*** empty log message ***

pad with spaces.

THANKS

@@ -64,6 +64,7 @@ Chuck Hedrick                       hedrick@klinzhai.rutgers.edu
 Clark Morgan                        cmorgan@aracnet.com
 Colin Plumb                         colin@nyx.net
 Collin Rogowski                     collin@rogowski.de
+Dale Scheetz                        dwarf@polaris.net
 Dan Hagerty                         hag@gnu.ai.it.edu
 Dan Pascu                           dan@services.iiruc.ro
 Daniel Bergstrom                    noa@melody.se
@@ -118,6 +119,7 @@ Hans Verkuil                        hans@wyst.hobby.nl
 Harry Liu                           rliu@lek.ugcs.caltech.edu
 Herbert Xu                          herbert@gondor.apana.org.au
 Holger Berger                       hberger@ess.nec.de
+Hon-Yin Kok                         hkok@yoda.unl.edu
 Hugh Daniel                         hugh@xanadu.com
 Ian Jackson                         ijackson@chiark.greenend.org.uk
 Ian Lance Taylor                    ian@cygnus.com
@@ -275,6 +277,7 @@ Sander van Malssen                  svm@kozmix.ow.nl
 Santiago Vila Doncel                sanvila@unex.es
 Savochkin Andrey Vladimirovich      saw@msu.ru
 Scott Lurndal                       slurn@griffin.engr.sgi.com
+Stéphane Chazelas                   Stephane_CHAZELAS@yahoo.fr
 Stephen Gildea                      gildea@x.org
 Stephen Smoogen                     ??????????
 Steve McConnel                      steve@acadcomp.sil.org

doc/sh-utils.texi

@@ -427,9 +427,10 @@ pipeline.
 @dfn{failure}.  It can be used as a place holder in shell scripts
 where an unsuccessful command is needed.
 
-@code{false} ignores @emph{all} command line arguments, even @samp{--help}
-and @samp{--version}, since to do otherwise would change expected
-behavior that some programmers may be relying on.
+By default, @code{false} honors the @samp{--help} and @samp{--version}
+options.  However, that is contrary to @sc{POSIX}, so when the environment
+variable @env{POSIXLY_CORRECT} is set, @code{false} ignores @emph{all}
+command line arguments, including @samp{--help} and @samp{--version}.
 
 This version of @code{false} is implemented as a C program, and is thus
 more secure and faster than a shell script implementation, and may safely
@@ -448,11 +449,15 @@ be used as a dummy shell for the purpose of disabling accounts.
 @code{true} does nothing except return an exit status of 0, meaning
 @dfn{success}.  It can be used as a place holder in shell scripts
 where a successful command is needed, although the shell built-in
-command @code{:} (colon) does the same thing faster.
+command @code{:} (colon) may do the same thing faster.
+In most modern shells, @code{true} is built-in command, so when
+you use @samp{true} in a script, you're probably using the built-in
+command, not the one documented here.
 
-@code{true} ignores @emph{all} command line arguments, even @samp{--help}
-and @samp{--version}, since to do otherwise would change expected
-behavior that some programmers may be relying on.
+By default, @code{true} honors the @samp{--help} and @samp{--version}
+options.  However, that is contrary to @sc{POSIX}, so when the environment
+variable @env{POSIXLY_CORRECT} is set, @code{true} ignores @emph{all}
+command line arguments, including @samp{--help} and @samp{--version}.
 
 This version of @code{true} is implemented as a C program, and is thus
 more secure and faster than a shell script implementation, and may safely

doc/textutils.texi

@@ -237,6 +237,14 @@ writing identical descriptions for each of the programs, they are
 described here.  (In fact, every @sc{gnu} program accepts (or should accept)
 these options.)
 
+@vindex POSIXLY_CORRECT
+Normally options and operands can appear in any order, and programs act
+as if all the options appear before any operands.  For example,
+@samp{sort -r passwd -t :} acts like @samp{sort -r -t : passwd}, since
+@samp{:} is an option-argument of @option{-t}.  However, if the
+@env{POSIXLY_CORRECT} environment variable is set, options must appear
+before operands, unless otherwise specified for a particular command.
+
 Some of these programs recognize the @samp{--help} and @samp{--version}
 options only when one of them is the sole command line argument.
 
@@ -252,8 +260,24 @@ Print a usage message listing all available options, then exit successfully.
 @cindex version number, finding
 Print the version number, then exit successfully.
 
+@item --
+@opindex --
+@cindex option delimiter
+Delimit the option list.  Later arguments, if any, are treated as
+operands even if they begin with @samp{-}.  For example, @samp{sort --
+-r} reads from the file named @file{-r}.
+
 @end table
 
+@cindex standard input
+@cindex standard output
+A single @samp{-} is not really an option, though it looks like one.  It
+stands for standard input, or for standard output if that is clear from
+the context, and it can be used either as an operand or as an
+option-argument.  For example, @samp{sort -o - -} outputs to standard
+output and reads from standard input, and is equivalent to plain
+@samp{sort}.  Unless otherwise specified, @samp{-} can appear in any
+context that requires a file name.
 
 @node Output of entire files
 @chapter Output of entire files
@@ -1051,8 +1075,8 @@ If a line is too long to fit in a column, it is truncated.
 @opindex -c
 @opindex --show-control-chars
 Print control characters using hat notation (e.g., @samp{^G}); print
-other unprintable characters in octal backslash notation.  By default,
-unprintable characters are not changed.
+other nonprinting characters in octal backslash notation.  By default,
+nonprinting characters are not changed.
 
 @item -d
 @itemx --double-space
@@ -1258,7 +1282,7 @@ set in the input files.
 @itemx --show-nonprinting
 @opindex -v
 @opindex --show-nonprinting
-Print unprintable characters in octal backslash notation.
+Print nonprinting characters in octal backslash notation.
 
 @item -w @var{page_width}
 @itemx --width=@var{page_width}
@@ -2109,14 +2133,18 @@ mode:
 @table @samp
 
 @item -c
+@itemx --check
 @opindex -c
+@opindex --check
 @cindex checking for sortedness
 Check whether the given files are already sorted: if they are not all
 sorted, print an error message and exit with a status of 1.
 Otherwise, exit successfully.
 
 @item -m
+@itemx --merge
 @opindex -m
+@opindex --merge
 @cindex merging sorted files
 Merge the given files by sorting them as a group.  Each input file must
 always be individually sorted.  It always works to sort instead of
@@ -2133,17 +2161,19 @@ options, until a difference is found or no fields are left.
 Unless otherwise specified, all comparisons use the character
 collating sequence specified by the @env{LC_COLLATE} locale.
 
-If any of the global options @samp{Mbdfinr} are given but no key fields
+If any of the global options @samp{bdfgiMnr} are given but no key fields
 are specified, @code{sort} compares the entire lines according to the
 global options.
 
 Finally, as a last resort when all keys compare equal (or if no
 ordering options were specified at all), @code{sort} compares the entire
 lines.  The last resort comparison
-honors the @samp{-r} global option.  The @samp{-s} (stable) option
+honors the @option{--reverse} (@option{-r}) global option.
+The @option{--stable} (@option{-s}) option
 disables this last-resort comparison so that lines in which all fields
 compare equal are left in their original relative order.  If no fields
-or global options are specified, @samp{-s} has no effect.
+or global options are specified, @option{--stable} (@option{-s}) has no
+effect.
 
 @sc{gnu} @code{sort} (as specified for all @sc{gnu} utilities) has no limits on
 input line length or restrictions on bytes allowed within lines.  In
@@ -2160,8 +2190,8 @@ Upon any error, @code{sort} exits with a status of @samp{2}.
 @vindex TMPDIR
 If the environment variable @env{TMPDIR} is set, @code{sort} uses its
 value as the directory for temporary files instead of @file{/tmp}.  The
-@samp{-T @var{tempdir}} option in turn overrides the environment
-variable.
+@option{--temporary-directory} (@option{-T}) option in turn overrides
+the environment variable.
 
 The following options affect the ordering of output lines.  They may be
 specified globally or as part of a specific key field.  If no key
@@ -2174,14 +2204,19 @@ so portable shell scripts should specify global options first.
 @table @samp
 
 @item -b
+@itemx --ignore-leading-blanks
 @opindex -b
+@opindex --ignore-leading-blanks
 @cindex blanks, ignoring leading
 @vindex LC_CTYPE
 Ignore leading blanks when finding sort keys in each line.
 The @env{LC_CTYPE} locale determines character types.
 
 @item -d
+@itemx --dictionary-order
 @opindex -d
+@opindex --dictionary-order
+@cindex dictionary order
 @cindex phone directory order
 @cindex telephone directory order
 @vindex LC_CTYPE
@@ -2190,15 +2225,20 @@ letters, digits and blanks when sorting.
 The @env{LC_CTYPE} locale determines character types.
 
 @item -f
+@itemx --ignore-case
 @opindex -f
+@opindex --ignore-case
+@cindex ignoring case
 @cindex case folding
 @vindex LC_CTYPE
 Fold lowercase characters into the equivalent uppercase characters when
-sorting so that, for example, @samp{b} and @samp{B} sort as equal.
+comparing so that, for example, @samp{b} and @samp{B} sort as equal.
 The @env{LC_CTYPE} locale determines character types.
 
 @item -g
+@itemx --general-numeric-sort
 @opindex -g
+@opindex --general-numeric-sort
 @cindex general numeric sort
 @vindex LC_NUMERIC
 Sort numerically, using the standard C function @code{strtod} to convert
@@ -2224,17 +2264,23 @@ Plus infinity.
 @end itemize
 
 Use this option only if there is no alternative; it is much slower than
-@samp{-n} and it can lose information when converting to floating point.
+@option{--numeric-sort} (@option{-n}) and it can lose information when
+converting to floating point.
 
 @item -i
+@itemx --ignore-nonprinting
 @opindex -i
+@opindex --ignore-nonprinting
+@cindex nonprinting characters, ignoring
 @cindex unprintable characters, ignoring
 @vindex LC_CTYPE
-Ignore unprintable characters.
+Ignore nonprinting characters.
 The @env{LC_CTYPE} locale determines character types.
 
 @item -M
+@itemx --month-sort
 @opindex -M
+@opindex --month-sort
 @cindex months, sorting by
 @vindex LC_TIME
 An initial string, consisting of any amount of whitespace, followed
@@ -2244,7 +2290,9 @@ Invalid names compare low to valid names.  The @env{LC_TIME} locale
 determines the month spellings.
 
 @item -n
+@itemx --numeric-sort
 @opindex -n
+@opindex --numeric-sort
 @cindex numeric sort
 @vindex LC_NUMERIC
 Sort numerically: the number begins each line; specifically, it consists
@@ -2253,10 +2301,11 @@ digits possibly separated by thousands separators, optionally followed
 by a decimal-point character and zero or more digits.  The @env{LC_NUMERIC}
 locale specifies the decimal-point character and thousands separator.
 
-@code{sort -n} uses what might be considered an unconventional method
+Numeric sort uses what might be considered an unconventional method
 to compare strings representing floating point numbers.  Rather than
 first converting each string to the C @code{double} type and then
-comparing those values, sort aligns the decimal-point characters in the two
+comparing those values, @command{sort} aligns the decimal-point
+characters in the two
 strings and compares the strings a character at a time.  One benefit
 of using this approach is its speed.  In practice this is much more
 efficient than performing the two corresponding string-to-double (or even
@@ -2266,10 +2315,13 @@ there is no corresponding loss of precision.  Converting each string to
 on most systems.
 
 Neither a leading @samp{+} nor exponential notation is recognized.
-To compare such strings numerically, use the @samp{-g} option.
+To compare such strings numerically, use the
+@option{--general-numeric-sort} (@option{-g}) option.
 
 @item -r
+@itemx --reverse
 @opindex -r
+@opindex --reverse
 @cindex reverse sorting
 Reverse the result of comparison, so that lines with greater key values
 appear earlier in the output instead of later.
@@ -2281,15 +2333,26 @@ Other options are:
 @table @samp
 
 @item -o @var{output-file}
+@itemx --output=@var{output-file}
 @opindex -o
+@opindex --output
 @cindex overwriting of input, allowed
 Write output to @var{output-file} instead of standard output.
 If necessary, @command{sort} reads input before opening
 @var{output-file}, so you can safely sort a file in place by using
-commands like @code{sort F -o F} and @code{cat F | sort -o F}.
+commands like @code{sort -o F F} and @code{cat F | sort -o F}.
+
+@vindex POSIXLY_CORRECT
+If @option{-c} is not also specified, @option{-o} may appear after an
+input file even if @env{POSIXLY_CORRECT} is set, e.g., @samp{sort F -o
+F}.  Warning: this usage is obsolescent.  Future versions of @sc{posix}
+will require that support for it be withdrawn.  Portable scripts should
+specify @samp{-o @var{output-file}} before any input files.
 
 @item -S @var{size}
+@itemx --buffer-size=@var{size}
 @opindex -S
+@opindex --buffer-size
 @cindex size for main memory sorting
 Use a main-memory sort buffer of the given @var{size}.  By default,
 @var{size} is in units of 1,024 bytes.  Appending @samp{%} causes
@@ -2307,7 +2370,9 @@ grows beyond @var{size} if @command{sort} encounters input lines larger
 than @var{size}.
 
 @item -t @var{separator}
+@itemx --field-separator=@var{separator}
 @opindex -t
+@opindex --field-separator
 @cindex field separator character
 Use character @var{separator} as the field separator when finding the
 sort keys in each line.  By default, fields are separated by the empty
@@ -2320,7 +2385,9 @@ as @samp{-k 2}, or sort fields consisting of a range, as @samp{-k 2,3},
 retain the field separators present between the endpoints of the range.
 
 @item -T @var{tempdir}
+@itemx --temporary-directory=@var{tempdir}
 @opindex -T
+@opindex --temporary-directory
 @cindex temporary directory
 @vindex TMPDIR
 Use directory @var{tempdir} to store temporary files, overriding the
@@ -2331,24 +2398,31 @@ performance by using this option to specify directories on different
 disks and controllers.
 
 @item -u
+@itemx --unique
 @opindex -u
+@opindex --unique
 @cindex uniquifying output
-For the default case or the @samp{-m} option, only output the first
-of a sequence of lines that compare equal.  For the @samp{-c} option,
+
+Normally, output only the first of a sequence of lines that compare
+equal.  For the @option{--check} (@option{-c}) option,
 check that no pair of consecutive lines compares equal.
 
 @item -k @var{pos1}[,@var{pos2}]
+@itemx --key=@var{pos1}[,@var{pos2}]
 @opindex -k
+@opindex --key
 @cindex sort field
-The recommended, @sc{posix}, option for specifying a sort field.  The field
+Specify a sort field that
 consists of the part of the line between @var{pos1} and @var{pos2} (or the
 end of the line, if @var{pos2} is omitted), @emph{inclusive}.
 Fields and character positions are numbered starting with 1.
-So to sort on the second field, you'd use @samp{-k 2,2}
+So to sort on the second field, you'd use @samp{--key=2,2} (@samp{-k 2,2}).
 See below for more examples.
 
 @item -z
+@itemx --zero-terminated
 @opindex -z
+@opindex --zero-terminated
 @cindex sort zero-terminated lines
 Treat the input as a set of lines, each terminated by a zero byte (@sc{ascii}
 @sc{nul} (Null) character) instead of an @sc{ascii} @sc{lf} (Line Feed).
@@ -2357,22 +2431,18 @@ This option can be useful in conjunction with @samp{perl -0} or
 reliably handle arbitrary pathnames (even those which contain Line Feed
 characters.)
 
-@item +@var{pos1}[-@var{pos2}]
+@item +@var{pos1} [-@var{pos2}]
 The obsolescent, traditional option for specifying a sort field.  The field
 consists of the line between @var{pos1} and up to but @emph{not including}
 @var{pos2} (or the end of the line if @var{pos2} is omitted).  Fields
 and character positions are numbered starting with 0.  See below.
 
-Warning: the @samp{+@var{pos}} usage is obsolescent.  Future versions of
+Warning: the @samp{+@var{pos1}} usage is obsolescent.  Future versions of
 @sc{posix} will require that support for it be withdrawn.  Use
-@option{-k} instead.
+@option{--key} (@option{-k}) instead.
 
 @end table
 
-In addition, when @sc{gnu} @code{sort} is invoked with exactly one argument,
-options @samp{--help} and @samp{--version} are recognized.  @xref{Common
-options}.
-
 Historical (BSD and System V) implementations of @code{sort} have
 differed in their interpretation of some options, particularly
 @samp{-b}, @samp{-f}, and @samp{-n}.  @sc{gnu} sort follows the @sc{posix}

lib/ChangeLog

@@ -1,3 +1,13 @@
+2001-04-08  Jim Meyering  <meyering@lucent.com>
+
+	* getdate.y (get_date): Set tm_isdst to -1 to ensure that it is
+	recomputed; that's necessary when the offset spans a DST transition.
+	Patch by David J. MacKenzie.  Reported by Hon-Yin Kok.
+
+2001-04-02  Jim Meyering  <meyering@lucent.com>
+
+	* regex.h, regex.c: Update from GNU libc.
+
 2001-03-19  Paul Eggert  <eggert@twinsun.com>
 
 	* lib/version-etc.c (version_etc_copyright): Update to 2001.

lib/getdate.y

@@ -990,7 +990,8 @@ get_date (const char *p, const time_t *now)
 
   /* Let mktime deduce tm_isdst if we have an absolute time stamp,
      or if the relative time stamp mentions days, months, or years.  */
-  if (pc.dates_seen | pc.days_seen | pc.times_seen | pc.rel_day | pc.rel_month | pc.rel_year)
+  if (pc.dates_seen | pc.days_seen | pc.times_seen | pc.rel_day
+      | pc.rel_month | pc.rel_year)
     tm.tm_isdst = -1;
 
   /* But if the input explicitly specifies local time with or without
@@ -1037,6 +1038,7 @@ get_date (const char *p, const time_t *now)
     {
       tm.tm_mday += ((pc.day_number - tm.tm_wday + 7) % 7
 		     + 7 * (pc.day_ordinal - (0 < pc.day_ordinal)));
+      tm.tm_isdst = -1;
       Start = mktime (&tm);
       if (Start == (time_t) -1)
 	return Start;

lib/regex.c

@@ -65,7 +65,7 @@
 # define CHAR_CLASS_SIZE ((__alignof__(wctype_t)+sizeof(wctype_t))/sizeof(CHAR_TYPE)+1)
 # define PUT_CHAR(c) \
   do {									      \
-    if (MC_CUR_MAX == 1)						      \
+    if (MB_CUR_MAX == 1)						      \
       putchar (c);							      \
     else								      \
       printf ("%C", (wint_t) c); /* Should we use wide stream??  */	      \
@@ -2137,21 +2137,21 @@ typedef struct
 
 
 /* Get the next unsigned number in the uncompiled pattern.  */
-#define GET_UNSIGNED_NUMBER(num) 					\
-  { if (p != pend)							\
-     {									\
-       PATFETCH (c); 							\
-       while ('0' <= c && c <= '9')					\
-         { 								\
-           if (num < 0)							\
-              num = 0;							\
-           num = num * 10 + c - '0'; 					\
-           if (p == pend) 						\
-              break; 							\
-           PATFETCH (c);						\
-         } 								\
-       } 								\
-    }
+#define GET_UNSIGNED_NUMBER(num) \
+  {									\
+    while (p != pend)							\
+      {									\
+	PATFETCH (c);							\
+	if (c < '0' || c > '9')						\
+	  break;							\
+	if (num <= RE_DUP_MAX)						\
+	  {								\
+	    if (num < 0)						\
+	      num = 0;							\
+	    num = num * 10 + c - '0';					\
+	  }								\
+      }									\
+  }
 
 #if defined _LIBC || WIDE_CHAR_SUPPORT
 /* The GNU C library provides support for user-defined character classes
@@ -2325,14 +2325,6 @@ regex_compile (pattern, size, syntax, bufp)
   /* Address of beginning of regexp, or inside of last group.  */
   US_CHAR_TYPE *begalt;
 
-  /* Place in the uncompiled pattern (i.e., the {) to
-     which to go back if the interval is invalid.  */
-#ifdef MBS_SUPPORT
-  const US_CHAR_TYPE *beg_interval;
-#else
-  const char *beg_interval;
-#endif /* MBS_SUPPORT */
-
   /* Address of the place where a forward jump should go to the end of
      the containing expression.  Each alternative of an `or' -- except the
      last -- ends with a forward jump of this sort.  */
@@ -2345,23 +2337,24 @@ regex_compile (pattern, size, syntax, bufp)
 
 #ifdef MBS_SUPPORT
   /* Initialize the wchar_t PATTERN and offset_buffer.  */
-  p = pend = pattern = TALLOC(csize, CHAR_TYPE);
+  p = pend = pattern = TALLOC(csize + 1, CHAR_TYPE);
   mbs_offset = TALLOC(csize + 1, int);
   is_binary = TALLOC(csize + 1, char);
   if (pattern == NULL || mbs_offset == NULL || is_binary == NULL)
     {
-      if (pattern) free(pattern);
-      if (mbs_offset) free(mbs_offset);
-      if (is_binary) free(is_binary);
+      free(pattern);
+      free(mbs_offset);
+      free(is_binary);
       return REG_ESPACE;
     }
+  pattern[csize] = L'\0';	/* sentinel */
   size = convert_mbs_to_wcs(pattern, cpattern, csize, mbs_offset, is_binary);
   pend = p + size;
   if (size < 0)
     {
-      if (pattern) free(pattern);
-      if (mbs_offset) free(mbs_offset);
-      if (is_binary) free(is_binary);
+      free(pattern);
+      free(mbs_offset);
+      free(is_binary);
       return REG_BADPAT;
     }
 #endif
@@ -2383,9 +2376,9 @@ regex_compile (pattern, size, syntax, bufp)
   if (compile_stack.stack == NULL)
     {
 #ifdef MBS_SUPPORT
-      if (pattern) free(pattern);
-      if (mbs_offset) free(mbs_offset);
-      if (is_binary) free(is_binary);
+      free(pattern);
+      free(mbs_offset);
+      free(is_binary);
 #endif
       return REG_ESPACE;
     }
@@ -3826,25 +3819,19 @@ regex_compile (pattern, size, syntax, bufp)
 
                 /* At least (most) this many matches must be made.  */
                 int lower_bound = -1, upper_bound = -1;
-                beg_interval = p - 1;
+
+		/* Place in the uncompiled pattern (i.e., just after
+		   the '{') to go back to if the interval is invalid.  */
+		const CHAR_TYPE *beg_interval = p;
 
                 if (p == pend)
-                  {
-                    if (!(syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES))
-                      goto unfetch_interval;
-                    else
-                      FREE_STACK_RETURN (REG_EBRACE);
-                  }
+		  goto invalid_interval;
 
                 GET_UNSIGNED_NUMBER (lower_bound);
 
                 if (c == ',')
                   {
                     GET_UNSIGNED_NUMBER (upper_bound);
-		    if ((!(syntax & RE_NO_BK_BRACES) && c != '\\')
-			|| ((syntax & RE_NO_BK_BRACES) && c != '}'))
-		      FREE_STACK_RETURN (REG_BADBR);
-
 		    if (upper_bound < 0)
 		      upper_bound = RE_DUP_MAX;
                   }
@@ -3852,36 +3839,24 @@ regex_compile (pattern, size, syntax, bufp)
                   /* Interval such as `{1}' => match exactly once. */
                   upper_bound = lower_bound;
 
-                if (lower_bound < 0 || upper_bound > RE_DUP_MAX
-                    || lower_bound > upper_bound)
-                  {
-                    if (!(syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES))
-                      goto unfetch_interval;
-                    else
-                      FREE_STACK_RETURN (REG_BADBR);
-                  }
+                if (! (0 <= lower_bound && lower_bound <= upper_bound))
+		  goto invalid_interval;
 
                 if (!(syntax & RE_NO_BK_BRACES))
                   {
-                    if (c != '\\') FREE_STACK_RETURN (REG_EBRACE);
-
+		    if (c != '\\' || p == pend)
+		      goto invalid_interval;
                     PATFETCH (c);
                   }
 
                 if (c != '}')
-                  {
-                    if (!(syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES))
-                      goto unfetch_interval;
-                    else
-                      FREE_STACK_RETURN (REG_BADBR);
-                  }
-
-                /* We just parsed a valid interval.  */
+		  goto invalid_interval;
 
                 /* If it's invalid to have no preceding re.  */
                 if (!laststart)
                   {
-                    if (syntax & RE_CONTEXT_INVALID_OPS)
+		    if (syntax & RE_CONTEXT_INVALID_OPS
+			&& !(syntax & RE_INVALID_INTERVAL_ORD))
                       FREE_STACK_RETURN (REG_BADRPT);
                     else if (syntax & RE_CONTEXT_INDEP_OPS)
                       laststart = b;
@@ -3889,6 +3864,11 @@ regex_compile (pattern, size, syntax, bufp)
                       goto unfetch_interval;
                   }
 
+                /* We just parsed a valid interval.  */
+
+                if (RE_DUP_MAX < upper_bound)
+		  FREE_STACK_RETURN (REG_BADBR);
+
                 /* If the upper bound is zero, don't want to succeed at
                    all; jump from `laststart' to `b + 3', which will be
 		   the end of the buffer after we insert the jump.  */
@@ -3974,25 +3954,20 @@ regex_compile (pattern, size, syntax, bufp)
                        }
                    }
                 pending_exact = 0;
-                beg_interval = NULL;
-              }
-              break;
+		break;
 
-            unfetch_interval:
-              /* If an invalid interval, match the characters as literals.  */
-               assert (beg_interval);
-               p = beg_interval;
-               beg_interval = NULL;
-
-               /* normal_char and normal_backslash need `c'.  */
-               PATFETCH (c);
-
-               if (!(syntax & RE_NO_BK_BRACES))
-                 {
-                   if (p > pattern  &&  p[-1] == '\\')
-                     goto normal_backslash;
-                 }
-               goto normal_char;
+	      invalid_interval:
+		if (!(syntax & RE_INVALID_INTERVAL_ORD))
+		  FREE_STACK_RETURN (p == pend ? REG_EBRACE : REG_BADBR);
+	      unfetch_interval:
+		/* Match the characters as literals.  */
+		p = beg_interval;
+		c = '{';
+		if (syntax & RE_NO_BK_BRACES)
+		  goto normal_char;
+		else
+		  goto normal_backslash;
+	      }
 
 #ifdef emacs
             /* There is no way to specify the before_dot and after_dot

lib/regex.h

@@ -160,6 +160,11 @@ typedef unsigned long int reg_syntax_t;
    this bit set, and it won't affect anything in the normal case. */
 #define RE_DEBUG (RE_NO_GNU_OPS << 1)
 
+/* If this bit is set, a syntactically invalid interval is treated as
+   a string of ordinary characters.  For example, the ERE 'a{1' is
+   treated as 'a\{1'.  */
+#define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1)
+
 /* This global variable defines the particular regexp syntax to use (for
    some interfaces).  When a regexp is compiled, the syntax used is
    stored in the pattern buffer, so changing this does not affect
@@ -199,7 +204,8 @@ extern reg_syntax_t re_syntax_options;
    | RE_NO_BK_VBAR)
 
 #define RE_SYNTAX_POSIX_EGREP						\
-  (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES)
+  (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES			\
+   | RE_INVALID_INTERVAL_ORD)
 
 /* P1003.2/D11.2, section 4.20.7.1, lines 5078ff.  */
 #define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC

m4/ChangeLog

@@ -1,3 +1,22 @@
+2001-04-21  Jim Meyering  <meyering@lucent.com>
+
+	* rmdir-errno.m4: Write to a new file, so that a restrictive umask
+	doesn't interfere.
+
+2001-04-21  Alexandre Duret-Lutz  <duret_g@epita.fr>
+
+	* ftruncate.m4: Check for chsize.
+	Link with ftruncate.o unconditionally if ftruncate is missing.
+	This was required when cross-compiling to i586-mingw32msvc.
+
+2001-03-24  Jim Meyering  <meyering@lucent.com>
+
+	* jm-macros.m4: Require autoconf-2.49d.
+
+2001-03-20  Bruno Haible  <haible@clisp.cons.org>
+
+        * iconv.m4 (jm_ICONV): Recommend GNU libiconv.
+
 2001-03-17  Jim Meyering  <meyering@lucent.com>
 
 	* memcmp.m4 (jm_AC_FUNC_MEMCMP): Remove my copy of AC_FUNC_MEMCMP,

m4/ftruncate.m4

@@ -1,27 +1,14 @@
-#serial 2
+#serial 3
 
-# See if we need to emulate a missing ftruncate function using fcntl.
+# See if we need to emulate a missing ftruncate function using fcntl or chsize.
 
 AC_DEFUN(jm_FUNC_FTRUNCATE,
 [
   AC_CHECK_FUNCS(ftruncate, , [ftruncate_missing=yes])
 
   if test "$ftruncate_missing" = yes; then
-    AC_CHECK_HEADERS(unistd.h)
-    AC_MSG_CHECKING([fcntl emulation of ftruncate])
-    AC_CACHE_VAL(fu_cv_sys_ftruncate_emulation,
-    [AC_TRY_LINK([
-#include <sys/types.h>
-#include <fcntl.h>], [
-#if !defined(F_CHSIZE) && !defined(F_FREESP)
-  chsize();
-#endif
-  ],
-      fu_cv_sys_ftruncate_emulation=yes,
-      fu_cv_sys_ftruncate_emulation=no)])
-    AC_MSG_RESULT($fu_cv_sys_ftruncate_emulation)
-    if test $fu_cv_sys_ftruncate_emulation = yes; then
-      AC_LIBOBJ(ftruncate)
-    fi
+    AC_CHECK_HEADERS([unistd.h])
+    AC_CHECK_FUNCS([chsize])
+    AC_LIBOBJ(ftruncate)
   fi
 ])

m4/iconv.m4

@@ -1,13 +1,13 @@
-#serial 2
+#serial 3
 
 dnl From Bruno Haible.
 
 AC_DEFUN(jm_ICONV,
 [
   dnl Some systems have iconv in libc, some have it in libiconv (OSF/1 and
-  dnl those with the standalone portable libiconv installed).
+  dnl those with the standalone portable GNU libiconv installed).
   AC_CACHE_CHECK(for iconv, jm_cv_func_iconv, [
-    jm_cv_func_iconv="no, consider installing libiconv"
+    jm_cv_func_iconv="no, consider installing GNU libiconv"
     jm_cv_lib_iconv=no
     AC_TRY_LINK([#include <stdlib.h>
 #include <iconv.h>],

m4/jm-macros.m4

@@ -1,10 +1,10 @@
-#serial 34   -*- autoconf -*-
+#serial 35   -*- autoconf -*-
 
 dnl Misc type-related macros for fileutils, sh-utils, textutils.
 
 AC_DEFUN(jm_MACROS,
 [
-  AC_PREREQ(2.14d)
+  AC_PREREQ(2.49d)
 
   GNU_PACKAGE="GNU $PACKAGE"
   AC_DEFINE_UNQUOTED(GNU_PACKAGE, "$GNU_PACKAGE",

m4/rmdir-errno.m4

@@ -1,4 +1,4 @@
-#serial 1
+#serial 2
 
 # When rmdir fails because the specified directory is not empty, it sets
 # errno to some value, usually ENOTEMPTY.  However, on some AIX systems,
@@ -25,12 +25,12 @@ extern int errno;
 	  int val;
 	  rmdir ("confdir2");
 	  val = errno;
-	  s = fopen ("confdir2/file", "w");
+	  s = fopen ("confdir2/errno", "w");
 	  fprintf (s, "%d\n", val);
 	  exit (0);
 	}
 	],
-      fetish_cv_func_rmdir_errno_not_empty=`cat confdir2/file`,
+      fetish_cv_func_rmdir_errno_not_empty=`cat confdir2/errno`,
       fetish_cv_func_rmdir_errno_not_empty='configure error in rmdir-errno.m4',
       fetish_cv_func_rmdir_errno_not_empty=ENOTEMPTY
       )

old/fileutils/ChangeLog

@@ -1,3 +1,67 @@
+2001-04-23  Jim Meyering  <meyering@lucent.com>
+
+	* Version 4.0.45.
+
+2001-04-22  Jim Meyering  <meyering@lucent.com>
+
+	* src/ls.c (decode_switches): Ensure that -1 has no effect when it
+	follows -l.  Reported by Ulrich Drepper.
+
+	* src/dd.c (usage): Mention that sync makes dd pad with spaces (rather
+	than NULs) when used with block or unblock.
+	(dd_copy): When using sync with either block or unblock,
+	pad with spaces.  Reported by Dale Scheetz.
+	* tests/dd/skip-seek (block-sync-1): New test, for this.  Based on
+	report from Dale Scheetz.
+	* doc/fileutils.texi (dd invocation): Document it here, too.
+
+	* configure: Regenerate using a patched copy of autoconf-2.49e to
+	work around a bug in its test for a working memcmp function.
+
+	* tests/ls/no-arg: New file.
+	* tests/ls/Makefile.am (TESTS): Add no-arg.
+	* src/ls.c (main): Fix off-by-one error introduced with last change.
+
+2001-04-21  Jim Meyering  <meyering@lucent.com>
+
+	* Version 4.0.44.
+
+	* configure, aclocal.m4, etc.: Regenerate using autoconf-2.49e.
+
+	* doc/fileutils.texi (touch invocation): Discuss ctime.
+	Based on suggestions and contributions from Aharon Robbins
+	and Dan Jacobson.
+
+	* src/ls.c (main): When given two or more arguments but the only one
+	that exists is a directory, don't treat it as if it were the only
+	argument.  Before, `mkdir d; ls no-dir d 2>/dev/null' would act like
+	`ls d' and produce no output.  Now, it prints `d:'.
+	Report and patch from Stéphane Chazelas.
+	* tests/ls-2/tests: New tests, for the above fix.
+
+2001-04-08  Jim Meyering  <meyering@lucent.com>
+
+	* depcomp: New version, from automake.
+
+2000-10-31  Bruno Haible  <haible@clisp.cons.org>
+
+	* ls.c: Don't inspect MB_LEN_MAX. Paul Eggert says it's
+	not always defined correctly.
+
+2001-04-03  John David Anglin  <dave@hiauly1.hia.nrc.ca>
+
+	* tests/chgrp/basic: Ensure that initial group id's are properly set
+	for `d' and `d/f3'.
+
+2001-04-02  Jim Meyering  <meyering@lucent.com>
+
+	* tests/mv/setup: Skip nonexistent directories so we don't get
+	diagnostics from df about e.g., `/usr/tmp not found'.
+
+2001-03-24  Jim Meyering  <meyering@lucent.com>
+
+	* configure.in: Don't require autoconf version here -- it's done in m4/.
+
 2001-03-23  Jim Meyering  <meyering@lucent.com>
 
 	* Version 4.0.43.

old/fileutils/NEWS

@@ -1,4 +1,21 @@
 Changes in release 4.1.0:
+[4.0.45]
+* dd conv=sync,block now pads only with spaces
+* ls's -1 option no longer cancels the effect of a preceding -l
+* regenerate configure using a patched version of autoconf-2.49e to work
+    around a bug in its test for a working memcmp function
+* ls: fix off-by-one error introduced with the previous change
+[4.0.44]
+* ls: When given two or more arguments but the only one that exists is a
+    directory, don't treat it as if it were the only argument.  Before,
+    `mkdir d; ls no-dir d 2>/dev/null' would act like `ls d' and produce
+    no output.  Now, it prints `d:'.
+* touch -d 'last friday' would use a time stamp that was one hour off
+    (e.g., 23:00 on *thursday* rather than 00:00 of the preceding friday)
+    when run such that the current time and the target date/time fall on
+    opposite sides of a daylight savings time transition.
+    This problem arises only with relative date strings like `last monday'.
+    It is not a problem with strings that include absolute dates.
 [4.0.43]
 * regenerate configure-related files using autoconf-2.49d
 [4.0.42]

old/sh-utils/ChangeLog

@@ -1,3 +1,9 @@
+2001-04-20  Jim Meyering  <meyering@lucent.com>
+
+	* doc/sh-utils.texi (false invocation): Describe how --help and
+	--version are treated with and without POSIXLY_CORRECT.
+	(true invocation): Likewise.  Forwarded by Michael Stone.
+
 2001-03-18  Jim Meyering  <meyering@lucent.com>
 
 	* tests/Fetish.pm: If the $DJDIR envvar is defined, set SHELL

old/sh-utils/NEWS

@@ -1,4 +1,11 @@
 Changes in release 2.1
+ [2.0.12]
+* date -d 'last friday' print a date/time that was one hour off
+    (e.g., 23:00 on *thursday* rather than 00:00 of the preceding friday)
+    when run such that the current time and the target date/time fall on
+    opposite sides of a daylight savings time transition.
+    This problem arises only with relative date strings like `last monday'.
+    It is not a problem with strings that include absolute dates.
  [2.0.11]
 * setting the date now works properly, even when using -u
 * `date -f - < /dev/null' no longer dumps core

old/textutils/ChangeLog

@@ -1,3 +1,72 @@
+2001-04-22  Jim Meyering  <meyering@lucent.com>
+
+	* Version 2.0.14.
+
+	* configure: Regenerate using a patched copy of autoconf-2.49e to
+	work around a bug in its test for a working memcmp function.
+
+2001-03-28  Paul Eggert  <eggert@twinsun.com>
+
+	* src/cksum.c: Fix bugs when computing length of large files.
+	Add overflow and write error checks.  Use uint_fast32_t, not
+	unsigned long, to do checksum calculation, as C99 says
+	uint_fast32_t should be no slower and might be faster.
+
+	Include <stdio.h> and "system.h" even if CRCTAB is defined,
+	so that the code will compile if CRCTAB is defined.
+	Include "human.h" if CRCTAB is not defined.
+	(uint_fast32_t): Define if it appears that stdint.h didn't.
+	(BIT, remainder, main, crctab): Use uint_fast32_t, not unsigned long,
+	for checksums.
+	(fill_r, remainder, main): Use ANSI prototypes.
+	(fill_r, remainder, main): Omit duplicate code.
+	(main): Use uintmax_t, not unsigned long, for file lengths.
+	Use size_t, not long, for result of fread.
+	Check for overflow when computing file lengths.
+	Check for write error immediately after printing a line, so that
+	we don't write to stdout indefinitely after an error.
+
+2001-04-14  Paul Eggert  <eggert@twinsun.com>
+
+	* src/sort.c (default_sort_size): Leave a 1/16 margin for RSS.
+	Suggestion from Solar Designer.
+
+2001-04-14  Jim Meyering  <meyering@lucent.com>
+
+	* src/wc.c (usage): Tweak --help output: s/line,/newline,/
+
+2001-04-13  Jim Meyering  <meyering@lucent.com>
+
+	* src/sort.c (main): Add a comment justifying the use of
+	`multi-character' rather than `multibyte' in a diagnostic.
+	From Paul Eggert.
+
+2001-04-12  Paul Eggert  <eggert@twinsun.com>
+
+	* src/sort.c (RLIMIT_AS): Do not define; just use conditional
+	code, since RLIMIT_RSS is similar (and is not standardized).
+	(default_sort_size): Don't allocate more than the RSS limit,
+	if this host has such a limit.
+
+2001-03-20  Paul Eggert  <eggert@twinsun.com>
+
+	* NEWS, doc/textutils.texi: sort now accepts long options and
+        checks POSIX option syntax.
+
+	* doc/textutils.texi: Document --, -, sort long options, and
+	sort -o after files.
+
+	* src/sort.c: Include <getopt.h>.
+	(usage, main): Add support for long options, and check option
+	syntax as POSIX requires, though (as usual for GNU apps)
+	options can follow file names unless POSIXLY_CORRECT is set.
+	Many diagnostic revamped.
+	(long_options): New constant.
+	(badfieldspec): New arg MSGID.  Mark as noreturn.
+	(parse_field_count): New arg MSGID; if null, just return null on error.
+	(new_key): Renamed from key_init.  All callers changed.  Now allocates
+	the new key.
+
 2001-03-18  Jim Meyering  <meyering@lucent.com>
 
 	* Version 2.0.13.

old/textutils/NEWS

@@ -1,4 +1,13 @@
 Changes in release 2.1
+[2.0.14]
+* sort now accepts long options like "--reverse" and "--".
+* sort now checks option syntax as POSIX requires, except that (as usual
+  for GNU) options can follow file names unless POSIXLY_CORRECT is set.
+  For example, invalid positional combinations like "sort +1 -r -2" are
+  now rejected as per POSIX.
+* The next POSIX standard will require that obsolescent 'sort'
+  positional options like +1 be treated as file names, not options.
+  Please use 'sort -k' instead.
 [2.0.13]
 * pr accepts new -D or --date option, to specify date format.
 * The following changes are required by POSIX:

src/cksum.c

@@ -47,12 +47,17 @@
 
 #define AUTHORS "Q. Frank Xia"
 
+#include <stdio.h>
+#include "system.h"
+
+#if !defined UINT_FAST32_MAX && !defined uint_fast32_t
+# define uint_fast32_t unsigned int
+#endif
+
 #ifdef CRCTAB
 
-# include <stdio.h>
-
-# define BIT(x)	( (unsigned long)1 << (x) )
-# define SBIT	BIT(31)
+# define BIT(x)	((uint_fast32_t) 1 << (x))
+# define SBIT	BIT (31)
 
 /* The generating polynomial is
 
@@ -61,47 +66,48 @@
 
   The i bit in GEN is set if X^i is a summand of G(X) except X^32.  */
 
-# define GEN     (BIT(26)|BIT(23)|BIT(22)|BIT(16)|BIT(12)|BIT(11)|BIT(10)\
-                |BIT(8) |BIT(7) |BIT(5) |BIT(4) |BIT(2) |BIT(1) |BIT(0));
+# define GEN	(BIT (26) | BIT (23) | BIT (22) | BIT (16) | BIT (12) \
+		 | BIT (11) | BIT (10) | BIT (8) | BIT (7) | BIT (5) \
+		 | BIT (4) | BIT (2) | BIT (1) | BIT (0))
 
-static unsigned long r[8];
+static uint_fast32_t r[8];
 
 static void
-fill_r ()
+fill_r (void)
 {
   int i;
 
   r[0] = GEN;
   for (i = 1; i < 8; i++)
-    r[i] = (r[i - 1] & SBIT) ? (r[i - 1] << 1) ^ r[0] : r[i - 1] << 1;
+    r[i] = (r[i - 1] << 1) ^ ((r[i - 1] & SBIT) ? GEN : 0);
 }
 
-static unsigned long
-remainder (m)
-     int m;
+static uint_fast32_t
+remainder (int m)
 {
-  unsigned long rem = 0;
+  uint_fast32_t rem = 0;
   int i;
 
   for (i = 0; i < 8; i++)
     if (BIT (i) & m)
-      rem = rem ^ r[i];
+      rem ^= r[i];
 
   return rem & 0xFFFFFFFF;	/* Make it run on 64-bit machine.  */
 }
 
 int
-main ()
+main (void)
 {
   int i;
 
   fill_r ();
-  printf ("unsigned long crctab[256] = {\n  0x0");
+  printf ("static uint_fast32_t crctab[256] =\n{\n  0x0");
   for (i = 0; i < 51; i++)
     {
       printf (",\n  0x%08X, 0x%08X, 0x%08X, 0x%08X, 0x%08X",
-	remainder (i * 5 + 1), remainder (i * 5 + 2), remainder (i * 5 + 3),
-	      remainder (i * 5 + 4), remainder (i * 5 + 5));
+	      remainder (i * 5 + 1), remainder (i * 5 + 2),
+	      remainder (i * 5 + 3), remainder (i * 5 + 4),
+	      remainder (i * 5 + 5));
     }
   printf ("\n};\n");
   exit (EXIT_SUCCESS);
@@ -109,13 +115,12 @@ main ()
 
 #else /* !CRCTAB */
 
-# include <stdio.h>
 # include <getopt.h>
 # include <sys/types.h>
-# include "system.h"
 # include "closeout.h"
 # include "long-options.h"
 # include "error.h"
+# include "human.h"
 
 /* Number of bytes to read at once.  */
 # define BUFLEN (1 << 16)
@@ -128,7 +133,7 @@ static struct option const long_options[] =
   {0, 0, 0, 0}
 };
 
-static unsigned long const crctab[256] =
+static uint_fast32_t crctab[256] =
 {
   0x0,
   0x04C11DB7, 0x09823B6E, 0x0D4326D9, 0x130476DC, 0x17C56B6B,
@@ -196,10 +201,12 @@ static int
 cksum (const char *file, int print_name)
 {
   unsigned char buf[BUFLEN];
-  unsigned long crc = 0;
-  long length = 0;
-  long bytes_read;
+  uint_fast32_t crc = 0;
+  uintmax_t length = 0;
+  size_t bytes_read;
   register FILE *fp;
+  char hbuf[LONGEST_HUMAN_READABLE + 1];
+  char *hp;
 
   if (STREQ (file, "-"))
     {
@@ -223,9 +230,11 @@ cksum (const char *file, int print_name)
     {
       unsigned char *cp = buf;
 
+      if (length + bytes_read < length)
+	error (EXIT_FAILURE, 0, _("%s: file too long"), file);
       length += bytes_read;
       while (bytes_read--)
-	crc = (crc << 8) ^ crctab[((crc >> 24) ^ *(cp++)) & 0xFF];
+	crc = (crc << 8) ^ crctab[((crc >> 24) ^ *cp++) & 0xFF];
     }
 
   if (ferror (fp))
@@ -242,19 +251,20 @@ cksum (const char *file, int print_name)
       return -1;
     }
 
-  bytes_read = length;
-  while (bytes_read > 0)
-    {
-      crc = (crc << 8) ^ crctab[((crc >> 24) ^ bytes_read) & 0xFF];
-      bytes_read >>= 8;
-    }
+  hp = human_readable (length, hbuf, 1, 1);
+
+  for (; length; length >>= 8)
+    crc = (crc << 8) ^ crctab[((crc >> 24) ^ length) & 0xFF];
 
   crc = ~crc & 0xFFFFFFFF;
 
-  printf ("%lu %ld", crc, length);
   if (print_name)
-    printf (" %s", file);
-  putchar ('\n');
+    printf ("%u %s %s\n", (unsigned) crc, hp, file);
+  else
+    printf ("%u %s\n", (unsigned) crc, hp);
+
+  if (ferror (stdout))
+    error (EXIT_FAILURE, errno, "-: %s", _("write error"));
 
   return 0;
 }
@@ -313,16 +323,12 @@ main (int argc, char **argv)
 	}
     }
 
-  if (optind >= argc)
-    {
-      if (cksum ("-", 0) < 0)
-	errors = 1;
-    }
+  if (optind == argc)
+    errors |= cksum ("-", 0);
   else
     {
       for (i = optind; i < argc; i++)
-	if (cksum (argv[i], 1) < 0)
-	  errors = 1;
+	errors |= cksum (argv[i], 1);
     }
 
   if (have_read_stdin && fclose (stdin) == EOF)

src/dd.c

@@ -321,7 +321,8 @@ Each KEYWORD may be:\n\
   ucase     change lower case to upper case\n\
   swab      swap every pair of input bytes\n\
   noerror   continue after read errors\n\
-  sync      pad every input block with NULs to ibs-size\n\
+  sync      pad every input block with NULs to ibs-size; when used\n\
+              with block or unblock, pad with spaces rather than NULs\n\
 "));
       puts (_("\nReport bugs to <bug-fileutils@gnu.org>."));
     }
@@ -945,7 +946,7 @@ dd_copy (void)
     {
       /* FIXME: this loses for
 	 % ./dd if=dd seek=1 |:
-	 ./dd: standard output: Bad file number
+	 ./dd: standard output: Bad file descriptor
 	 0+0 records in
 	 0+0 records out
 	 */
@@ -965,7 +966,9 @@ dd_copy (void)
 	 whatever data we are able to read is followed by zeros.
 	 This minimizes data loss. */
       if ((conversions_mask & C_SYNC) && (conversions_mask & C_NOERROR))
-	memset ((char *) ibuf, 0, input_blocksize);
+	memset ((char *) ibuf,
+		(conversions_mask & (C_BLOCK | C_UNBLOCK)) ? ' ' : '\0',
+		input_blocksize);
 
       nread = safe_read (STDIN_FILENO, ibuf, input_blocksize);
 
@@ -1004,7 +1007,8 @@ dd_copy (void)
 	    {
 	      if (!(conversions_mask & C_NOERROR))
 		/* If C_NOERROR, we zeroed the block before reading. */
-		memset ((char *) (ibuf + n_bytes_read), 0,
+		memset ((char *) (ibuf + n_bytes_read),
+			(conversions_mask & (C_BLOCK | C_UNBLOCK)) ? ' ' : '\0',
 			input_blocksize - n_bytes_read);
 	      n_bytes_read = input_blocksize;
 	    }

src/ls.c

@@ -70,11 +70,6 @@
 #include <pwd.h>
 #include <getopt.h>
 
-/* Get MB_LEN_MAX.  */
-#if HAVE_LIMITS_H
-# include <limits.h>
-#endif
-
 /* Get MB_CUR_MAX.  */
 #if HAVE_STDLIB_H
 # include <stdlib.h>
@@ -345,16 +340,13 @@ char *program_name;
    `files_index' is the number actually in use.  */
 
 /* Address of block containing the files that are described.  */
-
-static struct fileinfo *files;
+static struct fileinfo *files;  /* FIXME: rename this to e.g. cwd_file */
 
 /* Length of block that `files' points to, measured in files.  */
-
-static int nfiles;
+static int nfiles;  /* FIXME: rename this to e.g. cwd_n_alloc */
 
 /* Index of first unused in `files'.  */
-
-static int files_index;
+static int files_index;  /* FIXME: rename this to e.g. cwd_n_used */
 
 /* When nonzero, in a color listing, color each symlink name according to the
    type of file it points to.  Otherwise, color them according to the `ln'
@@ -854,6 +846,7 @@ main (int argc, char **argv)
 {
   register int i;
   register struct pending *thispend;
+  unsigned int n_files;
 
   program_name = argv[0];
   setlocale (LC_ALL, "");
@@ -901,8 +894,10 @@ main (int argc, char **argv)
 
   clear_files ();
 
-  if (i < argc)
+  n_files = argc - i;
+  if (0 < n_files)
     dir_defaulted = 0;
+
   for (; i < argc; i++)
     {
       gobble_file (argv[i], unknown, 1, "");
@@ -929,7 +924,7 @@ main (int argc, char **argv)
       if (pending_dirs)
 	DIRED_PUTCHAR ('\n');
     }
-  else if (pending_dirs && pending_dirs->next == 0)
+  else if (n_files <= 1 && pending_dirs && pending_dirs->next == 0)
     print_dir_name = 0;
 
   while (pending_dirs)
@@ -1274,7 +1269,9 @@ Use `--si' for the old meaning."));
 	  break;
 
 	case '1':
-	  format = one_per_line;
+	  /* -1 has no effect after -l.  */
+	  if (format != long_format)
+	    format = one_per_line;
 	  break;
 
 	case SORT_OPTION:
@@ -2644,7 +2641,7 @@ quote_name (FILE *out, const char *name, struct quoting_options const *options)
 
   if (qmark_funny_chars)
     {
-#if HAVE_MBRTOWC && (MB_LEN_MAX > 1)
+#if HAVE_MBRTOWC
       if (MB_CUR_MAX > 1)
 	{
 	  const char *p = buf;
@@ -2765,7 +2762,7 @@ quote_name (FILE *out, const char *name, struct quoting_options const *options)
   else
     {
       /* Assume unprintable characters have a displayed_width of 1.  */
-#if HAVE_MBRTOWC && (MB_LEN_MAX > 1)
+#if HAVE_MBRTOWC
       if (MB_CUR_MAX > 1)
 	displayed_width = mbsnwidth (buf, len,
 				     (MBSW_ACCEPT_INVALID

src/sort.c

@@ -23,6 +23,7 @@
 
 #include <config.h>
 
+#include <getopt.h>
 #include <sys/types.h>
 #include <signal.h>
 #include <stdio.h>
@@ -45,9 +46,6 @@
 struct rlimit { size_t rlim_cur; };
 # define getrlimit(Resource, Rlp) (-1)
 #endif
-#ifndef RLIMIT_AS
-# define RLIMIT_AS RLIMIT_DATA
-#endif
 
 /* The official name of this program (e.g., no `g' prefix).  */
 #define PROGRAM_NAME "sort"
@@ -291,29 +289,36 @@ Usage: %s [OPTION]... [FILE]...\n\
       printf (_("\
 Write sorted concatenation of all FILE(s) to standard output.\n\
 \n\
-  -b               ignore leading blanks in sort fields or keys\n\
-  -c               check if given files already sorted, do not sort\n\
-  -d               consider only blanks and alphanumeric characters in keys\n\
-  -f               fold lower case to upper case characters in keys\n\
-  -g               compare according to general numerical value, imply -b\n\
-  -i               consider only printable characters in keys\n\
-  -k POS1[,POS2]   start a key at POS1, end it *at* POS2 (origin 1)\n\
-  -m               merge already sorted files, do not sort\n\
-  -M               compare (unknown) < `JAN' < ... < `DEC', imply -b\n\
-  -n               compare according to string numerical value, imply -b\n\
-  -o FILE          write result on FILE instead of standard output\n\
-  -r               reverse the result of comparisons\n\
-  -s               stabilize sort by disabling last resort comparison\n\
-  -S SIZE          use SIZE for main memory sorting\n\
-  -t SEP           use SEParator instead of non- to whitespace transition\n\
-  -T DIRECTORY     use DIRECTORY for temporary files, not $TMPDIR or %s\n\
-                     multiple -T options specify multiple directories\n\
-  -u               with -c, check for strict ordering;\n\
-                   with -m, only output the first of an equal sequence\n\
-  -z               end lines with 0 byte, not newline, for find -print0\n\
-  +POS1 [-POS2]    start a key at POS1, end it *before* POS2 (origin 0)\n\
-                     Warning: this option is obsolescent and support for it\n\
-                     will be withdrawn.  Use -k instead.\n\
+Ordering options:\n\
+\n\
+  -b, --ignore-leading-blanks ignore leading blanks\n\
+  -d, --dictionary-order      consider only blanks and alphanumeric characters\n\
+  -f, --ignore-case           fold lower case to upper case characters\n\
+  -g, --general-numeric-sort  compare according to general numerical value\n\
+  -i, --ignore-nonprinting    consider only printable characters\n\
+  -M, --month-sort            compare (unknown) < `JAN' < ... < `DEC'\n\
+  -n, --numeric-sort          compare according to string numerical value\n\
+  -r, --reverse               reverse the result of comparisons\n\
+\n\
+")
+	      );
+      printf (_("\
+Other options:\n\
+\n\
+  -c, --check               check whether input is sorted; do not sort\n\
+  -k, --key=POS1[,POS2]     start a key at POS1, end it at POS 2 (origin 1)\n\
+  -m, --merge               merge already sorted files; do not sort\n\
+  -o, --output=FILE         write result to FILE instead of standard output\n\
+  -s, --stable              stabilize sort by disabling last-resort comparison\n\
+  -S, --buffer-size=SIZE    use SIZE for main memory buffer\n\
+  -t, --field-separator=SEP use SEP instead of non- to whitespace transition\n\
+  -T, --temporary-directory=DIR  use DIR for temporaries, not $TMPDIR or %s\n\
+                              multiple options specify multiple directories\n\
+  -u, --unique              with -c: check for strict ordering\n\
+                              otherwise: output only the first of an equal run\n\
+  -z, --zero-terminated     end lines with 0 byte, not newline\n\
+  +POS1 [-POS2]             start a key at POS1, end it before POS2 (origin 0)\n\
+                              Warning: this option is obsolescent\n\
       --help       display this help and exit\n\
       --version    output version information and exit\n\
 \n\
@@ -322,9 +327,9 @@ Write sorted concatenation of all FILE(s) to standard output.\n\
       printf (_("\
 POS is F[.C][OPTS], where F is the field number and C the character position\n\
 in the field, both counted from one with -k, from zero with the obsolescent\n\
-form.  OPTS is made up of one or more of Mbdfinr; this effectively disables\n\
-global -Mbdfinr settings for that key.  If no key is given, use the entire\n\
-line as the key.\n\
+form.  OPTS is made up of one or more single-letter ordering options, which\n\
+override global ordering options for that key.  If no key is given, use the\n\
+entire line as the key.\n\
 \n\
 SIZE may be followed by the following multiplicative suffixes:\n\
 %% 1%% of memory, b 1, k 1024 (default), and so on for M, G, T, P, E, Z, Y.\n\
@@ -345,6 +350,31 @@ Set LC_ALL=C to get the traditional sort order that uses native byte values.\n\
   exit (status);
 }
 
+static struct option const long_options[] =
+{
+  {"ignore-leading-blanks", no_argument, NULL, 'b'},
+  {"check", no_argument, NULL, 'c'},
+  {"dictionary-order", no_argument, NULL, 'd'},
+  {"ignore-case", no_argument, NULL, 'f'},
+  {"general-numeric-sort", no_argument, NULL, 'g'},
+  {"ignore-nonprinting", no_argument, NULL, 'i'},
+  {"key", required_argument, NULL, 'k'},
+  {"merge", no_argument, NULL, 'm'},
+  {"month-sort", no_argument, NULL, 'M'},
+  {"numeric-sort", no_argument, NULL, 'n'},
+  {"output", required_argument, NULL, 'o'},
+  {"reverse", no_argument, NULL, 'r'},
+  {"stable", no_argument, NULL, 's'},
+  {"buffer-size", required_argument, NULL, 'S'},
+  {"field-separator", required_argument, NULL, 't'},
+  {"temporary-directory", required_argument, NULL, 'T'},
+  {"unique", no_argument, NULL, 'u'},
+  {"zero-terminated", no_argument, NULL, 'z'},
+  {GETOPT_HELP_OPTION_DECL},
+  {GETOPT_VERSION_OPTION_DECL},
+  {0, 0, 0, 0},
+};
+
 /* The set of signals that are caught.  */
 static sigset_t caught_signals;
 
@@ -632,11 +662,24 @@ default_sort_size (void)
     size = mem;
   if (getrlimit (RLIMIT_DATA, &rlimit) == 0 && rlimit.rlim_cur < size)
     size = rlimit.rlim_cur;
+#ifdef RLIMIT_AS
   if (getrlimit (RLIMIT_AS, &rlimit) == 0 && rlimit.rlim_cur < size)
     size = rlimit.rlim_cur;
+#endif
 
-  /* Use half of SIZE, but no less than the minimum.  */
-  return MAX (size / 2, MIN_SORT_SIZE);
+  /* Leave a large safety margin for the above limits, as failure can
+     occur when they are exceeded.  */
+  size /= 2;
+
+#ifdef RLIMIT_RSS
+  /* Leave a 1/16 margin for RSS to leave room for code, stack, etc.
+     Exceeding RSS is not fatal, but can be quite slow.  */
+  if (getrlimit (RLIMIT_RSS, &rlimit) == 0 && rlimit.rlim_cur / 16 * 15 < size)
+    size = rlimit.rlim_cur / 16 * 15;
+#endif
+
+  /* Use no less than the minimum.  */
+  return MAX (size, MIN_SORT_SIZE);
 }
 
 /* Return the sort buffer size to use with the input files identified
@@ -1975,21 +2018,26 @@ insertkey (struct keyfield *key)
   key->next = NULL;
 }
 
+/* Report a bad field specification SPEC, with extra info MSGID.  */
+
+static void badfieldspec PARAMS ((char const *, char const *))
+     ATTRIBUTE_NORETURN;
 static void
-badfieldspec (const char *s)
+badfieldspec (char const *spec, char const *msgid)
 {
-  error (SORT_FAILURE, 0, _("invalid field specification `%s'"), s);
+  error (SORT_FAILURE, 0, _("%s: invalid field specification `%s'"),
+	 _(msgid), spec);
+  abort ();
 }
 
 /* Parse the leading integer in STRING and store the resulting value
    (which must fit into size_t) into *VAL.  Return the address of the
-   suffix after the integer.  */
+   suffix after the integer.  If MSGID is NULL, return NULL after
+   failure; otherwise, report MSGID and exit on failure.  */
+
 static char const *
-parse_field_count (char const *string, size_t *val)
+parse_field_count (char const *string, size_t *val, char const *msgid)
 {
-  /* '@' can't possibly be a valid suffix; return &invalid_suffix so that
-     the caller will eventually invoke badfieldspec.  */
-  static char const invalid_suffix = '@';
   char *suffix;
   uintmax_t n;
 
@@ -2002,13 +2050,16 @@ parse_field_count (char const *string, size_t *val)
 	break;
       /* Fall through.  */
     case LONGINT_OVERFLOW:
-      error (0, 0, _("count `%.*s' too large"),
-	     (int) (suffix - string), string);
-      return &invalid_suffix;
+      if (msgid)
+	error (SORT_FAILURE, 0, _("%s: count `%.*s' too large"),
+	       _(msgid), (int) (suffix - string), string);
+      return NULL;
 
     case LONGINT_INVALID:
-      error (0, 0, _("invalid count at start of `%s'"), string);
-      return &invalid_suffix;
+      if (msgid)
+	error (SORT_FAILURE, 0, _("%s: invalid count at start of `%s'"),
+	       _(msgid), string);
+      return NULL;
     }
 
   return suffix;
@@ -2089,20 +2140,24 @@ set_ordering (register const char *s, struct keyfield *key,
   return (char *) s;
 }
 
-static void
-key_init (struct keyfield *key)
+static struct keyfield *
+new_key (void)
 {
-  memset (key, 0, sizeof (*key));
+  struct keyfield *key = (struct keyfield *) xcalloc (1, sizeof *key);
   key->eword = -1;
+  return key;
 }
 
 int
 main (int argc, char **argv)
 {
-  struct keyfield *key = NULL, gkey;
+  struct keyfield *key;
+  struct keyfield gkey;
   char const *s;
   int i;
+  int c = 0;
   int checkonly = 0, mergeonly = 0, nfiles = 0;
+  int posix_pedantic = (getenv ("POSIXLY_CORRECT") != NULL);
   char *minus = "-", **files;
   char const *outfile = minus;
   static int const sigs[] = { SIGHUP, SIGINT, SIGPIPE, SIGTERM };
@@ -2143,9 +2198,6 @@ main (int argc, char **argv)
 
 #endif /* NLS */
 
-  parse_long_options (argc, argv, PROGRAM_NAME, PACKAGE, VERSION,
-		      AUTHORS, usage);
-
   have_read_stdin = 0;
   inittables ();
 
@@ -2183,236 +2235,201 @@ main (int argc, char **argv)
 
   files = (char **) xmalloc (sizeof (char *) * argc);
 
-  for (i = 1; i < argc; ++i)
+  for (;;)
     {
-      if (argv[i][0] == '+')
+      /* Parse an operand as a file after "--" was seen; or if
+         pedantic and a file was seen, unless -c was not seen and the
+         operand is "-o FILE" or "-oFILE".  POSIX 1003.1-200x d5
+         removes the exception for the -o options; when it becomes
+         official the code will need to be changed.  */
+
+      if (c == -1
+	  || (posix_pedantic && nfiles != 0
+	      && ! (! checkonly
+		    && optind != argc
+		    && argv[optind][0] == '-' && argv[optind][1] == 'o'
+		    && (argv[optind][2] || optind + 1 != argc)))
+	  || ((c = getopt_long (argc, argv,
+				"-bcdfgik:mMno:rsS:t:T:uy::z",
+				long_options, NULL))
+	      == -1))
 	{
-	  if (key)
-	    insertkey (key);
-	  key = (struct keyfield *) xmalloc (sizeof (struct keyfield));
-	  key_init (key);
-	  s = argv[i] + 1;
-	  if (! (ISDIGIT (*s) || (*s == '.' && ISDIGIT (s[1]))))
-	    badfieldspec (argv[i]);
-	  s = parse_field_count (s, &key->sword);
+	  if (optind == argc)
+	    break;
+	  files[nfiles++] = argv[optind++];
+	}
+      else switch (c)
+	{
+	case 1:
+	  /* Treat +POS1 [-POS2] as a key if possible; but silently
+	     treat an operand as a file if it is not a valid +POS1.
+	     POSIX 1003.1-200x d5 does not allow support for +POS1, so
+	     when it becomes official this code will need to be
+	     changed.  */
+	  key = NULL;
+	  if (optarg[0] == '+')
+	    {
+	      key = new_key ();
+	      s = parse_field_count (optarg + 1, &key->sword, NULL);
+	      if (s && *s == '.')
+		s = parse_field_count (s + 1, &key->schar, NULL);
+	      if (! (key->sword | key->schar))
+		key->sword = -1;
+	      if (! s || *set_ordering (s, key, bl_start))
+		{
+		  free (key);
+		  key = NULL;
+		}
+	      else
+		{
+		  if (optind != argc && argv[optind][0] == '-'
+		      && ISDIGIT (argv[optind][1]))
+		    {
+		      char const *optarg1 = argv[optind++];
+		      s = parse_field_count (optarg1 + 1, &key->eword,
+					     N_("invalid number after `-'"));
+		      if (*s == '.')
+			s = parse_field_count (s + 1, &key->echar,
+					       N_("invalid number after `.'"));
+		      if (*set_ordering (s, key, bl_end))
+			badfieldspec (optarg1,
+				      N_("stray character in field spec"));
+		    }
+		  insertkey (key);
+		}
+	    }
+	  if (! key)
+	    files[nfiles++] = optarg;
+	  break;
+
+	case 'b':
+	case 'd':
+	case 'f':
+	case 'g':
+	case 'i':
+	case 'M':
+	case 'n':
+	case 'r':
+	  {
+	    char str[2];
+	    str[0] = c;
+	    str[1] = '\0';
+	    set_ordering (str, &gkey, bl_both);
+	  }
+	  break;
+
+	case 'c':
+	  checkonly = 1;
+	  break;
+
+	case 'k':
+	  key = new_key ();
+
+	  /* Get POS1. */
+	  s = parse_field_count (optarg, &key->sword,
+				 N_("invalid number at field start"));
+	  if (! key->sword--)
+	    {
+	      /* Provoke with `sort -k0' */
+	      badfieldspec (optarg, N_("field number is zero"));
+	    }
 	  if (*s == '.')
-	    s = parse_field_count (s + 1, &key->schar);
+	    {
+	      s = parse_field_count (s + 1, &key->schar,
+				     N_("invalid number after `.'"));
+	      if (! key->schar--)
+		{
+		  /* Provoke with `sort -k1.0' */
+		  badfieldspec (optarg, N_("character offset is zero"));
+		}
+	    }
 	  if (! (key->sword | key->schar))
 	    key->sword = -1;
 	  s = set_ordering (s, key, bl_start);
-	  if (*s)
-	    badfieldspec (argv[i]);
-	}
-      else if (argv[i][0] == '-' && argv[i][1])
-	{
-	  s = argv[i] + 1;
-	  if (ISDIGIT (*s) || (*s == '.' && ISDIGIT (s[1])))
+	  if (*s != ',')
 	    {
-	      if (!key)
-		{
-		  /* Provoke with `sort -9'.  */
-		  error (0, 0, _("when using the old-style +POS and -POS \
-key specifiers,\nthe +POS specifier must come first"));
-		  usage (SORT_FAILURE);
-		}
-	      s = parse_field_count (s, &key->eword);
-	      if (*s == '.')
-		s = parse_field_count (s + 1, &key->echar);
-	      s = set_ordering (s, key, bl_end);
-	      if (*s)
-		badfieldspec (argv[i]);
-	      insertkey (key);
-	      key = NULL;
+	      key->eword = -1;
+	      key->echar = 0;
 	    }
 	  else
-	    while (*s)
-	      {
-		s = set_ordering (s, &gkey, bl_both);
-		switch (*s)
-		  {
-		  case '\0':
-		    break;
-		  case 'c':
-		    checkonly = 1;
-		    break;
-		  case 'k':
-		    if (s[1])
-		      ++s;
-		    else
-		      {
-			if (i == argc - 1)
-			  error (SORT_FAILURE, 0,
-				 _("option `-k' requires an argument"));
-			else
-			  s = argv[++i];
-		      }
-		    if (key)
-		      insertkey (key);
-		    key = (struct keyfield *)
-		      xmalloc (sizeof (struct keyfield));
-		    key_init (key);
-		    /* Get POS1. */
-		    if (!ISDIGIT (*s))
-		      badfieldspec (argv[i]);
-		    s = parse_field_count (s, &key->sword);
-		    if (! key->sword--)
-		      {
-			/* Provoke with `sort -k0' */
-			error (0, 0, _("the starting field number argument \
-to the `-k' option must be positive"));
-			badfieldspec (argv[i]);
-		      }
-		    if (*s == '.')
-		      {
-			if (!ISDIGIT (s[1]))
-			  {
-			    /* Provoke with `sort -k1.' */
-			    error (0, 0, _("starting field spec has `.' but \
-lacks following character offset"));
-			    badfieldspec (argv[i]);
-			  }
-			s = parse_field_count (s + 1, &key->schar);
-			if (! key->schar--)
-			  {
-			    /* Provoke with `sort -k1.0' */
-			    error (0, 0, _("starting field character offset \
-argument to the `-k' option must be positive"));
-			    badfieldspec (argv[i]);
-			  }
-		      }
-		    if (! (key->sword | key->schar))
-		      key->sword = -1;
-		    s = set_ordering (s, key, bl_start);
-		    if (*s == 0)
-		      {
-			key->eword = -1;
-			key->echar = 0;
-		      }
-		    else if (*s != ',')
-		      badfieldspec (argv[i]);
-		    else if (*s == ',')
-		      {
-			/* Skip over comma.  */
-			++s;
-			if (*s == 0)
-			  {
-			    /* Provoke with `sort -k1,' */
-			    error (0, 0, _("field specification has `,' but \
-lacks following field spec"));
-			    badfieldspec (argv[i]);
-			  }
-			/* Get POS2. */
-			s = parse_field_count (s, &key->eword);
-			if (! key->eword--)
-			  {
-			    /* Provoke with `sort -k1,0' */
-			    error (0, 0, _("ending field number argument \
-to the `-k' option must be positive"));
-			    badfieldspec (argv[i]);
-			  }
-			if (*s == '.')
-			  {
-			    if (!ISDIGIT (s[1]))
-			      {
-				/* Provoke with `sort -k1,1.' */
-				error (0, 0, _("ending field spec has `.' \
-but lacks following character offset"));
-				badfieldspec (argv[i]);
-			      }
-			    s = parse_field_count (s + 1, &key->echar);
-			  }
-			else
-			  {
-			    /* `-k 2,3' is equivalent to `+1 -3'.  */
-			    key->eword++;
-			  }
-			s = set_ordering (s, key, bl_end);
-			if (*s)
-			  badfieldspec (argv[i]);
-		      }
-		    insertkey (key);
-		    key = NULL;
-		    goto outer;
-		  case 'm':
-		    mergeonly = 1;
-		    break;
-		  case 'o':
-		    if (s[1])
-		      outfile = s + 1;
-		    else
-		      {
-			if (i == argc - 1)
-			  error (SORT_FAILURE, 0,
-				 _("option `-o' requires an argument"));
-			else
-			  outfile = argv[++i];
-		      }
-		    goto outer;
-		  case 's':
-		    stable = 1;
-		    break;
-		  case 'S':
-		    if (s[1])
-		      specify_sort_size (++s);
-		    else if (i < argc - 1)
-		      specify_sort_size (argv[++i]);
-		    else
-		      error (SORT_FAILURE, 0,
-			     _("option `-S' requires an argument"));
-		    goto outer;
-		  case 't':
-		    if (s[1])
-		      tab = *++s;
-		    else if (i < argc - 1)
-		      {
-			tab = *argv[++i];
-			goto outer;
-		      }
-		    else
-		      error (SORT_FAILURE, 0,
-			     _("option `-t' requires an argument"));
-		    break;
-		  case 'T':
-		    if (s[1])
-		      add_temp_dir (++s);
-		    else
-		      {
-			if (i < argc - 1)
-			  add_temp_dir (argv[++i]);
-			else
-			  error (SORT_FAILURE, 0,
-				 _("option `-T' requires an argument"));
-		      }
-		    goto outer;
-		    /* break; */
-		  case 'u':
-		    unique = 1;
-		    break;
-		  case 'z':
-		    eolchar = 0;
-		    break;
-		  case 'y':
-		    /* Accept and ignore e.g. -y0 for compatibility with
-		       Solaris 2.  */
-		    goto outer;
-		  default:
-		    fprintf (stderr, _("%s: unrecognized option `-%c'\n"),
-			     argv[0], *s);
-		    usage (SORT_FAILURE);
-		  }
-		if (*s)
-		  ++s;
-	      }
-	}
-      else			/* Not an option. */
-	{
-	  files[nfiles++] = argv[i];
-	}
-    outer:;
-    }
+	    {
+	      /* Get POS2. */
+	      s = parse_field_count (s + 1, &key->eword,
+				     N_("invalid number after `,'"));
+	      if (! key->eword--)
+		{
+		  /* Provoke with `sort -k1,0' */
+		  badfieldspec (optarg, N_("field number is zero"));
+		}
+	      if (*s == '.')
+		s = parse_field_count (s + 1, &key->echar,
+				       N_("invalid number after `.'"));
+	      else
+		{
+		  /* `-k 2,3' is equivalent to `+1 -3'.  */
+		  key->eword++;
+		}
+	      s = set_ordering (s, key, bl_end);
+	    }
+	  if (*s)
+	    badfieldspec (optarg, N_("stray character in field spec"));
+	  insertkey (key);
+	  break;
 
-  if (key)
-    insertkey (key);
+	case 'm':
+	  mergeonly = 1;
+	  break;
+
+	case 'o':
+	  outfile = optarg;
+	  break;
+
+	case 's':
+	  stable = 1;
+	  break;
+
+	case 'S':
+	  specify_sort_size (optarg);
+	  break;
+
+	case 't':
+	  tab = optarg[0];
+	  if (tab && optarg[1])
+	    {
+	      /* Provoke with `sort -txx'.  Complain about
+		 "multi-character tab" instead of "multibyte tab", so
+		 that the diagnostic's wording does not need to be
+		 changed once multibyte characters are supported.  */
+	      error (SORT_FAILURE, 0, _("multi-character tab `%s'"), optarg);
+	    }
+	  break;
+
+	case 'T':
+	  add_temp_dir (optarg);
+	  break;
+
+	case 'u':
+	  unique = 1;
+	  break;
+
+	case 'y':
+	  /* Accept and ignore e.g. -y0 for compatibility with Solaris
+	     2.x through Solaris 7.  -y is marked as obsolete starting
+	     with Solaris 8.  */
+	  break;
+
+	case 'z':
+	  eolchar = 0;
+	  break;
+
+	case_GETOPT_HELP_CHAR;
+
+	case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);
+
+	default:
+	  usage (SORT_FAILURE);
+	}
+    }
 
   /* Inheritance of global options to individual keys. */
   for (key = keylist; key; key = key->next)
@@ -2451,9 +2468,8 @@ but lacks following character offset"));
   if (checkonly)
     {
       if (nfiles > 1)
-	error (SORT_FAILURE, 0,
-	       _("too many arguments;  with -c, there may be at most\
- one file argument"));
+	error (SORT_FAILURE, 0, _("extra operand `%s' not allowed with -c"),
+	       files[1]);
 
       /* POSIX requires that sort return 1 IFF invoked with -c and the
 	 input is not properly sorted.  */

src/wc.c

@@ -126,7 +126,7 @@ Usage: %s [OPTION]... [FILE]...\n\
 "),
 	      program_name);
       printf (_("\
-Print line, word, and byte counts for each FILE, and a total line if\n\
+Print newline, word, and byte counts for each FILE, and a total line if\n\
 more than one FILE is specified.  With no FILE, or when FILE is -,\n\
 read standard input.\n\
   -c, --bytes            print the byte counts\n\

tests/chgrp/basic

@@ -34,6 +34,7 @@ touch f f2 d/f3
 chgrp $g1 f || fail=1
 chgrp $g2 f || fail=1
 chgrp $g2 f2 || fail=1
+chgrp -R $g1 d || fail=1
 
 (
   chgrp -c $g1 f

tests/dd/skip-seek

@@ -27,7 +27,7 @@ my $script_name = $ENV{SCRIPT_NAME};
 my @Tests =
     (
      [
-      '1', qw (bs=1 skip=1 seek=2 conv=notrunc count=3 of=@AUX@ < ),
+      'skip-seek-1', qw (bs=1 skip=1 seek=2 conv=notrunc count=3 of=@AUX@ < ),
       {IN=> '0123456789abcdef'},
       {AUX=> 'zyxwvutsrqponmlkji'},
       {OUT=> ''},
@@ -35,7 +35,7 @@ my @Tests =
       {CMP=> ['zy123utsrqponmlkji', {'@AUX@'=> undef}]},
      ],
      [
-      '3', qw (bs=5 skip=1 seek=1 conv=notrunc count=1 of=@AUX@ < ),
+      'skip-seek-2', qw (bs=5 skip=1 seek=1 conv=notrunc count=1 of=@AUX@ < ),
       {IN=> '0123456789abcdef'},
       {AUX=> 'zyxwvutsrqponmlkji'},
       {OUT=> ''},
@@ -43,13 +43,21 @@ my @Tests =
       {CMP=> ['zyxwv56789ponmlkji', {'@AUX@'=> undef}]},
      ],
      [
-      '4', qw (bs=5 skip=1 seek=1 count=1 of=@AUX@ < ),
+      'skip-seek-3', qw (bs=5 skip=1 seek=1 count=1 of=@AUX@ < ),
       {IN=> '0123456789abcdef'},
       {AUX=> 'zyxwvutsrqponmlkji'},
       {OUT=> ''},
       {ERR=> "1+0 records in\n1+0 records out\n"},
       {CMP=> ['zyxwv56789', {'@AUX@'=> undef}]},
      ],
+     [
+      # Before fileutils-4.0.45, the last 10 bytes of output
+      # were these "\0\0\0\0\0\0\0\0  ".
+      'block-sync-1', qw(ibs=10 cbs=10), 'conv=block,sync', '<',
+      {IN=> "01234567\nabcdefghijkl\n"},
+      {OUT=> "01234567  abcdefghij          "},
+      {ERR=> "2+1 records in\n0+1 records out\n1 truncated record\n"},
+     ],
     );
 
 my $save_temps = $ENV{DEBUG};

tests/ls-2/tests

@@ -22,6 +22,11 @@ use strict;
 my $mkdir = {PRE => sub {mkdir 'd',0755 or die "d: $!\n"}};
 my $rmdir = {POST => sub {rmdir 'd' or die "d: $!\n"}};
 
+my $mkdir2 = {PRE => sub {mkdir 'd',0755 or die "d: $!\n";
+			  mkdir 'd/e',0755 or die "d/e: $!\n" }};
+my $rmdir2 = {POST => sub {rmdir 'd/e' or die "d/e: $!\n";
+			   rmdir 'd' or die "d: $!\n" }};
+
 my $slink_d = {PRE => sub {symlink '/', 'd' or die "d: $!\n"}};
 my $unlink_d = {POST => sub {unlink 'd' or die "d: $!\n"}};
 
@@ -58,6 +63,14 @@ my @Tests =
 
      # FIXME: uncomment the following once ls has been fixed
      # ['slink-dir2', '-F d', {OUT => "d\@/\n"}, $slink_d, $unlink_d],
+
+     # From Stéphane Chazelas.
+     ['no-a-isdir-b', 'no-dir d',
+	 {OUT => "d:\n"},
+	 {ERR => "ls: no-dir: No such file or directory\n"},
+	 $mkdir, $rmdir, {EXIT => 1}],
+
+     ['recursive-2', '-R d', {OUT => "d:\ne\n\nd/e:\n"}, $mkdir2, $rmdir2],
     );
 
 my $save_temps = $ENV{SAVE_TEMPS};

tests/ls/Makefile.am

@@ -2,7 +2,7 @@
 
 AUTOMAKE_OPTIONS = 1.2 gnits
 
-TESTS = rt-1 time-1 symlink-slash follow-slink
+TESTS = rt-1 time-1 symlink-slash follow-slink no-arg
 EXTRA_DIST = $(TESTS)
 TESTS_ENVIRONMENT = \
   top_srcdir=$(top_srcdir) \

tests/ls/Makefile.in

@@ -121,7 +121,7 @@ l = @l@
 
 AUTOMAKE_OPTIONS = 1.2 gnits
 
-TESTS = rt-1 time-1 symlink-slash follow-slink
+TESTS = rt-1 time-1 symlink-slash follow-slink no-arg
 EXTRA_DIST = $(TESTS)
 TESTS_ENVIRONMENT = \
   top_srcdir=$(top_srcdir) \

tests/ls/no-arg

@@ -0,0 +1,59 @@
+#!/bin/sh
+# make sure ls and `ls -R' do the right thing when invoked with no arguments.
+
+if test "$VERBOSE" = yes; then
+  set -x
+  ls --version
+fi
+
+pwd=`pwd`
+tmp=no-args.$$
+trap 'status=$?; cd $pwd; rm -rf $tmp && exit $status' 0
+trap '(exit $?); exit' 1 2 13 15
+
+framework_failure=0
+mkdir $tmp || framework_failure=1
+cd $tmp || framework_failure=1
+mkdir -p dir/subdir || framework_failure=1
+touch dir/subdir/file2 || framework_failure=1
+ln -s f symlink || framework_failure=1
+
+cat > exp <<\EOF || framework_failure=1
+dir
+exp
+out
+symlink
+EOF
+
+if test $framework_failure = 1; then
+  echo 'failure in testing framework'
+  (exit 1); exit
+fi
+
+fail=0
+
+ls > out || fail=1
+
+cmp out exp || fail=1
+test $fail = 1 && diff out exp 2> /dev/null
+
+cat > exp <<\EOF
+.:
+dir
+exp
+out
+symlink
+
+./dir:
+subdir
+
+./dir/subdir:
+file2
+EOF
+
+ls -R > out || fail=1
+
+cmp out exp || fail=1
+test $fail = 1 && diff out exp 2> /dev/null
+
+(exit $fail); exit

tests/mv/setup

@@ -17,6 +17,10 @@ other_partition_tmpdir=
 # if the mount point name contains `% '.
 dot_mount_point=`df --no-sync -P . | sed -n '2s/.*%  *//p'`
 for d in $CANDIDATE_TMP_DIRS; do
+
+  # Skip nonexistent directories.
+  test -d $d || continue
+
   d_mount_point=`df --no-sync -P $d | sed -n '2s/.*%  *//p'`
 
   # Same partition?  Skip it.