1package bytes; 2 3our $VERSION = '1.01'; 4 5$bytes::hint_bits = 0x00000008; 6 7sub import { 8 $^H |= $bytes::hint_bits; 9} 10 11sub unimport { 12 $^H &= ~$bytes::hint_bits; 13} 14 15sub AUTOLOAD { 16 require "bytes_heavy.pl"; 17 goto &$AUTOLOAD; 18} 19 20sub length ($); 21sub chr ($); 22sub ord ($); 23sub substr ($$;$$); 24sub index ($$;$); 25sub rindex ($$;$); 26 271; 28__END__ 29 30=head1 NAME 31 32bytes - Perl pragma to force byte semantics rather than character semantics 33 34=head1 SYNOPSIS 35 36 use bytes; 37 ... chr(...); # or bytes::chr 38 ... index(...); # or bytes::index 39 ... length(...); # or bytes::length 40 ... ord(...); # or bytes::ord 41 ... rindex(...); # or bytes::rindex 42 ... substr(...); # or bytes::substr 43 no bytes; 44 45 46=head1 DESCRIPTION 47 48The C<use bytes> pragma disables character semantics for the rest of the 49lexical scope in which it appears. C<no bytes> can be used to reverse 50the effect of C<use bytes> within the current lexical scope. 51 52Perl normally assumes character semantics in the presence of character 53data (i.e. data that has come from a source that has been marked as 54being of a particular character encoding). When C<use bytes> is in 55effect, the encoding is temporarily ignored, and each string is treated 56as a series of bytes. 57 58As an example, when Perl sees C<$x = chr(400)>, it encodes the character 59in UTF-8 and stores it in $x. Then it is marked as character data, so, 60for instance, C<length $x> returns C<1>. However, in the scope of the 61C<bytes> pragma, $x is treated as a series of bytes - the bytes that make 62up the UTF8 encoding - and C<length $x> returns C<2>: 63 64 $x = chr(400); 65 print "Length is ", length $x, "\n"; # "Length is 1" 66 printf "Contents are %vd\n", $x; # "Contents are 400" 67 { 68 use bytes; # or "require bytes; bytes::length()" 69 print "Length is ", length $x, "\n"; # "Length is 2" 70 printf "Contents are %vd\n", $x; # "Contents are 198.144" 71 } 72 73chr(), ord(), substr(), index() and rindex() behave similarly. 74 75For more on the implications and differences between character 76semantics and byte semantics, see L<perluniintro> and L<perlunicode>. 77 78=head1 LIMITATIONS 79 80bytes::substr() does not work as an lvalue(). 81 82=head1 SEE ALSO 83 84L<perluniintro>, L<perlunicode>, L<utf8> 85 86=cut 87