X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FPIRFile.java;h=b958456265cb655472c75d783329a3ab2a07887f;hb=38299bef6dfd4b713f615781e631dcb66e1155f2;hp=d4b818b4d64c554c8433b687e811fc1168985c00;hpb=55e2e9b22b133db8b9ff0979b0338a33081fc8fd;p=jalview.git diff --git a/src/jalview/io/PIRFile.java b/src/jalview/io/PIRFile.java index d4b818b..b958456 100755 --- a/src/jalview/io/PIRFile.java +++ b/src/jalview/io/PIRFile.java @@ -21,12 +21,13 @@ package jalview.io; import java.io.*; import java.util.*; -import jalview.analysis.*; import jalview.datamodel.*; public class PIRFile extends AlignFile { + public static boolean useModellerOutput = false; + Vector words = new Vector(); //Stores the words in a line after splitting public PIRFile() @@ -44,21 +45,23 @@ public class PIRFile super(inFile, type); } - public void parse() + public void parse() throws IOException { - try - { StringBuffer sequence; String line = null; + ModellerDescription md; while ( (line = nextLine()) != null) { - if(line.length()==0) + if (line.length() == 0) { //System.out.println("blank line"); continue; } - + if (line.indexOf("C;") == 0 || line.indexOf("#") == 0) + { + continue; + } Sequence newSeq = parseId(line.substring(line.indexOf(";") + 1)); sequence = new StringBuffer(); @@ -81,19 +84,24 @@ public class PIRFile } } - if(sequence.length()>0) + if (sequence.length() > 0) { sequence.setLength(sequence.length() - 1); - newSeq.setSequence(sequence.toString()); + if (!isValidProteinSequence(newSeq.getSequence())) + { + throw new IOException(AppletFormatAdapter.INVALID_CHARACTERS + +" : "+ newSeq.getName() + +" : "+invalidCharacter); + } + seqs.addElement(newSeq); + + md = new ModellerDescription(newSeq. + getDescription()); + md.updateSequenceI(newSeq); } } - } - catch (Exception ex) - { - ex.printStackTrace(); - } } public String print() @@ -107,20 +115,58 @@ public class PIRFile int len = 72; StringBuffer out = new StringBuffer(); int i = 0; + ModellerDescription md; while ( (i < s.length) && (s[i] != null)) { String seq = s[i].getSequence(); seq = seq + "*"; - out.append(">P1;" + printId(s[i]) + "\n"); - if(s[i].getDescription()!=null) - out.append(s[i].getDescription()+"\n"); + if (is_NA) + { + // modeller doesn't really do nucleotides, so we don't do anything fancy + // Official tags area as follows, for now we'll use P1 and DL + // Protein (complete) P1 + // Protein (fragment) F1 + // DNA (linear) Dl + // DNA (circular) DC + // RNA (linear) RL + // RNA (circular) RC + // tRNA N3 + // other functional RNA N1 + + out.append(">N1;" + s[i].getName() + "\n"); + if (s[i].getDescription() == null) + { + out.append(s[i].getName() + " " + + (s[i].getEnd() - s[i].getStart() + 1)); + out.append(is_NA ? " bases\n" : " residues\n"); + } + else + { + out.append(s[i].getDescription()+"\n"); + } + } else { - out.append(s[i].getName()+" "+ (s[i].getEnd() - s[i].getStart() + 1)); - out.append( is_NA ? " bases\n" : " residues\n"); + + if(useModellerOutput) + { + out.append(">P1;" + s[i].getName() + "\n"); + md = new ModellerDescription(s[i]); + out.append(md.getDescriptionLine() + "\n"); + } + else + { + out.append(">P1;" + printId(s[i]) + "\n"); + if (s[i].getDescription() != null) + out.append(s[i].getDescription() + "\n"); + else + out.append(s[i].getName() + " " + + (s[i].getEnd() - s[i].getStart() + 1) + + " residues\n"); + } } int nochunks = (seq.length() / len) + 1;