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_CODE_PATTERN_1 = Pattern.compile( "\\b[A-Z0-9]{5}|RAT|PIG|PEA|CAP\\b" );
59 final private static Pattern TAXOMONY_CODE_PATTERN_2 = Pattern
60 .compile( "([A-Z0-9]{5}|RAT|PIG|PEA|CAP)[^0-9A-Za-z].*" );
61 final private static Pattern TAXOMONY_CODE_PATTERN_PF = Pattern
62 .compile( "([A-Z0-9]{5}|RAT|PIG|PEA|CAP)/\\d+-\\d+" );
63 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_1 = Pattern.compile( "\\b\\d{1,7}\\b" );
64 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_2 = Pattern.compile( "(\\d{1,7})[^0-9A-Za-z].*" );
65 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PF = Pattern.compile( "(\\d{1,7})/\\d+-\\d+" );
67 final public static PhylogenyParser createParserDependingFileContents( final File file,
68 final boolean phyloxml_validate_against_xsd )
69 throws FileNotFoundException, IOException {
70 PhylogenyParser parser = null;
71 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
72 if ( first_line.startsWith( "<" ) ) {
73 parser = new PhyloXmlParser();
74 if ( phyloxml_validate_against_xsd ) {
75 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
76 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
77 if ( xsd_url != null ) {
78 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
81 if ( ForesterConstants.RELEASE ) {
82 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
83 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
88 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
89 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
90 parser = new NexusPhylogeniesParser();
93 parser = new NHXParser();
98 final public static PhylogenyParser createParserDependingOnFileType( final File file,
99 final boolean phyloxml_validate_against_xsd )
100 throws FileNotFoundException, IOException {
101 PhylogenyParser parser = null;
102 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
103 if ( parser == null ) {
104 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
110 * Return null if it can not guess the parser to use based on name suffix.
115 final public static PhylogenyParser createParserDependingOnSuffix( final String filename,
116 final boolean phyloxml_validate_against_xsd ) {
117 PhylogenyParser parser = null;
118 final String filename_lc = filename.toLowerCase();
119 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
120 parser = new TolParser();
122 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" )
123 || filename_lc.endsWith( ".zip" ) ) {
124 parser = new PhyloXmlParser();
125 if ( phyloxml_validate_against_xsd ) {
126 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
127 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
128 if ( xsd_url != null ) {
129 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
132 if ( ForesterConstants.RELEASE ) {
133 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
134 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
139 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
140 parser = new NexusPhylogeniesParser();
142 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
143 || filename_lc.endsWith( ".nwk" ) ) {
144 parser = new NHXParser();
149 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
150 final boolean phyloxml_validate_against_xsd )
151 throws FileNotFoundException, IOException {
152 final String lc_filename = url.getFile().toString().toLowerCase();
153 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
154 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
155 if ( parser instanceof PhyloXmlParser ) {
156 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
158 else if ( parser instanceof TolParser ) {
159 ( ( TolParser ) parser ).setZippedInputstream( true );
162 if ( parser == null ) {
163 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
164 if ( first_line.startsWith( "<" ) ) {
165 parser = new PhyloXmlParser();
166 if ( phyloxml_validate_against_xsd ) {
167 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
168 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
169 if ( xsd_url != null ) {
170 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
173 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
174 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
178 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
179 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
180 parser = new NexusPhylogeniesParser();
183 parser = new NHXParser();
189 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
190 BufferedReader reader = null;
191 if ( ( source instanceof File ) || ( source instanceof String ) ) {
193 if ( source instanceof File ) {
197 f = new File( ( String ) source );
200 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
202 else if ( !f.isFile() ) {
203 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
205 else if ( !f.canRead() ) {
206 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
208 reader = new BufferedReader( new FileReader( f ) );
210 else if ( source instanceof InputStream ) {
211 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
213 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
214 reader = new BufferedReader( new StringReader( source.toString() ) );
217 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
218 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
223 public final static String extractTaxonomyCodeFromNodeName( final String name,
224 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
225 if ( ( name.indexOf( "_" ) > 0 )
226 && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) || ( name.indexOf( "/" ) > 4 ) ) ) {
227 final String[] s = name.split( "[_\\s]" );
228 if ( s.length > 1 ) {
229 final String str = s[ 1 ];
230 if ( !ForesterUtil.isEmpty( str ) ) {
231 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) {
232 final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( str );
238 final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( str );
239 if ( m1.matches() ) {
242 final Matcher m2 = TAXOMONY_CODE_PATTERN_2.matcher( str );
243 if ( m2.matches() ) {
244 return m2.group( 1 );
250 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.YES ) {
251 final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( name );
252 if ( m1.matches() ) {
259 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
260 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
261 if ( ( name.indexOf( "_" ) > 0 )
262 && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) || ( name.indexOf( "/" ) > 4 ) ) ) {
263 final String[] s = name.split( "[_\\s]" );
264 if ( s.length > 1 ) {
265 final String str = s[ 1 ];
266 if ( !ForesterUtil.isEmpty( str ) ) {
267 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) {
268 final Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PF.matcher( str );
274 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( str );
275 if ( m1.matches() ) {
278 final Matcher m2 = TAXOMONY_UNIPROT_ID_PATTERN_2.matcher( str );
279 if ( m2.matches() ) {
280 return m2.group( 1 );
286 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.YES ) {
287 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name );
288 if ( m1.matches() ) {
295 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
296 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
299 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
300 return readPhylogenies( new File( file_name ) );
303 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
304 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
305 throws PhyloXmlDataFormatException {
306 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
307 if ( !ForesterUtil.isEmpty( id ) ) {
308 if ( !node.getNodeData().isHasTaxonomy() ) {
309 node.getNodeData().setTaxonomy( new Taxonomy() );
311 if ( node.getNodeData().getTaxonomy().getIdentifier() == null || ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getIdentifier().getValue() ) ) {
312 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
317 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
318 if ( !ForesterUtil.isEmpty( code ) ) {
319 if ( !node.getNodeData().isHasTaxonomy() ) {
320 node.getNodeData().setTaxonomy( new Taxonomy() );
322 if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
323 node.getNodeData().getTaxonomy().setTaxonomyCode( code );