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 private static Pattern TAXOMONY_CODE_PATTERN_1 = Pattern.compile( "[A-Z0-9]{5}" );
- final private static Pattern TAXOMONY_CODE_PATTERN_2 = Pattern.compile( "([A-Z0-9]{5})[^A-Z].*" );
+ final public static Pattern TAXOMONY_SN_PATTERN = Pattern
+ .compile( "[^_]{2,}_([A-Z][a-z]+_[a-z]{2,}(_[A-Za-z]\\w+|))\\b" );
+ final public static Pattern TAXOMONY_CODE_PATTERN_1 = Pattern.compile( "\\b[A-Z0-9]{5}|RAT|PIG|PEA|CAP\\b" );
+ final private static Pattern TAXOMONY_CODE_PATTERN_2 = Pattern
+ .compile( "([A-Z0-9]{5}|RAT|PIG|PEA|CAP)[^0-9A-Za-z].*" );
+ final private static Pattern TAXOMONY_CODE_PATTERN_PF = Pattern
+ .compile( "([A-Z0-9]{5}|RAT|PIG|PEA|CAP)/\\d+-\\d+" );
+ 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 )
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
- * @return
- */
- public static String extractTaxonomyCodeFromNodeName( final String name,
- final PhylogenyMethods.TAXONOMY_EXTRACTION taxonomy_extraction ) {
+ public final static String extractTaxonomyCodeFromNodeName( 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_ONLY ) || ( name.indexOf( "/" ) > 4 ) ) ) {
+ final String[] s = name.split( "[_\\s]" );
if ( s.length > 1 ) {
final String str = s[ 1 ];
- // if ( str.length() < 6 ) {
- if ( ( str.length() < 5 ) && ( str.startsWith( "RAT" ) || str.startsWith( "PIG" ) ) ) {
- return str.substring( 0, 3 );
+ if ( !ForesterUtil.isEmpty( str ) ) {
+ if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) {
+ final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( str );
+ if ( m.matches() ) {
+ return m.group( 1 );
+ }
+ }
+ else {
+ final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( str );
+ if ( m1.matches() ) {
+ return m1.group();
+ }
+ final Matcher m2 = TAXOMONY_CODE_PATTERN_2.matcher( str );
+ if ( m2.matches() ) {
+ return m2.group( 1 );
+ }
+ }
+ }
+ }
+ }
+ else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.YES ) {
+ final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( name );
+ if ( m1.matches() ) {
+ return name;
+ }
+ }
+ return null;
+ }
+
+ public final static String extractScientificNameFromNodeName( final String name ) {
+ final Matcher m1 = TAXOMONY_SN_PATTERN.matcher( name );
+ if ( m1.matches() ) {
+ return m1.group( 1 ).replace( '_', ' ' );
+ }
+ return null;
+ }
+
+ public final static String extractTaxonomyDataFromNodeName( final PhylogenyNode node,
+ final NHXParser.TAXONOMY_EXTRACTION taxonomy_extraction )
+ throws PhyloXmlDataFormatException {
+ final String id = extractUniprotTaxonomyIdFromNodeName( node.getName(), taxonomy_extraction );
+ if ( !ForesterUtil.isEmpty( id ) ) {
+ if ( !node.getNodeData().isHasTaxonomy() ) {
+ node.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ if ( ( node.getNodeData().getTaxonomy().getIdentifier() == null )
+ || ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getIdentifier().getValue() ) ) {
+ 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() );
}
- final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( str );
- if ( m1.matches() ) {
- return m1.group();
+ if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
+ node.getNodeData().getTaxonomy().setTaxonomyCode( code );
+ return code;
+ }
+ }
+ else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.YES ) {
+ final String sn = extractScientificNameFromNodeName( node.getName() );
+ if ( !ForesterUtil.isEmpty( sn ) ) {
+ if ( !node.getNodeData().isHasTaxonomy() ) {
+ node.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ if ( ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) {
+ node.getNodeData().getTaxonomy().setScientificName( sn );
+ return sn;
+ }
}
- final Matcher m2 = TAXOMONY_CODE_PATTERN_2.matcher( str );
- if ( m2.matches() ) {
- return m2.group( 1 );
+ }
+ }
+ return null;
+ }
+
+ public final static String extractUniprotTaxonomyIdFromNodeName( final String name,
+ final TAXONOMY_EXTRACTION taxonomy_extraction ) {
+ if ( ( name.indexOf( "_" ) > 0 )
+ && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) || ( name.indexOf( "/" ) > 4 ) ) ) {
+ final String[] s = name.split( "[_\\s]" );
+ if ( s.length > 1 ) {
+ final String str = s[ 1 ];
+ if ( !ForesterUtil.isEmpty( str ) ) {
+ if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) {
+ final Matcher m = TAXOMONY_UNIPROT_ID_PATTERN_PF.matcher( str );
+ if ( m.matches() ) {
+ return m.group( 1 );
+ }
+ }
+ 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 null;
- // 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;
- // }
- // return str;
- // }
+ }
+ }
+ else if ( taxonomy_extraction == TAXONOMY_EXTRACTION.YES ) {
+ final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name );
+ if ( m1.matches() ) {
+ return name;
}
}
return null;