X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fio%2Fparsers%2Futil%2FParserUtils.java;h=92275ad20e9f224731727e20f12ad0502e88378a;hb=5608ffe84b2c541f79adaf498063906a9804a9db;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..92275ad 100644 --- a/forester/java/src/org/forester/io/parsers/util/ParserUtils.java +++ b/forester/java/src/org/forester/io/parsers/util/ParserUtils.java @@ -36,19 +36,38 @@ 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|CAP"; + final public static Pattern TAXOMONY_SN_PATTERN = Pattern + .compile( "[A-Z0-9]{2,}_([A-Z][a-z]+_[a-z]{2,}(?:_[a-z][a-z0-9_]+)?)\\b" ); + final public static Pattern TAXOMONY_CODE_PATTERN_R1 = Pattern.compile( "[A-Z0-9]+_(" + TAX_CODE + ")\\b" ); + final public static Pattern TAXOMONY_CODE_PATTERN_R2 = Pattern.compile( "(?:\\b|_)(" + TAX_CODE + ")\\b" ); + final private static Pattern TAXOMONY_CODE_PATTERN_PF = Pattern.compile( "[A-Z0-9]{2,}_(" + TAX_CODE + + ")/\\d+-\\d+" ); + final public static Pattern TAXOMONY_CODE_PATTERN_4 = Pattern.compile( "\\[(" + TAX_CODE + ")\\]" ); + final public static Pattern TAXOMONY_CODE_PATTERN_6 = Pattern.compile( "\\[([A-Z9][A-Z]{2}[A-Z0-9]{3})\\]" ); + final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_1 = Pattern.compile( "\\b\\d{1,7}\\b" ); + final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_2 = Pattern.compile( "(\\d{1,7})[^0-9A-Za-z].*" ); + final private static Pattern TAXOMONY_UNIPROT_ID_PATTERN_PF = Pattern.compile( "(\\d{1,7})/\\d+-\\d+" ); + final public static PhylogenyParser createParserDependingFileContents( final File file, final boolean phyloxml_validate_against_xsd ) throws FileNotFoundException, IOException { @@ -124,7 +143,8 @@ public final class ParserUtils { 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" ) ) { + else if ( filename_lc.endsWith( ".nhx" ) || filename_lc.endsWith( ".nh" ) || filename_lc.endsWith( ".newick" ) + || filename_lc.endsWith( ".nwk" ) ) { parser = new NHXParser(); } return parser; @@ -204,52 +224,107 @@ 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 ) { + public final static String extractTaxonomyCodeFromNodeName( final String name, + final TAXONOMY_EXTRACTION taxonomy_extraction ) { + if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) { + final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( name ); + if ( m.find() ) { + return m.group( 1 ); + } + } + else if ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED ) + || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) { + final Matcher m1 = TAXOMONY_CODE_PATTERN_R1.matcher( name ); + if ( m1.find() ) { + return m1.group( 1 ); + } + final Matcher m2 = TAXOMONY_CODE_PATTERN_R2.matcher( name ); + if ( m2.find() ) { + return m2.group( 1 ); + } + } + return null; + } + + public final static String extractScientificNameFromNodeName( final String name ) { + final Matcher m1 = TAXOMONY_SN_PATTERN.matcher( name ); + if ( m1.find() ) { + return m1.group( 1 ).replace( '_', ' ' ); + } + 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.PFAM_STYLE_RELAXED || taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) { + final String sn = extractScientificNameFromNodeName( node.getName() ); + if ( !ForesterUtil.isEmpty( sn ) ) { + if ( !node.getNodeData().isHasTaxonomy() ) { + node.getNodeData().setTaxonomy( new Taxonomy() ); + } + node.getNodeData().getTaxonomy().setScientificName( sn ); + return sn; + } + } + } + return null; + } + + public final static String extractUniprotTaxonomyIdFromNodeName( final String name, + final 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( "[_/]" ); + && ( ( ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED ) || ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) ) || ( ( ( name + .indexOf( "/" ) > 4 ) && ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) ) ) ) ) { + final String[] s = name.split( "[_\\s]" ); 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 String str = s[ 1 ]; + if ( !ForesterUtil.isEmpty( str ) ) { + if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT ) { + final Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PF.matcher( str ); + if ( m.matches() ) { + return m.group( 1 ); + } } - 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; + else { + final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( str ); + if ( m1.matches() ) { + return m1.group(); + } + final Matcher m2 = TAXOMONY_UNIPROT_ID_PATTERN_2.matcher( str ); + if ( m2.matches() ) { + return m2.group( 1 ); + } } - return str; } } } + if ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) { + final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name ); + if ( m1.matches() ) { + return name; + } + } return null; }