2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
26 package org.forester.tools;
29 import java.io.IOException;
30 import java.util.HashMap;
32 import java.util.regex.Matcher;
34 import org.forester.io.parsers.nhx.NHXFormatException;
35 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
36 import org.forester.io.parsers.util.ParserUtils;
37 import org.forester.phylogeny.Phylogeny;
38 import org.forester.phylogeny.PhylogenyNode;
39 import org.forester.phylogeny.data.Accession;
40 import org.forester.phylogeny.data.Annotation;
41 import org.forester.phylogeny.data.DomainArchitecture;
42 import org.forester.phylogeny.data.Identifier;
43 import org.forester.phylogeny.data.Sequence;
44 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
45 import org.forester.util.BasicTable;
46 import org.forester.util.BasicTableParser;
47 import org.forester.util.ForesterUtil;
49 public final class PhylogenyDecorator {
51 final private static String TP_NODE_NAME = "NODE_NAME";
52 final private static String TP_SEQ_ACCESSION = "SEQ_ACCESSION";
53 final private static String TP_SEQ_ACCESSION_SOURCE = "SEQ_ACCESSION_SOURCE";
54 final private static String TP_SEQ_ANNOTATION_DESC = "SEQ_ANNOTATION_DESC";
55 final private static String TP_SEQ_ANNOTATION_REF = "SEQ_ANNOTATION_REF";
56 final private static String TP_SEQ_MOL_SEQ = "SEQ_MOL_SEQ";
57 final private static String TP_SEQ_NAME = "SEQ_NAME";
58 final private static String TP_SEQ_SYMBOL = "SEQ_SYMBOL";
59 final private static String TP_TAXONOMY_CN = "TAXONOMY_CN";
60 // From evoruby/lib/evo/apps/tseq_taxonomy_processor.rb:
61 final private static String TP_TAXONOMY_CODE = "TAXONOMY_CODE";
62 final private static String TP_TAXONOMY_ID = "TAXONOMY_ID";
63 final private static String TP_TAXONOMY_ID_PROVIDER = "TAXONOMY_ID_PROVIDER";
64 final private static String TP_TAXONOMY_SN = "TAXONOMY_SN";
65 final private static String TP_TAXONOMY_SYN = "TAXONOMY_SYN";
67 private PhylogenyDecorator() {
71 public static void decorate( final Phylogeny phylogeny,
72 final Map<String, Map<String, String>> map,
73 final boolean picky ) throws IllegalArgumentException, PhyloXmlDataFormatException {
74 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
75 final PhylogenyNode node = iter.next();
76 final String name = node.getName();
77 if ( !ForesterUtil.isEmpty( name ) ) {
78 if ( map.containsKey( name ) ) {
79 final Map<String, String> new_values = map.get( name );
80 if ( new_values != null ) {
81 if ( new_values.containsKey( TP_TAXONOMY_CODE ) ) {
82 ForesterUtil.ensurePresenceOfTaxonomy( node );
83 node.getNodeData().getTaxonomy().setTaxonomyCode( new_values.get( TP_TAXONOMY_CODE ) );
85 if ( new_values.containsKey( TP_TAXONOMY_ID )
86 && new_values.containsKey( TP_TAXONOMY_ID_PROVIDER ) ) {
87 ForesterUtil.ensurePresenceOfTaxonomy( node );
90 .setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ),
91 new_values.get( TP_TAXONOMY_ID_PROVIDER ) ) );
93 else if ( new_values.containsKey( TP_TAXONOMY_ID ) ) {
94 ForesterUtil.ensurePresenceOfTaxonomy( node );
95 node.getNodeData().getTaxonomy()
96 .setIdentifier( new Identifier( new_values.get( TP_TAXONOMY_ID ) ) );
98 if ( new_values.containsKey( TP_TAXONOMY_SN ) ) {
99 ForesterUtil.ensurePresenceOfTaxonomy( node );
100 node.getNodeData().getTaxonomy().setScientificName( new_values.get( TP_TAXONOMY_SN ) );
102 if ( new_values.containsKey( TP_TAXONOMY_CN ) ) {
103 ForesterUtil.ensurePresenceOfTaxonomy( node );
104 node.getNodeData().getTaxonomy().setCommonName( new_values.get( TP_TAXONOMY_CN ) );
106 if ( new_values.containsKey( TP_TAXONOMY_SYN ) ) {
107 ForesterUtil.ensurePresenceOfTaxonomy( node );
108 node.getNodeData().getTaxonomy().getSynonyms().add( new_values.get( TP_TAXONOMY_SYN ) );
110 if ( new_values.containsKey( TP_SEQ_ACCESSION )
111 && new_values.containsKey( TP_SEQ_ACCESSION_SOURCE ) ) {
112 ForesterUtil.ensurePresenceOfSequence( node );
115 .setAccession( new Accession( new_values.get( TP_SEQ_ACCESSION ),
116 new_values.get( TP_SEQ_ACCESSION_SOURCE ) ) );
118 if ( new_values.containsKey( TP_SEQ_ANNOTATION_DESC ) ) {
119 ForesterUtil.ensurePresenceOfSequence( node );
120 final Annotation ann = new Annotation();
121 ann.setDesc( new_values.get( TP_SEQ_ANNOTATION_DESC ) );
122 node.getNodeData().getSequence().addAnnotation( ann );
124 if ( new_values.containsKey( TP_SEQ_ANNOTATION_REF ) ) {
125 ForesterUtil.ensurePresenceOfSequence( node );
126 final Annotation ann = new Annotation( new_values.get( TP_SEQ_ANNOTATION_REF ) );
127 node.getNodeData().getSequence().addAnnotation( ann );
129 if ( new_values.containsKey( TP_SEQ_SYMBOL ) ) {
130 ForesterUtil.ensurePresenceOfSequence( node );
131 node.getNodeData().getSequence().setSymbol( new_values.get( TP_SEQ_SYMBOL ) );
133 if ( new_values.containsKey( TP_SEQ_NAME ) ) {
134 ForesterUtil.ensurePresenceOfSequence( node );
135 node.getNodeData().getSequence().setName( new_values.get( TP_SEQ_NAME ) );
137 if ( new_values.containsKey( TP_SEQ_MOL_SEQ ) ) {
138 ForesterUtil.ensurePresenceOfSequence( node );
139 node.getNodeData().getSequence().setMolecularSequence( new_values.get( TP_SEQ_MOL_SEQ ) );
141 if ( new_values.containsKey( TP_NODE_NAME ) ) {
142 node.setName( new_values.get( TP_NODE_NAME ) );
144 } // if ( new_values != null )
145 } // if ( map.containsKey( name ) || ( numbers_of_chars_allowed_to_remove_if_not_found_in_map > 0 ) )
147 throw new IllegalArgumentException( "\"" + name + "\" not found in name map" );
153 public static String decorate( final Phylogeny phylogeny,
154 final Map<String, String> map,
156 final boolean extract_bracketed_scientific_name,
157 final boolean extract_bracketed_tax_code,
159 final boolean cut_name_after_space,
160 final boolean trim_after_tilde,
161 final boolean verbose ) throws IllegalArgumentException, NHXFormatException,
162 PhyloXmlDataFormatException {
163 return PhylogenyDecorator.decorate( phylogeny,
166 extract_bracketed_scientific_name,
167 extract_bracketed_tax_code,
170 cut_name_after_space,
181 * maps names (in phylogeny) to new values if intermediate_map is
182 * null otherwise maps intermediate value to new value
185 * @param intermediate_map
186 * maps name (in phylogeny) to a intermediate value
187 * @throws IllegalArgumentException
188 * @throws PhyloXmlDataFormatException
190 public static String decorate( final Phylogeny phylogeny,
191 final Map<String, String> map,
193 final boolean extract_bracketed_scientific_name,
194 final boolean extract_bracketed_tax_code,
196 final Map<String, String> intermediate_map,
197 final boolean cut_name_after_space,
198 final boolean trim_after_tilde,
199 final boolean verbose ) throws IllegalArgumentException, PhyloXmlDataFormatException {
200 if ( extract_bracketed_scientific_name && ( field == FIELD.TAXONOMY_SCIENTIFIC_NAME ) ) {
201 throw new IllegalArgumentException( "attempt to extract bracketed scientific name together with data field pointing to scientific name" );
203 if ( map.isEmpty() ) {
204 throw new IllegalArgumentException( "map is empty" );
207 int ext_nodes_updated = 0;
209 int int_nodes_updated = 0;
210 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPostorder(); iter.hasNext(); ) {
211 final PhylogenyNode node = iter.next();
212 if ( node.isExternal() ) {
218 String name = node.getName();
219 if ( picky && node.isExternal() && ForesterUtil.isEmpty( name ) ) {
220 throw new IllegalArgumentException( "external node with no name present" );
222 String tilde_annotation = null;
223 if ( trim_after_tilde && ( name.indexOf( '~' ) > 0 ) ) {
224 final int ti = name.indexOf( '~' );
225 final String orig = name;
226 tilde_annotation = name.substring( ti );
227 name = name.substring( 0, ti );
228 if ( node.isExternal() && ForesterUtil.isEmpty( name ) ) {
229 throw new IllegalArgumentException( "external node with illegal name: " + orig );
232 if ( !ForesterUtil.isEmpty( name ) ) {
233 if ( intermediate_map != null ) {
234 name = PhylogenyDecorator.extractIntermediate( intermediate_map, name, verbose );
236 if ( map.containsKey( name ) ) {
237 String new_value = map.get( name ).trim().replaceAll( "/\\s+/", " " );
238 if ( !ForesterUtil.isEmpty( new_value ) ) {
239 if ( node.isExternal() ) {
245 if ( extract_bracketed_scientific_name && new_value.endsWith( "]" ) ) {
246 new_value = extractBracketedScientificNames( node, new_value );
248 else if ( extract_bracketed_tax_code ) {
249 if ( ParserUtils.TAXOMONY_CODE_PATTERN_BRACKETED.matcher( new_value ).find() ) {
250 new_value = extractBracketedTaxCodes( node, new_value );
253 throw new IllegalArgumentException( " could not get taxonomy from \"" + new_value
260 System.out.println( name + ": " + new_value );
262 if ( !node.getNodeData().isHasSequence() ) {
263 node.getNodeData().setSequence( new Sequence() );
265 node.getNodeData().getSequence().setMolecularSequence( new_value );
267 case SEQUENCE_ANNOTATION_DESC:
269 System.out.println( name + ": " + new_value );
271 if ( !node.getNodeData().isHasSequence() ) {
272 node.getNodeData().setSequence( new Sequence() );
274 final Annotation annotation = new Annotation();
275 annotation.setDesc( new_value );
276 node.getNodeData().getSequence().addAnnotation( annotation );
278 case DOMAIN_STRUCTURE:
280 System.out.println( name + ": " + new_value );
282 if ( !node.getNodeData().isHasSequence() ) {
283 node.getNodeData().setSequence( new Sequence() );
285 node.getNodeData().getSequence()
286 .setDomainArchitecture( new DomainArchitecture( new_value ) );
290 System.out.println( name + ": " + new_value );
292 ForesterUtil.ensurePresenceOfTaxonomy( node );
293 node.getNodeData().getTaxonomy().setTaxonomyCode( new_value );
295 case TAXONOMY_SCIENTIFIC_NAME:
297 System.out.println( name + ": " + new_value );
299 ForesterUtil.ensurePresenceOfTaxonomy( node );
300 node.getNodeData().getTaxonomy().setScientificName( new_value );
303 if ( trim_after_tilde ) {
304 new_value = addTildeAnnotation( tilde_annotation, new_value );
307 System.out.println( name + ": " + new_value );
309 if ( !node.getNodeData().isHasSequence() ) {
310 node.getNodeData().setSequence( new Sequence() );
312 node.getNodeData().getSequence().setName( new_value );
316 System.out.print( name + " -> " );
318 if ( cut_name_after_space ) {
320 System.out.print( new_value + " -> " );
322 new_value = PhylogenyDecorator.deleteAtFirstSpace( new_value );
324 if ( trim_after_tilde ) {
325 new_value = addTildeAnnotation( tilde_annotation, new_value );
328 System.out.println( new_value );
330 node.setName( new_value );
333 throw new RuntimeException( "unknown field \"" + field + "\"" );
337 throw new IllegalArgumentException( "node name \"" + name + "\" maps to empty value" );
341 throw new IllegalArgumentException( "node name \"" + name + "\" not found in map" );
345 return "updated " + ext_nodes_updated + "/" + ext_nodes + " external nodes, updated " + int_nodes_updated + "/"
346 + int_nodes + " internal nodes";
349 public static Map<String, Map<String, String>> parseMappingTable( final File mapping_table_file )
351 final Map<String, Map<String, String>> map = new HashMap<String, Map<String, String>>();
352 BasicTable<String> mapping_table = null;
353 mapping_table = BasicTableParser.parse( mapping_table_file, '\t', false, false );
354 for( int row = 0; row < mapping_table.getNumberOfRows(); ++row ) {
355 final Map<String, String> row_map = new HashMap<String, String>();
357 for( int col = 0; col < mapping_table.getNumberOfColumns(); ++col ) {
358 final String table_cell = mapping_table.getValue( col, row );
362 else if ( table_cell != null ) {
363 final String key = table_cell.substring( 0, table_cell.indexOf( ':' ) );
364 final String val = table_cell.substring( table_cell.indexOf( ':' ) + 1, table_cell.length() );
365 row_map.put( key, val );
368 map.put( name, row_map );
373 private final static String addTildeAnnotation( final String tilde_annotation, final String new_value ) {
374 if ( ForesterUtil.isEmpty( tilde_annotation ) ) {
377 return new_value + tilde_annotation;
380 private static String deleteAtFirstSpace( final String name ) {
381 final int first_space = name.indexOf( " " );
382 if ( first_space > 1 ) {
383 return name.substring( 0, first_space ).trim();
388 private static String extractBracketedScientificNames( final PhylogenyNode node, final String new_value ) {
389 final int i = new_value.lastIndexOf( "[" );
390 final String scientific_name = new_value.substring( i + 1, new_value.length() - 1 );
391 ForesterUtil.ensurePresenceOfTaxonomy( node );
392 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
393 return new_value.substring( 0, i - 1 ).trim();
396 private static String extractBracketedTaxCodes( final PhylogenyNode node, final String new_value ) {
397 final StringBuilder sb = new StringBuilder();
398 sb.append( new_value );
399 final String tc = extractBracketedTaxCodes( sb );
400 if ( !ForesterUtil.isEmpty( tc ) ) {
401 ForesterUtil.ensurePresenceOfTaxonomy( node );
403 node.getNodeData().getTaxonomy().setTaxonomyCode( tc );
405 catch ( final PhyloXmlDataFormatException e ) {
406 throw new IllegalArgumentException( "illegal format for taxonomy code: " + tc );
408 return sb.toString().trim();
413 private static String extractBracketedTaxCodes( final StringBuilder sb ) {
414 final Matcher m = ParserUtils.TAXOMONY_CODE_PATTERN_BRACKETED.matcher( sb );
416 final String tc = m.group( 1 );
417 sb.delete( m.start( 1 ) - 1, m.end( 1 ) + 1 );
423 private static String extractIntermediate( final Map<String, String> intermediate_map,
425 final boolean verbose ) {
426 String new_name = null;
428 System.out.print( name + " => " );
430 if ( intermediate_map.containsKey( name ) ) {
431 new_name = intermediate_map.get( name );
432 if ( ForesterUtil.isEmpty( new_name ) ) {
433 throw new IllegalArgumentException( "\"" + name + "\" maps to null or empty string in secondary map" );
437 throw new IllegalArgumentException( "\"" + name + "\" not found in name secondary map" );
440 System.out.println( new_name + " " );
445 public static enum FIELD {
449 SEQUENCE_ANNOTATION_DESC,
452 TAXONOMY_SCIENTIFIC_NAME;