#!/usr/bin/perl 
use strict;
use warnings;

use utf8;
binmode(STDOUT, ":utf8");

use open ':encoding(utf8)'; # input/output default encoding will be
                                # UTF-8

my $infile;			# reads input file into string $infile

open INPUT, "<index_latin.html";
undef $/;
$infile =<INPUT>;
close INPUT;


my $k;              	  # parameter =1 between < > , =2 between > <
my $string;          	  #  "<code between>" 
my $txtstring = '';    	#  >"text between"<
my $outcode = '';   	# output: code and converted text together
my $for_conv;      	# string to be converted by sub
my $char;         	 # chatacter from input file
my $convert;     	 # converted string by sub


			# splits input file into characters 
foreach $char (split//, $infile) {

	if ($char eq "<") {
		$k = 1;
	}

	if ($k ==2)  {
		$txtstring= $txtstring . $char;
	}

	else {
		$string = $string .$char;
	}


	if ($char eq ">") {

		if (substr($txtstring, 0, 1) eq "&" ){   
				# &nbsp will not be converted
			$string =$txtstring.$string;  #goes to string code
			$txtstring = '';  ## 
		}

	$for_conv = $txtstring;

	$convert = konverter($for_conv);

	$outcode = $outcode .$convert.$string;

	$k = 2;	
	$string = '';
	$txtstring = '';
	
	}  		# of if char eq ">"

}   	# of foreach

				# writing to  file
	my $filename = "index_cyrilic.htm";	
	open(FH, '>', $filename) or die $!;
	print FH $outcode ;
	close(FH);
<readmore>

print "\n";
print "code on the output:\n";
print "\n";
print "$outcode\n";

# converting string into Cyrillic

sub konverter  {
              # dictionary

my %dict = ( "b"=> "&#1073;","B"=> "&#1041;","c"=> "&#1094;","C"=> "&#1062;","&#269;"=> "&#1095;","&#268;"=> "&#1063;","&#263;"=> "&#1115;","&#262;"=> "&#1035;","d"=> "&#1076;","D"=> "&#1044;","&#273;"=> "&#1106;","&#272;"=> "&#1026;","f"=> "&#1092;","F"=> "&#1060;","g"=> "&#1075;","G"=> "&#1043;","h"=> "&#1093;","H"=> "&#1061;","i"=> "&#1080;","I"=> "&#1048;","l"=> "&#1083;","L"=> "&#1051;","m"=> "&#1084;","n"=> "&#1085;","N"=> "&#1053;","p"=> "&#1087;","P" => "&#1055;","r" => "&#1088;","R" => "&#1056;","s"=> "&#1089;","S"=> "&#1057;","š"=> "&#1096;","Š"=> "&#1064;","t"=> "&#1090;","u"=> "&#1091;","U"=> "&#1059;","v"=> "&#1074;","V" => "&#1042;","z"=> "&#1079;", "Z"  => "&#1047;","ž"=> "&#1078;","Ž"=> "&#1046;"); 

my @conv_arr = split (//, $for_conv);   # splits input string for conversion

my $ind = 0;    # index of array element
my $out = "";   # output, converted string
my $str_char;   # string character
my $next;       # next string character
my $nj;  # Latin two character letters to be replaced with one Cyrillic 
my $Nj;
my $lj;
my $Lj;
my $dz;
my $Dz;

while ($ind <= $#conv_arr){
	$str_char = $conv_arr[$ind];   # current character 

	if ($ind ==$#conv_arr) {
		$next ="";  # there are no more characters
	}
	else {
		$next =$conv_arr[$ind+1];	# next character
	}
	
	if (exists ($dict{$str_char})) {  

                            # combination nj gives $nj = "&#1114;"
		if (($str_char eq "n") && ($next eq "j")){
			$nj = "&#1114;";
			$out = $out.$nj;
			$ind = $ind+1;
		}

		elsif (($str_char eq "N") && ($next eq "j")){
			$Nj = "&#1034;";
			$out = $out.$Nj;
			$ind = $ind+1;
		}

		elsif (($str_char eq "l") && ($next eq "j")){
			$lj = "&#1113;";
			$out = $out.$lj;
			$ind = $ind+1;
		}

		elsif (($str_char eq "L") && ($next eq "j")){
			$Lj = "&#1033;";
			$out = $out.$Lj;
			$ind = $ind+1;
		}

		elsif (($str_char eq "d") && ($next eq "ž")){
			$dz = "&#1119;";
			$out = $out.$dz;
			$ind = $ind+1;
		}

		elsif (($str_char eq "D") && ($next eq "ž")){
			$Dz = "&#1039;";
			$out = $out.$Dz;
			$ind = $ind+1;
		}
		else {   # one character letters
			$out = $out.$dict{$str_char};
		} 

	$ind++;
	} # of if exists

	else {      
		$out = $out.$str_char;
		$ind++;
	} 
}  		# of while

return $out;
} 		# of sub
</readmore>