X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FMSFfile.java;h=7e46978b7390b0b31c0e7bb086963ebe7c807270;hb=37de9310bec3501cbc6381e0c3dcb282fcaad812;hp=c3ee382a004d9e8577b8d06e872644d27e26821d;hpb=28787d9646cca5dd77190930f59b7ff32cf995b4;p=jalview.git diff --git a/src/jalview/io/MSFfile.java b/src/jalview/io/MSFfile.java index c3ee382..7e46978 100755 --- a/src/jalview/io/MSFfile.java +++ b/src/jalview/io/MSFfile.java @@ -1,36 +1,35 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8) - * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle + * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) + * Copyright (C) $$Year-Rel$$ 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. + * 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 . + * 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.Sequence; +import jalview.datamodel.SequenceI; +import jalview.util.Comparison; +import jalview.util.Format; -import javax.xml.parsers.ParserConfigurationException; - -import org.xml.sax.SAXException; - -import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax; -import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed; -import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied; -import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses; - -import jalview.datamodel.*; -import jalview.util.*; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Hashtable; +import java.util.List; +import java.util.StringTokenizer; /** * DOCUMENT ME! @@ -58,46 +57,35 @@ public class MSFfile extends AlignFile * * @throws IOException * DOCUMENT ME! - * @throws SAXException - * @throws ParserConfigurationException - * @throws ExceptionFileFormatOrSyntax - * @throws ExceptionLoadingFailed - * @throws ExceptionPermissionDenied - * @throws InterruptedException - * @throws ExceptionUnmatchedClosingParentheses */ - public MSFfile(String inFile, String type) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses + public MSFfile(String inFile, String type) throws IOException { super(inFile, type); } - public MSFfile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses + public MSFfile(FileParse source) throws IOException { super(source); } - { - // TODO Auto-generated constructor stub - } - /** - * DOCUMENT ME! + * Read and parse MSF sequence data */ + @Override public void parse() throws IOException { - int i = 0; boolean seqFlag = false; - String key = new String(); - Vector headers = new Vector(); - Hashtable seqhash = new Hashtable(); - String line; + List headers = new ArrayList(); + Hashtable seqhash = new Hashtable(); try { + String line; while ((line = nextLine()) != null) { StringTokenizer str = new StringTokenizer(line); + String key = null; while (str.hasMoreTokens()) { String inStr = str.nextToken(); @@ -106,31 +94,31 @@ public class MSFfile extends AlignFile if (inStr.indexOf("Name:") != -1) { key = str.nextToken(); - headers.addElement(key); + headers.add(key); } - // if line has // set SeqFlag to 1 so we know sequences are coming + // if line has // set SeqFlag so we know sequences are coming if (inStr.indexOf("//") != -1) { seqFlag = true; } // Process lines as sequence lines if seqFlag is set - if ((inStr.indexOf("//") == -1) && (seqFlag == true)) + if ((inStr.indexOf("//") == -1) && seqFlag) { - // seqeunce id is the first field + // sequence id is the first field key = inStr; - StringBuffer tempseq; + StringBuilder tempseq; // Get sequence from hash if it exists if (seqhash.containsKey(key)) { - tempseq = (StringBuffer) seqhash.get(key); + tempseq = seqhash.get(key); } else { - tempseq = new StringBuffer(); + tempseq = new StringBuilder(64); seqhash.put(key, tempseq); } @@ -138,7 +126,8 @@ public class MSFfile extends AlignFile while (str.hasMoreTokens()) { // append the word to the sequence - tempseq.append(str.nextToken()); + String sequenceBlock = str.nextToken(); + tempseq.append(sequenceBlock); } } } @@ -152,11 +141,11 @@ public class MSFfile extends AlignFile this.noSeqs = headers.size(); // Add sequences to the hash - for (i = 0; i < headers.size(); i++) + for (int i = 0; i < headers.size(); i++) { - if (seqhash.get(headers.elementAt(i)) != null) + if (seqhash.get(headers.get(i)) != null) { - String head = headers.elementAt(i).toString(); + String head = headers.get(i); String seq = seqhash.get(head).toString(); if (maxLength < head.length()) @@ -164,8 +153,11 @@ public class MSFfile extends AlignFile maxLength = head.length(); } - // Replace ~ with a sensible gap character - seq = seq.replace('~', '-'); + /* + * replace ~ (leading/trailing positions) with the gap character; + * use '.' as this is the internal gap character required by MSF + */ + seq = seq.replace('~', '.'); Sequence newSeq = parseId(head); @@ -176,7 +168,7 @@ public class MSFfile extends AlignFile else { System.err.println("MSFFile Parser: Can't find sequence for " - + headers.elementAt(i)); + + headers.get(i)); } } } @@ -224,15 +216,16 @@ public class MSFfile extends AlignFile * * @return DOCUMENT ME! */ - public String print(SequenceI[] seqs) + public String print(SequenceI[] sqs) { - boolean is_NA = jalview.util.Comparison.isNucleotide(seqs); + boolean is_NA = Comparison.isNucleotide(sqs); - SequenceI[] s = new SequenceI[seqs.length]; + SequenceI[] s = new SequenceI[sqs.length]; - StringBuffer out = new StringBuffer("!!" + (is_NA ? "NA" : "AA") - + "_MULTIPLE_ALIGNMENT 1.0"); + StringBuilder out = new StringBuilder(256); + out.append("!!").append(is_NA ? "NA" : "AA") + .append("_MULTIPLE_ALIGNMENT 1.0"); // TODO: JBPNote : Jalview doesn't remember NA or AA yet. out.append(newline); out.append(newline); @@ -240,14 +233,15 @@ public class MSFfile extends AlignFile int maxid = 0; int i = 0; - while ((i < seqs.length) && (seqs[i] != null)) + while ((i < sqs.length) && (sqs[i] != null)) { - // Replace all internal gaps with . and external spaces with ~ - s[i] = new Sequence(seqs[i].getName(), seqs[i].getSequenceAsString() - .replace('-', '.'), seqs[i].getStart(), seqs[i].getEnd()); + /* + * modify to MSF format: uses '.' for internal gaps, + * and '~' for leading or trailing gaps + */ + String seqString = sqs[i].getSequenceAsString().replace('-', '.'); - StringBuffer sb = new StringBuffer(); - sb.append(s[i].getSequence()); + StringBuilder sb = new StringBuilder(seqString); for (int ii = 0; ii < sb.length(); ii++) { @@ -272,12 +266,12 @@ public class MSFfile extends AlignFile break; } } + s[i] = new Sequence(sqs[i].getName(), sb.toString(), + sqs[i].getStart(), sqs[i].getEnd()); - s[i].setSequence(sb.toString()); - - if (s[i].getSequence().length > max) + if (sb.length() > max) { - max = s[i].getSequence().length; + max = sb.length(); } i++; @@ -357,12 +351,7 @@ public class MSFfile extends AlignFile out.append(newline); int len = 50; - int nochunks = (max / len) + 1; - - if ((max % len) == 0) - { - nochunks--; - } + int nochunks = (max / len) + (max % len > 0 ? 1 : 0); for (i = 0; i < nochunks; i++) { @@ -424,6 +413,7 @@ public class MSFfile extends AlignFile * * @return DOCUMENT ME! */ + @Override public String print() { return print(getSeqsAsArray());