#!/bin/perl -w

use strict;
use Benchmark( 'cmpthese');

use Encode;
use Text::Iconv;
use Unicode::Map8;
use Unicode::String qw(utf8);

use utf8;

my $enc= 'latin1';

my $convert_iconv   = Text::Iconv->new( 'utf8', $enc);
my $convert_unicode = Unicode::Map8->new ($enc);

my $text= <DATA>;
chomp $text; 


# lets just check the output!
print "Encode        : ", encode("iso-8859-1", $text), "\n";
print "Text::Iconv   : ", $convert_iconv->convert(   $text), "\n";
print "Unicode::Map8 : ", $convert_unicode->to8 (utf8($text)->ucs2), "\n";
print "regexp        : ", latin1(  $text), "\n";

# now benchmark
cmpthese( 500000, {
               'Encode'        => sub { encode("iso-8859-1", $text);               },
               'Text::Iconv'   => sub { $convert_iconv->convert( $text);           },
               'Unicode::Map8' => sub { $convert_unicode->to8 (utf8($text)->ucs2); },
               'regexp'        => sub { latin1( $text);                            },
           });


sub latin1 
  { my $text=shift;
    $text=~s{([\xc0-\xc3])(.)}{ my $hi = ord($1);
                                my $lo = ord($2);
                                chr((($hi & 0x03) <<6) | ($lo & 0x3F))
                              }ge;
    return $text;
  }


__DATA__
texte soupçonné d'être plein de caractÚres accentués