X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=src%2Fjalview%2Fio%2FFastaFile.java;h=8de469d1a38e20aa63e05d200e6ad332eb0ed5f1;hb=4e93b3351cecb6f07f401832fc1658d180c8008d;hp=4c1ba9ee3ec25e575de461095c6066f969bce4e9;hpb=6cbe1876d4a5fdd7d5b73e11bf2468fe4e75ce99;p=jalview.git diff --git a/src/jalview/io/FastaFile.java b/src/jalview/io/FastaFile.java index 4c1ba9e..8de469d 100755 --- a/src/jalview/io/FastaFile.java +++ b/src/jalview/io/FastaFile.java @@ -1,148 +1,235 @@ +/* + * Jalview - A Sequence Alignment Editor and Viewer + * 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 + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program 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 this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA + */ package jalview.io; -import jalview.datamodel.*; -import jalview.analysis.*; - import java.io.*; -import java.util.*; -public class FastaFile extends AlignFile { +import jalview.datamodel.*; +/** + * DOCUMENT ME! + * + * @author $author$ + * @version $Revision$ + */ +public class FastaFile + extends AlignFile +{ + /** + * Length of a sequence line + */ + int len = 72; + + StringBuffer out; + + /** + * Creates a new FastaFile object. + */ public FastaFile() - {} - - public FastaFile(String inStr) { - super(inStr); + { } - public FastaFile(String inFile, String type) throws IOException { - super(inFile,type); + /** + * Creates a new FastaFile object. + * + * @param inFile DOCUMENT ME! + * @param type DOCUMENT ME! + * + * @throws IOException DOCUMENT ME! + */ + public FastaFile(String inFile, String type) + throws IOException + { + super(inFile, type); } - public void parse() throws IOException + /** + * DOCUMENT ME! + * + * @throws IOException DOCUMENT ME! + */ + public void parse() + throws IOException { - - String id = ""; - StringBuffer seq = new StringBuffer(); - int count = 0; - boolean flag = false; - - int sstart = 0; - int send = 0; + StringBuffer sb = new StringBuffer(); + boolean firstLine = true; String line; - - while ((line = nextLine()) != null) { - - if (line.length() > 0) { - - // Do we have an id line? - - if (line.substring(0,1).equals(">")) { - - if (count != 0) { - if (sstart != 0) { - seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),sstart,send)); - } else { - seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),1,seq.length())); - } - } - - count++; - - StringTokenizer str = new StringTokenizer(line," "); - - id = str.nextToken(); - id = id.substring(1); - if(id.indexOf("UniProt/Swiss-Prot")>-1) + Sequence seq = null; + + boolean annotation = false; + + while ( (line = nextLine()) != null) + { + line = line.trim(); + if (line.length() > 0) + { + if (line.charAt(0) == '>') + { + if (line.startsWith(">#_")) + { + if (annotation) { - id = id.substring(id.indexOf("UniProt/Swiss-Prot|") + 19); - if(id.indexOf("|")>-1) - id = id.substring(id.indexOf("|") + 1); + Annotation[] anots = new Annotation[sb.length()]; + String anotString = sb.toString(); + for (int i = 0; i < sb.length(); i++) + { + anots[i] = new Annotation(anotString.substring(i, i + 1), + null, + ' ', 0); + } + AlignmentAnnotation aa = new AlignmentAnnotation( + seq.getName().substring(2), seq.getDescription(), + anots); + + annotations.addElement(aa); } + } + else + { + annotation = false; + } - if (id.indexOf("/") > 0 ) { - - StringTokenizer st = new StringTokenizer(id,"/"); - if (st.countTokens() == 2) { - id = st.nextToken(); - String tmp = st.nextToken(); + if (!firstLine) + { + seq.setSequence(sb.toString()); - st = new StringTokenizer(tmp,"-"); + if (!annotation) + { + seqs.addElement(seq); + } + } - if (st.countTokens() == 2) { - sstart = Integer.valueOf(st.nextToken()).intValue(); - send = Integer.valueOf(st.nextToken()).intValue(); - } - } - } + seq = parseId(line.substring(1)); + firstLine = false; - seq = new StringBuffer(); + sb = new StringBuffer(); - } else { - seq = seq.append(line); - } - } + if (line.startsWith(">#_")) + { + annotation = true; + } + } + else + { + sb.append(line); + } } - if (count > 0) { - - if(!isValidProteinSequence(seq.toString().toUpperCase())) - throw new IOException("Invalid protein sequence"); + } - if (sstart != 0) { - seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),sstart,send)); - } else { - seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),1,seq.length())); - } + if (annotation) + { + Annotation[] anots = new Annotation[sb.length()]; + String anotString = sb.toString(); + for (int i = 0; i < sb.length(); i++) + { + anots[i] = new Annotation(anotString.substring(i, i + 1), + null, + ' ', 0); } + AlignmentAnnotation aa = new AlignmentAnnotation( + seq.getName().substring(2), seq.getDescription(), + anots); - } + annotations.addElement(aa); + } - public static String print(SequenceI[] s) { - return print(s,72); - } - public static String print(SequenceI[] s, int len) { - return print(s,len,true); + else if (!firstLine) + { + seq.setSequence(sb.toString()); + seqs.addElement(seq); + } } - public static String print(SequenceI[] s, int len,boolean gaps) { - return print(s,len,gaps,true); + /** + * called by AppletFormatAdapter to generate + * an annotated alignment, rather than bare + * sequences. + * @param al + */ + public void addAnnotations(Alignment al) + { + addProperties(al); + for (int i = 0; i < annotations.size(); i++) + { + AlignmentAnnotation aa = (AlignmentAnnotation) annotations.elementAt(i); + aa.setPadGaps(true, al.getGapCharacter()); + al.addAnnotation( aa ); + } } - public static String print(SequenceI[] s, int len,boolean gaps, boolean displayId) { - StringBuffer out = new StringBuffer(); + + /** + * DOCUMENT ME! + * + * @param s DOCUMENT ME! + * @param len DOCUMENT ME! + * @param gaps DOCUMENT ME! + * @param displayId DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String print(SequenceI[] s) + { + out = new StringBuffer(); int i = 0; - while (i < s.length && s[i] != null) { - String seq = ""; - if (gaps) { - seq = s[i].getSequence(); - } else { - seq = AlignSeq.extractGaps("-. ",s[i].getSequence()); + + while ( (i < s.length) && (s[i] != null)) + { + out.append(">" + printId(s[i])); + if (s[i].getDescription() != null) + { + out.append(" " + s[i].getDescription()); } - // used to always put this here: + "/" + s[i].getStart() + "-" + s[i].getEnd() + - out.append(">" + ((displayId) ? s[i].getDisplayId() : s[i].getName())+"\n"); - int nochunks = seq.length() / len + 1; + out.append("\n"); + + int nochunks = (s[i].getLength() / len) + 1; - for (int j = 0; j < nochunks; j++) { - int start = j*len; + for (int j = 0; j < nochunks; j++) + { + int start = j * len; int end = start + len; - if (end < seq.length()) { - out.append(seq.substring(start,end) + "\n"); - } else if (start < seq.length()) { - out.append(seq.substring(start) + "\n"); + if (end < s[i].getLength()) + { + out.append(s[i].getSequenceAsString(start, end) + "\n"); + } + else if (start < s[i].getLength()) + { + out.append(s[i].getSequenceAsString(start, s[i].getLength()) + "\n"); } } + i++; } + return out.toString(); } - public String print() { + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String print() + { return print(getSeqsAsArray()); } } - - -