X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Fbytes.pm;h=b7fabbf359d1a85bc34e7934a2abaf1bcd89c27b;hb=3a0105ce22d984a07f87a03826385acd066a988a;hp=0424e1778da9bd374f8bfa9602238e00957742a6;hpb=8058d7abf600e878367b422ec507695e4ac6f25a;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/lib/bytes.pm b/lib/bytes.pm
index 0424e17..b7fabbf 100644
--- a/lib/bytes.pm
+++ b/lib/bytes.pm
@@ -1,50 +1,88 @@
-package byte;
+package bytes;
+
+our $VERSION = '1.03';
+
+$bytes::hint_bits = 0x00000008;
 
 sub import {
-    $^H |= 0x00000008;
+    $^H |= $bytes::hint_bits;
 }
 
 sub unimport {
-    $^H &= ~0x00000008;
+    $^H &= ~$bytes::hint_bits;
 }
 
 sub AUTOLOAD {
-    require "byte_heavy.pl";
-    goto &$AUTOLOAD;
+    require "bytes_heavy.pl";
+    goto &$AUTOLOAD if defined &$AUTOLOAD;
+    require Carp;
+    Carp::croak("Undefined subroutine $AUTOLOAD called");
 }
 
-sub length ($);
+sub length (_);
+sub chr (_);
+sub ord (_);
+sub substr ($$;$$);
+sub index ($$;$);
+sub rindex ($$;$);
 
 1;
 __END__
 
 =head1 NAME
 
-byte - Perl pragma to force byte semantics rather than character semantics
+bytes - Perl pragma to force byte semantics rather than character semantics
 
 =head1 SYNOPSIS
 
-    use byte;
-    no byte;
+    use bytes;
+    ... chr(...);       # or bytes::chr
+    ... index(...);     # or bytes::index
+    ... length(...);    # or bytes::length
+    ... ord(...);       # or bytes::ord
+    ... rindex(...);    # or bytes::rindex
+    ... substr(...);    # or bytes::substr
+    no bytes;
+
 
 =head1 DESCRIPTION
 
-WARNING: The implementation of Unicode support in Perl is incomplete.
-Expect sudden and unannounced changes!
+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). 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 UTF-8 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; # or "require bytes; bytes::length()"
+        print "Length is ", length $x, "\n"; # "Length is 2"
+        printf "Contents are %vd\n", $x;     # "Contents are 198.144"
+    }
+
+chr(), ord(), substr(), index() and rindex() behave similarly.
 
-The C<use byte> pragma disables character semantics for the rest of the
-lexical scope in which it appears.  C<no byte> can be used to reverse
-the effect of C<use byte> within the current lexical scope.
+For more on the implications and differences between character
+semantics and byte semantics, see L<perluniintro> and L<perlunicode>.
 
-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).
+=head1 LIMITATIONS
 
-To understand the implications and differences between character
-semantics and byte semantics, see L<perlunicode>.
+bytes::substr() does not work as an lvalue().
 
 =head1 SEE ALSO
 
-L<perlunicode>, L<utf8>
+L<perluniintro>, L<perlunicode>, L<utf8>
 
 =cut