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 java.io.IOException;
24 import java.util.ArrayList;
25 import java.util.Enumeration;
26 import java.util.Hashtable;
27 import java.util.List;
28 import java.util.Vector;
30 import jalview.datamodel.AlignmentAnnotation;
31 import jalview.datamodel.AlignmentI;
32 import jalview.datamodel.Sequence;
33 import jalview.datamodel.SequenceGroup;
34 import jalview.datamodel.SequenceI;
35 import jalview.util.MessageManager;
43 public abstract class AlignFile extends FileParse
44 implements 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;
76 * true if parse() has been called
78 private boolean parseCalled = false;
80 private boolean parseImmediately = true;
82 private boolean dataClosed = false;
85 * @return if doParse() was called at construction time
87 protected boolean isParseImmediately()
89 return parseImmediately;
93 * Creates a new AlignFile object.
97 // Shouldn't we init data structures (JBPNote: not sure - initData is for
98 // initialising the structures used for reading from a datasource, and the
99 // bare constructor hasn't got any datasource)
103 public AlignFile(SequenceI[] seqs)
110 * Constructor which parses the data from a file of some specified type.
113 * Filename, URL or Pasted String to read from.
115 * What type of file to read from (File, URL, Pasted String)
117 public AlignFile(Object dataObject, DataSourceType sourceType)
120 this(true, dataObject, sourceType);
124 * Constructor which (optionally delays) parsing of data from a file of some
127 * @param parseImmediately
128 * if false, need to call 'doParse()' to begin parsing data
130 * Filename, URL or Pasted String to read from.
132 * What type of file to read from (File, URL)
133 * @throws IOException
135 public AlignFile(boolean parseImmediately, Object dataObject,
136 DataSourceType sourceType) throws IOException
138 // BH allows File or String
139 super(dataObject, sourceType);
141 if (parseImmediately)
148 * Attempt to read from the position where some other parsing process left
152 * @throws IOException
154 public AlignFile(FileParse source) throws IOException
160 * Construct a new parser to read from the position where some other parsing
163 * @param parseImmediately
164 * if false, need to call 'doParse()' to begin parsing data
167 public AlignFile(boolean parseImmediately, FileParse source)
170 this(parseImmediately, source, true);
173 public AlignFile(boolean parseImmediately, FileParse source,
174 boolean closeData) throws IOException
179 // stash flag in case parse needs to know if it has to autoconfigure or was
180 // configured after construction
181 this.parseImmediately = parseImmediately;
183 if (parseImmediately)
190 * called if parsing was delayed till after parser was constructed
192 * @throws IOException
194 public void doParse() throws IOException
199 public void doParse(boolean closeData) throws IOException
203 throw new IOException(
204 "Implementation error: Parser called twice for same data.\n"
205 + "Need to call initData() again before parsing can be reattempted.");
209 if (closeData && !dataClosed)
217 * Return the seqs Vector
219 public Vector<SequenceI> getSeqs()
224 public List<SequenceGroup> getSeqGroups()
230 * Return the Sequences in the seqs Vector as an array of Sequences
233 public SequenceI[] getSeqsAsArray()
235 SequenceI[] s = new SequenceI[seqs.size()];
237 for (int i = 0; i < seqs.size(); i++)
239 s[i] = seqs.elementAt(i);
246 * called by AppletFormatAdapter to generate an annotated alignment, rather
247 * than bare sequences.
252 public void addAnnotations(AlignmentI al)
255 for (int i = 0; i < annotations.size(); i++)
257 // detect if annotations.elementAt(i) rna secondary structure
260 * SequenceFeature[] pairArray =
261 * Rna.GetBasePairsFromAlignmentAnnotation(annotations.elementAt(i));
262 * Rna.HelixMap(pairArray);
264 AlignmentAnnotation an = annotations.elementAt(i);
265 an.validateRangeAndDisplay();
266 al.addAnnotation(an);
272 * register sequence groups on the alignment for **output**
276 public void addSeqGroups(AlignmentI al)
278 this.seqGroups = al.getGroups();
283 * Add any additional information extracted from the file to the alignment
286 * @note implicitly called by addAnnotations()
289 public void addProperties(AlignmentI al)
291 if (properties != null && properties.size() > 0)
293 Enumeration keys = properties.keys();
294 Enumeration vals = properties.elements();
295 while (keys.hasMoreElements())
297 al.setProperty(keys.nextElement(), vals.nextElement());
303 * Store a non-null key-value pair in a hashtable used to set alignment
304 * properties note: null keys will raise an error, null values will result in
305 * the key/value pair being silently ignored.
308 * - non-null key object
312 protected void setAlignmentProperty(Object key, Object value)
316 throw new Error(MessageManager.getString(
317 "error.implementation_error_cannot_have_null_alignment"));
321 return; // null properties are ignored.
323 if (properties == null)
325 properties = new Hashtable();
327 properties.put(key, value);
330 protected Object getAlignmentProperty(Object key)
332 if (properties != null && key != null)
334 return properties.get(key);
340 * Initialise objects to store sequence data in.
342 protected void initData()
344 seqs = new Vector<>();
345 annotations = new Vector<>();
346 seqGroups = new ArrayList<>();
357 public void setSeqs(SequenceI[] s)
359 seqs = new Vector<>();
361 for (int i = 0; i < s.length; i++)
363 seqs.addElement(s[i]);
368 * This method must be implemented to parse the contents of the file.
370 public abstract void parse() throws IOException;
373 * A general parser for ids.
375 * @String id Id to be parsed
377 Sequence parseId(String id)
381 int space = id.indexOf(" ");
384 seq = new Sequence(id.substring(0, space), "");
385 String desc = id.substring(space + 1);
386 seq.setDescription(desc);
389 * it is tempting to parse Ensembl style gene description e.g.
390 * chromosome:GRCh38:7:140696688:140721955:1 and set the
391 * start position of the sequence, but this causes much confusion
392 * for reverse strand feature locations
397 seq = new Sequence(id, "");
404 * Creates the output id. Adds prefix Uniprot format source|id and optionally
405 * suffix Jalview /start-end
409 * @String id Id to be parsed
411 String printId(SequenceI seq, boolean jvsuffix)
413 return seq.getDisplayId(jvsuffix);
416 String printId(SequenceI seq)
418 return printId(seq, true);
422 * vector of String[] treeName, newickString pairs
424 Vector<String[]> newickStrings = null;
426 protected void addNewickTree(String treeName, String newickString)
428 if (newickStrings == null)
430 newickStrings = new Vector<>();
432 newickStrings.addElement(new String[] { treeName, newickString });
435 protected int getTreeCount()
437 return newickStrings == null ? 0 : newickStrings.size();
441 public void addGroups(AlignmentI al)
444 for (SequenceGroup sg : getSeqGroups())
450 protected void addSequence(SequenceI seq)
456 * Used only for hmmer statistics, so should probably be removed at some
457 * point. TODO remove this
461 public Vector<AlignmentAnnotation> getAnnotations()