Commit | Line | Data |
657b208b |
1 | package bytes; |
5bc28da9 |
2 | |
d5448623 |
3 | $bytes::hint_bits = 0x00000008; |
4 | |
5bc28da9 |
5 | sub import { |
d5448623 |
6 | $^H |= $bytes::hint_bits; |
5bc28da9 |
7 | } |
8 | |
9 | sub unimport { |
d5448623 |
10 | $^H &= ~$bytes::hint_bits; |
5bc28da9 |
11 | } |
12 | |
13 | sub AUTOLOAD { |
657b208b |
14 | require "bytes_heavy.pl"; |
5bc28da9 |
15 | goto &$AUTOLOAD; |
16 | } |
17 | |
18 | sub length ($); |
19 | |
20 | 1; |
21 | __END__ |
22 | |
23 | =head1 NAME |
24 | |
657b208b |
25 | bytes - Perl pragma to force byte semantics rather than character semantics |
5bc28da9 |
26 | |
27 | =head1 SYNOPSIS |
28 | |
657b208b |
29 | use bytes; |
30 | no bytes; |
5bc28da9 |
31 | |
32 | =head1 DESCRIPTION |
33 | |
393fec97 |
34 | WARNING: The implementation of Unicode support in Perl is incomplete. |
21bad921 |
35 | See L<perlunicode> for the exact details. |
393fec97 |
36 | |
657b208b |
37 | The C<use bytes> pragma disables character semantics for the rest of the |
38 | lexical scope in which it appears. C<no bytes> can be used to reverse |
39 | the effect of C<use bytes> within the current lexical scope. |
393fec97 |
40 | |
5de28535 |
41 | Perl normally assumes character semantics in the presence of character |
42 | data (i.e. data that has come from a source that has been marked as |
43 | being of a particular character encoding). When C<use bytes> is in |
44 | effect, the encoding is temporarily ignored, and each string is treated |
45 | as a series of bytes. |
46 | |
47 | As an example, when Perl sees C<$x = chr(400)>, it encodes the character |
48 | in UTF8 and stores it in $x. Then it is marked as character data, so, |
49 | for instance, C<length $x> returns C<1>. However, in the scope of the |
50 | C<bytes> pragma, $x is treated as a series of bytes - the bytes that make |
51 | up the UTF8 encoding - and C<length $x> returns C<2>: |
52 | |
53 | $x = chr(400); |
54 | print "Length is ", length $x, "\n"; # "Length is 1" |
55 | printf "Contents are %vd\n", $x; # "Contents are 400" |
56 | { |
57 | use bytes; |
58 | print "Length is ", length $x, "\n"; # "Length is 2" |
59 | printf "Contents are %vd\n", $x; # "Contents are 198.144" |
60 | } |
61 | |
62 | For more on the implications and differences between character |
393fec97 |
63 | semantics and byte semantics, see L<perlunicode>. |
64 | |
65 | =head1 SEE ALSO |
66 | |
67 | L<perlunicode>, L<utf8> |
5bc28da9 |
68 | |
69 | =cut |