+/*\r
+* Jalview - A Sequence Alignment Editor and Viewer\r
+* Copyright (C) 2005 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.analysis.*;\r
\r
+import jalview.datamodel.*;\r
+\r
import java.io.*;\r
+\r
import java.util.*;\r
\r
+\r
public class FastaFile extends AlignFile {\r
+ public FastaFile() {\r
+ }\r
\r
- public FastaFile()\r
- {}\r
+ public FastaFile(String inStr) {\r
+ super(inStr);\r
+ }\r
\r
- public FastaFile(String inStr) {\r
- super(inStr);\r
- }\r
+ public FastaFile(String inFile, String type) throws IOException {\r
+ super(inFile, type);\r
+ }\r
\r
- public FastaFile(String inFile, String type) throws IOException {\r
- super(inFile,type);\r
- }\r
+ public void parse() throws IOException {\r
+ String id = "";\r
+ StringBuffer seq = new StringBuffer();\r
+ int count = 0;\r
+ boolean flag = false;\r
+\r
+ int sstart = 0;\r
+ int send = 0;\r
+\r
+ String line;\r
+\r
+ while ((line = nextLine()) != null) {\r
+ if (line.length() > 0) {\r
+ // Do we have an id line?\r
+ // JBPNote - this code needs to be standardised to EBI/whatever for the\r
+ // >dbref/dbref/dbref|refid1|refid2|refid3 'human-readable' style of naming (should it really exist)\r
+\r
+ if (line.substring(0, 1).equals(">")) {\r
+ if (count != 0) {\r
+ if (sstart != 0) {\r
+ seqs.addElement(new Sequence(id,\r
+ seq.toString().toUpperCase(), sstart, send));\r
+ } else {\r
+ seqs.addElement(new Sequence(id,\r
+ seq.toString().toUpperCase(), 1,\r
+ seq.length()));\r
+ }\r
+ }\r
+\r
+ count++;\r
+\r
+ StringTokenizer str = new StringTokenizer(line, " ");\r
+\r
+ id = str.nextToken();\r
+ id = id.substring(1);\r
+\r
+ com.stevesoft.pat.Regex dbId = new com.stevesoft.pat.Regex(\r
+ "[A-Za-z-]+/?[A-Za-z-]+\\|(\\w+)\\|(.+)");\r
+ // JBPNote At the moment - we don't get rid of the friendly names but this\r
+ // behaviour is probably wrong in the long run.\r
+ if (dbId.search(id)) {\r
+ String dbid = dbId.stringMatched(1);\r
+ String idname = dbId.stringMatched(2);\r
+ if ( (idname.length() > 0) &&\r
+ (idname.indexOf("_") > -1)) {\r
+ id = idname; // use the friendly name - apparently no dbid\r
+ } else\r
+ if (dbid.length()>1) {\r
+ id = dbid; // ignore the friendly name - we lose uniprot accession ID otherwise\r
+ }\r
+ }\r
+\r
+ if (id.indexOf("/") > 0) {\r
+ StringTokenizer st = new StringTokenizer(id, "/");\r
+\r
+ if (st.countTokens() == 2) {\r
+ id = st.nextToken();\r
+\r
+ String tmp = st.nextToken();\r
+\r
+ st = new StringTokenizer(tmp, "-");\r
+\r
+ if (st.countTokens() == 2) {\r
+ sstart = Integer.valueOf(st.nextToken())\r
+ .intValue();\r
+ send = Integer.valueOf(st.nextToken()).intValue();\r
+ }\r
+ }\r
+ }\r
+\r
+ seq = new StringBuffer();\r
+ } else {\r
+ seq = seq.append(line);\r
+ }\r
+ }\r
+ }\r
\r
- public void parse() throws IOException\r
- {\r
+ if (count > 0) {\r
+ if (!isValidProteinSequence(seq.toString().toUpperCase())) {\r
+ throw new IOException("Invalid protein sequence");\r
+ }\r
\r
- String id = "";\r
- StringBuffer seq = new StringBuffer();\r
- int count = 0;\r
- boolean flag = false;\r
+ if (sstart != 0) {\r
+ seqs.addElement(new Sequence(id, seq.toString().toUpperCase(),\r
+ sstart, send));\r
+ } else {\r
+ seqs.addElement(new Sequence(id, seq.toString().toUpperCase(),\r
+ 1, seq.length()));\r
+ }\r
+ }\r
+ }\r
\r
- int sstart = 0;\r
- int send = 0;\r
+ public static String print(SequenceI[] s) {\r
+ return print(s, 72);\r
+ }\r
\r
- String line;\r
+ public static String print(SequenceI[] s, int len) {\r
+ return print(s, len, true);\r
+ }\r
\r
- while ((line = nextLine()) != null) {\r
+ public static String print(SequenceI[] s, int len, boolean gaps) {\r
+ return print(s, len, gaps, true);\r
+ }\r
\r
- if (line.length() > 0) {\r
+ public static String print(SequenceI[] s, int len, boolean gaps,\r
+ boolean displayId) {\r
+ StringBuffer out = new StringBuffer();\r
+ int i = 0;\r
\r
- // Do we have an id line?\r
+ while ((i < s.length) && (s[i] != null)) {\r
+ String seq = "";\r
\r
- if (line.substring(0,1).equals(">")) {\r
+ if (gaps) {\r
+ seq = s[i].getSequence();\r
+ } else {\r
+ seq = AlignSeq.extractGaps("-. ", s[i].getSequence());\r
+ }\r
\r
- if (count != 0) {\r
- if (sstart != 0) {\r
- seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),sstart,send));\r
- } else {\r
- seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),1,seq.length()));\r
- }\r
- }\r
+ // used to always put this here: + "/" + s[i].getStart() + "-" + s[i].getEnd() +\r
+ out.append(">" +\r
+ ((displayId) ? s[i].getDisplayId() : s[i].getName()) + "\n");\r
\r
- count++;\r
+ int nochunks = (seq.length() / len) + 1;\r
\r
- StringTokenizer str = new StringTokenizer(line," ");\r
+ for (int j = 0; j < nochunks; j++) {\r
+ int start = j * len;\r
+ int end = start + len;\r
\r
- id = str.nextToken();\r
- id = id.substring(1);\r
- if(id.indexOf("UniProt/Swiss-Prot")>-1)\r
- {\r
- id = id.substring(id.indexOf("UniProt/Swiss-Prot|") + 19);\r
- if(id.indexOf("|")>-1)\r
- id = id.substring(id.indexOf("|") + 1);\r
+ if (end < seq.length()) {\r
+ out.append(seq.substring(start, end) + "\n");\r
+ } else if (start < seq.length()) {\r
+ out.append(seq.substring(start) + "\n");\r
+ }\r
}\r
\r
- if (id.indexOf("/") > 0 ) {\r
-\r
- StringTokenizer st = new StringTokenizer(id,"/");\r
- if (st.countTokens() == 2) {\r
- id = st.nextToken();\r
- String tmp = st.nextToken();\r
-\r
- st = new StringTokenizer(tmp,"-");\r
-\r
- if (st.countTokens() == 2) {\r
- sstart = Integer.valueOf(st.nextToken()).intValue();\r
- send = Integer.valueOf(st.nextToken()).intValue();\r
- }\r
- }\r
- }\r
-\r
- seq = new StringBuffer();\r
-\r
- } else {\r
- seq = seq.append(line);\r
- }\r
- }\r
- }\r
- if (count > 0) {\r
-\r
- if(!isValidProteinSequence(seq.toString().toUpperCase()))\r
- throw new IOException("Invalid protein sequence");\r
-\r
- if (sstart != 0) {\r
- seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),sstart,send));\r
- } else {\r
- seqs.addElement(new Sequence(id,seq.toString().toUpperCase(),1,seq.length()));\r
- }\r
- }\r
-\r
- }\r
-\r
- public static String print(SequenceI[] s) {\r
- return print(s,72);\r
- }\r
- public static String print(SequenceI[] s, int len) {\r
- return print(s,len,true);\r
- }\r
-\r
- public static String print(SequenceI[] s, int len,boolean gaps) {\r
- return print(s,len,gaps,true);\r
- }\r
-\r
- public static String print(SequenceI[] s, int len,boolean gaps, boolean displayId) {\r
- StringBuffer out = new StringBuffer();\r
- int i = 0;\r
- while (i < s.length && s[i] != null) {\r
- String seq = "";\r
- if (gaps) {\r
- seq = s[i].getSequence();\r
- } else {\r
- seq = AlignSeq.extractGaps("-. ",s[i].getSequence());\r
- }\r
- // used to always put this here: + "/" + s[i].getStart() + "-" + s[i].getEnd() +\r
- out.append(">" + ((displayId) ? s[i].getDisplayId() : s[i].getName())+"\n");\r
-\r
- int nochunks = seq.length() / len + 1;\r
-\r
- for (int j = 0; j < nochunks; j++) {\r
- int start = j*len;\r
- int end = start + len;\r
-\r
- if (end < seq.length()) {\r
- out.append(seq.substring(start,end) + "\n");\r
- } else if (start < seq.length()) {\r
- out.append(seq.substring(start) + "\n");\r
+ i++;\r
}\r
- }\r
- i++;\r
+\r
+ return out.toString();\r
}\r
- return out.toString();\r
- }\r
\r
- public String print() {\r
- return print(getSeqsAsArray());\r
- }\r
+ public String print() {\r
+ return print(getSeqsAsArray());\r
+ }\r
}\r
-\r
-\r
-\r