X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Fbytes.pm;h=3b0268e644747092e5bf8d0e287f7f396f202149;hb=843dbe2696b695867a2230e1af4a98d63d6c9559;hp=e8ab16f1bdb2afb2d63805263164a96977e4b1cc;hpb=657b208b434818aa5e54d68b0a8ad320c0252adf;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/lib/bytes.pm b/lib/bytes.pm
index e8ab16f..3b0268e 100644
--- a/lib/bytes.pm
+++ b/lib/bytes.pm
@@ -1,11 +1,15 @@
 package bytes;
 
+our $VERSION = '1.00';
+
+$bytes::hint_bits = 0x00000008;
+
 sub import {
-    $^H |= 0x00000008;
+    $^H |= $bytes::hint_bits;
 }
 
 sub unimport {
-    $^H &= ~0x00000008;
+    $^H &= ~$bytes::hint_bits;
 }
 
 sub AUTOLOAD {
@@ -30,17 +34,34 @@ bytes - Perl pragma to force byte semantics rather than character semantics
 =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 bytes> pragma disables character semantics for the rest of the
 lexical scope in which it appears.  C<no bytes> can be used to reverse
 the effect of C<use bytes> within the current lexical scope.
 
-Perl normally assumes character semantics in the presence of
-character data (i.e. data that has come from a source that has
-been marked as being of a particular character encoding).
-
-To understand the implications and differences between character
+Perl normally assumes character semantics in the presence of character
+data (i.e. data that has come from a source that has been marked as
+being of a particular character encoding). When C<use bytes> is in
+effect, the encoding is temporarily ignored, and each string is treated
+as a series of bytes. 
+
+As an example, when Perl sees C<$x = chr(400)>, it encodes the character
+in UTF8 and stores it in $x. Then it is marked as character data, so,
+for instance, C<length $x> returns C<1>. However, in the scope of the
+C<bytes> pragma, $x is treated as a series of bytes - the bytes that make
+up the UTF8 encoding - and C<length $x> returns C<2>:
+
+    $x = chr(400);
+    print "Length is ", length $x, "\n";     # "Length is 1"
+    printf "Contents are %vd\n", $x;         # "Contents are 400"
+    { 
+        use bytes;
+        print "Length is ", length $x, "\n"; # "Length is 2"
+        printf "Contents are %vd\n", $x;     # "Contents are 198.144"
+    }
+
+For more on the implications and differences between character
 semantics and byte semantics, see L<perlunicode>.
 
 =head1 SEE ALSO