join: don't report disorder against an empty file

This allows one to use join as a field extractor like:
  join -a1 -o 1.3,1.1 - /dev/null

* src/join.c (join): Don't flag unpairable lines when
one of the files is empty.
* tests/misc/join: Add a new test for empty input, and adjust
a previous test that was only checking against empty input.
* doc/coreutils.texi (join invocation): Document the change.
* NEWS: Likewise.

diff --git a/NEWS b/NEWS
index a042ee0..6e7efe1 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -25,6 +25,12 @@ GNU coreutils NEWS                                    -*- outline -*-
   output format from the first line in each file, to ensure
   the same number of fields are output for each line.
 
+** Changes in behavior
+
+  join no longer reports disorder when one of the files is empty.
+  This allows one to use join as a field extractor like:
+  join -a1 -o 1.3,1.1 - /dev/null
+
 
 * Noteworthy changes in release 8.9 (2011-01-04) [stable]
 

diff --git a/doc/coreutils.texi b/doc/coreutils.texi
index d6e98c6..b89147e 100644 (file)
--- a/doc/coreutils.texi
+++ b/doc/coreutils.texi
@@ -4787,11 +4787,17 @@ If there is an error it exits with nonzero status.
 @macro checkOrderOption{cmd}
 If the @option{--check-order} option is given, unsorted inputs will
 cause a fatal error message.  If the option @option{--nocheck-order}
-is given, unsorted inputs will never cause an error message.  If
-neither of these options is given, wrongly sorted inputs are diagnosed
-only if an input file is found to contain unpairable lines.  If an
-input file is diagnosed as being unsorted, the @command{\cmd\} command
-will exit with a nonzero status (and the output should not be used).
+is given, unsorted inputs will never cause an error message.  If neither
+of these options is given, wrongly sorted inputs are diagnosed
+only if an input file is found to contain unpairable
+@ifset JOIN_COMMAND
+lines, and when both input files are non empty.
+@end ifset
+@ifclear JOIN_COMMAND
+lines.
+@end ifclear
+If an input file is diagnosed as being unsorted, the @command{\cmd\}
+command will exit with a nonzero status (and the output should not be used).
 
 Forcing @command{\cmd\} to process wrongly sorted input files
 containing unpairable lines by specifying @option{--nocheck-order} is
@@ -5672,7 +5678,9 @@ c c1 c2
 b b1 b2
 @end example
 
+@set JOIN_COMMAND
 @checkOrderOption{join}
+@clear JOIN_COMMAND
 
 The defaults are:
 @itemize

diff --git a/src/join.c b/src/join.c
index ab76251..941185c 100644 (file)
--- a/src/join.c
+++ b/src/join.c
@@ -736,7 +736,7 @@ join (FILE *fp1, FILE *fp2)
         seq2.count = 0;
     }
 
-  /* If the user did not specify --check-order, then we read the
+  /* If the user did not specify --nocheck-order, then we read the
      tail ends of both inputs to verify that they are in order.  We
      skip the rest of the tail once we have issued a warning for that
      file, unless we actually need to print the unpairable lines.  */
@@ -751,7 +751,8 @@ join (FILE *fp1, FILE *fp2)
     {
       if (print_unpairables_1)
         prjoin (seq1.lines[0], &uni_blank);
-      seen_unpairable = true;
+      if (seq2.count)
+        seen_unpairable = true;
       while (get_line (fp1, &line, 1))
         {
           if (print_unpairables_1)
@@ -765,7 +766,8 @@ join (FILE *fp1, FILE *fp2)
     {
       if (print_unpairables_2)
         prjoin (&uni_blank, seq2.lines[0]);
-      seen_unpairable = true;
+      if (seq1.count)
+        seen_unpairable = true;
       while (get_line (fp2, &line, 2))
         {
           if (print_unpairables_2)

diff --git a/tests/misc/join b/tests/misc/join
index 5086ee7..eae3f18 100755 (executable)
--- a/tests/misc/join
+++ b/tests/misc/join
@@ -209,7 +209,11 @@ 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],
+['chkodr-7', '-12', ["2 a\n1 b\n", "2 c\n1 d"], "", 0],
+
+# After 8.9, join doesn't report disorder by default
+# when comparing against an empty input file.
+['chkodr-8', '', ["2 a\n1 b\n", ""], "", 0],
 
 # Test '--header' feature
 ['header-1', '--header',