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,}(?:_[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,}(?:[_ ][a-z]+)?)(?:\\b|_)" );
67 final private static Pattern TAXOMONY_CODE_PATTERN_PFS = Pattern.compile( "(?:\\b|_)[A-Z0-9]{4,}_("
68 + TAX_CODE + ")/\\d+-\\d+\\b" );
69 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFR = Pattern
70 .compile( "(?:\\b|_)[A-Z0-9]{1,}_(\\d{1,7})\\b" );
71 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFS = Pattern
72 .compile( "(?:\\b|_)[A-Z0-9]{4,}_(\\d{1,7})/\\d+-\\d+\\b" );
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 = PhyloXmlParser.createPhyloXmlParser();
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 );
113 if ( ( parser != null ) && file.toString().toLowerCase().endsWith( ".zip" ) ) {
114 if ( parser instanceof PhyloXmlParser ) {
115 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
117 else if ( parser instanceof TolParser ) {
118 ( ( TolParser ) parser ).setZippedInputstream( true );
124 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
125 final boolean phyloxml_validate_against_xsd )
126 throws FileNotFoundException, IOException {
127 final String lc_filename = url.getFile().toString().toLowerCase();
128 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
129 if ( parser == null ) {
130 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
131 if ( first_line.startsWith( "<" ) ) {
132 parser = PhyloXmlParser.createPhyloXmlParser();
133 if ( phyloxml_validate_against_xsd ) {
134 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
135 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
136 if ( xsd_url != null ) {
137 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
140 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
141 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
145 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
146 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
147 parser = new NexusPhylogeniesParser();
150 parser = new NHXParser();
153 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
154 if ( parser instanceof PhyloXmlParser ) {
155 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
157 else if ( parser instanceof TolParser ) {
158 ( ( TolParser ) parser ).setZippedInputstream( true );
164 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
165 BufferedReader reader = null;
166 if ( ( source instanceof File ) || ( source instanceof String ) ) {
168 if ( source instanceof File ) {
172 f = new File( ( String ) source );
175 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
177 else if ( !f.isFile() ) {
178 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
180 else if ( !f.canRead() ) {
181 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
183 reader = new BufferedReader( new FileReader( f ) );
185 else if ( source instanceof InputStream ) {
186 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
188 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
189 reader = new BufferedReader( new StringReader( source.toString() ) );
192 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
193 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
198 public final static String extractScientificNameFromNodeName( final String name ) {
199 final Matcher m = TAXOMONY_SN_PATTERN.matcher( name );
201 return m.group( 1 ).replace( '_', ' ' );
203 final Matcher m_sn = TAXOMONY_SN_PATTERN_SN.matcher( name );
205 return m_sn.group( 1 ).replace( '_', ' ' );
210 public final static String extractTaxonomyCodeFromNodeName( final String name,
211 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
212 Matcher m = TAXOMONY_CODE_PATTERN_PFS.matcher( name );
216 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
217 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
218 m = TAXOMONY_CODE_PATTERN_PFR.matcher( name );
222 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
223 m = TAXOMONY_CODE_PATTERN_A.matcher( name );
232 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
233 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
234 throws PhyloXmlDataFormatException {
235 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) {
236 throw new IllegalArgumentException();
238 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
239 if ( !ForesterUtil.isEmpty( id ) ) {
240 if ( !node.getNodeData().isHasTaxonomy() ) {
241 node.getNodeData().setTaxonomy( new Taxonomy() );
243 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
247 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
248 if ( !ForesterUtil.isEmpty( code ) ) {
249 if ( !node.getNodeData().isHasTaxonomy() ) {
250 node.getNodeData().setTaxonomy( new Taxonomy() );
252 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
255 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
256 final String sn = extractScientificNameFromNodeName( node.getName() );
257 if ( !ForesterUtil.isEmpty( sn ) ) {
258 if ( !node.getNodeData().isHasTaxonomy() ) {
259 node.getNodeData().setTaxonomy( new Taxonomy() );
261 node.getNodeData().getTaxonomy().setScientificName( sn );
269 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
270 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
271 Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PFS.matcher( name );
275 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
276 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
277 m = TAXOMONY_UNIPROT_ID_PATTERN_PFR.matcher( name );
281 //else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
282 // m = TAXOMONY_UNIPROT_ID_PATTERN_A.matcher( name );
284 // return m.group( 1 );
291 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
292 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
295 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
296 return readPhylogenies( new File( file_name ) );
300 * Return null if it can not guess the parser to use based on name suffix.
305 final private static PhylogenyParser createParserDependingOnSuffix( final String filename,
306 final boolean phyloxml_validate_against_xsd ) {
307 PhylogenyParser parser = null;
308 final String filename_lc = filename.toLowerCase();
309 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
310 parser = new TolParser();
312 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( "phyloxml" ) || filename_lc.endsWith( ".zip" ) ) {
313 parser = PhyloXmlParser.createPhyloXmlParser();
314 if ( phyloxml_validate_against_xsd ) {
315 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
316 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
317 if ( xsd_url != null ) {
318 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
321 if ( ForesterConstants.RELEASE ) {
322 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
323 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
328 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
329 parser = new NexusPhylogeniesParser();
331 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
332 || filename_lc.endsWith( ".nwk" ) ) {
333 parser = new NHXParser();