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" );
+ }
for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
String name = node.getName();
if ( extract_bracketed_scientific_name && new_value.endsWith( "]" ) ) {
new_value = extractBracketedScientificNames( node, new_value );
}
- else if ( extract_bracketed_tax_code
- && ParserUtils.TAXOMONY_CODE_PATTERN_4.matcher( new_value ).matches() ) {
- new_value = extractBracketedTaxCodes( node, new_value );
+ else if ( extract_bracketed_tax_code ) {
+ if ( ParserUtils.TAXOMONY_CODE_PATTERN_4.matcher( new_value ).find() ) {
+ new_value = extractBracketedTaxCodes( node, new_value );
+ }
+ else if ( ParserUtils.TAXOMONY_CODE_PATTERN_6.matcher( new_value ).find() ) {
+ new_value = extractBracketedTaxCodes6( node, new_value );
+ }
+ else if ( picky ) {
+ throw new IllegalArgumentException( " could not get taxonomy from \"" + new_value
+ + "\"" );
+ }
}
switch ( field ) {
case SEQUENCE_ANNOTATION_DESC:
if ( !node.getNodeData().isHasSequence() ) {
node.getNodeData().setSequence( new Sequence() );
}
- final Annotation annotation = new Annotation( "?" );
+ final Annotation annotation = new Annotation();
annotation.setDesc( new_value );
node.getNodeData().getSequence().addAnnotation( annotation );
break;
throws IOException {
final Map<String, Map<String, String>> map = new HashMap<String, Map<String, String>>();
BasicTable<String> mapping_table = null;
- mapping_table = BasicTableParser.parse( mapping_table_file, "\t", false, false );
+ mapping_table = BasicTableParser.parse( mapping_table_file, '\t', false, false );
for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
final Map<String, String> row_map = new HashMap<String, String>();
String name = null;
private static String extractBracketedTaxCodes( final PhylogenyNode node, final String new_value ) {
final Matcher m = ParserUtils.TAXOMONY_CODE_PATTERN_4.matcher( new_value );
- String tc = null;
- if ( m.matches() ) {
+ String tc = "?";
+ if ( m.find() ) {
tc = m.group( 1 );
}
ForesterUtil.ensurePresenceOfTaxonomy( node );
return new_value; //TODO //FIXME
}
+ private static String extractBracketedTaxCodes6( final PhylogenyNode node, final String new_value ) {
+ final Matcher m = ParserUtils.TAXOMONY_CODE_PATTERN_6.matcher( new_value );
+ String tc = "?";
+ if ( m.find() ) {
+ tc = m.group( 1 );
+ }
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
+ try {
+ if ( tc.length() == 6 ) {
+ final String t = tc.substring( 0, 5 );
+ System.out.println( "WARNING: taxonomy code " + tc + " -> " + t );
+ tc = t;
+ }
+ else {
+ throw new IllegalArgumentException();
+ }
+ node.getNodeData().getTaxonomy().setTaxonomyCode( tc );
+ }
+ catch ( final PhyloXmlDataFormatException e ) {
+ throw new IllegalArgumentException( "illegal format for taxonomy code: " + tc );
+ }
+ return new_value; //TODO //FIXME
+ }
+
private static String extractIntermediate( final Map<String, String> intermediate_map, final String name ) {
String new_name = null;
if ( PhylogenyDecorator.VERBOSE ) {