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_SN_PATTERN = Pattern
60 .compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_([A-Z][a-z]+_[a-z]{2,}(?:_[a-z][a-z0-9_]+)?)\\b" );
61 final private static Pattern TAXOMONY_CODE_PATTERN_PFS = Pattern.compile( "(?:\\b|_)[A-Z0-9]{4,}_("
62 + TAX_CODE + ")/\\d+-\\d+\\b" );
63 final public static Pattern TAXOMONY_CODE_PATTERN_PFR = Pattern.compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_("
64 + TAX_CODE + ")\\b" );
65 final public static Pattern TAXOMONY_CODE_PATTERN_A = Pattern.compile( "(?:\\b|_)(" + TAX_CODE + ")\\b" );
66 final public static Pattern TAXOMONY_CODE_PATTERN_BRACKETED = Pattern.compile( "\\[(" + TAX_CODE + ")\\]" );
67 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_A = Pattern.compile( "(?:\\b|_)(\\d{1,7})\\b" );
68 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFS = Pattern
69 .compile( "(?:\\b|_)[A-Z0-9]{4,}_(\\d{1,7})/\\d+-\\d+\\b" );
70 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFR = Pattern
71 .compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_(\\d{1,7})\\b" );
73 final public static PhylogenyParser createParserDependingFileContents( final File file,
74 final boolean phyloxml_validate_against_xsd )
75 throws FileNotFoundException, IOException {
76 PhylogenyParser parser = null;
77 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
78 if ( first_line.startsWith( "<" ) ) {
79 parser = PhyloXmlParser.createPhyloXmlParser();
80 if ( phyloxml_validate_against_xsd ) {
81 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
82 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
83 if ( xsd_url != null ) {
84 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
87 if ( ForesterConstants.RELEASE ) {
88 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
89 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
94 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
95 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
96 parser = new NexusPhylogeniesParser();
99 parser = new NHXParser();
104 final public static PhylogenyParser createParserDependingOnFileType( final File file,
105 final boolean phyloxml_validate_against_xsd )
106 throws FileNotFoundException, IOException {
107 PhylogenyParser parser = null;
108 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
109 if ( parser == null ) {
110 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
112 if ( ( parser != null ) && file.toString().toLowerCase().endsWith( ".zip" ) ) {
113 if ( parser instanceof PhyloXmlParser ) {
114 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
116 else if ( parser instanceof TolParser ) {
117 ( ( TolParser ) parser ).setZippedInputstream( true );
124 * Return null if it can not guess the parser to use based on name suffix.
129 final private static PhylogenyParser createParserDependingOnSuffix( final String filename,
130 final boolean phyloxml_validate_against_xsd ) {
131 PhylogenyParser parser = null;
132 final String filename_lc = filename.toLowerCase();
133 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
134 parser = new TolParser();
136 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( "phyloxml" ) || filename_lc.endsWith( ".zip" ) ) {
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 if ( ForesterConstants.RELEASE ) {
146 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
147 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
152 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
153 parser = new NexusPhylogeniesParser();
155 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
156 || filename_lc.endsWith( ".nwk" ) ) {
157 parser = new NHXParser();
162 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
163 final boolean phyloxml_validate_against_xsd )
164 throws FileNotFoundException, IOException {
165 final String lc_filename = url.getFile().toString().toLowerCase();
166 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
167 if ( parser == null ) {
168 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
169 if ( first_line.startsWith( "<" ) ) {
170 parser = PhyloXmlParser.createPhyloXmlParser();
171 if ( phyloxml_validate_against_xsd ) {
172 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
173 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
174 if ( xsd_url != null ) {
175 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
178 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
179 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
183 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
184 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
185 parser = new NexusPhylogeniesParser();
188 parser = new NHXParser();
191 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
192 if ( parser instanceof PhyloXmlParser ) {
193 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
195 else if ( parser instanceof TolParser ) {
196 ( ( TolParser ) parser ).setZippedInputstream( true );
202 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
203 BufferedReader reader = null;
204 if ( ( source instanceof File ) || ( source instanceof String ) ) {
206 if ( source instanceof File ) {
210 f = new File( ( String ) source );
213 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
215 else if ( !f.isFile() ) {
216 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
218 else if ( !f.canRead() ) {
219 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
221 reader = new BufferedReader( new FileReader( f ) );
223 else if ( source instanceof InputStream ) {
224 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
226 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
227 reader = new BufferedReader( new StringReader( source.toString() ) );
230 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
231 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
236 public final static String extractScientificNameFromNodeName( final String name ) {
237 final Matcher m = TAXOMONY_SN_PATTERN.matcher( name );
239 return m.group( 1 ).replace( '_', ' ' );
244 public final static String extractTaxonomyCodeFromNodeName( final String name,
245 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
246 Matcher m = TAXOMONY_CODE_PATTERN_PFS.matcher( name );
250 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
251 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
252 m = TAXOMONY_CODE_PATTERN_PFR.matcher( name );
256 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
257 m = TAXOMONY_CODE_PATTERN_A.matcher( name );
266 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
267 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
268 throws PhyloXmlDataFormatException {
269 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) {
270 throw new IllegalArgumentException();
272 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
273 if ( !ForesterUtil.isEmpty( id ) ) {
274 if ( !node.getNodeData().isHasTaxonomy() ) {
275 node.getNodeData().setTaxonomy( new Taxonomy() );
277 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
281 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
282 if ( !ForesterUtil.isEmpty( code ) ) {
283 if ( !node.getNodeData().isHasTaxonomy() ) {
284 node.getNodeData().setTaxonomy( new Taxonomy() );
286 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
289 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
290 final String sn = extractScientificNameFromNodeName( node.getName() );
291 if ( !ForesterUtil.isEmpty( sn ) ) {
292 if ( !node.getNodeData().isHasTaxonomy() ) {
293 node.getNodeData().setTaxonomy( new Taxonomy() );
295 node.getNodeData().getTaxonomy().setScientificName( sn );
303 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
304 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
305 Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PFS.matcher( name );
309 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
310 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
311 m = TAXOMONY_UNIPROT_ID_PATTERN_PFR.matcher( name );
315 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
316 m = TAXOMONY_UNIPROT_ID_PATTERN_A.matcher( name );
325 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
326 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
329 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
330 return readPhylogenies( new File( file_name ) );