2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ 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
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
23 import jalview.datamodel.AlignmentAnnotation;
24 import jalview.datamodel.AlignmentI;
25 import jalview.datamodel.Sequence;
26 import jalview.datamodel.SequenceGroup;
27 import jalview.datamodel.SequenceI;
28 import jalview.util.MessageManager;
30 import java.io.IOException;
31 import java.util.ArrayList;
32 import java.util.Enumeration;
33 import java.util.Hashtable;
34 import java.util.List;
35 import java.util.Vector;
43 public abstract class AlignFile extends FileParse implements AlignmentFileI
50 * Sequences to be added to form a new alignment. TODO: remove vector in this
53 protected Vector<SequenceI> seqs;
56 * annotation to be added to generated alignment object
58 protected Vector<AlignmentAnnotation> annotations;
61 * SequenceGroups to be added to the alignment object
63 protected List<SequenceGroup> seqGroups;
66 * Properties to be added to generated alignment object
68 protected Hashtable properties;
74 boolean jvSuffix = true;
76 private boolean parseCalled;
79 * Creates a new AlignFile object.
83 // Shouldn't we init data structures (JBPNote: not sure - initData is for
84 // initialising the structures used for reading from a datasource, and the
85 // bare constructor hasn't got any datasource)
90 * Constructor which parses the data from a file of some specified type.
93 * Filename, URL or Pasted String to read from.
95 * What type of file to read from (File, URL, Pasted String)
97 public AlignFile(String dataObject, DataSourceType sourceType)
100 this(true, dataObject, sourceType);
104 * Constructor which (optionally delays) parsing of data from a file of some
107 * @param parseImmediately
108 * if false, need to call 'doParse()' to begin parsing data
110 * Filename, URL or Pasted String to read from.
112 * What type of file to read from (File, URL)
113 * @throws IOException
115 public AlignFile(boolean parseImmediately, String dataObject,
116 DataSourceType sourceType)
119 super(dataObject, sourceType);
121 if (parseImmediately)
128 * Attempt to read from the position where some other parsing process left
132 * @throws IOException
134 public AlignFile(FileParse source) throws IOException
140 * Construct a new parser to read from the position where some other parsing
143 * @param parseImmediately
144 * if false, need to call 'doParse()' to begin parsing data
147 public AlignFile(boolean parseImmediately, FileParse source)
152 if (parseImmediately)
159 * called if parsing was delayed till after parser was constructed
161 * @throws IOException
163 public void doParse() throws IOException
167 throw new IOException(
168 "Implementation error: Parser called twice for same data.\n"
169 + "Need to call initData() again before parsing can be reattempted.");
173 // sets the index of each sequence in the alignment
174 for (int i = 0, c = seqs.size(); i < c; i++)
176 seqs.get(i).setIndex(i);
181 * Return the seqs Vector
183 public Vector<SequenceI> getSeqs()
188 public List<SequenceGroup> getSeqGroups()
194 * Return the Sequences in the seqs Vector as an array of Sequences
197 public SequenceI[] getSeqsAsArray()
199 SequenceI[] s = new SequenceI[seqs.size()];
201 for (int i = 0; i < seqs.size(); i++)
203 s[i] = seqs.elementAt(i);
210 * called by AppletFormatAdapter to generate an annotated alignment, rather
211 * than bare sequences.
216 public void addAnnotations(AlignmentI al)
219 for (int i = 0; i < annotations.size(); i++)
221 // detect if annotations.elementAt(i) rna secondary structure
224 * SequenceFeature[] pairArray =
225 * Rna.GetBasePairsFromAlignmentAnnotation(annotations.elementAt(i));
226 * Rna.HelixMap(pairArray);
228 AlignmentAnnotation an = annotations.elementAt(i);
229 an.validateRangeAndDisplay();
230 al.addAnnotation(an);
236 * register sequence groups on the alignment for **output**
240 public void addSeqGroups(AlignmentI al)
242 this.seqGroups = al.getGroups();
247 * Add any additional information extracted from the file to the alignment
250 * @note implicitly called by addAnnotations()
253 public void addProperties(AlignmentI al)
255 if (properties != null && properties.size() > 0)
257 Enumeration keys = properties.keys();
258 Enumeration vals = properties.elements();
259 while (keys.hasMoreElements())
261 al.setProperty(keys.nextElement(), vals.nextElement());
267 * Store a non-null key-value pair in a hashtable used to set alignment
268 * properties note: null keys will raise an error, null values will result in
269 * the key/value pair being silently ignored.
272 * - non-null key object
276 protected void setAlignmentProperty(Object key, Object value)
282 .getString("error.implementation_error_cannot_have_null_alignment"));
286 return; // null properties are ignored.
288 if (properties == null)
290 properties = new Hashtable();
292 properties.put(key, value);
295 protected Object getAlignmentProperty(Object key)
297 if (properties != null && key != null)
299 return properties.get(key);
305 * Initialise objects to store sequence data in.
307 protected void initData()
309 seqs = new Vector<SequenceI>();
310 annotations = new Vector<AlignmentAnnotation>();
311 seqGroups = new ArrayList<SequenceGroup>();
322 public void setSeqs(SequenceI[] s)
324 seqs = new Vector<SequenceI>();
326 for (int i = 0; i < s.length; i++)
328 seqs.addElement(s[i]);
333 * This method must be implemented to parse the contents of the file.
335 public abstract void parse() throws IOException;
338 * Print out in alignment file format the Sequences in the seqs Vector.
341 public abstract String print();
344 public void addJVSuffix(boolean b)
350 * A general parser for ids.
352 * @String id Id to be parsed
354 Sequence parseId(String id)
358 int space = id.indexOf(" ");
361 seq = new Sequence(id.substring(0, space), "");
362 String desc = id.substring(space + 1);
363 seq.setDescription(desc);
366 * it is tempting to parse Ensembl style gene description e.g.
367 * chromosome:GRCh38:7:140696688:140721955:1 and set the
368 * start position of the sequence, but this causes much confusion
369 * for reverse strand feature locations
374 seq = new Sequence(id, "");
381 * Creates the output id. Adds prefix Uniprot format source|id And suffix
384 * @String id Id to be parsed
386 String printId(SequenceI seq)
388 return seq.getDisplayId(jvSuffix);
392 * vector of String[] treeName, newickString pairs
394 Vector<String[]> newickStrings = null;
396 protected void addNewickTree(String treeName, String newickString)
398 if (newickStrings == null)
400 newickStrings = new Vector<String[]>();
402 newickStrings.addElement(new String[] { treeName, newickString });
405 protected int getTreeCount()
407 return newickStrings == null ? 0 : newickStrings.size();
411 public void addGroups(AlignmentI al)
414 for (SequenceGroup sg : getSeqGroups())