Integrate changes #9259,9260 from maintperl into mainline.

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

diff --git a/lib/utf8.pm b/lib/utf8.pm
index c362a1c..7c9a7df 100644 (file)
--- a/lib/utf8.pm
+++ b/lib/utf8.pm
@@ -1,7 +1,11 @@
 package utf8;
 
+if (ord('A') != 193) { # make things more pragmatic for EBCDIC folk
+
 $utf8::hint_bits = 0x00800000;
 
+our $VERSION = '1.00';
+
 sub import {
     $^H |= $utf8::hint_bits;
     $enc{caller()} = $_[1] if $_[1];
@@ -13,7 +17,10 @@ sub unimport {
 
 sub AUTOLOAD {
     require "utf8_heavy.pl";
-    goto &$AUTOLOAD;
+    goto &$AUTOLOAD if defined &$AUTOLOAD;
+    Carp::croak("Undefined subroutine $AUTOLOAD called");
+}
+
 }
 
 1;
@@ -31,7 +38,7 @@ utf8 - Perl pragma to enable/disable UTF-8 in source code
 =head1 DESCRIPTION
 
 WARNING: The implementation of Unicode support in Perl is incomplete.
-Expect sudden and unannounced changes!
+See L<perlunicode> for the exact details.
 
 The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the
 program text in the current lexical scope.  The C<no utf8> pragma
@@ -44,11 +51,13 @@ in future we would like to standardize on the UTF-8 encoding for
 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.
+effectively become a no-op.  This pragma already is a no-op on
+EBCDIC platforms (where it is alright to code perl in EBCDIC
+rather than UTF-8).
 
 Enabling the C<utf8> pragma has the following effects:
 
-=over
+=over 4
 
 =item *
 
@@ -70,6 +79,34 @@ of byte semantics.
        @chars = split //, $data;       # splits characters
     }
 
+=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>