X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FPfamFile.java;h=bc22fae2933693a7dec73c3ed1a5c81b12ad7a92;hb=7d67fb613ec026dc9a265e351e7fab542e3f1d61;hp=f74a15a7fe3a218be8fd993665d506544fd8c5fe;hpb=797df64fa2a0a30773d0f48f5494d4155e5a8be3;p=jalview.git
diff --git a/src/jalview/io/PfamFile.java b/src/jalview/io/PfamFile.java
index f74a15a..bc22fae 100755
--- a/src/jalview/io/PfamFile.java
+++ b/src/jalview/io/PfamFile.java
@@ -1,27 +1,33 @@
/*
- * 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
+ * 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.Format;
+import jalview.util.MessageManager;
-import jalview.datamodel.*;
-import jalview.util.*;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashMap;
public class PfamFile extends AlignFile
{
@@ -30,9 +36,10 @@ public class PfamFile extends AlignFile
{
}
- public PfamFile(String inFile, String type) throws IOException
+ public PfamFile(String inFile, DataSourceType sourceType)
+ throws IOException
{
- super(inFile, type);
+ super(inFile, sourceType);
}
public PfamFile(FileParse source) throws IOException
@@ -40,90 +47,104 @@ public class PfamFile extends AlignFile
super(source);
}
+ @Override
public void initData()
{
super.initData();
}
+ @Override
public void parse() throws IOException
{
int i = 0;
String line;
- Hashtable seqhash = new Hashtable();
- Vector headers = new Vector();
-
+ HashMap seqhash = new HashMap();
+ ArrayList headers = new ArrayList();
+ boolean useTabs = false;
+ int spces;
while ((line = nextLine()) != null)
{
- if (line.indexOf(" ") != 0)
+ if (line.indexOf("#") == 0)
+ {
+ // skip comment lines
+ continue;
+ }
+ // locate first space or (if already checked), tab
+ if (useTabs)
+ {
+ spces = line.indexOf("\t");
+ }
+ else
{
- if (line.indexOf("#") != 0)
+ spces = line.indexOf(" ");
+ // check to see if we ought to split on tabs instead.
+ if (!useTabs && spces == -1)
{
- // TODO: verify pfam format requires spaces and not tab characters -
- // if not upgrade to use stevesoft regex and look for whitespace.
- StringTokenizer str = new StringTokenizer(line, " ");
- String id = "";
-
- if (str.hasMoreTokens())
- {
- id = str.nextToken();
-
- StringBuffer tempseq;
-
- 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());
- }
- }
+ useTabs = true;
+ spces = line.indexOf("\t");
}
}
+ if (spces <= 0)
+ {
+ // no sequence data to split on
+ continue;
+ }
+ String id = line.substring(0, spces);
+ StringBuffer tempseq;
+
+ if (seqhash.containsKey(id))
+ {
+ tempseq = seqhash.get(id);
+ }
+ else
+ {
+ tempseq = new StringBuffer();
+ seqhash.put(id, tempseq);
+ }
+
+ if (!(headers.contains(id)))
+ {
+ headers.add(id);
+ }
+ if (spces + 1 < line.length())
+ {
+ tempseq.append(line.substring(spces + 1).trim());
+ }
}
this.noSeqs = headers.size();
if (noSeqs < 1)
{
- throw new IOException("No sequences found (PFAM input)");
+ throw new IOException(
+ MessageManager.getString("exception.pfam_no_sequences_found"));
}
for (i = 0; i < headers.size(); i++)
{
- if (seqhash.get(headers.elementAt(i)) != null)
+ if (seqhash.get(headers.get(i)) != null)
{
- if (maxLength < seqhash.get(headers.elementAt(i)).toString()
- .length())
+ if (maxLength < seqhash.get(headers.get(i)).toString().length())
{
- maxLength = seqhash.get(headers.elementAt(i)).toString().length();
+ maxLength = seqhash.get(headers.get(i)).toString().length();
}
- Sequence newSeq = parseId(headers.elementAt(i).toString());
- newSeq.setSequence(seqhash.get(headers.elementAt(i).toString())
+ Sequence newSeq = parseId(headers.get(i).toString());
+ newSeq.setSequence(seqhash.get(headers.get(i).toString())
.toString());
seqs.addElement(newSeq);
}
else
{
System.err.println("PFAM File reader: Can't find sequence for "
- + headers.elementAt(i));
+ + headers.get(i));
}
}
}
- public String print(SequenceI[] s)
+ @Override
+ public String print(SequenceI[] s, boolean jvsuffix)
{
StringBuffer out = new StringBuffer("");
@@ -134,7 +155,7 @@ public class PfamFile extends AlignFile
while ((i < s.length) && (s[i] != null))
{
- String tmp = printId(s[i]);
+ String tmp = printId(s[i], jvsuffix);
if (s[i].getSequence().length > max)
{
@@ -158,7 +179,8 @@ public class PfamFile extends AlignFile
while ((j < s.length) && (s[j] != null))
{
- out.append(new Format("%-" + maxid + "s").form(printId(s[j]) + " "));
+ out.append(new Format("%-" + maxid + "s")
+ .form(printId(s[j], jvsuffix) + " "));
out.append(s[j].getSequenceAsString());
out.append(newline);
@@ -169,9 +191,4 @@ public class PfamFile extends AlignFile
return out.toString();
}
-
- public String print()
- {
- return print(getSeqsAsArray());
- }
}