/*\r
* Jalview - A Sequence Alignment Editor and Viewer\r
- * Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\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
import java.io.*;\r
import java.util.*;\r
\r
-import jalview.analysis.*;\r
import jalview.datamodel.*;\r
\r
public class PIRFile\r
extends AlignFile\r
{\r
+ public static boolean useModellerOutput = false;\r
+\r
Vector words = new Vector(); //Stores the words in a line after splitting\r
\r
public PIRFile()\r
{\r
}\r
\r
- public PIRFile(String inStr)\r
- {\r
- super(inStr);\r
- }\r
-\r
public PIRFile(String inFile, String type)\r
throws IOException\r
{\r
super(inFile, type);\r
}\r
\r
- public void parse()\r
+ public void parse() throws IOException\r
{\r
- try\r
- {\r
- String id;\r
- String start;\r
- String end;\r
StringBuffer sequence;\r
String line = null;\r
+ ModellerDescription md;\r
\r
while ( (line = nextLine()) != null)\r
{\r
- if(line.length()==0)\r
+ if (line.length() == 0)\r
{\r
//System.out.println("blank line");\r
continue;\r
}\r
-\r
- id = "No id";\r
- start = "1";\r
- end = "-1";\r
-\r
- try\r
+ if (line.indexOf("C;") == 0 || line.indexOf("#") == 0)\r
{\r
- int slashIndex = line.indexOf("/");\r
- if(slashIndex!=-1)\r
- {\r
- id = line.substring(line.indexOf(";") + 1, line.indexOf("/"));\r
- line = line.substring(line.indexOf("/") + 1);\r
- start = line.substring(0, line.indexOf("-"));\r
- end = line.substring(line.indexOf("-") + 1);\r
- }\r
- else\r
- {\r
- id = line.substring(line.indexOf(";")+1);\r
- }\r
+ continue;\r
}\r
- catch (Exception ex)\r
- { }// Default id, start and end unchanged\r
+ Sequence newSeq = parseId(line.substring(line.indexOf(";") + 1));\r
\r
sequence = new StringBuffer();\r
\r
- line = nextLine(); // this is the title line\r
+ newSeq.setDescription(nextLine()); // this is the title line\r
\r
boolean starFound = false;\r
\r
}\r
}\r
\r
- if(sequence.length()>0)\r
+ if (sequence.length() > 0)\r
{\r
sequence.setLength(sequence.length() - 1);\r
+ newSeq.setSequence(sequence.toString());\r
+ if (!isValidProteinSequence(newSeq.getSequence()))\r
+ {\r
+ throw new IOException(AppletFormatAdapter.INVALID_CHARACTERS\r
+ +" : "+ newSeq.getName()\r
+ +" : "+invalidCharacter);\r
+ }\r
\r
- Sequence newSeq = new Sequence(id, sequence.toString(),\r
- Integer.parseInt(start),\r
- Integer.parseInt(end));\r
seqs.addElement(newSeq);\r
+\r
+ md = new ModellerDescription(newSeq.\r
+ getDescription());\r
+ md.updateSequenceI(newSeq);\r
}\r
}\r
- }\r
- catch (Exception ex)\r
- {\r
- ex.printStackTrace();\r
- }\r
}\r
\r
public String print()\r
return print(getSeqsAsArray());\r
}\r
\r
- public static String print(SequenceI[] s)\r
- {\r
- return print(s, 72, true);\r
- }\r
-\r
- public static String print(SequenceI[] s, int len)\r
- {\r
- return print(s, len, true);\r
- }\r
-\r
- public static String print(SequenceI[] s, int len, boolean gaps)\r
+ public String print(SequenceI[] s)\r
{\r
+ boolean is_NA = jalview.util.Comparison.isNucleotide(s);\r
+ int len = 72;\r
StringBuffer out = new StringBuffer();\r
int i = 0;\r
+ ModellerDescription md;\r
\r
while ( (i < s.length) && (s[i] != null))\r
{\r
- String seq = "";\r
+ String seq = s[i].getSequence();\r
+ seq = seq + "*";\r
\r
- if (gaps)\r
+\r
+ if (is_NA)\r
{\r
- seq = s[i].getSequence() + "*";\r
+ // modeller doesn't really do nucleotides, so we don't do anything fancy\r
+ // Official tags area as follows, for now we'll use P1 and DL\r
+ // Protein (complete) P1\r
+ // Protein (fragment) F1\r
+ // DNA (linear) Dl\r
+ // DNA (circular) DC\r
+ // RNA (linear) RL\r
+ // RNA (circular) RC\r
+ // tRNA N3\r
+ // other functional RNA N1\r
+\r
+ out.append(">N1;" + s[i].getName() + "\n");\r
+ if (s[i].getDescription() == null)\r
+ {\r
+ out.append(s[i].getName() + " " +\r
+ (s[i].getEnd() - s[i].getStart() + 1));\r
+ out.append(is_NA ? " bases\n" : " residues\n");\r
+ }\r
+ else\r
+ {\r
+ out.append(s[i].getDescription()+"\n");\r
+ }\r
}\r
else\r
{\r
- seq = AlignSeq.extractGaps(s[i].getSequence(), "-");\r
- seq = AlignSeq.extractGaps(seq, ".");\r
- seq = AlignSeq.extractGaps(seq, " ");\r
- seq = seq + "*";\r
- }\r
-\r
- out.append(">P1;" + s[i].getName() + "/" + s[i].getStart() + "-" +\r
- s[i].getEnd() + "\n");\r
- out.append(" Dummy title\n");\r
\r
+ if(useModellerOutput)\r
+ {\r
+ out.append(">P1;" + s[i].getName() + "\n");\r
+ md = new ModellerDescription(s[i]);\r
+ out.append(md.getDescriptionLine() + "\n");\r
+ }\r
+ else\r
+ {\r
+ out.append(">P1;" + printId(s[i]) + "\n");\r
+ if (s[i].getDescription() != null)\r
+ out.append(s[i].getDescription() + "\n");\r
+ else\r
+ out.append(s[i].getName() + " "\r
+ + (s[i].getEnd() - s[i].getStart() + 1)\r
+ + " residues\n");\r
+ }\r
+ }\r
int nochunks = (seq.length() / len) + 1;\r
\r
for (int j = 0; j < nochunks; j++)\r