-package jalview.io;\r
-\r
-import jalview.datamodel.*;\r
-import jalview.util.*;\r
-\r
-import java.io.*;\r
-import java.util.*;\r
-\r
-public class ClustalFile extends AlignFile {\r
-\r
- Vector ids;\r
-\r
- public ClustalFile()\r
- {}\r
-\r
- public ClustalFile(String inStr) {\r
- super(inStr);\r
- }\r
-\r
-\r
- public void initData() {\r
- super.initData();\r
- ids = new Vector();\r
- }\r
-\r
- public ClustalFile(String inFile, String type) throws IOException {\r
- super(inFile,type);\r
- }\r
-\r
- public void parse() {\r
- int i = 0;\r
- boolean flag = false;\r
-\r
- Vector headers = new Vector();\r
- Hashtable seqhash = new Hashtable();\r
-\r
- String line;\r
-\r
- try {\r
- while ((line = nextLine()) != null) {\r
- if (line.indexOf(" ") != 0) {\r
- StringTokenizer str = new StringTokenizer(line," ");\r
- String id = "";\r
-\r
- if (str.hasMoreTokens()) {\r
- id = str.nextToken();\r
- if (id.equals("CLUSTAL")) {\r
- flag = true;\r
- } else {\r
- if (flag) {\r
- StringBuffer tempseq;\r
- if (seqhash.containsKey(id)) {\r
- tempseq = (StringBuffer)seqhash.get(id);\r
- } else {\r
- tempseq = new StringBuffer();\r
- seqhash.put(id,tempseq);\r
- }\r
-\r
- if (!(headers.contains(id))) {\r
- headers.addElement(id);\r
- }\r
-\r
- if(str.hasMoreTokens())\r
- tempseq.append(str.nextToken());\r
- }\r
- }\r
- }\r
- }\r
- }\r
- } catch (IOException e) {\r
- System.err.println("Exception parsing clustal file " + e);\r
- e.printStackTrace();\r
- }\r
-\r
- if (flag) {\r
- this.noSeqs = headers.size();\r
-\r
- //Add sequences to the hash\r
- for (i = 0; i < headers.size(); i++ ) {\r
- int start = -1;\r
- int end = -1;\r
-\r
- if ( seqhash.get(headers.elementAt(i)) != null) {\r
- if (maxLength < seqhash.get(headers.elementAt(i)).toString().length() ) {\r
- maxLength = seqhash.get(headers.elementAt(i)).toString().length();\r
- }\r
- String head = headers.elementAt(i).toString();\r
- start = 1;\r
- end = seqhash.get(headers.elementAt(i)).toString().length();\r
-\r
- if (head.indexOf("/") > 0 ) {\r
- StringTokenizer st = new StringTokenizer(head,"/");\r
- if (st.countTokens() == 2) {\r
-\r
- ids.addElement(st.nextToken());\r
-\r
- String tmp = st.nextToken();\r
- st = new StringTokenizer(tmp,"-");\r
- if (st.countTokens() == 2) {\r
- start = Integer.valueOf(st.nextToken()).intValue();\r
- end = Integer.valueOf(st.nextToken()).intValue();\r
- }\r
- } else {\r
- ids.addElement(headers.elementAt(i));\r
- }\r
- } else {\r
- ids.addElement(headers.elementAt(i));\r
-\r
- }\r
- Sequence newSeq = new Sequence(ids.elementAt(i).toString(),\r
- seqhash.get(headers.elementAt(i).toString()).toString(),start,end);\r
-\r
- seqs.addElement(newSeq);\r
-\r
- } else {\r
- System.err.println("Clustal File Reader: Can't find sequence for " + headers.elementAt(i));\r
- }\r
- }\r
- }\r
-\r
- }\r
-\r
- public String print() {\r
- return print(getSeqsAsArray());\r
- }\r
- public static String print(SequenceI[] s) {\r
-\r
- StringBuffer out = new StringBuffer("CLUSTAL\n\n");\r
-\r
- int max = 0;\r
- int maxid = 0;\r
-\r
- int i = 0;\r
-\r
- while (i < s.length && s[i] != null) {\r
- String tmp = s[i].getName() + "/" + s[i].getStart() + "-" + s[i].getEnd();\r
-\r
- if (s[i].getSequence().length() > max) {\r
- max = s[i].getSequence().length();\r
- }\r
- if (tmp.length() > maxid) {\r
- maxid = tmp.length();\r
- }\r
- i++;\r
- }\r
-\r
- if (maxid < 15) {\r
- maxid = 15;\r
- }\r
- maxid++;\r
- int len = 60;\r
- int nochunks = max / len + 1;\r
-\r
- for (i = 0; i < nochunks; i++) {\r
- int j = 0;\r
- while ( j < s.length && s[j] != null) {\r
- out.append( new Format("%-" + maxid + "s").form(s[j].getName() + "/" + s[j].getStart() + "-" + s[j].getEnd()) + " ");\r
- int start = i*len;\r
- int end = start + len;\r
-\r
- if (end < s[j].getSequence().length() && start < s[j].getSequence().length() )\r
- out.append(s[j].getSequence().substring(start,end));\r
- else\r
- {\r
- if (start < s[j].getSequence().length())\r
- out.append(s[j].getSequence().substring(start));\r
- }\r
- out.append("\n");\r
- j++;\r
- }\r
- out.append("\n");\r
-\r
- }\r
-\r
- return out.toString();\r
- }\r
-\r
-\r
-}\r
+/*
+ * 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 <http://www.gnu.org/licenses/>.
+ * 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.Hashtable;
+import java.util.StringTokenizer;
+import java.util.Vector;
+
+public class ClustalFile extends AlignFile
+{
+
+ public ClustalFile()
+ {
+ }
+
+ public ClustalFile(String inFile, String type) throws IOException
+ {
+ super(inFile, type);
+ }
+
+ public ClustalFile(FileParse source) throws IOException
+ {
+ super(source);
+ }
+
+ @Override
+ public void initData()
+ {
+ super.initData();
+ }
+
+ @Override
+ public void parse() throws IOException
+ {
+ int i = 0;
+ boolean flag = false;
+ boolean rna = false;
+ boolean top = false;
+ StringBuffer pssecstr = new StringBuffer(), consstr = new StringBuffer();
+ Vector headers = new Vector();
+ Hashtable seqhash = new Hashtable();
+ StringBuffer tempseq;
+ String line, id;
+ StringTokenizer str;
+
+ try
+ {
+ while ((line = nextLine()) != null)
+ {
+ if (line.length() == 0)
+ {
+ top = true;
+ }
+ 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());
+ }
+ 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);
+ }
+ }
+ }
+ }
+
+ @Override
+ public String print()
+ {
+ return print(getSeqsAsArray());
+ // TODO: locaRNA style aln output
+ }
+
+ public String print(SequenceI[] s)
+ {
+ StringBuffer out = new StringBuffer("CLUSTAL" + newline + newline);
+
+ 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) + (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]) + " "));
+
+ int start = i * len;
+ int end = start + len;
+
+ if ((end < s[j].getSequence().length)
+ && (start < s[j].getSequence().length))
+ {
+ out.append(s[j].getSequenceAsString(start, end));
+ }
+ else
+ {
+ if (start < s[j].getSequence().length)
+ {
+ out.append(s[j].getSequenceAsString().substring(start));
+ }
+ }
+
+ out.append(newline);
+ j++;
+ }
+
+ out.append(newline);
+ }
+
+ return out.toString();
+ }
+}