X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FClustalFile.java;h=c5581867c48d1934c4c4b8cfaede90e62de08147;hb=refs%2Fheads%2Fpatch%2FJAL-1236_customClustalHeader;hp=e3f83ee652bda92538a9e0e627c197065af4765b;hpb=174230b4233d9ce80f94527768d2cd2f76da11ab;p=jalview.git
diff --git a/src/jalview/io/ClustalFile.java b/src/jalview/io/ClustalFile.java
index e3f83ee..c558186 100755
--- a/src/jalview/io/ClustalFile.java
+++ b/src/jalview/io/ClustalFile.java
@@ -1,223 +1,283 @@
-/*
- * Jalview - A Sequence Alignment Editor and Viewer
- * Copyright (C) 2006 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 java.io.*;
-import java.util.*;
-
-import jalview.datamodel.*;
-import jalview.util.*;
-
-public class ClustalFile
- extends AlignFile
-{
-
- public ClustalFile()
- {
- }
-
- public ClustalFile(String inFile, String type)
- throws IOException
- {
- super(inFile, type);
- }
-
- public void initData()
- {
- super.initData();
- }
-
- public void parse() throws IOException
- {
- int i = 0;
- boolean flag = false;
-
- Vector headers = new Vector();
- Hashtable seqhash = new Hashtable();
- StringBuffer tempseq;
- String line, id;
- StringTokenizer str;
-
- try
- {
- while ( (line = nextLine()) != null)
- {
- if (line.indexOf(" ") != 0)
- {
- str = new StringTokenizer(line, " ");
-
- if (str.hasMoreTokens())
- {
- id = str.nextToken();
-
- if (id.equalsIgnoreCase("CLUSTAL"))
- {
- flag = true;
- }
- else
- {
- if (flag)
- {
- 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());
- }
- }
- }
- }
- else
- flag = true;
- }
- }
- }
- catch (IOException e)
- {
- System.err.println("Exception parsing clustal file " + e);
- e.printStackTrace();
- }
-
- if (flag)
- {
- this.noSeqs = headers.size();
-
- //Add sequences to the hash
- 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() );
-
- if (!isValidProteinSequence(newSeq.getSequence()))
- {
- throw new IOException(AppletFormatAdapter.INVALID_CHARACTERS
- + " : " + newSeq.getName()
- + " : " + invalidCharacter);
- }
-
-
- seqs.addElement(newSeq);
- }
- else
- {
- System.err.println(
- "Clustal File Reader: Can't find sequence for " +
- headers.elementAt(i));
- }
- }
- }
- }
-
- public String print()
- {
- return print(getSeqsAsArray());
- }
-
- public String print(SequenceI[] s)
- {
- StringBuffer out = new StringBuffer("CLUSTAL\n\n");
-
- 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;
- }
-
- maxid++;
-
- int len = 60;
- int nochunks = (max / len) + 1;
-
- for (i = 0; i < nochunks; i++)
- {
- int j = 0;
-
- while ( (j < s.length) && (s[j] != null))
- {
- out.append(new Format("%-" + maxid + "s").form( printId(s[j]) + " "));
-
- int start = i * len;
- int end = start + len;
-
- if ( (end < s[j].getSequence().length()) &&
- (start < s[j].getSequence().length()))
- {
- out.append(s[j].getSequence().substring(start, end));
- }
- else
- {
- if (start < s[j].getSequence().length())
- {
- out.append(s[j].getSequence().substring(start));
- }
- }
-
- out.append("\n");
- j++;
- }
-
- out.append("\n");
- }
-
- return out.toString();
- }
-}
+/*
+ * 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.
+ *
+ * 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.AlignmentAnnotation;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceI;
+import jalview.util.Format;
+
+import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
+import java.util.StringTokenizer;
+import java.util.Vector;
+
+public class ClustalFile extends AlignFile
+{
+
+ public ClustalFile()
+ {
+ _initHeader();
+ }
+
+ public ClustalFile(String inFile, DataSourceType sourceType)
+ throws IOException
+ {
+ super(inFile, sourceType);
+ _initHeader();
+ }
+
+ public ClustalFile(FileParse source) throws IOException
+ {
+ super(source);
+ _initHeader();
+ }
+
+ private void _initHeader()
+ {
+ try {
+ clustalHeader = jalview.bin.Cache.getDefault("CLUSTAL_HEADER","CLUSTAL");
+ } catch (Error e) {};
+
+ }
+
+ @Override
+ public void initData()
+ {
+ super.initData();
+ }
+
+ @Override
+ public void parse() throws IOException
+ {
+ int i = 0;
+ boolean flag = false;
+ boolean top = false;
+ StringBuffer pssecstr = new StringBuffer();
+ StringBuffer consstr = new StringBuffer();
+ Vector headers = new Vector<>();
+ Map seqhash = new HashMap<>();
+ StringBuffer tempseq;
+ String line, id;
+ StringTokenizer str;
+
+ try
+ {
+ while ((line = nextLine()) != null)
+ {
+ if (line.length() == 0)
+ {
+ top = true;
+ }
+ boolean isConservation = line.startsWith(SPACE)
+ || line.startsWith(TAB);
+ if (!isConservation)
+ {
+ str = new StringTokenizer(line);
+
+ if (str.hasMoreTokens())
+ {
+ id = str.nextToken();
+ // TODO: JAL-1236 other tokens may be indicative of a header for Clustal format
+ if (id.equalsIgnoreCase("CLUSTAL"))
+ {
+ flag = true;
+ }
+ else
+ {
+ if (flag)
+ {
+ if (seqhash.containsKey(id))
+ {
+ tempseq = 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());
+ }
+ top = false;
+ }
+ }
+ }
+ else
+ {
+ flag = true;
+ }
+ }
+ else
+ {
+ if (line.matches("\\s+(-|\\.|\\(|\\[|\\]|\\))+"))
+ {
+ if (top)
+ {
+ pssecstr.append(line.trim());
+ }
+ else
+ {
+ consstr.append(line.trim());
+ }
+ }
+ }
+ }
+ } catch (IOException e)
+ {
+ System.err.println("Exception parsing clustal file " + e);
+ e.printStackTrace();
+ }
+
+ if (flag)
+ {
+ this.noSeqs = headers.size();
+
+ // Add sequences to the hash
+ 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("Clustal File Reader: Can't find sequence for "
+ + headers.elementAt(i));
+ }
+ }
+ AlignmentAnnotation lastssa = null;
+ if (pssecstr.length() == maxLength)
+ {
+ Vector ss = new Vector<>();
+ AlignmentAnnotation ssa = lastssa = StockholmFile
+ .parseAnnotationRow(ss, "secondary structure",
+ pssecstr.toString());
+ ssa.label = "Secondary Structure";
+ annotations.addElement(ssa);
+ }
+ if (consstr.length() == maxLength)
+ {
+ Vector ss = new Vector<>();
+ AlignmentAnnotation ssa = StockholmFile.parseAnnotationRow(ss,
+ "secondary structure", consstr.toString());
+ ssa.label = "Consensus Secondary Structure";
+ if (lastssa == null || !lastssa.getRNAStruc()
+ .equals(ssa.getRNAStruc().replace('-', '.')))
+ {
+ annotations.addElement(ssa);
+ }
+ }
+ }
+ }
+ /**
+ * clustal header - customise if needed
+ */
+ public String clustalHeader = "CLUSTAL";
+
+ @Override
+ public String print(SequenceI[] s, boolean jvsuffix)
+ {
+ StringBuffer out = new StringBuffer(clustalHeader + newline + newline);
+
+ int max = 0;
+ int maxid = 0;
+
+ int i = 0;
+
+ while ((i < s.length) && (s[i] != null))
+ {
+ String tmp = printId(s[i], jvsuffix);
+
+ max = Math.max(max, s[i].getLength());
+
+ if (tmp.length() > maxid)
+ {
+ maxid = tmp.length();
+ }
+
+ i++;
+ }
+
+ if (maxid < 15)
+ {
+ maxid = 15;
+ }
+
+ maxid++;
+
+ int len = 60;
+ int nochunks = (max / len) + (max % len > 0 ? 1 : 0);
+
+ for (i = 0; i < nochunks; i++)
+ {
+ int j = 0;
+
+ while ((j < s.length) && (s[j] != null))
+ {
+ out.append(new Format("%-" + maxid + "s")
+ .form(printId(s[j], jvsuffix) + " "));
+
+ int chunkStart = i * len;
+ int chunkEnd = chunkStart + len;
+
+ int length = s[j].getLength();
+ if ((chunkEnd < length) && (chunkStart < length))
+ {
+ out.append(s[j].getSequenceAsString(chunkStart, chunkEnd));
+ }
+ else
+ {
+ if (chunkStart < length)
+ {
+ out.append(s[j].getSequenceAsString().substring(chunkStart));
+ }
+ }
+
+ out.append(newline);
+ j++;
+ }
+
+ out.append(newline);
+ }
+
+ return out.toString();
+ }
+}