package bytes;
+our $VERSION = '1.07';
+
$bytes::hint_bits = 0x00000008;
sub import {
sub AUTOLOAD {
require "bytes_heavy.pl";
- goto &$AUTOLOAD;
+ 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
-bytes - Perl pragma to force byte semantics rather than character semantics
+bytes - Perl pragma to expose the individual bytes of characters
+
+=head1 NOTICE
+
+Because the bytes pragma breaks encapsulation (i.e. it exposes the innards of
+how the perl executable currently happens to store a string), the byte values
+that result are in an unspecified encoding.
+
+B<Use of this module for anything other than debugging purposes is
+strongly discouraged.> If you feel that the functions here within
+might be useful for your application, this possibly indicates a
+mismatch between your mental model of Perl Unicode and the current
+reality. In that case, you may wish to read some of the perl Unicode
+documentation: L<perluniintro>, L<perlunitut>, L<perlunifaq> and
+L<perlunicode>.
=head1 SYNOPSIS
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.
-See L<perlunicode> for the exact details.
+Perl's characters are stored internally as sequences of one or more bytes.
+This pragma allows for the examination of the individual bytes that together
+comprise a character.
+
+Originally the pragma was designed for the loftier goal of helping incorporate
+Unicode into Perl, but the approach that used it was found to be defective,
+and the one remaining legitimate use is for debugging when you need to
+non-destructively examine characters' individual bytes. Just insert this
+pragma temporarily, and remove it after the debugging is finished.
+
+The original usage can be accomplished by explicit (rather than this pragma's
+implicit) encoding using the L<Encode> module:
+
+ use Encode qw/encode/;
-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.
+ my $utf8_byte_string = encode "UTF8", $string;
+ my $latin1_byte_string = encode "Latin1", $string;
-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.
+Or, if performance is needed and you are only interested in the UTF-8
+representation:
+
+ utf8::encode(my $utf8_byte_string = $string);
+
+C<no bytes> can be used to reverse the effect of C<use bytes> within the
+current lexical scope.
As an example, when Perl sees C<$x = chr(400)>, it encodes the character
-in UTF8 and stores it in $x. Then it is marked as character data, so,
+in UTF-8 and stores it in C<$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, $x is treated as a series of bytes - the bytes that make
+C<bytes> pragma, C<$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"
- }
+ $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 (on
+ # ASCII platforms)"
+ }
+
+C<chr()>, C<ord()>, C<substr()>, C<index()> and C<rindex()> behave similarly.
+
+For more on the implications, see L<perluniintro> and L<perlunicode>.
+
+C<bytes::length()> is admittedly handy if you need to know the
+B<byte length> of a Perl scalar. But a more modern way is:
+
+ use Encode 'encode';
+ length(encode('UTF-8', $scalar))
+
+=head1 LIMITATIONS
-For more on the implications and differences between character
-semantics and byte semantics, see L<perlunicode>.
+C<bytes::substr()> does not work as an I<lvalue()>.
=head1 SEE ALSO
-L<perlunicode>, L<utf8>
+L<perluniintro>, L<perlunicode>, L<utf8>, L<Encode>
=cut
https://perl5.git.perl.org / perl5.git / blobdiff