package TechnicalReplicates;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.FileWriter;
import java.text.DecimalFormat;
import java.text.NumberFormat;
import java.util.Arrays;
import java.util.Hashtable;

import GTF_annotation.UCSCGene;

import net.sf.samtools.SAMFileHeader;
import net.sf.samtools.SAMFileHeader.SortOrder;
import net.sf.samtools.SAMFileReader;
import net.sf.samtools.SAMFileWriter;
import net.sf.samtools.SAMFileWriterFactory;
import net.sf.samtools.SAMRecord;
import net.sf.samtools.SAMRecordIterator;

public class splitTechnRep_confiBand 
{
	private static String outFile1;
	private static String prefixBam;
	private static String hashFile;
	private static String samOrBamFile;
	private static SAMFileWriter obam1;
	private static SAMFileWriter obam2;
	private static long readLimit;
	private static int[][] hashMatrix;
	private static String ending;
	private static SAMRecord[] shuffle;
	private static Hashtable<String, UCSCGene> gene_tab;
	
	private static NumberFormat f = new DecimalFormat("000");
	/**
	 * @param args
	 * @throws Exception 
	 */
	public static void main(String[] args) 
	{
		System.out.println(Arrays.toString(args));
		//parameter input
		if(args.length != 11){
			System.out.println("java -jar program.jar samOrBamFile hashFile endingHash outFile prefixBam ucsc_ref ofname prefixExonCount repeating start end");
			System.exit(-1);
		}
		samOrBamFile = args[0];
		hashFile = args[1];
		ending = args[2];
		//check files existence 
		try{
			File f = new File(samOrBamFile);
			if(!f.exists()) 
				throw new FileNotFoundException("SAM or BAM file missing.");
		}catch(Exception e){e.printStackTrace(); System.exit(-1);}
		outFile1 = args[3];
		prefixBam = args[4];
		
		// initial parameters
		String ucsc_ref = args[5];
		String ofname1 = args[6];
		String prefixExonCount = args[7];
		int repeatings = Integer.parseInt(args[8]);
		int start = Integer.parseInt(args[9]);
		int end = Integer.parseInt(args[10]);
		
		try {
			System.out.println("Readin hash matrix");
			
			//readin organism information
			System.out.println("Readin genome annotation");
			gene_tab = UCSCGene.makeGeneList(ucsc_ref);
			System.out.println("Run simulation");
			System.out.print("Simulating the following read amounts: ");
			long[] readAmount = {3000000, 4000000, 6000000, 7000000, 8000000, 9000000};
			for(long l : readAmount)
				System.out.print(l +"\t");
			System.out.println();
			// ~ start repeated simulation
			for(int k=start; k<=end;k++){
				System.out.println("hash: "+ k);
				File f = new File(hashFile+k+"."+ending);
				if(!f.exists()) 
					throw new FileNotFoundException("Hash file missing.");
				readHash(k, ending);
				for(int j=0; j<repeatings; j++)
				{
					//shuffle reads
					System.out.println(j);
					splitTechnRep_confiBand.shuffle(j);
					for(int i = 0; i<readAmount.length; i++)
					{
						readLimit = readAmount[i];
						//split files according read count
						splitTechnRep_confiBand.split((outFile1+"/"+k+"/"+prefixBam+ ".1.V" + (j + 1)+ ".RL" + readLimit + ".bam"), (outFile1+"/"+k+"/"+prefixBam+ ".2.V" + (j + 1)+ ".RL" + readLimit + ".bam"));
						//exon counts and delete bam file
						exonCount(ucsc_ref, (outFile1+"/"+k+"/" +prefixBam+ ".1.V" + (j + 1)+ ".RL" + readLimit + ".bam"), (ofname1+"/"+k+"/" +prefixExonCount+ ".1.V" + (j + 1)+ ".RL" + readLimit + ".txt"));
						delete( (outFile1+"/"+k+"/" +prefixBam+ ".1.V" + (j + 1)+ ".RL" + readLimit + ".bam") );
						exonCount(ucsc_ref, (outFile1+"/"+k+"/" +prefixBam+ ".2.V" + (j + 1)+ ".RL" + readLimit + ".bam"), (ofname1+"/"+k+"/" +prefixExonCount+ ".2.V" + (j + 1)+ ".RL" + readLimit + ".txt"));
						delete( (outFile1+"/"+k+"/" +prefixBam+ ".2.V" + (j + 1)+ ".RL" + readLimit + ".bam") );
					}	
				}// ~end repeated simulation
			}		
		} catch (Exception e) { e.printStackTrace(); System.exit(-1); }
	}
	
	private static void shuffle(int j){
		// readers and writers
		SAMFileReader ibam = new SAMFileReader(new File(samOrBamFile));
		// shuffle alignment file
		shuffle = new SAMRecord[hashMatrix.length];
		int index = 0;
		for (SAMRecord rec : ibam) 
			shuffle[hashMatrix[index++][j]] = rec;
		ibam.close();
	}
	
	private static void split(String fileName1, String fileName2) throws Exception 
	{
		// readers and writers
		SAMFileReader ibam = new SAMFileReader(new File(samOrBamFile));
		SAMFileHeader header = ibam.getFileHeader();
		// sort order will be coordinate sorted
		header.setSortOrder(SortOrder.coordinate);
		/*
		 * SAMFileWriter
		 * net::sf::samtools::SAMFileWriterFactory::makeSAMOrBAMWriter ( final
		 * SAMFileHeader header, final boolean presorted, final File outputFile
		 * )
		 */
		obam1 = new SAMFileWriterFactory().setCreateIndex(true).makeSAMOrBAMWriter(header, false, new File(fileName1));
		obam2 = new SAMFileWriterFactory().setCreateIndex(true).makeSAMOrBAMWriter(header, false, new File(fileName2));
		/*
		 * split file into readLimit sized portions output will be coordinate
		 * sorted (header.setSortOrder(SortOrder.coordinate)) and indexed
		 * (setCreateIndex(true))
		 */
		for (int k = 0; k < 2 * readLimit; k++) {
			if (k % 2 == 0)
				obam1.addAlignment(shuffle[k]);
			else
				obam2.addAlignment(shuffle[k]);
		}
		obam1.close();
		obam2.close();
	}
	
	private static int[] toIntArray(int ncol, String[] indeces)
	{
		int[] h = new int[ncol];
		for(int i=0;i<ncol;i++)
			h[i] = Integer.parseInt(indeces[i]) - 1;  //hash index starts at 1 to number of reads in seq file >> - 1 for index start at 0
		return h;
	}
	
	private static void readHash(int subfile, String ending) throws Exception
	{
		//count lines and columns
		BufferedReader readerHash = new BufferedReader(new FileReader(new File(hashFile+subfile+"."+ending)));
		int countLines = 1;
		String line = readerHash.readLine();
		int countColumns = line.split("\t").length; 
		while( (line = readerHash.readLine()) != null) 
			countLines++;
		readerHash.close();
		System.out.println("Lines = " + countLines + "\tcolumns = " + countColumns);
		hashMatrix = new int[countLines][countColumns];
		
		//readin hash file as matrix
		readerHash = new BufferedReader(new FileReader(new File(hashFile+subfile+"."+ending)));
		line = "";
		int i = 0;
		while( (line = readerHash.readLine()) != null)
			hashMatrix[i++] = toIntArray(countColumns, line.split("\t"));
		readerHash.close();
	}
	
	private static void exonCount(String ucsc_ref, String sam_file, String ofname) throws Exception
	{
		// Find counts per exon
		SAMFileReader ibam = new SAMFileReader(new File(sam_file));
		BufferedWriter obuf = new BufferedWriter(new FileWriter(new File(ofname)));
		for (String gname : gene_tab.keySet()) {
			UCSCGene gene = gene_tab.get(gname);
			int exonId =0;
			for (GTF_annotation.GenomeInterval uexon : gene.getExonList()) 
			{
				long read_cnt = 0;
				String chr = gene.getChr();
				SAMRecordIterator itr = ibam.query(chr, uexon.getStart(), uexon.getEnd(), true);
				while (itr.hasNext() ){
					read_cnt++;
					itr.next();
				}
				itr.close();
				obuf.write(chr +"|"+ gene.getName2() + "|" + f.format(exonId++) + "\t" + read_cnt + "\n");
			}
		}
		obuf.close();
		ibam.close();	
	}
	
	private static void exonCountDmel(String ucsc_ref, String sam_file, String ofname) throws Exception
	{
		//readin organism information
		Hashtable<String, UCSCGene> gene_tab = UCSCGene.makeGeneList(ucsc_ref);
		
		// Find counts per exon
		SAMFileReader ibam = new SAMFileReader(new File(sam_file));
		BufferedWriter obuf = new BufferedWriter(new FileWriter(ofname));
		for (String gname : gene_tab.keySet()) {
			UCSCGene gene = gene_tab.get(gname);
			int exonId =0;
			for (GTF_annotation.GenomeInterval uexon : gene.getExonList()) 
			{
				long read_cnt = 0;
				String chr = gene.getChr();
				if(chr.contains("chrom"))
					chr = "Uextra";
				else if(chr.contains("chrM"))
					chr = "dmel_mitochondrion_genome";
				else
					chr = chr.replace("chr", "");
				
				SAMRecordIterator itr = ibam.query(chr, uexon.getStart(), uexon.getEnd(), true);
				while ((itr.hasNext())) 
				{
					read_cnt++;
					itr.next();
				}
				itr.close();
				exonId++;
				obuf.write(chr +"|"+ gene.getName2() + "|" + f.format(exonId) + "\t" + read_cnt + "\n");
			}
		}
		obuf.close();
		ibam.close();	
	}
	
	private static void delete(String split_sam_file)
	{
		File f = new File(split_sam_file);
		f.delete();
		f = new File(split_sam_file.replace("bam", "bai"));
		f.delete();
		f = null;
	}
}