join: add --header option to always output the first line

This essentially allows one to use --check-order with headings.
Note join without --check-order will already handle the common case
where headings do match in each file, however using --check-order will fail
often when the header sorts after the first line of data.

Note also that this will join header lines from each file even if
they don't match, with headings from the first file being used.

* NEWS: Mention the new option.
* doc/coreutils.texi (join invocation): Describe the new option.
* src/join.c (usage): Likewise.
(join): Join the header lines unconditionally.
* tests/misc/join: Add 5 new tests.

1 files changed, 22 insertions, 1 deletions

diff --git a/src/join.c b/src/join.c
index d86e62c03..6030a01b3 100644
--- a/src/join.c
+++ b/src/join.c
@@ -137,7 +137,8 @@ static enum
 enum
 {
   CHECK_ORDER_OPTION = CHAR_MAX + 1,
-  NOCHECK_ORDER_OPTION
+  NOCHECK_ORDER_OPTION,
+  HEADER_LINE_OPTION
 };
 
 
@@ -146,6 +147,7 @@ static struct option const longopts[] =
   {"ignore-case", no_argument, NULL, 'i'},
   {"check-order", no_argument, NULL, CHECK_ORDER_OPTION},
   {"nocheck-order", no_argument, NULL, NOCHECK_ORDER_OPTION},
+  {"header", no_argument, NULL, HEADER_LINE_OPTION},
   {GETOPT_HELP_OPTION_DECL},
   {GETOPT_VERSION_OPTION_DECL},
   {NULL, 0, NULL, 0}
@@ -157,6 +159,10 @@ static struct line uni_blank;
 /* If nonzero, ignore case when comparing join fields.  */
 static bool ignore_case;
 
+/* If nonzero, treat the first line of each file as column headers -
+   join them without checking for ordering */
+static bool join_header_lines;
+
 void
 usage (int status)
 {
@@ -191,6 +197,8 @@ by whitespace.  When FILE1 or FILE2 (not both) is -, read standard input.\n\
   --check-order     check that the input is correctly sorted, even\n\
                       if all input lines are pairable\n\
   --nocheck-order   do not check that the input is correctly sorted\n\
+  --header          treat first line in each file as field header line,\n\
+                      print them without trying to pair them.\n\
 "), stdout);
       fputs (HELP_OPTION_DESCRIPTION, stdout);
       fputs (VERSION_OPTION_DESCRIPTION, stdout);
@@ -614,6 +622,15 @@ join (FILE *fp1, FILE *fp2)
   initseq (&seq2);
   getseq (fp2, &seq2, 2);
 
+  if (join_header_lines && seq1.count && seq2.count)
+    {
+      prjoin(seq1.lines[0], seq2.lines[0]);
+      prevline[0] = NULL;
+      prevline[1] = NULL;
+      advance_seq (fp1, &seq1, true, 1);
+      advance_seq (fp2, &seq2, true, 2);
+    }
+
   while (seq1.count && seq2.count)
     {
       size_t i;
@@ -1051,6 +1068,10 @@ main (int argc, char **argv)
                          &nfiles, &prev_optc_status, &optc_status);
           break;
 
+        case HEADER_LINE_OPTION:
+          join_header_lines = true;
+          break;
+
         case_GETOPT_HELP_CHAR;
 
         case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);