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.

diff --git a/NEWS b/NEWS
index aa37d69e02d48cbf834ea635c4dd7b1317453a5d..3fe52e7b36b2f74473347b134b3c058ce9aa295e 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -4,6 +4,9 @@ GNU coreutils NEWS                                    -*- outline -*-
 
 ** New features
 
+  join now accepts the --header option, to treat the first line of each
+  file as a header line to be joined and printed unconditionally.
+
   who: the "+/-" --mesg (-T) indicator of whether a user/tty is accepting
   messages could be incorrectly listed as "+", when in fact, the user was
   not accepting messages (mesg no).  Before, who would examine only the

diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index 184b55a8ce49de3a95addb718d9638f4669821fe..2b3d32b940303d12b7e78d1342134ecedc70a419 100644 (file)
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -5515,6 +5515,15 @@ Do not check that both input files are in sorted order.  This is the default.
 Replace those output fields that are missing in the input with
 @var{string}.
 
+@item --header
+@opindex --header
+Treat the first line of each input file as a header line. The header lines will
+be joined and printed as the first output line.  If @option{-o} is used to
+specify output format, the header line will be printed according to the
+specified format.  The header lines will not be checked for ordering even if
+@option{--check-order} is specified.  Also if the header lines from each file
+do not match, the heading fields from the first file will be used.
+
 @item -i
 @itemx --ignore-case
 @opindex -i

diff --git a/src/join.c b/src/join.c
index d86e62c03e57f75a7ef81571ca706677e0edfc5f..6030a01b37d033734d8926f6f0212aede0db4931 100644 (file)
--- 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);

diff --git a/tests/misc/join b/tests/misc/join
index 49194e046dccacbb9e92957f3ea52a8d88ac718f..4e7798fd9d12ca21946910b46e28f6886558506f 100755 (executable)
--- a/tests/misc/join
+++ b/tests/misc/join
@@ -185,6 +185,34 @@ my @tv = (
 # Before 6.10.143, this would mistakenly fail with the diagnostic:
 # join: File 1 is not in sorted order
 ['chkodr-7', '-12', ["2 a\n1 b\n", ""], "", 0],
+
+# Test '--header' feature
+['header-1', '--header',
+ [ "ID Name\n1 A\n2 B\n", "ID Color\n1 red\n"], "ID Name Color\n1 A red\n", 0],
+
+# '--header' with '--check-order' : The header line is out-of-order but the
+# actual data is in order. This join should succeed.
+['header-2', '--header --check-order',
+ ["ID Name\n1 A\n2 B\n", "ID Color\n2 green\n"],
+ "ID Name Color\n2 B green\n", 0],
+
+# '--header' with '--check-order' : The header line is out-of-order AND the
+# actual data out-of-order. This join should fail.
+['header-3', '--header --check-order',
+ ["ID Name\n2 B\n1 A\n", "ID Color\n2 blue\n"], "ID Name Color\n", 1,
+ "$prog: file 1 is not in sorted order\n"],
+
+# '--header' with specific output format '-o'.
+# output header line should respect the requested format
+['header-4', '--header -o "0,1.3,2.2"',
+ ["ID Group Name\n1 Foo A\n2 Bar B\n", "ID Color\n2 blue\n"],
+ "ID Name Color\n2 B blue\n", 0],
+
+# '--header' always outputs headers from the first file
+# even if the headers from the second file don't match
+['header-5', '--header',
+ [ "ID1 Name\n1 A\n2 B\n", "ID2 Color\n1 red\n"], "ID1 Name Color\n1 A red\n", 0],
+
 );
 
 # Convert the above old-style test vectors to the newer