X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FMSFfile.java;h=6b584a80f16363d2cc452db9dca1e6853049eee1;hb=797df64fa2a0a30773d0f48f5494d4155e5a8be3;hp=3c18432c98864608f1d6c99b3e33e1ff4414e9d8;hpb=128c1c559ce7749ba5a39d30e6108f5ce8f4b99e;p=jalview.git diff --git a/src/jalview/io/MSFfile.java b/src/jalview/io/MSFfile.java index 3c18432..6b584a8 100755 --- a/src/jalview/io/MSFfile.java +++ b/src/jalview/io/MSFfile.java @@ -1,235 +1,414 @@ -package jalview.io; - -import jalview.datamodel.*; -import jalview.util.*; - -import java.io.*; -import java.util.*; - -public class MSFfile extends AlignFile { - - public MSFfile() - {} - - public MSFfile(String inStr) { - super(inStr); - } - - public MSFfile(String inFile, String type) throws IOException { - super(inFile,type); - } - - private static com.stevesoft.pat.Regex gapre = new com.stevesoft.pat.Regex("\\~","-"); - private static com.stevesoft.pat.Regex re2gap = new com.stevesoft.pat.Regex("["+jalview.util.Comparison.GapChars+"]","\\~"); - - public void parse() { - int i = 0; - boolean seqFlag = false; - String key = new String(); - Vector headers = new Vector(); - Hashtable seqhash = new Hashtable(); - String line; - - try { - while ((line = nextLine()) != null) { - - StringTokenizer str = new StringTokenizer(line); - - while (str.hasMoreTokens()) { - - String inStr = str.nextToken(); - - //If line has header information add to the headers vector - if (inStr.indexOf("Name:") != -1) { - key = str.nextToken(); - headers.addElement(key); - } - - //if line has // set SeqFlag to 1 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)) { - //seqeunce id is the first field - key = inStr; - StringBuffer tempseq; - - //Get sequence from hash if it exists - if (seqhash.containsKey(key)) { - tempseq = (StringBuffer)seqhash.get(key); - } else { - tempseq = new StringBuffer(); - seqhash.put(key,tempseq); - } - - //loop through the rest of the words - while (str.hasMoreTokens()) { - //append the word to the sequence - tempseq.append(str.nextToken()); - } - } - } - } - } catch (IOException e) { - System.err.println("Exception parsing MSFFile " + e); - e.printStackTrace(); - } - - this.noSeqs = headers.size(); - - //Add sequences to the hash - for (i = 0; i < headers.size(); i++ ) { - - if ( seqhash.get(headers.elementAt(i)) != null) { - String head = headers.elementAt(i).toString(); - String seq = seqhash.get(head).toString(); - - int start = 1; - int end = seq.length(); - - if (maxLength < head.length() ) { - maxLength = head.length(); - } - - if (head.indexOf("/") > 0 ) { - - StringTokenizer st = new StringTokenizer(head,"/"); - - if (st.countTokens() == 2) { - - head = 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(); - } - } - } - // Replace ~ with a sensible gap character - seq = gapre.replaceAll(seq); - Sequence newSeq = new Sequence(head,seq,start,end); - - seqs.addElement(newSeq); - - } else { - System.err.println("MSFFile Parser: Can't find sequence for " + headers.elementAt(i)); - } - } - - } - - public static int checkSum(String seq) { - //String chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz.*~&@"; - int check = 0; - - String index = "--------------------------------------&---*---.-----------------@ABCDEFGHIJKLMNOPQRSTUVWXYZ------ABCDEFGHIJKLMNOPQRSTUVWXYZ----@"; - index += "--------------------------------------------------------------------------------------------------------------------------------"; - - for(int i = 0; i < seq.length(); i++) { - try { - if (i max) { - max = seq.length(); - } - if (name.length() > maxid) { - maxid = name.length(); - } - i++; - } - - if (maxid < 10) { - maxid = 10; - } - maxid++; - out.append( "\n\n//\n\n"); - - int len = 50; - - int nochunks = max / len + 1; - if (max%len == 0) { - nochunks--; - } - for (i = 0; i < nochunks; i++) { - int j = 0; - while (j < s.length && s[j] != null) { - String name = s[j].getName(); - out.append( new Format("%-" + maxid + "s").form(name + "/" + s[j].getStart() + "-" + s[j].getEnd()) + " "); - for (int k = 0; k < 5; k++) { - - int start = i*50 + k*10; - int end = start + 10; - - if (end < s[j].getSequence().length() && start < s[j].getSequence().length() ) { - out.append(re2gap.replaceAll(s[j].getSequence().substring(start,end))); - if (k < 4) { - // out.append(" "); - } else { - out.append("\n"); - } - } else { - if (start < s[j].getSequence().length()) { - out.append(re2gap.replaceAll(s[j].getSequence().substring(start))); - out.append("\n"); - } else { - if (k == 0) { - out.append("\n"); - } - } - } - } - j++; - } - out.append("\n"); - - } - return out.toString(); - } - public String print() { - return print(getSeqsAsArray()); - } -} - - - - - - - +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7) + * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle + * + * 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 . + */ +package jalview.io; + +import java.io.*; +import java.util.*; + +import jalview.datamodel.*; +import jalview.util.*; + +/** + * DOCUMENT ME! + * + * @author $author$ + * @version $Revision$ + */ +public class MSFfile extends AlignFile +{ + + /** + * Creates a new MSFfile object. + */ + public MSFfile() + { + } + + /** + * Creates a new MSFfile object. + * + * @param inFile + * DOCUMENT ME! + * @param type + * DOCUMENT ME! + * + * @throws IOException + * DOCUMENT ME! + */ + public MSFfile(String inFile, String type) throws IOException + { + super(inFile, type); + } + + public MSFfile(FileParse source) throws IOException + { + super(source); + } + + { + // TODO Auto-generated constructor stub + } + + /** + * DOCUMENT ME! + */ + 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; + + try + { + while ((line = nextLine()) != null) + { + StringTokenizer str = new StringTokenizer(line); + + while (str.hasMoreTokens()) + { + String inStr = str.nextToken(); + + // If line has header information add to the headers vector + if (inStr.indexOf("Name:") != -1) + { + key = str.nextToken(); + headers.addElement(key); + } + + // if line has // set SeqFlag to 1 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)) + { + // seqeunce id is the first field + key = inStr; + + StringBuffer tempseq; + + // Get sequence from hash if it exists + if (seqhash.containsKey(key)) + { + tempseq = (StringBuffer) seqhash.get(key); + } + else + { + tempseq = new StringBuffer(); + seqhash.put(key, tempseq); + } + + // loop through the rest of the words + while (str.hasMoreTokens()) + { + // append the word to the sequence + tempseq.append(str.nextToken()); + } + } + } + } + } catch (IOException e) + { + System.err.println("Exception parsing MSFFile " + e); + e.printStackTrace(); + } + + this.noSeqs = headers.size(); + + // Add sequences to the hash + for (i = 0; i < headers.size(); i++) + { + if (seqhash.get(headers.elementAt(i)) != null) + { + String head = headers.elementAt(i).toString(); + String seq = seqhash.get(head).toString(); + + if (maxLength < head.length()) + { + maxLength = head.length(); + } + + // Replace ~ with a sensible gap character + seq = seq.replace('~', '-'); + + Sequence newSeq = parseId(head); + + newSeq.setSequence(seq); + + seqs.addElement(newSeq); + } + else + { + System.err.println("MSFFile Parser: Can't find sequence for " + + headers.elementAt(i)); + } + } + } + + /** + * DOCUMENT ME! + * + * @param seq + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public int checkSum(String seq) + { + int check = 0; + String sequence = seq.toUpperCase(); + + for (int i = 0; i < sequence.length(); i++) + { + try + { + + int value = sequence.charAt(i); + if (value != -1) + { + check += (i % 57 + 1) * value; + } + } catch (Exception e) + { + System.err.println("Exception during MSF Checksum calculation"); + e.printStackTrace(); + } + } + + return check % 10000; + } + + /** + * DOCUMENT ME! + * + * @param s + * DOCUMENT ME! + * @param is_NA + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String print(SequenceI[] seqs) + { + + boolean is_NA = jalview.util.Comparison.isNucleotide(seqs); + + SequenceI[] s = new SequenceI[seqs.length]; + + StringBuffer out = new StringBuffer("!!" + (is_NA ? "NA" : "AA") + + "_MULTIPLE_ALIGNMENT 1.0"); + // TODO: JBPNote : Jalview doesn't remember NA or AA yet. + out.append(newline); + out.append(newline); + int max = 0; + int maxid = 0; + int i = 0; + + while ((i < seqs.length) && (seqs[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()); + + StringBuffer sb = new StringBuffer(); + sb.append(s[i].getSequence()); + + for (int ii = 0; ii < sb.length(); ii++) + { + if (sb.charAt(ii) == '.') + { + sb.setCharAt(ii, '~'); + } + else + { + break; + } + } + + for (int ii = sb.length() - 1; ii > 0; ii--) + { + if (sb.charAt(ii) == '.') + { + sb.setCharAt(ii, '~'); + } + else + { + break; + } + } + + s[i].setSequence(sb.toString()); + + if (s[i].getSequence().length > max) + { + max = s[i].getSequence().length; + } + + i++; + } + + Format maxLenpad = new Format("%" + (new String("" + max)).length() + + "d"); + Format maxChkpad = new Format("%" + (new String("1" + max)).length() + + "d"); + i = 0; + + int bigChecksum = 0; + int[] checksums = new int[s.length]; + while (i < s.length) + { + checksums[i] = checkSum(s[i].getSequenceAsString()); + bigChecksum += checksums[i]; + i++; + } + + long maxNB = 0; + out.append(" MSF: " + s[0].getSequence().length + " Type: " + + (is_NA ? "N" : "P") + " Check: " + (bigChecksum % 10000) + + " .."); + out.append(newline); + out.append(newline); + out.append(newline); + + String[] nameBlock = new String[s.length]; + String[] idBlock = new String[s.length]; + + i = 0; + while ((i < s.length) && (s[i] != null)) + { + + nameBlock[i] = new String(" Name: " + printId(s[i]) + " "); + + idBlock[i] = new String("Len: " + + maxLenpad.form(s[i].getSequence().length) + " Check: " + + maxChkpad.form(checksums[i]) + " Weight: 1.00"+newline); + + if (s[i].getName().length() > maxid) + { + maxid = s[i].getName().length(); + } + + if (nameBlock[i].length() > maxNB) + { + maxNB = nameBlock[i].length(); + } + + i++; + } + + if (maxid < 10) + { + maxid = 10; + } + + if (maxNB < 15) + { + maxNB = 15; + } + + Format nbFormat = new Format("%-" + maxNB + "s"); + + for (i = 0; (i < s.length) && (s[i] != null); i++) + { + out.append(nbFormat.form(nameBlock[i]) + idBlock[i]); + } + + maxid++; + out.append(newline); + out.append(newline);out.append("//"); + out.append(newline); + out.append(newline); + int len = 50; + + int nochunks = (max / len) + 1; + + if ((max % len) == 0) + { + nochunks--; + } + + for (i = 0; i < nochunks; i++) + { + int j = 0; + + while ((j < s.length) && (s[j] != null)) + { + String name = printId(s[j]); + + out.append(new Format("%-" + maxid + "s").form(name + " ")); + + for (int k = 0; k < 5; k++) + { + int start = (i * 50) + (k * 10); + int end = start + 10; + + if ((end < s[j].getSequence().length) + && (start < s[j].getSequence().length)) + { + out.append(s[j].getSequence(start, end)); + + if (k < 4) + { + out.append(" "); + } + else + { + out.append(newline); + } + } + else + { + if (start < s[j].getSequence().length) + { + out.append(s[j].getSequenceAsString().substring(start)); + out.append(newline); + } + else + { + if (k == 0) + { + out.append(newline); + } + } + } + } + + j++; + } + + out.append(newline); + } + + return out.toString(); + } + + /** + * DOCUMENT ME! + * + * @return DOCUMENT ME! + */ + public String print() + { + return print(getSeqsAsArray()); + } +}