#!/usr/bin/perl
$russianDictFileName = "ruen.dic";
open (MAILFILE, "<$russianDictFileName") or die "Can't open file!";
$original ="";
$temp = "";
$counter = 0;

# read in the file in one go
$size=(stat($russianDictFileName))[7];
read MAILFILE, $original, $size;
$output = "";


# $original  =~ s/(.+)\*(.+)\n/$1:$2;\n/ig;
#$original  =~ s/(.+)\*(.+)\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n.+\n/$1:$2;\n/ig;



use Encode;
#my $string = "ืำลอ";
#Encode::from_to($string, "koi8_r", "Unicode");
#binmode STDOUT,':utf8';
#print length($string)," chars '$string'\n";

#my $ord = join("\n", map( ord($_),split(//,$string)));
#print "$ord";
#printf("\n Hmm " .sprintf('%X',15));


@lines = split('\n', $original);

open (FINAL_OUT, ">ruen.js") or die "Can't open file!";
print FINAL_OUT  "CONTSTR=\"";
$currEntry="";
$cou = 0;

foreach $currLine (@lines) {
  # TODO: THIS causes only each 10th entry to be used, thus
  # making it possible to stay below Langmixers 3000 entry limit
  if ($cou <= 10 ) {
    $cou++;    
  } else {
    $cou = 0;
  
  #print "\n>$currLine\n";
  #$currLine =~ m/^(.)*$/gi;
  @tempWords = split('\*', $currLine);
  $currRussian = @tempWords[0];
  $currEnglish = @tempWords[1];
  $currEnglish =~ s/;/ /gi;
  #print("CURR RUSSIAN: $currRussian");
  
  #my $currWord = "ืำลอ";
  Encode::from_to($currRussian, "koi8_r", "Unicode");
  #print(", {$currRussian}\n");
  @currWordList = split( '', $currRussian);
  $currEntry = "";
  foreach $nextChar (@currWordList) { 
    # $nextChar = "ื";
    $nextChar = sprintf('%X',ord($nextChar));
    $numZeros = 4 -length($nextChar);
    for(; $numZeros>0; $numZeros--){
      $nextChar = "0" . $nextChar;
    }
    $currEntry = $currEntry . "\\u" .$nextChar;
  #  printf("Char [$nextChar]\n");
  }
  print FINAL_OUT "$currEntry:$currEnglish;";
  }# END 100 COUNT FOR
}

# print the last closing quote
print FINAL_OUT "\"";
close FINAL_OUT;