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
44 AlignmentFileReaderI, AlignmentFileWriterI
51 * Sequences to be added to form a new alignment. TODO: remove vector in this
54 protected Vector<SequenceI> seqs;
57 * annotation to be added to generated alignment object
59 protected Vector<AlignmentAnnotation> annotations;
62 * SequenceGroups to be added to the alignment object
64 protected List<SequenceGroup> seqGroups;
67 * Properties to be added to generated alignment object
69 private Hashtable properties;
75 private boolean parseCalled;
78 * Creates a new AlignFile object.
82 // Shouldn't we init data structures (JBPNote: not sure - initData is for
83 // initialising the structures used for reading from a datasource, and the
84 // bare constructor hasn't got any datasource)
88 public AlignFile(SequenceI[] seqs)
95 * Constructor which parses the data from a file of some specified type.
98 * Filename, URL or Pasted String to read from.
100 * What type of file to read from (File, URL, Pasted String)
102 public AlignFile(String dataObject, DataSourceType sourceType)
105 this(true, dataObject, sourceType);
109 * Constructor which (optionally delays) parsing of data from a file of some
112 * @param parseImmediately
113 * if false, need to call 'doParse()' to begin parsing data
115 * Filename, URL or Pasted String to read from.
117 * What type of file to read from (File, URL)
118 * @throws IOException
120 public AlignFile(boolean parseImmediately, String dataObject,
121 DataSourceType sourceType)
124 super(dataObject, sourceType);
126 if (parseImmediately)
133 * Attempt to read from the position where some other parsing process left
137 * @throws IOException
139 public AlignFile(FileParse source) throws IOException
145 * Construct a new parser to read from the position where some other parsing
148 * @param parseImmediately
149 * if false, need to call 'doParse()' to begin parsing data
152 public AlignFile(boolean parseImmediately, FileParse source)
157 if (parseImmediately)
164 * called if parsing was delayed till after parser was constructed
166 * @throws IOException
168 public void doParse() throws IOException
172 throw new IOException(
173 "Implementation error: Parser called twice for same data.\n"
174 + "Need to call initData() again before parsing can be reattempted.");
178 // sets the index of each sequence in the alignment
179 for (int i = 0, c = seqs.size(); i < c; i++)
181 seqs.get(i).setIndex(i);
186 * Return the seqs Vector
188 public Vector<SequenceI> getSeqs()
193 public List<SequenceGroup> getSeqGroups()
199 * Return the Sequences in the seqs Vector as an array of Sequences
202 public SequenceI[] getSeqsAsArray()
204 SequenceI[] s = new SequenceI[seqs.size()];
206 for (int i = 0; i < seqs.size(); i++)
208 s[i] = seqs.elementAt(i);
215 * called by AppletFormatAdapter to generate an annotated alignment, rather
216 * than bare sequences.
221 public void addAnnotations(AlignmentI al)
224 for (int i = 0; i < annotations.size(); i++)
226 // detect if annotations.elementAt(i) rna secondary structure
229 * SequenceFeature[] pairArray =
230 * Rna.GetBasePairsFromAlignmentAnnotation(annotations.elementAt(i));
231 * Rna.HelixMap(pairArray);
233 AlignmentAnnotation an = annotations.elementAt(i);
234 an.validateRangeAndDisplay();
235 al.addAnnotation(an);
241 * register sequence groups on the alignment for **output**
245 public void addSeqGroups(AlignmentI al)
247 this.seqGroups = al.getGroups();
252 * Add any additional information extracted from the file to the alignment
255 * @note implicitly called by addAnnotations()
258 public void addProperties(AlignmentI al)
260 if (properties != null && properties.size() > 0)
262 Enumeration keys = properties.keys();
263 Enumeration vals = properties.elements();
264 while (keys.hasMoreElements())
266 al.setProperty(keys.nextElement(), vals.nextElement());
272 * Store a non-null key-value pair in a hashtable used to set alignment
273 * properties note: null keys will raise an error, null values will result in
274 * the key/value pair being silently ignored.
277 * - non-null key object
281 protected void setAlignmentProperty(Object key, Object value)
287 .getString("error.implementation_error_cannot_have_null_alignment"));
291 return; // null properties are ignored.
293 if (properties == null)
295 properties = new Hashtable();
297 properties.put(key, value);
300 protected Object getAlignmentProperty(Object key)
302 if (properties != null && key != null)
304 return properties.get(key);
310 * Initialise objects to store sequence data in.
312 protected void initData()
314 seqs = new Vector<SequenceI>();
315 annotations = new Vector<AlignmentAnnotation>();
316 seqGroups = new ArrayList<SequenceGroup>();
327 public void setSeqs(SequenceI[] s)
329 seqs = new Vector<SequenceI>();
331 for (int i = 0; i < s.length; i++)
333 seqs.addElement(s[i]);
338 * This method must be implemented to parse the contents of the file.
340 public abstract void parse() throws IOException;
343 * A general parser for ids.
345 * @String id Id to be parsed
347 Sequence parseId(String id)
351 int space = id.indexOf(" ");
354 seq = new Sequence(id.substring(0, space), "");
355 String desc = id.substring(space + 1);
356 seq.setDescription(desc);
359 * it is tempting to parse Ensembl style gene description e.g.
360 * chromosome:GRCh38:7:140696688:140721955:1 and set the
361 * start position of the sequence, but this causes much confusion
362 * for reverse strand feature locations
367 seq = new Sequence(id, "");
374 * Creates the output id. Adds prefix Uniprot format source|id and optionally
375 * suffix Jalview /start-end
379 * @String id Id to be parsed
381 String printId(SequenceI seq, boolean jvsuffix)
383 return seq.getDisplayId(jvsuffix);
386 String printId(SequenceI seq)
388 return printId(seq, true);
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())
420 protected void addSequence(SequenceI seq)