+/*\r
+ * Jalview - A Sequence Alignment Editor and Viewer\r
+ * Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
+ *\r
+ * This program is free software; you can redistribute it and/or\r
+ * modify it under the terms of the GNU General Public License\r
+ * as published by the Free Software Foundation; either version 2\r
+ * of the License, or (at your option) any later version.\r
+ *\r
+ * This program is distributed in the hope that it will be useful,\r
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of\r
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
+ * GNU General Public License for more details.\r
+ *\r
+ * You should have received a copy of the GNU General Public License\r
+ * along with this program; if not, write to the Free Software\r
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
+ */\r
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
+import jalview.datamodel.*;\r
+import jalview.util.*;\r
\r
- Vector ids;\r
+public class ClustalFile\r
+ extends AlignFile\r
+{\r
\r
public ClustalFile()\r
- {}\r
-\r
- public ClustalFile(String inStr) {\r
- super(inStr);\r
+ {\r
}\r
\r
-\r
- public void initData() {\r
- super.initData();\r
- ids = new Vector();\r
+ public ClustalFile(String inFile, String type)\r
+ throws IOException\r
+ {\r
+ super(inFile, type);\r
}\r
\r
- public ClustalFile(String inFile, String type) throws IOException {\r
- super(inFile,type);\r
+ public void initData()\r
+ {\r
+ super.initData();\r
}\r
\r
- public void parse() {\r
- int i = 0;\r
+ public void parse() throws IOException\r
+ {\r
+ int i = 0;\r
boolean flag = false;\r
\r
- Vector headers = new Vector();\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
- tempseq.append(str.nextToken());\r
- }\r
- }\r
- }\r
- }\r
+ StringBuffer tempseq;\r
+ String line, id;\r
+ StringTokenizer str;\r
+\r
+ try\r
+ {\r
+ while ( (line = nextLine()) != null)\r
+ {\r
+ if (line.indexOf(" ") != 0)\r
+ {\r
+ str = new StringTokenizer(line, " ");\r
+\r
+ if (str.hasMoreTokens())\r
+ {\r
+ id = str.nextToken();\r
+\r
+ if (id.equalsIgnoreCase("CLUSTAL"))\r
+ {\r
+ flag = true;\r
+ }\r
+ else\r
+ {\r
+ if (flag)\r
+ {\r
+ if (seqhash.containsKey(id))\r
+ {\r
+ tempseq = (StringBuffer) seqhash.get(id);\r
+ }\r
+ else\r
+ {\r
+ tempseq = new StringBuffer();\r
+ seqhash.put(id, tempseq);\r
+ }\r
+\r
+ if (! (headers.contains(id)))\r
+ {\r
+ headers.addElement(id);\r
+ }\r
+\r
+ if (str.hasMoreTokens())\r
+ {\r
+ tempseq.append(str.nextToken());\r
+ }\r
+ }\r
+ }\r
+ }\r
+ else\r
+ flag = true;\r
+ }\r
}\r
- } catch (IOException e) {\r
+ }\r
+ catch (IOException e)\r
+ {\r
System.err.println("Exception parsing clustal file " + e);\r
- e.stacktrace();\r
+ e.printStackTrace();\r
}\r
\r
- if (flag) {\r
+ if (flag)\r
+ {\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
+ for (i = 0; i < headers.size(); i++)\r
+ {\r
+ if (seqhash.get(headers.elementAt(i)) != null)\r
+ {\r
+ if (maxLength < seqhash.get(headers.elementAt(i)).toString()\r
+ .length())\r
+ {\r
+ maxLength = seqhash.get(headers.elementAt(i)).toString()\r
+ .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
+ Sequence newSeq = parseId(headers.elementAt(i).toString());\r
+ newSeq.setSequence( seqhash.get(headers.elementAt(i).toString()).toString() );\r
\r
+ if (!isValidProteinSequence(newSeq.getSequence()))\r
+ {\r
+ throw new IOException(AppletFormatAdapter.INVALID_CHARACTERS\r
+ + " : " + newSeq.getName()\r
+ + " : " + invalidCharacter);\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
+ seqs.addElement(newSeq);\r
+ }\r
+ else\r
+ {\r
+ System.err.println(\r
+ "Clustal File Reader: Can't find sequence for " +\r
+ headers.elementAt(i));\r
}\r
}\r
}\r
-\r
}\r
\r
- public String print() {\r
+ public String print()\r
+ {\r
return print(getSeqsAsArray());\r
}\r
- public static String print(SequenceI[] s) {\r
+\r
+ public String print(SequenceI[] s)\r
+ {\r
StringBuffer out = new StringBuffer("CLUSTAL\n\n");\r
\r
int max = 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
+ while ( (i < s.length) && (s[i] != null))\r
+ {\r
+ String tmp = printId(s[i]);\r
\r
- if (s[i].getSequence().length() > max) {\r
+ if (s[i].getSequence().length() > max)\r
+ {\r
max = s[i].getSequence().length();\r
}\r
- if (tmp.length() > maxid) {\r
+\r
+ if (tmp.length() > maxid)\r
+ {\r
maxid = tmp.length();\r
}\r
+\r
i++;\r
}\r
\r
- if (maxid < 15) {\r
+ if (maxid < 15)\r
+ {\r
maxid = 15;\r
}\r
+\r
maxid++;\r
+\r
int len = 60;\r
- int nochunks = max / len + 1;\r
+ int nochunks = (max / len) + 1;\r
\r
- for (i = 0; i < nochunks; i++) {\r
+ for (i = 0; i < nochunks; i++)\r
+ {\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
+\r
+ while ( (j < s.length) && (s[j] != null))\r
+ {\r
+ out.append(new Format("%-" + maxid + "s").form( printId(s[j]) + " "));\r
+\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) + "\n");\r
- } else {\r
- if (start < s[j].getSequence().length()) {\r
- out.append(s[j].getSequence().substring(start) + "\n");\r
+ if ( (end < s[j].getSequence().length()) &&\r
+ (start < s[j].getSequence().length()))\r
+ {\r
+ out.append(s[j].getSequence().substring(start, end));\r
+ }\r
+ else\r
+ {\r
+ if (start < s[j].getSequence().length())\r
+ {\r
+ out.append(s[j].getSequence().substring(start));\r
}\r
}\r
+\r
+ out.append("\n");\r
j++;\r
}\r
- out.append("\n");\r
\r
+ out.append("\n");\r
}\r
+\r
return out.toString();\r
}\r
-\r
-\r
}\r
git://source.jalview.org / jalview.git / blobdiff