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: www.phylosoft.org/
27 package org.forester.io.parsers.util;
29 import java.io.BufferedReader;
31 import java.io.FileNotFoundException;
32 import java.io.FileReader;
33 import java.io.IOException;
34 import java.io.InputStream;
35 import java.io.InputStreamReader;
36 import java.io.StringReader;
38 import java.util.regex.Matcher;
39 import java.util.regex.Pattern;
41 import org.forester.io.parsers.PhylogenyParser;
42 import org.forester.io.parsers.nexus.NexusPhylogeniesParser;
43 import org.forester.io.parsers.nhx.NHXParser;
44 import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
45 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
46 import org.forester.io.parsers.phyloxml.PhyloXmlParser;
47 import org.forester.io.parsers.tol.TolParser;
48 import org.forester.phylogeny.Phylogeny;
49 import org.forester.phylogeny.PhylogenyMethods;
50 import org.forester.phylogeny.PhylogenyNode;
51 import org.forester.phylogeny.data.Identifier;
52 import org.forester.phylogeny.data.Taxonomy;
53 import org.forester.util.ForesterConstants;
54 import org.forester.util.ForesterUtil;
56 public final class ParserUtils {
58 final public static Pattern TAXOMONY_SN_PATTERN = Pattern
59 .compile( "[^_]{2,}_([A-Z][a-z]+_[a-z]{2,}(_[A-Za-z]\\w+|))\\b" );
60 final public static Pattern TAXOMONY_CODE_PATTERN_1 = Pattern
61 .compile( "\\b[A-Z9][A-Z]{2}[A-Z0-9]{2}|RAT|PIG|PEA|CAP\\b" );
62 final private static Pattern TAXOMONY_CODE_PATTERN_2 = Pattern
63 .compile( "([A-Z9][A-Z]{2}[A-Z0-9]{2}|RAT|PIG|PEA|CAP)[^0-9A-Za-z].*" );
64 final private static Pattern TAXOMONY_CODE_PATTERN_3 = Pattern
65 .compile( "_([A-Z9][A-Z]{2}[A-Z0-9]{2}|RAT|PIG|PEA|CAP)_" );
66 final private static Pattern TAXOMONY_CODE_PATTERN_PF = Pattern
67 .compile( "([A-Z9][A-Z]{2}[A-Z0-9]{2}|RAT|PIG|PEA|CAP)/\\d+-\\d+" );
68 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_1 = Pattern.compile( "\\b\\d{1,7}\\b" );
69 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_2 = Pattern.compile( "(\\d{1,7})[^0-9A-Za-z].*" );
70 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PF = Pattern.compile( "(\\d{1,7})/\\d+-\\d+" );
72 final public static PhylogenyParser createParserDependingFileContents( final File file,
73 final boolean phyloxml_validate_against_xsd )
74 throws FileNotFoundException, IOException {
75 PhylogenyParser parser = null;
76 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
77 if ( first_line.startsWith( "<" ) ) {
78 parser = new PhyloXmlParser();
79 if ( phyloxml_validate_against_xsd ) {
80 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
81 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
82 if ( xsd_url != null ) {
83 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
86 if ( ForesterConstants.RELEASE ) {
87 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
88 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
93 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
94 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
95 parser = new NexusPhylogeniesParser();
98 parser = new NHXParser();
103 final public static PhylogenyParser createParserDependingOnFileType( final File file,
104 final boolean phyloxml_validate_against_xsd )
105 throws FileNotFoundException, IOException {
106 PhylogenyParser parser = null;
107 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
108 if ( parser == null ) {
109 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
115 * Return null if it can not guess the parser to use based on name suffix.
120 final public static PhylogenyParser createParserDependingOnSuffix( final String filename,
121 final boolean phyloxml_validate_against_xsd ) {
122 PhylogenyParser parser = null;
123 final String filename_lc = filename.toLowerCase();
124 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
125 parser = new TolParser();
127 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" )
128 || filename_lc.endsWith( ".zip" ) ) {
129 parser = new PhyloXmlParser();
130 if ( phyloxml_validate_against_xsd ) {
131 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
132 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
133 if ( xsd_url != null ) {
134 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
137 if ( ForesterConstants.RELEASE ) {
138 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
139 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
144 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
145 parser = new NexusPhylogeniesParser();
147 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
148 || filename_lc.endsWith( ".nwk" ) ) {
149 parser = new NHXParser();
154 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
155 final boolean phyloxml_validate_against_xsd )
156 throws FileNotFoundException, IOException {
157 final String lc_filename = url.getFile().toString().toLowerCase();
158 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
159 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
160 if ( parser instanceof PhyloXmlParser ) {
161 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
163 else if ( parser instanceof TolParser ) {
164 ( ( TolParser ) parser ).setZippedInputstream( true );
167 if ( parser == null ) {
168 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
169 if ( first_line.startsWith( "<" ) ) {
170 parser = new PhyloXmlParser();
171 if ( phyloxml_validate_against_xsd ) {
172 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
173 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
174 if ( xsd_url != null ) {
175 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
178 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
179 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
183 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
184 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
185 parser = new NexusPhylogeniesParser();
188 parser = new NHXParser();
194 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
195 BufferedReader reader = null;
196 if ( ( source instanceof File ) || ( source instanceof String ) ) {
198 if ( source instanceof File ) {
202 f = new File( ( String ) source );
205 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
207 else if ( !f.isFile() ) {
208 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
210 else if ( !f.canRead() ) {
211 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
213 reader = new BufferedReader( new FileReader( f ) );
215 else if ( source instanceof InputStream ) {
216 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
218 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
219 reader = new BufferedReader( new StringReader( source.toString() ) );
222 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
223 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
228 public final static String extractTaxonomyCodeFromNodeName( final String name,
229 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
230 if ( ( name.indexOf( "_" ) > 0 )
231 && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) || ( name.indexOf( "/" ) > 4 ) ) ) {
232 final String[] s = name.split( "[_\\s]" );
233 if ( s.length > 1 ) {
234 final String str = s[ 1 ];
235 if ( !ForesterUtil.isEmpty( str ) ) {
236 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) {
237 final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( str );
243 final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( str );
244 if ( m1.matches() ) {
247 final Matcher m2 = TAXOMONY_CODE_PATTERN_2.matcher( str );
248 if ( m2.matches() ) {
249 return m2.group( 1 );
255 if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
256 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGRESSIVE ) ) {
257 final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( name );
258 if ( m1.matches() ) {
261 final Matcher m3 = TAXOMONY_CODE_PATTERN_3.matcher( name );
262 if ( m3.matches() ) {
263 return m3.group( 1 );
269 public final static String extractScientificNameFromNodeName( final String name ) {
270 final Matcher m1 = TAXOMONY_SN_PATTERN.matcher( name );
271 if ( m1.matches() ) {
272 return m1.group( 1 ).replace( '_', ' ' );
277 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
278 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
279 throws PhyloXmlDataFormatException {
280 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
281 if ( !ForesterUtil.isEmpty( id ) ) {
282 if ( !node.getNodeData().isHasTaxonomy() ) {
283 node.getNodeData().setTaxonomy( new Taxonomy() );
285 if ( ( node.getNodeData().getTaxonomy().getIdentifier() == null )
286 || ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getIdentifier().getValue() ) ) {
287 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
292 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
293 if ( !ForesterUtil.isEmpty( code ) ) {
294 if ( !node.getNodeData().isHasTaxonomy() ) {
295 node.getNodeData().setTaxonomy( new Taxonomy() );
297 if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
298 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
302 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
303 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGRESSIVE ) ) {
304 final String sn = extractScientificNameFromNodeName( node.getName() );
305 if ( !ForesterUtil.isEmpty( sn ) ) {
306 if ( !node.getNodeData().isHasTaxonomy() ) {
307 node.getNodeData().setTaxonomy( new Taxonomy() );
309 if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) {
310 node.getNodeData().getTaxonomy().setScientificName( sn );
319 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
320 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
321 if ( ( name.indexOf( "_" ) > 0 )
322 && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) || ( name.indexOf( "/" ) > 4 ) ) ) {
323 final String[] s = name.split( "[_\\s]" );
324 if ( s.length > 1 ) {
325 final String str = s[ 1 ];
326 if ( !ForesterUtil.isEmpty( str ) ) {
327 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) {
328 final Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PF.matcher( str );
334 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( str );
335 if ( m1.matches() ) {
338 final Matcher m2 = TAXOMONY_UNIPROT_ID_PATTERN_2.matcher( str );
339 if ( m2.matches() ) {
340 return m2.group( 1 );
346 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGRESSIVE ) {
347 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name );
348 if ( m1.matches() ) {
355 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
356 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
359 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
360 return readPhylogenies( new File( file_name ) );