refactoring org to uk

[vamsas.git] / src / uk / ac / vamsas / objects / utils / SeqSet.java

diff --git a/src/uk/ac/vamsas/objects/utils/SeqSet.java b/src/uk/ac/vamsas/objects/utils/SeqSet.java
new file mode 100644 (file)
index 0000000..e75bd54
--- /dev/null
+++ b/src/uk/ac/vamsas/objects/utils/SeqSet.java
@@ -0,0 +1,138 @@
+/*
+ * Created on 17-May-2005
+ * Slurped into VamsasClient object set on 12th Jan 2006
+ *
+ * TODO To change the template for this generated file go to
+ * Window - Preferences - Java - Code Style - Code Templates
+ */
+package uk.ac.vamsas.objects.utils;
+
+import java.io.BufferedReader;
+import java.io.BufferedWriter;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.io.OutputStream;
+import java.io.OutputStreamWriter;
+import java.util.Hashtable;
+import java.util.Vector;
+import java.util.regex.Pattern;
+
+import uk.ac.vamsas.objects.core.*;
+
+/**
+ * @author jimp
+ *
+ * TODO To change the template for this generated type comment go to
+ * Window - Preferences - Java - Code Style - Code Templates
+ */
+public class SeqSet {
+  
+  public static void write_Fasta(OutputStream os, SequenceType[] seqs) throws IOException {
+    write_Fasta(os, seqs, 80);
+  }
+  
+  public static void write_Fasta(OutputStream os, SequenceType[] seqs, boolean width80) throws IOException {
+    write_Fasta(os, seqs, (width80) ? 80 : 0);
+  }
+  
+  public static void write_Fasta(OutputStream os, SequenceType[] seqs, int width) throws IOException {
+    int i, nseq = seqs.length;
+    BufferedWriter fasta_out = new BufferedWriter(new OutputStreamWriter(os));
+    System.err.println("NOT FULLY IMPLEMENTED!"); // TODO: Finish adapting this method
+    for (i=0; i<nseq; i++) {
+      fasta_out.write(">"+seqs[i].getName()+"\n");
+      if (width<=0) {
+        fasta_out.write(seqs[i].getSequence()+"\n");
+      } else {
+        // TODO: adapt to SymbolDictionary labelwidths
+        String tempseq = seqs[i].getSequence();
+        int j=0, k=tempseq.length();
+        while (j<k) {
+          int d = k-j;
+          if (d>=width) {
+            fasta_out.write(tempseq, j, width);
+          } else {
+            fasta_out.write(tempseq, j, d);
+          }
+          fasta_out.write("\n");
+          j+=width;
+        }                          
+      }
+    }
+    fasta_out.flush();
+  }
+  /**
+   * TODO: introduce a dictionary parameter for qualified sequence symbols
+   * Reads a sequence set from a stream - will only read prescribed amino acid
+   * symbols. 
+   * @param os
+   * @return
+   * @throws IOException
+   */  
+  public static Sequence[] read_SeqFasta(InputStream os) throws IOException {
+    Vector seqs = new Vector();
+    int nseq = 0;
+    BufferedReader infasta = new BufferedReader(new InputStreamReader(os));
+    System.err.println("NOT FULLY IMPLEMENTED!"); // TODO: Finish adapting this method
+    // TODO: decide on return type - SequenceType is a partly complete vamsas Vobject - either for a dataset or alignment sequence
+    // so could go in either!
+    String line;
+    Sequence seq = null;
+    Pattern aaMatch = Pattern.compile("[ARNDCQEGHILKMFPSTUWYV]", Pattern.CASE_INSENSITIVE);
+    String sname = "", seqstr=null;
+    do {
+      line = infasta.readLine();
+      if (line==null || line.startsWith(">")) {
+        if (seqstr!=null) 
+          seqs.add((Object) Seq.newSequence(sname.substring(1), seqstr, SymbolDictionary.STANDARD_AA, 0,0));
+        sname = line; // remove >
+        seqstr="";
+      } else { 
+        String subseq = Pattern.compile("//s+").matcher(line).replaceAll("");
+        seqstr += subseq;                      
+      }
+    } while (line!=null);
+    nseq = seqs.size();
+    if (nseq>0) {
+      // TODO:POSS: should really return a sequence if there's only one in the file.
+      Sequence[] seqset = new Sequence[nseq];
+      for (int i=0; i<nseq; i++) {
+        seqset[i] = (Sequence) seqs.elementAt(i);
+      }
+      return seqset;
+    }
+    
+    return null;
+  }
+  
+  public static Hashtable uniquify(SequenceType[] sequences) {
+    System.err.println("NOT FULLY IMPLEMENTED!"); // TODO: Finish adapting this method
+    // TODO: do we need this with vamsas sequences ?
+    // Generate a safely named sequence set and a hash to recover the sequence names
+    Hashtable map = new Hashtable();
+    for (int i = 0; i < sequences.length; i++) {
+      String safename = new String("Sequence" + i);
+      map.put(safename, sequences[i].getName());
+      sequences[i].setName(safename);
+    }
+    return map;
+  }
+  
+  public static boolean deuniquify(Hashtable map, SequenceType[] sequences) {
+    System.err.println("NOT FULLY IMPLEMENTED!"); // TODO: Finish adapting this method
+    // TODO: do we need this with vamsas sequences ?
+    // recover unsafe sequence names for a sequence set
+    boolean allfound = true;
+    for (int i = 0; i < sequences.length; i++) {
+      if (map.containsKey(sequences[i].getName())) {
+        String unsafename = (String) map.get(sequences[i].getName());
+        sequences[i].setName(unsafename);
+      } else {
+        allfound = false;
+      }
+    }
+    return allfound;
+  }
+  
+}