Add -z option to uniq. Originally proposed by Egmont Koblinger.

* NEWS: Mention uniq's new option: --zero-terminated (-z).
* src/uniq.c: Add new option, --zero-terminated (-z), to make
uniq use the NUL byte as separator/delimiter rather than newline.
(check_file): Add a parameter: delimiter.  Update caller.
Use readlinebuffer_delim in place of readlinebuffer everywhere.
(main): Handle the new option.
(usage): Describe new option the same way sort does.
* doc/coreutils.texi (uniq invocation): Describe the new option.

diff --git a/ChangeLog b/ChangeLog
index d9950c6..ed23b65 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+2007-05-12  James Youngman  <jay@gnu.org>
+
+       Add -z option to uniq.  Originally proposed by Egmont Koblinger.
+       * NEWS: Mention uniq's new option: --zero-terminated (-z).
+       * src/uniq.c: Add new option, --zero-terminated (-z), to make
+       uniq use the NUL byte as separator/delimiter rather than newline.
+       (check_file): Add a parameter: delimiter.  Update caller.
+       Use readlinebuffer_delim in place of readlinebuffer everywhere.
+       (main): Handle the new option.
+       (usage): Describe new option the same way sort does.
+       * doc/coreutils.texi (uniq invocation): Describe the new option.
+
 2007-05-07  Jim Meyering  <jim@meyering.net>
 
        * NEWS: Mention that last week's tr bug dates back to 1992.

diff --git a/NEWS b/NEWS
index ea3aafb..2a23108 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -6,6 +6,10 @@ GNU coreutils NEWS                                    -*- outline -*-
 
   Add SELinux support (FIXME: add details here)
 
+  uniq accepts a new option: --zero-terminated (-z).  As with the sort
+  option of the same name, this makes uniq consume and produce
+  NUL-terminated lines rather than newline-terminated lines.
+
 ** Bug fixes
 
   ls -x DIR would sometimes output the wrong string in place of the

diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index 6fc72ec..cc4d0b8 100644 (file)
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -4229,11 +4229,15 @@ This is equivalent to @option{--all-repeated} (@option{-D}).
 
 @item prepend
 Output a newline before each group of repeated lines.
+With @option{--zero-terminated} (@option{-z}), use
+an @acronym{ASCII} @sc{nul} (zero) byte instead of a newline.
 
 @item separate
 Separate groups of repeated lines with a single newline.
+With @option{--zero-terminated} (@option{-z}), use
+an @acronym{ASCII} @sc{nul} (zero) byte instead of a newline.
 This is the same as using @samp{prepend}, except that
-there is no newline before the first group, and hence
+no delimiter is inserted before the first group, and hence
 may be better suited for output direct to users.
 @end table
 
@@ -4261,6 +4265,19 @@ Compare at most @var{n} characters on each line (after skipping any specified
 fields and characters).  By default the entire rest of the lines are
 compared.
 
+@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 null character
+(@acronym{ASCII} @sc{nul}) instead of a line feed
+(@acronym{ASCII} @sc{lf}).
+This option can be useful in conjunction with @samp{sort -z}, @samp{perl -0} or
+@samp{find -print0} and @samp{xargs -0} which do the same in order to
+reliably handle arbitrary file names (even those containing blanks
+or other special characters).
+
 @end table
 
 @exitstatus

diff --git a/src/uniq.c b/src/uniq.c
index ac0840b..36e2ea3 100644 (file)
--- a/src/uniq.c
+++ b/src/uniq.c
@@ -1,5 +1,5 @@
 /* uniq -- remove duplicate lines from a sorted file
-   Copyright (C) 86, 91, 1995-2006 Free Software Foundation, Inc.
+   Copyright (C) 86, 91, 1995-2007 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
@@ -119,6 +119,7 @@ static struct option const longopts[] =
   {"skip-fields", required_argument, NULL, 'f'},
   {"skip-chars", required_argument, NULL, 's'},
   {"check-chars", required_argument, NULL, 'w'},
+  {"zero-terminated", no_argument, NULL, 'z'},
   {GETOPT_HELP_OPTION_DECL},
   {GETOPT_VERSION_OPTION_DECL},
   {NULL, 0, NULL, 0}
@@ -156,6 +157,7 @@ Mandatory arguments to long options are mandatory for short options too.\n\
   -i, --ignore-case     ignore differences in case when comparing\n\
   -s, --skip-chars=N    avoid comparing the first N characters\n\
   -u, --unique          only print unique lines\n\
+  -z, --zero-terminated  end lines with 0 byte, not newline\n\
 "), stdout);
      fputs (_("\
   -w, --check-chars=N   compare no more than N characters in lines\n\
@@ -268,7 +270,7 @@ writeline (struct linebuffer const *line,
    If either is "-", use the standard I/O stream for it instead. */
 
 static void
-check_file (const char *infile, const char *outfile)
+check_file (const char *infile, const char *outfile, char delimiter)
 {
   struct linebuffer lb1, lb2;
   struct linebuffer *thisline, *prevline;
@@ -300,7 +302,7 @@ check_file (const char *infile, const char *outfile)
        {
          char *thisfield;
          size_t thislen;
-         if (readlinebuffer (thisline, stdin) == 0)
+         if (readlinebuffer_delim (thisline, stdin, delimiter) == 0)
            break;
          thisfield = find_field (thisline);
          thislen = thisline->length - 1 - (thisfield - thisline->buffer);
@@ -323,7 +325,7 @@ check_file (const char *infile, const char *outfile)
       uintmax_t match_count = 0;
       bool first_delimiter = true;
 
-      if (readlinebuffer (prevline, stdin) == 0)
+      if (readlinebuffer_delim (prevline, stdin, delimiter) == 0)
        goto closefiles;
       prevfield = find_field (prevline);
       prevlen = prevline->length - 1 - (prevfield - prevline->buffer);
@@ -333,7 +335,7 @@ check_file (const char *infile, const char *outfile)
          bool match;
          char *thisfield;
          size_t thislen;
-         if (readlinebuffer (thisline, stdin) == 0)
+         if (readlinebuffer_delim (thisline, stdin, delimiter) == 0)
            {
              if (ferror (stdin))
                goto closefiles;
@@ -363,7 +365,7 @@ check_file (const char *infile, const char *outfile)
                  if ((delimit_groups == DM_PREPEND)
                      || (delimit_groups == DM_SEPARATE
                          && !first_delimiter))
-                   putchar ('\n');
+                   putchar (delimiter);
                }
            }
 
@@ -406,6 +408,7 @@ main (int argc, char **argv)
   enum Skip_field_option_type skip_field_option_type = SFO_NONE;
   int nfiles = 0;
   char const *file[2];
+  char delimiter = '\n';       /* change with --zero-terminated, -z */
 
   file[0] = file[1] = "-";
   initialize_main (&argc, &argv);
@@ -434,7 +437,7 @@ main (int argc, char **argv)
       if (optc == -1
          || (posixly_correct && nfiles != 0)
          || ((optc = getopt_long (argc, argv,
-                                  "-0123456789Dcdf:is:uw:", longopts, NULL))
+                                  "-0123456789Dcdf:is:uw:z", longopts, NULL))
              == -1))
        {
          if (argc <= optind)
@@ -530,6 +533,10 @@ main (int argc, char **argv)
                                  N_("invalid number of bytes to compare"));
          break;
 
+       case 'z':
+         delimiter = '\0';
+         break;
+
        case_GETOPT_HELP_CHAR;
 
        case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);
@@ -546,7 +553,7 @@ main (int argc, char **argv)
       usage (EXIT_FAILURE);
     }
 
-  check_file (file[0], file[1]);
+  check_file (file[0], file[1], delimiter);
 
   exit (EXIT_SUCCESS);
 }