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 = new PhyloXmlParser();
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 );
116 * Return null if it can not guess the parser to use based on name suffix.
121 final public static PhylogenyParser createParserDependingOnSuffix( final String filename,
122 final boolean phyloxml_validate_against_xsd ) {
123 PhylogenyParser parser = null;
124 final String filename_lc = filename.toLowerCase();
125 if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) {
126 parser = new TolParser();
128 else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" )
129 || filename_lc.endsWith( ".zip" ) ) {
130 parser = new PhyloXmlParser();
131 if ( phyloxml_validate_against_xsd ) {
132 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
133 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
134 if ( xsd_url != null ) {
135 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
138 if ( ForesterConstants.RELEASE ) {
139 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
140 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
145 else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) {
146 parser = new NexusPhylogeniesParser();
148 else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" )
149 || filename_lc.endsWith( ".nwk" ) ) {
150 parser = new NHXParser();
155 final public static PhylogenyParser createParserDependingOnUrlContents( final URL url,
156 final boolean phyloxml_validate_against_xsd )
157 throws FileNotFoundException, IOException {
158 final String lc_filename = url.getFile().toString().toLowerCase();
159 PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd );
160 if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) {
161 if ( parser instanceof PhyloXmlParser ) {
162 ( ( PhyloXmlParser ) parser ).setZippedInputstream( true );
164 else if ( parser instanceof TolParser ) {
165 ( ( TolParser ) parser ).setZippedInputstream( true );
168 if ( parser == null ) {
169 final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase();
170 if ( first_line.startsWith( "<" ) ) {
171 parser = new PhyloXmlParser();
172 if ( phyloxml_validate_against_xsd ) {
173 final ClassLoader cl = PhyloXmlParser.class.getClassLoader();
174 final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE );
175 if ( xsd_url != null ) {
176 ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() );
179 throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from ["
180 + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" );
184 else if ( ( first_line.startsWith( "nexus" ) ) || ( first_line.startsWith( "#nexus" ) )
185 || ( first_line.startsWith( "# nexus" ) ) || ( first_line.startsWith( "begin" ) ) ) {
186 parser = new NexusPhylogeniesParser();
189 parser = new NHXParser();
195 public static BufferedReader createReader( final Object source ) throws IOException, FileNotFoundException {
196 BufferedReader reader = null;
197 if ( ( source instanceof File ) || ( source instanceof String ) ) {
199 if ( source instanceof File ) {
203 f = new File( ( String ) source );
206 throw new IOException( "[" + f.getAbsolutePath() + "] does not exist" );
208 else if ( !f.isFile() ) {
209 throw new IOException( "[" + f.getAbsolutePath() + "] is not a file" );
211 else if ( !f.canRead() ) {
212 throw new IOException( "[" + f.getAbsolutePath() + "] is not a readable" );
214 reader = new BufferedReader( new FileReader( f ) );
216 else if ( source instanceof InputStream ) {
217 reader = new BufferedReader( new InputStreamReader( ( InputStream ) source ) );
219 else if ( ( source instanceof StringBuffer ) || ( source instanceof StringBuilder ) ) {
220 reader = new BufferedReader( new StringReader( source.toString() ) );
223 throw new IllegalArgumentException( "attempt to parse object of type [" + source.getClass()
224 + "] (can only parse objects of type File/String, InputStream, StringBuffer, or StringBuilder)" );
229 public final static String extractScientificNameFromNodeName( final String name ) {
230 final Matcher m = TAXOMONY_SN_PATTERN.matcher( name );
232 return m.group( 1 ).replace( '_', ' ' );
237 public final static String extractTaxonomyCodeFromNodeName( final String name,
238 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
239 Matcher m = TAXOMONY_CODE_PATTERN_PFS.matcher( name );
243 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
244 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
245 m = TAXOMONY_CODE_PATTERN_PFR.matcher( name );
249 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
250 m = TAXOMONY_CODE_PATTERN_A.matcher( name );
259 public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
260 final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
261 throws PhyloXmlDataFormatException {
262 if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) {
263 throw new IllegalArgumentException();
265 final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
266 if ( !ForesterUtil.isEmpty( id ) ) {
267 if ( !node.getNodeData().isHasTaxonomy() ) {
268 node.getNodeData().setTaxonomy( new Taxonomy() );
270 node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) );
274 final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction );
275 if ( !ForesterUtil.isEmpty( code ) ) {
276 if ( !node.getNodeData().isHasTaxonomy() ) {
277 node.getNodeData().setTaxonomy( new Taxonomy() );
279 node.getNodeData().getTaxonomy().setTaxonomyCode( code );
282 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
283 final String sn = extractScientificNameFromNodeName( node.getName() );
284 if ( !ForesterUtil.isEmpty( sn ) ) {
285 if ( !node.getNodeData().isHasTaxonomy() ) {
286 node.getNodeData().setTaxonomy( new Taxonomy() );
288 node.getNodeData().getTaxonomy().setScientificName( sn );
296 public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
297 final TAXONOMY_EXTRACTION taxonomy_extraction ) {
298 Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PFS.matcher( name );
302 else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED )
303 || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) {
304 m = TAXOMONY_UNIPROT_ID_PATTERN_PFR.matcher( name );
308 else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
309 m = TAXOMONY_UNIPROT_ID_PATTERN_A.matcher( name );
318 public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException {
319 return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file );
322 public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException {
323 return readPhylogenies( new File( file_name ) );