2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
3 * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
11 * Jalview is distributed in the hope that it will be useful, but
12 * WITHOUT ANY WARRANTY; without even the implied warranty
13 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
14 * PURPOSE. See the GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
18 package jalview.ws.dbsources.das.datamodel;
20 import java.util.ArrayList;
21 import java.util.Arrays;
22 import java.util.HashMap;
23 import java.util.List;
25 import java.util.StringTokenizer;
26 import java.util.Vector;
28 import org.biodas.jdas.client.SequenceClient;
29 import org.biodas.jdas.client.adapters.sequence.DasSequenceAdapter;
30 import org.biodas.jdas.client.threads.MultipleConnectionPropertyProviderI;
31 import org.biodas.jdas.client.threads.SequenceClientMultipleSources;
32 import org.biodas.jdas.schema.sequence.SEQUENCE;
33 import org.biodas.jdas.schema.sources.COORDINATES;
34 import org.biodas.jdas.schema.sources.SOURCE;
35 import org.biodas.jdas.schema.sources.VERSION;
37 import com.stevesoft.pat.Regex;
39 import jalview.ws.dbsources.das.api.jalviewSourceI;
40 import jalview.ws.seqfetcher.*;
41 import jalview.bin.Cache;
42 import jalview.datamodel.Alignment;
43 import jalview.datamodel.AlignmentI;
44 import jalview.datamodel.DBRefEntry;
45 import jalview.datamodel.Sequence;
46 import jalview.datamodel.SequenceI;
49 * an instance of this class is created for each unique DAS Sequence source (ie
50 * one capable of handling the 'sequence' for a particular MapMaster)
55 public class DasSequenceSource extends DbSourceProxyImpl implements
58 private jalviewSourceI jsrc;
60 protected SOURCE source = null;
62 protected VERSION version = null;
64 protected COORDINATES coordsys = null;
66 protected String dbname = "DASCS";
68 protected String dbrefname = "das:source";
70 protected MultipleConnectionPropertyProviderI connprops = null;
73 * DAS sources are tier 1 - if we have a direct DB connection then we should prefer it
78 * create a new DbSource proxy for a DAS 1 source
81 * Human Readable Name to use when fetching from this source
83 * DbRefName for DbRefs attached to sequences retrieved from this
88 * specific coordinate system to use for this source
90 * if source is not capable of the 'sequence' command
92 public DasSequenceSource(String dbname, String dbrefname, SOURCE source,
93 VERSION version, COORDINATES coordsys,
94 MultipleConnectionPropertyProviderI connprops) throws Exception
96 if (!(jsrc = new JalviewSource(source, connprops, false))
99 throw new Exception("Source " + source.getTitle()
100 + " does not support the sequence command.");
102 this.tier = 1+((jsrc.isLocal() || jsrc.isReferenceSource()) ? 0 : 1);
103 this.source = source;
104 this.dbname = dbname;
105 this.dbrefname = dbrefname.toUpperCase();
106 if (coordsys != null)
108 this.coordsys = coordsys;
110 this.connprops = connprops;
113 public String getAccessionSeparator()
118 public Regex getAccessionValidator()
121 return Regex.perlCode("m/([^:]+)(:\\d+,\\d+)?/");
124 public String getDbName()
127 return dbname + " (DAS)";
130 public String getDbSource()
135 public String getDbVersion()
137 return coordsys != null ? coordsys.getVersion() : "";
140 public AlignmentI getSequenceRecords(String queries) throws Exception
142 StringTokenizer st = new StringTokenizer(queries, "\t");
143 List<String> toks = new ArrayList<String>(), src = new ArrayList<String>(), acIds = new ArrayList<String>();
144 while (st.hasMoreTokens())
147 toks.add(t = st.nextToken());
148 acIds.add(t.replaceAll(":[0-9,]+", ""));
150 src.add(jsrc.getSourceURL());
151 Map<String, Map<List<String>, DasSequenceAdapter>> resultset = new HashMap<String, Map<List<String>, DasSequenceAdapter>>();
152 Map<String, Map<List<String>, Exception>> errors = new HashMap<String, Map<List<String>, Exception>>();
154 // First try multiple sources
155 boolean multiple = true, retry = false;
161 // slow, fetch one at a time.
162 for (String sr : src)
165 .println("Retrieving IDs individually from das source: "
167 org.biodas.jdas.client.SequenceClient sq = new SequenceClient(
168 connprops.getConnectionPropertyProviderFor(sr));
169 for (String q : toks)
171 List<String> qset = Arrays.asList(new String[]
175 DasSequenceAdapter s = sq.fetchData(sr, qset);
176 Map<List<String>, DasSequenceAdapter> dss = resultset.get(sr);
181 dss = new HashMap<List<String>, DasSequenceAdapter>());
184 } catch (Exception x)
186 Map<List<String>, Exception> ers = errors.get(sr);
189 errors.put(sr, ers = new HashMap<List<String>, Exception>());
198 SequenceClientMultipleSources sclient;
199 sclient = new SequenceClientMultipleSources();
200 sclient.fetchData(src, toks, resultset, errors);
202 while (!sclient.isTerminated())
208 } catch (InterruptedException x)
212 if (resultset.isEmpty() && !errors.isEmpty())
220 if (resultset.isEmpty())
222 System.err.println("Sequence Query to " + jsrc.getTitle() + " with '"
223 + queries + "' returned no sequences.");
228 Vector<SequenceI> seqs = null;
229 for (Map.Entry<String, Map<List<String>, DasSequenceAdapter>> resset : resultset
232 for (Map.Entry<List<String>, DasSequenceAdapter> result : resset
233 .getValue().entrySet())
235 DasSequenceAdapter dasseqresp = result.getValue();
236 List<String> accessions = result.getKey();
237 for (SEQUENCE e : dasseqresp.getSequence())
239 String lbl = e.getId();
241 if (acIds.indexOf(lbl) == -1)
244 .println("Warning - received sequence event for strange accession code ("
251 if (e.getContent().length() == 0)
254 .println("Empty sequence returned for accession code ("
258 + " (source is " + getDbName());
262 seqs = new java.util.Vector<SequenceI>();
263 // JDAS returns a sequence complete with any newlines and spaces
265 Sequence sq = new Sequence(lbl, e.getContent().replaceAll(
267 sq.setStart(e.getStart().intValue());
268 sq.addDBRef(new DBRefEntry(getDbSource(), getDbVersion()
269 + ":" + e.getVersion(), lbl));
276 if (seqs == null || seqs.size() == 0)
278 SequenceI[] sqs = new SequenceI[seqs.size()];
279 for (int i = 0, iSize = seqs.size(); i < iSize; i++)
281 sqs[i] = (SequenceI) seqs.elementAt(i);
283 Alignment al = new Alignment(sqs);
284 if (jsrc.isFeatureSource())
286 java.util.Vector<jalviewSourceI> srcs = new java.util.Vector<jalviewSourceI>();
287 srcs.addElement(jsrc);
290 jalview.ws.DasSequenceFeatureFetcher dssf = new jalview.ws.DasSequenceFeatureFetcher(
291 sqs, null, srcs, false, false, multiple);
292 while (dssf.isRunning())
297 } catch (InterruptedException x)
303 } catch (Exception x)
306 .error("Couldn't retrieve features for sequence from its source.",
315 public String getTestQuery()
317 return coordsys == null ? "" : coordsys.getTestRange();
320 public boolean isValidReference(String accession)
322 // TODO try to validate an accession against source
323 // We don't really know how to do this without querying source
331 public SOURCE getSource()
337 * @return the coordsys
339 public COORDINATES getCoordsys()