+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.ext.ensembl;
import jalview.datamodel.DBRefSource;
* A base class for Ensembl sequence fetchers
*
* @author gmcarstairs
- *
*/
-public abstract class EnsemblSequenceFetcher extends DbSourceProxyImpl
+abstract class EnsemblSequenceFetcher extends DbSourceProxyImpl
{
/*
- * possible values for the 'feature' parameter of the REST overlap endpoint
- * @see
+ * accepts ENSG/T/E/P with 11 digits
+ * or ENSMUSP or similar for other species
+ * or CCDSnnnnn.nn with at least 3 digits
+ */
+ private static final Regex ACCESSION_REGEX = new Regex(
+ "(ENS([A-Z]{3}|)[GTEP]{1}[0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
+
+ protected static final String ENSEMBL_GENOMES_REST = "http://rest.ensemblgenomes.org";
+
+ protected static final String ENSEMBL_REST = "http://rest.ensembl.org";
+
+ /*
+ * possible values for the 'feature' parameter of the /overlap REST service
+ * @see http://rest.ensembl.org/documentation/info/overlap_id
*/
protected enum EnsemblFeatureType
{
constrained, regulatory
}
+ private String domain = ENSEMBL_REST;
+
@Override
public String getDbSource()
{
// NB ensure Uniprot xrefs are canonicalised from "Ensembl" to "ENSEMBL"
- return DBRefSource.ENSEMBL; // "ENSEMBL"
- }
-
- @Override
- public String getDbVersion()
- {
- return "0";
+ if (ENSEMBL_GENOMES_REST.equals(getDomain()))
+ {
+ return DBRefSource.ENSEMBLGENOMES;
+ }
+ return DBRefSource.ENSEMBL;
}
@Override
return " ";
}
+ /**
+ * Ensembl accession are ENST + 11 digits for human transcript, ENSG for human
+ * gene. Other species insert 3 letters e.g. ENSMUST..., ENSMUSG...
+ *
+ * @see http://www.ensembl.org/Help/View?id=151
+ */
@Override
public Regex getAccessionValidator()
{
- return new Regex("((ENSP|ENST|ENSG|CCDS)[0-9.]{3,})");
+ return ACCESSION_REGEX;
}
@Override
{
return true;
}
+
+ /**
+ * Returns the domain name to query e.g. http://rest.ensembl.org or
+ * http://rest.ensemblgenomes.org
+ *
+ * @return
+ */
+ protected String getDomain()
+ {
+ return domain;
+ }
+
+ protected void setDomain(String d)
+ {
+ domain = d;
+ }
}