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
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 to read from.
95 * What type of file to read from (File, URL)
97 public AlignFile(String inFile, String type) throws IOException
99 this(true, inFile, type);
103 * Constructor which (optionally delays) parsing of data from a file of some
106 * @param parseImmediately
107 * if false, need to call 'doParse()' to begin parsing data
109 * Filename to read from.
111 * What type of file to read from (File, URL)
112 * @throws IOException
114 public AlignFile(boolean parseImmediately, String inFile, String type)
119 if (parseImmediately)
126 * Attempt to read from the position where some other parsing process left
130 * @throws IOException
132 public AlignFile(FileParse source) throws IOException
138 * Construct a new parser to read from the position where some other parsing
141 * @param parseImmediately
142 * if false, need to call 'doParse()' to begin parsing data
145 public AlignFile(boolean parseImmediately, FileParse source)
150 if (parseImmediately)
157 * called if parsing was delayed till after parser was constructed
159 * @throws IOException
161 public void doParse() throws IOException
165 throw new IOException(
166 "Implementation error: Parser called twice for same data.\n"
167 + "Need to call initData() again before parsing can be reattempted.");
171 // sets the index of each sequence in the alignment
172 for (int i = 0, c = seqs.size(); i < c; i++)
174 seqs.get(i).setIndex(i);
179 * Return the seqs Vector
181 public Vector<SequenceI> getSeqs()
186 public List<SequenceGroup> getSeqGroups()
192 * Return the Sequences in the seqs Vector as an array of Sequences
194 public SequenceI[] getSeqsAsArray()
196 SequenceI[] s = new SequenceI[seqs.size()];
198 for (int i = 0; i < seqs.size(); i++)
200 s[i] = seqs.elementAt(i);
207 * called by AppletFormatAdapter to generate an annotated alignment, rather
208 * than bare sequences.
212 public void addAnnotations(AlignmentI al)
215 for (int i = 0; i < annotations.size(); i++)
217 // detect if annotations.elementAt(i) rna secondary structure
220 * SequenceFeature[] pairArray =
221 * Rna.GetBasePairsFromAlignmentAnnotation(annotations.elementAt(i));
222 * Rna.HelixMap(pairArray);
224 AlignmentAnnotation an = annotations.elementAt(i);
225 an.validateRangeAndDisplay();
226 al.addAnnotation(an);
232 * register sequence groups on the alignment for **output**
236 public void addSeqGroups(AlignmentI al)
238 this.seqGroups = al.getGroups();
243 * Add any additional information extracted from the file to the alignment
246 * @note implicitly called by addAnnotations()
249 public void addProperties(AlignmentI al)
251 if (properties != null && properties.size() > 0)
253 Enumeration keys = properties.keys();
254 Enumeration vals = properties.elements();
255 while (keys.hasMoreElements())
257 al.setProperty(keys.nextElement(), vals.nextElement());
263 * Store a non-null key-value pair in a hashtable used to set alignment
264 * properties note: null keys will raise an error, null values will result in
265 * the key/value pair being silently ignored.
268 * - non-null key object
272 protected void setAlignmentProperty(Object key, Object value)
278 .getString("error.implementation_error_cannot_have_null_alignment"));
282 return; // null properties are ignored.
284 if (properties == null)
286 properties = new Hashtable();
288 properties.put(key, value);
291 protected Object getAlignmentProperty(Object key)
293 if (properties != null && key != null)
295 return properties.get(key);
301 * Initialise objects to store sequence data in.
303 protected void initData()
305 seqs = new Vector<SequenceI>();
306 annotations = new Vector<AlignmentAnnotation>();
307 seqGroups = new ArrayList<SequenceGroup>();
317 protected void setSeqs(SequenceI[] s)
319 seqs = new Vector<SequenceI>();
321 for (int i = 0; i < s.length; i++)
323 seqs.addElement(s[i]);
328 * This method must be implemented to parse the contents of the file.
330 public abstract void parse() throws IOException;
333 * Print out in alignment file format the Sequences in the seqs Vector.
335 public abstract String print();
337 public void addJVSuffix(boolean b)
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 suffix
377 * @String id Id to be parsed
379 String printId(SequenceI seq)
381 return seq.getDisplayId(jvSuffix);
385 * vector of String[] treeName, newickString pairs
387 Vector<String[]> newickStrings = null;
389 protected void addNewickTree(String treeName, String newickString)
391 if (newickStrings == null)
393 newickStrings = new Vector<String[]>();
395 newickStrings.addElement(new String[] { treeName, newickString });
398 protected int getTreeCount()
400 return newickStrings == null ? 0 : newickStrings.size();
403 public void addGroups(AlignmentI al)
406 for (SequenceGroup sg : getSeqGroups())