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}|RAT|PIG|PEA" );
- final private static Pattern TAXOMONY_CODE_PATTERN_2 = Pattern.compile( "([A-Z0-9]{5}|RAT|PIG|PEA)[^A-Za-z].*" );
- final private static Pattern TAXOMONY_CODE_PATTERN_PF = Pattern.compile( "([A-Z0-9]{5}|RAT|PIG|PEA)/\\d+-\\d+" );
+ 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 )
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 )
- && ( ( taxonomy_extraction != TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) || ( name.indexOf( "/" ) > 4 ) ) ) {
+ && ( ( ( 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 ) {
final String str = s[ 1 ];
if ( !ForesterUtil.isEmpty( str ) ) {
- if ( taxonomy_extraction == TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY ) {
- final Matcher m = TAXOMONY_CODE_PATTERN_PF.matcher( 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 );
}
}
else {
- final Matcher m1 = TAXOMONY_CODE_PATTERN_1.matcher( str );
+ final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( str );
if ( m1.matches() ) {
return m1.group();
}
- final Matcher m2 = TAXOMONY_CODE_PATTERN_2.matcher( str );
+ final Matcher m2 = TAXOMONY_UNIPROT_ID_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 ( taxonomy_extraction == TAXONOMY_EXTRACTION.AGGRESSIVE ) {
+ final Matcher m1 = TAXOMONY_UNIPROT_ID_PATTERN_1.matcher( name );
if ( m1.matches() ) {
return name;
}
git://source.jalview.org / jalview.git / blobdiff