###############################################################################
##### Solution 01 #############################################################
###############################################################################

#! /usr/bin/perl -w

print "Type data filename: ";
$infilename = <STDIN>;
print "Type result filename: ";
$outfilename = <STDIN>;
chomp($infilename);
chomp($outfilename);
#$filename = "sequence.txt";

open (SEQUENCE, '<', $infilename) 
  or die "Can't open the file: $infilename\n";

open (RESULT, '>', $outfilename) 
  or die "Can't open the file: $outfilename\n";

while (<SEQUENCE>){
  $line = $_;
  chomp($line);
  $length = length($line);
  $firstchar = substr($line,0,1);
  for ($i = 0; $i < ($length-1); $i++){
    $char = substr($line, $i, 2);
    $charCount{$char}++;
    $totLength ++;
  }
  if(defined($lastchar)){
    $char = $lastchar.$firstchar;
    $charCount{$char}++;
    $totLength ++;
  }
  $lastchar = substr($line,$i,1);
}
close(SEQUENCE);

foreach $char (sort keys %charCount){
  $frac = ($charCount{$char}/$totLength) *100;
  print "The two-character word $char occurs $charCount{$char} times, or $frac %.\n";
  print RESULT "The two-character word $char occurs $charCount{$char} times, or $frac %.\n";
} 
print "The total number of characters is $totLength.\n";
print RESULT "The total number of characters is $totLength.\n";
close(RESULT);


###############################################################################
##### Solution 02 #############################################################
###############################################################################

#!/usr/bin/perl

print "Type data filename: ";
chomp($filename = <STDIN>);

print "Type result filename: ";
chomp($filename2 = <STDIN>);

open (SEQUENCE, '<', $filename) 
  or die "Can't open the file: $filename\n";

while (<SEQUENCE>){
  $line = substr ($line, -1, 1) . $_;
  chomp($line);
  $length = length($line);
  for ($i = 0; $i < $length - 1; $i++){
    $pair = substr($line, $i, 2);
    $pairCount{$pair}++;
    $total++;
  } 	
}
close(SEQUENCE);

open (RESULT, '>', $filename2) 
  or die "Can't open the file: $filename2\n";

select RESULT;
foreach $pair (sort keys %pairCount){
  $percent = $pairCount{$pair}/$total*100;
  print "The two-character word $pair occurs $pairCount{$pair} times, or $percent %.\n";
} 

print "The total number of characters is $total.\n";
select STDOUT;
print "Results sent to $filename2\n";
close RESULT;


###############################################################################
##### Solution 03 #############################################################
###############################################################################

#!/usr/bin/perl

print "Type data filename: ";
chomp($filename = <STDIN>);
open (SEQUENCE, '<', $filename) 
  or die "Can't open the file: $filename\n";

print "Type result filename: ";
chomp($filename2 = <STDIN>);
open (OUTPUT, '>', $filename2) 
  or die "Can't open the file: $filename2\n";

$count = 0;
$prev = '';

while (<SEQUENCE>){
  $line = $prev . $_;
  chomp($line);
  $length = length($line);
  for ($i = 0; $i < $length - 1; $i++){
    $char = substr($line, $i, 2);
    $charCount{$char}++;
    $count++;
    $prev = substr($line, $i + 1, 1);
  }
}
close(SEQUENCE);

foreach $char (sort keys %charCount){
  $per = $charCount{$char} / $count * 100;
  print OUTPUT "The two-character word $char occurs $charCount{$char} times, or $per%.\n";
} 
print OUTPUT "The total number of characters is $count.\n";
close(OUTPUT);


###############################################################################
##### Solution 04 #############################################################
###############################################################################
#!/lusr/bin/perl -w

print "Type data filename: ";
$filename = <STDIN>;
chomp $filename;
open (SEQUENCE, '<', $filename) 
  or die "Can't open the file: $filename\n";

$total = 0;

while (<SEQUENCE>){
  $line = $_;
  chomp($line);
  $length = length($line);
  for ($i = 0; $i < $length; $i++){
    $last = $char;
    $char = substr($line, $i, 1);
    if ($total) {
        $charCount{($last.$char)}++;
    }
    $total++;
  }
}
close(SEQUENCE);

print "Type result filename: ";
$filename = <STDIN>;
chomp $filename;
open (RESULT, '>', $filename) 
  or die "Can't open the file: $filename\n";

foreach $char (sort keys %charCount){
  $ratio = 100 * $charCount{$char} / $total;
  print RESULT "The two-character word $char occurs $charCount{$char} times, or $ratio %.\n";
} 
print RESULT "The total number of characters is $total - 1.\n";
print RESULT "End of file.\n";
close(RESULT);


###############################################################################
##### Solution 05 #############################################################
###############################################################################
#!/usr/bin/perl

print "Type data filename: ";
chomp($filename = <STDIN>);
open (SEQUENCE, '<', $filename)
	or die "Can't open the file: $filename\n";

print "Type result filename: ";
chomp($outfilename = <STDIN>);
open(OUTFILE, ">" , $outfilename)
	or die "Can't create the file: $outfilename\n";

$longString = "";

while(<SEQUENCE>){
	chomp($_);
	$longString .= $_;
}
$fulllength = length($longString);
$fulllength--;

for($i=0; $i < $fulllength; $i++){
    $char = substr($longString,$i,2);
    $charCount{$char}++;
}
close(SEQUENCE);

foreach $char(sort keys %charCount){
	print OUTFILE 'The character ',$char," occurs $charCount{$char} times, or ",$charCount{$char}/$fulllength*100, " %.\n";
}
print OUTFILE "The total number of characters is ", $fulllength ,".\n";
close(OUTFILE);


###############################################################################
##### Solution 06 #############################################################
###############################################################################
#!/usr/bin/perl

# Get and open the input file.
print "Type data filename: ";
$filename = <STDIN>;
chomp($filename);

###if ($filename == "") { $filename = "sequence.txt"; }
if ($filename eq "") { $filename = "sequence.txt"; }

open (SEQUENCE, '<', $filename) 
  or die "Can't open the file: $filename\n";

# Get and open the output file
print "Type result filename: ";

$outfile = <STDIN>;
chomp($outfile);

if ($outfile == "") {
  $outfile = "result2.txt";
  open (RESULT, '>', $outfile)
    or die "Can't open result file: $outfile\n";
  $out = RESULT;
} elsif ($outfile == "-") {                 
  $outfile = "STDOUT";
  $out = STDOUT;
} else {
  open (RESULT, '>', $outfile)
    or die "Can't open result file: $outfile\n";
  $out = RESULT;
}

# Processing time!

$totalLength = 0;
$prevChar = '';

while (<SEQUENCE>){
  $line = $_;
  chomp($line);
  $totalLength += length($line);
  
  $line = $prevChar . $line;
  $length = length($line);

  for ($i = 0; $i < $length - 1; $i++){
    $word = substr($line, $i, 2);
    $wordCount{$word}++;
  }
  
  # grab the last character, so we can pop it onto the beginning
  # of the following string...
  $prevChar = substr($line, $i, 1);
}

close(SEQUENCE);

# Print output.
foreach $word (sort keys %wordCount){
  print $out "The two-character word $word occurs $wordCount{$word} times, or ";
  print $out (($wordCount{$word} / $totalLength) * 100);
  print $out " \%.\n";
} 
print $out "The total number of characters is $totalLength - 1.\n";
print $out "End of file.\n"


###############################################################################
##### Solution 07 #############################################################
###############################################################################
#!/usr/bin/perl

print "Type data filename: ";
chomp($filename = <STDIN>);

print "Type result filename: ";
chomp($outFile = <STDIN>);

open (SEQUENCE, '<', $filename) 
  or die "Can't open the file: $filename\n";

$totalCount = 0;
$prevChar = undef;

while (<SEQUENCE>){
  $line = $_;
  chomp($line);
  $length = length($line);
  for ($i = 0; $i < $length; $i++){
    if (!defined $prevChar) {
      $prevChar = substr($line, $i, 1);
      next;
    }
    $currChar = substr($line, $i, 1);
    $sequence = $prevChar . $currChar;
    $sequenceCount{$sequence}++;
	$totalCount++;
    $prevChar = $currChar;
  }
}
close(SEQUENCE);

@sortedKeys = sort (keys %sequenceCount);

open RES, ">$outFile";
foreach $sequence (@sortedKeys){
  $currCount = $sequenceCount{$sequence};
  $currFraction = 100 * ($currCount / $totalCount);
  print "The two-character word $sequence occurs $currCount times, or $currFraction %\n";
  print RES "The two-character word $sequence occurs $currCount times, or $currFraction %\n";
} 
print "The total number of characters is $totalCount.\n";
print RES "The total number of characters is $totalCount.\nEnd of file.";


###############################################################################
##### Solution 08 #############################################################
###############################################################################
#!/usr/bin/perl

print "Type data filename: ";
chomp ($inputFilename = <STDIN>);

print "Type result filename: ";
chomp ($outputFilename = <STDIN>);

open (SEQUENCE, '<', $inputFilename) 
  or die "Can't open the file: $inputFilename\n";
  
open (RESULT, '>', $outputFilename)
  or die "Can't open the file: $outputFilename\n";

while (defined($line=<SEQUENCE>))
{
  chomp($line);
  $length = length($line);
  $size += $length;
  for ($i = 0; $i < $length; $i++)
  {
    $char = substr($line, $i, 1);
    if (defined($prevChar))
    {
    	$word = $prevChar . $char;
    	$wordCount{$word}++;
    }
    $prevChar = $char;
  }
}

$size--;

close(SEQUENCE);

foreach $word (sort keys %wordCount)
{
  $wordFraction{$word} = $wordCount{$word} / $size * 100;
  print RESULT "The two-character word $word occurs $wordCount{$word} times, or $wordFraction{$word}%.\n";
} 

print RESULT "The total number of characters is $size.\n";
close(RESULT);


###############################################################################
##### Solution 09 #############################################################
###############################################################################
#! /usr/bin/perl

print "Type data filename: ";
$filename = <STDIN>; 
chomp($filename);

print "Type results filename: ";
$resultsFilename = <STDIN>;
chomp($resultsFilename);

open (SEQUENCE, '<', $filename) 
  or die "Can't open the file: $filename\n";

$total = 0;

$lastChar;

while (<SEQUENCE>){
  $line = $_;
  chomp($line);
  $length = length($line);
  for ($i = 0; $i < $length; $i++){
    $char = substr($line, $i, 1);
    if( !($lastChar eq "") ){
      $charCount{($lastChar.$char)}++;
      $lastChar = $char;
      $total++;
      }
    else {
      $lastChar = $char;
    }
  }
}
close(SEQUENCE);

open FILE, ">$resultsFilename" or die "unable to open $resultsFilename $!";
foreach $char (sort (keys %charCount)){
  $percentage = ($charCount{$char} / $total) * 100;
  print FILE "The character $char occurs $charCount{$char} times, or $percentage %.\
n";
} 
print FILE "The total number of characters is $total.\n";
print FILE "End of file.";


###############################################################################
##### Solution 10 #############################################################
###############################################################################
#! /lusr/bin/perl

print "Type data filename: ";
$filename = <STDIN>;
chomp $filename;
open(SEQUENCE, "<", $filename) or die "Can't open the file: $filename\n";
print "Type result filename: ";
$ofile = <STDIN>;
chomp $ofile;
open(RESULT, ">", $ofile) or die "Can't create the file: $ofile\n";

$total = 0;
$char='';
while(<SEQUENCE>)
{
	$line = $_;
	chomp $line;
	$length = length $line;
	if($length != 0)
	{
		if($char)
		{
			$char = $char . substr($line,0,1);
			$charCount{$char}++;
			$total++;
		}
		for($i = 0; $i < $length-1; $i++)
		{
			$char = substr($line, $i, 2);
			$charCount{$char}++;
			$total++;
		}
		$char = substr($line,$length-1,1);
	}
}
$total++;
close SEQUENCE;

foreach $char (sort keys %charCount)
{
	$percentage = $charCount{$char} / $total * 100;
	print "The two-character word $char occurs $charCount{$char} times, or $percentage %.\n";
	print RESULT "The two-character word $char occurs $charCount{$char} times, or $percentage %.\n";
} 
print "The total number of characters is $total.\n";
print RESULT "The total number of characters is $total.\n";
close RESULT;