comm: add --total option

* src/comm.c (total_option): Add bool variable for the new option.
(TOTAL_OPTION): Add enum value.
(long_options): Add array element for the new option.
(usage): Document the new option here.
(compare_files): Count the lines in total[3], and output the summary at
the end.
(main): Accept the new option.
* doc/coreutils.texi (comm invocation): Document it.
* tests/misc/comm.pl: Test it.  While at it, improve the test data
to have 1 unique line in the first file, 2 unique lines in the second
file, and 3 common lines.
* NEWS (New Features): Mention the new option.

Fixes http://bugs.gnu.org/24929

diff --git a/NEWS b/NEWS
index 41c1e3c8c38613598cd172105c1c708e4c626a2c..edfbdfa1d1f240a9a6c244a79637645d1a1943c0 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -114,6 +114,8 @@ GNU coreutils NEWS                                    -*- outline -*-
 
 ** New Features
 
+  comm now accepts the --total option to output a summary at the end.
+
   date now accepts the --debug option, to annotate the parsed date string,
   display timezone information, and warn about potential misuse.
 

diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index d0694fdd0b8e874b3f0ad248b50042dfcadfb5ff..521ac3923b89759a54dace65972cd617a5d16678 100644 (file)
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -5174,6 +5174,37 @@ rather than the default of a single TAB character.
 
 The delimiter @var{str} may not be empty.
 
+@item --total
+Output a summary at the end.
+
+Similar to the regular output,
+column one contains the total number of lines unique to @var{file1},
+column two contains the total number of lines unique to @var{file2}, and
+column three contains the total number of lines common to both files,
+followed by the word @samp{total} in the additional column four.
+
+In the following example, @command{comm} omits the regular output
+(@option{-123}), thus just printing the summary:
+
+@example
+$ printf '%s\n' a b c d e     > file1
+$ printf '%s\n'   b c d e f g > file2
+$ comm --total -123 file1 file2
+1       2       4       total
+@end example
+
+This option is a GNU extension.  Portable scripts should use @command{wc} to
+get the totals, e.g. for the above example files:
+
+@example
+$ comm -23 file1 file2 | wc -l    # number of lines only in file1
+1
+$ comm -13 file1 file2 | wc -l    # number of lines only in file2
+2
+$ comm -12 file1 file2 | wc -l    # number of lines common to both files
+4
+@end example
+
 @optZeroTerminated
 
 @end table

diff --git a/src/comm.c b/src/comm.c
index eab81328b6ff25dd469d0db1b8121e2e03dfd990..095ee1d2db2bbdc3222ee9f9a7c34b2658e006a9 100644 (file)
--- a/src/comm.c
+++ b/src/comm.c
@@ -63,6 +63,9 @@ static bool issued_disorder_warning[2];
 /* line delimiter.  */
 static unsigned char delim = '\n';
 
+/* If true, print a summary.  */
+static bool total_option;
+
 /* If nonzero, check that the input is correctly ordered. */
 static enum
   {
@@ -82,7 +85,8 @@ enum
 {
   CHECK_ORDER_OPTION = CHAR_MAX + 1,
   NOCHECK_ORDER_OPTION,
-  OUTPUT_DELIMITER_OPTION
+  OUTPUT_DELIMITER_OPTION,
+  TOTAL_OPTION
 };
 
 static struct option const long_options[] =
@@ -90,6 +94,7 @@ static struct option const long_options[] =
   {"check-order", no_argument, NULL, CHECK_ORDER_OPTION},
   {"nocheck-order", no_argument, NULL, NOCHECK_ORDER_OPTION},
   {"output-delimiter", required_argument, NULL, OUTPUT_DELIMITER_OPTION},
+  {"total", no_argument, NULL, TOTAL_OPTION},
   {"zero-terminated", no_argument, NULL, 'z'},
   {GETOPT_HELP_OPTION_DECL},
   {GETOPT_VERSION_OPTION_DECL},
@@ -135,6 +140,9 @@ and column three contains lines common to both files.\n\
 "), stdout);
       fputs (_("\
   --output-delimiter=STR  separate columns with STR\n\
+"), stdout);
+      fputs (_("\
+  --total           output a summary\n\
 "), stdout);
       fputs (_("\
   -z, --zero-terminated    line delimiter is NUL, not newline\n\
@@ -263,6 +271,9 @@ compare_files (char **infiles)
   /* streams[i] holds the input stream for file i.  */
   FILE *streams[2];
 
+  /* Counters for the summary.  */
+  uintmax_t total[] = {0, 0, 0};
+
   int i, j;
 
   /* Initialize the storage. */
@@ -317,14 +328,26 @@ compare_files (char **infiles)
 
       /* Output the line that is lesser. */
       if (order == 0)
-        writeline (thisline[1], stdout, 3);
+        {
+          /* Line is seen in both files.  */
+          total[2]++;
+          writeline (thisline[1], stdout, 3);
+        }
       else
         {
           seen_unpairable = true;
           if (order <= 0)
-            writeline (thisline[0], stdout, 1);
+            {
+              /* Line is seen in file 1 only.  */
+              total[0]++;
+              writeline (thisline[0], stdout, 1);
+            }
           else
-            writeline (thisline[1], stdout, 2);
+            {
+              /* Line is seen in file 2 only.  */
+              total[1]++;
+              writeline (thisline[1], stdout, 2);
+            }
         }
 
       /* Step the file the line came from.
@@ -365,6 +388,19 @@ compare_files (char **infiles)
   for (i = 0; i < 2; i++)
     if (fclose (streams[i]) != 0)
       die (EXIT_FAILURE, errno, "%s", quotef (infiles[i]));
+
+  if (total_option)
+    {
+      /* Print the summary, minding the column and line delimiters.  */
+      char buf1[INT_BUFSIZE_BOUND (uintmax_t)];
+      char buf2[INT_BUFSIZE_BOUND (uintmax_t)];
+      char buf3[INT_BUFSIZE_BOUND (uintmax_t)];
+      printf ("%s%s%s%s%s%s%s%c",
+              umaxtostr (total[0], buf1), col_sep,
+              umaxtostr (total[1], buf2), col_sep,
+              umaxtostr (total[2], buf3), col_sep,
+              _("total"), delim);
+    }
 }
 
 int
@@ -388,6 +424,7 @@ main (int argc, char **argv)
   seen_unpairable = false;
   issued_disorder_warning[0] = issued_disorder_warning[1] = false;
   check_input_order = CHECK_ORDER_DEFAULT;
+  total_option = false;
 
   while ((c = getopt_long (argc, argv, "123z", long_options, NULL)) != -1)
     switch (c)
@@ -423,6 +460,10 @@ main (int argc, char **argv)
         col_sep_len = *optarg ? strlen (optarg) : 1;
         break;
 
+      case TOTAL_OPTION:
+        total_option = true;
+        break;
+
       case_GETOPT_HELP_CHAR;
 
       case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);

diff --git a/tests/misc/comm.pl b/tests/misc/comm.pl
index c5cd27f39940a93675b6dc5f319877404f6cbae4..fdec3d62cf75205dec14ade458fd2d4f4922dbff 100755 (executable)
--- a/tests/misc/comm.pl
+++ b/tests/misc/comm.pl
@@ -27,37 +27,50 @@ my $prog = 'comm';
 # Turn off localization of executable's ouput.
 @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
 
-my @inputs = ({IN=>{a=>"1\n3"}}, {IN=>{b=>"2\n3"}});
-my @zinputs = ({IN=>{za=>"1\0003"}}, {IN=>{zb=>"2\0003"}});
+my @inputs = ({IN=>{a=>"1\n3\n3\n3"}}, {IN=>{b=>"2\n2\n3\n3\n3"}});
+my @zinputs = ({IN=>{za=>"1\0003\0003\0003"}},
+               {IN=>{zb=>"2\0002\0003\0003\0003"}});
 
 my @Tests =
   (
    # basic operation
-   ['basic', @inputs, {OUT=>"1\n\t2\n\t\t3\n"} ],
-   ['zbasic', '-z', @zinputs, {OUT=>"1\0\t2\0\t\t3\0"} ],
+   ['basic', @inputs, {OUT=>"1\n\t2\n\t2\n\t\t3\n\t\t3\n\t\t3\n"} ],
+   ['zbasic', '-z', @zinputs, {OUT=>"1\0\t2\0\t2\0\t\t3\0\t\t3\0\t\t3\0"} ],
 
    # suppress lines unique to file 1
-   ['opt-1', '-1', @inputs, {OUT=>"2\n\t3\n"} ],
-   ['zopt-1', '-z', '-1', @zinputs, {OUT=>"2\0\t3\0"} ],
+   ['opt-1', '-1', @inputs, {OUT=>"2\n2\n\t3\n\t3\n\t3\n"} ],
+   ['zopt-1', '-z', '-1', @zinputs, {OUT=>"2\0002\000\t3\000\t3\000\t3\000"} ],
 
    # suppress lines unique to file 2
-   ['opt-2', '-2', @inputs, {OUT=>"1\n\t3\n"} ],
+   ['opt-2', '-2', @inputs, {OUT=>"1\n\t3\n\t3\n\t3\n"} ],
+   ['zopt-2', '-z', '-2', @zinputs, {OUT=>"1\000\t3\000\t3\000\t3\000"} ],
 
    # suppress lines that appear in both files
-   ['opt-3', '-3', @inputs, {OUT=>"1\n\t2\n"} ],
+   ['opt-3', '-3', @inputs, {OUT=>"1\n\t2\n\t2\n"} ],
+   ['zopt-3', '-z', '-3', @zinputs, {OUT=>"1\000\t2\000\t2\000"} ],
 
    # suppress lines unique to file 1 and lines unique to file 2
-   ['opt-12', '-1', '-2', @inputs, {OUT=>"3\n"} ],
+   ['opt-12', '-1', '-2', @inputs, {OUT=>"3\n3\n3\n"} ],
+   ['zopt-12', '-12z', @zinputs, {OUT=>"3\0003\0003\000"} ],
 
    # suppress lines unique to file 1 and those that appear in both files
-   ['opt-13', '-1', '-3', @inputs, {OUT=>"2\n"} ],
+   ['opt-13', '-1', '-3', @inputs, {OUT=>"2\n2\n"} ],
+   ['zopt-13', '-13z', @zinputs, {OUT=>"2\0002\000"} ],
 
    # suppress lines unique to file 2 and those that appear in both files
    ['opt-23', '-2', '-3', @inputs, {OUT=>"1\n"} ],
+   ['zopt-23', '-23z', @zinputs, {OUT=>"1\000"} ],
 
-   # suppress all output (really?)
+   # suppress all output
    ['opt-123', '-1', '-2', '-3', @inputs, {OUT=>""} ],
 
+   # show summary: 1 only in file1, 2 only in file2, 3 in both files
+   ['total-all', '--total', @inputs, {OUT=>"1\n\t2\n\t2\n\t\t3\n\t\t3\n\t\t3\n"
+     . "1\t2\t3\ttotal\n"} ],
+
+   # show summary only, suppressing regular output
+   ['total-123', '--total', '-123', @inputs, {OUT=>"1\t2\t3\ttotal\n"} ],
+
    # invalid missing command line argument (1)
    ['missing-arg1', $inputs[0], {EXIT=>1},
     {ERR => "$prog: missing operand after 'a'\n"
@@ -128,17 +141,17 @@ my @Tests =
 
    # alternate delimiter: ','
    ['delim-comma', '--output-delimiter=,', @inputs,
-    {OUT=>"1\n,2\n,,3\n"} ],
+    {OUT=>"1\n,2\n,2\n,,3\n,,3\n,,3\n"} ],
 
    # two-character alternate delimiter: '++'
    ['delim-2char', '--output-delimiter=++', @inputs,
-    {OUT=>"1\n++2\n++++3\n"} ],
+    {OUT=>"1\n++2\n++2\n++++3\n++++3\n++++3\n"} ],
 
    # NUL delimiter
    ['delim-empty', '--output-delimiter=', @inputs,
-    {OUT=>"1\n\0002\n\000\0003\n"} ],
+    {OUT=>"1\n\0002\n\0002\n\000\0003\n\000\0003\n\000\0003\n"} ],
    ['zdelim-empty', '-z', '-z --output-delimiter=', @zinputs,
-    {OUT=>"1\000\0002\000\000\0003\000"} ],
+    {OUT=>"1\000\0002\000\0002\000\000\0003\000\000\0003\000\000\0003\000"} ],
 
    # invalid dual delimiter
    ['delim-dual', '--output-delimiter=,', '--output-delimiter=+', @inputs,
@@ -146,8 +159,16 @@ my @Tests =
 
    # valid dual delimiter specification
    ['delim-dual2', '--output-delimiter=,', '--output-delimiter=,', @inputs,
-    {OUT=>"1\n,2\n,,3\n"} ],
+    {OUT=>"1\n,2\n,2\n,,3\n,,3\n,,3\n"} ],
+
+   # show summary, zero-terminated
+   ['totalz-all', '--total', '-z', @zinputs,
+    {OUT=>"1\000\t2\000\t2\000\t\t3\000\t\t3\000\t\t3\000"
+        . "1\t2\t3\ttotal\000"} ],
 
+   # show summary only (-123), zero-terminated and with ',' as delimiter
+   ['totalz-123', '--total', '-z123', '--output-delimiter=,', @zinputs,
+    {OUT=>"1,2,3,total\000"} ],
  );
 
 my $save_temps = $ENV{DEBUG};