3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.application;
30 import java.io.IOException;
31 import java.util.ArrayList;
32 import java.util.List;
34 import org.forester.io.parsers.PhylogenyParser;
35 import org.forester.io.parsers.nexus.NexusPhylogeniesParser;
36 import org.forester.io.parsers.nhx.NHXParser;
37 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
38 import org.forester.io.parsers.util.ParserUtils;
39 import org.forester.io.writers.PhylogenyWriter;
40 import org.forester.phylogeny.Phylogeny;
41 import org.forester.phylogeny.PhylogenyMethods;
42 import org.forester.phylogeny.PhylogenyMethods.DESCENDANT_SORT_PRIORITY;
43 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
44 import org.forester.phylogeny.factories.PhylogenyFactory;
45 import org.forester.util.CommandLineArguments;
46 import org.forester.util.ForesterUtil;
48 public class phyloxml_converter {
50 final static private String HELP_OPTION_1 = "help";
51 final static private String HELP_OPTION_2 = "h";
52 final static private String FIELD_OPTION = "f";
53 final static private String FIELD_CLADE_NAME = "nn";
54 final static private String FIELD_TAXONOMY_CODE = "tc";
55 final static private String FIELD_TAXONOMY_SCI_NAME = "sn";
56 final static private String FIELD_TAXONOMY_COMM_NAME = "cn";
57 final static private String FIELD_SEQUENCE_GENE_NAME = "gn";
58 final static private String FIELD_SEQUENCE_SYMBOL = "sy";
59 final static private String FIELD_UNIPROT_TAXONOMY_ID_SPLIT_1 = "i1";
60 final static private String FIELD_UNIPROT_TAXONOMY_ID_SPLIT_2 = "i2";
61 final static private String FIELD_DUMMY = "dummy";
62 final static private String INTERNAL_NAMES_ARE_BOOT_SUPPPORT = "i";
63 final static private String MIDPOINT_REROOT = "m";
64 final static private String EXTRACT_TAXONOMY = "xt";
65 final static private String EXTRACT_TAXONOMY_PF = "xp";
66 final static private String ORDER_SUBTREES = "o";
67 final static private String NO_TREE_LEVEL_INDENDATION = "ni";
68 final static private String REPLACE_UNDER_SCORES = "ru";
69 final static private String IGNORE_QUOTES = "iqs";
70 final static private String CONFIDENCE_TYPE = "c";
71 final static private String PRG_NAME = "phyloxml_converter";
72 final static private String PRG_VERSION = "1.303";
73 final static private String PRG_DATE = "170510";
74 final static private String E_MAIL = "phyloxml@gmail.com";
75 final static private String WWW = "sites.google.com/site/cmzmasek/home/software/forester/phyloxml-converter";
77 public static void main( final String args[] ) throws PhyloXmlDataFormatException {
78 ForesterUtil.printProgramInformation( PRG_NAME, PRG_VERSION, PRG_DATE, E_MAIL, WWW );
79 CommandLineArguments cla = null;
81 cla = new CommandLineArguments( args );
83 catch ( final Exception e ) {
84 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
86 if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
90 if ( args.length < 3 ) {
92 System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
97 final List<String> allowed_options = new ArrayList<String>();
98 allowed_options.add( NO_TREE_LEVEL_INDENDATION );
99 allowed_options.add( FIELD_OPTION );
100 allowed_options.add( MIDPOINT_REROOT );
101 allowed_options.add( ORDER_SUBTREES );
102 allowed_options.add( INTERNAL_NAMES_ARE_BOOT_SUPPPORT );
103 allowed_options.add( REPLACE_UNDER_SCORES );
104 allowed_options.add( EXTRACT_TAXONOMY );
105 allowed_options.add( EXTRACT_TAXONOMY_PF );
106 allowed_options.add( IGNORE_QUOTES );
107 allowed_options.add( CONFIDENCE_TYPE );
108 if ( cla.getNumberOfNames() != 2 ) {
109 System.out.println();
110 System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
111 System.out.println();
115 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
116 if ( dissallowed_options.length() > 0 ) {
117 ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
119 final List<String> mandatory_options = new ArrayList<String>();
120 mandatory_options.add( FIELD_OPTION );
121 final String missing_options = cla.validateMandatoryOptionsAsString( mandatory_options );
122 if ( missing_options.length() > 0 ) {
123 ForesterUtil.fatalError( PRG_NAME, "missing option(s): " + missing_options );
125 if ( !cla.isOptionValueSet( FIELD_OPTION ) ) {
126 System.out.println();
130 final String field_option_value = cla.getOptionValue( FIELD_OPTION );
131 PhylogenyMethods.PhylogenyNodeField field = null;
132 if ( field_option_value.equals( FIELD_CLADE_NAME ) ) {
133 field = PhylogenyMethods.PhylogenyNodeField.CLADE_NAME;
135 else if ( field_option_value.equals( FIELD_TAXONOMY_CODE ) ) {
136 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_CODE;
138 else if ( field_option_value.equals( FIELD_TAXONOMY_SCI_NAME ) ) {
139 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME;
141 else if ( field_option_value.equals( FIELD_TAXONOMY_COMM_NAME ) ) {
142 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_COMMON_NAME;
144 else if ( field_option_value.equals( FIELD_SEQUENCE_GENE_NAME ) ) {
145 field = PhylogenyMethods.PhylogenyNodeField.SEQUENCE_NAME;
147 else if ( field_option_value.equals( FIELD_SEQUENCE_SYMBOL ) ) {
148 field = PhylogenyMethods.PhylogenyNodeField.SEQUENCE_SYMBOL;
150 else if ( field_option_value.equals( FIELD_UNIPROT_TAXONOMY_ID_SPLIT_1 ) ) {
151 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_ID_UNIPROT_1;
153 else if ( field_option_value.equals( FIELD_UNIPROT_TAXONOMY_ID_SPLIT_2 ) ) {
154 field = PhylogenyMethods.PhylogenyNodeField.TAXONOMY_ID_UNIPROT_2;
156 else if ( field_option_value.equals( FIELD_DUMMY ) ) {
160 .fatalError( PRG_NAME,
161 "unknown value for -\"" + FIELD_OPTION + "\" option: \"" + field_option_value + "\"" );
163 boolean ignore_quotes = false;
164 if ( cla.isOptionSet( IGNORE_QUOTES ) ) {
165 ignore_quotes = true;
167 boolean int_values_are_boots = false;
168 if ( cla.isOptionSet( INTERNAL_NAMES_ARE_BOOT_SUPPPORT ) ) {
169 int_values_are_boots = true;
171 String conf_type = "unknown";
172 if ( cla.isOptionSet( CONFIDENCE_TYPE ) ) {
173 final String str = cla.getOptionValueAsCleanString( CONFIDENCE_TYPE );
174 if ( !ForesterUtil.isEmpty( str ) ) {
178 boolean midpoint_reroot = false;
179 if ( cla.isOptionSet( MIDPOINT_REROOT ) ) {
180 midpoint_reroot = true;
182 boolean order_subtrees = false;
183 if ( cla.isOptionSet( ORDER_SUBTREES ) ) {
184 order_subtrees = true;
186 boolean replace_underscores = false;
187 if ( cla.isOptionSet( REPLACE_UNDER_SCORES ) ) {
188 replace_underscores = true;
190 boolean no_indendation = false;
191 if ( cla.isOptionSet( NO_TREE_LEVEL_INDENDATION ) ) {
192 no_indendation = true;
194 boolean extr_taxonomy = false;
195 if ( cla.isOptionSet( EXTRACT_TAXONOMY ) ) {
196 extr_taxonomy = true;
198 boolean extr_taxonomy_pf_only = false;
199 if ( cla.isOptionSet( EXTRACT_TAXONOMY_PF ) ) {
200 extr_taxonomy_pf_only = true;
202 final File infile = cla.getFile( 0 );
203 final File outfile = cla.getFile( 1 );
204 if ( outfile.exists() ) {
205 ForesterUtil.fatalError( PRG_NAME, "[" + outfile + "] already exists" );
207 if ( !infile.exists() ) {
208 ForesterUtil.fatalError( PRG_NAME, "[" + infile + "] does not exist" );
210 Phylogeny[] phys = null;
212 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
213 final PhylogenyParser parser = ParserUtils.createParserDependingOnFileType( infile, true );
214 if ( parser instanceof NHXParser ) {
215 if ( ( field != PhylogenyMethods.PhylogenyNodeField.TAXONOMY_CODE )
216 && ( field != PhylogenyMethods.PhylogenyNodeField.TAXONOMY_COMMON_NAME )
217 && ( field != PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME ) ) {
218 if ( extr_taxonomy_pf_only ) {
219 ( ( NHXParser ) parser )
220 .setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT );
221 replace_underscores = false;
223 else if ( extr_taxonomy ) {
224 ( ( NHXParser ) parser )
225 .setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED );
226 replace_underscores = false;
230 ( ( NHXParser ) parser ).setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.NO );
232 ( ( NHXParser ) parser ).setReplaceUnderscores( replace_underscores );
233 ( ( NHXParser ) parser ).setIgnoreQuotes( ignore_quotes );
235 else if ( parser instanceof NexusPhylogeniesParser ) {
236 ( ( NexusPhylogeniesParser ) parser ).setReplaceUnderscores( replace_underscores );
237 ( ( NexusPhylogeniesParser ) parser ).setIgnoreQuotes( false );
239 phys = factory.create( infile, parser );
241 catch ( final IOException e ) {
242 ForesterUtil.fatalError( PRG_NAME, "failed to read phylogeny from [" + infile + "]: " + e.getMessage() );
244 if ( int_values_are_boots ) {
245 for( final Phylogeny phy : phys ) {
246 PhylogenyMethods.transferInternalNamesToConfidenceValues( phy, conf_type );
249 if ( field != null ) {
250 for( final Phylogeny phy : phys ) {
251 PhylogenyMethods.transferNodeNameToField( phy, field, false );
254 if ( midpoint_reroot ) {
256 for( final Phylogeny phy : phys ) {
257 PhylogenyMethods.midpointRoot( phy );
260 catch ( final Exception e ) {
261 System.out.println( "" );
262 ForesterUtil.printWarningMessage( PRG_NAME, "midpoint rerooting failed: " + e.getLocalizedMessage() );
265 if ( order_subtrees ) {
266 for( final Phylogeny phy : phys ) {
267 PhylogenyMethods.orderAppearance( phy.getRoot(), true, true, DESCENDANT_SORT_PRIORITY.TAXONOMY );
268 phy.externalNodesHaveChanged();
269 phy.clearHashIdToNodeMap();
270 phy.recalculateNumberOfExternalDescendants( true );
274 final PhylogenyWriter writer = new PhylogenyWriter();
275 if ( no_indendation ) {
276 writer.setIndentPhyloxml( false );
278 writer.toPhyloXML( phys, 0, outfile, ForesterUtil.LINE_SEPARATOR );
280 catch ( final IOException e ) {
281 ForesterUtil.fatalError( PRG_NAME, "failed to write to [" + outfile + "]: " + e.getMessage() );
283 System.out.println( "[" + PRG_NAME + "] wrote: [" + outfile + "]" );
284 System.out.println( "[" + PRG_NAME + "] OK" );
285 System.out.println();
288 private static void printHelp() {
289 System.out.println( "Usage:" );
290 System.out.println();
291 System.out.println( PRG_NAME + " -" + FIELD_OPTION
292 + "=<field option> [options] <infile in New Hamphshire, NHX, Nexus, ToL XML, or phyloXML format> <outfile>" );
293 System.out.println();
294 System.out.println( " field options: " );
295 System.out.println();
296 System.out.println( " " + FIELD_CLADE_NAME + ": transfer name to node/clade name" );
297 System.out.println( " " + FIELD_TAXONOMY_CODE + ": transfer name to taxonomy code" );
298 System.out.println( " " + FIELD_TAXONOMY_SCI_NAME + ": transfer name to taxonomy scientific name" );
299 System.out.println( " " + FIELD_TAXONOMY_COMM_NAME + ": transfer name to taxonomy common name" );
300 System.out.println( " " + FIELD_SEQUENCE_GENE_NAME + ": transfer name to sequence name" );
301 System.out.println( " " + FIELD_SEQUENCE_SYMBOL + ": transfer name to sequence symbol" );
302 System.out.println( " " + FIELD_DUMMY + ": to convert NHX formatted trees to phyloXML" );
303 System.out.println( " " + FIELD_UNIPROT_TAXONOMY_ID_SPLIT_1
304 + ": transfer/split name to taxonomy uniprot identifier" );
305 System.out.println( " (split at underscore if \"id_name\" pattern, e.g. \"817_SusD\")" );
306 System.out.println( " " + FIELD_UNIPROT_TAXONOMY_ID_SPLIT_2
307 + ": transfer/split name to taxonomy uniprot identifier" );
308 System.out.println( " (split at underscore if \"name_id\" pattern, e.g. \"SusD_817\")" );
309 System.out.println();
310 System.out.println( " options: " );
311 System.out.println( " -" + INTERNAL_NAMES_ARE_BOOT_SUPPPORT
312 + " : internal names in NH or NHX tree are confidence values" );
313 System.out.println( " -" + CONFIDENCE_TYPE + "=<conf>"
314 + ": confidence type (e.g. \"bootstrap\", default is \"unknown\")" );
315 System.out.println( " -" + REPLACE_UNDER_SCORES + " : replace all underscores with spaces" );
316 System.out.println( " -" + MIDPOINT_REROOT + " : midpoint reroot" );
317 System.out.println( " -" + ORDER_SUBTREES + " : order subtrees" );
318 System.out.println( " -" + EXTRACT_TAXONOMY
319 + " : extract taxonomy to taxonomy code from \"seqname_TAXON\"-style names (cannot be used with the following field options: "
320 + FIELD_TAXONOMY_CODE + ", " + FIELD_TAXONOMY_COMM_NAME + ", " + FIELD_TAXONOMY_SCI_NAME + ")" );
321 System.out.println( " -" + EXTRACT_TAXONOMY_PF
322 + " : extract taxonomy to taxonomy code from Pfam (\"seqname_TAXON/x-y\") style names only (cannot be used with the following field options: "
323 + FIELD_TAXONOMY_CODE + ", " + FIELD_TAXONOMY_COMM_NAME + ", " + FIELD_TAXONOMY_SCI_NAME + ")" );
324 System.out.println( " -" + NO_TREE_LEVEL_INDENDATION + " : no tree level indendation in phyloXML output" );
325 System.out.println( " -" + IGNORE_QUOTES + " : ignore quotes and whitespace (e.g. \"a b\" becomes ab)" );
326 System.out.println();