test.java

生物信息学中文件处理的程序是其它软件需求格式的基础

import java.io.*;
import java.util.StringTokenizer;
public class test{
	public static void main(String[] args) throws Exception{
		
		BufferedReader in  = new BufferedReader(new FileReader("e:/chrom_9"));
		BufferedWriter out = new BufferedWriter(new FileWriter("e:/result.arp"));
		String ls = System.getProperty("line.separator");
		String line = "";
		String newline = "";
		String newline1 = "";
		String newline2 = "";
	    String[] strs=new String[39];
	    int linenumber=0;
		
		while((line=in.readLine())!=null){
	    int counter=0;
	    StringTokenizer st = new StringTokenizer(line);
		while (st.hasMoreTokens()) {
		  if(counter==0)
		  strs[counter]= st.nextToken() +" 1 ";
          else
          strs[counter]= st.nextToken();
          counter++;
	     }
	     
	     newline=newline+strs[0];
	     
	     for(int i=1; i<strs.length; i++){
				
				if(i%2==1){
					if(strs[i].equals("-9")){
					strs[i]=" ?";
					newline1+="\t"+strs[i];
					}
					else
					newline1+="\t"+strs[i];
				}
				if(i%2==0){
					if(strs[i].equals("-9")){
					strs[i]=" ?";
					newline2+="\t"+strs[i];
					}
					else
					newline2+="\t"+strs[i];
				}
			}
			linenumber++;
		    newline += newline1 + ls + "         "+ newline2 + ls;
			newline1 = "";
			newline2 = "";
			for(int i=0;i<39;i++){
				strs[i]="";
			}
		}
		
        out.write("#====================================================================#" + ls);
		out.flush();
		out.write("#                 Project file created by eArlequin                  #" + ls);
		out.flush();
		out.write("# Copyleft 2008 Dept. of Bioinformatics of Harbin Medical University #" + ls);
		out.flush();
		out.write("#                      Maintained by Manjusaka                       #" + ls);
		out.flush();
		out.write("#====================================================================#" + ls);
		out.flush();
		out.write(ls);
		out.flush();
		out.write("[Profile]" + ls);
		out.flush();
		out.write("\tNbSamples=1" + ls);
		out.flush();
		out.write("\tDataType=STANDARD  # - {DNA, RFLP, MICROSAT, STANDARD, FREQUENCY}" + ls);
		out.flush();
		out.write("\tGenotypicData=1  # - {0, 1}" + ls);
		out.flush();
		out.write("\tGameticPhase=0  # - {0, 1}" + ls);
		out.flush();
		out.write("\tLocusSeparator=TAB  # - {TAB, WHITESPACE, NONE}" + ls);
		out.flush();
		out.write("\tRecessiveData=0  # - {0, 1}" + ls);
		out.flush();
		out.write("\tMissingData='?'  # A single character specifying missing data" + ls);
		out.flush();
		out.write("#\tSome advanced settings the experienced user can uncomment" + ls);
		out.flush();
		out.write("#\tFrequency= ABS             # - {ABS, REL}" + ls);
		out.flush();
		out.write("#\tFrequencyThreshold= 1.0e-5 # - (Any real number, usually between 1.0e-7 and 1.e-3)" + ls);
		out.flush();
		out.write("#\tEpsilonValue= 1.0e-7       # - (Any real number, usually between 1.0e-12 and 1.0e-5)" + ls);
		out.flush();
		out.write(ls);
		out.flush();
		out.write("[Data]" + ls);
		out.flush();
		out.write(ls);
		out.flush();
		out.write("[[Samples]]" + ls);
		out.flush();
		out.write(ls);
		out.flush();
		out.write("\tSampleName=\"Population number 1\"" + ls);
		out.flush();
		out.write("\tSampleSize=" + linenumber + ls);
		out.flush();
		out.write("\tSampleData={" + ls);
		out.flush();
		out.write(newline);
		out.flush();
		out.write("}" + ls);
		out.flush();
		out.close();
		
	}
	 
}