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.
21 package jalview.analysis;
23 //import com.stevesoft.pat.Regex;
25 import jalview.datamodel.AlignmentAnnotation;
26 import jalview.datamodel.AlignmentI;
27 import jalview.datamodel.SequenceI;
28 import jalview.jsdev.RegExp;
29 import jalview.jsdev.api.RegExpInterface;
31 public class ParseProperties
34 * Methods for parsing free text properties on alignments and sequences. There
35 * are a number of ways we might want to do this: arbitrary regex. and an
36 * associated score name for the number that's extracted. Regex that provides
37 * both score and name.
39 * We may also want to : - modify description to remove parsed numbers (this
40 * behaviour is dangerous since exporting the alignment would lose the
41 * original form then) -
45 * The alignment being operated on
47 private AlignmentI al = null;
50 * initialise a new property parser
54 public ParseProperties(AlignmentI al)
59 public int getScoresFromDescription(String ScoreName,
60 String ScoreDescriptions, String regex, boolean repeat)
62 return getScoresFromDescription(new String[]
63 { ScoreName }, new String[]
64 { ScoreDescriptions }, regex, repeat);
67 public int getScoresFromDescription(String[] ScoreNames,
68 String[] ScoreDescriptions, String regex, boolean repeat)
70 return getScoresFromDescription(al.getSequencesArray(), ScoreNames,
71 ScoreDescriptions, regex, repeat);
75 * Extract scores for sequences by applying regex to description string.
78 * seuqences to extract annotation from.
80 * labels for each numeric field in regex match
81 * @param ScoreDescriptions
82 * description for each numeric field in regex match
84 * Regular Expression string for passing to
85 * <code>new jalview.jsdevt.Regex(regex)</code>
87 * true means the regex will be applied multiple times along the
88 * description string of each sequence
89 * @return total number of sequences that matched the regex
91 public int getScoresFromDescription(SequenceI[] seqs,
92 String[] ScoreNames, String[] ScoreDescriptions, String regex,
96 RegExpInterface pattern = RegExp.newRegex(regex);
97 if (pattern.numSubs() > ScoreNames.length)
99 // Check that we have enough labels and descriptions for any parsed
101 int onamelen = ScoreNames.length;
102 String[] tnames = new String[pattern.numSubs() + 1];
103 System.arraycopy(ScoreNames, 0, tnames, 0, ScoreNames.length);
104 String base = tnames[ScoreNames.length - 1];
106 String descrbase = ScoreDescriptions[onamelen - 1];
107 if (descrbase == null)
109 descrbase = "Score parsed from (" + regex + ")";
111 tnames = new String[pattern.numSubs() + 1];
112 System.arraycopy(ScoreDescriptions, 0, tnames, 0,
113 ScoreDescriptions.length);
114 ScoreDescriptions = tnames;
115 for (int i = onamelen; i < ScoreNames.length; i++)
117 ScoreNames[i] = base + "_" + i;
118 ScoreDescriptions[i] = descrbase + " (column " + i + ")";
121 for (int i = 0; i < seqs.length; i++)
123 String descr = seqs[i].getDescription();
129 boolean added = false;
131 while ((repeat || pos == 0) && pattern.searchFrom(descr, pos))
133 pos = pattern.matchedTo();
134 for (int cols = 0; cols < pattern.numSubs(); cols++)
136 String sstring = pattern.stringMatchedI(cols + 1);
137 double score = Double.NaN;
140 score = new Double(sstring).doubleValue();
141 } catch (Exception e)
143 // don't try very hard to parse if regex was wrong.
146 // add score to sequence annotation.
147 AlignmentAnnotation an = new AlignmentAnnotation(ScoreNames[cols]
148 + ((reps > 0) ? "_" + reps : ""),
149 ScoreDescriptions[cols], null);
151 System.out.println(seqs[i].getName() + " score: '"
152 + ScoreNames[cols] + "' = " + score); // DEBUG
153 an.setSequenceRef(seqs[i]);
154 seqs[i].addAlignmentAnnotation(an);
155 al.addAnnotation(an);
158 reps++; // repeated matches