Commit | Line | Data |
---|---|---|
a0ed51b3 LW |
1 | package utf8; |
2 | ||
663b9db3 | 3 | |
d5448623 GS |
4 | $utf8::hint_bits = 0x00800000; |
5 | ||
b75c8c73 MS |
6 | our $VERSION = '1.00'; |
7 | ||
a0ed51b3 | 8 | sub import { |
d5448623 | 9 | $^H |= $utf8::hint_bits; |
a0ed51b3 LW |
10 | $enc{caller()} = $_[1] if $_[1]; |
11 | } | |
12 | ||
13 | sub unimport { | |
d5448623 | 14 | $^H &= ~$utf8::hint_bits; |
a0ed51b3 LW |
15 | } |
16 | ||
17 | sub AUTOLOAD { | |
18 | require "utf8_heavy.pl"; | |
daf4d4ea SC |
19 | goto &$AUTOLOAD if defined &$AUTOLOAD; |
20 | Carp::croak("Undefined subroutine $AUTOLOAD called"); | |
a0ed51b3 LW |
21 | } |
22 | ||
23 | 1; | |
24 | __END__ | |
25 | ||
26 | =head1 NAME | |
27 | ||
b3419ed8 | 28 | utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code |
a0ed51b3 LW |
29 | |
30 | =head1 SYNOPSIS | |
31 | ||
32 | use utf8; | |
33 | no utf8; | |
34 | ||
35 | =head1 DESCRIPTION | |
36 | ||
393fec97 | 37 | WARNING: The implementation of Unicode support in Perl is incomplete. |
21bad921 | 38 | See L<perlunicode> for the exact details. |
a0ed51b3 | 39 | |
393fec97 | 40 | The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the |
b3419ed8 PK |
41 | program text in the current lexical scope (allow UTF-EBCDIC on EBCDIC based |
42 | platforms). The C<no utf8> pragma tells Perl to switch back to treating | |
43 | the source text as literal bytes in the current lexical scope. | |
a0ed51b3 | 44 | |
393fec97 GS |
45 | This pragma is primarily a compatibility device. Perl versions |
46 | earlier than 5.6 allowed arbitrary bytes in source code, whereas | |
47 | in future we would like to standardize on the UTF-8 encoding for | |
48 | source text. Until UTF-8 becomes the default format for source | |
49 | text, this pragma should be used to recognize UTF-8 in the source. | |
50 | When UTF-8 becomes the standard source format, this pragma will | |
b3419ed8 PK |
51 | effectively become a no-op. For convenience in what follows the |
52 | term UTF-X is used to refer to UTF-8 on ASCII and ISO Latin based | |
53 | platforms and UTF-EBCDIC on EBCDIC based platforms. | |
a0ed51b3 | 54 | |
393fec97 | 55 | Enabling the C<utf8> pragma has the following effects: |
a0ed51b3 | 56 | |
4ac9195f | 57 | =over 4 |
a0ed51b3 LW |
58 | |
59 | =item * | |
60 | ||
393fec97 GS |
61 | Bytes in the source text that have their high-bit set will be treated |
62 | as being part of a literal UTF-8 character. This includes most literals | |
63 | such as identifiers, string constants, constant regular expression patterns | |
395f5a0c PK |
64 | and package names. On EBCDIC platforms characters in the Latin 1 |
65 | character set are treated as being part of a literal UTF-EBCDIC character. | |
a0ed51b3 LW |
66 | |
67 | =item * | |
68 | ||
b3419ed8 | 69 | In the absence of inputs marked as UTF-X, regular expressions within the |
393fec97 GS |
70 | scope of this pragma will default to using character semantics instead |
71 | of byte semantics. | |
a0ed51b3 | 72 | |
393fec97 | 73 | @bytes_or_chars = split //, $data; # may split to bytes if data |
b3419ed8 | 74 | # $data isn't UTF-X |
393fec97 GS |
75 | { |
76 | use utf8; # force char semantics | |
77 | @chars = split //, $data; # splits characters | |
a0ed51b3 LW |
78 | } |
79 | ||
4ac9195f MS |
80 | =back |
81 | ||
1b026014 NIS |
82 | =head2 Utility functions |
83 | ||
84 | The following functions are defined in the C<utf8::> package by the perl core. | |
85 | ||
86 | =over 4 | |
87 | ||
88 | =item * $num_octets = utf8::upgrade($string); | |
89 | ||
90 | Converts internal representation of string to the perls internal UTF-X form. | |
91 | Returns the number of octets necessary to represent the string as UTF-X. | |
92 | ||
93 | =item * utf8::downgrade($string[, CHECK]) | |
94 | ||
95 | Converts internal representation of string to be un-encoded bytes. | |
96 | ||
97 | =item * utf8::encode($string) | |
98 | ||
99 | Converts (in-place) I<$string> from logical characters to octet sequence | |
100 | representing it in perl's UTF-X encoding. | |
101 | ||
102 | =item * $flag = utf8::decode($string) | |
103 | ||
b3419ed8 | 104 | Attempts to convert I<$string> in-place from perl's UTF-X encoding into logical characters. |
1b026014 NIS |
105 | |
106 | =back | |
107 | ||
393fec97 | 108 | =head1 SEE ALSO |
a0ed51b3 | 109 | |
8058d7ab | 110 | L<perlunicode>, L<bytes> |
a0ed51b3 LW |
111 | |
112 | =cut |