import java.io.FileWriter;
import java.io.IOException;
import java.util.SortedSet;
+import java.util.TreeSet;
import org.forester.archaeopteryx.tools.SequenceDataRetriver;
import org.forester.io.parsers.util.ParserUtils;
import org.forester.io.writers.PhylogenyWriter;
import org.forester.phylogeny.Phylogeny;
-import org.forester.phylogeny.PhylogenyMethods;
+import org.forester.phylogeny.PhylogenyNode;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
+import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
import org.forester.util.CommandLineArguments;
import org.forester.util.ForesterUtil;
final static private String HELP_OPTION_2 = "h";
final static private String PRG_NAME = "gene_tree_preprocess";
final static private String PRG_DESC = "gene tree preprocessing for SDI analysis";
- final static private String PRG_VERSION = "1.00";
+ final static private String PRG_VERSION = "1.01";
final static private String PRG_DATE = "2012.06.07";
final static private String E_MAIL = "phylosoft@gmail.com";
- final static private String WWW = "www.phylosoft.org/forester/";
+ final static private String WWW = "www.phylosoft.org/forester";
public static void main( final String[] args ) {
try {
}
catch ( final IOException e ) {
ForesterUtil.fatalError( PRG_NAME,
- "failed to read phylogeny from [" + in + "]: "
- + e.getLocalizedMessage() );
+ "failed to read phylogeny from [" + in + "]: " + e.getLocalizedMessage() );
}
final File outtree = new File( ForesterUtil.removeSuffix( in.toString() )
+ "_preprocessed_gene_tree.phylo.xml" );
final File removed_nodes = new File( ForesterUtil.removeSuffix( in.toString() ) + "_removed_nodes.txt" );
+ final File present_species = new File( ForesterUtil.removeSuffix( in.toString() ) + "_species_present.txt" );
checkForOutputFileWriteability( outtree );
checkForOutputFileWriteability( removed_nodes );
+ checkForOutputFileWriteability( present_species );
if ( phy.getNumberOfExternalNodes() < 2 ) {
ForesterUtil.fatalError( PRG_NAME, "phylogeny has " + phy.getNumberOfExternalNodes()
+ " external node(s), aborting" );
}
- final SortedSet<String> not_found = SequenceDataRetriver.obtainSeqInformation( phy, true );
+ final SortedSet<String> not_found = SequenceDataRetriver.obtainSeqInformation( phy, true, false );
for( final String remove_me : not_found ) {
- System.out.println( " not found: " + remove_me );
- PhylogenyMethods.removeNode( phy.getNode( remove_me ), phy );
+ phy.deleteSubtree( phy.getNode( remove_me ), true );
}
+ phy.clearHashIdToNodeMap();
+ phy.externalNodesHaveChanged();
if ( phy.getNumberOfExternalNodes() < 2 ) {
ForesterUtil.fatalError( PRG_NAME,
"after removal of unresolvable external nodes, phylogeny has "
ForesterUtil.fatalError( PRG_NAME, "failed to write to [" + outtree + "]: " + e.getLocalizedMessage() );
}
ForesterUtil.programMessage( PRG_NAME, "wrote output phylogeny to: " + outtree );
+ final SortedSet<String> species_set = new TreeSet<String>();
+ for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
+ final PhylogenyNode node = iter.next();
+ if ( node.getNodeData().isHasTaxonomy() ) {
+ final String sn = node.getNodeData().getTaxonomy().getScientificName();
+ if ( !ForesterUtil.isEmpty( sn ) ) {
+ species_set.add( sn );
+ }
+ }
+ }
+ try {
+ final BufferedWriter out = new BufferedWriter( new FileWriter( present_species ) );
+ for( final String species : species_set ) {
+ out.write( species );
+ out.newLine();
+ }
+ out.close();
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( PRG_NAME,
+ "failed to write to [" + present_species + "]: " + e.getLocalizedMessage() );
+ }
+ ForesterUtil.programMessage( PRG_NAME, "wrote present species to: " + present_species );
try {
final BufferedWriter out = new BufferedWriter( new FileWriter( removed_nodes ) );
for( final String remove_me : not_found ) {