lib/perl5/5.6.1/utf8.pm

   1 package utf8;
   2
   3 if (ord('A') != 193) { # make things more pragmatic for EBCDIC folk
   4
   5 $utf8::hint_bits = 0x00800000;
   6
   7 sub import {
   8     $^H |= $utf8::hint_bits;
   9     $enc{caller()} = $_[1] if $_[1];
  10 }
  11
  12 sub unimport {
  13     $^H &= ~$utf8::hint_bits;
  14 }
  15
  16 sub AUTOLOAD {
  17     require "utf8_heavy.pl";
  18     goto &$AUTOLOAD if defined &$AUTOLOAD;
  19     Carp::croak("Undefined subroutine $AUTOLOAD called");
  20 }
  21
  22 }
  23
  24 1;
  25 __END__
  26
  27 =head1 NAME
  28
  29 utf8 - Perl pragma to enable/disable UTF-8 in source code
  30
  31 =head1 SYNOPSIS
  32
  33     use utf8;
  34     no utf8;
  35
  36 =head1 DESCRIPTION
  37
  38 WARNING: The implementation of Unicode support in Perl is incomplete.
  39 See L<perlunicode> for the exact details.
  40
  41 The C<use utf8> pragma tells the Perl parser to allow UTF-8 in the
  42 program text in the current lexical scope.  The C<no utf8> pragma
  43 tells Perl to switch back to treating the source text as literal
  44 bytes in the current lexical scope.
  45
  46 This pragma is primarily a compatibility device.  Perl versions
  47 earlier than 5.6 allowed arbitrary bytes in source code, whereas
  48 in future we would like to standardize on the UTF-8 encoding for
  49 source text.  Until UTF-8 becomes the default format for source
  50 text, this pragma should be used to recognize UTF-8 in the source.
  51 When UTF-8 becomes the standard source format, this pragma will
  52 effectively become a no-op.  This pragma already is a no-op on
  53 EBCDIC platforms (where it is alright to code perl in EBCDIC
  54 rather than UTF-8).
  55
  56 Enabling the C<utf8> pragma has the following effects:
  57
  58 =over
  59
  60 =item *
  61
  62 Bytes in the source text that have their high-bit set will be treated
  63 as being part of a literal UTF-8 character.  This includes most literals
  64 such as identifiers, string constants, constant regular expression patterns
  65 and package names.
  66
  67 =item *
  68
  69 In the absence of inputs marked as UTF-8, 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-8
  75     {
  76         use utf8;                       # force char semantics
  77         @chars = split //, $data;       # splits characters
  78     }
  79
  80 =head1 SEE ALSO
  81
  82 L<perlunicode>, L<bytes>
  83
  84 =cut