From: Karl Williamson <khw@cpan.org>
Date: Sat, 21 May 2016 17:35:10 +0000 (-0600)
Subject: perllocale: Document NUL collation handling
X-Git-Tag: v5.25.2~147
X-Git-Url: https://perl5.git.perl.org/perl5.git/commitdiff_plain/4e615abd31bcd0bb8f321ae4687e5aef1a8aa391

perllocale: Document NUL collation handling

And add a TODO test, because this shortly will be improved upon
---

diff --git a/lib/locale.t b/lib/locale.t
index 1e99b6e..ddb5d79 100644
--- a/lib/locale.t
+++ b/lib/locale.t
@@ -1735,6 +1735,20 @@ foreach my $Locale (@Locale) {
                 last;
             }
         }
+
+        use locale;
+
+        ++$locales_test_number;
+        $test_names{$locales_test_number}
+            = 'TODO Skip in locales where \001 has primary sorting weight; '
+            . 'otherwise verify that \0 doesn\'t have primary sorting weight';
+        if ("a\001c" lt "ab") {
+            report_result($Locale, $locales_test_number, 1);
+        }
+        else {
+            my $ok = "ab" lt "a\0c";
+            report_result($Locale, $locales_test_number, $ok);
+        }
     }
 
     my $ok1;
diff --git a/pod/perllocale.pod b/pod/perllocale.pod
index 018f916..0c7e769 100644
--- a/pod/perllocale.pod
+++ b/pod/perllocale.pod
@@ -1565,6 +1565,16 @@ called, and whatever it does is what you get.
 
 =head1 BUGS
 
+=head2 Collation of strings containing embedded C<NUL> characters
+
+Perl handles C<NUL> characters in the middle of strings.  In many
+locales, control characters are ignored unless the strings otherwise
+compare equal.  Unlike other control characters, C<NUL> characters are
+never ignored.   For example, if given that C<"b"> sorts after
+C<"\001">, and C<"c"> sorts after C<"b">, C<"a\0c"> always sorts before
+C<"ab">.  This is true even in locales in which C<"ab"> sorts before
+C<"a\001c">.
+
 =head2 Broken systems
 
 In certain systems, the operating system's locale support