#!/usr/bin/perl --
use Path::Tiny qw/ path /;
use Data::Dump qw/ dd /;
use XML::Twig;
my $infile = 'twiggy-test.xml';
my $outfile = 'twiggy-WHAT.xml';
dd( path( $infile )->slurp_utf8 );
getTwiggy( $infile , $outfile );
dd( path( $outfile )->slurp_raw );
sub getTwiggy {
# set up the XML parser:
my $twig= XML::Twig->new(
comments => 'keep',
# keep_encoding => 1,
keep_spaces=> 1,
twig_handlers => { li => sub_ix_strings($infile),
},
);
$twig->parsefile($infile);
print " Saving $outfile...\n";
open(NEW,">$outfile") || die("cannot open file $outfile for writing
+.\n");
$twig->flush( \*NEW);
close(NEW);
}
sub sub_ix_strings {
my($file) = @_;
return sub {
my($twig,$elt) = @_;
$elt->set_att('test',"hello");
}
}
__END__
OUTPUT (looks the same, but file is now ANSI not UTF-8):
<?xml version="1.0" encoding="UTF-8"?>
<reference id="ids_excal_142" xml:lang="en-us">
<title>The ISO character set</title>
<refbody>
<section><p>Each ISO character has its own value, except that lowercas
+e
characters are translated to uppercase. Two characters that have no
uppercase equivalent are: <ul>
<li test="hello">German small sharp s (ß - 0xDF)</li>
<li test="hello">Lowercase y diaeresis/umlaut (ÿ - 0xFF)</li>
</ul></p></section>
</refbody>
</reference>
So the output looks ok in my text editor (TextPad) but when I open it in an XML editor (Arbortext or Oxygen) the special characters don't display correctly.
Thanks! Scott |