| 1 | package utf8; |
| 2 | |
| 3 | |
| 4 | $utf8::hint_bits = 0x00800000; |
| 5 | |
| 6 | our $VERSION = '1.00'; |
| 7 | |
| 8 | sub import { |
| 9 | $^H |= $utf8::hint_bits; |
| 10 | $enc{caller()} = $_[1] if $_[1]; |
| 11 | } |
| 12 | |
| 13 | sub unimport { |
| 14 | $^H &= ~$utf8::hint_bits; |
| 15 | } |
| 16 | |
| 17 | sub AUTOLOAD { |
| 18 | require "utf8_heavy.pl"; |
| 19 | goto &$AUTOLOAD if defined &$AUTOLOAD; |
| 20 | Carp::croak("Undefined subroutine $AUTOLOAD called"); |
| 21 | } |
| 22 | |
| 23 | 1; |
| 24 | __END__ |
| 25 | |
| 26 | =head1 NAME |
| 27 | |
| 28 | utf8 - Perl pragma to enable/disable UTF-8 (or UTF-EBCDIC) in source code |
| 29 | |
| 30 | =head1 SYNOPSIS |
| 31 | |
| 32 | use utf8; |
| 33 | no utf8; |
| 34 | |
| 35 | =head1 DESCRIPTION |
| 36 | |
| 37 | WARNING: The implementation of Unicode support in Perl is incomplete. |
| 38 | See L<perlunicode> for the exact details. |
| 39 | |
| 40 | The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the |
| 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. |
| 44 | |
| 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 |
| 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. |
| 54 | |
| 55 | Enabling the C<utf8> pragma has the following effects: |
| 56 | |
| 57 | =over 4 |
| 58 | |
| 59 | =item * |
| 60 | |
| 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 |
| 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. |
| 66 | |
| 67 | =item * |
| 68 | |
| 69 | In the absence of inputs marked as UTF-X, regular expressions within the |
| 70 | scope of this pragma will default to using character semantics instead |
| 71 | of byte semantics. |
| 72 | |
| 73 | @bytes_or_chars = split //, $data; # may split to bytes if data |
| 74 | # $data isn't UTF-X |
| 75 | { |
| 76 | use utf8; # force char semantics |
| 77 | @chars = split //, $data; # splits characters |
| 78 | } |
| 79 | |
| 80 | =back |
| 81 | |
| 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 | |
| 104 | Attempts to convert I<$string> in-place from perl's UTF-X encoding into logical characters. |
| 105 | |
| 106 | =back |
| 107 | |
| 108 | =head1 SEE ALSO |
| 109 | |
| 110 | L<perlunicode>, L<bytes> |
| 111 | |
| 112 | =cut |