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 String TAX_CODE = "(?:[A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA";
59 final public static Pattern TAXOMONY_CODE_PATTERN_A = Pattern.compile( "(?:\\b|_)(" + TAX_CODE + ")\\b" );
60 final public static Pattern TAXOMONY_CODE_PATTERN_BRACKETED = Pattern.compile( "\\[(" + TAX_CODE + ")\\]" );
61 final public static Pattern TAXOMONY_CODE_PATTERN_PFR = Pattern.compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_("
62 + TAX_CODE + ")\\b" );
63 final public static Pattern TAXOMONY_SN_PATTERN = Pattern
64 .compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_([A-Z][a-z]+_[a-z]{2,30}(?:_[a-z][a-z0-9_]+)?)\\b" );
65 final public static Pattern TAXOMONY_SN_PATTERN_SN = Pattern
66 .compile( "\\b([A-Z][a-z]+[_ ][a-z]{2,30}(?:[_ ][a-z]{2,30})?)(?:\\b|_)" );
67 final public static Pattern TAXOMONY_SN_PATTERN_STRAIN_1 = Pattern
68 .compile( "\\b([A-Z][a-z]+[_ ][a-z]{2,30}[_ ](?:str|subsp|var)[a-z]{0,5}\\.?[_ ]\\S{1,60})(?:\\b|_)" );
69 final public static Pattern TAXOMONY_SN_PATTERN_STRAIN_2 = Pattern
70 .compile( "\\b([A-Z][a-z]+[_ ][a-z]{2,30}[_ ]\\((?:str|subsp|var)[a-z]{0,5}\\.?[_ ]\\S{1,60}\\))(?:\\b|_)?" );
71 final public static Pattern TAXOMONY_SN_PATTERN_GENUS = Pattern.compile( "([A-Z][a-z]{2,30})" );
72 final private static Pattern TAXOMONY_CODE_PATTERN_PFS = Pattern.compile( "(?:\\b|_)[A-Z0-9]{4,}_("
73 + TAX_CODE + ")/\\d+-\\d+\\b" );
74 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFR = Pattern
75 .compile( "(?:\\b|_)[A-Z0-9]{1,}_(\\d{1,7})\\b" );
76 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFS = Pattern
77 .compile( "(?:\\b|_)[A-Z0-9]{4,}_(\\d{1,7})/\\d+-\\d+\\b" );
79 final public static PhylogenyParser createParserDependingFileContents( final File file,
80 final boolean phyloxml_validate_against_xsd )
81 throws FileNotFoundException, IOException {
82 PhylogenyParser parser = null;
83 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
84 if ( first_line.startsWith( "<" ) ) {
85 parser = PhyloXmlParser.createPhyloXmlParser();
86 if ( phyloxml_validate_against_xsd ) {
87 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
88 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
89 if ( xsd_url != null ) {
90 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
93 if ( ForesterConstants.RELEASE ) {
94 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
95 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
100 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
101 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
102 parser = new NexusPhylogeniesParser();
105 parser = new NHXParser();
110 final public static PhylogenyParser createParserDependingOnFileType( final File file,
111 final boolean phyloxml_validate_against_xsd )
112 throws FileNotFoundException, IOException {
113 PhylogenyParser parser = null;
114 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
115 if ( parser == null ) {
116 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
118 if ( ( parser != null ) && file.toString().toLowerCase().endsWith( ".zip" ) ) {
119 if ( parser instanceof PhyloXmlParser ) {
120 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
122 else if ( parser instanceof TolParser ) {
123 ( ( TolParser ) parser ).setZippedInputstream( true );
129 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
130 final boolean phyloxml_validate_against_xsd )
131 throws FileNotFoundException, IOException {
132 final String lc_filename = url.getFile().toString().toLowerCase();
133 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
134 if ( parser == null ) {
135 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
136 if ( first_line.startsWith( "<" ) ) {
137 parser = PhyloXmlParser.createPhyloXmlParser();
138 if ( phyloxml_validate_against_xsd ) {
139 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
140 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
141 if ( xsd_url != null ) {
142 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
145 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
146 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
150 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
151 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
152 parser = new NexusPhylogeniesParser();
155 parser = new NHXParser();
158 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
159 if ( parser instanceof PhyloXmlParser ) {
160 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
162 else if ( parser instanceof TolParser ) {
163 ( ( TolParser ) parser ).setZippedInputstream( true );
169 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
170 BufferedReader reader = null;
171 if ( ( source instanceof File ) || ( source instanceof String ) ) {
173 if ( source instanceof File ) {
177 f = new File( ( String ) source );
180 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
182 else if ( !f.isFile() ) {
183 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
185 else if ( !f.canRead() ) {
186 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
188 reader = new BufferedReader( new FileReader( f ) );
190 else if ( source instanceof InputStream ) {
191 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
193 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
194 reader = new BufferedReader( new StringReader( source.toString() ) );
197 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
198 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
203 public final static String extractScientificNameFromNodeName( final String name ) {
204 final Matcher m = TAXOMONY_SN_PATTERN.matcher( name );
206 return m.group( 1 ).replace( '_', ' ' );
208 final Matcher m_str1 = TAXOMONY_SN_PATTERN_STRAIN_1.matcher( name );
209 if ( m_str1.find() ) {
210 return m_str1.group( 1 ).replace( '_', ' ' );
212 final Matcher m_str2 = TAXOMONY_SN_PATTERN_STRAIN_2.matcher( name );
213 if ( m_str2.find() ) {
214 return m_str2.group( 1 ).replace( '_', ' ' );
216 final Matcher m_sn = TAXOMONY_SN_PATTERN_SN.matcher( name );
218 return m_sn.group( 1 ).replace( '_', ' ' );
223 public final static String extractTaxonomyCodeFromNodeName( final String name,
224 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
225 Matcher m = TAXOMONY_CODE_PATTERN_PFS.matcher( name );
229 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
230 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
231 m = TAXOMONY_CODE_PATTERN_PFR.matcher( name );
235 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
236 m = TAXOMONY_CODE_PATTERN_A.matcher( name );
245 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
246 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
247 throws PhyloXmlDataFormatException {
248 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) {
249 throw new IllegalArgumentException();
251 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
252 if ( !ForesterUtil.isEmpty( id ) ) {
253 if ( !node.getNodeData().isHasTaxonomy() ) {
254 node.getNodeData().setTaxonomy( new Taxonomy() );
256 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
260 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
261 if ( !ForesterUtil.isEmpty( code ) ) {
262 if ( !node.getNodeData().isHasTaxonomy() ) {
263 node.getNodeData().setTaxonomy( new Taxonomy() );
265 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
268 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
269 final String sn = extractScientificNameFromNodeName( node.getName() );
270 if ( !ForesterUtil.isEmpty( sn ) ) {
271 if ( !node.getNodeData().isHasTaxonomy() ) {
272 node.getNodeData().setTaxonomy( new Taxonomy() );
274 node.getNodeData().getTaxonomy().setScientificName( sn );
282 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
283 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
284 Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PFS.matcher( name );
288 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
289 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
290 m = TAXOMONY_UNIPROT_ID_PATTERN_PFR.matcher( name );
294 //else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
295 // m = TAXOMONY_UNIPROT_ID_PATTERN_A.matcher( name );
297 // return m.group( 1 );
304 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
305 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
308 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
309 return readPhylogenies( new File( file_name ) );
313 * Return null if it can not guess the parser to use based on name suffix.
318 final private static PhylogenyParser createParserDependingOnSuffix( final String filename,
319 final boolean phyloxml_validate_against_xsd ) {
320 PhylogenyParser parser = null;
321 final String filename_lc = filename.toLowerCase();
322 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
323 parser = new TolParser();
325 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( "phyloxml" ) || filename_lc.endsWith( ".zip" ) ) {
326 parser = PhyloXmlParser.createPhyloXmlParser();
327 if ( phyloxml_validate_against_xsd ) {
328 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
329 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
330 if ( xsd_url != null ) {
331 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
334 if ( ForesterConstants.RELEASE ) {
335 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
336 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
341 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
342 parser = new NexusPhylogeniesParser();
344 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
345 || filename_lc.endsWith( ".nwk" ) ) {
346 parser = new NHXParser();