#!/usr/bin/perl

##############################################
##############################################
# SCRIPT NAME:  Page_Statistics.cgi
# FUNCTION:     Show database statistics
##############################################


# MINE: Molecular INformation Explorer
# Copyright 2000 Dawn Field.  All rights reserved.
# The CGI-PERL scripts belonging to MINE
# may be used and modified freely, but I do
# request that this copyright notice remain attached
# to this file/source code.  If you make modifications
# please do not distribute unless
# you fully document the modifications.
	
	
use  CGI;
require "CGI-MINE.pl";

        #################
        # START EACH MINE CGI SCRIPT
        #################
        # this redirects the error messages to the user's screen
        # and is useful for debugging CGI scripts!
        open (STDERR, ">&STDOUT");         # print errors to screen
        $| = 1;                            # flush the print buffer continuously
        # make a new query object using CGI.pm module
        $query = new CGI;
        # print the required header and start the web page
        print $query->header;   
        print $query->start_html('MINE');
        # Each time a script is invoked for the first time (or $action undef),
        # log the visit in the custom MINE server log (see CGI-MINE.pl)
        # (put this after the header incase an error message is printed)
        # check value of $action
        $action = $query->param('action');
        if ($action eq undef) {&log();}
	$debug = 0; # set to one to see debugging print info


        #######
        # START THE WEBPAGE
        #######
        # print the MINE menu
        &menu;
        # start the basic gray table used for formatting MINE pages
        &table_top();
        # put the main title of your page here
	print "<font name=arial size=3>";
        print "<b><i><font size=+1>Database Statistics</font></i></b><p><p>";
	

        ############
        # START AUTOMATIC PROCESS OF STATISTICS
        ############
	# put all the files in the database into an array
 #	@files = <*.db>;	
	# use this array to print how many files are in the database
	print "<table BORDER=0 CELLSPACING=0 CELLPADDING=0 BORDER WIDTH=\"300\"><tr>";
	print "<td>File Type</td><td>Total Number</td><td>Total characters</td></tr>";
	# go into each set of files and get the length of the sequences 
	# don't presume the "length" field is defined, caluculate it
	# again here from the sequences in each file
	foreach $ext (@stat_extensions) {
	        # use Perl's equivalent function called readdir to get the names of all the files
	        opendir THISDIR, "." or die "can't read the files in this directory";
	        @database = grep /$ext$/, readdir THISDIR;
	        closedir THISDIR;
	        # this puts the files into order, so that you get 0001, 0002, 0003, and not 0001, 0010 or stranger
	        @database = sort @database;
		@files = @database;
		# call the function to calculate total characters 
                &total_nuc_in_database(@files);
                print "</tr><td>$ext</td><td>".@files."</td><td>$total_len<P></td></tr>";
                $total_count += $total_len;
                undef($total_len);
	}
        print "<\/tr><\/table>";
        # finish the table formatting
        &table_bottom();

        #################
        # END PROCESSING STATISTICS
        #################


        # PRINT BOTTOM OF EACH WEB PAGE
        # if $show_source is set to 1 show a link
        # at the bottom of each script to the source
        # code - pass the name of this script to the
        # function in CGI-MINE.pl
        if ($show_source) {
                $script_name = $query->script_name();
                &source ($script_name);
        }
        # ATTACH the MINE copywrite
        &mine_cp;
	print "</font>";
        print $query->end_html;
        #################
        # END WEBPAGE
        #################



#####################
# FUNCTIONS
#####################

#############################
# FUNCTION: TOTAL NUCLEOTIDES 
# goes through all .db file
# and tallies up the total
# nucleotide lengths of all
# combined seq

# basic start to a more
# general function for
# determine lengths of
# sets of seqs
#############################


# Usage:  &total_nuc_in_database(@files);

sub total_nuc_in_database {
	# get the list of files
	@files = @_;
	# declare local variables
	my $seq_len = undef;
	my $search_query = undef;
	my $file = undef;
	# loop over them to get the sequence out of each
	# send and list of file names in the array!
	# @files = ("SBW0002.db", "SBW0003.db");
	# by default @files is all .db files in the directory
        foreach $file (@files) {
	        # open the file to restore the query
	        open (IN, $file) || die "can't open the file $file";
	        $search_query = new CGI(IN);
	        # get the sequence from the file
	        $seq = $search_query->param('seq');
		# get the length
		$seq_len = length $seq;
		if ($debug) { print "$seq_len<P>";}
		# add it to the total length
		$total_len += $seq_len;
		$seq_len = undef;
        }  # end foreach $file (@files)
}