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|CAP";
59 final public static Pattern TAXOMONY_SN_PATTERN = Pattern
60 .compile( "[A-Z0-9]{2,}_([A-Z][a-z]+_[a-z]{2,}(?:_[a-z][a-z0-9_]+)?)\\b" );
61 final public static Pattern TAXOMONY_CODE_PATTERN_R1 = Pattern.compile( "[A-Z0-9]+_(" + TAX_CODE + ")\\b" );
62 final public static Pattern TAXOMONY_CODE_PATTERN_R2 = Pattern.compile( "(?:\\b|_)(" + TAX_CODE + ")\\b" );
63 final private static Pattern TAXOMONY_CODE_PATTERN_PF = Pattern.compile( "[A-Z0-9]{2,}_(" + TAX_CODE
65 final public static Pattern TAXOMONY_CODE_PATTERN_4 = Pattern.compile( "\\[(" + TAX_CODE + ")\\]" );
66 final public static Pattern TAXOMONY_CODE_PATTERN_6 = Pattern.compile( "\\[([A-Z9][A-Z]{2}[A-Z0-9]{3})\\]" );
67 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_1 = Pattern.compile( "\\b\\d{1,7}\\b" );
68 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_2 = Pattern.compile( "(\\d{1,7})[^0-9A-Za-z].*" );
69 final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PF = Pattern.compile( "(\\d{1,7})/\\d+-\\d+" );
71 final public static PhylogenyParser createParserDependingFileContents( final File file,
72 final boolean phyloxml_validate_against_xsd )
73 throws FileNotFoundException, IOException {
74 PhylogenyParser parser = null;
75 final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase();
76 if ( first_line.startsWith( "<" ) ) {
77 parser = new PhyloXmlParser();
78 if ( phyloxml_validate_against_xsd ) {
79 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
80 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
81 if ( xsd_url != null ) {
82 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
85 if ( ForesterConstants.RELEASE ) {
86 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
87 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
92 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
93 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
94 parser = new NexusPhylogeniesParser();
97 parser = new NHXParser();
102 final public static PhylogenyParser createParserDependingOnFileType( final File file,
103 final boolean phyloxml_validate_against_xsd )
104 throws FileNotFoundException, IOException {
105 PhylogenyParser parser = null;
106 parser = ParserUtils.createParserDependingOnSuffix( file.getName(), phyloxml_validate_against_xsd );
107 if ( parser == null ) {
108 parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd );
114 * Return null if it can not guess the parser to use based on name suffix.
119 final public static PhylogenyParser createParserDependingOnSuffix( final String filename,
120 final boolean phyloxml_validate_against_xsd ) {
121 PhylogenyParser parser = null;
122 final String filename_lc = filename.toLowerCase();
123 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
124 parser = new TolParser();
126 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" )
127 || filename_lc.endsWith( ".zip" ) ) {
128 parser = new PhyloXmlParser();
129 if ( phyloxml_validate_against_xsd ) {
130 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
131 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
132 if ( xsd_url != null ) {
133 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
136 if ( ForesterConstants.RELEASE ) {
137 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
138 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
143 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
144 parser = new NexusPhylogeniesParser();
146 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
147 || filename_lc.endsWith( ".nwk" ) ) {
148 parser = new NHXParser();
153 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
154 final boolean phyloxml_validate_against_xsd )
155 throws FileNotFoundException, IOException {
156 final String lc_filename = url.getFile().toString().toLowerCase();
157 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
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 );
166 if ( parser == null ) {
167 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
168 if ( first_line.startsWith( "<" ) ) {
169 parser = new PhyloXmlParser();
170 if ( phyloxml_validate_against_xsd ) {
171 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
172 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
173 if ( xsd_url != null ) {
174 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
177 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
178 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
182 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
183 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
184 parser = new NexusPhylogeniesParser();
187 parser = new NHXParser();
193 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
194 BufferedReader reader = null;
195 if ( ( source instanceof File ) || ( source instanceof String ) ) {
197 if ( source instanceof File ) {
201 f = new File( ( String ) source );
204 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
206 else if ( !f.isFile() ) {
207 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
209 else if ( !f.canRead() ) {
210 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
212 reader = new BufferedReader( new FileReader( f ) );
214 else if ( source instanceof InputStream ) {
215 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
217 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
218 reader = new BufferedReader( new StringReader( source.toString() ) );
221 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
222 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
227 public final static String extractTaxonomyCodeFromNodeName( final String name,
228 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
229 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) {
230 final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( name );
235 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
236 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
237 final Matcher m1 = TAXOMONY_CODE_PATTERN_R1.matcher( name );
239 return m1.group( 1 );
241 final Matcher m2 = TAXOMONY_CODE_PATTERN_R2.matcher( name );
243 return m2.group( 1 );
249 public final static String extractScientificNameFromNodeName( final String name ) {
250 final Matcher m1 = TAXOMONY_SN_PATTERN.matcher( name );
252 return m1.group( 1 ).replace( '_', ' ' );
257 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
258 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
259 throws PhyloXmlDataFormatException {
260 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) {
261 throw new IllegalArgumentException();
263 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
264 if ( !ForesterUtil.isEmpty( id ) ) {
265 if ( !node.getNodeData().isHasTaxonomy() ) {
266 node.getNodeData().setTaxonomy( new Taxonomy() );
268 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
272 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
273 if ( !ForesterUtil.isEmpty( code ) ) {
274 if ( !node.getNodeData().isHasTaxonomy() ) {
275 node.getNodeData().setTaxonomy( new Taxonomy() );
277 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
280 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED || taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
281 final String sn = extractScientificNameFromNodeName( node.getName() );
282 if ( !ForesterUtil.isEmpty( sn ) ) {
283 if ( !node.getNodeData().isHasTaxonomy() ) {
284 node.getNodeData().setTaxonomy( new Taxonomy() );
286 node.getNodeData().getTaxonomy().setScientificName( sn );
294 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
295 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
296 if ( ( name.indexOf( "_" ) > 0 )
297 && ( ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED ) || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) || ( ( ( name
298 .indexOf( "/" ) > 4 ) && ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) ) ) ) ) {
299 final String[] s = name.split( "[_\\s]" );
300 if ( s.length > 1 ) {
301 final String str = s[ 1 ];
302 if ( !ForesterUtil.isEmpty( str ) ) {
303 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) {
304 final Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PF.matcher( str );
310 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( str );
311 if ( m1.matches() ) {
314 final Matcher m2 = TAXOMONY_UNIPROT_ID_PATTERN_2.matcher( str );
315 if ( m2.matches() ) {
316 return m2.group( 1 );
322 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
323 final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name );
324 if ( m1.matches() ) {
331 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
332 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
335 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
336 return readPhylogenies( new File( file_name ) );