X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fio%2Fparsers%2Futil%2FParserUtils.java;h=ef37f98d0aa8969d0696c804d121111c8efdc602;hb=e9776288e623af2543d3a5e396c60ff1411d01c3;hp=a1f842ee0df8353be6a37a3606bda2296cfd42d9;hpb=44fddb76faa8975295b8b0ad38609256b5011ced;p=jalview.git diff --git a/forester/java/src/org/forester/io/parsers/util/ParserUtils.java b/forester/java/src/org/forester/io/parsers/util/ParserUtils.java index a1f842e..ef37f98 100644 --- a/forester/java/src/org/forester/io/parsers/util/ParserUtils.java +++ b/forester/java/src/org/forester/io/parsers/util/ParserUtils.java @@ -36,26 +36,56 @@ import java.io.InputStreamReader; import java.io.StringReader; import java.net.URL; import java.util.regex.Matcher; +import java.util.regex.Pattern; import org.forester.io.parsers.PhylogenyParser; import org.forester.io.parsers.nexus.NexusPhylogeniesParser; import org.forester.io.parsers.nhx.NHXParser; +import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION; +import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException; import org.forester.io.parsers.phyloxml.PhyloXmlParser; import org.forester.io.parsers.tol.TolParser; import org.forester.phylogeny.Phylogeny; import org.forester.phylogeny.PhylogenyMethods; +import org.forester.phylogeny.PhylogenyNode; +import org.forester.phylogeny.data.Identifier; +import org.forester.phylogeny.data.Taxonomy; import org.forester.util.ForesterConstants; import org.forester.util.ForesterUtil; public final class ParserUtils { + final public static String TAX_CODE = "(?:[A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA"; + final public static Pattern TAXOMONY_CODE_PATTERN_A = Pattern.compile( "(?:\\b|_)(" + TAX_CODE + ")\\b" ); + final public static Pattern TAXOMONY_CODE_PATTERN_BRACKETED = Pattern.compile( "\\[(" + TAX_CODE + ")\\]" ); + final public static Pattern TAXOMONY_CODE_PATTERN_PFR = Pattern.compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_(" + + TAX_CODE + ")\\b" ); + final public static Pattern TAXOMONY_SN_PATTERN = Pattern + .compile( "(?:\\b|_)[a-zA-Z0-9]{3,}_([A-Z][a-z]{2,30}_[a-z]{3,30}(?:_[a-z][a-z0-9_]+)?)\\b" ); + final public static Pattern TAXOMONY_SN_PATTERN_SN = Pattern + .compile( "\\b([A-Z][a-z]{2,30}[_ ][a-z]{3,30}(?:[_ ][a-z]{3,30})?)(?:\\b|_)?" ); + final public static Pattern TAXOMONY_SN_PATTERN_STRAIN_1 = Pattern + .compile( "\\b([A-Z][a-z]{2,30}[_ ][a-z]{3,30}[_ ](?:str|subsp|var)[a-z]{0,5}\\.?[_ ]\\S{1,60})(?:\\b|_)" ); + final public static Pattern TAXOMONY_SN_PATTERN_STRAIN_2 = Pattern + .compile( "\\b([A-Z][a-z]{2,30}[_ ][a-z]{3,30}[_ ]\\((?:str|subsp|var)[a-z]{0,5}\\.?[_ ]\\S{1,60}\\))(?:\\b|_)?" ); + final public static Pattern TAXOMONY_SN_PATTERN_SP = Pattern + .compile( "\\b([A-Z][a-z]{2,30}[_ ]sp\\.)(?:\\b|_)?" ); + + final public static Pattern TAXOMONY_SN_PATTERN_GENUS = Pattern.compile( "([A-Z][a-z]{2,30})" ); + final private static Pattern TAXOMONY_CODE_PATTERN_PFS = Pattern.compile( "(?:\\b|_)[A-Z0-9]{4,}_(" + + TAX_CODE + ")/\\d+-\\d+\\b" ); + final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFR = Pattern + .compile( "(?:\\b|_)[A-Z0-9]{1,}_(\\d{1,7})\\b" ); + final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PFS = Pattern + .compile( "(?:\\b|_)[A-Z0-9]{4,}_(\\d{1,7})/\\d+-\\d+\\b" ); + final public static PhylogenyParser createParserDependingFileContents( final File file, final boolean phyloxml_validate_against_xsd ) throws FileNotFoundException, IOException { PhylogenyParser parser = null; final String first_line = ForesterUtil.getFirstLine( file ).trim().toLowerCase(); if ( first_line.startsWith( "<" ) ) { - parser = new PhyloXmlParser(); + parser = PhyloXmlParser.createPhyloXmlParser(); if ( phyloxml_validate_against_xsd ) { final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); @@ -88,44 +118,13 @@ public final class ParserUtils { if ( parser == null ) { parser = createParserDependingFileContents( file, phyloxml_validate_against_xsd ); } - return parser; - } - - /** - * Return null if it can not guess the parser to use based on name suffix. - * - * @param filename - * @return - */ - final public static PhylogenyParser createParserDependingOnSuffix( final String filename, - final boolean phyloxml_validate_against_xsd ) { - PhylogenyParser parser = null; - final String filename_lc = filename.toLowerCase(); - if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) { - parser = new TolParser(); - } - else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( ".px" ) || filename_lc.endsWith( "phyloxml" ) - || filename_lc.endsWith( ".zip" ) ) { - parser = new PhyloXmlParser(); - if ( phyloxml_validate_against_xsd ) { - final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); - final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); - if ( xsd_url != null ) { - ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() ); - } - else { - if ( ForesterConstants.RELEASE ) { - throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from [" - + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" ); - } - } + if ( ( parser != null ) && file.toString().toLowerCase().endsWith( ".zip" ) ) { + if ( parser instanceof PhyloXmlParser ) { + ( ( PhyloXmlParser ) parser ).setZippedInputstream( true ); + } + else if ( parser instanceof TolParser ) { + ( ( TolParser ) parser ).setZippedInputstream( true ); } - } - else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) { - parser = new NexusPhylogeniesParser(); - } - else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" ) ) { - parser = new NHXParser(); } return parser; } @@ -135,18 +134,10 @@ public final class ParserUtils { throws FileNotFoundException, IOException { final String lc_filename = url.getFile().toString().toLowerCase(); PhylogenyParser parser = createParserDependingOnSuffix( lc_filename, phyloxml_validate_against_xsd ); - if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) { - if ( parser instanceof PhyloXmlParser ) { - ( ( PhyloXmlParser ) parser ).setZippedInputstream( true ); - } - else if ( parser instanceof TolParser ) { - ( ( TolParser ) parser ).setZippedInputstream( true ); - } - } if ( parser == null ) { final String first_line = ForesterUtil.getFirstLine( url ).trim().toLowerCase(); if ( first_line.startsWith( "<" ) ) { - parser = new PhyloXmlParser(); + parser = PhyloXmlParser.createPhyloXmlParser(); if ( phyloxml_validate_against_xsd ) { final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); @@ -167,6 +158,14 @@ public final class ParserUtils { parser = new NHXParser(); } } + if ( ( parser != null ) && lc_filename.endsWith( ".zip" ) ) { + if ( parser instanceof PhyloXmlParser ) { + ( ( PhyloXmlParser ) parser ).setZippedInputstream( true ); + } + else if ( parser instanceof TolParser ) { + ( ( TolParser ) parser ).setZippedInputstream( true ); + } + } return parser; } @@ -204,55 +203,114 @@ public final class ParserUtils { return reader; } - /** - * Extracts a code if and only if: - * one and only one _, - * shorter than 25, - * no |, - * no ., - * if / present it has to be after the _, - * if PFAM_STYLE_ONLY: / must be present, - * tax code can only contain uppercase letters and numbers, - * and must contain at least one uppercase letter. - * Return null if no code extractable. - * - * @param name - * @param limit_to_five - * @return - */ - public static String extractTaxonomyCodeFromNodeName( final String name, - final boolean limit_to_five, - final PhylogenyMethods.TAXONOMY_EXTRACTION taxonomy_extraction ) { - if ( ( name.indexOf( "_" ) > 0 ) - && ( name.length() < 31 ) - // && ( name.lastIndexOf( "_" ) == name.indexOf( "_" ) ) - && ( name.indexOf( "|" ) < 0 ) - && ( name.indexOf( "." ) < 0 ) - && ( ( taxonomy_extraction != PhylogenyMethods.TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) || ( name - .indexOf( "/" ) >= 0 ) ) - && ( ( ( name.indexOf( "/" ) ) < 0 ) || ( name.indexOf( "/" ) > name.indexOf( "_" ) ) ) ) { - final String[] s = name.split( "[_/]" ); - if ( s.length > 1 ) { - String str = s[ 1 ]; - if ( ( str.length() < 6 ) || ( !limit_to_five && ( str.length() < 7 ) ) ) { - if ( ( str.length() < 5 ) && ( str.startsWith( "RAT" ) || str.startsWith( "PIG" ) ) ) { - str = str.substring( 0, 3 ); - } - final Matcher uc_letters_and_numbers = NHXParser.UC_LETTERS_NUMBERS_PATTERN.matcher( str ); - if ( !uc_letters_and_numbers.matches() ) { - return null; - } - final Matcher numbers_only = NHXParser.NUMBERS_ONLY_PATTERN.matcher( str ); - if ( numbers_only.matches() ) { - return null; + public final static String extractScientificNameFromNodeName( final String name ) { + final Matcher m = TAXOMONY_SN_PATTERN.matcher( name ); + if ( m.find() ) { + return m.group( 1 ).replace( '_', ' ' ); + } + final Matcher m_str1 = TAXOMONY_SN_PATTERN_STRAIN_1.matcher( name ); + if ( m_str1.find() ) { + return m_str1.group( 1 ).replace( '_', ' ' ); + } + final Matcher m_str2 = TAXOMONY_SN_PATTERN_STRAIN_2.matcher( name ); + if ( m_str2.find() ) { + return m_str2.group( 1 ).replace( '_', ' ' ); + } + final Matcher m_sn = TAXOMONY_SN_PATTERN_SN.matcher( name ); + + if ( m_sn.find() ) { + return m_sn.group( 1 ).replace( '_', ' ' ); + } + + final Matcher m_sp = TAXOMONY_SN_PATTERN_SP.matcher( name ); + + if ( m_sp.find() ) { + return m_sp.group( 1 ).replace( '_', ' ' ); + } + return null; + } + + public final static String extractTaxonomyCodeFromNodeName( final String name, + final TAXONOMY_EXTRACTION taxonomy_extraction ) { + Matcher m = TAXOMONY_CODE_PATTERN_PFS.matcher( name ); + if ( m.find() ) { + return m.group( 1 ); + } + else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED ) + || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) { + m = TAXOMONY_CODE_PATTERN_PFR.matcher( name ); + if ( m.find() ) { + return m.group( 1 ); + } + else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) { + m = TAXOMONY_CODE_PATTERN_A.matcher( name ); + if ( m.find() ) { + return m.group( 1 ); + } + } + } + return null; + } + + public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node, + final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction ) + throws PhyloXmlDataFormatException { + if ( taxonomy_extraction == TAXONOMY_EXTRACTION.NO ) { + throw new IllegalArgumentException(); + } + final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction ); + if ( !ForesterUtil.isEmpty( id ) ) { + if ( !node.getNodeData().isHasTaxonomy() ) { + node.getNodeData().setTaxonomy( new Taxonomy() ); + } + node.getNodeData().getTaxonomy().setIdentifier( new Identifier( id, "uniprot" ) ); + return id; + } + else { + final String code = extractTaxonomyCodeFromNodeName( node.getName(), taxonomy_extraction ); + if ( !ForesterUtil.isEmpty( code ) ) { + if ( !node.getNodeData().isHasTaxonomy() ) { + node.getNodeData().setTaxonomy( new Taxonomy() ); + } + node.getNodeData().getTaxonomy().setTaxonomyCode( code ); + return code; + } + else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) { + final String sn = extractScientificNameFromNodeName( node.getName() ); + if ( !ForesterUtil.isEmpty( sn ) ) { + if ( !node.getNodeData().isHasTaxonomy() ) { + node.getNodeData().setTaxonomy( new Taxonomy() ); } - return str; + node.getNodeData().getTaxonomy().setScientificName( sn ); + return sn; } } } return null; } + public final static String extractUniprotTaxonomyIdFromNodeName( final String name, + final TAXONOMY_EXTRACTION taxonomy_extraction ) { + Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PFS.matcher( name ); + if ( m.find() ) { + return m.group( 1 ); + } + else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED ) + || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) { + m = TAXOMONY_UNIPROT_ID_PATTERN_PFR.matcher( name ); + if ( m.find() ) { + return m.group( 1 ); + } + //else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) { + // m = TAXOMONY_UNIPROT_ID_PATTERN_A.matcher( name ); + // if ( m.find() ) { + // return m.group( 1 ); + // } + //} + } + return null; + } + public final static Phylogeny[] readPhylogenies( final File file ) throws FileNotFoundException, IOException { return PhylogenyMethods.readPhylogenies( ParserUtils.createParserDependingOnFileType( file, true ), file ); } @@ -260,4 +318,43 @@ public final class ParserUtils { public final static Phylogeny[] readPhylogenies( final String file_name ) throws FileNotFoundException, IOException { return readPhylogenies( new File( file_name ) ); } + + /** + * Return null if it can not guess the parser to use based on name suffix. + * + * @param filename + * @return + */ + final private static PhylogenyParser createParserDependingOnSuffix( final String filename, + final boolean phyloxml_validate_against_xsd ) { + PhylogenyParser parser = null; + final String filename_lc = filename.toLowerCase(); + if ( filename_lc.endsWith( ".tol" ) || filename_lc.endsWith( ".tolxml" ) || filename_lc.endsWith( ".tol.zip" ) ) { + parser = new TolParser(); + } + else if ( filename_lc.endsWith( ".xml" ) || filename_lc.endsWith( "phyloxml" ) || filename_lc.endsWith( ".zip" ) ) { + parser = PhyloXmlParser.createPhyloXmlParser(); + if ( phyloxml_validate_against_xsd ) { + final ClassLoader cl = PhyloXmlParser.class.getClassLoader(); + final URL xsd_url = cl.getResource( ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE ); + if ( xsd_url != null ) { + ( ( PhyloXmlParser ) parser ).setValidateAgainstSchema( xsd_url.toString() ); + } + else { + if ( ForesterConstants.RELEASE ) { + throw new RuntimeException( "failed to get URL for phyloXML XSD from jar file from [" + + ForesterConstants.LOCAL_PHYLOXML_XSD_RESOURCE + "]" ); + } + } + } + } + else if ( filename_lc.endsWith( ".nexus" ) || filename_lc.endsWith( ".nex" ) || filename_lc.endsWith( ".nx" ) ) { + parser = new NexusPhylogeniesParser(); + } + else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" ) + || filename_lc.endsWith( ".nwk" ) ) { + parser = new NHXParser(); + } + return parser; + } }