X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Futil%2FComparison.java;h=0beb45bcefca1ad9319236dac9d93bd18af68636;hb=37de9310bec3501cbc6381e0c3dcb282fcaad812;hp=cec9bc365e70a1db5e38cba02c246e277ac0442c;hpb=59d682209891099d46b960509907c79e3fb276fe;p=jalview.git

diff --git a/src/jalview/util/Comparison.java b/src/jalview/util/Comparison.java
index cec9bc3..0beb45b 100644
--- a/src/jalview/util/Comparison.java
+++ b/src/jalview/util/Comparison.java
@@ -1,34 +1,47 @@
 /*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
- * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ 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.
+ * 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/>.
+ * 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.util;
 
-import jalview.datamodel.*;
+import jalview.datamodel.SequenceI;
+
+import java.util.ArrayList;
+import java.util.List;
 
 /**
- * DOCUMENT ME!
- * 
- * @author $author$
- * @version $Revision$
+ * Assorted methods for analysing or comparing sequences.
  */
 public class Comparison
 {
-  /** DOCUMENT ME!! */
-  public static final String GapChars = " .-";
+  private static final int EIGHTY_FIVE = 85;
+
+  private static final int TO_UPPER_CASE = 'a' - 'A';
+
+  private static final char GAP_SPACE = ' ';
+
+  private static final char GAP_DOT = '.';
+
+  private static final char GAP_DASH = '-';
+
+  public static final String GapChars = new String(new char[] { GAP_SPACE,
+      GAP_DOT, GAP_DASH });
 
   /**
    * DOCUMENT ME!
@@ -66,12 +79,12 @@ public class Comparison
     int ilen = si.length() - 1;
     int jlen = sj.length() - 1;
 
-    while (jalview.util.Comparison.isGap(si.charAt(start + ilen)))
+    while (Comparison.isGap(si.charAt(start + ilen)))
     {
       ilen--;
     }
 
-    while (jalview.util.Comparison.isGap(sj.charAt(start + jlen)))
+    while (Comparison.isGap(sj.charAt(start + jlen)))
     {
       jlen--;
     }
@@ -222,47 +235,99 @@ public class Comparison
   }
 
   /**
-   * DOCUMENT ME!
+   * Answers true if the supplied character is a recognised gap character, else
+   * false. Currently hard-coded to recognise '-', '-' or ' ' (hyphen / dot /
+   * space).
    * 
    * @param c
-   *          DOCUMENT ME!
    * 
-   * @return DOCUMENT ME!
+   * @return
    */
   public static final boolean isGap(char c)
   {
-    return (c == '-' || c == '.' || c == ' ') ? true : false;
+    return (c == GAP_DASH || c == GAP_DOT || c == GAP_SPACE) ? true : false;
   }
 
+  /**
+   * Overloaded method signature to test whether a single sequence is nucleotide
+   * (that is, more than 85% CGTA)
+   * 
+   * @param seq
+   * @return
+   */
+  public static final boolean isNucleotide(SequenceI seq)
+  {
+    return isNucleotide(new SequenceI[] { seq });
+  }
+
+  /**
+   * Answers true if more than 85% of the sequence residues (ignoring gaps) are
+   * A, G, C, T or U, else false. This is just a heuristic guess and may give a
+   * wrong answer (as AGCT are also amino acid codes).
+   * 
+   * @param seqs
+   * @return
+   */
   public static final boolean isNucleotide(SequenceI[] seqs)
   {
-    int i = 0, iSize = seqs.length, j, jSize;
-    float nt = 0, aa = 0;
-    char c;
-    while (i < iSize)
+    if (seqs == null)
     {
-      jSize = seqs[i].getLength();
-      for (j = 0; j < jSize; j++)
+      return false;
+    }
+    char[][] letters = new char[seqs.length][];
+    for (int i = 0; i < seqs.length; i++)
+    {
+      if (seqs[i] != null)
       {
-        c = seqs[i].getCharAt(j);
-        if ('a' <= c && c <= 'z')
+        char[] sequence = seqs[i].getSequence();
+        if (sequence != null)
         {
-          c -= ('a' - 'A');
+          letters[i] = sequence;
         }
+      }
+    }
+
+    return areNucleotide(letters);
+  }
 
-        if (c == 'A' || c == 'G' || c == 'C' || c == 'T' || c == 'U')
+  /**
+   * Answers true if more than 85% of the sequence residues (ignoring gaps) are
+   * A, G, C, T or U, else false. This is just a heuristic guess and may give a
+   * wrong answer (as AGCT are also amino acid codes).
+   * 
+   * @param letters
+   * @return
+   */
+  static final boolean areNucleotide(char[][] letters)
+  {
+    int ntCount = 0;
+    int aaCount = 0;
+    for (char[] seq : letters)
+    {
+      if (seq == null)
+      {
+        continue;
+      }
+      // TODO could possibly make an informed guess just from the first sequence
+      // to save a lengthy calculation
+      for (char c : seq)
+      {
+        if (isNucleotide(c))
         {
-          nt++;
+          ntCount++;
         }
-        else if (!jalview.util.Comparison.isGap(seqs[i].getCharAt(j)))
+        else if (!isGap(c))
         {
-          aa++;
+          aaCount++;
         }
       }
-      i++;
     }
 
-    if ((nt / (nt + aa)) > 0.85f)
+    /*
+     * Check for nucleotide count > 85% of total count (in a form that evades
+     * int / float conversion or divide by zero).
+     */
+    if (ntCount * 100 > EIGHTY_FIVE * (ntCount + aaCount))
     {
       return true;
     }
@@ -272,4 +337,82 @@ public class Comparison
     }
 
   }
+
+  /**
+   * Answers true if the character is one of aAcCgGtTuU
+   * 
+   * @param c
+   * @return
+   */
+  public static boolean isNucleotide(char c)
+  {
+    if ('a' <= c && c <= 'z')
+    {
+      c -= TO_UPPER_CASE;
+    }
+
+    switch (c)
+    {
+    case 'A':
+    case 'C':
+    case 'G':
+    case 'T':
+    case 'U':
+      return true;
+    }
+    return false;
+  }
+
+  /**
+   * Answers true if every character in the string is one of aAcCgGtTuU, or
+   * (optionally) a gap character (dot, dash, space), else false
+   * 
+   * @param s
+   * @param allowGaps
+   * @return
+   */
+  public static boolean isNucleotideSequence(String s, boolean allowGaps)
+  {
+    if (s == null)
+    {
+      return false;
+    }
+    for (int i = 0; i < s.length(); i++)
+    {
+      char c = s.charAt(i);
+      if (!isNucleotide(c))
+      {
+        if (!allowGaps || !isGap(c))
+        {
+          return false;
+        }
+      }
+    }
+    return true;
+  }
+
+  /**
+   * Convenience overload of isNucleotide
+   * 
+   * @param seqs
+   * @return
+   */
+  public static boolean isNucleotide(SequenceI[][] seqs)
+  {
+    if (seqs == null)
+    {
+      return false;
+    }
+    List<SequenceI> flattened = new ArrayList<SequenceI>();
+    for (SequenceI[] ss : seqs)
+    {
+      for (SequenceI s : ss)
+      {
+        flattened.add(s);
+      }
+    }
+    final SequenceI[] oneDArray = flattened.toArray(new SequenceI[flattened
+            .size()]);
+    return isNucleotide(oneDArray);
+  }
 }