use 5.014;
use strict;
use warnings;
use Path::Tiny qw/ path /;
use POSIX();
use autodie qw/ close /;
use File::BOM;
use Carp::Always; 
use Data::Dump qw/ dd /;
use Encode qw(encode decode);
use File::Glob;
use Text::Diff;

Main( @ARGV );
exit( 0 );

sub Main {

    #my( $infile_paths ) = @_; #if run via command line
    my( $infile_paths ) = 'C:\dev\test_paths.txt';
    chomp $infile_paths;
    my @paths = GetPaths( $infile_paths );
    for my $path ( @paths ){
        RetrieveAndBackupXML( $path );
		CompareAndCheckForReplacements( $path );
    }
    return @paths;
} 

## end sub Main

sub GetPaths  {
      use File::BOM;
##    my @paths = path( shift )->lines_utf8;
    my @paths = path( shift )->lines( { binmode => ":via(File::BOM)" } );
    s/\s+$// for @paths; # "chomp"
    return @paths;
} 

## end sub GetPaths 

sub RetrieveAndBackupXML {
    my( $directory ) = shift; ## same as shift @_ ##  
    my $date      = POSIX::strftime( '%Y-%m-%d', localtime );  #suffix for the backup-file, e.g. 2014-08-01
    my $bak       = "$date.bak"; 
    my @xml_files = path( $directory )->children( qr/\.xml$/ );
    for my $file ( @xml_files ) {
        Replace( $file, "$file-$bak" ); 
    }
} 

## end sub Main

# Fix xml entities and create a copy of the original file before editing
sub Replace {
    my( $in, $bak ) = @_;
    
    path( $in )-> copy( $bak ); #create a copy of $in with the ending specified in $bak
    
    my $infh  = path( $bak )->openr_raw;
    my $outfh = path( $in )->openrw_raw;
    
    while( <$infh> ) {
        s{&}{&amp;}g; # In some very rare cases does not match as intended, thus file comparison added
        s{\s>\s}{&gt;}g;
        s{\s<\s}{&lt;}g;
        print $outfh $_;
    }
  
    close $infh;
    close $outfh;
}

 ## end sub Replace

sub CompareAndCheckForReplacements{ 
	my( $directory ) = shift;
	## compare files to check where replacements were made

	#open log-file to write results to
	open my $FH, '>', "file_difference_report" or die $!;

	#retrieve xml file name and trim file extension
	my @base_file_names_xml = map { s/\.xml$//; $_ } glob('*.xml');
	my @base_file_names_bak = glob('*.bak');
	
	#cutting off file extension to use file name only, extension for
	#comparing .xml and .bak added by code below;
	for my $file_name ( @base_file_names_xml ) {
		if ( ! -e "$file_name.xml" ){
			print "$file_name.xml: Not present ... not interesting file?\n";
			next;
		}
		if ( ! -e "$file_name.xml.bak" ){
			print "$file_name: no backup, so probably not changed\n";
			next;
		}
		# If we get here, we have a .bak and a .xml file, so make another
		# program to compare them for us:
		my $output = diff "$file_name.xml", "$file_name.xml.bak";
		print $FH "\n\n===== $file_name changes =====\n";
		print $FH $output;
		print $FH "\n\n";
	}
}