md5sum,b2sum,sha*sum: support -z,--zero option

* doc/coreutils.texi (md5sum invocation): Describe the new option,
and how it's not supported by --check, and how it disables escaping.
* src/md5sum.c (delim): A new global to parmeterize the out delimiter.
(main): Don't enable file name escaping with -z, and output '\0'.
* tests/misc/md5sum-newline.pl: Add a test case.
* NEWS: Mention the new feature.

diff --git a/NEWS b/NEWS
index 2020ab6e3708a26ac72dd55c32f4e690a7d5f333..8f4aefa9c9e91490eabff7b72fa951833aaf35b4 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -46,6 +46,12 @@ GNU coreutils NEWS                                    -*- outline -*-
   'cp --force file symlink' now removes the symlink even if
   it is self referential.
 
+** New features
+
+  md5sum accepts a new option: --zero (-z) to delimit the output lines with a
+  NUL instead of a newline character.  This also disables file name escaping.
+  This also applies to sha*sum and b2sum.
+
 ** Improvements
 
   cut supports line lengths up to the max file size on 32 bit systems.

diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index c28b8d0435f8056a73de0cc15b2f5d8af3e94c47..b18c6a5178d4f76324cd785722fd6c55ada9f7a7 100644 (file)
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -3865,8 +3865,8 @@ a space, a flag indicating binary or text input mode, and the file name.
 Binary mode is indicated with @samp{*}, text mode with @samp{ } (space).
 Binary mode is the default on systems where it's significant,
 otherwise text mode is the default.
-If @var{file} contains a backslash or newline, the
-line is started with a backslash, and each problematic character in
+Without @option{--zero}, if @var{file} contains a backslash or newline,
+the line is started with a backslash, and each problematic character in
 the file name is escaped with a backslash, making the output
 unambiguous even in the presence of arbitrary file names.
 If @var{file} is omitted or specified as @samp{-}, standard input is read.
@@ -3899,6 +3899,7 @@ Three input formats are supported.  Either the default output
 format described above, the @option{--tag} output format,
 or the BSD reversed mode format which is similar to the default mode,
 but doesn't use a character to distinguish binary and text modes.
+Output with @option{--zero} enabled is not supported by @option{--check}.
 @sp 1
 For each such line, @command{md5sum} reads the named file and computes its
 MD5 checksum.  Then, if the computed message digest does not match the
@@ -3947,9 +3948,9 @@ indicating there was a failure.
 @opindex --tag
 @cindex BSD output
 Output BSD style checksums, which indicate the checksum algorithm used.
-As a GNU extension, file names with problematic characters
-are escaped as described above, with the same escaping indicator of @samp{\}
-at the start of the line, being used.
+As a GNU extension, if @option{--zero} is not used, file names with problematic
+characters are escaped as described above, with the same escaping indicator of
+@samp{\} at the start of the line, being used.
 The @option{--tag} option implies binary mode, and is disallowed with
 @option{--text} mode as supporting that would unnecessarily complicate
 the output format, while providing little benefit.
@@ -3982,6 +3983,8 @@ When verifying checksums,
 if one or more input line is invalid,
 exit nonzero after all warnings have been issued.
 
+@optZero
+Also file name escaping is not used.
 @end table
 
 @exitstatus

diff --git a/src/md5sum.c b/src/md5sum.c
index a5c30d9c45f30866230ae4afd527f271dcfdd82f..e41fb24bef06e6d1fcec0ba328e3c2cc0dfce2b5 100644 (file)
--- a/src/md5sum.c
+++ b/src/md5sum.c
@@ -157,6 +157,9 @@ static bool strict = false;
 /* Whether a BSD reversed format checksum is detected.  */
 static int bsd_reversed = -1;
 
+/* line delimiter.  */
+static unsigned char delim = '\n';
+
 #if HASH_ALGO_BLAKE2
 static char const *const algorithm_in_string[] =
 {
@@ -210,6 +213,7 @@ static struct option const long_options[] =
   { "warn", no_argument, NULL, 'w' },
   { "strict", no_argument, NULL, STRICT_OPTION },
   { "tag", no_argument, NULL, TAG_OPTION },
+  { "zero", no_argument, NULL, 'z' },
   { GETOPT_HELP_OPTION_DECL },
   { GETOPT_VERSION_OPTION_DECL },
   { NULL, 0, NULL, 0 }
@@ -261,6 +265,10 @@ Print or check %s (%d-bit) checksums.\n\
       else
         fputs (_("\
   -t, --text           read in text mode (default)\n\
+"), stdout);
+      fputs (_("\
+  -z, --zero           end each output line with NUL, not newline,\n\
+                       and disable file name escaping\n\
 "), stdout);
       fputs (_("\
 \n\
@@ -875,10 +883,10 @@ main (int argc, char **argv)
   setvbuf (stdout, NULL, _IOLBF, 0);
 
 #if HASH_ALGO_BLAKE2
-  const char* short_opts = "l:bctw";
+  const char* short_opts = "l:bctwz";
   const char* b2_length_str = "";
 #else
-  const char* short_opts = "bctw";
+  const char* short_opts = "bctwz";
 #endif
 
   while ((opt = getopt_long (argc, argv, short_opts, long_options, NULL)) != -1)
@@ -930,6 +938,9 @@ main (int argc, char **argv)
         prefix_tag = true;
         binary = 1;
         break;
+      case 'z':
+        delim = '\0';
+        break;
       case_GETOPT_HELP_CHAR;
       case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);
       default:
@@ -964,6 +975,13 @@ main (int argc, char **argv)
      usage (EXIT_FAILURE);
    }
 
+  if (delim != '\n' && do_check)
+    {
+      error (0, 0, _("the --zero option is not supported when "
+                     "verifying checksums"));
+      usage (EXIT_FAILURE);
+    }
+
   if (prefix_tag && do_check)
     {
       error (0, 0, _("the --tag option is meaningless when "
@@ -1043,7 +1061,8 @@ main (int argc, char **argv)
                  against old (hashed) outputs, in the presence of files
                  containing '\\' characters, we decided to not simplify the
                  output in this case.  */
-              bool needs_escape = strchr (file, '\\') || strchr (file, '\n');
+              bool needs_escape = (strchr (file, '\\') || strchr (file, '\n'))
+                                  && delim == '\n';
 
               if (prefix_tag)
                 {
@@ -1079,7 +1098,7 @@ main (int argc, char **argv)
                   print_filename (file, needs_escape);
                 }
 
-              putchar ('\n');
+              putchar (delim);
             }
         }
     }

diff --git a/tests/misc/md5sum-newline.pl b/tests/misc/md5sum-newline.pl
index b76e2b867cfdd79cadc26ad009abbf53fba68248..a7ab2bd91ababccb15971cc3e3a233f5ab849b4b 100755 (executable)
--- a/tests/misc/md5sum-newline.pl
+++ b/tests/misc/md5sum-newline.pl
@@ -30,10 +30,12 @@ system ('touch', "a\nb") == 0
 
 my $degenerate = "d41d8cd98f00b204e9800998ecf8427e";
 my $t = '--text';
+my $z = '--zero';
 
 my @Tests =
     (
      ['newline', $t, {IN=> {"a\nb"=> ''}}, {OUT=>"\\$degenerate  a\\nb\n"}],
+     ['zero', $z, {IN=> {"a\nb"=> ''}}, {OUT=>"$degenerate  a\nb\0"}],
     );
 
 my $save_temps = $ENV{DEBUG};