/*
* BioJava development code
*
* This code may be freely distributed and modified under the
* terms of the GNU Lesser General Public Licence. This should
* be distributed with the code. If you do not have a copy,
* see:
*
* http://www.gnu.org/copyleft/lesser.html
*
* Copyright for this code is held jointly by the individual
* authors. These should be listed in @author doc comments.
*
* For more information on the BioJava project and its aims,
* or to join the biojava-l mailing list, visit the home page
* at:
*
* http://www.biojava.org/
*
* Created on Jun 19, 2008
*
*/
package performance;
import java.io.BufferedInputStream;
import java.io.InputStream;
import java.net.URL;
import java.net.URLConnection;
import java.util.zip.GZIPInputStream;
import org.biojavax.SimpleNamespace;
import org.biojavax.bio.seq.RichSequence;
import org.biojavax.bio.seq.RichSequenceIterator;
/** Demo class that reads all chromosomes of Drosophila and prints out their sizes.
* See http://biojava.org/wiki/BioJava:Performance
*
*
* Uses the quicker biojavax implementation.
*
* @author Andreas Prlic
* @since 1.7
* @date Jun 17, 2008
*/
public class ReadFastaX2 {
public static void main (String[] args){
try {
UserDisplay display = new UserDisplay();
display.setTitle("BioJava performance example - BioJavaX");
display.setVisible(true);
StringBuffer txt = new StringBuffer("");
txt.append( "BioJava performance example
Read all chromosomes of Drosophila and print the length of each using BioJavaX.
");
long start = System.currentTimeMillis();
// setup file input
String fileName = "/dmel-all-chromosome-r5.8.fasta.gz";
URL u = ReadFastaX2.class.getResource(fileName);
System.out.println(u);
txt.append( "reading " + fileName + " (47 MB)");
System.out.println(txt);
display.setText(txt + "");
URLConnection urlc = u.openConnection();
InputStream inStream = urlc.getInputStream();
if (inStream == null){
System.err.println("could not find file " + fileName);
txt.append("could not find file " + fileName);
display.setText(txt + " ");
return;
}
GZIPInputStream gzip = new GZIPInputStream(inStream);
InputStream is = new BufferedInputStream(gzip);
BufferedInputStream bis = new BufferedInputStream(gzip);
SimpleNamespace ns = null;
ns = new SimpleNamespace("biojava");
// You can use any of the convenience methods found in the BioJava 1.6 API
RichSequenceIterator rsi = RichSequence.IOTools.readHashedFastaDNA(bis,ns);
long total = 0;
long maxMem = 0;
// Since a single file can contain more than a sequence, you need to iterate over
// rsi to get the information.
txt .append( "