X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FPfamFile.java;h=85588a6d0e52794a3c548343d018d182c2e244ad;hb=ab43013b7e357b84b4abade0dba949668dfb2a0e;hp=e17f831dbc6e1990899a9709853bb810ad7ad6fe;hpb=1ecf6419aba86993b3c223bf5ec0fa79427baf85;p=jalview.git diff --git a/src/jalview/io/PfamFile.java b/src/jalview/io/PfamFile.java index e17f831..85588a6 100755 --- a/src/jalview/io/PfamFile.java +++ b/src/jalview/io/PfamFile.java @@ -1,173 +1,180 @@ -package jalview.io; - -import jalview.datamodel.*; -import jalview.util.*; - -import java.io.*; -import java.util.*; - -public class PfamFile extends AlignFile { - - Vector ids; - - public PfamFile() - {} - - public PfamFile(String inStr) { - super(inStr); - } - - public void initData() { - super.initData(); - ids = new Vector(); - } - - public PfamFile(String inFile, String type) throws IOException { - super(inFile,type); - } - - public void parse() throws IOException{ - int i = 0; - String line; - - - Hashtable seqhash = new Hashtable(); - Vector headers = new Vector(); - - - while ((line = nextLine()) != null) - { - - if (line.indexOf(" ") != 0) - { - if (line.indexOf("#") != 0) - { - - StringTokenizer str = new StringTokenizer(line," "); - String id = ""; - - if (str.hasMoreTokens()) - { - id = str.nextToken(); - - StringBuffer tempseq; - - if (seqhash.containsKey(id)) - tempseq = (StringBuffer)seqhash.get(id); - else - { - tempseq = new StringBuffer(); - seqhash.put(id,tempseq); - } - - if (!(headers.contains(id))) - headers.addElement(id); - - - tempseq.append(str.nextToken()); - } - } - } - } - - this.noSeqs = headers.size(); - if(noSeqs<1) - throw new IOException("No sequences found (PFAM input)"); - - for (i = 0; i < headers.size(); i++ ) { - - if ( seqhash.get(headers.elementAt(i)) != null) { - if (maxLength < seqhash.get(headers.elementAt(i)).toString().length() ) - maxLength = seqhash.get(headers.elementAt(i)).toString().length(); - - String head = headers.elementAt(i).toString(); - int start = 1; - int end = seqhash.get(headers.elementAt(i)).toString().length(); - - if (head.indexOf("/") > 0 ) { - StringTokenizer st = new StringTokenizer(head,"/"); - if (st.countTokens() == 2) { - ids.addElement(st.nextToken()); - String tmp = st.nextToken(); - st = new StringTokenizer(tmp,"-"); - if (st.countTokens() == 2) { - start = Integer.valueOf(st.nextToken()).intValue(); - end = Integer.valueOf(st.nextToken()).intValue(); - } else - { - start = -1; - end = -1; - } - } else - ids.addElement(headers.elementAt(i)); - - } - else - ids.addElement(headers.elementAt(i)); - - - Sequence newSeq = null; - if (start != -1 && end != -1) - { - newSeq = new Sequence(ids.elementAt(i).toString(), - seqhash.get(headers.elementAt(i).toString()).toString(),start,end); - seqs.addElement(newSeq); - } - else - { - newSeq = new Sequence(ids.elementAt(i).toString(), - seqhash.get(headers.elementAt(i).toString()).toString(),1, - seqhash.get(headers.elementAt(i).toString()).toString().length()); - seqs.addElement(newSeq); - } - - if(!isValidProteinSequence(newSeq.getSequence())) - throw new IOException("Not a valid protein sequence - (PFAM input)"); - } - else - System.out.println("Can't find sequence for " + headers.elementAt(i)); - - } - - } - - public static String print(SequenceI[] s) { - StringBuffer out = new StringBuffer(""); - - int max = 0; - int maxid = 0; - - int i = 0; - - while (i < s.length && s[i] != null) { - String tmp = s[i].getName() + "/" + s[i].getStart()+ "-" + s[i].getEnd(); - - if (s[i].getSequence().length() > max) { - max = s[i].getSequence().length(); - } - if (tmp.length() > maxid) { - maxid = tmp.length(); - } - i++; - } - - if (maxid < 15) { - maxid = 15; - } - - int j = 0; - while ( j < s.length && s[j] != null) { - out.append( new Format("%-" + maxid + "s").form(s[j].getName() + "/" + s[j].getStart() + "-" + s[j].getEnd() ) + " "); - - out.append(s[j].getSequence() + "\n"); - j++; - } - out.append("\n"); - - return out.toString(); - } - - public String print() { - return print(getSeqsAsArray()); - } -} +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2b1) + * Copyright (C) 2014 The Jalview Authors + * + * This file is part of Jalview. + * + * Jalview is free software: you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, either version 3 + * of the License, or (at your option) any later version. + * + * Jalview is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR + * PURPOSE. See the GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with Jalview. If not, see . + * The Jalview Authors are detailed in the 'AUTHORS' file. + */ +package jalview.io; + +import java.io.*; +import java.util.*; + +import jalview.datamodel.*; +import jalview.util.*; + +public class PfamFile extends AlignFile +{ + + public PfamFile() + { + } + + public PfamFile(String inFile, String type) throws IOException + { + super(inFile, type); + } + + public PfamFile(FileParse source) throws IOException + { + super(source); + } + + public void initData() + { + super.initData(); + } + + public void parse() throws IOException + { + int i = 0; + String line; + + Hashtable seqhash = new Hashtable(); + Vector headers = new Vector(); + + while ((line = nextLine()) != null) + { + if (line.indexOf(" ") != 0) + { + if (line.indexOf("#") != 0) + { + // TODO: verify pfam format requires spaces and not tab characters - + // if not upgrade to use stevesoft regex and look for whitespace. + StringTokenizer str = new StringTokenizer(line, " "); + String id = ""; + + if (str.hasMoreTokens()) + { + id = str.nextToken(); + + StringBuffer tempseq; + + if (seqhash.containsKey(id)) + { + tempseq = (StringBuffer) seqhash.get(id); + } + else + { + tempseq = new StringBuffer(); + seqhash.put(id, tempseq); + } + + if (!(headers.contains(id))) + { + headers.addElement(id); + } + if (str.hasMoreTokens()) + { + tempseq.append(str.nextToken()); + } + } + } + } + } + + this.noSeqs = headers.size(); + + if (noSeqs < 1) + { + throw new IOException(MessageManager.getString("exception.pfam_no_sequences_found")); + } + + for (i = 0; i < headers.size(); i++) + { + if (seqhash.get(headers.elementAt(i)) != null) + { + if (maxLength < seqhash.get(headers.elementAt(i)).toString() + .length()) + { + maxLength = seqhash.get(headers.elementAt(i)).toString().length(); + } + + Sequence newSeq = parseId(headers.elementAt(i).toString()); + newSeq.setSequence(seqhash.get(headers.elementAt(i).toString()) + .toString()); + seqs.addElement(newSeq); + } + else + { + System.err.println("PFAM File reader: Can't find sequence for " + + headers.elementAt(i)); + } + } + } + + public String print(SequenceI[] s) + { + StringBuffer out = new StringBuffer(""); + + int max = 0; + int maxid = 0; + + int i = 0; + + while ((i < s.length) && (s[i] != null)) + { + String tmp = printId(s[i]); + + if (s[i].getSequence().length > max) + { + max = s[i].getSequence().length; + } + + if (tmp.length() > maxid) + { + maxid = tmp.length(); + } + + i++; + } + + if (maxid < 15) + { + maxid = 15; + } + + int j = 0; + + while ((j < s.length) && (s[j] != null)) + { + out.append(new Format("%-" + maxid + "s").form(printId(s[j]) + " ")); + + out.append(s[j].getSequenceAsString()); + out.append(newline); + j++; + } + + out.append(newline); + + return out.toString(); + } + + public String print() + { + return print(getSeqsAsArray()); + } +}