X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FStockholmFile.java;h=0e73af13cc025548f130c4db7f2cabbae6e8dab0;hb=0b266ea40bfb194f843840cd474b8b3a27e0df84;hp=7f3f93bbfcdcfbcbb0a08c3e7532e10dfb9ec111;hpb=7e7c422421698d7a47a9bad846c5522556f066d6;p=jalview.git diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index 7f3f93b..0e73af1 100644 --- a/src/jalview/io/StockholmFile.java +++ b/src/jalview/io/StockholmFile.java @@ -74,6 +74,8 @@ import fr.orsay.lri.varna.models.rna.RNA; */ public class StockholmFile extends AlignFile { + private static final String ANNOTATION = "annotation"; + private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "("); private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")"); @@ -81,6 +83,14 @@ public class StockholmFile extends AlignFile public static final Regex DETECT_BRACKETS = new Regex( "(<|>|\\[|\\]|\\(|\\)|\\{|\\})"); + // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using NOT_RNASS first. + public static final String RNASS_BRACKETS = "<>[](){}AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz"; + + // use the following regex to decide an annotations (whole) line is NOT an RNA + // SS (it contains only E,H,e,h and other non-brace/non-alpha chars) + private static final Regex NOT_RNASS = new Regex( + "^[^<>[\\](){}A-DF-Za-df-z]*$"); + StringBuffer out; // output buffer AlignmentI al; @@ -163,8 +173,8 @@ public class StockholmFile extends AlignFile for (int k = 0; k < rna.length(); k++) { - ann[k] = new Annotation(annot[k], "", Rna.getRNASecStrucState( - annot[k]).charAt(0), 0f); + ann[k] = new Annotation(annot[k], "", + Rna.getRNASecStrucState(annot[k]).charAt(0), 0f); } AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.", @@ -195,7 +205,7 @@ public class StockholmFile extends AlignFile String version; // String id; Hashtable seqAnn = new Hashtable(); // Sequence related annotations - LinkedHashMap seqs = new LinkedHashMap(); + LinkedHashMap seqs = new LinkedHashMap<>(); Regex p, r, rend, s, x; // Temporary line for processing RNA annotation // String RNAannot = ""; @@ -207,9 +217,8 @@ public class StockholmFile extends AlignFile r = new Regex("# STOCKHOLM ([\\d\\.]+)"); if (!r.search(nextLine())) { - throw new IOException( - MessageManager - .getString("exception.stockholm_invalid_format")); + throw new IOException(MessageManager + .getString("exception.stockholm_invalid_format")); } else { @@ -392,7 +401,7 @@ public class StockholmFile extends AlignFile while (j.hasMoreElements()) { String desc = j.nextElement().toString(); - if ("annotations".equals(desc) && annotsAdded) + if (ANNOTATION.equals(desc) && annotsAdded) { // don't add features if we already added an annotation row continue; @@ -412,7 +421,7 @@ public class StockholmFile extends AlignFile int new_pos = posmap[k]; // look up nearest seqeunce // position to this column SequenceFeature feat = new SequenceFeature(type, desc, - new_pos, new_pos, 0f, null); + new_pos, new_pos, null); seqO.addSequenceFeature(feat); } @@ -439,8 +448,8 @@ public class StockholmFile extends AlignFile { // logger.error("Could not parse sequence line: " + line); throw new IOException(MessageManager.formatMessage( - "exception.couldnt_parse_sequence_line", - new String[] { line })); + "exception.couldnt_parse_sequence_line", new String[] + { line })); } String ns = seqs.get(x.stringMatched(1)); if (ns == null) @@ -635,7 +644,7 @@ public class StockholmFile extends AlignFile content = new Hashtable(); features.put(this.id2type(type), content); } - String ns = (String) content.get("annotation"); + String ns = (String) content.get(ANNOTATION); if (ns == null) { @@ -643,7 +652,7 @@ public class StockholmFile extends AlignFile } // finally, append the annotation line ns += seq; - content.put("annotation", ns); + content.put(ANNOTATION, ns); // // end of wrapped annotation block. // // Now a new row is created with the current set of data @@ -657,7 +666,7 @@ public class StockholmFile extends AlignFile strucAnn = new Hashtable(); } - Vector newStruc = new Vector(); + Vector newStruc = new Vector<>(); parseAnnotationRow(newStruc, type, ns); for (AlignmentAnnotation alan : newStruc) { @@ -671,8 +680,8 @@ public class StockholmFile extends AlignFile // } else { - System.err - .println("Warning - couldn't parse sequence annotation row line:\n" + System.err.println( + "Warning - couldn't parse sequence annotation row line:\n" + line); // throw new IOException("Error parsing " + line); } @@ -680,8 +689,8 @@ public class StockholmFile extends AlignFile else { throw new IOException(MessageManager.formatMessage( - "exception.unknown_annotation_detected", new String[] { - annType, annContent })); + "exception.unknown_annotation_detected", new String[] + { annType, annContent })); } } } @@ -709,7 +718,7 @@ public class StockholmFile extends AlignFile private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource) { DBRefEntry dbrf = null; - List dbrs = new ArrayList(); + List dbrs = new ArrayList<>(); String seqdb = "Unknown", sdbac = "" + dbr; int st = -1, en = -1, p; if ((st = sdbac.indexOf("/")) > -1) @@ -794,8 +803,10 @@ public class StockholmFile extends AlignFile { for (DBRefEntry d : dbrs) { - jalview.util.MapList mp = new jalview.util.MapList(new int[] { - seqO.getStart(), seqO.getEnd() }, new int[] { st, en }, 1, 1); + jalview.util.MapList mp = new jalview.util.MapList( + new int[] + { seqO.getStart(), seqO.getEnd() }, new int[] { st, en }, 1, + 1); jalview.datamodel.Mapping mping = new Mapping(mp); d.setMap(mping); } @@ -815,14 +826,20 @@ public class StockholmFile extends AlignFile String type = label; if (label.contains("_cons")) { - type = (label.indexOf("_cons") == label.length() - 5) ? label - .substring(0, label.length() - 5) : label; + type = (label.indexOf("_cons") == label.length() - 5) + ? label.substring(0, label.length() - 5) + : label; } boolean ss = false, posterior = false; type = id2type(type); - if (type.equals("secondary structure")) + + boolean isrnass = false; + if (type.equalsIgnoreCase("secondary structure")) { ss = true; + isrnass = !NOT_RNASS.search(annots); // sorry about the double negative + // here (it's easier for dealing with + // other non-alpha-non-brace chars) } if (type.equalsIgnoreCase("posterior probability")) { @@ -840,7 +857,7 @@ public class StockholmFile extends AlignFile { // if (" .-_".indexOf(pos) == -1) { - if (DETECT_BRACKETS.search(pos)) + if (isrnass && RNASS_BRACKETS.indexOf(pos) >= 0) { ann.secondaryStructure = Rna.getRNASecStrucState(pos).charAt(0); ann.displayCharacter = "" + pos.charAt(0); @@ -850,14 +867,14 @@ public class StockholmFile extends AlignFile ann.secondaryStructure = ResidueProperties.getDssp3state(pos) .charAt(0); - if (ann.secondaryStructure == pos.charAt(0)) - { - ann.displayCharacter = ""; // null; // " "; - } - else - { - ann.displayCharacter = " " + ann.displayCharacter; - } + if (ann.secondaryStructure == pos.charAt(0)) + { + ann.displayCharacter = ""; // null; // " "; + } + else + { + ann.displayCharacter = " " + ann.displayCharacter; + } } } @@ -928,10 +945,7 @@ public class StockholmFile extends AlignFile while ((in < s.length) && (s[in] != null)) { String tmp = printId(s[in], jvSuffix); - if (s[in].getSequence().length > max) - { - max = s[in].getSequence().length; - } + max = Math.max(max, s[in].getLength()); if (tmp.length() > maxid) { @@ -980,8 +994,8 @@ public class StockholmFile extends AlignFile { Object idd = en.nextElement(); String type = (String) dataRef.remove(idd); - out.append(new Format("%-" + (maxid - 2) + "s").form("#=GS " - + idd.toString() + " ")); + out.append(new Format("%-" + (maxid - 2) + "s") + .form("#=GS " + idd.toString() + " ")); if (type.contains("PFAM") || type.contains("RFAM")) { @@ -1021,8 +1035,8 @@ public class StockholmFile extends AlignFile } // out.append("#=GR "); - out.append(new Format("%-" + maxid + "s").form("#=GR " - + printId(s[i], jvSuffix) + " " + key + " ")); + out.append(new Format("%-" + maxid + "s").form( + "#=GR " + printId(s[i], jvSuffix) + " " + key + " ")); ann = alAnot[j].annotations; String seq = ""; for (int k = 0; k < ann.length; k++) @@ -1077,8 +1091,8 @@ public class StockholmFile extends AlignFile } label = label.replace(" ", "_"); - out.append(new Format("%-" + maxid + "s").form("#=GC " + label - + " ")); + out.append( + new Format("%-" + maxid + "s").form("#=GC " + label + " ")); boolean isrna = aa.isValidStruc(); for (int j = 0; j < aa.annotations.length; j++) { @@ -1110,23 +1124,39 @@ public class StockholmFile extends AlignFile { char seq = ' '; Annotation annot = ann[k]; - String ch = (annot == null) ? ((sequenceI == null) ? "-" : Character - .toString(sequenceI.getCharAt(k))) : annot.displayCharacter; + String ch = (annot == null) + ? ((sequenceI == null) ? "-" + : Character.toString(sequenceI.getCharAt(k))) + : (annot.displayCharacter == null + ? String.valueOf(annot.secondaryStructure) + : annot.displayCharacter); + if (ch == null) + { + ch = " "; + } if (key != null && key.equals("SS")) { + char ssannotchar = ' '; + boolean charset = false; if (annot == null) { // sensible gap character - return ' '; + ssannotchar = ' '; + charset = true; } else { // valid secondary structure AND no alternative label (e.g. ' B') if (annot.secondaryStructure > ' ' && ch.length() < 2) { - return annot.secondaryStructure; + ssannotchar = annot.secondaryStructure; + charset = true; } } + if (charset) + { + return (ssannotchar == ' ' && isrna) ? '.' : ssannotchar; + } } if (ch.length() == 0) @@ -1141,7 +1171,9 @@ public class StockholmFile extends AlignFile { seq = ch.charAt(1); } - return seq; + + return (seq == ' ' && key != null && key.equals("SS") && isrna) ? '.' + : seq; } public String print() @@ -1163,10 +1195,10 @@ public class StockholmFile extends AlignFile if (typeIds == null) { typeIds = new Hashtable(); - typeIds.put("SS", "secondary structure"); - typeIds.put("SA", "surface accessibility"); + typeIds.put("SS", "Secondary Structure"); + typeIds.put("SA", "Surface Accessibility"); typeIds.put("TM", "transmembrane"); - typeIds.put("PP", "posterior probability"); + typeIds.put("PP", "Posterior Probability"); typeIds.put("LI", "ligand binding"); typeIds.put("AS", "active site"); typeIds.put("IN", "intron"); @@ -1177,7 +1209,7 @@ public class StockholmFile extends AlignFile typeIds.put("DE", "description"); typeIds.put("DR", "reference"); typeIds.put("LO", "look"); - typeIds.put("RF", "reference positions"); + typeIds.put("RF", "Reference Positions"); } } @@ -1188,8 +1220,8 @@ public class StockholmFile extends AlignFile { return (String) typeIds.get(id); } - System.err.println("Warning : Unknown Stockholm annotation type code " - + id); + System.err.println( + "Warning : Unknown Stockholm annotation type code " + id); return id; } @@ -1200,7 +1232,7 @@ public class StockholmFile extends AlignFile while (e.hasMoreElements()) { Object ll = e.nextElement(); - if (typeIds.get(ll).toString().equals(type)) + if (typeIds.get(ll).toString().equalsIgnoreCase(type)) { key = (String) ll; break; @@ -1210,8 +1242,8 @@ public class StockholmFile extends AlignFile { return key; } - System.err.println("Warning : Unknown Stockholm annotation type: " - + type); + System.err.println( + "Warning : Unknown Stockholm annotation type: " + type); return key; }