#!/usr/bin/perl -w

my $usage="Usage: $0 [-e] fastaFile1 fastaFile2\n" .
    " -e: make sure the 2 files contains the sequences in Exact same order\n".
    "With -e, sequences have to be in exactly the same order and has " . 
    "identical names in the two files. Without -e, it joins the sequence " .
    "whose name appears in both files and ignore the rest." . 
    "Order in the 1st file is preserved in this case";

my $sep = "\t";

use Getopt::Std;
getopts('e') || die "$usage\n";

@ARGV = ('-') unless @ARGV;

@maxLenVect = ();
while ($argv = shift) {
    my @dat = ReadInFASTA($argv);
    my $len = MaxSeqLen(@dat);
    push @maxLenVect, $len;
}

print join " ", @maxLenVect;
print "\n";

exit(0);

# takes an arg; name of a file from which data are read Then read in
# the data and make an array.  Each element of this array corresponds
# to a sequence, name tab data.
sub ReadInFASTA {
    my $infile = shift;
    my @line;
    my $i = -1;
    my @result = ();
    my @seqName = ();
    my @seqDat = ();

    open (INFILE, "<$infile") || die "Can't open $infile\n";

    while (<INFILE>) {
        chomp;
        if (/^>/) {  # name line in fasta format
            $i++;
            s/^>\s*//; s/^\s+//; s/\s+$//;
            $seqName[$i] = $_;
            $seqDat[$i] = "";
        } else {
            s/^\s+//; s/\s+$//;
	    s/\s+//g;                  # get rid of any spaces
            next if (/^$/);            # skip empty line
            s/[uU]/T/g;                  # change U to T
            $seqDat[$i] = $seqDat[$i] . uc($_);
        }

	# checking no occurence of internal separator $sep.
	die ("ERROR: \"$sep\" is an internal separator.  Line $. of " .
	     "the input FASTA file contains this charcter. Make sure this " . 
	     "separator character is not used in your data file or modify " .
	     "variable \$sep in this script to some other character.\n")
	    if (/$sep/);

    }
    close(INFILE);

    foreach my $i (0..$#seqName) {
	$result[$i] = $seqName[$i] . $sep . $seqDat[$i];
    }
    return (@result);
}

sub GetSeqDat {
    my @data = @_;
    my @line;
    my @result = ();

    foreach my $i (@data) {
	@line = split (/$sep/, $i);
	push @result, $line[1];
    }

    return (@result)
}

sub GetSeqName {
    my @data = @_;
    my @line;
    my @result = ();

    foreach my $i (@data) {
	@line = split (/$sep/, $i);
	push @result, $line[0];
    }
    return (@result)
}

sub CharLen {
    my $string = shift;
    my @charString = split (//, $string);
    return scalar(@charString);
}

sub MaxSeqLen {
    my @data = GetSeqDat(@_);
    my $maxLen = 0;
    foreach $i (@data) {
        my $len = CharLen($i);
        $maxLen = $len if ($len > $maxLen);
    }
    return ($maxLen);
}