// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
//
// Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
package org.forester.tools;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
-import java.util.regex.Pattern;
+import java.util.regex.Matcher;
-import org.forester.archaeopteryx.AptxUtil;
import org.forester.io.parsers.nhx.NHXFormatException;
import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
+import org.forester.io.parsers.util.ParserUtils;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyNode;
import org.forester.phylogeny.data.Accession;
public final class PhylogenyDecorator {
// From evoruby/lib/evo/apps/tseq_taxonomy_processor.rb:
- final private static String TP_TAXONOMY_CODE = "TAXONOMY_CODE";
- final private static String TP_TAXONOMY_ID = "TAXONOMY_ID";
- final private static String TP_TAXONOMY_ID_PROVIDER = "TAXONOMY_ID_PROVIDER";
- final private static String TP_TAXONOMY_SN = "TAXONOMY_SN";
- final private static String TP_TAXONOMY_CN = "TAXONOMY_CN";
- final private static String TP_TAXONOMY_SYN = "TAXONOMY_SYN";
- final private static String TP_SEQ_SYMBOL = "SEQ_SYMBOL";
- final private static String TP_SEQ_ACCESSION = "SEQ_ACCESSION";
- final private static String TP_SEQ_ACCESSION_SOURCE = "SEQ_ACCESSION_SOURCE";
- final private static String TP_SEQ_ANNOTATION_DESC = "SEQ_ANNOTATION_DESC";
- final private static String TP_SEQ_ANNOTATION_REF = "SEQ_ANNOTATION_REF";
- final private static String TP_SEQ_MOL_SEQ = "SEQ_MOL_SEQ";
- final private static String TP_SEQ_NAME = "SEQ_NAME";
- final private static String TP_NODE_NAME = "NODE_NAME";
- final private static Pattern NODENAME_SEQNUMBER_TAXDOMAINNUMBER = Pattern
- .compile( "^([a-fA-Z0-9]{1,5})_([A-Z0-9]{2,4}[A-Z])(\\d{1,4})$" );
- public final static boolean SANITIZE = false;
- public final static boolean VERBOSE = true;
- private static final boolean CUT = true;
+ final private static String TP_TAXONOMY_CODE = "TAXONOMY_CODE";
+ final private static String TP_TAXONOMY_ID = "TAXONOMY_ID";
+ final private static String TP_TAXONOMY_ID_PROVIDER = "TAXONOMY_ID_PROVIDER";
+ final private static String TP_TAXONOMY_SN = "TAXONOMY_SN";
+ final private static String TP_TAXONOMY_CN = "TAXONOMY_CN";
+ final private static String TP_TAXONOMY_SYN = "TAXONOMY_SYN";
+ final private static String TP_SEQ_SYMBOL = "SEQ_SYMBOL";
+ final private static String TP_SEQ_ACCESSION = "SEQ_ACCESSION";
+ final private static String TP_SEQ_ACCESSION_SOURCE = "SEQ_ACCESSION_SOURCE";
+ final private static String TP_SEQ_ANNOTATION_DESC = "SEQ_ANNOTATION_DESC";
+ final private static String TP_SEQ_ANNOTATION_REF = "SEQ_ANNOTATION_REF";
+ final private static String TP_SEQ_MOL_SEQ = "SEQ_MOL_SEQ";
+ final private static String TP_SEQ_NAME = "SEQ_NAME";
+ final private static String TP_NODE_NAME = "NODE_NAME";
+ public final static boolean SANITIZE = false;
+ public final static boolean VERBOSE = true;
private PhylogenyDecorator() {
// Not needed.
}
if ( new_values != null ) {
if ( new_values.containsKey( TP_TAXONOMY_CODE ) ) {
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().setTaxonomyCode( new_values.get( TP_TAXONOMY_CODE ) );
}
if ( new_values.containsKey( TP_TAXONOMY_ID )
&& new_values.containsKey( TP_TAXONOMY_ID_PROVIDER ) ) {
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData()
.getTaxonomy()
.setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ),
new_values.get( TP_TAXONOMY_ID_PROVIDER ) ) );
}
else if ( new_values.containsKey( TP_TAXONOMY_ID ) ) {
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy()
.setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ) ) );
}
if ( new_values.containsKey( TP_TAXONOMY_SN ) ) {
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().setScientificName( new_values.get( TP_TAXONOMY_SN ) );
}
if ( new_values.containsKey( TP_TAXONOMY_CN ) ) {
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().setCommonName( new_values.get( TP_TAXONOMY_CN ) );
}
if ( new_values.containsKey( TP_TAXONOMY_SYN ) ) {
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().getSynonyms().add( new_values.get( TP_TAXONOMY_SYN ) );
}
if ( new_values.containsKey( TP_SEQ_ACCESSION )
&& new_values.containsKey( TP_SEQ_ACCESSION_SOURCE ) ) {
- AptxUtil.ensurePresenceOfSequence( node );
+ ForesterUtil.ensurePresenceOfSequence( node );
node.getNodeData()
.getSequence()
.setAccession( new Accession( new_values.get( TP_SEQ_ACCESSION ),
new_values.get( TP_SEQ_ACCESSION_SOURCE ) ) );
}
if ( new_values.containsKey( TP_SEQ_ANNOTATION_DESC ) ) {
- AptxUtil.ensurePresenceOfSequence( node );
- final Annotation ann = new Annotation( "?" );
+ ForesterUtil.ensurePresenceOfSequence( node );
+ final Annotation ann = new Annotation();
ann.setDesc( new_values.get( TP_SEQ_ANNOTATION_DESC ) );
node.getNodeData().getSequence().addAnnotation( ann );
}
if ( new_values.containsKey( TP_SEQ_ANNOTATION_REF ) ) {
- AptxUtil.ensurePresenceOfSequence( node );
+ ForesterUtil.ensurePresenceOfSequence( node );
final Annotation ann = new Annotation( new_values.get( TP_SEQ_ANNOTATION_REF ) );
node.getNodeData().getSequence().addAnnotation( ann );
}
if ( new_values.containsKey( TP_SEQ_SYMBOL ) ) {
- AptxUtil.ensurePresenceOfSequence( node );
+ ForesterUtil.ensurePresenceOfSequence( node );
node.getNodeData().getSequence().setSymbol( new_values.get( TP_SEQ_SYMBOL ) );
}
if ( new_values.containsKey( TP_SEQ_NAME ) ) {
- AptxUtil.ensurePresenceOfSequence( node );
+ ForesterUtil.ensurePresenceOfSequence( node );
node.getNodeData().getSequence().setName( new_values.get( TP_SEQ_NAME ) );
}
if ( new_values.containsKey( TP_SEQ_MOL_SEQ ) ) {
- AptxUtil.ensurePresenceOfSequence( node );
+ ForesterUtil.ensurePresenceOfSequence( node );
node.getNodeData().getSequence().setMolecularSequence( new_values.get( TP_SEQ_MOL_SEQ ) );
}
if ( new_values.containsKey( TP_NODE_NAME ) ) {
}
}
- /**
- *
- *
- *
- *
- *
- * @param phylogeny
- * @param map
- * maps names (in phylogeny) to new values
- * @param field
- * @param picky
- * @throws IllegalArgumentException
- * @throws NHXFormatException
- * @throws PhyloXmlDataFormatException
- */
public static void decorate( final Phylogeny phylogeny,
final Map<String, String> map,
final FIELD field,
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();
+ String tilde_annotation = null;
if ( trim_after_tilde && ( name.indexOf( '~' ) > 0 ) ) {
- name = name.substring( 0, name.indexOf( '~' ) );
+ final int ti = name.indexOf( '~' );
+ tilde_annotation = name.substring( ti );
+ name = name.substring( 0, ti );
}
if ( !ForesterUtil.isEmpty( name ) ) {
if ( intermediate_map != null ) {
name = PhylogenyDecorator.extractIntermediate( intermediate_map, name );
}
- // int space_index = name.indexOf( " " );
- // if ( CUT && space_index > 0 ) {
- // int y = name.lastIndexOf( "|" );
- // name = name.substring( y + 1, space_index );
- // }
- // String new_value = null;
- // for( String key : map.keySet() ) {
- // if ( key.indexOf( name ) >= 0 ) {
- // if ( new_value == null ) {
- // new_value = map.get( key );
- // }
- // else {
- // System.out.println( name + " is not unique" );
- // System.exit( -1 );
- // }
- // }
- // }
- // if ( new_value != null ) {
if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) ) {
String new_value = map.get( name );
int x = 0;
if ( extract_bracketed_scientific_name && new_value.endsWith( "]" ) ) {
new_value = extractBracketedScientificNames( node, new_value );
}
- else if ( extract_bracketed_tax_code && new_value.endsWith( "]" ) ) {
- 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;
if ( PhylogenyDecorator.VERBOSE ) {
System.out.println( name + ": " + new_value );
}
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().setTaxonomyCode( new_value );
break;
case TAXONOMY_SCIENTIFIC_NAME:
if ( PhylogenyDecorator.VERBOSE ) {
System.out.println( name + ": " + new_value );
}
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().setScientificName( new_value );
break;
case SEQUENCE_NAME:
+ if ( trim_after_tilde ) {
+ new_value = addTildeAnnotation( tilde_annotation, new_value );
+ }
if ( PhylogenyDecorator.VERBOSE ) {
System.out.println( name + ": " + new_value );
}
if ( PhylogenyDecorator.SANITIZE ) {
new_value = PhylogenyDecorator.sanitize( new_value );
}
+ if ( trim_after_tilde ) {
+ new_value = addTildeAnnotation( tilde_annotation, new_value );
+ }
if ( PhylogenyDecorator.VERBOSE ) {
System.out.println( new_value );
}
}
}
+ private final static String addTildeAnnotation( final String tilde_annotation, final String new_value ) {
+ if ( ForesterUtil.isEmpty( tilde_annotation ) ) {
+ return new_value;
+ }
+ return new_value + tilde_annotation;
+ }
+
public static void decorate( final Phylogeny[] phylogenies,
final Map<String, Map<String, String>> map,
final boolean picky,
}
}
+ public static Map<String, Map<String, String>> parseMappingTable( final File mapping_table_file )
+ 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 );
+ for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
+ final Map<String, String> row_map = new HashMap<String, String>();
+ String name = null;
+ for( int col = 0; col < mapping_table.getNumberOfColumns(); ++col ) {
+ final String table_cell = mapping_table.getValue( col, row );
+ if ( col == 0 ) {
+ name = table_cell;
+ }
+ else if ( table_cell != null ) {
+ final String key = table_cell.substring( 0, table_cell.indexOf( ':' ) );
+ final String val = table_cell.substring( table_cell.indexOf( ':' ) + 1, table_cell.length() );
+ row_map.put( key, val );
+ }
+ }
+ map.put( name, row_map );
+ }
+ return map;
+ }
+
private static String deleteAtFirstSpace( final String name ) {
final int first_space = name.indexOf( " " );
if ( first_space > 1 ) {
private static String extractBracketedScientificNames( final PhylogenyNode node, final String new_value ) {
final int i = new_value.lastIndexOf( "[" );
final String scientific_name = new_value.substring( i + 1, new_value.length() - 1 );
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
node.getNodeData().getTaxonomy().setScientificName( scientific_name );
return new_value.substring( 0, i - 1 ).trim();
}
private static String extractBracketedTaxCodes( final PhylogenyNode node, final String new_value ) {
- final int i = new_value.lastIndexOf( "[" );
- final String tc = new_value.substring( i + 1, new_value.length() - 1 );
- AptxUtil.ensurePresenceOfTaxonomy( node );
+ final Matcher m = ParserUtils.TAXOMONY_CODE_PATTERN_4.matcher( new_value );
+ String tc = "?";
+ if ( m.find() ) {
+ tc = m.group( 1 );
+ }
+ ForesterUtil.ensurePresenceOfTaxonomy( node );
try {
node.getNodeData().getTaxonomy().setTaxonomyCode( tc );
}
catch ( final PhyloXmlDataFormatException e ) {
throw new IllegalArgumentException( "illegal format for taxonomy code: " + tc );
}
- return new_value.substring( 0, i - 1 ).trim();
+ 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 ) {
return new_name;
}
- public static Map<String, Map<String, String>> parseMappingTable( final File mapping_table_file )
- 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 );
- for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
- final Map<String, String> row_map = new HashMap<String, String>();
- String name = null;
- for( int col = 0; col < mapping_table.getNumberOfColumns(); ++col ) {
- final String table_cell = mapping_table.getValue( col, row );
- if ( col == 0 ) {
- name = table_cell;
- }
- else if ( table_cell != null ) {
- final String key = table_cell.substring( 0, table_cell.indexOf( ':' ) );
- final String val = table_cell.substring( table_cell.indexOf( ':' ) + 1, table_cell.length() );
- row_map.put( key, val );
- }
- }
- map.put( name, row_map );
- }
- return map;
- }
-
private static String processNameIntelligently( final String name ) {
final String[] s = name.split( " " );
if ( s.length < 2 ) {