritten unless the @option{-a} option is used.
 
-In previous versions of GNU coreutils (v5.3.0 - v8.23), a @var{file} of @samp{-}
+In previous versions of GNU Coreutils (v5.3.0 -- v8.23),
+a @var{file} of @samp{-}
 caused @command{tee} to send another copy of input to standard output.
 However, as the interleaved output was not very useful, @command{tee} now
-conforms to POSIX which explicitly mandates it to treat @samp{-} as a file
-with such name.
+conforms to POSIX and treats @samp{-} as a file name.
 
 The program accepts the following options.  Also see @ref{Common options}.
 
@@ -15967,6 +16035,11 @@ date [-u|--utc|--universal] @c this avoids a newline in the output
 [ MMDDhhmm[[CC]YY][.ss] ]
 @end example
 
+The @command{date} command displays the date and time.
+With the @option{--set} (@option{-s}) option, or with
+@samp{MMDDhhmm[[CC]YY][.ss]},
+it sets the date and time.
+
 @vindex LC_TIME
 Invoking @command{date} with no @var{format} argument is equivalent to invoking
 it with a default format that depends on the @env{LC_TIME} locale category.
@@ -16218,6 +16291,12 @@ The following optional flags can appear after the @samp{%}:
 (hyphen) Do not pad the field; useful if the output is intended for
 human consumption.
 This is a GNU extension.
+As a special case, @samp{%-N} outputs only enough trailing digits to
+not lose information, assuming that the timestamp's resolution is the
+same as the current hardware clock.  For example, if the hardware
+clock resolution is 1 microsecond, @samp{%s.%-N} outputs something
+like @samp{1640890100.395710}.
+
 @item _
 (underscore) Pad with spaces; useful if you need a fixed
 number of characters in the output, but zeros are too distracting.
@@ -16294,17 +16373,18 @@ modifiers are GNU extensions.
 @cindex time setting
 @cindex appropriate privileges
 
-If given an argument that does not start with @samp{+}, @command{date} sets
-the system clock to the date and time specified by that argument (as
-described below).  You must have appropriate privileges to set the
-system clock.  Note for changes to persist across a reboot, the
+You must have appropriate privileges to set the
+system clock.  For changes to persist across a reboot, the
 hardware clock may need to be updated from the system clock, which
 might not happen automatically on your system.
 
-The argument must consist entirely of digits, which have the following
-meaning:
+To set the clock, you can use the @option{--set} (@option{-s}) option
+(@pxref{Options for date}).  To set the clock without using GNU
+extensions, you can give @command{date} an argument of the form
+@samp{MMDDhhmm[[CC]YY][.ss]} where each two-letter
+component stands for two digits with the following meanings:
 
-@table @samp
+@table @var
 @item MM
 month
 @item DD
@@ -16334,6 +16414,7 @@ relative to Universal Time rather than to the local time zone.
 @cindex options for @command{date}
 
 The program accepts the following options.  Also see @ref{Common options}.
+Except for @option{-u}, these options are all GNU extensions to POSIX.
 
 @table @samp
 
@@ -16421,6 +16502,19 @@ for the @option{--date} (@option{-d}) and @option{--file}
 Display the date and time of the last modification of @var{file},
 instead of the current date and time.
 
+@item --resolution
+@opindex --resolution
+Display the timestamp resolution instead of the time.
+Current clock timestamps that are output by @command{date}
+are integer multiples of the timestamp resolution.
+With this option, the format defaults to @samp{%s.%N}.
+For example, if the clock resolution is 1 millsecond,
+the output is:
+
+@example
+0.001000000
+@end example
+
 @item -R
 @itemx --rfc-email
 @opindex -R
@@ -16449,7 +16543,8 @@ For compatibility with older versions of @command{date},
 Display the date using a format specified by
 @uref{https://tools.ietf.org/search/rfc3339, Internet
 RFC 3339}.  This is like @option{--iso-8601}, except that a space rather
-than a @samp{T} separates dates from times.
+than a @samp{T} separates dates from times, and a period rather than
+a comma separates seconds from subseconds.
 @dateParseNote
 
 The argument @var{timespec} specifies how much of the time to include.
@@ -18273,8 +18368,9 @@ The specified @var{duration} starts from the point in time when
 @command{timeout} sends the initial signal to @var{command}, i.e.,
 not from the beginning when the @var{command} is started.
 
-This option has no effect if @command{timeout}'s duration is 0 which
-disables the associated timeout.
+This option has no effect if either the main @var{duration}
+of the @command{timeout} command, or the @var{duration} specified
+to this option, is 0.
 
 This option may be useful if the selected signal did not kill the @var{command},
 either because the signal was blocked or ignored, or if the @var{command} takes
@@ -18321,7 +18417,7 @@ Exit status:
 the exit status of @var{command} otherwise
 @end display
 
-In case of the @samp{KILL(9)} signal, @command{timeout} returns with
+In the case of the @samp{KILL(9)} signal, @command{timeout} returns with
 exit status 137, regardless of whether that signal is sent to @var{command}
 or to @command{timeout} itself, i.e., these cases cannot be distinguished.
 In the latter case, the @var{command} process may still be alive after

doc/fdl.texi

@@ -414,7 +414,7 @@ The Free Software Foundation may publish new, revised versions
 of the GNU Free Documentation License from time to time.  Such new
 versions will be similar in spirit to the present version, but may
 differ in detail to address new problems or concerns.  See
-@uref{https://www.gnu.org/copyleft/}.
+@uref{https://www.gnu.org/licenses/}.
 
 Each version of the License is given a distinguishing version number.
 If the Document specifies that a particular numbered version of this

doc/local.mk

@@ -1,7 +1,7 @@
 # Make coreutils documentation.				-*-Makefile-*-
 # This is included by the top-level Makefile.am.
 
-# Copyright (C) 1995-2021 Free Software Foundation, Inc.
+# Copyright (C) 1995-2022 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

doc/perm.texi

@@ -1,6 +1,6 @@
 @c File mode bits
 
-@c Copyright (C) 1994--2021 Free Software Foundation, Inc.
+@c Copyright (C) 1994--2022 Free Software Foundation, Inc.
 
 @c Permission is granted to copy, distribute and/or modify this document
 @c under the terms of the GNU Free Documentation License, Version 1.3 or

doc/sort-version.texi

@@ -1,6 +1,6 @@
 @c GNU Version-sort ordering documentation
 
-@c Copyright (C) 2019--2021 Free Software Foundation, Inc.
+@c Copyright (C) 2019--2022 Free Software Foundation, Inc.
 
 @c Permission is granted to copy, distribute and/or modify this document
 @c under the terms of the GNU Free Documentation License, Version 1.3 or
@@ -19,18 +19,17 @@
 @node Version sort overview
 @section Version sort overview
 
-@dfn{version sort} ordering (and similarly, @dfn{natural sort}
-ordering) is a method to sort items such as file names and lines of
-text in an order that feels more natural to people, when the text
+@dfn{Version sort} puts items such as file names and lines of
+text in an order that feels natural to people, when the text
 contains a mixture of letters and digits.
 
-Standard sorting usually does not produce the order that one expects
+Lexicographic sorting usually does not produce the order that one expects
 because comparisons are made on a character-by-character basis.
 
 Compare the sorting of the following items:
 
 @example
-Alphabetical sort:           Version Sort:
+Lexicographic sort:          Version Sort:
 
 a1                           a1
 a120                         a2
@@ -38,18 +37,19 @@ a13                          a13
 a2                           a120
 @end example
 
-version sort functionality in GNU coreutils is available in the @samp{ls -v},
-@samp{ls --sort=version}, @samp{sort -V}, @samp{sort --version-sort} commands.
+Version sort functionality in GNU Coreutils is available in the @samp{ls -v},
+@samp{ls --sort=version}, @samp{sort -V}, and
+@samp{sort --version-sort} commands.
 
 
 
-@node Using version sort in GNU coreutils
-@subsection Using version sort in GNU coreutils
+@node Using version sort in GNU Coreutils
+@subsection Using version sort in GNU Coreutils
 
-Two GNU coreutils programs use version sort: @command{ls} and @command{sort}.
+Two GNU Coreutils programs use version sort: @command{ls} and @command{sort}.
 
 To list files in version sort order, use @command{ls}
-with @option{-v} or @option{--sort=version} options:
+with the @option{-v} or @option{--sort=version} option:
 
 @example
 default sort:              version sort:
@@ -64,7 +64,7 @@ a2                         a100
 @end example
 
 To sort text files in version sort order, use @command{sort} with
-the @option{-V} option:
+the @option{-V} or @option{--version-sort} option:
 
 @example
 $ cat input
@@ -74,7 +74,7 @@ b1
 b20
 
 
-alphabetical order:        version sort order:
+lexicographic order:       version sort order:
 
 $ sort input               $ sort -V input
 b1                         b1
@@ -83,71 +83,71 @@ b20                        b11
 b3                         b20
 @end example
 
-To sort a specific column in a file use @option{-k/--key} with @samp{V}
-ordering option:
+To sort a specific field in a file, use @option{-k/--key} with
+@samp{V} type sorting, which is often combined with @samp{b} to
+ignore leading blanks in the field:
 
 @example
 $ cat input2
-1000  b3   apples
+100   b3   apples
 2000  b11  oranges
 3000  b1   potatoes
 4000  b20  bananas
-
-$ sort -k2V,2 input2
+$ sort -k 2bV,2 input2
 3000  b1   potatoes
-1000  b3   apples
+100   b3   apples
 2000  b11  oranges
 4000  b20  bananas
 @end example
 
-@node Origin of version sort and differences from natural sort
-@subsection Origin of version sort and differences from natural sort
+@node Version sort and natural sort
+@subsection Version sort and natural sort
 
-In GNU coreutils, the name @dfn{version sort} was chosen because it is based
+In GNU Coreutils, the name @dfn{version sort} was chosen because it is based
 on Debian GNU/Linux's algorithm of sorting packages' versions.
 
-Its goal is to answer the question
-``which package is newer, @file{firefox-60.7.2} or @file{firefox-60.12.3} ?''
+Its goal is to answer questions like
+``Which package is newer, @file{firefox-60.7.2} or @file{firefox-60.12.3}?''
 
-In coreutils this algorithm was slightly modified to work on more
+In Coreutils this algorithm was slightly modified to work on more
 general input such as textual strings and file names
-(see @ref{Differences from the official Debian Algorithm}).
+(see @ref{Differences from Debian version sort}).
 
 In other contexts, such as other programs and other programming
 languages, a similar sorting functionality is called
 @uref{https://en.wikipedia.org/wiki/Natural_sort_order,natural sort}.
 
 
-@node Correct/Incorrect ordering and Expected/Unexpected results
-@subsection Correct/Incorrect ordering and Expected/Unexpected results
+@node Variations in version sort order
+@subsection Variations in version sort order
 
-Currently there is no standard for version/natural sort ordering.
+Currently there is no standard for version sort.
 
 That is: there is no one correct way or universally agreed-upon way to
 order items. Each program and each programming language can decide its
-own ordering algorithm and call it 'natural sort' (or other various
-names).
+own ordering algorithm and call it ``version sort'', ``natural sort'',
+or other names.
 
 See @ref{Other version/natural sort implementations} for many examples of
 differing sorting possibilities, each with its own rules and variations.
 
-If you do suspect a bug in coreutils' implementation of version-sort,
-see @ref{Reporting bugs or incorrect results} on how to report them.
+If you find a bug in the Coreutils implementation of version-sort, please
+report it.  @xref{Reporting version sort bugs}.
 
 
-@node Implementation Details
-@section Implementation Details
+@node Version sort implementation
+@section Version sort implementation
 
-GNU coreutils' version sort algorithm is based on
+GNU Coreutils version sort is based on the ``upstream version''
+part of
 @uref{https://www.debian.org/doc/debian-policy/ch-controlfields.html#version,
-Debian's versioning scheme}, specifically on the "upstream version"
-part.
+Debian's versioning scheme}.
 
-This section describes the ordering rules.
+This section describes the GNU Coreutils sort ordering rules.
 
-The next section (@ref{Differences from the official Debian
-Algorithm}) describes some differences between GNU coreutils
-implementation and Debian's official algorithm.
+The next section (@ref{Differences from Debian version
+sort}) describes some differences between GNU Coreutils
+and Debian version sort.
 
 
 @node Version-sort ordering rules
@@ -161,33 +161,40 @@ The strings are compared from left to right.
 
 @item
 First the initial part of each string consisting entirely of non-digit
-characters is determined.
+bytes is determined.
 
-@enumerate
+@enumerate A
 @item
-These two parts (one of which may be empty) are compared lexically.
+These two parts (either of which may be empty) are compared lexically.
 If a difference is found it is returned.
 
 @item
-The lexical comparison is a comparison of ASCII values modified so that:
+The lexical comparison is a lexicographic comparison of byte strings,
+except that:
 
-@enumerate
+@enumerate a
 @item
-all the letters sort earlier than all the non-letters and
+ASCII letters sort before other bytes.
 @item
-so that a tilde sorts before anything, even the end of a part.
+A tilde sorts before anything, even an empty string.
 @end enumerate
 @end enumerate
 
 @item
-Then the initial part of the remainder of each string which consists
-entirely of digit characters is determined. The numerical values of
+Then the initial part of the remainder of each string that contains
+all the leading digits is determined. The numerical values represented by
 these two parts are compared, and any difference found is returned as
 the result of the comparison.
-@enumerate
+
+@enumerate A
 @item
 For these purposes an empty string (which can only occur at the end of
 one or both version strings being compared) counts as zero.
+
+@item
+Because the numerical value is used, non-identical strings can compare
+equal.  For example, @samp{123} compares equal to @samp{00123}, and
+the empty string compares equal to @samp{0}.
 @end enumerate
 
 @item
@@ -202,8 +209,8 @@ down to the following parts, and the parts compared respectively from
 each string:
 
 @example
-foo  @r{vs}  foo   @r{(rule 2, non-digits characters)}
-07   @r{vs}  7     @r{(rule 3, digits characters)}
+foo  @r{vs}  foo   @r{(rule 2, non-digits)}
+07   @r{vs}  7     @r{(rule 3, digits)}
 .    @r{vs}  a.    @r{(rule 2)}
 7    @r{vs}  7     @r{(rule 3)}
 z    @r{vs}  z     @r{(rule 2)}
@@ -213,23 +220,23 @@ Comparison flow based on above algorithm:
 
 @enumerate
 @item
-The first parts (@code{foo}) are identical in both strings.
+The first parts (@samp{foo}) are identical.
 
 @item
-The second parts (@code{07} and @code{7}) are compared numerically,
-and are identical.
+The second parts (@samp{07} and @samp{7}) are compared numerically,
+and compare equal.
 
 @item
-The third parts (@samp{@code{.}} vs @samp{@code{a.}}) are compared
-lexically by ASCII value (rule 2.2).
+The third parts (@samp{.} vs @samp{a.}) are compared
+lexically by ASCII value (rule 2.B).
 
 @item
-The first character of the first string (@samp{@code{.}}) is compared
-to the first character of the second string (@samp{@code{a}}).
+The first byte of the first string (@samp{.}) is compared
+to the first byte of the second string (@samp{a}).
 
 @item
-Rule 2.2.1 dictates that "all letters sorts earlier than all non-letters".
-Hence, @samp{@code{a}} comes before @samp{@code{.}}.
+Rule 2.B.a says letters sorts before non-letters.
+Hence, @samp{a} comes before @samp{.}.
 
 @item
 The returned result is that @file{foo7a.7z} comes before @file{foo07.7z}.
@@ -241,14 +248,13 @@ Result when using sort:
 $ cat input3
 foo07.7z
 foo7a.7z
-
 $ sort -V input3
 foo7a.7z
 foo07.7z
 @end example
 
-See @ref{Differences from the official Debian Algorithm} for
-additional rules that extend the Debian algorithm in coreutils.
+See @ref{Differences from Debian version sort} for
+additional rules that extend the Debian algorithm in Coreutils.
 
 
 @node Version sort is not the same as numeric sort
@@ -266,8 +272,6 @@ $ cat input4
 8.100
 8.49
 
-
-
 Numerical Sort:                   Version Sort:
 
 $ sort -n input4                  $ sort -V input4
@@ -281,64 +285,63 @@ $ sort -n input4                  $ sort -V input4
 @end example
 
 Numeric sort (@samp{sort -n}) treats the entire string as a single numeric
-value, and compares it to other values. For example, @code{8.1}, @code{8.10} and
-@code{8.100} are numerically equivalent, and are ordered together. Similarly,
-@code{8.49} is numerically smaller than @code{8.5}, and appears before first.
+value, and compares it to other values. For example, @samp{8.1}, @samp{8.10} and
+@samp{8.100} are numerically equivalent, and are ordered together. Similarly,
+@samp{8.49} is numerically less than @samp{8.5}, and appears before first.
 
-Version sort (@samp{sort -V}) first breaks down the string into digits and
-non-digits parts, and only then compares each part (see annotated
-example in Version-sort ordering rules).
+Version sort (@samp{sort -V}) first breaks down the string into digit and
+non-digit parts, and only then compares each part (see annotated
+example in @ref{Version-sort ordering rules}).
 
-Comparing the string @code{8.1} to @code{8.01}, first the
-@samp{@code{8}} characters are compared (and are identical), then the
-dots (@samp{@code{.}}) are compared and are identical, and lastly the
-remaining digits are compared numerically (@code{1} and @code{01}) -
-which are numerically equivalent. Hence, @code{8.01} and @code{8.1}
+Comparing the string @samp{8.1} to @samp{8.01}, first the
+@samp{8}s are compared (and are identical), then the
+dots (@samp{.}) are compared and are identical, and lastly the
+remaining digits are compared numerically (@samp{1} and @samp{01}) -
+which are numerically equal.  Hence, @samp{8.01} and @samp{8.1}
 are grouped together.
 
-Similarly, comparing @code{8.5} to @code{8.49} - the @samp{@code{8}}
-and @samp{@code{.}} parts are identical, then the numeric values @code{5} and
-@code{49} are compared. The resulting @code{5} appears before @code{49}.
+Similarly, comparing @samp{8.5} to @samp{8.49} -- the @samp{8}
+and @samp{.} parts are identical, then the numeric values @samp{5} and
+@samp{49} are compared. The resulting @samp{5} appears before @samp{49}.
 
-This sorting order (where @code{8.5} comes before @code{8.49}) is common when
+This sorting order (where @samp{8.5} comes before @samp{8.49}) is common when
 assigning versions to computer programs (while perhaps not intuitive
-or 'natural' for people).
+or ``natural'' for people).
 
-@node Punctuation Characters
-@subsection Punctuation Characters
+@node Version sort punctuation
+@subsection Version sort punctuation
 
-Punctuation characters are sorted by ASCII order (rule 2.2).
+Punctuation is sorted by ASCII order (rule 2.B).
 
 @example
-$ touch    1.0.5_src.tar.gz    1.0_src.tar.gz
-
+$ touch 1.0.5_src.tar.gz 1.0_src.tar.gz
 $ ls -v -1
 1.0.5_src.tar.gz
 1.0_src.tar.gz
 @end example
 
-Why is @file{1.0.5_src.tar.gz} listed before @file{1.0_src.tar.gz} ?
+Why is @file{1.0.5_src.tar.gz} listed before @file{1.0_src.tar.gz}?
 
-Based on the @ref{Version-sort ordering rules,algorithm,algorithm}
-above, the strings are broken down into the following parts:
+Based on the version-sort ordering rules, the strings are broken down
+into the following parts:
 
 @example
-          1   @r{vs}  1               @r{(rule 3, all digit characters)}
-          .   @r{vs}  .               @r{(rule 2, all non-digit characters)}
+          1   @r{vs}  1               @r{(rule 3, all digits)}
+          .   @r{vs}  .               @r{(rule 2, all non-digits)}
           0   @r{vs}  0               @r{(rule 3)}
           .   @r{vs}  _src.tar.gz     @r{(rule 2)}
-          5   @r{vs}  empty string    @r{(no more character in the file name)}
+          5   @r{vs}  empty string    @r{(no more bytes in the file name)}
 _src.tar.gz   @r{vs}  empty string
 @end example
 
-The fourth parts (@samp{@code{.}} and @code{_src.tar.gz}) are compared
-lexically by ASCII order. The character @samp{@code{.}} (ASCII value 46) is
-smaller than @samp{@code{_}} (ASCII value 95) - and should be listed before it.
+The fourth parts (@samp{.} and @samp{_src.tar.gz}) are compared
+lexically by ASCII order. The @samp{.} (ASCII value 46) is
+less than @samp{_} (ASCII value 95) -- and should be listed before it.
 
 Hence, @file{1.0.5_src.tar.gz} is listed first.
 
-If a different character appears instead of the underscore (for
-example, percent sign @samp{@code{%}} ASCII value 37, which is smaller
+If a different byte appears instead of the underscore (for
+example, percent sign @samp{%} ASCII value 37, which is less
 than dot's ASCII value of 46), that file will be listed first:
 
 @example
@@ -347,55 +350,52 @@ $ touch   1.0.5_src.tar.gz     1.0%zzzzz.gz
 1.0.5_src.tar.gz
 @end example
 
-The same reasoning applies to the following example: The character
-@samp{@code{.}}  has ASCII value 46, and is smaller than slash
-character @samp{@code{/}} ASCII value 47:
+The same reasoning applies to the following example, as @samp{.} with
+ASCII value 46 is less than @samp{/} with ASCII value 47:
 
 @example
 $ cat input5
 3.0/
 3.0.5
-
 $ sort -V input5
 3.0.5
 3.0/
 @end example
 
 
-@node Punctuation Characters vs letters
-@subsection Punctuation Characters vs letters
+@node Punctuation vs letters
+@subsection Punctuation vs letters
 
-Rule 2.2.1 dictates that letters sorts earlier than all non-letters
-(after breaking down a string to digits and non-digits parts).
+Rule 2.B.a says letters sort before non-letters
+(after breaking down a string to digit and non-digit parts).
 
 @example
 $ cat input6
 a%
 az
-
 $ sort -V input6
 az
 a%
 @end example
 
 The input strings consist entirely of non-digits, and based on the
-above algorithm have only one part, all non-digit characters
-(@samp{@code{a%}} vs @samp{@code{az}}).
+above algorithm have only one part, all non-digits
+(@samp{a%} vs @samp{az}).
 
 Each part is then compared lexically,
-character-by-character. @samp{@code{a}} compares identically in both
+byte-by-byte; @samp{a} compares identically in both
 strings.
 
-Rule 2.2.1 dictates that letters (@samp{@code{z}}) sorts earlier than all
-non-letters (@samp{@code{%}}) - hence @samp{@code{az}} appears first (despite
-@samp{@code{z}} having ASCII value of 122, much bigger than @samp{@code{%}}
+Rule 2.B.a says a letter like @samp{z} sorts before
+a non-letter like @samp{%} -- hence @samp{az} appears first (despite
+@samp{z} having ASCII value of 122, much larger than @samp{%}
 with ASCII value 37).
 
-@node Tilde @samp{~} character
-@subsection Tilde @samp{~} character
+@node The tilde @samp{~}
+@subsection The tilde @samp{~}
 
-Rule 2.2.2 dictates that tilde character @samp{@code{~}} (ASCII 126) sorts
-before all other non-digit characters, including an empty part.
+Rule 2.B.b says the tilde @samp{~} (ASCII 126) sorts
+before other bytes, and before an empty string.
 
 @example
 $ cat input7
@@ -404,7 +404,6 @@ $ cat input7
 1.2
 1~
 ~
-
 $ sort -V input7
 ~
 1~
@@ -414,42 +413,42 @@ $ sort -V input7
 @end example
 
 The sorting algorithm starts by breaking down the string into
-non-digits (rule 2) and digits parts (rule 3).
+non-digit (rule 2) and digit parts (rule 3).
 
 In the above input file, only the last line in the input file starts
-with a non-digit (@samp{@code{~}}). This is the first part. All other lines
-in the input file start with a digit - their first non-digit part is
+with a non-digit (@samp{~}). This is the first part. All other lines
+in the input file start with a digit -- their first non-digit part is
 empty.
 
-Based on rule 2.2.2, tilde @samp{@code{~}} sorts before all other non-digits
-including the empty part - hence it comes before all other strings,
+Based on rule 2.B.b, tilde @samp{~} sorts before other bytes
+and before the empty string -- hence it comes before all other strings,
 and is listed first in the sorted output.
 
-The remaining lines (@code{1}, @code{1%}, @code{1.2}, @code{1~})
+The remaining lines (@samp{1}, @samp{1%}, @samp{1.2}, @samp{1~})
 follow similar logic: The digit part is extracted (1 for all strings)
-and compares identical. The following extracted parts for the remaining
-input lines are: empty part, @code{%}, @code{.}, @code{~}.
+and compares equal. The following extracted parts for the remaining
+input lines are: empty part, @samp{%}, @samp{.}, @samp{~}.
 
-Tilde sorts before all others, hence the line @code{1~} appears next.
+Tilde sorts before all others, hence the line @samp{1~} appears next.
 
-The remaining lines (@code{1}, @code{1%}, @code{1.2}) are sorted based
+The remaining lines (@samp{1}, @samp{1%}, @samp{1.2}) are sorted based
 on previously explained rules.
 
 @node Version sort ignores locale
-@subsection Version sort uses ASCII order, ignores locale, unicode characters
+@subsection Version sort ignores locale
 
-In version sort, unicode characters are compared byte-by-byte according
-to their binary representation, ignoring their unicode value or the
+In version sort, Unicode characters are compared byte-by-byte according
+to their binary representation, ignoring their Unicode value or the
 current locale.
 
-Most commonly, unicode characters (e.g. Greek Small Letter Alpha
-U+03B1 @samp{α}) are encoded as UTF-8 bytes (e.g. @samp{α} is encoded as UTF-8
-sequence @code{0xCE 0xB1}). The encoding will be compared byte-by-byte,
-e.g. first @code{0xCE} (decimal value 206) then @code{0xB1} (decimal value 177).
+Most commonly, Unicode characters are encoded as UTF-8 bytes; for
+example, GREEK SMALL LETTER ALPHA (U+03B1, @samp{α}) is encoded as the
+UTF-8 sequence @samp{0xCE 0xB1}).  The encoding is compared
+byte-by-byte, e.g., first @samp{0xCE} (decimal value 206) then
+@samp{0xB1} (decimal value 177).
 
 @example
-$ touch   aa    az    "a%"    "aα"
-
+$ touch aa az "a%" "aα"
 $ ls -1 -v
 aa
 az
@@ -457,32 +456,32 @@ a%
 aα
 @end example
 
-Ignoring the first letter (@code{a}) which is identical in all
+Ignoring the first letter (@samp{a}) which is identical in all
 strings, the compared values are:
 
-@samp{@code{a}} and @samp{@code{z}} are letters, and sort earlier than
-all other non-digit characters.
+@samp{a} and @samp{z} are letters, and sort before
+all other non-digits.
 
-Then, percent sign @samp{@code{%}} (ASCII value 37) is compared to the
-first byte of the UTF-8 sequence of @samp{@code{α}}, which is 0xCE or 206). The
-value 37 is smaller, hence @samp{@code{a%}} is listed before @samp{@code{aα}}.
+Then, percent sign @samp{%} (ASCII value 37) is compared to the
+first byte of the UTF-8 sequence of @samp{α}, which is 0xCE or 206). The
+value 37 is smaller, hence @samp{a%} is listed before @samp{aα}.
 
-@node Differences from the official Debian Algorithm
-@section Differences from the official Debian Algorithm
+@node Differences from Debian version sort
+@section Differences from Debian version sort
 
-The GNU coreutils' version sort algorithm differs slightly from the
+GNU Coreutils version sort differs slightly from the
 official Debian algorithm, in order to accommodate more general usage
 and file name listing.
 
 
-@node Minus/Hyphen and Colon characters
-@subsection Minus/Hyphen @samp{-} and Colon @samp{:} characters
+@node Hyphen-minus and colon
+@subsection Hyphen-minus @samp{-} and colon @samp{:}
 
 In Debian's version string syntax the version consists of three parts:
 @example
 [epoch:]upstream_version[-debian_revision]
 @end example
-The @code{epoch} and @code{debian_revision} parts are optional.
+The @samp{epoch} and @samp{debian_revision} parts are optional.
 
 Example of such version strings:
 
@@ -495,62 +494,62 @@ Example of such version strings:
 2:1.19.2-1+deb9u5
 @end example
 
-If the @code{debian_revision part} is not present,
-hyphen characters @samp{-} are not allowed.
+If the @samp{debian_revision part} is not present,
+hyphens @samp{-} are not allowed.
 If epoch is not present, colons @samp{:} are not allowed.
 
 If these parts are present, hyphen and/or colons can appear only once
 in valid Debian version strings.
 
-In GNU coreutils, such restrictions are not reasonable (a file name can
+In GNU Coreutils, such restrictions are not reasonable (a file name can
 have many hyphens, a line of text can have many colons).
 
-As a result, in GNU coreutils hyphens and colons are treated exactly
-like all other punctuation characters (i.e., they are sorted after
-letters. See Punctuation Characters above).
+As a result, in GNU Coreutils hyphens and colons are treated exactly
+like all other punctuation, i.e., they are sorted after
+letters.  @xref{Version sort punctuation}.
 
-In Debian, these characters are treated differently than in coreutils:
+In Debian, these characters are treated differently than in Coreutils:
 a version string with hyphen will sort before similar strings without
 hyphens.
 
 Compare:
 
 @example
-$ touch   abb   ab-cd
-
+$ touch 1ab-cd 1abb
 $ ls -v -1
-abb
-ab-cd
+1abb
+1ab-cd
+$ if dpkg --compare-versions 1abb lt 1ab-cd
+> then echo sorted
+> else echo out of order
+> fi
+out of order
 @end example
 
-With Debian's @command{dpkg} they will be listed as @code{ab-cd} first and
-@code{abb} second.
+For further details, see @ref{Comparing two strings using Debian's
+algorithm} and @uref{https://bugs.gnu.org/35939,GNU Bug 35939}.
 
-For further technical details see @uref{https://bugs.gnu.org/35939,bug35939}.
+@node Special priority in GNU Coreutils version sort
+@subsection Special priority in GNU Coreutils version sort
 
-@node Additional hard-coded priorities in GNU coreutils' version sort
-@subsection Additional hard-coded priorities in GNU coreutils' version sort
-
-In GNU coreutils' version sort algorithm, the following items have
-special priority and sort earlier than all other characters (listed in
-order);
+In GNU Coreutils version sort, the following items have
+special priority and sort before all other strings (listed in order):
 
 @enumerate
 @item The empty string
 
-@item The string @samp{@code{.}} (a single dot character, ASCII 46)
+@item The string @samp{.} (a single dot, ASCII 46)
 
-@item The string @samp{@code{..}} (two dot characters)
+@item The string @samp{..} (two dots)
 
-@item Strings start with a dot (@samp{@code{.}}) sort earlier than
-strings starting with any other characters.
+@item Strings starting with dot (@samp{.}) sort before
+strings starting with any other byte.
 @end enumerate
 
 Example:
 
 @example
-$ printf "%s\n" a "" b "." c  ".."  ".d20" ".d3"  | sort -V
-
+$ printf '%s\n' a "" b "." c  ".."  ".d20" ".d3"  | sort -V
 .
 ..
 .d3
@@ -561,7 +560,7 @@ c
 @end example
 
 These priorities make perfect sense for @samp{ls -v}: The special
-files dot @samp{@code{.}} and dot-dot @samp{@code{..}} will be listed
+files dot @samp{.} and dot-dot @samp{..} will be listed
 first, followed by any hidden files (files starting with a dot),
 followed by non-hidden files.
 
@@ -572,71 +571,76 @@ program, the ordering rules are the same.
 @node Special handling of file extensions
 @subsection Special handling of file extensions
 
-GNU coreutils' version sort algorithm implements specialized handling
-of file extensions (or strings that look like file names with
-extensions).
+GNU Coreutils version sort implements specialized handling
+of strings that look like file names with extensions.
+This enables slightly more natural ordering of file
+names.
 
-This nuanced implementation enables slightly more natural ordering of files.
-
-The additional rules are:
+The following additional rules apply when comparing two strings where
+both begin with non-@samp{.}.  They also apply when comparing two
+strings where both begin with @samp{.} but neither is @samp{.} or @samp{..}.
 
 @enumerate
 @item
-A suffix (i.e., a file extension) is defined as: a dot, followed by a
-letter or tilde, followed by one or more letters, digits, or tildes
-(possibly repeated more than once), until the end of the string
-(technically, matching the regular expression
-@code{(\.[A-Za-z~][A-Za-z0-9~]*)*}).
+A suffix (i.e., a file extension) is defined as: a dot, followed by an
+ASCII letter or tilde, followed by zero or more ASCII letters, digits,
+or tildes; all repeated zero or more times, and ending at string end.
+This is equivalent to matching the extended regular expression
+@code{(\.[A-Za-z~][A-Za-z0-9~]*)*$} in the C locale.
 
 @item
-If the strings contains suffixes, the suffixes are temporarily
-removed, and the strings are compared without them (using the
-@ref{Version-sort ordering rules,algorithm,algorithm} above).
+The suffixes are temporarily removed, and the strings are compared
+without them, using version sort (see @ref{Version-sort ordering
+rules}) without special priority (see @ref{Special priority in GNU
+Coreutils version sort}).
 
 @item
-If the suffix-less strings are identical, the suffix is restored and
-the entire strings are compared.
+If the suffix-less strings do not compare equal, this comparison
+result is used and the suffixes are effectively ignored.
 
 @item
-If the non-suffixed strings differ, the result is returned and the
-suffix is effectively ignored.
+If the suffix-less strings compare equal, the suffixes are restored
+and the entire strings are compared using version sort.
 @end enumerate
 
 Examples for rule 1:
 
 @itemize
 @item
-@code{hello-8.txt}: the suffix is @code{.txt}
+@samp{hello-8.txt}: the suffix is @samp{.txt}
 
 @item
-@code{hello-8.2.txt}: the suffix is @code{.txt}
-(@samp{@code{.2}} is not included because the dot is not followed by a letter)
+@samp{hello-8.2.txt}: the suffix is @samp{.txt}
+(@samp{.2} is not included because the dot is not followed by a letter)
 
 @item
-@code{hello-8.0.12.tar.gz}: the suffix is @code{.tar.gz} (@samp{@code{.0.12}}
+@samp{hello-8.0.12.tar.gz}: the suffix is @samp{.tar.gz} (@samp{.0.12}
 is not included)
 
 @item
-@code{hello-8.2}: no suffix (suffix is an empty string)
+@samp{hello-8.2}: no suffix (suffix is an empty string)
 
 @item
-@code{hello.foobar65}: the suffix is @code{.foobar65}
+@samp{hello.foobar65}: the suffix is @samp{.foobar65}
 
 @item
-@code{gcc-c++-10.8.12-0.7rc2.fc9.tar.bz2}: the suffix is
-@code{.fc9.tar.bz2} (@code{.7rc2} is not included as it begins with a digit)
+@samp{gcc-c++-10.8.12-0.7rc2.fc9.tar.bz2}: the suffix is
+@samp{.fc9.tar.bz2} (@samp{.7rc2} is not included as it begins with a digit)
+
+@item
+@samp{.autom4te.cfg}: the suffix is the entire string.
 @end itemize
 
 Examples for rule 2:
 
 @itemize
 @item
-Comparing @code{hello-8.txt} to @code{hello-8.2.12.txt}, the
-@code{.txt} suffix is temporarily removed from both strings.
+Comparing @samp{hello-8.txt} to @samp{hello-8.2.12.txt}, the
+@samp{.txt} suffix is temporarily removed from both strings.
 
 @item
-Comparing @code{foo-10.3.tar.gz} to @code{foo-10.tar.xz}, the suffixes
-@code{.tar.gz} and @code{.tar.xz} are temporarily removed from the
+Comparing @samp{foo-10.3.tar.gz} to @samp{foo-10.tar.xz}, the suffixes
+@samp{.tar.gz} and @samp{.tar.xz} are temporarily removed from the
 strings.
 @end itemize
 
@@ -644,10 +648,10 @@ Example for rule 3:
 
 @itemize
 @item
-Comparing @code{hello.foobar65} to @code{hello.foobar4}, the suffixes
-(@code{.foobar65} and @code{.foobar4}) are temporarily removed. The
-remaining strings are identical (@code{hello}). The suffixes are then
-restored, and the entire strings are compared (@code{hello.foobar4} comes
+Comparing @samp{hello.foobar65} to @samp{hello.foobar4}, the suffixes
+(@samp{.foobar65} and @samp{.foobar4}) are temporarily removed. The
+remaining strings are identical (@samp{hello}). The suffixes are then
+restored, and the entire strings are compared (@samp{hello.foobar4} comes
 first).
 @end itemize
 
@@ -655,10 +659,10 @@ Examples for rule 4:
 
 @itemize
 @item
-When comparing the strings @code{hello-8.2.txt} and @code{hello-8.10.txt}, the
-suffixes (@code{.txt}) are temporarily removed. The remaining strings
-(@code{hello-8.2} and @code{hello-8.10}) are compared as previously described
-(@code{hello-8.2} comes first).
+When comparing the strings @samp{hello-8.2.txt} and @samp{hello-8.10.txt}, the
+suffixes (@samp{.txt}) are temporarily removed. The remaining strings
+(@samp{hello-8.2} and @samp{hello-8.10}) are compared as previously described
+(@samp{hello-8.2} comes first).
 @slanted{(In this case the suffix removal algorithm
 does not have a noticeable effect on the resulting order.)}
 @end itemize
@@ -671,15 +675,15 @@ Without the suffix-removal algorithm, the strings will be broken down
 to the following parts:
 
 @example
-hello-  @r{vs}  hello-  @r{(rule 2, all non-digit characters)}
-8       @r{vs}  8       @r{(rule 3, all digit characters)}
+hello-  @r{vs}  hello-  @r{(rule 2, all non-digits)}
+8       @r{vs}  8       @r{(rule 3, all digits)}
 .txt    @r{vs}  .       @r{(rule 2)}
 empty   @r{vs}  2
 empty   @r{vs}  .txt
 @end example
 
-The comparison of the third parts (@samp{@code{.}} vs
-@samp{@code{.txt}}) will determine that the shorter string comes first -
+The comparison of the third parts (@samp{.} vs
+@samp{.txt}) will determine that the shorter string comes first -
 resulting in @file{hello-8.2.txt} appearing first.
 
 Indeed this is the order in which Debian's @command{dpkg} compares the strings.
@@ -687,17 +691,17 @@ Indeed this is the order in which Debian's @command{dpkg} compares the strings.
 A more natural result is that @file{hello-8.txt} should come before
 @file{hello-8.2.txt}, and this is where the suffix-removal comes into play:
 
-The suffixes (@code{.txt}) are removed, and the remaining strings are
+The suffixes (@samp{.txt}) are removed, and the remaining strings are
 broken down into the following parts:
 
 @example
-hello-  @r{vs}  hello-  @r{(rule 2, all non-digit characters)}
-8       @r{vs}  8       @r{(rule 3, all digit characters)}
+hello-  @r{vs}  hello-  @r{(rule 2, all non-digits)}
+8       @r{vs}  8       @r{(rule 3, all digits)}
 empty   @r{vs}  .       @r{(rule 2)}
 empty   @r{vs}  2
 @end example
 
-As empty strings sort before non-empty strings, the result is @code{hello-8}
+As empty strings sort before non-empty strings, the result is @samp{hello-8}
 being first.
 
 A real-world example would be listing files such as:
@@ -714,10 +718,6 @@ because the sorting code is shared between the @command{ls} and @command{sort}
 program, the ordering rules are the same.
 
 
-@node Advanced Topics
-@section Advanced Topics
-
-
 @node Comparing two strings using Debian's algorithm
 @subsection Comparing two strings using Debian's algorithm
 
@@ -730,13 +730,14 @@ following snippet to your shell command-prompt):
 
 @example
 compver() @{
-  dpkg --compare-versions "$1" lt "$2" \
-    && printf "%s\n" "$1" "$2" \
-    || printf "%s\n" "$2" "$1" ; \
+  if dpkg --compare-versions "$1" lt "$2"
+  then printf '%s\n' "$1" "$2"
+  else printf '%s\n' "$2" "$1"
+  fi
 @}
 @end example
 
-Then compare two strings by calling compver:
+Then compare two strings by calling @command{compver}:
 
 @example
 $ compver 8.49 8.5
@@ -754,7 +755,6 @@ dpkg: warning: version 'foo7a.7z' has bad syntax:
                version number does not start with digit
 foo7a.7z
 foo07.7z
-
 $ compver "3.0/" "3.0.5"
 dpkg: warning: version '3.0/' has bad syntax:
                invalid character in version number
@@ -763,11 +763,11 @@ dpkg: warning: version '3.0/' has bad syntax:
 @end example
 
 To illustrate the different handling of hyphens between Debian and
-coreutils' algorithms (see
-@ref{Minus/Hyphen and Colon characters}):
+Coreutils algorithms (see
+@ref{Hyphen-minus and colon}):
 
 @example
-$ compver abb ab-cd 2>/dev/null     $ printf "abb\nab-cd\n" | sort -V
+$ compver abb ab-cd 2>/dev/null     $ printf 'abb\nab-cd\n' | sort -V
 ab-cd                               abb
 abb                                 ab-cd
 @end example
@@ -779,30 +779,32 @@ handling of file extensions}):
 $ compver hello-8.txt hello-8.2.txt 2>/dev/null
 hello-8.2.txt
 hello-8.txt
-
-$ printf "%s\n" hello-8.txt hello-8.2.txt | sort -V
+$ printf '%s\n' hello-8.txt hello-8.2.txt | sort -V
 hello-8.txt
 hello-8.2.txt
 @end example
 
 
+@node Advanced version sort topics
+@section Advanced Topics
 
-@node Reporting bugs or incorrect results
-@subsection Reporting bugs or incorrect results
 
-If you suspect a bug in GNU coreutils' version sort (i.e., in the
+@node Reporting version sort bugs
+@subsection Reporting version sort bugs
+
+If you suspect a bug in GNU Coreutils version sort (i.e., in the
 output of @samp{ls -v} or @samp{sort -V}), please first check the following:
 
 @enumerate
 @item
 Is the result consistent with Debian's own ordering (using @command{dpkg}, see
-@ref{Comparing two strings using Debian's algorithm}) ? If it is, then this
-is not a bug - please do not report it.
+@ref{Comparing two strings using Debian's algorithm})? If it is, then this
+is not a bug -- please do not report it.
 
 @item
 If the result differs from Debian's, is it explained by one of the
-sections in @ref{Differences from the official Debian Algorithm}? If it is,
-then this is not a bug - please do not report it.
+sections in @ref{Differences from Debian version sort}? If it is,
+then this is not a bug -- please do not report it.
 
 @item
 If you have a question about specific ordering which is not explained
@@ -833,7 +835,7 @@ Natural Sorting variants in
 Python's @uref{https://pypi.org/project/natsort/,natsort package}
 (includes detailed description of their sorting rules:
 @uref{https://natsort.readthedocs.io/en/master/howitworks.html,
-natsort - how it works}).
+natsort -- how it works}).
 
 @item
 Ruby's @uref{https://github.com/github/version_sorter,version_sorter}.
@@ -855,16 +857,16 @@ NodeJS's @uref{https://www.npmjs.com/package/natural-sort,natural-sort package}.
 @item
 In zsh, the
 @uref{http://zsh.sourceforge.net/Doc/Release/Expansion.html#Glob-Qualifiers,
-glob modifier} @code{*(n)} will expand to files in natural sort order.
+glob modifier} @samp{*(n)} will expand to files in natural sort order.
 
 @item
-When writing @code{C} programs, the GNU libc library (@code{glibc})
+When writing C programs, the GNU libc library (@samp{glibc})
 provides the
 @uref{http://man7.org/linux/man-pages/man3/strverscmp.3.html,
 strvercmp(3)} function to compare two strings, and
 @uref{http://man7.org/linux/man-pages/man3/versionsort.3.html,versionsort(3)}
 function to compare two directory entries (despite the names, they are
-not identical to GNU coreutils' version sort ordering).
+not identical to GNU Coreutils version sort ordering).
 
 @item
 Using Debian's sorting algorithm in:
@@ -882,8 +884,8 @@ deb-version-compare}.
 @end itemize
 
 
-@node Related Source code
-@subsection Related Source code
+@node Related source code
+@subsection Related source code
 
 @itemize
 
@@ -899,7 +901,7 @@ Debian's code which performs the @code{upstream_version} comparison:
 version.c}.
 
 @item
-GNULIB code (used by GNU coreutils) which performs the version comparison:
+Gnulib code (used by GNU Coreutils) which performs the version comparison:
 @uref{https://git.savannah.gnu.org/cgit/gnulib.git/tree/lib/filevercmp.c,
 filevercmp.c}.
 @end itemize

gl/lib/buffer-lcm.c

@@ -1,6 +1,6 @@
 /* buffer-lcm.c - compute a good buffer size for dealing with two files
 
-   Copyright (C) 2002-2021 Free Software Foundation, Inc.
+   Copyright (C) 2002-2022 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

gl/lib/cl-strtod.c

@@ -1,6 +1,6 @@
 /* Convert string to double in the current locale, falling back on the C locale.
 
-   Copyright 2019-2021 Free Software Foundation, Inc.
+   Copyright 2019-2022 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

gl/lib/cl-strtod.h

@@ -1,2 +1,4 @@
-double cl_strtod (char const *, char **restrict);
-long double cl_strtold (char const *, char **restrict);
+double cl_strtod (char const *, char **restrict)
+  _GL_ATTRIBUTE_NONNULL ((1));
+long double cl_strtold (char const *, char **restrict)
+  _GL_ATTRIBUTE_NONNULL ((1));

gl/lib/fadvise.c

@@ -1,5 +1,5 @@
 /* Declare an access pattern hint for files.
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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

gl/lib/fadvise.h

@@ -1,5 +1,5 @@
 /* Declare an access pattern hint for files.
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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

gl/lib/fd-reopen.c

@@ -1,6 +1,6 @@
 /* Invoke open, but return either a desired file descriptor or -1.
 
-   Copyright (C) 2005-2021 Free Software Foundation, Inc.
+   Copyright (C) 2005-2022 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

gl/lib/fd-reopen.h

@@ -1,6 +1,6 @@
 /* Invoke open, but return either a desired file descriptor or -1.
 
-   Copyright (C) 2005-2021 Free Software Foundation, Inc.
+   Copyright (C) 2005-2022 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
@@ -19,4 +19,4 @@
 
 #include <sys/types.h>
 
-int fd_reopen (int, char const *, int, mode_t);
+int fd_reopen (int, char const *, int, mode_t) _GL_ATTRIBUTE_NONNULL ();

gl/lib/heap.c

@@ -1,6 +1,6 @@
 /* Barebones heap implementation supporting only insert and pop.
 
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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
@@ -118,7 +118,7 @@ heapify_down (void **array, size_t count, size_t initial,
     {
       size_t child = 2 * parent;
 
-      if (child < count && compare (array[child], array[child+1]) < 0)
+      if (child < count && compare (array[child], array[child + 1]) < 0)
         child++;
 
       if (compare (array[child], element) <= 0)
@@ -141,9 +141,9 @@ heapify_up (void **array, size_t count,
   size_t k = count;
   void *new_element = array[k];
 
-  while (k != 1 && compare (array[k/2], new_element) <= 0)
+  while (k != 1 && compare (array[k / 2], new_element) <= 0)
     {
-      array[k] = array[k/2];
+      array[k] = array[k / 2];
       k /= 2;
     }
 

gl/lib/heap.h

@@ -1,6 +1,6 @@
 /* Barebones heap implementation supporting only insert and pop.
 
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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
@@ -20,7 +20,13 @@
 
 #include <stddef.h>
 
-struct heap *heap_alloc (int (*) (void const *, void const *), size_t);
-void heap_free (struct heap *);
-int heap_insert (struct heap *heap, void *item);
-void *heap_remove_top (struct heap *heap);
+struct heap;
+
+void heap_free (struct heap *) _GL_ATTRIBUTE_NONNULL ();
+
+struct heap *heap_alloc (int (*) (void const *, void const *), size_t)
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC (heap_free, 1)
+  _GL_ATTRIBUTE_RETURNS_NONNULL;
+
+int heap_insert (struct heap *heap, void *item) _GL_ATTRIBUTE_NONNULL ();
+void *heap_remove_top (struct heap *heap) _GL_ATTRIBUTE_NONNULL ();

gl/lib/mbsalign.c

@@ -1,5 +1,5 @@
 /* Align/Truncate a string in a given screen width
-   Copyright (C) 2009-2021 Free Software Foundation, Inc.
+   Copyright (C) 2009-2022 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
@@ -19,6 +19,8 @@
 #include <config.h>
 #include "mbsalign.h"
 
+#include "minmax.h"
+
 #include <stdlib.h>
 #include <string.h>
 #include <stdio.h>
@@ -28,10 +30,6 @@
 #include <wchar.h>
 #include <wctype.h>
 
-#ifndef MIN
-# define MIN(a, b) ((a) < (b) ? (a) : (b))
-#endif
-
 /* Replace non printable chars.
    Note \t and \n etc. are non printable.
    Return 1 if replacement made, 0 otherwise.  */
@@ -84,8 +82,8 @@ wc_truncate (wchar_t *wc, size_t width)
    is always added to DEST.
    A pointer to the terminating NUL is returned.  */
 
-static char*
-mbs_align_pad (char *dest, const char* dest_end, size_t n_spaces)
+static char *
+mbs_align_pad (char *dest, char const *dest_end, size_t n_spaces)
 {
   /* FIXME: Should we pad with "figure space" (\u2007)
      if non ascii data present?  */

gl/lib/mbsalign.h

@@ -1,5 +1,5 @@
 /* Align/Truncate a string in a given screen width
-   Copyright (C) 2009-2021 Free Software Foundation, Inc.
+   Copyright (C) 2009-2022 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
@@ -15,6 +15,7 @@
    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
 
 #include <stddef.h>
+#include <stdlib.h>
 
 typedef enum { MBS_ALIGN_LEFT, MBS_ALIGN_RIGHT, MBS_ALIGN_CENTER } mbs_align_t;
 
@@ -53,7 +54,10 @@ enum {
 
 size_t
 mbsalign (char const *src, char *dest, size_t dest_size,
-          size_t *width, mbs_align_t align, int flags);
+          size_t *width, mbs_align_t align, int flags)
+  _GL_ATTRIBUTE_NONNULL ();
 
 char *
-ambsalign (char const *src, size_t *width, mbs_align_t align, int flags);
+ambsalign (char const *src, size_t *width, mbs_align_t align, int flags)
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC_FREE
+  _GL_ATTRIBUTE_NONNULL ();

gl/lib/rand-isaac.c

@@ -1,6 +1,6 @@
 /* Bob Jenkins's cryptographic random number generators, ISAAC and ISAAC64.
 
-   Copyright (C) 1999-2021 Free Software Foundation, Inc.
+   Copyright (C) 1999-2022 Free Software Foundation, Inc.
    Copyright (C) 1997, 1998, 1999 Colin Plumb.
 
    This program is free software: you can redistribute it and/or modify

gl/lib/rand-isaac.h

@@ -1,6 +1,6 @@
 /* Bob Jenkins's cryptographic random number generators, ISAAC and ISAAC64.
 
-   Copyright (C) 1999-2021 Free Software Foundation, Inc.
+   Copyright (C) 1999-2022 Free Software Foundation, Inc.
    Copyright (C) 1997, 1998, 1999 Colin Plumb.
 
    This program is free software: you can redistribute it and/or modify
@@ -59,7 +59,8 @@ struct isaac_state
     isaac_word a, b, c;		/* Extra variables */
   };
 
-void isaac_seed (struct isaac_state *);
-void isaac_refill (struct isaac_state *, isaac_word[ISAAC_WORDS]);
+void isaac_seed (struct isaac_state *) _GL_ATTRIBUTE_NONNULL ();
+void isaac_refill (struct isaac_state *, isaac_word[ISAAC_WORDS])
+  _GL_ATTRIBUTE_NONNULL ();
 
 #endif

gl/lib/randint.c

@@ -1,6 +1,6 @@
 /* Generate random integers.
 
-   Copyright (C) 2006-2021 Free Software Foundation, Inc.
+   Copyright (C) 2006-2022 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

gl/lib/randint.h

@@ -1,6 +1,6 @@
 /* Generate random integers.
 
-   Copyright (C) 2006-2021 Free Software Foundation, Inc.
+   Copyright (C) 2006-2022 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
@@ -32,11 +32,17 @@ typedef uintmax_t randint;
 
 struct randint_source;
 
-struct randint_source *randint_new (struct randread_source *);
-struct randint_source *randint_all_new (char const *, size_t);
+void randint_free (struct randint_source *) _GL_ATTRIBUTE_NONNULL ();
+int randint_all_free (struct randint_source *) _GL_ATTRIBUTE_NONNULL ();
+struct randint_source *randint_new (struct randread_source *)
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC (randint_free, 1)
+  _GL_ATTRIBUTE_NONNULL () _GL_ATTRIBUTE_RETURNS_NONNULL;
+struct randint_source *randint_all_new (char const *, size_t)
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC (randint_all_free, 1);
 struct randread_source *randint_get_source (struct randint_source const *)
-  _GL_ATTRIBUTE_PURE;
-randint randint_genmax (struct randint_source *, randint genmax);
+  _GL_ATTRIBUTE_NONNULL () _GL_ATTRIBUTE_PURE;
+randint randint_genmax (struct randint_source *, randint genmax)
+  _GL_ATTRIBUTE_NONNULL ();
 
 /* Consume random data from *S to generate a random number in the range
    0 .. CHOICES-1.  CHOICES must be nonzero.  */
@@ -46,7 +52,4 @@ randint_choose (struct randint_source *s, randint choices)
   return randint_genmax (s, choices - 1);
 }
 
-void randint_free (struct randint_source *);
-int randint_all_free (struct randint_source *);
-
 #endif

gl/lib/randperm.c

@@ -1,6 +1,6 @@
 /* Generate random permutations.
 
-   Copyright (C) 2006-2021 Free Software Foundation, Inc.
+   Copyright (C) 2006-2022 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
@@ -25,6 +25,7 @@
 #include <stdint.h>
 #include <stdlib.h>
 
+#include "attribute.h"
 #include "count-leading-zeros.h"
 #include "hash.h"
 #include "verify.h"
@@ -32,7 +33,7 @@
 
 /* Return the floor of the log base 2 of N.  If N is zero, return -1.  */
 
-static int _GL_ATTRIBUTE_CONST
+ATTRIBUTE_CONST static int
 floor_lg (size_t n)
 {
   verify (SIZE_WIDTH <= ULLONG_WIDTH);
@@ -117,7 +118,7 @@ sparse_new (size_t size_hint)
    index I in array V.  */
 
 static void
-sparse_swap (sparse_map *sv, size_t* v, size_t i, size_t j)
+sparse_swap (sparse_map *sv, size_t *v, size_t i, size_t j)
 {
   struct sparse_ent_ *v1 = hash_remove (sv, &(struct sparse_ent_) {i,0});
   struct sparse_ent_ *v2 = hash_remove (sv, &(struct sparse_ent_) {j,0});

gl/lib/randperm.h

@@ -1,4 +1,6 @@
 #include "randint.h"
 #include <stddef.h>
+#include <stdlib.h>
 size_t randperm_bound (size_t, size_t) _GL_ATTRIBUTE_CONST;
-size_t *randperm_new (struct randint_source *, size_t, size_t);
+size_t *randperm_new (struct randint_source *, size_t, size_t)
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC_FREE;

gl/lib/randread.c

@@ -1,6 +1,6 @@
 /* Generate buffers of random data.
 
-   Copyright (C) 2006-2021 Free Software Foundation, Inc.
+   Copyright (C) 2006-2022 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
@@ -40,25 +40,12 @@
 #include "gettext.h"
 #define _(msgid) gettext (msgid)
 
+#include "minmax.h"
 #include "rand-isaac.h"
 #include "stdio-safer.h"
 #include "unlocked-io.h"
 #include "xalloc.h"
 
-#ifndef __attribute__
-# if __GNUC__ < 2 || (__GNUC__ == 2 && __GNUC_MINOR__ < 8)
-#  define __attribute__(x) /* empty */
-# endif
-#endif
-
-#ifndef ATTRIBUTE_NORETURN
-# define ATTRIBUTE_NORETURN __attribute__ ((__noreturn__))
-#endif
-
-#ifndef MIN
-# define MIN(a, b) ((a) < (b) ? (a) : (b))
-#endif
-
 #if _STRING_ARCH_unaligned || _STRING_INLINE_unaligned
 # define ALIGNED_POINTER(ptr, type) true
 #else
@@ -115,7 +102,7 @@ struct randread_source
 
 /* The default error handler.  */
 
-static void ATTRIBUTE_NORETURN
+static void
 randread_error (void const *file_name)
 {
   if (file_name)
@@ -156,6 +143,17 @@ get_nonce (void *buffer, size_t bufsize)
   return true;
 }
 
+/* Body of randread_free, broken out to pacify gcc -Wmismatched-dealloc.  */
+
+static int
+randread_free_body (struct randread_source *s)
+{
+  FILE *source = s->source;
+  explicit_bzero (s, sizeof *s);
+  free (s);
+  return source ? fclose (source) : 0;
+}
+
 /* Create and initialize a random data source from NAME, or use a
    reasonable default source if NAME is null.  BYTES_BOUND is an upper
    bound on the number of bytes that will be needed.  If zero, it is a
@@ -192,7 +190,7 @@ randread_new (char const *name, size_t bytes_bound)
                            MIN (sizeof s->buf.isaac.state.m, bytes_bound)))
             {
               int e = errno;
-              randread_free (s);
+              randread_free_body (s);
               errno = e;
               return NULL;
             }
@@ -313,8 +311,5 @@ randread (struct randread_source *s, void *buf, size_t size)
 int
 randread_free (struct randread_source *s)
 {
-  FILE *source = s->source;
-  explicit_bzero (s, sizeof *s);
-  free (s);
-  return (source ? fclose (source) : 0);
+  return randread_free_body (s);
 }

gl/lib/randread.h

@@ -1,6 +1,6 @@
 /* Generate buffers of random data.
 
-   Copyright (C) 2006-2021 Free Software Foundation, Inc.
+   Copyright (C) 2006-2022 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
@@ -24,10 +24,14 @@
 
 struct randread_source;
 
-struct randread_source *randread_new (char const *, size_t);
-void randread (struct randread_source *, void *, size_t);
-void randread_set_handler (struct randread_source *, void (*) (void const *));
-void randread_set_handler_arg (struct randread_source *, void const *);
-int randread_free (struct randread_source *);
+int randread_free (struct randread_source *) _GL_ATTRIBUTE_NONNULL ();
+struct randread_source *randread_new (char const *, size_t)
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC (randread_free, 1);
+void randread (struct randread_source *, void *, size_t)
+  _GL_ATTRIBUTE_NONNULL ();
+void randread_set_handler (struct randread_source *, void (*) (void const *))
+  _GL_ATTRIBUTE_NONNULL ();
+void randread_set_handler_arg (struct randread_source *, void const *)
+  _GL_ATTRIBUTE_NONNULL ((1));
 
 #endif

gl/lib/root-dev-ino.c

@@ -1,5 +1,5 @@
 /* root-dev-ino.c -- get the device and inode numbers for '/'.
-   Copyright (C) 2003-2021 Free Software Foundation, Inc.
+   Copyright (C) 2003-2022 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

gl/lib/root-dev-ino.h

@@ -1,6 +1,6 @@
 /* Root device and inode number checking.
 
-   Copyright (C) 2003-2021 Free Software Foundation, Inc.
+   Copyright (C) 2003-2022 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
@@ -22,7 +22,7 @@
 # include "same-inode.h"
 
 struct dev_ino *
-get_root_dev_ino (struct dev_ino *root_d_i);
+get_root_dev_ino (struct dev_ino *root_d_i) _GL_ATTRIBUTE_NONNULL ();
 
 /* These macros are common to the programs that support the
    --preserve-root and --no-preserve-root options.  */

gl/lib/smack.h

@@ -1,5 +1,5 @@
 /* Include and determine availability of smack routines
-   Copyright (C) 2013-2021 Free Software Foundation, Inc.
+   Copyright (C) 2013-2022 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

gl/lib/strintcmp.c

@@ -1,6 +1,6 @@
 /* Compare integer strings.
 
-   Copyright (C) 2005-2021 Free Software Foundation, Inc.
+   Copyright (C) 2005-2022 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
@@ -21,6 +21,8 @@
 
 #include "strnumcmp-in.h"
 
+#include <limits.h>
+
 /* Compare strings A and B as integers without explicitly converting
    them to machine numbers, to avoid overflow problems and perhaps
    improve performance.  */
@@ -28,5 +30,5 @@
 int
 strintcmp (char const *a, char const *b)
 {
-  return numcompare (a, b, -1, -1);
+  return numcompare (a, b, CHAR_MAX + 1, CHAR_MAX + 1);
 }

gl/lib/strnumcmp-in.h

@@ -1,6 +1,6 @@
 /* Compare numeric strings.  This is an internal include file.
 
-   Copyright (C) 1988-2021 Free Software Foundation, Inc.
+   Copyright (C) 1988-2022 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
@@ -106,8 +106,8 @@ fraccompare (char const *a, char const *b, char decimal_point)
 /* Compare strings A and B as numbers without explicitly converting
    them to machine numbers, to avoid overflow problems and perhaps
    improve performance.  DECIMAL_POINT is the decimal point and
-   THOUSANDS_SEP the thousands separator.  A DECIMAL_POINT of -1
-   causes comparisons to act as if there is no decimal point
+   THOUSANDS_SEP the thousands separator.  A DECIMAL_POINT outside
+   'char' range causes comparisons to act as if there is no decimal point
    character, and likewise for THOUSANDS_SEP.  */
 
 static inline int _GL_ATTRIBUTE_PURE

gl/lib/strnumcmp.c

@@ -1,6 +1,6 @@
 /* Compare numeric strings.
 
-   Copyright (C) 2005-2021 Free Software Foundation, Inc.
+   Copyright (C) 2005-2022 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
@@ -23,7 +23,7 @@
 
 /* Externally-visible name for numcompare.  */
 
-int _GL_ATTRIBUTE_PURE
+int
 strnumcmp (char const *a, char const *b,
            int decimal_point, int thousands_sep)
 {

gl/lib/strnumcmp.h

@@ -1,2 +1,4 @@
-int strintcmp (char const *, char const *) _GL_ATTRIBUTE_PURE;
-int strnumcmp (char const *, char const *, int, int);
+int strintcmp (char const *, char const *)
+  _GL_ATTRIBUTE_NONNULL () _GL_ATTRIBUTE_PURE;
+int strnumcmp (char const *, char const *, int, int)
+  _GL_ATTRIBUTE_NONNULL () _GL_ATTRIBUTE_PURE;

gl/lib/targetdir.c

@@ -0,0 +1,118 @@
+/* Target directory operands for coreutils
+
+   Copyright 2004-2022 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 <https://www.gnu.org/licenses/>.  */
+
+#include <config.h>
+
+#define TARGETDIR_INLINE _GL_EXTERN_INLINE
+#include <targetdir.h>
+
+#include <attribute.h>
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#ifdef O_PATH
+enum { O_PATHSEARCH = O_PATH };
+#else
+enum { O_PATHSEARCH = O_SEARCH };
+#endif
+
+/* Must F designate the working directory?  */
+
+ATTRIBUTE_PURE static bool
+must_be_working_directory (char const *f)
+{
+  /* Return true for ".", "./.", ".///./", etc.  */
+  while (*f++ == '.')
+    {
+      if (*f != '/')
+        return !*f;
+      while (*++f == '/')
+        continue;
+      if (!*f)
+        return true;
+    }
+  return false;
+}
+
+/* Return a file descriptor open to FILE, for use in openat.
+   As an optimization, return AT_FDCWD if FILE must be the working directory.
+   As a side effect, possibly set *ST to the file's status.
+   Fail and set errno if FILE is not a directory.
+   On failure return -2 if AT_FDCWD is -1, -1 otherwise.  */
+
+int
+target_directory_operand (char const *file, struct stat *st)
+{
+  if (must_be_working_directory (file))
+    return AT_FDCWD;
+
+  int fd = -1;
+  int try_to_open = 1;
+  int stat_result;
+
+  /* On old systems without O_DIRECTORY, like Solaris 10, check with
+     stat first lest we try to open a fifo for example and hang.  */
+  if (!O_DIRECTORY)
+    {
+      stat_result = stat (file, st);
+      if (stat_result == 0)
+        {
+          try_to_open = S_ISDIR (st->st_mode);
+          errno = ENOTDIR;
+        }
+      else
+        {
+          /* On EOVERFLOW failure, give up on checking, as there is no
+             easy way to check.  This should be rare.  */
+          try_to_open = errno == EOVERFLOW;
+        }
+    }
+
+  if (try_to_open)
+    {
+      fd = open (file, O_PATHSEARCH | O_DIRECTORY);
+
+      /* On platforms lacking O_PATH, using O_SEARCH | O_DIRECTORY to
+         open an overly-protected non-directory can fail with either
+         EACCES or ENOTDIR.  Prefer ENOTDIR as it makes for better
+         diagnostics.  */
+      if (O_PATHSEARCH == O_SEARCH && fd < 0 && errno == EACCES)
+        errno = (((O_DIRECTORY ? stat (file, st) : stat_result) == 0
+                  && !S_ISDIR (st->st_mode))
+                 ? ENOTDIR : EACCES);
+    }
+
+  if (!O_DIRECTORY && 0 <= fd)
+    {
+      /* On old systems like Solaris 10 double check type,
+         to ensure we've opened a directory.  */
+      int err;
+      if (fstat (fd, st) == 0
+          ? !S_ISDIR (st->st_mode) && (err = ENOTDIR, true)
+          : (err = errno) != EOVERFLOW)
+        {
+          close (fd);
+          errno = err;
+          fd = -1;
+        }
+    }
+
+  return fd - (AT_FDCWD == -1 && fd < 0);
+}

gl/lib/targetdir.h

@@ -0,0 +1,44 @@
+/* Target directory operands for coreutils
+
+   Copyright 2022 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 <https://www.gnu.org/licenses/>.  */
+
+#include <fcntl.h>
+#include <stdbool.h>
+#include <sys/stat.h>
+
+#ifndef _GL_INLINE_HEADER_BEGIN
+# error "Please include config.h first."
+#endif
+_GL_INLINE_HEADER_BEGIN
+#ifndef TARGETDIR_INLINE
+# define TARGETDIR_INLINE _GL_INLINE
+#endif
+
+/* Return a file descriptor open to FILE, for use in openat.
+   As an optimization, return AT_FDCWD if FILE must be the working directory.
+   As a side effect, possibly set *ST to the file's status.
+   Fail and set errno if FILE is not a directory.
+   On failure return -2 if AT_FDCWD is -1, -1 otherwise.  */
+extern int target_directory_operand (char const *file, struct stat *st);
+
+/* Return true if FD represents success for target_directory_operand.  */
+TARGETDIR_INLINE _GL_ATTRIBUTE_PURE bool
+target_dirfd_valid (int fd)
+{
+  return fd != -1 - (AT_FDCWD == -1);
+}
+
+_GL_INLINE_HEADER_END

gl/lib/xdectoint.c

@@ -1,6 +1,6 @@
 /* Convert decimal strings with bounds checking and exit on error.
 
-   Copyright (C) 2014-2021 Free Software Foundation, Inc.
+   Copyright (C) 2014-2022 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
@@ -21,10 +21,12 @@
 
 #include <errno.h>
 #include <inttypes.h>
+#include <stdbool.h>
 #include <stdlib.h>
 
 #include "error.h"
 #include "quote.h"
+#include "verify.h"
 #include "xstrtol.h"
 
 /* Parse numeric string N_STR of base BASE, and return the value.
@@ -48,10 +50,10 @@ __xnumtoint (char const *n_str, int base, __xdectoint_t min, __xdectoint_t max,
           s_err = LONGINT_OVERFLOW;
           /* Use have the INT range as a heuristic to distinguish
              type overflow rather than other min/max limits.  */
-          if (tnum > INT_MAX/2)
+          if (tnum > INT_MAX / 2)
             errno = EOVERFLOW;
 #if __xdectoint_signed
-          else if (tnum < INT_MIN/2)
+          else if (tnum < INT_MIN / 2)
             errno = EOVERFLOW;
 #endif
           else
@@ -68,6 +70,7 @@ __xnumtoint (char const *n_str, int base, __xdectoint_t min, __xdectoint_t max,
       /* EINVAL error message is redundant in this context.  */
       error (err_exit ? err_exit : EXIT_FAILURE, errno == EINVAL ? 0 : errno,
              "%s: %s", err, quote (n_str));
+      assume (false);
     }
 
   return tnum;

gl/lib/xdectoint.h

@@ -1,6 +1,6 @@
 /* Convert decimal strings with bounds checking and exit on error.
 
-   Copyright (C) 2014-2021 Free Software Foundation, Inc.
+   Copyright (C) 2014-2022 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
@@ -22,10 +22,12 @@
 
 # define _DECLARE_XDECTOINT(name, type) \
   type name (char const *n_str, type min, type max, \
-             char const *suffixes, char const *err, int err_exit);
+             char const *suffixes, char const *err, int err_exit) \
+    _GL_ATTRIBUTE_NONNULL ((1, 5));
 # define _DECLARE_XNUMTOINT(name, type) \
   type name (char const *n_str, int base, type min, type max, \
-             char const *suffixes, char const *err, int err_exit);
+             char const *suffixes, char const *err, int err_exit) \
+    _GL_ATTRIBUTE_NONNULL ((1, 6));
 
 _DECLARE_XDECTOINT (xdectoimax, intmax_t)
 _DECLARE_XDECTOINT (xdectoumax, uintmax_t)

gl/lib/xfts.c

@@ -1,6 +1,6 @@
 /* xfts.c -- a wrapper for fts_open
 
-   Copyright (C) 2003-2021 Free Software Foundation, Inc.
+   Copyright (C) 2003-2022 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

gl/lib/xfts.h

@@ -3,8 +3,10 @@
 
 FTS *
 xfts_open (char * const *, int options,
-           int (*) (const FTSENT **, const FTSENT **));
+           int (*) (const FTSENT **, const FTSENT **))
+  _GL_ATTRIBUTE_MALLOC _GL_ATTRIBUTE_DEALLOC (fts_close, 1)
+  _GL_ATTRIBUTE_NONNULL ((1)) _GL_ATTRIBUTE_RETURNS_NONNULL;
 
 bool
 cycle_warning_required (FTS const *fts, FTSENT const *ent)
-  _GL_ATTRIBUTE_PURE;
+  _GL_ATTRIBUTE_NONNULL () _GL_ATTRIBUTE_PURE;

gl/modules/mbsalign

@@ -6,6 +6,7 @@ lib/mbsalign.c
 lib/mbsalign.h
 
 Depends-on:
+minmax
 wchar
 wctype
 wcwidth

gl/modules/randread

@@ -14,6 +14,7 @@ inline
 fopen-safer
 getrandom
 quote
+minmax
 stdalign
 stdbool
 stdint

gl/modules/targetdir

@@ -0,0 +1,25 @@
+Description:
+Target directory operands
+
+Files:
+lib/targetdir.c
+lib/targetdir.h
+
+Depends-on:
+attribute
+fcntl-h
+stdbool
+
+configure.ac:
+
+Makefile.am:
+lib_SOURCES += targetdir.c targetdir.h
+
+Include:
+"targetdir.h"
+
+License:
+GPL
+
+Maintainer:
+all

gl/modules/xdectoint

@@ -11,6 +11,8 @@ Depends-on:
 error
 errno
 quote
+stdbool
+verify
 xstrtoimax
 xstrtoumax
 

gl/tests/test-fadvise.c

@@ -1,5 +1,5 @@
 /* Test that fadvise works as advertised.
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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

gl/tests/test-mbsalign.c

@@ -1,5 +1,5 @@
 /* Test that mbsalign works as advertised.
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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

gl/tests/test-rand-isaac.c

@@ -1,6 +1,6 @@
 /* Test the ISAAC or ISAAC64 pseudorandom number generator.
 
-   Copyright (C) 2010-2021 Free Software Foundation, Inc.
+   Copyright (C) 2010-2022 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

init.cfg

@@ -1,6 +1,6 @@
 # This file is sourced by init.sh, *before* its initialization.
 
-# Copyright (C) 2010-2021 Free Software Foundation, Inc.
+# Copyright (C) 2010-2022 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
@@ -384,6 +384,7 @@ rwx_to_mode_()
 # with a space.
 stty_reversible_init_()
 {
+  require_perl_
   # Pad start with one space for the first option to match in query function.
   stty_reversible_=' '$(perl -lne '/^ *{"(.*?)",.*\bREV\b/ and print $1' \
     "$abs_top_srcdir"/src/stty.c | tr '\n' ' ')
@@ -540,7 +541,14 @@ seek_data_capable_()
       warn_ 'seek_data_capable_: python missing: assuming not SEEK_DATA capable'
       return 1
   fi
-  $PYTHON_ "$abs_srcdir"/tests/seek-data-capable "$@"
+
+  # Use timeout if available to skip cases where SEEK_DATA takes a long time.
+  # We saw FreeBSD 9.1 take 35s to return from SEEK_DATA for a 1TiB empty file.
+  # Note lseek() is uninterruptible on FreeBSD 9.1, but it does eventually
+  # return, and the timeout will ensure a failure return from the process.
+  timeout --version >/dev/null && TIMEOUT_='timeout 10'
+
+  $TIMEOUT_ $PYTHON_ "$abs_srcdir"/tests/seek-data-capable "$@"
 }
 
 # Skip the current test if "." lacks d_type support.

lib/t-chdir-long

@@ -1,7 +1,7 @@
 #!/bin/sh
 # Exercise chdir-long's sample main program.
 
-# Copyright (C) 2005-2021 Free Software Foundation, Inc.
+# Copyright (C) 2005-2022 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

m4/boottime.m4

@@ -1,7 +1,7 @@
 # boottime.m4 serial 4
 # Determine whether this system has infrastructure for obtaining the boot time.
 
-# Copyright (C) 1996-2021 Free Software Foundation, Inc.
+# Copyright (C) 1996-2022 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

m4/check-decl.m4

@@ -1,7 +1,7 @@
 #serial 27
 # Check declarations for this package.
 
-dnl Copyright (C) 1997-2021 Free Software Foundation, Inc.
+dnl Copyright (C) 1997-2022 Free Software Foundation, Inc.
 
 dnl This file is free software; the Free Software Foundation
 dnl gives unlimited permission to copy and/or distribute it,

m4/include-exclude-prog.m4

@@ -1,5 +1,5 @@
 #serial 2
-dnl Copyright (C) 2007-2021 Free Software Foundation, Inc.
+dnl Copyright (C) 2007-2022 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.

m4/jm-macros.m4

@@ -2,7 +2,7 @@
 
 dnl Misc type-related macros for coreutils.
 
-# Copyright (C) 1998-2021 Free Software Foundation, Inc.
+# Copyright (C) 1998-2022 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

m4/prereq.m4

@@ -7,7 +7,7 @@ m4_pattern_forbid([^gl_[ABCDEFGHIJKLMNOPQRSTUVXYZ]])dnl
 # directory of the coreutils package.
 
 
-# Copyright (C) 1998-2021 Free Software Foundation, Inc.
+# Copyright (C) 1998-2022 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

m4/stat-prog.m4

@@ -1,7 +1,7 @@
 # stat-prog.m4 serial 7
 # Record the prerequisites of src/stat.c from the coreutils package.
 
-# Copyright (C) 2002-2021 Free Software Foundation, Inc.
+# Copyright (C) 2002-2022 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

m4/xattr.m4

@@ -1,7 +1,7 @@
 # xattr.m4 - check for Extended Attributes (Linux)
 # serial 4
 
-# Copyright (C) 2003-2021 Free Software Foundation, Inc.
+# Copyright (C) 2003-2022 Free Software Foundation, Inc.
 # This file is free software; the Free Software Foundation
 # gives unlimited permission to copy and/or distribute it,
 # with or without modifications, as long as this notice is preserved.

man/basenc.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 2018-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 2018-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/chmod.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 1998-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/chown.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 1998-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/df.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 1998-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/du.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 1998-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/echo.x

@@ -2,3 +2,5 @@
 echo \- display a line of text
 [DESCRIPTION]
 .\" Add any additional description here
+[SEE ALSO]
+printf(1)

man/env.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 1998-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.
@@ -54,7 +54,7 @@ sh \-c 'env \-\-default-signal=PIPE seq inf | head \-n1'
 .PP
 
 [NOTES]
-POSIX's exec(2) pages says:
+POSIX's exec(3p) pages says:
 .RS
 "many existing applications wrongly assume that they start with certain
 signals set to the default action and/or unblocked.... Therefore, it is best

man/help2man

@@ -78,6 +78,7 @@ Usage: %s [OPTION]... EXECUTABLE
  -p, --info-page=TEXT    name of Texinfo manual
  -N, --no-info           suppress pointer to Texinfo manual
  -l, --libtool           exclude the `lt-' from the program name
+ -b, --bold-refs         apply bold style to references
      --help              print this help, then exit
      --version           print version number, then exit
 
@@ -99,7 +100,7 @@ my $help_option = '--help';
 my $version_option = '--version';
 my $discard_stderr = 1;
 my ($opt_name, @opt_include, $opt_output, $opt_info, $opt_no_info, $opt_libtool,
-    $version_text);
+    $opt_bold_refs, $version_text);
 
 my %opt_def = (
     'n|name=s'		 => \$opt_name,
@@ -113,6 +114,7 @@ my %opt_def = (
     'p|info-page=s'	 => \$opt_info,
     'N|no-info'		 => \$opt_no_info,
     'l|libtool'		 => \$opt_libtool,
+    'b|bold-refs'	 => \$opt_bold_refs,
     'help'		 => sub { print $help_info; exit },
     'version'		 => sub { print $version_info; exit },
     'h|help-option=s'	 => \$help_option,
@@ -714,6 +716,13 @@ for my $sect (@pre, (grep !$filter{$_}, @sections), @post)
 
 	for ($include{$sect})
 	{
+            # Add bold style around referenced pages.
+            if ($opt_bold_refs)
+            {
+                # This will ignore entries already marked up (with \)
+                s/(^|\s|,)([\[\w\x83]+)\(([1-9][[:lower:]]?)\)/$1\\fB$2\\fP($3)/g;
+            }
+
 	    # Replace leading dot, apostrophe, backslash and hyphen
 	    # tokens.
 	    s/\x80/\\&./g;

man/local.mk

@@ -1,7 +1,7 @@
 # Make coreutils man pages.				-*-Makefile-*-
 # This is included by the top-level Makefile.am.
 
-# Copyright (C) 2002-2021 Free Software Foundation, Inc.
+# Copyright (C) 2002-2022 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
@@ -24,7 +24,10 @@ run_help2man = $(SHELL) $(srcdir)/man/dummy-man
 else
 ## Graceful degradation for systems lacking perl.
 if HAVE_PERL
-run_help2man = $(PERL) -- $(srcdir)/man/help2man
+if BOLD_MAN_REFS
+help2man_OPTS=--bold-refs
+endif
+run_help2man = $(PERL) -- $(srcdir)/man/help2man $(help2man_OPTS)
 else
 run_help2man = $(SHELL) $(srcdir)/man/dummy-man
 endif

man/ls.x

@@ -2,3 +2,5 @@
 ls \- list directory contents
 [DESCRIPTION]
 .\" Add any additional description here
+[SEE ALSO]
+dircolors(1)

man/rm.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 1998-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/stdbuf.x

@@ -1,4 +1,4 @@
-'\" Copyright (C) 2009-2021 Free Software Foundation, Inc.
+'\" Copyright (C) 2009-2022 Free Software Foundation, Inc.
 '\"
 '\" This is free software.  You may redistribute copies of it under the terms
 '\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.

man/test.x

@@ -1,3 +1,8 @@
+'\" Copyright (C) 1998-2022 Free Software Foundation, Inc.
+'\"
+'\" This is free software.  You may redistribute copies of it under the terms
+'\" of the GNU General Public License <https://www.gnu.org/licenses/gpl.html>.
+'\" There is NO WARRANTY, to the extent permitted by law.
 [NAME]
 test \- check file types and compare values
 [SYNOPSIS]
@@ -17,3 +22,5 @@ test \- check file types and compare values
 .I OPTION
 [DESCRIPTION]
 .\" Add any additional description here
+[SEE ALSO]
+access(2)

man/tr.x

@@ -2,3 +2,12 @@
 tr \- translate or delete characters
 [DESCRIPTION]
 .\" Add any additional description here
+[BUGS]
+.PP
+Full support is available only for safe single-byte locales,
+in which every possible input byte represents a single character.
+The C locale is safe in GNU systems, so you can avoid this issue
+in the shell by running
+.B "LC_ALL=C tr"
+instead of plain
+.BR tr .

po/POTFILES.in

@@ -1,5 +1,5 @@
 # List of files which contain translatable strings.
-# Copyright (C) 1996-2021 Free Software Foundation, Inc.
+# Copyright (C) 1996-2022 Free Software Foundation, Inc.
 
 # These are nominally temporary...
 lib/argmatch.c

scripts/build-older-versions/README.older-versions

@@ -164,7 +164,7 @@ By adding the directory to your $PATH, older versions can be easily used:
 
 ========================================================================
 
-Copyright (C) 2019-2021 Free Software Foundation, Inc.
+Copyright (C) 2019-2022 Free Software Foundation, Inc.
 
 Permission is granted to copy, distribute and/or modify this document
 under the terms of the GNU Free Documentation License, Version 1.3 or

scripts/build-older-versions/build-older-versions.sh

@@ -1,6 +1,6 @@
 #!/bin/sh
 #
-# Copyright (C) 2019-2021 Free Software Foundation, Inc.
+# Copyright (C) 2019-2022 Free Software Foundation, Inc.
 #
 # Copying and distribution of this file, with or without modification,
 # are permitted in any medium without royalty provided the copyright

scripts/git-hooks/commit-msg

@@ -14,7 +14,7 @@ $editor = "vi" if $? != 0 or $editor =~ /^\s*\z/;
 # Keywords allowed before the colon on the first line of a commit message:
 # program names and a few general category names.
 my @valid = qw(
-    arch b2sum base32 base64 basenc nbasename cat chcon chgrp chmod chown
+    arch b2sum base32 base64 basenc basename cat chcon chgrp chmod chown
     chroot cksum comm cp csplit cut date dd df dir dircolors dirname du echo
     env expand expr factor false fmt fold groups head hostid hostname id
     install join kill link ln logname ls md5sum mkdir mkfifo mknod mktemp
@@ -87,7 +87,7 @@ sub check_msg($$)
   my ($log_file, $line_ref) = @_;
 
   local *LOG;
-  open LOG, '<', $log_file
+  open LOG, '<:utf8', $log_file
     or return "failed to open for reading: $!";
   @$line_ref = <LOG>;
   close LOG;
@@ -117,10 +117,12 @@ sub check_msg($$)
     and return 'second line must be empty';
 
   # Limit line length to allow for the ChangeLog's leading TAB.
+  my $max_len = 72;
   foreach my $line (@line)
     {
-      72 < length $line && $line =~ /^[^#]/
-        and return 'line longer than 72';
+      my $len = length $line;
+      $max_len < $len && $line =~ /^[^#]/
+        and return "line length ($len) greater than than max: $max_len";
     }
 
   my $buf = join ("\n", @line) . "\n";
@@ -149,6 +151,7 @@ sub check_msg($$)
       $err eq ''
         and last;
       $err = "$ME: $err\n";
+      -t STDOUT or die $err;
       warn $err;
       # Insert the diagnostic as a comment on the first line of $log_file.
       rewrite $log_file, $err, \@line;

src/basename.c

@@ -1,5 +1,5 @@
 /* basename -- strip directory and suffix from file names
-   Copyright (C) 1990-2021 Free Software Foundation, Inc.
+   Copyright (C) 1990-2022 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

src/basenc.c

@@ -1,5 +1,5 @@
 /* Base64, base32, and similar encoding/decoding strings or files.
-   Copyright (C) 2004-2021 Free Software Foundation, Inc.
+   Copyright (C) 2004-2022 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
@@ -175,13 +175,13 @@ from any other non-alphabet bytes in the encoded stream.\n"),
   exit (status);
 }
 
-#define ENC_BLOCKSIZE (1024*3*10)
+#define ENC_BLOCKSIZE (1024 * 3 * 10)
 
 #if BASE_TYPE == 32
 # define BASE_LENGTH BASE32_LENGTH
 /* Note that increasing this may decrease performance if --ignore-garbage
    is used, because of the memmove operation below.  */
-# define DEC_BLOCKSIZE (1024*5)
+# define DEC_BLOCKSIZE (1024 * 5)
 
 /* Ensure that BLOCKSIZE is a multiple of 5 and 8.  */
 verify (ENC_BLOCKSIZE % 40 == 0);  /* So padding chars only on last block.  */
@@ -196,7 +196,7 @@ verify (DEC_BLOCKSIZE % 40 == 0);  /* So complete encoded blocks are used.  */
 # define BASE_LENGTH BASE64_LENGTH
 /* Note that increasing this may decrease performance if --ignore-garbage
    is used, because of the memmove operation below.  */
-# define DEC_BLOCKSIZE (1024*3)
+# define DEC_BLOCKSIZE (1024 * 3)
 
 /* Ensure that BLOCKSIZE is a multiple of 3 and 4.  */
 verify (ENC_BLOCKSIZE % 12 == 0);  /* So padding chars only on last block.  */
@@ -310,7 +310,7 @@ base64url_encode (char const *restrict in, idx_t inlen,
 {
   base64_encode (in, inlen, out, outlen);
   /* translate 62nd and 63rd characters */
-  char* p = out;
+  char *p = out;
   while (outlen--)
     {
       if (*p == '+')
@@ -346,7 +346,7 @@ base64url_decode_ctx_wrapper (struct base_decode_context *ctx,
 
   /* translate 62nd and 63rd characters */
   idx_t i = inlen;
-  char* p = ctx->inbuf;
+  char *p = ctx->inbuf;
   while (i--)
     {
       if (*p == '+' || *p == '/')
@@ -395,7 +395,7 @@ base32_decode_ctx_wrapper (struct base_decode_context *ctx,
 /* ABCDEFGHIJKLMNOPQRSTUVWXYZ234567
      to
    0123456789ABCDEFGHIJKLMNOPQRSTUV */
-static const char base32_norm_to_hex[32+9] = {
+static const char base32_norm_to_hex[32 + 9] = {
 /*0x32, 0x33, 0x34, 0x35, 0x36, 0x37, */
   'Q',  'R',  'S',  'T',  'U',  'V',
 
@@ -417,7 +417,7 @@ static const char base32_norm_to_hex[32+9] = {
 /* 0123456789ABCDEFGHIJKLMNOPQRSTUV
      to
    ABCDEFGHIJKLMNOPQRSTUVWXYZ234567 */
-static const char base32_hex_to_norm[32+9] = {
+static const char base32_hex_to_norm[32 + 9] = {
   /* from: 0x30 .. 0x39 ('0' to '9') */
   /* to:*/ 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J',
 
@@ -581,7 +581,7 @@ static int
 z85_length (int len)
 {
   /* Z85 does not allow padding, so no need to round to highest integer.  */
-  int outlen = (len*5)/4;
+  int outlen = (len * 5) / 4;
   return outlen;
 }
 
@@ -949,8 +949,22 @@ wrap_write (char const *buffer, idx_t len,
       }
 }
 
-static void
-do_encode (FILE *in, FILE *out, idx_t wrap_column)
+static _Noreturn void
+finish_and_exit (FILE *in, char const *infile)
+{
+  if (fclose (in) != 0)
+    {
+      if (STREQ (infile, "-"))
+        die (EXIT_FAILURE, errno, _("closing standard input"));
+      else
+        die (EXIT_FAILURE, errno, "%s", quotef (infile));
+    }
+
+  exit (EXIT_SUCCESS);
+}
+
+static _Noreturn void
+do_encode (FILE *in, char const *infile, FILE *out, idx_t wrap_column)
 {
   idx_t current_column = 0;
   char *inbuf, *outbuf;
@@ -990,12 +1004,11 @@ do_encode (FILE *in, FILE *out, idx_t wrap_column)
   if (ferror (in))
     die (EXIT_FAILURE, errno, _("read error"));
 
-  IF_LINT (free (inbuf));
-  IF_LINT (free (outbuf));
+  finish_and_exit (in, infile);
 }
 
-static void
-do_decode (FILE *in, FILE *out, bool ignore_garbage)
+static _Noreturn void
+do_decode (FILE *in, char const *infile, FILE *out, bool ignore_garbage)
 {
   char *inbuf, *outbuf;
   idx_t sum;
@@ -1057,11 +1070,7 @@ do_decode (FILE *in, FILE *out, bool ignore_garbage)
     }
   while (!feof (in));
 
-#if BASE_TYPE == 42
-  IF_LINT (free (ctx.inbuf));
-#endif
-  IF_LINT (free (inbuf));
-  IF_LINT (free (outbuf));
+  finish_and_exit (in, infile);
 }
 
 int
@@ -1209,7 +1218,7 @@ main (int argc, char **argv)
 
   if (argc - optind > 1)
     {
-      error (0, 0, _("extra operand %s"), quote (argv[optind+1]));
+      error (0, 0, _("extra operand %s"), quote (argv[optind + 1]));
       usage (EXIT_FAILURE);
     }
 
@@ -1233,17 +1242,7 @@ main (int argc, char **argv)
   fadvise (input_fh, FADVISE_SEQUENTIAL);
 
   if (decode)
-    do_decode (input_fh, stdout, ignore_garbage);
+    do_decode (input_fh, infile, stdout, ignore_garbage);
   else
-    do_encode (input_fh, stdout, wrap_column);
-
-  if (fclose (input_fh) == EOF)
-    {
-      if (STREQ (infile, "-"))
-        die (EXIT_FAILURE, errno, _("closing standard input"));
-      else
-        die (EXIT_FAILURE, errno, "%s", quotef (infile));
-    }
-
-  return EXIT_SUCCESS;
+    do_encode (input_fh, infile, stdout, wrap_column);
 }

src/blake2/b2sum.h

@@ -13,7 +13,8 @@
    https://blake2.net.
 */
 
-int blake2b_stream( FILE *stream, void *resstream, size_t outbytes );
+int blake2b_stream (FILE *stream, void *resstream, size_t outbytes)
+  _GL_ATTRIBUTE_NONNULL ((1));
 typedef int ( *blake2fn )( FILE *, void *, size_t );
 #define BLAKE2S_OUTBYTES 32
 #define BLAKE2B_OUTBYTES 64

src/blake2/blake2.h

@@ -18,18 +18,12 @@
 #include <stddef.h>
 #include <stdint.h>
 
-#ifdef __has_attribute
-# if __has_attribute (packed)
-#  define BLAKE2_PACKED(x) x __attribute__ ((packed))
-# endif
-#endif
-#if !defined BLAKE2_PACKED && defined _MSC_VER
+/* Pack a structure if possible.  This might save space, and is not
+   needed for correctness.  */
+#ifdef _MSC_VER
 # define BLAKE2_PACKED(x) __pragma (pack (push, 1)) x __pragma (pack (pop))
-#endif
-#ifndef BLAKE2_PACKED
-/* This should be good enough on other platforms.
-   If it's not good on yours, please file a bug report.  */
-# define BLAKE2_PACKED(x) x
+#else
+# define BLAKE2_PACKED(x) x _GL_ATTRIBUTE_PACKED
 #endif
 
 #if defined(__cplusplus)
@@ -145,8 +139,8 @@ extern "C" {
 
   /* Padded structs result in a compile-time error */
   enum {
-    BLAKE2_DUMMY_1 = 1/(sizeof(blake2s_param) == BLAKE2S_OUTBYTES),
-    BLAKE2_DUMMY_2 = 1/(sizeof(blake2b_param) == BLAKE2B_OUTBYTES)
+    BLAKE2_DUMMY_1 = 1 / (sizeof (blake2s_param) == BLAKE2S_OUTBYTES),
+    BLAKE2_DUMMY_2 = 1 / (sizeof (blake2b_param) == BLAKE2B_OUTBYTES)
   };
 
   /* Streaming API */
@@ -158,7 +152,8 @@ extern "C" {
 
   int blake2b_init( blake2b_state *S, size_t outlen );
   int blake2b_init_key( blake2b_state *S, size_t outlen, const void *key, size_t keylen );
-  int blake2b_init_param( blake2b_state *S, const blake2b_param *P );
+  int blake2b_init_param (blake2b_state *S, const blake2b_param *P)
+    _GL_ATTRIBUTE_NONNULL ();
   int blake2b_update( blake2b_state *S, const void *in, size_t inlen );
   int blake2b_final( blake2b_state *S, void *out, size_t outlen );
 

src/blake2/blake2b-ref.c

@@ -156,11 +156,11 @@ int blake2b_init_key( blake2b_state *S, size_t outlen, const void *key, size_t k
 
 #define G(r,i,a,b,c,d)                      \
   do {                                      \
-    a = a + b + m[blake2b_sigma[r][2*i+0]]; \
+    a = a + b + m[blake2b_sigma[r][2 * i + 0]]; \
     d = rotr64(d ^ a, 32);                  \
     c = c + d;                              \
     b = rotr64(b ^ c, 24);                  \
-    a = a + b + m[blake2b_sigma[r][2*i+1]]; \
+    a = a + b + m[blake2b_sigma[r][2 * i + 1]]; \
     d = rotr64(d ^ a, 16);                  \
     c = c + d;                              \
     b = rotr64(b ^ c, 63);                  \

src/cat.c

@@ -1,5 +1,5 @@
 /* cat -- concatenate files and print on the standard output.
-   Copyright (C) 1988-2021 Free Software Foundation, Inc.
+   Copyright (C) 1988-2022 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
@@ -33,6 +33,8 @@
 #include <sys/ioctl.h>
 
 #include "system.h"
+#include "alignalloc.h"
+#include "idx.h"
 #include "ioblksize.h"
 #include "die.h"
 #include "error.h"
@@ -140,6 +142,7 @@ next_line_num (void)
       *endp-- = '0';
     }
   while (endp >= line_num_start);
+
   if (line_num_start > line_buf)
     *--line_num_start = '1';
   else
@@ -148,28 +151,20 @@ next_line_num (void)
     line_num_print--;
 }
 
-/* Plain cat.  Copies the file behind 'input_desc' to STDOUT_FILENO.
+/* Plain cat.  Copy the file behind 'input_desc' to STDOUT_FILENO.
+   BUF (of size BUFSIZE) is the I/O buffer, used by reads and writes.
    Return true if successful.  */
 
 static bool
-simple_cat (
-     /* Pointer to the buffer, used by reads and writes.  */
-     char *buf,
-
-     /* Number of characters preferably read or written by each read and write
-        call.  */
-     size_t bufsize)
+simple_cat (char *buf, idx_t bufsize)
 {
-  /* Actual number of characters read, and therefore written.  */
-  size_t n_read;
-
   /* Loop until the end of the file.  */
 
   while (true)
     {
       /* Read a block of input.  */
 
-      n_read = safe_read (input_desc, buf, bufsize);
+      size_t n_read = safe_read (input_desc, buf, bufsize);
       if (n_read == SAFE_READ_ERROR)
         {
           error (0, errno, "%s", quotef (infile));
@@ -183,12 +178,8 @@ simple_cat (
 
       /* Write this block out.  */
 
-      {
-        /* The following is ok, since we know that 0 < n_read.  */
-        size_t n = n_read;
-        if (full_write (STDOUT_FILENO, buf, n) != n)
-          die (EXIT_FAILURE, errno, _("write error"));
-      }
+      if (full_write (STDOUT_FILENO, buf, n_read) != n_read)
+        die (EXIT_FAILURE, errno, _("write error"));
     }
 }
 
@@ -199,7 +190,7 @@ simple_cat (
 static inline void
 write_pending (char *outbuf, char **bpout)
 {
-  size_t n_write = *bpout - outbuf;
+  idx_t n_write = *bpout - outbuf;
   if (0 < n_write)
     {
       if (full_write (STDOUT_FILENO, outbuf, n_write) != n_write)
@@ -208,7 +199,12 @@ write_pending (char *outbuf, char **bpout)
     }
 }
 
-/* Cat the file behind INPUT_DESC to the file behind OUTPUT_DESC.
+/* Copy the file behind 'input_desc' to STDOUT_FILENO.
+   Use INBUF and read INSIZE with each call,
+   and OUTBUF and write OUTSIZE with each call.
+   (The buffers are a bit larger than the I/O sizes.)
+   The remaining boolean args say what 'cat' options to use.
+
    Return true if successful.
    Called if any option more than -u was specified.
 
@@ -216,43 +212,13 @@ write_pending (char *outbuf, char **bpout)
    an explicit test for buffer end unnecessary.  */
 
 static bool
-cat (
-     /* Pointer to the beginning of the input buffer.  */
-     char *inbuf,
-
-     /* Number of characters read in each read call.  */
-     size_t insize,
-
-     /* Pointer to the beginning of the output buffer.  */
-     char *outbuf,
-
-     /* Number of characters written by each write call.  */
-     size_t outsize,
-
-     /* Variables that have values according to the specified options.  */
-     bool show_nonprinting,
-     bool show_tabs,
-     bool number,
-     bool number_nonblank,
-     bool show_ends,
-     bool squeeze_blank)
+cat (char *inbuf, idx_t insize, char *outbuf, idx_t outsize,
+     bool show_nonprinting, bool show_tabs, bool number, bool number_nonblank,
+     bool show_ends, bool squeeze_blank)
 {
   /* Last character read from the input buffer.  */
   unsigned char ch;
 
-  /* Pointer to the next character in the input buffer.  */
-  char *bpin;
-
-  /* Pointer to the first non-valid byte in the input buffer, i.e., the
-     current end of the buffer.  */
-  char *eob;
-
-  /* Pointer to the position where the next character shall be written.  */
-  char *bpout;
-
-  /* Number of characters read by the last read call.  */
-  size_t n_read;
-
   /* Determines how many consecutive newlines there have been in the
      input.  0 newlines makes NEWLINES -1, 1 newline makes NEWLINES 1,
      etc.  Initially 0 to indicate that we are at the beginning of a
@@ -269,10 +235,15 @@ cat (
   /* The inbuf pointers are initialized so that BPIN > EOB, and thereby input
      is read immediately.  */
 
-  eob = inbuf;
-  bpin = eob + 1;
+  /* Pointer to the first non-valid byte in the input buffer, i.e., the
+     current end of the buffer.  */
+  char *eob = inbuf;
 
-  bpout = outbuf;
+  /* Pointer to the next character in the input buffer.  */
+  char *bpin = eob + 1;
+
+  /* Pointer to the position where the next character shall be written.  */
+  char *bpout = outbuf;
 
   while (true)
     {
@@ -283,7 +254,7 @@ cat (
           if (outbuf + outsize <= bpout)
             {
               char *wp = outbuf;
-              size_t remaining_bytes;
+              idx_t remaining_bytes;
               do
                 {
                   if (full_write (STDOUT_FILENO, wp, outsize) != outsize)
@@ -342,7 +313,7 @@ cat (
 
               /* Read more input into INBUF.  */
 
-              n_read = safe_read (input_desc, inbuf, insize);
+              size_t n_read = safe_read (input_desc, inbuf, insize);
               if (n_read == SAFE_READ_ERROR)
                 {
                   error (0, errno, "%s", quotef (infile));
@@ -528,38 +499,45 @@ cat (
     }
 }
 
+/* Copy data from input to output using copy_file_range if possible.
+   Return 1 if successful, 0 if ordinary read+write should be tried,
+   -1 if a serious problem has been diagnosed.  */
+
+static int
+copy_cat (void)
+{
+  /* Copy at most COPY_MAX bytes at a time; this is min
+     (SSIZE_MAX, SIZE_MAX) truncated to a value that is
+     surely aligned well.  */
+  ssize_t copy_max = MIN (SSIZE_MAX, SIZE_MAX) >> 30 << 30;
+
+  /* copy_file_range does not support some cases, and it
+     incorrectly returns 0 when reading from the proc file
+     system on the Linux kernel through at least 5.6.19 (2020),
+     so fall back on read+write if the copy_file_range is
+     unsupported or the input file seems empty.  */
+
+  for (bool some_copied = false; ; some_copied = true)
+    switch (copy_file_range (input_desc, NULL, STDOUT_FILENO, NULL,
+                             copy_max, 0))
+      {
+      case 0:
+        return some_copied;
+
+      case -1:
+        if (errno == ENOSYS || is_ENOTSUP (errno) || errno == EINVAL
+            || errno == EBADF || errno == EXDEV || errno == ETXTBSY
+            || errno == EPERM)
+          return 0;
+        error (0, errno, "%s", quotef (infile));
+        return -1;
+      }
+}
+
+
 int
 main (int argc, char **argv)
 {
-  /* Optimal size of i/o operations of output.  */
-  size_t outsize;
-
-  /* Optimal size of i/o operations of input.  */
-  size_t insize;
-
-  size_t page_size = getpagesize ();
-
-  /* Pointer to the input buffer.  */
-  char *inbuf;
-
-  /* Pointer to the output buffer.  */
-  char *outbuf;
-
-  bool ok = true;
-  int c;
-
-  /* Index in argv to processed argument.  */
-  int argind;
-
-  /* Device number of the output (file or whatever).  */
-  dev_t out_dev;
-
-  /* I-node number of the output.  */
-  ino_t out_ino;
-
-  /* True if the output is a regular file.  */
-  bool out_isreg;
-
   /* Nonzero if we have ever read standard input.  */
   bool have_read_stdin = false;
 
@@ -602,6 +580,7 @@ main (int argc, char **argv)
 
   /* Parse command line options.  */
 
+  int c;
   while ((c = getopt_long (argc, argv, "benstuvAET", long_options, NULL))
          != -1)
     {
@@ -666,10 +645,15 @@ main (int argc, char **argv)
   if (fstat (STDOUT_FILENO, &stat_buf) < 0)
     die (EXIT_FAILURE, errno, _("standard output"));
 
-  outsize = io_blksize (stat_buf);
-  out_dev = stat_buf.st_dev;
-  out_ino = stat_buf.st_ino;
-  out_isreg = S_ISREG (stat_buf.st_mode) != 0;
+  /* Optimal size of i/o operations of output.  */
+  idx_t outsize = io_blksize (stat_buf);
+
+  /* Device and I-node number of the output.  */
+  dev_t out_dev = stat_buf.st_dev;
+  ino_t out_ino = stat_buf.st_ino;
+
+  /* True if the output is a regular file.  */
+  bool out_isreg = S_ISREG (stat_buf.st_mode) != 0;
 
   if (! (number || show_ends || squeeze_blank))
     {
@@ -677,19 +661,20 @@ main (int argc, char **argv)
       xset_binary_mode (STDOUT_FILENO, O_BINARY);
     }
 
-  /* Check if any of the input files are the same as the output file.  */
-
   /* Main loop.  */
 
   infile = "-";
-  argind = optind;
+  int argind = optind;
+  bool ok = true;
+  idx_t page_size = getpagesize ();
 
   do
     {
       if (argind < argc)
         infile = argv[argind];
 
-      if (STREQ (infile, "-"))
+      bool reading_stdin = STREQ (infile, "-");
+      if (reading_stdin)
         {
           have_read_stdin = true;
           input_desc = STDIN_FILENO;
@@ -713,7 +698,9 @@ main (int argc, char **argv)
           ok = false;
           goto contin;
         }
-      insize = io_blksize (stat_buf);
+
+      /* Optimal size of i/o operations of input.  */
+      idx_t insize = io_blksize (stat_buf);
 
       fdadvise (input_desc, 0, 0, FADVISE_SEQUENTIAL);
 
@@ -730,23 +717,37 @@ main (int argc, char **argv)
           goto contin;
         }
 
+      /* Pointer to the input buffer.  */
+      char *inbuf;
+
       /* Select which version of 'cat' to use.  If any format-oriented
-         options were given use 'cat'; otherwise use 'simple_cat'.  */
+         options were given use 'cat'; if not, use 'copy_cat' if it
+         works, 'simple_cat' otherwise.  */
 
       if (! (number || show_ends || show_nonprinting
              || show_tabs || squeeze_blank))
         {
-          insize = MAX (insize, outsize);
-          inbuf = xmalloc (insize + page_size - 1);
-
-          ok &= simple_cat (ptr_align (inbuf, page_size), insize);
+          int copy_cat_status =
+            out_isreg && S_ISREG (stat_buf.st_mode) ? copy_cat () : 0;
+          if (copy_cat_status != 0)
+            {
+              inbuf = NULL;
+              ok &= 0 < copy_cat_status;
+            }
+          else
+            {
+              insize = MAX (insize, outsize);
+              inbuf = xalignalloc (page_size, insize);
+              ok &= simple_cat (inbuf, insize);
+            }
         }
       else
         {
-          inbuf = xmalloc (insize + 1 + page_size - 1);
+          /* Allocate, with an extra byte for a newline sentinel.  */
+          inbuf = xalignalloc (page_size, insize + 1);
 
           /* Why are
-             (OUTSIZE - 1 + INSIZE * 4 + LINE_COUNTER_BUF_LEN + PAGE_SIZE - 1)
+             (OUTSIZE - 1 + INSIZE * 4 + LINE_COUNTER_BUF_LEN)
              bytes allocated for the output buffer?
 
              A test whether output needs to be written is done when the input
@@ -764,24 +765,26 @@ main (int argc, char **argv)
              positions.
 
              Align the output buffer to a page size boundary, for efficiency
-             on some paging implementations, so add PAGE_SIZE - 1 bytes to the
-             request to make room for the alignment.  */
+             on some paging implementations.  */
 
-          outbuf = xmalloc (outsize - 1 + insize * 4 + LINE_COUNTER_BUF_LEN
-                            + page_size - 1);
+          idx_t bufsize;
+          if (INT_MULTIPLY_WRAPV (insize, 4, &bufsize)
+              || INT_ADD_WRAPV (bufsize, outsize, &bufsize)
+              || INT_ADD_WRAPV (bufsize, LINE_COUNTER_BUF_LEN - 1, &bufsize))
+            xalloc_die ();
+          char *outbuf = xalignalloc (page_size, bufsize);
 
-          ok &= cat (ptr_align (inbuf, page_size), insize,
-                     ptr_align (outbuf, page_size), outsize, show_nonprinting,
+          ok &= cat (inbuf, insize, outbuf, outsize, show_nonprinting,
                      show_tabs, number, number_nonblank, show_ends,
                      squeeze_blank);
 
-          free (outbuf);
+          alignfree (outbuf);
         }
 
-      free (inbuf);
+      alignfree (inbuf);
 
     contin:
-      if (!STREQ (infile, "-") && close (input_desc) < 0)
+      if (!reading_stdin && close (input_desc) < 0)
         {
           error (0, errno, "%s", quotef (infile));
           ok = false;

src/chcon.c

@@ -1,5 +1,5 @@
 /* chcon -- change security context of files
-   Copyright (C) 2005-2021 Free Software Foundation, Inc.
+   Copyright (C) 2005-2022 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

src/chgrp.c

@@ -1,5 +1,5 @@
 /* chgrp -- change group ownership of files
-   Copyright (C) 1989-2021 Free Software Foundation, Inc.
+   Copyright (C) 1989-2022 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
@@ -313,7 +313,5 @@ main (int argc, char **argv)
                     (uid_t) -1, gid,
                     (uid_t) -1, (gid_t) -1, &chopt);
 
-  IF_LINT (chopt_free (&chopt));
-
-  return ok ? EXIT_SUCCESS : EXIT_FAILURE;
+  main_exit (ok ? EXIT_SUCCESS : EXIT_FAILURE);
 }

src/chmod.c

@@ -1,5 +1,5 @@
 /* chmod -- change permission modes of files
-   Copyright (C) 1989-2021 Free Software Foundation, Inc.
+   Copyright (C) 1989-2022 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
@@ -44,8 +44,8 @@ struct change_status
   enum
     {
       CH_NO_STAT,
-      CH_NOT_APPLIED,
       CH_FAILED,
+      CH_NOT_APPLIED,
       CH_NO_CHANGE_REQUESTED,
       CH_SUCCEEDED
     }
@@ -322,7 +322,7 @@ process_file (FTS *fts, FTSENT *ent)
   if ( ! recurse)
     fts_set (fts, ent, FTS_SKIP);
 
-  return CH_NO_CHANGE_REQUESTED <= ch.status;
+  return CH_NOT_APPLIED <= ch.status;
 }
 
 /* Recursively change the modes of the specified FILES (the last entry
@@ -567,7 +567,5 @@ main (int argc, char **argv)
   ok = process_files (argv + optind,
                       FTS_COMFOLLOW | FTS_PHYSICAL | FTS_DEFER_STAT);
 
-  IF_LINT (free (change));
-
-  return ok ? EXIT_SUCCESS : EXIT_FAILURE;
+  main_exit (ok ? EXIT_SUCCESS : EXIT_FAILURE);
 }

src/chown-core.c

@@ -1,5 +1,5 @@
 /* chown-core.c -- core functions for changing ownership.
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 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
@@ -73,6 +73,28 @@ chopt_free (struct Chown_option *chopt)
   free (chopt->group_name);
 }
 
+/* Convert the numeric user-id, UID, to a string stored in xmalloc'd memory,
+   and return it.  Use the decimal representation of the ID.  */
+
+static char *
+uid_to_str (uid_t uid)
+{
+  char buf[INT_BUFSIZE_BOUND (intmax_t)];
+  return xstrdup (TYPE_SIGNED (uid_t) ? imaxtostr (uid, buf)
+                  : umaxtostr (uid, buf));
+}
+
+/* Convert the numeric group-id, GID, to a string stored in xmalloc'd memory,
+   and return it.  Use the decimal representation of the ID.  */
+
+static char *
+gid_to_str (gid_t gid)
+{
+  char buf[INT_BUFSIZE_BOUND (intmax_t)];
+  return xstrdup (TYPE_SIGNED (gid_t) ? imaxtostr (gid, buf)
+                  : umaxtostr (gid, buf));
+}
+
 /* Convert the numeric group-id, GID, to a string stored in xmalloc'd memory,
    and return it.  If there's no corresponding group name, use the decimal
    representation of the ID.  */
@@ -80,11 +102,8 @@ chopt_free (struct Chown_option *chopt)
 extern char *
 gid_to_name (gid_t gid)
 {
-  char buf[INT_BUFSIZE_BOUND (intmax_t)];
   struct group *grp = getgrgid (gid);
-  return xstrdup (grp ? grp->gr_name
-                  : TYPE_SIGNED (gid_t) ? imaxtostr (gid, buf)
-                  : umaxtostr (gid, buf));
+  return grp ? xstrdup (grp->gr_name) : gid_to_str (gid);
 }
 
 /* Convert the numeric user-id, UID, to a string stored in xmalloc'd memory,
@@ -94,11 +113,8 @@ gid_to_name (gid_t gid)
 extern char *
 uid_to_name (uid_t uid)
 {
-  char buf[INT_BUFSIZE_BOUND (intmax_t)];
   struct passwd *pwd = getpwuid (uid);
-  return xstrdup (pwd ? pwd->pw_name
-                  : TYPE_SIGNED (uid_t) ? imaxtostr (uid, buf)
-                  : umaxtostr (uid, buf));
+  return pwd ? xstrdup (pwd->pw_name) : uid_to_str (uid);
 }
 
 /* Allocate a string representing USER and GROUP.  */
@@ -484,11 +500,21 @@ change_file_owner (FTS *fts, FTSENT *ent,
              : CH_SUCCEEDED);
           char *old_usr = file_stats ? uid_to_name (file_stats->st_uid) : NULL;
           char *old_grp = file_stats ? gid_to_name (file_stats->st_gid) : NULL;
+          char *new_usr = chopt->user_name
+                          ? chopt->user_name : uid != -1
+                                               ? uid_to_str (uid) : NULL;
+          char *new_grp = chopt->group_name
+                          ? chopt->group_name : gid != -1
+                                               ? gid_to_str (gid) : NULL;
           describe_change (file_full_name, ch_status,
                            old_usr, old_grp,
-                           chopt->user_name, chopt->group_name);
+                           new_usr, new_grp);
           free (old_usr);
           free (old_grp);
+          if (new_usr != chopt->user_name)
+            free (new_usr);
+          if (new_grp != chopt->group_name)
+            free (new_grp);
         }
     }