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]{2,30}_[a-z]{3,30}(?:_[a-z][a-z0-9_]+)?)\\b" );
65 final public static Pattern TAXOMONY_SN_PATTERN_SN = Pattern
66 .compile( "\\b([A-Z][a-z]{2,30}[_ ][a-z]{3,30}(?:[_ ][a-z]{3,30})?)(?:\\b|_)?" );
67 final public static Pattern TAXOMONY_SN_PATTERN_STRAIN_1 = Pattern
68 .compile( "\\b([A-Z][a-z]{2,30}[_ ][a-z]{3,30}[_ ](?: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]{2,30}[_ ][a-z]{3,30}[_ ]\\((?:str|subsp|var)[a-z]{0,5}\\.?[_ ]\\S{1,60}\\))(?:\\b|_)?" );
71 final public static Pattern TAXOMONY_SN_PATTERN_SP = Pattern
72 .compile( "\\b([A-Z][a-z]{2,30}[_ ]sp\\.)(?:\\b|_)?" );
74 final public static Pattern TAXOMONY_SN_PATTERN_GENUS = Pattern.compile( "([A-Z][a-z]{2,30})" );
75 final private static Pattern TAXOMONY_CODE_PATTERN_PFS = Pattern.compile( "(?:\\b|_)[A-Z0-9]{4,}_("
76 + TAX_CODE + ")/\\d+-\\d+\\b" );
77 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFR = Pattern
78 .compile( "(?:\\b|_)[A-Z0-9]{1,}_(\\d{1,7})\\b" );
79 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFS = Pattern
80 .compile( "(?:\\b|_)[A-Z0-9]{4,}_(\\d{1,7})/\\d+-\\d+\\b" );
82 final public static PhylogenyParser createParserDependingFileContents( final File file,
83 final boolean phyloxml_validate_against_xsd )
84 throws FileNotFoundException, IOException {
85 PhylogenyParser parser = null;
86 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
87 if ( first_line.startsWith( "<" ) ) {
88 parser = PhyloXmlParser.createPhyloXmlParser();
89 if ( phyloxml_validate_against_xsd ) {
90 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
91 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
92 if ( xsd_url != null ) {
93 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
96 if ( ForesterConstants.RELEASE ) {
97 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
98 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
103 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
104 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
105 parser = new NexusPhylogeniesParser();
108 parser = new NHXParser();
113 final public static PhylogenyParser createParserDependingOnFileType( final File file,
114 final boolean phyloxml_validate_against_xsd )
115 throws FileNotFoundException, IOException {
116 PhylogenyParser parser = null;
117 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
118 if ( parser == null ) {
119 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
121 if ( ( parser != null ) && file.toString().toLowerCase().endsWith( ".zip" ) ) {
122 if ( parser instanceof PhyloXmlParser ) {
123 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
125 else if ( parser instanceof TolParser ) {
126 ( ( TolParser ) parser ).setZippedInputstream( true );
132 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
133 final boolean phyloxml_validate_against_xsd )
134 throws FileNotFoundException, IOException {
135 final String lc_filename = url.getFile().toString().toLowerCase();
136 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
137 if ( parser == null ) {
138 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
139 if ( first_line.startsWith( "<" ) ) {
140 parser = PhyloXmlParser.createPhyloXmlParser();
141 if ( phyloxml_validate_against_xsd ) {
142 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
143 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
144 if ( xsd_url != null ) {
145 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
148 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
149 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
153 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
154 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
155 parser = new NexusPhylogeniesParser();
158 parser = new NHXParser();
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 );
172 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
173 BufferedReader reader = null;
174 if ( ( source instanceof File ) || ( source instanceof String ) ) {
176 if ( source instanceof File ) {
180 f = new File( ( String ) source );
183 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
185 else if ( !f.isFile() ) {
186 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
188 else if ( !f.canRead() ) {
189 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
191 reader = new BufferedReader( new FileReader( f ) );
193 else if ( source instanceof InputStream ) {
194 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
196 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
197 reader = new BufferedReader( new StringReader( source.toString() ) );
200 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
201 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
206 public final static String extractScientificNameFromNodeName( final String name ) {
207 final Matcher m = TAXOMONY_SN_PATTERN.matcher( name );
209 return m.group( 1 ).replace( '_', ' ' );
211 final Matcher m_str1 = TAXOMONY_SN_PATTERN_STRAIN_1.matcher( name );
212 if ( m_str1.find() ) {
213 return m_str1.group( 1 ).replace( '_', ' ' );
215 final Matcher m_str2 = TAXOMONY_SN_PATTERN_STRAIN_2.matcher( name );
216 if ( m_str2.find() ) {
217 return m_str2.group( 1 ).replace( '_', ' ' );
219 final Matcher m_sn = TAXOMONY_SN_PATTERN_SN.matcher( name );
222 return m_sn.group( 1 ).replace( '_', ' ' );
225 final Matcher m_sp = TAXOMONY_SN_PATTERN_SP.matcher( name );
228 return m_sp.group( 1 ).replace( '_', ' ' );
233 public final static String extractTaxonomyCodeFromNodeName( final String name,
234 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
235 Matcher m = TAXOMONY_CODE_PATTERN_PFS.matcher( name );
239 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
240 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
241 m = TAXOMONY_CODE_PATTERN_PFR.matcher( name );
245 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
246 m = TAXOMONY_CODE_PATTERN_A.matcher( name );
255 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
256 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
257 throws PhyloXmlDataFormatException {
258 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) {
259 throw new IllegalArgumentException();
261 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
262 if ( !ForesterUtil.isEmpty( id ) ) {
263 if ( !node.getNodeData().isHasTaxonomy() ) {
264 node.getNodeData().setTaxonomy( new Taxonomy() );
266 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
270 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
271 if ( !ForesterUtil.isEmpty( code ) ) {
272 if ( !node.getNodeData().isHasTaxonomy() ) {
273 node.getNodeData().setTaxonomy( new Taxonomy() );
275 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
278 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
279 final String sn = extractScientificNameFromNodeName( node.getName() );
280 if ( !ForesterUtil.isEmpty( sn ) ) {
281 if ( !node.getNodeData().isHasTaxonomy() ) {
282 node.getNodeData().setTaxonomy( new Taxonomy() );
284 node.getNodeData().getTaxonomy().setScientificName( sn );
292 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
293 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
294 Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PFS.matcher( name );
298 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
299 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
300 m = TAXOMONY_UNIPROT_ID_PATTERN_PFR.matcher( name );
304 //else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
305 // m = TAXOMONY_UNIPROT_ID_PATTERN_A.matcher( name );
307 // return m.group( 1 );
314 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
315 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
318 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
319 return readPhylogenies( new File( file_name ) );
323 * Return null if it can not guess the parser to use based on name suffix.
328 final private static PhylogenyParser createParserDependingOnSuffix( final String filename,
329 final boolean phyloxml_validate_against_xsd ) {
330 PhylogenyParser parser = null;
331 final String filename_lc = filename.toLowerCase();
332 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
333 parser = new TolParser();
335 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( "phyloxml" ) || filename_lc.endsWith( ".zip" ) ) {
336 parser = PhyloXmlParser.createPhyloXmlParser();
337 if ( phyloxml_validate_against_xsd ) {
338 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
339 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
340 if ( xsd_url != null ) {
341 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
344 if ( ForesterConstants.RELEASE ) {
345 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
346 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
351 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
352 parser = new NexusPhylogeniesParser();
354 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
355 || filename_lc.endsWith( ".nwk" ) ) {
356 parser = new NHXParser();