+ // dataset gets contaminated ccwith non-ds sequences. why ??!
+ // try: Ensembl -> Nuc->Ensembl, Nuc->Uniprot-->Protein->EMBL->
+ SequenceI retrievedDss = retrievedSequence
+ .getDatasetSequence() == null ? retrievedSequence
+ : retrievedSequence.getDatasetSequence();
+ addedXref |= importCrossRefSeq(cf, newDsSeqs, doNotAdd, dss,
+ retrievedDss);
+ }
+ }
+ for (SequenceI newToSeq : newDsSeqs)
+ {
+ if (!doNotAdd.contains(newToSeq)
+ && dataset.findIndex(newToSeq) == -1)
+ {
+ dataset.addSequence(newToSeq);
+ matcher.add(newToSeq);
+ }
+ }
+ }
+ }
+
+ /**
+ * Search dataset for sequences with a primary reference contained in
+ * sourceRefs.
+ *
+ * @param sourceRefs
+ * - list of references to filter.
+ * @param fromDna
+ * - type of sequence to search for matching primary reference.
+ */
+ private void removeAlreadyRetrievedSeqs(List<DBRefEntry> sourceRefs,
+ boolean fromDna)
+ {
+ List<DBRefEntry> dbrSourceSet = new ArrayList<>(sourceRefs);
+ List<SequenceI> dsSeqs = dataset.getSequences();
+ for (int ids = 0, nds = dsSeqs.size(); ids < nds; ids++)
+ {
+ SequenceI sq = dsSeqs.get(ids);
+ boolean dupeFound = false;
+ // !fromDna means we are looking only for nucleotide sequences, not
+ // protein
+ if (sq.isProtein() == fromDna)
+ {
+ List<DBRefEntry> sqdbrefs = sq.getPrimaryDBRefs();
+ for (int idb = 0, ndb = sqdbrefs.size(); idb < ndb; idb++)
+ {
+ DBRefEntry dbr = sqdbrefs.get(idb);
+ List<DBRefEntry> searchrefs = DBRefUtils.searchRefs(dbrSourceSet,
+ dbr, DBRefUtils.SEARCH_MODE_FULL);
+ for (int isr = 0, nsr = searchrefs.size(); isr < nsr; isr++)