X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FPIRFile.java;h=910d18929e48d60b65664bc33312104b556b1335;hb=ce886100c1eae01eac7d59c961e694f4493d4bcb;hp=65890a9543561baefead60ff4135acbe18e55794;hpb=f24dacb1da56fccf05d684e2f4899facec2aecf7;p=jalview.git diff --git a/src/jalview/io/PIRFile.java b/src/jalview/io/PIRFile.java index 65890a9..910d189 100755 --- a/src/jalview/io/PIRFile.java +++ b/src/jalview/io/PIRFile.java @@ -1,6 +1,6 @@ /* * Jalview - A Sequence Alignment Editor and Viewer - * Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle + * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -21,23 +21,19 @@ 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() { } - public PIRFile(String inStr) - { - super(inStr); - } - public PIRFile(String inFile, String type) throws IOException { @@ -45,79 +41,58 @@ public class PIRFile } public void parse() + throws IOException { - try - { - String id; - String start; - String end; - StringBuffer sequence; - String line = null; + StringBuffer sequence; + String line = null; + ModellerDescription md; - while ( (line = nextLine()) != null) + while ( (line = nextLine()) != null) + { + if (line.length() == 0) { - if(line.length()==0) - { - //System.out.println("blank line"); - continue; - } - - id = "No id"; - start = "1"; - end = "-1"; + //System.out.println("blank line"); + continue; + } + if (line.indexOf("C;") == 0 || line.indexOf("#") == 0) + { + continue; + } + Sequence newSeq = parseId(line.substring(line.indexOf(";") + 1)); - try - { - int slashIndex = line.indexOf("/"); - if(slashIndex!=-1) - { - id = line.substring(line.indexOf(";") + 1, line.indexOf("/")); - line = line.substring(line.indexOf("/") + 1); - start = line.substring(0, line.indexOf("-")); - end = line.substring(line.indexOf("-") + 1); - } - else - { - id = line.substring(line.indexOf(";")+1); - } - } - catch (Exception ex) - { }// Default id, start and end unchanged + sequence = new StringBuffer(); - sequence = new StringBuffer(); + newSeq.setDescription(nextLine()); // this is the title line - line = nextLine(); // this is the title line + boolean starFound = false; - boolean starFound = false; + while (!starFound) + { + line = nextLine(); + sequence.append(line); - while(!starFound) + if (line == null) { - line = nextLine(); - sequence.append(line); - - if (line == null) - break; - - if (line.indexOf("*") > -1) - { - starFound = true; - } + break; } - if(sequence.length()>0) + if (line.indexOf("*") > -1) { - sequence.setLength(sequence.length() - 1); - - Sequence newSeq = new Sequence(id, sequence.toString(), - Integer.parseInt(start), - Integer.parseInt(end)); - seqs.addElement(newSeq); + starFound = true; } } - } - catch (Exception ex) - { - ex.printStackTrace(); + + if (sequence.length() > 0) + { + sequence.setLength(sequence.length() - 1); + newSeq.setSequence(sequence.toString()); + + seqs.addElement(newSeq); + + md = new ModellerDescription(newSeq. + getDescription()); + md.updateSequenceI(newSeq); + } } } @@ -126,41 +101,68 @@ public class PIRFile return print(getSeqsAsArray()); } - public static String print(SequenceI[] s) - { - return print(s, 72, true); - } - - public static String print(SequenceI[] s, int len) - { - return print(s, len, true); - } - - public static String print(SequenceI[] s, int len, boolean gaps) + public String print(SequenceI[] s) { + boolean is_NA = jalview.util.Comparison.isNucleotide(s); + int len = 72; StringBuffer out = new StringBuffer(); int i = 0; + ModellerDescription md; while ( (i < s.length) && (s[i] != null)) { - String seq = ""; + String seq = s[i].getSequenceAsString(); + seq = seq + "*"; - if (gaps) + if (is_NA) { - seq = s[i].getSequence() + "*"; + // 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 { - seq = AlignSeq.extractGaps(s[i].getSequence(), "-"); - seq = AlignSeq.extractGaps(seq, "."); - seq = AlignSeq.extractGaps(seq, " "); - seq = seq + "*"; - } - - out.append(">P1;" + s[i].getName() + "/" + s[i].getStart() + "-" + - s[i].getEnd() + "\n"); - out.append(" Dummy title\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; for (int j = 0; j < nochunks; j++)