Commit | Line | Data |
a0ed51b3 |
1 | package utf8; |
2 | |
663b9db3 |
3 | if (ord('A') != 193) { # make things more pragmatic for EBCDIC folk |
4 | |
d5448623 |
5 | $utf8::hint_bits = 0x00800000; |
6 | |
b75c8c73 |
7 | our $VERSION = '1.00'; |
8 | |
a0ed51b3 |
9 | sub import { |
d5448623 |
10 | $^H |= $utf8::hint_bits; |
a0ed51b3 |
11 | $enc{caller()} = $_[1] if $_[1]; |
12 | } |
13 | |
14 | sub unimport { |
d5448623 |
15 | $^H &= ~$utf8::hint_bits; |
a0ed51b3 |
16 | } |
17 | |
18 | sub AUTOLOAD { |
19 | require "utf8_heavy.pl"; |
daf4d4ea |
20 | goto &$AUTOLOAD if defined &$AUTOLOAD; |
21 | Carp::croak("Undefined subroutine $AUTOLOAD called"); |
a0ed51b3 |
22 | } |
23 | |
663b9db3 |
24 | } |
25 | |
a0ed51b3 |
26 | 1; |
27 | __END__ |
28 | |
29 | =head1 NAME |
30 | |
393fec97 |
31 | utf8 - Perl pragma to enable/disable UTF-8 in source code |
a0ed51b3 |
32 | |
33 | =head1 SYNOPSIS |
34 | |
35 | use utf8; |
36 | no utf8; |
37 | |
38 | =head1 DESCRIPTION |
39 | |
393fec97 |
40 | WARNING: The implementation of Unicode support in Perl is incomplete. |
21bad921 |
41 | See L<perlunicode> for the exact details. |
a0ed51b3 |
42 | |
393fec97 |
43 | The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the |
44 | program text in the current lexical scope. The C<no utf8> pragma |
45 | tells Perl to switch back to treating the source text as literal |
46 | bytes in the current lexical scope. |
a0ed51b3 |
47 | |
393fec97 |
48 | This pragma is primarily a compatibility device. Perl versions |
49 | earlier than 5.6 allowed arbitrary bytes in source code, whereas |
50 | in future we would like to standardize on the UTF-8 encoding for |
51 | source text. Until UTF-8 becomes the default format for source |
52 | text, this pragma should be used to recognize UTF-8 in the source. |
53 | When UTF-8 becomes the standard source format, this pragma will |
663b9db3 |
54 | effectively become a no-op. This pragma already is a no-op on |
55 | EBCDIC platforms (where it is alright to code perl in EBCDIC |
56 | rather than UTF-8). |
a0ed51b3 |
57 | |
393fec97 |
58 | Enabling the C<utf8> pragma has the following effects: |
a0ed51b3 |
59 | |
4ac9195f |
60 | =over 4 |
a0ed51b3 |
61 | |
62 | =item * |
63 | |
393fec97 |
64 | Bytes in the source text that have their high-bit set will be treated |
65 | as being part of a literal UTF-8 character. This includes most literals |
66 | such as identifiers, string constants, constant regular expression patterns |
67 | and package names. |
a0ed51b3 |
68 | |
69 | =item * |
70 | |
393fec97 |
71 | In the absence of inputs marked as UTF-8, regular expressions within the |
72 | scope of this pragma will default to using character semantics instead |
73 | of byte semantics. |
a0ed51b3 |
74 | |
393fec97 |
75 | @bytes_or_chars = split //, $data; # may split to bytes if data |
76 | # $data isn't UTF-8 |
77 | { |
78 | use utf8; # force char semantics |
79 | @chars = split //, $data; # splits characters |
a0ed51b3 |
80 | } |
81 | |
4ac9195f |
82 | =back |
83 | |
393fec97 |
84 | =head1 SEE ALSO |
a0ed51b3 |
85 | |
8058d7ab |
86 | L<perlunicode>, L<bytes> |
a0ed51b3 |
87 | |
88 | =cut |