2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1)
3 * Copyright (C) 2014 The Jalview Authors
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/>.
17 * The Jalview Authors are detailed in the 'AUTHORS' file.
19 package jalview.ws.dbsources.das.datamodel;
21 import java.util.ArrayList;
22 import java.util.Arrays;
23 import java.util.HashMap;
24 import java.util.List;
26 import java.util.StringTokenizer;
27 import java.util.Vector;
29 import org.biodas.jdas.client.SequenceClient;
30 import org.biodas.jdas.client.adapters.sequence.DasSequenceAdapter;
31 import org.biodas.jdas.client.threads.MultipleConnectionPropertyProviderI;
32 import org.biodas.jdas.client.threads.SequenceClientMultipleSources;
33 import org.biodas.jdas.schema.sequence.SEQUENCE;
34 import org.biodas.jdas.schema.sources.COORDINATES;
35 import org.biodas.jdas.schema.sources.SOURCE;
36 import org.biodas.jdas.schema.sources.VERSION;
38 import com.stevesoft.pat.Regex;
40 import jalview.ws.dbsources.das.api.jalviewSourceI;
41 import jalview.ws.seqfetcher.*;
42 import jalview.bin.Cache;
43 import jalview.datamodel.Alignment;
44 import jalview.datamodel.AlignmentI;
45 import jalview.datamodel.DBRefEntry;
46 import jalview.datamodel.Sequence;
47 import jalview.datamodel.SequenceI;
50 * an instance of this class is created for each unique DAS Sequence source (ie
51 * one capable of handling the 'sequence' for a particular MapMaster)
56 public class DasSequenceSource extends DbSourceProxyImpl implements
59 private jalviewSourceI jsrc;
61 protected SOURCE source = null;
63 protected VERSION version = null;
65 protected COORDINATES coordsys = null;
67 protected String dbname = "DASCS";
69 protected String dbrefname = "das:source";
71 protected MultipleConnectionPropertyProviderI connprops = null;
74 * DAS sources are tier 1 - if we have a direct DB connection then we should prefer it
79 * create a new DbSource proxy for a DAS 1 source
82 * Human Readable Name to use when fetching from this source
84 * DbRefName for DbRefs attached to sequences retrieved from this
89 * specific coordinate system to use for this source
91 * if source is not capable of the 'sequence' command
93 public DasSequenceSource(String dbname, String dbrefname, SOURCE source,
94 VERSION version, COORDINATES coordsys,
95 MultipleConnectionPropertyProviderI connprops) throws Exception
97 if (!(jsrc = new JalviewSource(source, connprops, false))
100 throw new Exception("Source " + source.getTitle()
101 + " does not support the sequence command.");
103 this.tier = 1+((jsrc.isLocal() || jsrc.isReferenceSource()) ? 0 : 1);
104 this.source = source;
105 this.dbname = dbname;
106 this.dbrefname = dbrefname.toUpperCase();
107 if (coordsys != null)
109 this.coordsys = coordsys;
111 this.connprops = connprops;
114 public String getAccessionSeparator()
119 public Regex getAccessionValidator()
122 return Regex.perlCode("m/([^:]+)(:\\d+,\\d+)?/");
125 public String getDbName()
128 return dbname + " (DAS)";
131 public String getDbSource()
136 public String getDbVersion()
138 return coordsys != null ? coordsys.getVersion() : "";
141 public AlignmentI getSequenceRecords(String queries) throws Exception
143 StringTokenizer st = new StringTokenizer(queries, "\t");
144 List<String> toks = new ArrayList<String>(), src = new ArrayList<String>(), acIds = new ArrayList<String>();
145 while (st.hasMoreTokens())
148 toks.add(t = st.nextToken());
149 acIds.add(t.replaceAll(":[0-9,]+", ""));
151 src.add(jsrc.getSourceURL());
152 Map<String, Map<List<String>, DasSequenceAdapter>> resultset = new HashMap<String, Map<List<String>, DasSequenceAdapter>>();
153 Map<String, Map<List<String>, Exception>> errors = new HashMap<String, Map<List<String>, Exception>>();
155 // First try multiple sources
156 boolean multiple = true, retry = false;
162 // slow, fetch one at a time.
163 for (String sr : src)
166 .println("Retrieving IDs individually from das source: "
168 org.biodas.jdas.client.SequenceClient sq = new SequenceClient(
169 connprops.getConnectionPropertyProviderFor(sr));
170 for (String q : toks)
172 List<String> qset = Arrays.asList(new String[]
176 DasSequenceAdapter s = sq.fetchData(sr, qset);
177 Map<List<String>, DasSequenceAdapter> dss = resultset.get(sr);
182 dss = new HashMap<List<String>, DasSequenceAdapter>());
185 } catch (Exception x)
187 Map<List<String>, Exception> ers = errors.get(sr);
190 errors.put(sr, ers = new HashMap<List<String>, Exception>());
199 SequenceClientMultipleSources sclient;
200 sclient = new SequenceClientMultipleSources();
201 sclient.fetchData(src, toks, resultset, errors);
203 while (!sclient.isTerminated())
209 } catch (InterruptedException x)
213 if (resultset.isEmpty() && !errors.isEmpty())
221 if (resultset.isEmpty())
223 System.err.println("Sequence Query to " + jsrc.getTitle() + " with '"
224 + queries + "' returned no sequences.");
229 Vector<SequenceI> seqs = null;
230 for (Map.Entry<String, Map<List<String>, DasSequenceAdapter>> resset : resultset
233 for (Map.Entry<List<String>, DasSequenceAdapter> result : resset
234 .getValue().entrySet())
236 DasSequenceAdapter dasseqresp = result.getValue();
237 List<String> accessions = result.getKey();
238 for (SEQUENCE e : dasseqresp.getSequence())
240 String lbl = e.getId();
242 if (acIds.indexOf(lbl) == -1)
245 .println("Warning - received sequence event for strange accession code ("
252 if (e.getContent().length() == 0)
255 .println("Empty sequence returned for accession code ("
259 + " (source is " + getDbName());
263 seqs = new java.util.Vector<SequenceI>();
264 // JDAS returns a sequence complete with any newlines and spaces
266 Sequence sq = new Sequence(lbl, e.getContent().replaceAll(
268 sq.setStart(e.getStart().intValue());
269 sq.addDBRef(new DBRefEntry(getDbSource(), getDbVersion()
270 + ":" + e.getVersion(), lbl));
277 if (seqs == null || seqs.size() == 0)
279 SequenceI[] sqs = new SequenceI[seqs.size()];
280 for (int i = 0, iSize = seqs.size(); i < iSize; i++)
282 sqs[i] = (SequenceI) seqs.elementAt(i);
284 Alignment al = new Alignment(sqs);
285 if (jsrc.isFeatureSource())
287 java.util.Vector<jalviewSourceI> srcs = new java.util.Vector<jalviewSourceI>();
288 srcs.addElement(jsrc);
291 jalview.ws.DasSequenceFeatureFetcher dssf = new jalview.ws.DasSequenceFeatureFetcher(
292 sqs, null, srcs, false, false, multiple);
293 while (dssf.isRunning())
298 } catch (InterruptedException x)
304 } catch (Exception x)
307 .error("Couldn't retrieve features for sequence from its source.",
316 public String getTestQuery()
318 return coordsys == null ? "" : coordsys.getTestRange();
321 public boolean isValidReference(String accession)
323 // TODO try to validate an accession against source
324 // We don't really know how to do this without querying source
332 public SOURCE getSource()
338 * @return the coordsys
340 public COORDINATES getCoordsys()