Implement the encoding pragma for regex literals.

p4raw-id: //depot/perl@12864

2 files changed, 36 insertions, 3 deletions

diff --git a/lib/encoding.pm b/lib/encoding.pm
index 6f5970f2ca..94ee3231fb 100644
--- a/lib/encoding.pm
+++ b/lib/encoding.pm
@@ -57,14 +57,33 @@ encoding pragma you can change this default.
 The pragma is a per script, not a per block lexical.  Only the last
 C<use encoding> matters, and it affects B<the whole script>.
 
+Notice that only literals (string or regular expression) having only
+legacy code points are affected: if you mix data like this
+
+	\xDF\x{100}
+
+the data is assumed to be in (Latin 1 and) Unicode, not in your native
+encoding.  In other words, this will match in "greek":
+
+	"\xDF" =~ /\x{3af}/
+
+but this will not
+
+	"\xDF\x{100}" =~ /\x{3af}\x{100}/
+
+since the C<\xDF> on the left will B<not> be upgraded to C<\x{3af}>
+because of the C<\x{100}> on the left.  You should not be mixing your
+legacy data and Unicode in the same string.
+
 If no encoding is specified, the environment variable L<PERL_ENCODING>
 is consulted.  If that fails, "latin1" (ISO 8859-1) is assumed.  If no
 encoding can be found, C<Unknown encoding '...'> error will be thrown.
 
 =head1 KNOWN PROBLEMS
 
-Literals in regular expressions are not affected by this pragma.
-They very probably should.
+For native multibyte encodings (either fixed or variable length)
+the current implementation of the regular expressions may introduce
+recoding errors for longer regular expression literals than 127 bytes.
 
 =head1 SEE ALSO
 
diff --git a/lib/encoding.t b/lib/encoding.t
index 03634410f4..8b14c8881a 100644
--- a/lib/encoding.t
+++ b/lib/encoding.t
@@ -1,4 +1,4 @@
-print "1..15\n";
+print "1..19\n";
 
 use encoding "latin1"; # ignored (overwritten by the next line)
 use encoding "greek";  # iso 8859-7 (no "latin" alias, surprise...)
@@ -68,3 +68,17 @@ print "ok 14\n";
 print "not " unless ord(substr($c, 2, 1)) == 0x3af;
 print "ok 15\n";
 
+# regex literals
+
+print "not " unless "\xDF"    =~ /\x{3AF}/;
+print "ok 16\n";
+
+print "not " unless "\x{3AF}" =~ /\xDF/;
+print "ok 17\n";
+
+print "not " unless "\xDF"    =~ /\xDF/;
+print "ok 18\n";
+
+print "not " unless "\x{3AF}" =~ /\x{3AF}/;
+print "ok 19\n";
+