*/
package jalview.datamodel;
-import java.lang.reflect.Field;
-import java.util.ArrayList;
-import java.util.List;
-
/**
* BH 2018 SwingJS note: If additional final static Strings are added to this
* file, they should be added to public static final String[] allTypes.
- /**
- * UNIPROT Accession Number
- */
public static final String UNIPROT = "UNIPROT";
-
- /**
- * UNIPROT Entry Name
- */
public static final String UP_NAME = "UNIPROT_NAME".toUpperCase();
-
/**
* Uniprot Knowledgebase/TrEMBL as served from EMBL protein products.
*/
public static final String UNIPROTKB = "UniProtKB/TrEMBL".toUpperCase();
- public static final String EMBLCDSProduct = "EMBLCDSProtein".toUpperCase();
-
-
- /**
- * PDB Entry Code
- */
- public static final String PDB = "PDB";
-
- /**
- * EMBL ID
- */
- public static final String EMBL = "EMBL";
-
- /**
- * EMBLCDS ID
- */
- public static final String EMBLCDS = "EMBLCDS";
-
+ public static final String ENSEMBL = "ENSEMBL";
+ public static final String ENSEMBLGENOMES = "ENSEMBLGENOMES";
- /**
- * PFAM ID
- */
- public static final String PFAM = "PFAM";
-
- /**
- * RFAM ID
- */
- public static final String RFAM = "RFAM";
+ public static final String EMBL = "EMBL";
+ public static final String EMBLCDS = "EMBLCDS";
+ public static final String EMBLCDSProduct = "EMBLCDSProtein".toUpperCase();
- /**
- * GeneDB ID
- */
+ public static final String PDB = "PDB";
+ public static final String PFAM = "PFAM";
+ public static final String RFAM = "RFAM";
public static final String GENEDB = "GeneDB".toUpperCase();
-
- /**
- * Ensembl
- */
- public static final String ENSEMBL = "ENSEMBL";
+ public static final String PDB_CANONICAL_NAME = PDB;
+
+
+ public static final String[] allSources = new String[] {
+ UNIPROT,
+ UP_NAME, UNIPROTKB,
+ ENSEMBL, ENSEMBLGENOMES,
+ EMBL, EMBLCDS, EMBLCDSProduct,
+ PDB, PFAM, RFAM, GENEDB
+ };
+
+ public static final int UNIPROT_MASK = 1<<0;
+ public static final int UP_NAME_MASK = 1<<1;
+ public static final int UNIPROT_KB_MASK = 1<<2;
+ public static final int ENSEMBL_MASK = 1<<3;
+ public static final int ENSEMBL_GENOMES_MASK = 1<<4;
+ public static final int EMBL_MASK = 1<<5;
+ public static final int EMBL_CDS_MASK = 1<<6;
+ public static final int EMBL_CDS_PRODUCT_MASK = 1<<7;
+ public static final int PDB_MASK = 1<<8;
+ public static final int PFAM_MASK = 1<<9;
+ public static final int RFAM_MASK = 1<<10;
+ public static final int GENE_DB_MASK = 1<<11;
+
+ public static final int MASK_COUNT = 12;
+
+ public static final int ALL_MASKS = (1 << MASK_COUNT) - 1;
+
+ public static int getSourceKey(String name) {
+ for (int i = 0; i < MASK_COUNT; i++) {
+ if (name.equals(allSources[i]))
+ return 1<<i;
+ }
+ return 0;
+ }
+
+ public static final int PRIMARY_MASK = UNIPROT_MASK | ENSEMBL_MASK;
+
+ /**
+ * List of databases whose sequences might have coding regions annotated
+ */
+ public static final String[] DNACODINGDBS = {
+ ENSEMBL, ENSEMBLGENOMES,
+ EMBL, EMBLCDS, GENEDB
+ };
+
+ public static final int DNA_CODING_MASK =
+ ENSEMBL_MASK | ENSEMBL_GENOMES_MASK
+ | EMBL_MASK | EMBL_CDS_MASK | GENE_DB_MASK;
- public static final String ENSEMBLGENOMES = "ENSEMBLGENOMES";
+
+
+ public static final String[] CODINGDBS = { EMBLCDS, GENEDB, ENSEMBL };
+ public static final int CODING_MASK = EMBL_CDS_MASK | GENE_DB_MASK | ENSEMBL_MASK;
- /**
- * List of databases whose sequences might have coding regions annotated
- */
- public static final String[] DNACODINGDBS = { EMBL, EMBLCDS, GENEDB,
- ENSEMBL, ENSEMBLGENOMES };
-
- public static final String[] CODINGDBS = { EMBLCDS, GENEDB, ENSEMBL };
-
- public static final String[] PROTEINDBS = { UNIPROT, UNIPROTKB,
- EMBLCDSProduct, ENSEMBL }; // Ensembl ENSP* entries are protein
-
+
- public static final String[] allTypes = new String[] {
- UNIPROT, UP_NAME, UNIPROTKB,
- EMBLCDSProduct, PDB, EMBL,
- EMBLCDS, PFAM, RFAM,
- GENEDB, ENSEMBL, ENSEMBLGENOMES
- };
-
-public static final String PROTEINDBSKEYS, DNACODINGDBSKEYS;
-
-public static final String[] PROMTYPES;
-
-
-public static final int UNIPROT_MASK = 1;
-
-public static final int ENSEMBL_MASK = 2;
-
-public static final int ALL_MASKS = UNIPROT_MASK | ENSEMBL_MASK;
-
-public static final String PDB_CANONICAL_NAME = PDB;
-
-static {
- // BH 2019.01.25 trying to speed this up
- String s = ";";
- for (int i = PROTEINDBS.length; --i >= 0;)
- s += PROTEINDBS[i] + ";";
- PROTEINDBSKEYS = s;
-
- s = ";";
- for (int i = DNACODINGDBS.length; --i >= 0;)
- s += DNACODINGDBS[i] + ";";
- DNACODINGDBSKEYS = s;
-
- PROMTYPES = new String[] { null, ";" + UNIPROT + ";", ";" + ENSEMBL + ";" , ";" + UNIPROT + ";" + ENSEMBL + ";" };
-}
-
- public static String[] allSourcesFromReflection;
-
- public static String[] allSources()
+ public static final String[] PROTEINDBS = {
+ UNIPROT, UNIPROTKB,
+ ENSEMBL, EMBLCDSProduct }; // Ensembl ENSP* entries are protein
+
+ public static final int PROTEIN_MASK =
+ UNIPROT_MASK | UNIPROT_KB_MASK
+ | ENSEMBL_MASK | EMBL_CDS_PRODUCT_MASK ;
+
+
+ // for SequenceAnnotationReport only
+
+// public static final String[][] PRIMARY_SOURCES = new String[][] {
+// CODINGDBS, DNACODINGDBS, PROTEINDBS };
+//
+ public static final int PRIMARY_SOURCES_MASK = CODING_MASK | DNA_CODING_MASK | PROTEIN_MASK;
+
+ public static boolean isPrimarySource(String source)
+ {
+ return ((PRIMARY_SOURCES_MASK & getSourceKey(source)) != 0);
+ }
- {
- /**
- * @j2sNative
- *
- * return C$.allTypes;
- *
- */
+// public static String[] allSourcesFromReflection;
+//
+// public static String[] allSources()
+//
+// {
+// /**
+// * @j2sNative
+// *
+// * return C$.allTypes;
+// *
+// */
+//
+// {
+// if (allSourcesFromReflection == null)
+// {
+// List<String> src = new ArrayList<>();
+// for (Field f : DBRefSource.class.getFields())
+// {
+// if (String.class.equals(f.getType()))
+// {
+// try
+// {
+// src.add((String) f.get(null));
+// } catch (Exception x)
+// {
+// x.printStackTrace();
+// }
+// }
+// }
+// allSourcesFromReflection = src.toArray(new String[0]);
+// }
+// return allSourcesFromReflection;
+// }
+// }
+
+ public static boolean isPrimaryCandidate(String ucversion) {
+ // tricky - this test really needs to search the sequence's set of dbrefs to
+ // see if there is a primary reference that derived this reference.
+ for (int i = allSources.length; --i >= 0;)
{
- if (allSourcesFromReflection == null)
+ if (ucversion.startsWith(allSources[i])) // BH 2019.01.25 .toUpperCase() unnecessary here for allSources
{
- List<String> src = new ArrayList<>();
- for (Field f : DBRefSource.class.getFields())
- {
- if (String.class.equals(f.getType()))
- {
- try
- {
- src.add((String) f.get(null));
- } catch (Exception x)
- {
- x.printStackTrace();
- }
- }
- }
- allSourcesFromReflection = src.toArray(new String[0]);
+ // by convention, many secondary references inherit the primary
+ // reference's
+ // source string as a prefix for any version information from the
+ // secondary reference.
+ return false;
}
- return allSourcesFromReflection;
}
- }
-
+ return true;
+}
+
+
+
}