(old)Puppy Linux Discussion Forum

Code: Select all

#!/usr/bin/perl
use Encode 'decode';

#do we need to use unzip?
$filenamePar = $ARGV[0];
my $filename;
if ($filenamePar =~ m/.zip$/) {
        $filename = "unzip -p $filenamePar |";
}
else {
        $filename = $filenamePar;
}

#get file encoding
open(F, $filename) or die "Coudn't open file $filename: $!";
@lines = <F>;
close(F);

$text = join(" ", @lines);
$text =~ /<\?xml.*?encoding="(.*?)".*?\?>/;
$enc = $1;
if ("x$enc" eq "x") {
        $enc = "utf8";#defaults to utf-8
}

$lines=();
$text="";

#parse source
open (F, $filename) or die "Coudn't open file $filename: $!";
@lines = <F>;
close(F);
$text = join(" ", @lines);
$text = decode("$enc", $text);
$text =~ s/<binary.*?>.*?<\/binary>//g; #remove binary data
$text =~ s/<.*?>/ /g; #remove all xml tags
print $text;