X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FFastaFile.java;h=2801ac4f37306280c9b52b185e8bf4d7bc585f69;hb=17e77c3f2949a0729322b4a8d907f3f34b6a9914;hp=28109d5ae002e3c48df53f11a395009272d0214d;hpb=1ecf6419aba86993b3c223bf5ec0fa79427baf85;p=jalview.git diff --git a/src/jalview/io/FastaFile.java b/src/jalview/io/FastaFile.java index 28109d5..2801ac4 100755 --- a/src/jalview/io/FastaFile.java +++ b/src/jalview/io/FastaFile.java @@ -1,139 +1,245 @@ -package jalview.io; - -import jalview.datamodel.*; -import jalview.analysis.*; - -import java.io.*; -import java.util.*; - -public class FastaFile extends AlignFile { - - public FastaFile() - {} - - public FastaFile(String inStr) { - super(inStr); - } - - public FastaFile(String inFile, String type) throws IOException { - super(inFile,type); - } - - public void parse() throws IOException - { - - String id = ""; - StringBuffer seq = new StringBuffer(); - int count = 0; - boolean flag = false; - - int sstart = 0; - int send = 0; - - 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("/") > 0 ) { - - StringTokenizer st = new StringTokenizer(id,"/"); - if (st.countTokens() == 2) { - id = st.nextToken(); - String tmp = st.nextToken(); - - st = new StringTokenizer(tmp,"-"); - - if (st.countTokens() == 2) { - sstart = Integer.valueOf(st.nextToken()).intValue(); - send = Integer.valueOf(st.nextToken()).intValue(); - } - } - } - - seq = new StringBuffer(); - - } else { - seq = seq.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())); - } - } - - } - - public static String print(SequenceI[] s) { - return print(s,72); - } - public static String print(SequenceI[] s, int len) { - return print(s,len,true); - } - public static String print(SequenceI[] s, int len,boolean gaps) { - StringBuffer 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(),"-"); - seq = AlignSeq.extractGaps(seq,"."); - seq = AlignSeq.extractGaps(seq," "); - } - - out.append(">" + s[i].getName() + "/" + s[i].getStart() + "-" + s[i].getEnd() + "\n"); - - int nochunks = seq.length() / len + 1; - - 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"); - } - } - i++; - } - return out.toString(); - } - - public String print() { - return print(getSeqsAsArray()); - } -} - - - +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9) + * Copyright (C) 2015 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 jalview.datamodel.Alignment; +import jalview.datamodel.AlignmentAnnotation; +import jalview.datamodel.Annotation; +import jalview.datamodel.Sequence; +import jalview.datamodel.SequenceI; + +import java.io.IOException; + +/** + * 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() + { + } + + /** + * 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 FastaFile(FileParse source) throws IOException + { + super(source); + } + + /** + * DOCUMENT ME! + * + * @throws IOException + * DOCUMENT ME! + */ + public void parse() throws IOException + { + StringBuffer sb = new StringBuffer(); + boolean firstLine = true; + + String line, uline; + Sequence seq = null; + + boolean annotation = false; + + while ((uline = nextLine()) != null) + { + line = uline.trim(); + if (line.length() > 0) + { + if (line.charAt(0) == '>') + { + if (line.startsWith(">#_")) + { + if (annotation) + { + annotations.addElement(makeAnnotation(seq, sb)); + } + } + else + { + annotation = false; + } + + if (!firstLine) + { + seq.setSequence(sb.toString()); + + if (!annotation) + { + seqs.addElement(seq); + } + } + + seq = parseId(line.substring(1)); + firstLine = false; + + sb = new StringBuffer(); + + if (line.startsWith(">#_")) + { + annotation = true; + } + } + else + { + sb.append(annotation ? uline : line); + } + } + } + + if (annotation) + { + annotations.addElement(makeAnnotation(seq, sb)); + } + + else if (!firstLine) + { + seq.setSequence(sb.toString()); + seqs.addElement(seq); + } + } + + private AlignmentAnnotation makeAnnotation(SequenceI seq, StringBuffer sb) + { + Annotation[] anots = new Annotation[sb.length()]; + char cb; + for (int i = 0; i < anots.length; i++) + { + char cn = sb.charAt(i); + if (cn != ' ') + { + anots[i] = new Annotation("" + cn, null, ' ', Float.NaN); + } + } + AlignmentAnnotation aa = new AlignmentAnnotation(seq.getName() + .substring(2), seq.getDescription(), anots); + return aa; + } + + /** + * 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); + } + } + + /** + * 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)) + { + out.append(">" + printId(s[i])); + if (s[i].getDescription() != null) + { + out.append(" " + s[i].getDescription()); + } + + out.append(newline); + + int nochunks = (s[i].getLength() / len) + 1; + + for (int j = 0; j < nochunks; j++) + { + int start = j * len; + int end = start + len; + + if (end < s[i].getLength()) + { + out.append(s[i].getSequenceAsString(start, end) + newline); + } + else if (start < s[i].getLength()) + { + out.append(s[i].getSequenceAsString(start, s[i].getLength()) + + newline); + } + } + + i++; + } + + return out.toString(); + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String print() + { + return print(getSeqsAsArray()); + } +}