#!/bin/perl -w
# converts XML data from UTF-8 back into latin1
# -r uses a regexp
# -u uses Unicode::Strings
# -i uses Text::Iconv (and the iconv library)

# Note: -r does not work properly with XML::Parser 2.30

use strict;

my $filter;

if(    $ARGV[0] eq '-r') { $filter = \&latin1;                  }
elsif( $ARGV[0] eq '-u') { $filter= unicode_convert( 'latin1'); }
elsif( $ARGV[0] eq '-i') { $filter= iconv_convert( 'latin1');   }
else { die "usage: $0 [-r|-u|-i]"; }

my $text= <DATA>;
chomp $text; 
print "$text => ", $filter->( $text), "\n"; 

# shamelessly lifted from XML::TyePYX
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;
  }

sub unicode_convert
  { my $enc= shift;
    require Unicode::Map8;
    require Unicode::String;
    import Unicode::String qw(utf8);
    my $sub= eval q{
            { my $cnv;
          sub { $cnv ||= new Unicode::Map8 ($enc) 
                  or die "Can't create converter";
            return  $cnv->to8 (utf8($_[0])->ucs2); 
              } 
        } };
    return $sub;
  }

sub iconv_convert
  { my $enc= shift;
    require Text::Iconv;
    my $sub= eval q{
            { my $cnv;
          sub { $cnv ||= new Text::Iconv( 'utf8', $enc) 
                  or die "Can't create converter";
            return  $cnv->convert( $_[0]); 
              } 
        } };
    return $sub;
  }

__DATA__
texte soupçonné d'être plein de caractÚres accentués