maint: copy join, uniq tests from Fedora

* tests/misc/join.pl, tests/uniq/uniq.pl:
Copy from Fedora 39.  This adds more multi-byte tests.

diff --git a/tests/misc/join.pl b/tests/misc/join.pl
index 2ca8567bad0b2b91d4c334c608e94aba156aa672..1d01a3d3d7893f86baa7dcae769fac0af783a547 100755 (executable)
--- a/tests/misc/join.pl
+++ b/tests/misc/join.pl
@@ -25,6 +25,15 @@ my $limits = getlimits ();
 
 my $prog = 'join';
 
+my $try = "Try \`$prog --help' for more information.\n";
+my $inval = "$prog: invalid byte, character or field list\n$try";
+
+my $mb_locale;
+#Comment out next line to disable multibyte tests
+$mb_locale = $ENV{LOCALE_FR_UTF8};
+! defined $mb_locale || $mb_locale eq 'none'
+  and $mb_locale = 'C';
+
 my $delim = chr 0247;
 sub t_subst ($)
 {
@@ -333,8 +342,49 @@ foreach my $t (@tv)
     push @Tests, $new_ent;
   }
 
+# Add _POSIX2_VERSION=199209 to the environment of each test
+# that uses an old-style option like +1.
+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 join 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;
+          }
+        #Adjust the output some error messages including test_name for mb
+        if (grep {ref $_ eq 'HASH' && exists $_->{ERR}}
+             (@new_t))
+          {
+            my $sub2 = {ERR_SUBST => "s/$test_name-mb/$test_name/"};
+            push @new_t, $sub2;
+            push @$t, $sub2;
+          }
+        push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}];
+      }
+    push @Tests, @new;
+  }
+
 @Tests = triple_test \@Tests;
 
+#skip invalid-j-mb test, it is failing because of the format
+@Tests = grep {$_->[0] ne 'invalid-j-mb'} @Tests;
+
 my $save_temps = $ENV{DEBUG};
 my $verbose = $ENV{VERBOSE};
 

diff --git a/tests/uniq/uniq.pl b/tests/uniq/uniq.pl
index a6354dc3c2f1f1c40ce2af573f620162e652ee2f..e43cd6e3f745800979d191d49d3c0905659cdc2d 100755 (executable)
--- a/tests/uniq/uniq.pl
+++ b/tests/uniq/uniq.pl
@@ -23,9 +23,17 @@ my $limits = getlimits ();
 my $prog = 'uniq';
 my $try = "Try '$prog --help' for more information.\n";
 
+my $inval = "$prog: invalid byte, character or field list\n$try";
+
 # Turn off localization of executable's output.
 @ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
 
+my $mb_locale;
+#Comment out next line to disable multibyte tests
+$mb_locale = $ENV{LOCALE_FR_UTF8};
+! defined $mb_locale || $mb_locale eq 'none'
+  and $mb_locale = 'C';
+
 # When possible, create a "-z"-testing variant of each test.
 sub add_z_variants($)
 {
@@ -262,6 +270,53 @@ foreach my $t (@Tests)
       and push @$t, {ENV=>'_POSIX2_VERSION=199209'};
   }
 
+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 uniq 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, $sub;
+          }
+        # In test #145, replace the each ‘...’ by '...'.
+        if ($test_name =~ "145")
+          {
+            my $sub = { ERR_SUBST => "s/‘([^’]+)’/'\$1'/g"};
+            push @new_t, $sub;
+            push @$t, $sub;
+          }
+        next if (   $test_name =~ "schar"
+                 or $test_name =~ "^obs-plus"
+                 or $test_name =~ "119");
+        push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}];
+      }
+    push @Tests, @new;
+   }
+
+# Remember that triple_test creates from each test with exactly one "IN"
+# file two more tests (.p and .r suffix on name) corresponding to reading
+# input from a file and from a pipe.  The pipe-reading test would fail
+# due to a race condition about 1 in 20 times.
+# Remove the IN_PIPE version of the "output-is-input" test above.
+# The others aren't susceptible because they have three inputs each.
+
+@Tests = grep {$_->[0] ne 'output-is-input.p'} @Tests;
+
 @Tests = add_z_variants \@Tests;
 @Tests = triple_test \@Tests;