summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/bytes.pm
diff options
context:
space:
mode:
Diffstat (limited to 'Master/tlpkg/tlperl/lib/bytes.pm')
-rw-r--r--Master/tlpkg/tlperl/lib/bytes.pm100
1 files changed, 100 insertions, 0 deletions
diff --git a/Master/tlpkg/tlperl/lib/bytes.pm b/Master/tlpkg/tlperl/lib/bytes.pm
new file mode 100644
index 00000000000..6dad41ad9ff
--- /dev/null
+++ b/Master/tlpkg/tlperl/lib/bytes.pm
@@ -0,0 +1,100 @@
+package bytes;
+
+our $VERSION = '1.04';
+
+$bytes::hint_bits = 0x00000008;
+
+sub import {
+ $^H |= $bytes::hint_bits;
+}
+
+sub unimport {
+ $^H &= ~$bytes::hint_bits;
+}
+
+sub AUTOLOAD {
+ require "bytes_heavy.pl";
+ goto &$AUTOLOAD if defined &$AUTOLOAD;
+ require Carp;
+ Carp::croak("Undefined subroutine $AUTOLOAD called");
+}
+
+sub length (_);
+sub chr (_);
+sub ord (_);
+sub substr ($$;$$);
+sub index ($$;$);
+sub rindex ($$;$);
+
+1;
+__END__
+
+=head1 NAME
+
+bytes - Perl pragma to force byte semantics rather than character semantics
+
+=head1 NOTICE
+
+This pragma reflects early attempts to incorporate Unicode into perl and
+has since been superseded. It breaks encapsulation (i.e. it exposes the
+innards of how the perl executable currently happens to store a string),
+and use of this module for anything other than debugging purposes is
+strongly discouraged. If you feel that the functions here within might be
+useful for your application, this possibly indicates a mismatch between
+your mental model of Perl Unicode and the current reality. In that case,
+you may wish to read some of the perl Unicode documentation:
+L<perluniintro>, L<perlunitut>, L<perlunifaq> and L<perlunicode>.
+
+=head1 SYNOPSIS
+
+ use bytes;
+ ... chr(...); # or bytes::chr
+ ... index(...); # or bytes::index
+ ... length(...); # or bytes::length
+ ... ord(...); # or bytes::ord
+ ... rindex(...); # or bytes::rindex
+ ... substr(...); # or bytes::substr
+ no bytes;
+
+
+=head1 DESCRIPTION
+
+The C<use bytes> pragma disables character semantics for the rest of the
+lexical scope in which it appears. C<no bytes> can be used to reverse
+the effect of C<use bytes> within the current lexical scope.
+
+Perl normally assumes character semantics in the presence of character
+data (i.e. data that has come from a source that has been marked as
+being of a particular character encoding). When C<use bytes> is in
+effect, the encoding is temporarily ignored, and each string is treated
+as a series of bytes.
+
+As an example, when Perl sees C<$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.
+
+For more on the implications and differences between character
+semantics and byte semantics, see L<perluniintro> and L<perlunicode>.
+
+=head1 LIMITATIONS
+
+bytes::substr() does not work as an lvalue().
+
+=head1 SEE ALSO
+
+L<perluniintro>, L<perlunicode>, L<utf8>
+
+=cut