From f86bb6967dba1e2b6026997963a90e00cd641490 Mon Sep 17 00:00:00 2001
From: =?utf8?q?P=C3=A1draig=20Brady?= <P@draigBrady.com>
Date: Mon, 1 Feb 2010 15:19:08 +0000
Subject: [PATCH] join: make -t '' operate on the whole line

Previously passing an empty parameter to -t would
raise an error, but now it means to treat each line
as a single field for matching.  This matches the
default operation of `sort` which is usually used
in conjunction with join.

* src/join.c (main): Set the field delimiter to '\n' if
an empty parameter is passed to -t.
(usage): Mention the operation of -t ''.
* tests/misc/join: Add 2 new tests, for the existing -t '\0'
and the new -t '' functionality.
* doc/coreutils.texi (join invocation): Mention that
join -t '' always operates on the whole line, while
join -t '\0' usually does.
* NEWS: Mention the change in behavior.
---
 NEWS               | 3 +++
 doc/coreutils.texi | 7 ++++++-
 src/join.c         | 7 ++++---
 tests/misc/join    | 5 +++++
 4 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/NEWS b/NEWS
index 3fe52e7..a96e594 100644
--- a/NEWS
+++ b/NEWS
@@ -22,6 +22,9 @@ GNU coreutils NEWS                                    -*- outline -*-
   ls --color no longer emits the final 3-byte color-resetting escape
   sequence when it would be a no-op.
 
+  join -t '' no longer emits an error and instead operates on
+  each line as a whole (even if they contains NUL characters).
+
 
 * Noteworthy changes in release 8.4 (2010-01-13) [stable]
 
diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index 2b3d32b..e3e95f5 100644
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -5462,6 +5462,8 @@ locales and options if the output of @command{sort} is fed to
 sort a file on its default join field, but if you select a non-default
 locale, join field, separator, or comparison options, then you should
 do so consistently between @command{join} and @command{sort}.
+If @samp{join -t ''} is specified then the whole line is considered which
+matches the default operation of sort.
 
 If the input has no unpairable lines, a @acronym{GNU} extension is
 available; the sort order can be any order that considers two fields
@@ -5572,7 +5574,10 @@ option---are subject to the specified @var{field-list}.
 Use character @var{char} as the input and output field separator.
 Treat as significant each occurrence of @var{char} in the input file.
 Use @samp{sort -t @var{char}}, without the @option{-b} option of
-@samp{sort}, to produce this ordering.
+@samp{sort}, to produce this ordering.  If @samp{join -t ''} is specified,
+the whole line is considered, matching the default operation of sort.
+If @samp{-t '\0'} is specified then the @acronym{ASCII} @sc{nul}
+character is used to delimit the fields.
 
 @item -v @var{file-number}
 Print a line for each unpairable line in file @var{file-number}
diff --git a/src/join.c b/src/join.c
index 6030a01..b1f3310 100644
--- a/src/join.c
+++ b/src/join.c
@@ -212,7 +212,8 @@ the remaining fields from FILE1, the remaining fields from FILE2, all\n\
 separated by CHAR.\n\
 \n\
 Important: FILE1 and FILE2 must be sorted on the join fields.\n\
-E.g., use `sort -k 1b,1' if `join' has no options.\n\
+E.g., use ` sort -k 1b,1 ' if `join' has no options,\n\
+or use ` join -t '' ' if `sort' has no options.\n\
 Note, comparisons honor the rules specified by `LC_COLLATE'.\n\
 If the input is not sorted and some lines cannot be joined, a\n\
 warning message will be given.\n\
@@ -1040,8 +1041,8 @@ main (int argc, char **argv)
           {
             unsigned char newtab = optarg[0];
             if (! newtab)
-              error (EXIT_FAILURE, 0, _("empty tab"));
-            if (optarg[1])
+              newtab = '\n'; /* '' => process the whole line.  */
+            else if (optarg[1])
               {
                 if (STREQ (optarg, "\\0"))
                   newtab = '\0';
diff --git a/tests/misc/join b/tests/misc/join
index 4e7798f..cef8137 100755
--- a/tests/misc/join
+++ b/tests/misc/join
@@ -51,6 +51,11 @@ my @tv = (
 
 ['3a', '-t:', ["a:1\nb:1\n", "a:2:\nb:2:\n"], "a:1:2:\nb:1:2:\n", 0],
 
+# operate on whole line (as sort does by default)
+['3b', '-t ""', ["a 1\nb 1\n", "a 1\nb 2\n"], "a 1\n", 0],
+# use NUL as the field delimiter
+['3c', '-t "\\0"', ["a\0a\n", "a\0b\n"], "a\0a\0b\n", 0],
+
 # Just like -a1 and -a2 when there are no pairable lines
 ['4a', '-v 1', ["a 1\n", "b\n"],   "a 1\n",          0],
 ['4b', '-v 2', ["a 1\n", "b\n"],   "b\n",            0],
-- 
2.7.4