-/*\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.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(String inStr) {\r
- super(inStr);\r
- }\r
-\r
- public FastaFile(String inFile, String type) throws IOException {\r
- super(inFile, type);\r
- }\r
-\r
- public void parse() throws IOException {\r
- String id = "";\r
- StringBuffer seq = new StringBuffer();\r
- int count = 0;\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(), sstart, send));\r
- } else {\r
- seqs.addElement(new Sequence(id,\r
- seq.toString(), 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
- if (count > 0) {\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(),\r
- sstart, send));\r
- } else {\r
- seqs.addElement(new Sequence(id, seq.toString().toUpperCase(),\r
- 1, seq.length()));\r
- }\r
- }\r
- }\r
-\r
- public static String print(SequenceI[] s) {\r
- return print(s, 72);\r
- }\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,\r
- boolean displayId) {\r
- StringBuffer out = new StringBuffer();\r
- int i = 0;\r
-\r
- while ((i < s.length) && (s[i] != null)) {\r
- String seq = "";\r
-\r
- if (gaps) {\r
- seq = s[i].getSequence();\r
- } else {\r
- seq = AlignSeq.extractGaps("-. ", s[i].getSequence());\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
- 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
- }\r
- }\r
-\r
- i++;\r
- }\r
-\r
- return out.toString();\r
- }\r
-\r
- public String print() {\r
- return print(getSeqsAsArray());\r
- }\r
-}\r
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1)
+ * Copyright (C) 2014 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.
+ *
+ * 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 <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.io;
+
+import java.io.*;
+
+import jalview.datamodel.*;
+
+/**
+ * DOCUMENT ME!
+ *
+ * @author $author$
+ * @version $Revision$
+ */
+public class FastaFile extends AlignFile
+{
+ /**
+ * Length of a sequence line
+ */
+ int len = 72;
+
+ StringBuffer out;
+
+ /**
+ * Creates a new FastaFile object.
+ */
+ public FastaFile()
+ {
+ }
+
+ /**
+ * Creates a new FastaFile object.
+ *
+ * @param inFile
+ * DOCUMENT ME!
+ * @param type
+ * DOCUMENT ME!
+ *
+ * @throws IOException
+ * DOCUMENT ME!
+ */
+ public FastaFile(String inFile, String type) throws IOException
+ {
+ super(inFile, type);
+ }
+
+ public FastaFile(FileParse source) throws IOException
+ {
+ super(source);
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @throws IOException
+ * DOCUMENT ME!
+ */
+ public void parse() throws IOException
+ {
+ StringBuffer sb = new StringBuffer();
+ boolean firstLine = true;
+
+ String line,uline;
+ Sequence seq = null;
+
+ boolean annotation = false;
+
+ while ((uline = nextLine()) != null)
+ {
+ line = uline.trim();
+ if (line.length() > 0)
+ {
+ if (line.charAt(0) == '>')
+ {
+ if (line.startsWith(">#_"))
+ {
+ if (annotation)
+ {
+ annotations.addElement(makeAnnotation(seq, sb));
+ }
+ }
+ else
+ {
+ annotation = false;
+ }
+
+ if (!firstLine)
+ {
+ seq.setSequence(sb.toString());
+
+ if (!annotation)
+ {
+ seqs.addElement(seq);
+ }
+ }
+
+ seq = parseId(line.substring(1));
+ firstLine = false;
+
+ sb = new StringBuffer();
+
+ if (line.startsWith(">#_"))
+ {
+ annotation = true;
+ }
+ }
+ else
+ {
+ sb.append(annotation ? uline : line);
+ }
+ }
+ }
+
+ if (annotation)
+ {
+ annotations.addElement(makeAnnotation(seq, sb));
+ }
+
+ else if (!firstLine)
+ {
+ seq.setSequence(sb.toString());
+ seqs.addElement(seq);
+ }
+ }
+ private AlignmentAnnotation makeAnnotation(SequenceI seq, StringBuffer sb)
+ {
+ Annotation[] anots = new Annotation[sb.length()];
+ char cb;
+ for (int i=0;i<anots.length;i++)
+ {
+ char cn = sb.charAt(i);
+ if (cn != ' ')
+ {
+ anots[i] = new Annotation(""+cn, null,
+ ' ', Float.NaN);
+ }
+ }
+ AlignmentAnnotation aa = new AlignmentAnnotation(seq.getName()
+ .substring(2), seq.getDescription(), anots);
+ return aa;
+ }
+ /**
+ * called by AppletFormatAdapter to generate an annotated alignment, rather
+ * than bare sequences.
+ *
+ * @param al
+ */
+ public void addAnnotations(Alignment al)
+ {
+ addProperties(al);
+ for (int i = 0; i < annotations.size(); i++)
+ {
+ AlignmentAnnotation aa = (AlignmentAnnotation) annotations
+ .elementAt(i);
+ aa.setPadGaps(true, al.getGapCharacter());
+ al.addAnnotation(aa);
+ }
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @param s
+ * DOCUMENT ME!
+ * @param len
+ * DOCUMENT ME!
+ * @param gaps
+ * DOCUMENT ME!
+ * @param displayId
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public String print(SequenceI[] s)
+ {
+ out = new StringBuffer();
+ int i = 0;
+
+ while ((i < s.length) && (s[i] != null))
+ {
+ out.append(">" + printId(s[i]));
+ if (s[i].getDescription() != null)
+ {
+ out.append(" " + s[i].getDescription());
+ }
+
+ out.append(newline);
+
+ int nochunks = (s[i].getLength() / len) + 1;
+
+ for (int j = 0; j < nochunks; j++)
+ {
+ int start = j * len;
+ int end = start + len;
+
+ if (end < s[i].getLength())
+ {
+ out.append(s[i].getSequenceAsString(start, end) + newline);
+ }
+ else if (start < s[i].getLength())
+ {
+ out.append(s[i].getSequenceAsString(start, s[i].getLength())
+ + newline);
+ }
+ }
+
+ i++;
+ }
+
+ return out.toString();
+ }
+
+ /**
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public String print()
+ {
+ return print(getSeqsAsArray());
+ }
+}