import org.forester.phylogeny.data.Identifier;
import org.forester.phylogeny.data.Sequence;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
+import org.forester.sequence.MolecularSequence.TYPE;
import org.forester.util.BasicTable;
import org.forester.util.BasicTableParser;
import org.forester.util.ForesterUtil;
public static void decorate( final Phylogeny phylogeny,
final Map<String, Map<String, String>> map,
- final boolean picky ) throws IllegalArgumentException, PhyloXmlDataFormatException {
+ final boolean picky )
+ throws IllegalArgumentException, PhyloXmlDataFormatException {
for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
final String name = node.getName();
if ( new_values.containsKey( TP_TAXONOMY_ID )
&& new_values.containsKey( TP_TAXONOMY_ID_PROVIDER ) ) {
ForesterUtil.ensurePresenceOfTaxonomy( node );
- node.getNodeData()
- .getTaxonomy()
+ node.getNodeData().getTaxonomy()
.setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ),
new_values.get( TP_TAXONOMY_ID_PROVIDER ) ) );
}
if ( new_values.containsKey( TP_SEQ_ACCESSION )
&& new_values.containsKey( TP_SEQ_ACCESSION_SOURCE ) ) {
ForesterUtil.ensurePresenceOfSequence( node );
- node.getNodeData()
- .getSequence()
+ node.getNodeData().getSequence()
.setAccession( new Accession( new_values.get( TP_SEQ_ACCESSION ),
new_values.get( TP_SEQ_ACCESSION_SOURCE ) ) );
}
if ( new_values.containsKey( TP_NODE_NAME ) ) {
node.setName( new_values.get( TP_NODE_NAME ) );
}
- } // if ( new_values != null )
+ } // if ( new_values != null )
} // if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) )
else if ( picky ) {
throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
final boolean picky,
final boolean cut_name_after_space,
final boolean trim_after_tilde,
- final boolean verbose ) throws IllegalArgumentException, NHXFormatException,
- PhyloXmlDataFormatException {
+ final boolean verbose )
+ throws IllegalArgumentException, NHXFormatException, PhyloXmlDataFormatException {
return PhylogenyDecorator.decorate( phylogeny,
map,
field,
}
/**
- *
- *
- *
+ *
+ *
+ *
* @param phylogeny
* @param map
* maps names (in phylogeny) to new values if intermediate_map is
* @param intermediate_map
* maps name (in phylogeny) to a intermediate value
* @throws IllegalArgumentException
- * @throws PhyloXmlDataFormatException
+ * @throws PhyloXmlDataFormatException
*/
public static String decorate( final Phylogeny phylogeny,
final Map<String, String> map,
final Map<String, String> intermediate_map,
final boolean cut_name_after_space,
final boolean trim_after_tilde,
- final boolean verbose ) throws IllegalArgumentException, PhyloXmlDataFormatException {
+ final boolean verbose )
+ throws IllegalArgumentException, PhyloXmlDataFormatException {
if ( extract_bracketed_scientific_name && ( field == FIELD.TAXONOMY_SCIENTIFIC_NAME ) ) {
throw new IllegalArgumentException( "attempt to extract bracketed scientific name together with data field pointing to scientific name" );
}
if ( map.isEmpty() ) {
throw new IllegalArgumentException( "map is empty" );
}
- if ( picky && ( map.size() < phylogeny.getNumberOfExternalNodes() ) ) {
- throw new IllegalArgumentException( "map contains less entries than the tree has external nodes" );
- }
int ext_nodes = 0;
int ext_nodes_updated = 0;
int int_nodes = 0;
throw new IllegalArgumentException( "external node with no name present" );
}
String tilde_annotation = null;
+ final String orig_name = name;
if ( trim_after_tilde && ( name.indexOf( '~' ) > 0 ) ) {
final int ti = name.indexOf( '~' );
- final String orig = name;
tilde_annotation = name.substring( ti );
name = name.substring( 0, ti );
if ( node.isExternal() && ForesterUtil.isEmpty( name ) ) {
- throw new IllegalArgumentException( "external node with illegal name: " + orig );
+ throw new IllegalArgumentException( "external node with illegal name: " + orig_name );
}
}
if ( !ForesterUtil.isEmpty( name ) ) {
if ( intermediate_map != null ) {
name = PhylogenyDecorator.extractIntermediate( intermediate_map, name, verbose );
}
+ if ( ( field == FIELD.MOL_SEQ ) && !map.containsKey( name ) ) {
+ name = orig_name;
+ }
if ( map.containsKey( name ) ) {
String new_value = map.get( name ).trim().replaceAll( "/\\s+/", " " );
if ( !ForesterUtil.isEmpty( new_value ) ) {
node.getNodeData().setSequence( new Sequence() );
}
node.getNodeData().getSequence().setMolecularSequence( new_value );
+ final TYPE type = ForesterUtil.guessMolecularSequenceType( new_value );
+ if ( type != null ) {
+ if ( type == TYPE.AA ) {
+ node.getNodeData().getSequence().setType( "protein" );
+ }
+ else if ( type == TYPE.DNA ) {
+ node.getNodeData().getSequence().setType( "dna" );
+ }
+ else if ( type == TYPE.RNA ) {
+ node.getNodeData().getSequence().setType( "rna" );
+ }
+ }
break;
case SEQUENCE_ANNOTATION_DESC:
if ( verbose ) {
throw new IllegalArgumentException( "node name \"" + name + "\" maps to empty value" );
}
}
- else if ( picky ) {
+ else if ( picky && node.isExternal() ) {
throw new IllegalArgumentException( "node name \"" + name + "\" not found in map" );
}
}
}
public static enum FIELD {
- DOMAIN_STRUCTURE,
- MOL_SEQ,
- NODE_NAME,
- SEQUENCE_ANNOTATION_DESC,
- SEQUENCE_NAME,
- TAXONOMY_CODE,
- TAXONOMY_SCIENTIFIC_NAME;
+ DOMAIN_STRUCTURE,
+ MOL_SEQ,
+ NODE_NAME,
+ SEQUENCE_ANNOTATION_DESC,
+ SEQUENCE_NAME,
+ TAXONOMY_CODE,
+ TAXONOMY_SCIENTIFIC_NAME;
}
}