#! /usr/bin/perl -w
# Script to Create Database files

use strict;


my $output;
my $infile;
my $summary;
my $input = "C:\\Elliott\\Database\\Repository\\";
my $line;
my $wait;
my $linecount = 0;
my @fieldsize;
my @temparray;
my $i;
my @inputfiles = ("gene2accession", "gene2go","gene2sts","gene2unigene","gene2pubmed","gene2refseq","gene_history","gene_info","gene_refseq_uniprotkb_collab","generifs_basic","hiv_interactions","interactions");
$summary = $input."myentrezgenefilesummary.txt";

open (SUMMARY,"> $summary") or die "Cannot open $summary: $!";
print SUMMARY "This file lists the processed files their field and maximum field size\n";
print SUMMARY "This data can be used to determine the varchar field sizes in the novel therapies SQL database\n";

foreach (@inputfiles) {
	$linecount = 0;
	
	#get input and output files and open for reading/writing
	$infile = $input.$_;
	$output = $input.$_.".txt";

		open (INFILE, "< $infile") or die "Cannot open $input: $!";
		open (OUTFILE,"> $output") or die "Cannot open $output: $!";
		print "FILE ", $infile, " OPEN", "\n";
		while ($line = <INFILE>) {
			chomp $line;
			if ($linecount == 0) {
				#if first line print field names
				#print "SUMMARY is".(is_writable_fh(\*SUMMARY)?"":"n't")." writable.\n";
				if ($_ =~ /gene2accession/) {
					print OUTFILE "Taxon\tGeneID\tStatus\tRNA_Nucleotide_Accession\tRNA_Nucleotide_gi\tProtein_Accession\tProtein_gi\tGenomic_Nucleotide_Accession\tGenomic_Nucleotide_gi\tGenomic_Accession_Start_Pos\tGenomic_Accession_End_Pos\tOrientation\tAssembly\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tStatus\tRNA_Nucleotide_Accession\tRNA_Nucleotide_gi\tProtein_Accession\tProtein_gi\tGenomic_Nucleotide_Accession\tGenomic_Nucleotide_gi\tGenomic_Accession_Start_Pos\tGenomic_Accession_End_Pos\tOrientation\tAssembly\n";
				}
				elsif ($_ =~ /gene2go/){
					print OUTFILE "Taxon\tGeneID\tGO_ID\tEvidence\tQualifier\tGO_term\tPubMedID\tCategory\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tGO_ID\tEvidence\tQualifier\tGO_term\tPubMedID\tCategory\n";
				}
				elsif ($_ =~ /gene2pubmed/){
					print OUTFILE "Taxon\tGeneID\tPubMedID\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tPubMedID\n";
				}
				elsif ($_ =~ /gene2refseq/){
					print OUTFILE "Taxon\tGeneID\tStatus\tRNA_Nucleotide_Accession\tRNA_Nucleotide_gi\tProtein_Accession\tProtein_gi\tGenomic_Nucleotide_Accession\tGenomic_Nucleotide_gi\tGenomic_Accession_Start_Pos\tGenomic_Accession_End_Pos\tOrientation\tAssembly\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tStatus\tRNA_Nucleotide_Accession\tRNA_Nucleotide_gi\tProtein_Accession\tProtein_gi\tGenomic_Nucleotide_Accession\tGenomic_Nucleotide_gi\tGenomic_Accession_Start_Pos\tGenomic_Accession_End_Pos\tOrientation\tAssembly\n";
				}
				elsif ($_ =~ /gene2sts/){
					print OUTFILE "GeneID\tUniSTSID\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "GeneID\tUniSTSID\n";
				}
				elsif ($_ =~ /gene2unigene/){
					print OUTFILE "GeneID\tUnigeneUD\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "GeneID\tUnigeneUD\n";
				}
				elsif ($_ =~ /gene_history/){
					print OUTFILE "Taxon\tGeneID\tDiscontinued_GeneID\tDiscontinued_Symbol\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tDiscontinued_GeneID\tDiscontinued_Symbol\n";
				}
				elsif ($_ =~ /gene_info/){
					print OUTFILE "Taxon\tGeneID\tSymbol\tLocusTag\tSynonyms\tdbXrefs\tChromosome\tMap_Location\tDescription\tType_Of_Gene\tSymbol_From_Nomenclature_Authority\tFull_Name_From_Nomenclature_Authority\tNomenclature_Status\tOther_Designations\tModification_Date\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tSymbol\tLocusTag\tSynonyms\tdbXrefs\tChromosome\tMap_Location\tDescription\tType_Of_Gene\tSymbol_From_Nomenclature_Authority\tFull_Name_From_Nomenclature_Authority\tNomenclature_Status\tOther_Designations\tModification_Date\n";
				}
				elsif ($_ =~ /gene_refseq_uniprotkb_collab/){
					print OUTFILE "NCBI_Protein_Accession\tUniProtKB_Protein_Accession\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "NCBI_Protein_Accession\tUniProtKB_Protein_Accession\n";
				}
				elsif ($_ =~ /generifs_basic/){
					print OUTFILE "Taxon\tGeneID\tPubMedID\tLastUpdate\tGeneRIFText\n";
					print OUTFILE "$line\n";
					# no header row in file get field for comparison
					@fieldsize = split(/\t/, $line);
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tPubMedID\tLastUpdate\tGeneRIFText\n";
				}
				elsif ($_ =~ /hiv_interactions/){
					print OUTFILE "Taxon\tGeneID\tProductAccession\tProductName\tInteractionShortName\tInteractorTaxon\tInteractorGeneID\tInteractorProdictAccession\tInteractorProductName\tPubMedID\tLastUpdate\tGeneRIFText\n";				
					print OUTFILE "$line\n";
					# no header row in file get field for comparison
					@fieldsize = split(/\t/, $line);
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tProductAccession\tProductName\tInteractionShortName\tInteractorTaxon\tInteractorGeneID\tInteractorProdictAccession\tInteractorProductName\tPubMedID\tLastUpdate\tGeneRIFText\n";
				}
				elsif ($_ =~ /interactions/){
					print OUTFILE "Taxon\tGeneID\tProteinAccession\tGeneName\tKeyPhrase\tInteractorTaxon\tInteractorGeneID\tInteractionType\tInteractorProductAccession\tInteractorProductName\tComplexID\tComplexIDType\tComplexName\tPubMedID\tLastUpdate\tGeneRIFText\tInteractionID\tInteractionIDType\n";
					print SUMMARY "Field lengths for file $_\n";
					print SUMMARY "Taxon\tGeneID\tProteinAccession\tGeneName\tKeyPhrase\tInteractorTaxon\tInteractorGeneID\tInteractionType\tInteractorProductAccession\tInteractorProductName\tComplexID\tComplexIDType\tComplexName\tPubMedID\tLastUpdate\tGeneRIFText\tInteractionID\tInteractionIDType\n";
				}
				else {
					print "Header line for this input file not definaed please contact system administator.\n";
					exit;
				}
				$linecount = 1;
			}
			else {
				#print line of data to outfile
				print OUTFILE "$line\n";
				
				#get fields to test size against existing.
				@temparray = split(/\t/, $line);
				
				# if elements in array test new values to see if larger than existing.
				if (@fieldsize > 0) {
					#test the field in the line to see if larger than previous and replace field size value if so.
					for($i=0; $i<@temparray; $i++) {				
						if (length($fieldsize[$i]) < length($temparray[$i])) {
							$fieldsize[$i] = $temparray[$i];
						}
					}
				}
				#set fields array
				else {
					@fieldsize = split(/\t/, $line);
				}
			}

		}		
		#print "SUMMARY is".(is_writable_fh(\*SUMMARY)?"":"n't")." writable.\n";
		
		#print summary field size information to summary file
		foreach(@fieldsize) {
			print SUMMARY length($_), "\t";
		}
		print SUMMARY "\n\n";
		@fieldsize = ();
		print "FINSHED PROCESSING ", $infile, "\n";
		$linecount =0;
		close INFILE;
		close OUTFILE;
		
}
close SUMMARY;


sub is_writable_fh
{
  my($fh)=@_;
  local $\='';
  return print $fh '';
}