\r
import org.forester.phylogeny.PhylogenyNode;\r
import org.forester.phylogeny.data.Accession;\r
+import org.forester.phylogeny.data.Accession.Source;\r
import org.forester.phylogeny.data.Sequence;\r
\r
public final class SequenceAccessionTools {\r
\r
- public final static Pattern UNIPROT_KB_PATTERN_0 = Pattern\r
- .compile( "\\b([A-Z][0-9][A-Z0-9]{3}[0-9])\\b" );\r
- public final static Pattern UNIPROT_KB_PATTERN_1 = Pattern\r
- .compile( "(?:\\b|_)(?:sp|tr)[\\.|\\-_=/\\\\]([A-Z][0-9][A-Z0-9]{3}[0-9])(?:\\b|_)" );\r
- public final static Pattern UNIPROT_KB_PATTERN_2 = Pattern\r
- .compile( "(?:\\b|_)(?:[A-Z0-9]{2,5}|(?:[A-Z][0-9][A-Z0-9]{3}[0-9]))_(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA)(?:\\b|_)" );\r
- // gb_ADF31344_1_segmented_worms_\r
- // gb_AAA96518_1\r
- // gb_EHB07727_1_rodents_\r
- // dbj_BAF37827_1_turtles_\r
- // emb_CAA73223_1_primates_\r
- // lcl_91970_unknown_\r
- // mites|ref_XP_002434188_1\r
- // ref_XP_002434188_1_mites___ticks_\r
- // ref_NP_001121530_1_frogs___toads_\r
//The format for GenBank Accession numbers are:\r
//Nucleotide: 1 letter + 5 numerals OR 2 letters + 6 numerals\r
//Protein: 3 letters + 5 numerals\r
//http://www.ncbi.nlm.nih.gov/Sequin/acc.html\r
- private final static Pattern GENBANK_NUCLEOTIDE_AC_PATTERN_1 = Pattern\r
- .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" );\r
- private final static Pattern GENBANK_NUCLEOTIDE_AC_PATTERN_2 = Pattern\r
- .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}\\d{6}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" );\r
- private final static Pattern GENBANK_PROTEIN_AC_PATTERN = Pattern\r
- .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{3}\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" );\r
- private final static Pattern GI_PATTERN = Pattern\r
- .compile( "(?:\\b|_)(?:GI|gi)[|_=:](\\d+)(?:\\b|_)" );\r
- // RefSeq accession numbers can be distinguished from GenBank accessions \r
+ public final static Pattern GENBANK_NUC_PATTERN_1 = Pattern\r
+ .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" );\r
+ public final static Pattern GENBANK_NUC_PATTERN_2 = Pattern\r
+ .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}\\d{6}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" );\r
+ public final static Pattern GENBANK_PROT_PATTERN = Pattern\r
+ .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{3}\\d{5}(?:\\.\\d+)?)(?:[^a-zA-Z0-9]|\\Z)" );\r
+ public final static Pattern GI_PATTERN = Pattern\r
+ .compile( "(?:\\b|_)(?:GI|gi)[|_=:](\\d+)(?:\\b|_)" );\r
+ public final static String UNIPROT_KB_BASE_PATTERN_STR = "((?:[OPQ][0-9][A-Z0-9]{3}[0-9])|(?:[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}))";\r
+ public final static Pattern UNIPROT_KB_PATTERN_0 = Pattern.compile( "(?:\\b|_)"\r
+ + UNIPROT_KB_BASE_PATTERN_STR + "(?:\\b|_)" );\r
+ public final static Pattern UNIPROT_KB_PATTERN_1 = Pattern.compile( "(?:\\b|_)(?:sp|tr)[\\.|\\-_=/\\\\]"\r
+ + UNIPROT_KB_BASE_PATTERN_STR + "(?:\\b|_)" );\r
+ public final static Pattern UNIPROT_KB_PATTERN_2 = Pattern\r
+ .compile( "(?:\\b|_)(?:[A-Z0-9]{2,5}|"\r
+ + UNIPROT_KB_BASE_PATTERN_STR\r
+ + ")_(([A-Z9][A-Z]{2}[A-Z0-9]{2})|RAT|PIG|PEA)(?:\\b|_)" );\r
+ public final static Pattern ENSEMBL_PATTERN = Pattern.compile( "(?:\\b|_)(ENS[A-Z]*[0-9]+)(?:\\b|_)" );\r
+ // RefSeq accession numbers can be distinguished from GenBank accessions\r
// by their distinct prefix format of 2 characters followed by an\r
- // underscore character ('_'). For example, a RefSeq protein accession is NP_015325. \r
- private final static Pattern REFSEQ_PATTERN = Pattern\r
- .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}_\\d{6,})(?:[^a-zA-Z0-9]|\\Z)" );\r
+ // underscore character ('_'). For example, a RefSeq protein accession is NP_015325.\r
+ private final static Pattern REFSEQ_PATTERN = Pattern\r
+ .compile( "(?:\\A|.*[^a-zA-Z0-9])([A-Z]{2}_\\d{6,})(?:[^a-zA-Z0-9]|\\Z)" );\r
\r
private SequenceAccessionTools() {\r
// Hiding the constructor.\r
}\r
\r
- public static String extractGenbankAccessor( final PhylogenyNode node ) {\r
- String v = null;\r
- if ( node.getNodeData().isHasSequence() ) {\r
- final Sequence seq = node.getNodeData().getSequence();\r
- if ( !ForesterUtil.isEmpty( seq.getSymbol() ) ) {\r
- v = parseGenbankAccessor( seq.getSymbol() );\r
- }\r
- if ( !ForesterUtil.isEmpty( seq.getGeneName() ) ) {\r
- v = parseGenbankAccessor( seq.getGeneName() );\r
- }\r
- if ( ForesterUtil.isEmpty( v ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
- v = parseGenbankAccessor( seq.getName() );\r
- }\r
- if ( ForesterUtil.isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null )\r
- && !ForesterUtil.isEmpty( seq.getAccession().getValue() ) ) {\r
- v = parseGenbankAccessor( seq.getAccession().getValue() );\r
- }\r
+ public final static boolean isProteinDbQuery( final String query ) {\r
+ final String r1 = parseRefSeqAccessorFromString( query );\r
+ if ( !ForesterUtil.isEmpty( r1 ) && ( r1.charAt( 1 ) == 'P' ) ) {\r
+ return true;\r
+ }\r
+ final String r2 = parseUniProtAccessorFromString( query );\r
+ if ( !ForesterUtil.isEmpty( r2 ) ) {\r
+ return true;\r
+ }\r
+ return GENBANK_PROT_PATTERN.matcher( query ).lookingAt();\r
+ }\r
+\r
+ public final static Accession obtainAccessorFromDataFields( final PhylogenyNode n ) {\r
+ String a = obtainUniProtAccessorFromDataFields( n );\r
+ if ( !ForesterUtil.isEmpty( a ) ) {\r
+ return new Accession( a, Source.UNIPROT );\r
+ }\r
+ a = obtainGenbankAccessorFromDataFields( n );\r
+ if ( !ForesterUtil.isEmpty( a ) ) {\r
+ return new Accession( a, Source.NCBI );\r
+ }\r
+ a = obtainRefSeqAccessorFromDataFields( n );\r
+ if ( !ForesterUtil.isEmpty( a ) ) {\r
+ return new Accession( a, Source.REFSEQ );\r
}\r
- if ( ForesterUtil.isEmpty( v ) && !ForesterUtil.isEmpty( node.getName() ) ) {\r
- v = parseGenbankAccessor( node.getName() );\r
+ a = obtainGiNumberFromDataFields( n );\r
+ if ( !ForesterUtil.isEmpty( a ) ) {\r
+ return new Accession( a, Source.GI );\r
}\r
- return v;\r
+ return null;\r
}\r
\r
- public static String extractGInumber( final PhylogenyNode node ) {\r
- String v = null;\r
- if ( node.getNodeData().isHasSequence() ) {\r
- final Sequence seq = node.getNodeData().getSequence();\r
- if ( ForesterUtil.isEmpty( v ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
- v = parseGInumber( seq.getName() );\r
+ public final static Accession obtainFromSeqAccession( final PhylogenyNode n ) {\r
+ if ( n.getNodeData().isHasSequence() && ( n.getNodeData().getSequence().getAccession() != null )\r
+ && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getAccession().getSource() )\r
+ && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getAccession().getValue() ) ) {\r
+ final String source = n.getNodeData().getSequence().getAccession().getSource().toLowerCase();\r
+ final String value = n.getNodeData().getSequence().getAccession().getValue();\r
+ if ( ( source.startsWith( "uniprot" ) || source.equals( "swissprot" ) || source.equals( "trembl" ) || source\r
+ .equals( "sp" ) ) ) {\r
+ return new Accession( value, Source.UNIPROT );\r
}\r
- if ( ForesterUtil.isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null )\r
- && !ForesterUtil.isEmpty( seq.getAccession().getValue() ) ) {\r
- v = parseGInumber( seq.getAccession().getValue() );\r
+ else if ( source.equals( "embl" ) || source.equals( "ebi" ) ) {\r
+ return new Accession( value, Source.EMBL );\r
+ }\r
+ else if ( source.equals( "ncbi" ) || source.equals( "genbank" ) ) {\r
+ return new Accession( value, Source.NCBI );\r
+ }\r
+ else if ( source.equals( "refseq" ) ) {\r
+ return new Accession( value, Source.REFSEQ );\r
+ }\r
+ else if ( source.equals( "gi" ) ) {\r
+ return new Accession( value, Source.GI );\r
}\r
}\r
- if ( ForesterUtil.isEmpty( v ) && !ForesterUtil.isEmpty( node.getName() ) ) {\r
- v = parseGInumber( node.getName() );\r
- }\r
- return v;\r
+ return null;\r
}\r
\r
- public static String extractRefSeqAccessor( final PhylogenyNode node ) {\r
- String v = null;\r
- if ( node.getNodeData().isHasSequence() ) {\r
- final Sequence seq = node.getNodeData().getSequence();\r
+ public final static String obtainGenbankAccessorFromDataFields( final PhylogenyNode n ) {\r
+ String a = null;\r
+ if ( n.getNodeData().isHasSequence() ) {\r
+ final Sequence seq = n.getNodeData().getSequence();\r
if ( !ForesterUtil.isEmpty( seq.getSymbol() ) ) {\r
- v = parseRefSeqAccessor( seq.getSymbol() );\r
+ a = parseGenbankAccessorFromString( seq.getSymbol() );\r
}\r
if ( !ForesterUtil.isEmpty( seq.getGeneName() ) ) {\r
- v = parseRefSeqAccessor( seq.getGeneName() );\r
+ a = parseGenbankAccessorFromString( seq.getGeneName() );\r
}\r
- if ( ForesterUtil.isEmpty( v ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
- v = parseRefSeqAccessor( seq.getName() );\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
+ a = parseGenbankAccessorFromString( seq.getName() );\r
}\r
- if ( ForesterUtil.isEmpty( v ) && ( node.getNodeData().getSequence().getAccession() != null )\r
+ if ( ForesterUtil.isEmpty( a ) && ( n.getNodeData().getSequence().getAccession() != null )\r
&& !ForesterUtil.isEmpty( seq.getAccession().getValue() ) ) {\r
- v = parseRefSeqAccessor( seq.getAccession().getValue() );\r
+ a = parseGenbankAccessorFromString( seq.getAccession().getValue() );\r
}\r
}\r
- if ( ForesterUtil.isEmpty( v ) && !ForesterUtil.isEmpty( node.getName() ) ) {\r
- v = parseRefSeqAccessor( node.getName() );\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( n.getName() ) ) {\r
+ a = parseGenbankAccessorFromString( n.getName() );\r
}\r
- return v;\r
+ return a;\r
}\r
\r
- public static String extractUniProtKbProteinSeqIdentifier( final PhylogenyNode node ) {\r
+ public final static String obtainGiNumberFromDataFields( final PhylogenyNode n ) {\r
String a = null;\r
- if ( node.getNodeData().isHasSequence() ) {\r
- final Sequence seq = node.getNodeData().getSequence();\r
- if ( !ForesterUtil.isEmpty( seq.getSymbol() ) ) {\r
- a = SequenceAccessionTools.extractUniProtKbProteinSeqIdentifier( seq.getSymbol() );\r
- }\r
+ if ( n.getNodeData().isHasSequence() ) {\r
+ final Sequence seq = n.getNodeData().getSequence();\r
if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
- a = SequenceAccessionTools.extractUniProtKbProteinSeqIdentifier( seq.getName() );\r
+ a = parseGInumberFromString( seq.getName() );\r
}\r
if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( seq.getGeneName() ) ) {\r
- a = SequenceAccessionTools.extractUniProtKbProteinSeqIdentifier( seq.getGeneName() );\r
+ a = parseGInumberFromString( seq.getGeneName() );\r
}\r
- if ( ForesterUtil.isEmpty( a ) && ( node.getNodeData().getSequence().getAccession() != null )\r
+ if ( ForesterUtil.isEmpty( a ) && ( n.getNodeData().getSequence().getAccession() != null )\r
&& !ForesterUtil.isEmpty( seq.getAccession().getValue() ) ) {\r
- a = SequenceAccessionTools.extractUniProtKbProteinSeqIdentifier( seq.getAccession().getValue() );\r
+ a = parseGInumberFromString( seq.getAccession().getValue() );\r
}\r
}\r
- if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( node.getName() ) ) {\r
- a = SequenceAccessionTools.extractUniProtKbProteinSeqIdentifier( node.getName() );\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( n.getName() ) ) {\r
+ a = parseGInumberFromString( n.getName() );\r
}\r
return a;\r
}\r
\r
- public static String extractUniProtKbProteinSeqIdentifier( final String str ) {\r
- Matcher m = UNIPROT_KB_PATTERN_0.matcher( str );\r
- if ( m.find() ) {\r
- return m.group( 1 );\r
- }\r
- m = UNIPROT_KB_PATTERN_1.matcher( str );\r
- if ( m.find() ) {\r
- return m.group( 1 );\r
- }\r
- m = UNIPROT_KB_PATTERN_2.matcher( str );\r
- if ( m.find() ) {\r
- return m.group();\r
- }\r
- return null;\r
- }\r
-\r
- public final static boolean isProtein( final String query ) {\r
- final String r1 = parseRefSeqAccessor( query );\r
- if ( !ForesterUtil.isEmpty( r1 ) && ( r1.charAt( 1 ) == 'P' ) ) {\r
- return true;\r
- }\r
- final String r2 = extractUniProtKbProteinSeqIdentifier( query );\r
- if ( !ForesterUtil.isEmpty( r2 ) ) {\r
- return true;\r
- }\r
- return GENBANK_PROTEIN_AC_PATTERN.matcher( query ).lookingAt();\r
- }\r
-\r
- public final static Accession parse( final PhylogenyNode n ) {\r
- String v = extractUniProtKbProteinSeqIdentifier( n );\r
- if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.UNIPROT );\r
- }\r
- v = extractGenbankAccessor( n );\r
- if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.NCBI );\r
- }\r
- v = extractRefSeqAccessor( n );\r
- if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.REFSEQ );\r
+ public final static String obtainRefSeqAccessorFromDataFields( final PhylogenyNode n ) {\r
+ String a = null;\r
+ if ( n.getNodeData().isHasSequence() ) {\r
+ final Sequence seq = n.getNodeData().getSequence();\r
+ if ( !ForesterUtil.isEmpty( seq.getSymbol() ) ) {\r
+ a = parseRefSeqAccessorFromString( seq.getSymbol() );\r
+ }\r
+ if ( !ForesterUtil.isEmpty( seq.getGeneName() ) ) {\r
+ a = parseRefSeqAccessorFromString( seq.getGeneName() );\r
+ }\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
+ a = parseRefSeqAccessorFromString( seq.getName() );\r
+ }\r
+ if ( ForesterUtil.isEmpty( a ) && ( n.getNodeData().getSequence().getAccession() != null )\r
+ && !ForesterUtil.isEmpty( seq.getAccession().getValue() ) ) {\r
+ a = parseRefSeqAccessorFromString( seq.getAccession().getValue() );\r
+ }\r
}\r
- v = extractGInumber( n );\r
- if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.GI );\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( n.getName() ) ) {\r
+ a = parseRefSeqAccessorFromString( n.getName() );\r
}\r
- return null;\r
+ return a;\r
}\r
\r
- public final static Accession obtainFromSeqAccession( final PhylogenyNode node ) {\r
- if ( node.getNodeData().isHasSequence() && ( node.getNodeData().getSequence().getAccession() != null )\r
- && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getSource() )\r
- && !ForesterUtil.isEmpty( node.getNodeData().getSequence().getAccession().getValue() ) ) {\r
- final String source = node.getNodeData().getSequence().getAccession().getSource().toLowerCase();\r
- final String value = node.getNodeData().getSequence().getAccession().getValue();\r
- if ( ( source.startsWith( "uniprot" ) || source.equals( "swissprot" ) || source.equals( "trembl" ) || source\r
- .equals( "sp" ) ) ) {\r
- return new Accession( value, Accession.UNIPROT );\r
- }\r
- else if ( source.equals( "embl" ) || source.equals( "ebi" ) ) {\r
- return new Accession( value, Accession.EMBL );\r
+ public final static String obtainUniProtAccessorFromDataFields( final PhylogenyNode n ) {\r
+ String a = null;\r
+ if ( n.getNodeData().isHasSequence() ) {\r
+ final Sequence seq = n.getNodeData().getSequence();\r
+ if ( !ForesterUtil.isEmpty( seq.getSymbol() ) ) {\r
+ a = SequenceAccessionTools.parseUniProtAccessorFromString( seq.getSymbol() );\r
}\r
- else if ( source.equals( "ncbi" ) || source.equals( "genbank" ) ) {\r
- return new Accession( value, Accession.NCBI );\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( seq.getName() ) ) {\r
+ a = SequenceAccessionTools.parseUniProtAccessorFromString( seq.getName() );\r
}\r
- else if ( source.equals( "refseq" ) ) {\r
- return new Accession( value, Accession.REFSEQ );\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( seq.getGeneName() ) ) {\r
+ a = SequenceAccessionTools.parseUniProtAccessorFromString( seq.getGeneName() );\r
}\r
- else if ( source.equals( "gi" ) ) {\r
- return new Accession( value, Accession.GI );\r
+ if ( ForesterUtil.isEmpty( a ) && ( n.getNodeData().getSequence().getAccession() != null )\r
+ && !ForesterUtil.isEmpty( seq.getAccession().getValue() ) ) {\r
+ a = SequenceAccessionTools.parseUniProtAccessorFromString( seq.getAccession().getValue() );\r
}\r
}\r
- return null;\r
+ if ( ForesterUtil.isEmpty( a ) && !ForesterUtil.isEmpty( n.getName() ) ) {\r
+ a = SequenceAccessionTools.parseUniProtAccessorFromString( n.getName() );\r
+ }\r
+ return a;\r
}\r
\r
- /**\r
- * Returns null if no match.\r
- * \r
- */\r
- public final static Accession parse( final String s ) {\r
+ public final static Accession parseAccessorFromString( final String s ) {\r
if ( !ForesterUtil.isEmpty( s ) ) {\r
- String v = extractUniProtKbProteinSeqIdentifier( s );\r
+ String v = parseUniProtAccessorFromString( s );\r
+ if ( !ForesterUtil.isEmpty( v ) ) {\r
+ return new Accession( v, Source.UNIPROT );\r
+ }\r
+ v = parseGenbankAccessorFromString( s );\r
if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.UNIPROT );\r
+ return new Accession( v, Source.NCBI );\r
}\r
- v = parseGenbankAccessor( s );\r
+ v = parseRefSeqAccessorFromString( s );\r
if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.NCBI );\r
+ return new Accession( v, Source.REFSEQ );\r
}\r
- v = parseRefSeqAccessor( s );\r
+ v = parseGInumberFromString( s );\r
if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.REFSEQ );\r
+ return new Accession( v, Source.GI );\r
}\r
- v = parseGInumber( s );\r
+ v = parseEnsemlAccessorFromString( s );\r
if ( !ForesterUtil.isEmpty( v ) ) {\r
- return new Accession( v, Accession.GI );\r
+ return new Accession( v, Source.ENSEMBL );\r
}\r
}\r
return null;\r
}\r
\r
- /**\r
- * Returns null if no match.\r
- * \r
- */\r
- public static String parseGenbankAccessor( final String query ) {\r
- Matcher m = GENBANK_NUCLEOTIDE_AC_PATTERN_1.matcher( query );\r
+ public final static String parseGenbankAccessorFromString( final String s ) {\r
+ Matcher m = GENBANK_NUC_PATTERN_1.matcher( s );\r
if ( m.lookingAt() ) {\r
return m.group( 1 );\r
}\r
else {\r
- m = GENBANK_NUCLEOTIDE_AC_PATTERN_2.matcher( query );\r
+ m = GENBANK_NUC_PATTERN_2.matcher( s );\r
if ( m.lookingAt() ) {\r
return m.group( 1 );\r
}\r
else {\r
- m = GENBANK_PROTEIN_AC_PATTERN.matcher( query );\r
+ m = GENBANK_PROT_PATTERN.matcher( s );\r
if ( m.lookingAt() ) {\r
return m.group( 1 );\r
}\r
}\r
}\r
\r
- public static String parseGenbankProteinAccessor( final String query ) {\r
- final Matcher m = GENBANK_PROTEIN_AC_PATTERN.matcher( query );\r
+ public final static String parseGenbankProteinAccessorFromString( final String s ) {\r
+ final Matcher m = GENBANK_PROT_PATTERN.matcher( s );\r
if ( m.lookingAt() ) {\r
return m.group( 1 );\r
}\r
}\r
}\r
\r
- public static String parseGInumber( final String query ) {\r
- final Matcher m = GI_PATTERN.matcher( query );\r
+ public final static String parseGInumberFromString( final String s ) {\r
+ final Matcher m = GI_PATTERN.matcher( s );\r
+ if ( m.find() ) {\r
+ return m.group( 1 );\r
+ }\r
+ return null;\r
+ }\r
+\r
+ public final static String parseEnsemlAccessorFromString( final String s ) {\r
+ final Matcher m = ENSEMBL_PATTERN.matcher( s );\r
if ( m.find() ) {\r
return m.group( 1 );\r
}\r
return null;\r
}\r
\r
- /**\r
- * Returns null if no match.\r
- * \r
- */\r
- public final static String parseRefSeqAccessor( final String query ) {\r
- final Matcher m = REFSEQ_PATTERN.matcher( query );\r
+ public final static String parseRefSeqAccessorFromString( final String s ) {\r
+ final Matcher m = REFSEQ_PATTERN.matcher( s );\r
if ( m.lookingAt() ) {\r
return m.group( 1 );\r
}\r
return null;\r
}\r
+\r
+ public final static String parseUniProtAccessorFromString( final String s ) {\r
+ Matcher m = UNIPROT_KB_PATTERN_1.matcher( s );\r
+ if ( m.find() ) {\r
+ return m.group( 1 );\r
+ }\r
+ m = UNIPROT_KB_PATTERN_2.matcher( s );\r
+ if ( m.find() ) {\r
+ return m.group();\r
+ }\r
+ m = UNIPROT_KB_PATTERN_0.matcher( s );\r
+ if ( m.find() ) {\r
+ return m.group( 1 );\r
+ }\r
+ return null;\r
+ }\r
}\r
git://source.jalview.org / jalview.git / blobdiff