VMS fix-ups and status

[p5sagit/p5-mst-13.2.git] / lib / utf8.pm

diff --git a/lib/utf8.pm b/lib/utf8.pm
index f9055b5..f32c0bc 100644 (file)
--- a/lib/utf8.pm
+++ b/lib/utf8.pm
@@ -1,6 +1,5 @@
 package utf8;
 
-if (ord('A') != 193) { # make things more pragmatic for EBCDIC folk
 
 $utf8::hint_bits = 0x00800000;
 
@@ -21,8 +20,6 @@ sub AUTOLOAD {
     Carp::croak("Undefined subroutine $AUTOLOAD called");
 }
 
-}
-
 1;
 __END__
 
@@ -52,7 +49,7 @@ source text.  Until UTF-8 becomes the default format for source
 text, this pragma should be used to recognize UTF-8 in the source.
 When UTF-8 becomes the standard source format, this pragma will
 effectively become a no-op.  This pragma already is a no-op on
-EBCDIC platforms (where it is alright to code perl in EBCDIC 
+EBCDIC platforms (where it is alright to code perl in EBCDIC
 rather than UTF-8).
 
 Enabling the C<utf8> pragma has the following effects:
@@ -81,6 +78,32 @@ of byte semantics.
 
 =back
 
+=head2 Utility functions
+
+The following functions are defined in the C<utf8::> package by the perl core.
+
+=over 4
+
+=item * $num_octets = utf8::upgrade($string);
+
+Converts internal representation of string to the perls internal UTF-X form.
+Returns the number of octets necessary to represent the string as UTF-X.
+
+=item * utf8::downgrade($string[, CHECK])
+
+Converts internal representation of string to be un-encoded bytes.
+
+=item * utf8::encode($string)
+
+Converts (in-place) I<$string> from logical characters to octet sequence
+representing it in perl's UTF-X encoding.
+
+=item * $flag = utf8::decode($string)
+
+Attempts to converts I<$string> in-place from perl's UTF-X encoding into logical characters.
+
+=back
+
 =head1 SEE ALSO
 
 L<perlunicode>, L<bytes>