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 public static Pattern TAXOMONY_CODE_PATTERN_4 = Pattern
69 .compile( "\\[(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA|CAP)\\]" );
70 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_1 = Pattern.compile( "\\b\\d{1,7}\\b" );
71 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_2 = Pattern.compile( "(\\d{1,7})[^0-9A-Za-z].*" );
72 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PF = Pattern.compile( "(\\d{1,7})/\\d+-\\d+" );
74 final public static PhylogenyParser createParserDependingFileContents( final File file,
75 final boolean phyloxml_validate_against_xsd )
76 throws FileNotFoundException, IOException {
77 PhylogenyParser parser = null;
78 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
79 if ( first_line.startsWith( "<" ) ) {
80 parser = new PhyloXmlParser();
81 if ( phyloxml_validate_against_xsd ) {
82 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
83 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
84 if ( xsd_url != null ) {
85 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
88 if ( ForesterConstants.RELEASE ) {
89 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
90 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
95 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
96 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
97 parser = new NexusPhylogeniesParser();
100 parser = new NHXParser();
105 final public static PhylogenyParser createParserDependingOnFileType( final File file,
106 final boolean phyloxml_validate_against_xsd )
107 throws FileNotFoundException, IOException {
108 PhylogenyParser parser = null;
109 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
110 if ( parser == null ) {
111 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
117 * Return null if it can not guess the parser to use based on name suffix.
122 final public static PhylogenyParser createParserDependingOnSuffix( final String filename,
123 final boolean phyloxml_validate_against_xsd ) {
124 PhylogenyParser parser = null;
125 final String filename_lc = filename.toLowerCase();
126 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
127 parser = new TolParser();
129 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" )
130 || filename_lc.endsWith( ".zip" ) ) {
131 parser = new PhyloXmlParser();
132 if ( phyloxml_validate_against_xsd ) {
133 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
134 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
135 if ( xsd_url != null ) {
136 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
139 if ( ForesterConstants.RELEASE ) {
140 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
141 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
146 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
147 parser = new NexusPhylogeniesParser();
149 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
150 || filename_lc.endsWith( ".nwk" ) ) {
151 parser = new NHXParser();
156 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
157 final boolean phyloxml_validate_against_xsd )
158 throws FileNotFoundException, IOException {
159 final String lc_filename = url.getFile().toString().toLowerCase();
160 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
161 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
162 if ( parser instanceof PhyloXmlParser ) {
163 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
165 else if ( parser instanceof TolParser ) {
166 ( ( TolParser ) parser ).setZippedInputstream( true );
169 if ( parser == null ) {
170 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
171 if ( first_line.startsWith( "<" ) ) {
172 parser = new PhyloXmlParser();
173 if ( phyloxml_validate_against_xsd ) {
174 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
175 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
176 if ( xsd_url != null ) {
177 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
180 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
181 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
185 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
186 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
187 parser = new NexusPhylogeniesParser();
190 parser = new NHXParser();
196 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
197 BufferedReader reader = null;
198 if ( ( source instanceof File ) || ( source instanceof String ) ) {
200 if ( source instanceof File ) {
204 f = new File( ( String ) source );
207 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
209 else if ( !f.isFile() ) {
210 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
212 else if ( !f.canRead() ) {
213 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
215 reader = new BufferedReader( new FileReader( f ) );
217 else if ( source instanceof InputStream ) {
218 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
220 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
221 reader = new BufferedReader( new StringReader( source.toString() ) );
224 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
225 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
230 public final static String extractTaxonomyCodeFromNodeName( final String name,
231 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
232 if ( ( name.indexOf( "_" ) > 0 )
233 && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) || ( name.indexOf( "/" ) > 4 ) ) ) {
234 final String[] s = name.split( "[_\\s]" );
235 if ( s.length > 1 ) {
236 final String str = s[ 1 ];
237 if ( !ForesterUtil.isEmpty( str ) ) {
238 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) {
239 final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( str );
245 final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( str );
246 if ( m1.matches() ) {
249 final Matcher m2 = TAXOMONY_CODE_PATTERN_2.matcher( str );
250 if ( m2.matches() ) {
251 return m2.group( 1 );
257 if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
258 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGRESSIVE ) ) {
259 final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( name );
260 if ( m1.matches() ) {
263 final Matcher m3 = TAXOMONY_CODE_PATTERN_3.matcher( name );
264 if ( m3.matches() ) {
265 return m3.group( 1 );
271 public final static String extractScientificNameFromNodeName( final String name ) {
272 final Matcher m1 = TAXOMONY_SN_PATTERN.matcher( name );
273 if ( m1.matches() ) {
274 return m1.group( 1 ).replace( '_', ' ' );
279 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
280 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
281 throws PhyloXmlDataFormatException {
282 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
283 if ( !ForesterUtil.isEmpty( id ) ) {
284 if ( !node.getNodeData().isHasTaxonomy() ) {
285 node.getNodeData().setTaxonomy( new Taxonomy() );
287 if ( ( node.getNodeData().getTaxonomy().getIdentifier() == null )
288 || ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getIdentifier().getValue() ) ) {
289 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
294 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
295 if ( !ForesterUtil.isEmpty( code ) ) {
296 if ( !node.getNodeData().isHasTaxonomy() ) {
297 node.getNodeData().setTaxonomy( new Taxonomy() );
299 if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
300 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
304 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
305 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGRESSIVE ) ) {
306 final String sn = extractScientificNameFromNodeName( node.getName() );
307 if ( !ForesterUtil.isEmpty( sn ) ) {
308 if ( !node.getNodeData().isHasTaxonomy() ) {
309 node.getNodeData().setTaxonomy( new Taxonomy() );
311 if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) {
312 node.getNodeData().getTaxonomy().setScientificName( sn );
321 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
322 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
323 if ( ( name.indexOf( "_" ) > 0 )
324 && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) || ( name.indexOf( "/" ) > 4 ) ) ) {
325 final String[] s = name.split( "[_\\s]" );
326 if ( s.length > 1 ) {
327 final String str = s[ 1 ];
328 if ( !ForesterUtil.isEmpty( str ) ) {
329 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) {
330 final Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PF.matcher( str );
336 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( str );
337 if ( m1.matches() ) {
340 final Matcher m2 = TAXOMONY_UNIPROT_ID_PATTERN_2.matcher( str );
341 if ( m2.matches() ) {
342 return m2.group( 1 );
348 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGRESSIVE ) {
349 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name );
350 if ( m1.matches() ) {
357 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
358 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
361 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
362 return readPhylogenies( new File( file_name ) );