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: www.phylosoft.org/forester
26 package org.forester.application;
29 import java.io.IOException;
30 import java.util.ArrayList;
31 import java.util.List;
34 import org.forester.io.parsers.PhylogenyParser;
35 import org.forester.io.parsers.util.ParserUtils;
36 import org.forester.io.writers.PhylogenyWriter;
37 import org.forester.phylogeny.Phylogeny;
38 import org.forester.phylogeny.data.Identifier;
39 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
40 import org.forester.phylogeny.factories.PhylogenyFactory;
41 import org.forester.tools.PhylogenyDecorator;
42 import org.forester.tools.PhylogenyDecorator.FIELD;
43 import org.forester.util.BasicTable;
44 import org.forester.util.BasicTableParser;
45 import org.forester.util.CommandLineArguments;
46 import org.forester.util.ForesterUtil;
48 public final class decorator {
50 private static final String SEQUENCE_NAME_FIELD = "s";
51 private static final String TAXONOMY_CODE_FIELD = "c";
52 private static final String TAXONOMY_SCIENTIFIC_NAME_FIELD = "sn";
53 private static final String DS_FILED = "d";
54 private static final String SEQUENCE_ANNOTATION_DESC = "a";
55 private static final String NODE_NAME_FIELD = "n";
56 final static private String PICKY_OPTION = "p";
57 final static private String FIELD_OPTION = "f";
58 final static private String MOVE_DOMAIN_NUMBER_OPTION = "mdn"; // Hidden expert option.
59 final static private String TREE_NAME_OPTION = "pn";
60 final static private String TREE_ID_OPTION = "pi";
61 final static private String TREE_DESC_OPTION = "pd";
62 final static private String EXTRACT_BRACKETED_SCIENTIC_NAME_OPTION = "sn";
63 final static private String PROCESS_NAME_INTELLIGENTLY_OPTION = "x";
64 final static private String PROCESS_SIMILAR_TO_OPTION = "xs";
65 final static private String CUT_NAME_AFTER_FIRST_SPACE_OPTION = "c";
66 final static private String ALLOW_REMOVAL_OF_CHARS_OPTION = "r";
67 final static private String ADVANCED_TABLE_OPTION = "table";
68 final static private String KEY_COLUMN = "k";
69 final static private String VALUE_COLUMN = "v";
70 final static private String MAPPING_FILE_SEPARATOR_OPTION = "s";
71 final static private String MAPPING_FILE_SEPARATOR_DEFAULT = ":";
72 final static private boolean USE_FIRST_SEPARATOR_ONLY = true;
73 final static private String PRG_NAME = "decorator";
74 final static private String PRG_VERSION = "1.10";
75 final static private String PRG_DATE = "2009.10.08";
77 private static void argumentsError() {
79 System.out.println( decorator.PRG_NAME + " -" + ADVANCED_TABLE_OPTION + " | -f=<c> <phylogenies infile> "
80 + "[mapping table file] <phylogenies outfile>" );
82 System.out.println( "options:" );
84 System.out.println( " -" + ADVANCED_TABLE_OPTION + " : table instead of one to one map (-f=<c>)" );
85 System.out.println( " -r=<n> : allow to remove up to n characters from the end of the names" );
86 System.out.println( " in phylogenies infile if not found (in map) otherwise" );
87 System.out.println( " -p : for picky, fails if node name not found in mapping table, default is off" );
88 System.out.println( " -" + TREE_NAME_OPTION + "=<s>: name for the phylogeny" );
89 System.out.println( " -" + TREE_ID_OPTION + "=<s>: identifier for the phylogeny (in the form provider:value)" );
90 System.out.println( " -" + TREE_DESC_OPTION + "=<s>: description for phylogenies" );
93 System.out.println( "advanced options, only available if -" + ADVANCED_TABLE_OPTION + " is not used:" );
95 System.out.println( " -f=<c> : field to be replaced: " + NODE_NAME_FIELD + " : node name" );
96 System.out.println( " " + SEQUENCE_ANNOTATION_DESC
97 + " : sequence annotation description" );
98 System.out.println( " " + DS_FILED + " : domain structure" );
99 System.out.println( " " + TAXONOMY_CODE_FIELD + " : taxonomy code" );
100 System.out.println( " " + TAXONOMY_SCIENTIFIC_NAME_FIELD
101 + ": taxonomy scientific name" );
102 System.out.println( " " + SEQUENCE_NAME_FIELD + " : sequence name" );
103 System.out.println( " -k=<n> : key column in mapping table (0 based)," );
104 System.out.println( " names of the node to be decorated - default is 0" );
105 System.out.println( " -v=<n> : value column in mapping table (0 based)," );
106 System.out.println( " data which with to decorate - default is 1" );
107 System.out.println( " -" + EXTRACT_BRACKETED_SCIENTIC_NAME_OPTION
108 + " : to extract bracketed scientific names" );
109 System.out.println( " -s=<c> : column separator in mapping file, default is \""
110 + decorator.MAPPING_FILE_SEPARATOR_DEFAULT + "\"" );
111 System.out.println( " -x : process name \"intelligently\" (only for -f=n)" );
112 System.out.println( " -" + decorator.PROCESS_SIMILAR_TO_OPTION
113 + " : process name \"intelligently\" and process information after \"similar to\" (only for -f=n)" );
114 System.out.println( " -c : cut name after first space (only for -f=n)" );
115 System.out.println();
119 public static void main( final String args[] ) {
120 ForesterUtil.printProgramInformation( decorator.PRG_NAME, decorator.PRG_VERSION, decorator.PRG_DATE );
121 if ( ( args.length < 4 ) || ( args.length > 12 ) ) {
122 decorator.argumentsError();
124 CommandLineArguments cla = null;
126 cla = new CommandLineArguments( args );
128 catch ( final Exception e ) {
129 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
131 if ( ( cla.getNumberOfNames() < 3 ) || ( cla.getNumberOfNames() > 4 ) ) {
132 decorator.argumentsError();
134 final File phylogenies_infile = cla.getFile( 0 );
135 final File mapping_infile = cla.getFile( 1 );
136 final File phylogenies_outfile = cla.getFile( 2 );
137 if ( phylogenies_outfile.exists() ) {
138 ForesterUtil.fatalError( PRG_NAME, "[" + phylogenies_outfile + "] already exists" );
140 final List<String> allowed_options = new ArrayList<String>();
141 allowed_options.add( decorator.ADVANCED_TABLE_OPTION );
142 allowed_options.add( decorator.PICKY_OPTION );
143 allowed_options.add( decorator.FIELD_OPTION );
144 allowed_options.add( decorator.PROCESS_NAME_INTELLIGENTLY_OPTION );
145 allowed_options.add( decorator.PROCESS_SIMILAR_TO_OPTION );
146 allowed_options.add( decorator.CUT_NAME_AFTER_FIRST_SPACE_OPTION );
147 allowed_options.add( decorator.ALLOW_REMOVAL_OF_CHARS_OPTION );
148 allowed_options.add( decorator.KEY_COLUMN );
149 allowed_options.add( decorator.VALUE_COLUMN );
150 allowed_options.add( decorator.MAPPING_FILE_SEPARATOR_OPTION );
151 allowed_options.add( decorator.EXTRACT_BRACKETED_SCIENTIC_NAME_OPTION );
152 allowed_options.add( decorator.TREE_NAME_OPTION );
153 allowed_options.add( decorator.TREE_ID_OPTION );
154 allowed_options.add( decorator.TREE_DESC_OPTION );
155 allowed_options.add( decorator.MOVE_DOMAIN_NUMBER_OPTION );
156 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
157 if ( dissallowed_options.length() > 0 ) {
158 ForesterUtil.fatalError( decorator.PRG_NAME, "unknown option(s): " + dissallowed_options );
160 final boolean advanced_table = cla.isOptionSet( decorator.ADVANCED_TABLE_OPTION );
161 if ( !advanced_table ) {
162 final List<String> mandatory_options = new ArrayList<String>();
163 mandatory_options.add( decorator.FIELD_OPTION );
164 final String missing_options = cla.validateMandatoryOptionsAsString( mandatory_options );
165 if ( missing_options.length() > 0 ) {
166 ForesterUtil.fatalError( decorator.PRG_NAME, "missing option(s): " + missing_options );
169 final boolean picky = cla.isOptionSet( decorator.PICKY_OPTION );
170 String separator = decorator.MAPPING_FILE_SEPARATOR_DEFAULT;
171 if ( cla.isOptionSet( decorator.MAPPING_FILE_SEPARATOR_OPTION ) ) {
172 if ( advanced_table ) {
175 separator = cla.getOptionValue( decorator.MAPPING_FILE_SEPARATOR_OPTION );
178 int value_column = 1;
179 String field_str = "";
180 FIELD field = FIELD.NODE_NAME;
181 int numbers_of_chars_allowed_to_remove_if_not_found_in_map = -1;
182 boolean cut_name_after_space = false;
183 boolean process_name_intelligently = false;
184 boolean process_similar_to = false;
185 boolean extract_bracketed_scientific_name = false;
186 boolean move_domain_numbers_at_end_to_middle = false;
187 String tree_name = "";
189 String tree_desc = "";
191 if ( cla.isOptionSet( decorator.TREE_NAME_OPTION ) ) {
192 tree_name = cla.getOptionValueAsCleanString( decorator.TREE_NAME_OPTION );
194 if ( cla.isOptionSet( decorator.TREE_ID_OPTION ) ) {
195 tree_id = cla.getOptionValueAsCleanString( decorator.TREE_ID_OPTION );
197 if ( cla.isOptionSet( decorator.TREE_DESC_OPTION ) ) {
198 tree_desc = cla.getOptionValueAsCleanString( decorator.TREE_DESC_OPTION );
200 if ( cla.isOptionSet( decorator.EXTRACT_BRACKETED_SCIENTIC_NAME_OPTION ) ) {
201 if ( advanced_table ) {
204 extract_bracketed_scientific_name = true;
206 if ( cla.isOptionSet( decorator.KEY_COLUMN ) ) {
207 if ( advanced_table ) {
210 key_column = cla.getOptionValueAsInt( decorator.KEY_COLUMN );
212 if ( cla.isOptionSet( decorator.VALUE_COLUMN ) ) {
213 if ( advanced_table ) {
216 value_column = cla.getOptionValueAsInt( decorator.VALUE_COLUMN );
218 if ( cla.isOptionSet( decorator.CUT_NAME_AFTER_FIRST_SPACE_OPTION ) ) {
219 if ( advanced_table ) {
222 cut_name_after_space = true;
224 if ( cla.isOptionSet( decorator.PROCESS_NAME_INTELLIGENTLY_OPTION ) ) {
225 if ( advanced_table ) {
228 process_name_intelligently = true;
230 if ( cla.isOptionSet( decorator.PROCESS_SIMILAR_TO_OPTION ) ) {
231 if ( advanced_table ) {
234 process_similar_to = true;
236 if ( cla.isOptionSet( decorator.ALLOW_REMOVAL_OF_CHARS_OPTION ) ) {
237 numbers_of_chars_allowed_to_remove_if_not_found_in_map = cla
238 .getOptionValueAsInt( decorator.ALLOW_REMOVAL_OF_CHARS_OPTION );
240 if ( cla.isOptionSet( decorator.MOVE_DOMAIN_NUMBER_OPTION ) ) {
241 move_domain_numbers_at_end_to_middle = true;
243 if ( cla.isOptionSet( decorator.FIELD_OPTION ) ) {
244 field_str = cla.getOptionValue( decorator.FIELD_OPTION );
245 if ( field_str.equals( NODE_NAME_FIELD ) ) {
246 field = FIELD.NODE_NAME;
248 else if ( field_str.equals( SEQUENCE_ANNOTATION_DESC ) ) {
249 field = FIELD.SEQUENCE_ANNOTATION_DESC;
251 else if ( field_str.equals( DS_FILED ) ) {
252 field = FIELD.DOMAIN_STRUCTURE;
253 extract_bracketed_scientific_name = false;
255 else if ( field_str.equals( TAXONOMY_CODE_FIELD ) ) {
256 field = FIELD.TAXONOMY_CODE;
258 else if ( field_str.equals( SEQUENCE_NAME_FIELD ) ) {
259 field = FIELD.SEQUENCE_NAME;
261 else if ( field_str.equals( TAXONOMY_SCIENTIFIC_NAME_FIELD ) ) {
262 field = FIELD.TAXONOMY_SCIENTIFIC_NAME;
263 extract_bracketed_scientific_name = false;
266 ForesterUtil.fatalError( decorator.PRG_NAME, "unknown value for \"" + decorator.FIELD_OPTION
267 + "\" option: \"" + field_str + "\"" );
271 catch ( final Exception e ) {
272 ForesterUtil.fatalError( decorator.PRG_NAME, "error in command line: " + e.getMessage() );
274 if ( ( field != FIELD.NODE_NAME ) && ( cut_name_after_space || process_name_intelligently ) ) {
275 ForesterUtil.fatalError( decorator.PRG_NAME, "attempt to use -x or -c option without -f=n" );
277 if ( ( field != FIELD.NODE_NAME ) && process_similar_to ) {
278 ForesterUtil.fatalError( decorator.PRG_NAME, "attempt to use -" + decorator.PROCESS_SIMILAR_TO_OPTION
279 + " option without -f=n" );
281 if ( cut_name_after_space && process_name_intelligently ) {
282 ForesterUtil.fatalError( decorator.PRG_NAME, "attempt to use -x and -c option together" );
284 if ( process_similar_to && process_name_intelligently ) {
285 ForesterUtil.fatalError( decorator.PRG_NAME, "attempt to use -" + decorator.PROCESS_SIMILAR_TO_OPTION
286 + " and -x option together" );
288 if ( process_similar_to && cut_name_after_space ) {
289 ForesterUtil.fatalError( decorator.PRG_NAME, "attempt to use -" + decorator.PROCESS_SIMILAR_TO_OPTION
290 + " and -c option together" );
292 Phylogeny[] phylogenies = null;
294 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
295 final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( phylogenies_infile, true );
296 phylogenies = factory.create( phylogenies_infile, pp );
298 catch ( final Exception e ) {
299 ForesterUtil.fatalError( decorator.PRG_NAME, "failed to read phylgenies from [" + phylogenies_infile
300 + "] [" + e.getMessage() + "]" );
302 Map<String, String> map = null;
303 if ( !advanced_table ) {
304 BasicTable<String> mapping_table = null;
306 mapping_table = BasicTableParser.parse( mapping_infile, separator, decorator.USE_FIRST_SEPARATOR_ONLY );
308 catch ( final Exception e ) {
309 ForesterUtil.fatalError( decorator.PRG_NAME,
310 "failed to read [" + mapping_infile + "] [" + e.getMessage() + "]" );
312 if ( ( key_column < 0 ) || ( key_column >= mapping_table.getNumberOfColumns() ) ) {
313 ForesterUtil.fatalError( decorator.PRG_NAME, "illegal value for key column" );
315 if ( ( value_column < 0 ) || ( value_column >= mapping_table.getNumberOfColumns() ) ) {
316 ForesterUtil.fatalError( decorator.PRG_NAME, "illegal value for value column" );
318 map = mapping_table.getColumnsAsMap( key_column, value_column );
320 if ( !ForesterUtil.isEmpty( tree_name ) || !ForesterUtil.isEmpty( tree_id )
321 || !ForesterUtil.isEmpty( tree_desc ) ) {
322 if ( ( phylogenies.length > 1 )
323 && ( !ForesterUtil.isEmpty( tree_name ) || !ForesterUtil.isEmpty( tree_id ) ) ) {
324 ForesterUtil.fatalError( decorator.PRG_NAME,
325 "attempt to set same name or id on more than one phylogeny" );
327 if ( !ForesterUtil.isEmpty( tree_name ) ) {
328 phylogenies[ 0 ].setName( tree_name );
330 if ( !ForesterUtil.isEmpty( tree_id ) ) {
331 final String[] s_ary = tree_id.split( ":" );
332 phylogenies[ 0 ].setIdentifier( new Identifier( s_ary[ 1 ], s_ary[ 0 ] ) );
334 if ( !ForesterUtil.isEmpty( tree_desc ) ) {
335 for( int i = 0; i < phylogenies.length; ++i ) {
336 phylogenies[ i ].setDescription( tree_desc );
341 if ( advanced_table ) {
342 Map<String, Map<String, String>> table = null;
344 table = PhylogenyDecorator.parseMappingTable( mapping_infile );
346 catch ( final IOException e ) {
347 ForesterUtil.fatalError( decorator.PRG_NAME,
348 "failed to read \"" + mapping_infile + "\" [" + e.getMessage() + "]" );
350 PhylogenyDecorator.decorate( phylogenies,
353 numbers_of_chars_allowed_to_remove_if_not_found_in_map );
356 PhylogenyDecorator.decorate( phylogenies,
359 extract_bracketed_scientific_name,
361 cut_name_after_space,
362 process_name_intelligently,
364 numbers_of_chars_allowed_to_remove_if_not_found_in_map,
365 move_domain_numbers_at_end_to_middle );
368 catch ( final NullPointerException e ) {
369 ForesterUtil.unexpectedFatalError( decorator.PRG_NAME, e );
371 catch ( final Exception e ) {
372 ForesterUtil.fatalError( decorator.PRG_NAME, "failed to map [" + e + "]" );
375 final PhylogenyWriter w = new PhylogenyWriter();
376 w.toPhyloXML( phylogenies, 0, phylogenies_outfile, ForesterUtil.getLineSeparator() );
378 catch ( final IOException e ) {
379 ForesterUtil.fatalError( decorator.PRG_NAME, "failed to write output [" + e.getMessage() + "]" );
381 System.out.println();
382 ForesterUtil.programMessage( PRG_NAME, "wrote: " + phylogenies_outfile );
383 ForesterUtil.programMessage( PRG_NAME, "OK." );