/*\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
-\r
+ * Jalview - A Sequence Alignment Editor and Viewer\r
+ * Copyright (C) 2007 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 java.io.*;\r
-import java.util.*;\r
\r
-public class FastaFile extends AlignFile {\r
+import jalview.datamodel.*;\r
\r
+/**\r
+ * DOCUMENT ME!\r
+ *\r
+ * @author $author$\r
+ * @version $Revision$\r
+ */\r
+public class FastaFile\r
+ extends AlignFile\r
+{\r
+ /**\r
+ * Length of a sequence line\r
+ */\r
+ int len = 72;\r
+\r
+ StringBuffer out;\r
+\r
+ /**\r
+ * Creates a new FastaFile object.\r
+ */\r
public FastaFile()\r
- {}\r
-\r
- public FastaFile(String inStr) {\r
- super(inStr);\r
+ {\r
}\r
\r
- public FastaFile(String inFile, String type) throws IOException {\r
- super(inFile,type);\r
+ /**\r
+ * Creates a new FastaFile object.\r
+ *\r
+ * @param inFile DOCUMENT ME!\r
+ * @param type DOCUMENT ME!\r
+ *\r
+ * @throws IOException DOCUMENT ME!\r
+ */\r
+ public FastaFile(String inFile, String type)\r
+ throws IOException\r
+ {\r
+ super(inFile, type);\r
}\r
\r
- public void parse() throws IOException\r
+ /**\r
+ * DOCUMENT ME!\r
+ *\r
+ * @throws IOException DOCUMENT ME!\r
+ */\r
+ public void parse()\r
+ throws IOException\r
{\r
-\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
+ StringBuffer sb = new StringBuffer();\r
+ boolean firstLine = true;\r
\r
String line;\r
-\r
- while ((line = nextLine()) != null) {\r
-\r
- if (line.length() > 0) {\r
-\r
- // Do we have an id line?\r
-\r
- if (line.substring(0,1).equals(">")) {\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
-\r
- count++;\r
-\r
- StringTokenizer str = new StringTokenizer(line," ");\r
-\r
- id = str.nextToken();\r
- id = id.substring(1);\r
- com.stevesoft.pat.Regex dbId = new com.stevesoft.pat.Regex("[A-Za-z-]+/[A-Za-z-]+\\|(\\w+)\\|(.+)");\r
- if (dbId.search(id))\r
- {\r
- String dbid = dbId.stringMatched(1);\r
- String idname = dbId.stringMatched(2);\r
- if (idname.length()>0 && idname.indexOf("_") > -1)\r
- {\r
- id = idname; // just use friendly name // JBPNote: we may lose uniprot standardised ID here.\r
- }\r
- else\r
- {\r
- id = dbid; // use dbid to ensure sensible queries\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
+ Sequence seq = null;\r
+\r
+ boolean annotation = false;\r
+\r
+ while ( (line = nextLine()) != null)\r
+ {\r
+ line = line.trim();\r
+ if (line.length() > 0)\r
+ {\r
+ if (line.charAt(0) == '>')\r
+ {\r
+ if (line.startsWith(">#_"))\r
+ {\r
+ if (annotation)\r
+ {\r
+ Annotation[] anots = new Annotation[sb.length()];\r
+ String anotString = sb.toString();\r
+ for (int i = 0; i < sb.length(); i++)\r
+ {\r
+ anots[i] = new Annotation(anotString.substring(i, i + 1),\r
+ null,\r
+ ' ', 0);\r
+ }\r
+ AlignmentAnnotation aa = new AlignmentAnnotation(\r
+ seq.getName().substring(2), seq.getDescription(),\r
+ anots);\r
+\r
+ annotations.addElement(aa);\r
+ }\r
+ }\r
+ else\r
+ {\r
+ annotation = false;\r
+ }\r
+\r
+ if (!firstLine)\r
+ {\r
+ seq.setSequence(sb.toString());\r
+\r
+ if (!annotation)\r
+ {\r
+ seqs.addElement(seq);\r
+ }\r
+ }\r
+\r
+ seq = parseId(line.substring(1));\r
+ firstLine = false;\r
+\r
+ sb = new StringBuffer();\r
+\r
+ if (line.startsWith(">#_"))\r
+ {\r
+ annotation = true;\r
+ }\r
+ }\r
+ else\r
+ {\r
+ sb.append(line);\r
+ }\r
}\r
- if (count > 0) {\r
-\r
- if(!isValidProteinSequence(seq.toString().toUpperCase()))\r
- throw new IOException("Invalid protein sequence");\r
+ }\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
+ if (annotation)\r
+ {\r
+ Annotation[] anots = new Annotation[sb.length()];\r
+ String anotString = sb.toString();\r
+ for (int i = 0; i < sb.length(); i++)\r
+ {\r
+ anots[i] = new Annotation(anotString.substring(i, i + 1),\r
+ null,\r
+ ' ', 0);\r
}\r
+ AlignmentAnnotation aa = new AlignmentAnnotation(\r
+ seq.getName().substring(2), seq.getDescription(),\r
+ anots);\r
\r
- }\r
+ annotations.addElement(aa);\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
+ else if (!firstLine)\r
+ {\r
+ seq.setSequence(sb.toString());\r
+ seqs.addElement(seq);\r
+ }\r
}\r
\r
- public static String print(SequenceI[] s, int len,boolean gaps) {\r
- return print(s,len,gaps,true);\r
+ /**\r
+ * called by AppletFormatAdapter to generate\r
+ * an annotated alignment, rather than bare\r
+ * sequences.\r
+ * @param al\r
+ */\r
+ public void addAnnotations(Alignment al)\r
+ {\r
+ addProperties(al);\r
+ for (int i = 0; i < annotations.size(); i++)\r
+ {\r
+ AlignmentAnnotation aa = (AlignmentAnnotation) annotations.elementAt(i);\r
+ aa.setPadGaps(true, al.getGapCharacter());\r
+ al.addAnnotation( aa );\r
+ }\r
}\r
\r
- public static String print(SequenceI[] s, int len,boolean gaps, boolean displayId) {\r
- StringBuffer out = new StringBuffer();\r
+\r
+ /**\r
+ * DOCUMENT ME!\r
+ *\r
+ * @param s DOCUMENT ME!\r
+ * @param len DOCUMENT ME!\r
+ * @param gaps DOCUMENT ME!\r
+ * @param displayId DOCUMENT ME!\r
+ *\r
+ * @return DOCUMENT ME!\r
+ */\r
+ public String print(SequenceI[] s)\r
+ {\r
+ 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
+ while ( (i < s.length) && (s[i] != null))\r
+ {\r
+ out.append(">" + printId(s[i]));\r
+ if (s[i].getDescription() != null)\r
+ {\r
+ out.append(" " + s[i].getDescription());\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
+ out.append("\n");\r
+\r
+ int nochunks = (s[i].getLength() / len) + 1;\r
\r
- for (int j = 0; j < nochunks; j++) {\r
- int start = j*len;\r
+ for (int j = 0; j < nochunks; j++)\r
+ {\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
+ if (end < s[i].getLength())\r
+ {\r
+ out.append(s[i].getSequenceAsString(start, end) + "\n");\r
+ }\r
+ else if (start < s[i].getLength())\r
+ {\r
+ out.append(s[i].getSequenceAsString(start, s[i].getLength()) + "\n");\r
}\r
}\r
+\r
i++;\r
}\r
+\r
return out.toString();\r
}\r
\r
- public String print() {\r
+ /**\r
+ * DOCUMENT ME!\r
+ *\r
+ * @return DOCUMENT ME!\r
+ */\r
+ public String print()\r
+ {\r
return print(getSeqsAsArray());\r
}\r
}\r
-\r
-\r
-\r