tests: cut: exercise distro-added multibyte code paths

* tests/misc/cut: Repeat each test using a multibyte locale,
if the configure-time test found such a locale.
Adjust the tests so that they also accept a slightly
different diagnostic that is specific to the MB-patched cut.

diff --git a/tests/misc/cut b/tests/misc/cut
index c905ba9a3162391fcdb7c34409da1dc3f164a8bb..7ed41344875fa343a6f6c795e37e305456175ac1 100755 (executable)
--- a/tests/misc/cut
+++ b/tests/misc/cut
@@ -23,6 +23,10 @@ use strict;
 # Turn off localization of executable's output.
 @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
 
+my $mb_locale = $ENV{LOCALE_FR_UTF8};
+! defined $mb_locale || $mb_locale eq 'none'
+  and $mb_locale = 'C';
+
 my $prog = 'cut';
 my $try = "Try \`$prog --help' for more information.\n";
 my $from_1 = "$prog: fields and positions are numbered from 1\n$try";
@@ -156,6 +160,35 @@ my @Tests =
   ['big-unbounded-f', '--output-d=:', '-f1234567890-', {IN=>''}, {OUT=>''}],
  );
 
+if ($mb_locale ne 'C')
+  {
+    # Duplicate each test vector, appending "-mb" to the test name and
+    # inserting {ENV => "LC_ALL=$mb_locale"} in the copy, so that we
+    # provide coverage for the distro-added multi-byte code paths.
+    my @new;
+    foreach my $t (@Tests)
+      {
+        my @new_t = @$t;
+        my $test_name = shift @new_t;
+
+        # Depending on whether cut is multi-byte-patched,
+        # it emits different diagnostics:
+        #   non-MB: invalid byte or field list
+        #   MB:     invalid byte, character or field list
+        # Adjust the expected error output accordingly.
+        if (grep {ref $_ eq 'HASH' && exists $_->{ERR} && $_->{ERR} eq $inval}
+            (@new_t))
+          {
+            my $sub = {ERR_SUBST => 's/, character//'};
+            push @new_t, $sub;
+            push @$t, $sub;
+          }
+        push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}];
+      }
+    push @Tests, @new;
+  }
+
+
 @Tests = triple_test \@Tests;
 
 my $save_temps = $ENV{DEBUG};