package utf8::all; use strict; use warnings; use 5.010; # state # ABSTRACT: turn on Unicode - all of it our $VERSION = '0.011'; # VERSION use Import::Into; use parent qw(Encode charnames utf8 open warnings feature); use Symbol qw/qualify_to_ref/; sub import { my $target = caller; 'utf8'->import::into($target); 'open'->import::into($target, qw{:encoding(UTF-8) :std}); 'charnames'->import::into($target, qw{:full :short}); 'warnings'->import::into($target, qw{FATAL utf8}); 'feature'->import::into($target, qw{unicode_strings}) if $^V >= v5.11.0; 'feature'->import::into($target, qw{unicode_eval fc}) if $^V >= v5.16.0; { no strict qw(refs); ## no critic (TestingAndDebugging::ProhibitNoStrict) *{$target . '::readdir'} = \&_utf8_readdir; } # utf8 in @ARGV state $have_encoded_argv = 0; _encode_argv() unless $have_encoded_argv++; $^H{'utf8::all'} = 1; return; } sub _encode_argv { $_ = Encode::decode('UTF-8', $_) for @ARGV; return; } sub _utf8_readdir(*) { ## no critic (Subroutines::ProhibitSubroutinePrototypes) my $pre_handle = shift; my $handle = ref($pre_handle) ? $pre_handle : qualify_to_ref($pre_handle, caller); my $hints = (caller 0)[10]; if (wantarray) { my @all_files = CORE::readdir($handle); return @all_files if not $hints->{'utf8::all'}; $_ = Encode::decode('UTF-8', $_) for @all_files; return @all_files; } else { my $next_file = CORE::readdir($handle); $next_file = Encode::decode('UTF-8', $next_file) if $hints->{'utf8::all'}; return $next_file; } } 1; __END__ =pod =encoding utf-8 =head1 NAME utf8::all - turn on Unicode - all of it =head1 VERSION version 0.011 =head1 SYNOPSIS use utf8::all; # Turn on UTF-8. All of it. open my $in, '<', 'contains-utf8'; # UTF-8 already turned on here print length 'føø bār'; # 7 UTF-8 characters my $utf8_arg = shift @ARGV; # @ARGV is UTF-8 too! =head1 DESCRIPTION L allows you to write your Perl encoded in UTF-8. That means UTF-8 strings, variable names, and regular expressions. C goes further, and makes C<@ARGV> encoded in UTF-8, and filehandles are opened with UTF-8 encoding turned on by default (including STDIN, STDOUT, STDERR), and charnames are imported so C<\N{...}> sequences can be used to compile Unicode characters based on names. If you I want UTF-8 for a particular filehandle, you'll have to set C. The pragma is lexically-scoped, so you can do the following if you had some reason to: { use utf8::all; open my $out, '>', 'outfile'; my $utf8_str = 'føø bār'; print length $utf8_str, "\n"; # 7 print $out $utf8_str; # out as utf8 } open my $in, '<', 'outfile'; # in as raw my $text = do { local $/; <$in>}; print length $text, "\n"; # 10, not 7! =head1 INTERACTION WITH AUTODIE If you use L, which is a great idea, you need to use at least version B<2.12>, released on L. Otherwise, autodie obliterates the IO layers set by the L pragma. See L and L. =head1 AVAILABILITY The project homepage is L. The latest version of this module is available from the Comprehensive Perl Archive Network (CPAN). Visit L to find a CPAN site near you, or see L. =head1 SOURCE The development version is on github at L and may be cloned from L =head1 BUGS AND LIMITATIONS You can make new bug reports, and view existing ones, through the web interface at L. =head1 AUTHORS =over 4 =item * Michael Schwern =item * Mike Doherty =back =head1 COPYRIGHT AND LICENSE This software is copyright (c) 2009 by Michael Schwern . This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself. =cut