Merge branch 'develop' into update_212_Dec_merge_with_21125_chamges

[jalview.git] / src / jalview / datamodel / ResidueCount.java

diff --git a/src/jalview/datamodel/ResidueCount.java b/src/jalview/datamodel/ResidueCount.java
index 0d0348c..4ca4c80 100644 (file)
--- a/src/jalview/datamodel/ResidueCount.java
+++ b/src/jalview/datamodel/ResidueCount.java
@@ -1,3 +1,23 @@
+/*
+ * 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.
+ *  
+ * 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.datamodel;
 
 import jalview.util.Comparison;
@@ -5,9 +25,12 @@ import jalview.util.Format;
 import jalview.util.QuickSort;
 import jalview.util.SparseCount;
 
+import java.util.List;
+
 /**
  * A class to count occurrences of residues in a profile, optimised for speed
  * and memory footprint.
+ * 
  * @author gmcarstairs
  *
  */
@@ -49,7 +72,7 @@ public class ResidueCount
    */
   private static final String AAS = "ACDEFGHIKLMNPQRSTUVWXY";
 
-  private static final int GAP_COUNT = 0;
+  static final int GAP_COUNT = 0;
 
   /*
    * fast lookup tables holding the index into our count
@@ -127,6 +150,24 @@ public class ResidueCount
   }
 
   /**
+   * A constructor that counts frequency of all symbols (including gaps) in the
+   * sequences (not case-sensitive)
+   * 
+   * @param sequences
+   */
+  public ResidueCount(List<SequenceI> sequences)
+  {
+    this();
+    for (SequenceI seq : sequences)
+    {
+      for (int i = 0; i < seq.getLength(); i++)
+      {
+        add(seq.getCharAt(i));
+      }
+    }
+  }
+
+  /**
    * Increments the count for the given character. The supplied character may be
    * upper or lower case but counts are for the upper case only. Gap characters
    * (space, ., -) are all counted together.
@@ -191,7 +232,12 @@ public class ResidueCount
         counts[offset] = (short) ++newValue;
       }
     }
-    maxCount = Math.max(maxCount, newValue);
+
+    if (offset != GAP_COUNT)
+    {
+      // update modal residue count
+      maxCount = Math.max(maxCount, newValue);
+    }
     return newValue;
   }
 
@@ -280,15 +326,7 @@ public class ResidueCount
    */
   public int addGap()
   {
-    int newValue;
-    if (useIntCounts)
-    {
-      newValue = ++intCounts[GAP_COUNT];
-    }
-    else
-    {
-      newValue = ++counts[GAP_COUNT];
-    }
+    int newValue = increment(GAP_COUNT);
     return newValue;
   }
 
@@ -427,8 +465,8 @@ public class ResidueCount
       {
         if (intCounts[i] == count)
         {
-          modal.append(isNucleotide ? NUCS.charAt(i - 1) : AAS
-                  .charAt(i - 1));
+          modal.append(
+                  isNucleotide ? NUCS.charAt(i - 1) : AAS.charAt(i - 1));
         }
       }
     }
@@ -438,8 +476,8 @@ public class ResidueCount
       {
         if (counts[i] == count)
         {
-          modal.append(isNucleotide ? NUCS.charAt(i - 1) : AAS
-                  .charAt(i - 1));
+          modal.append(
+                  isNucleotide ? NUCS.charAt(i - 1) : AAS.charAt(i - 1));
         }
       }
     }
@@ -472,7 +510,8 @@ public class ResidueCount
    * 
    * @return
    */
-  public int size() {
+  public int size()
+  {
     int size = 0;
     if (useIntCounts)
     {
@@ -526,8 +565,8 @@ public class ResidueCount
       {
         if (intCounts[i] > 0)
         {
-          char symbol = isNucleotide ? NUCS.charAt(i - 1) : AAS
-                  .charAt(i - 1);
+          char symbol = isNucleotide ? NUCS.charAt(i - 1)
+                  : AAS.charAt(i - 1);
           symbols[j] = symbol;
           values[j] = intCounts[i];
           j++;
@@ -540,8 +579,8 @@ public class ResidueCount
       {
         if (counts[i] > 0)
         {
-          char symbol = isNucleotide ? NUCS.charAt(i - 1) : AAS
-                  .charAt(i - 1);
+          char symbol = isNucleotide ? NUCS.charAt(i - 1)
+                  : AAS.charAt(i - 1);
           symbols[j] = symbol;
           values[j] = counts[i];
           j++;
@@ -618,4 +657,19 @@ public class ResidueCount
     sb.append("]");
     return sb.toString();
   }
+
+  /**
+   * Answers the total count for all symbols (excluding gaps)
+   * 
+   * @return
+   */
+  public int getTotalResidueCount()
+  {
+    int total = 0;
+    for (char symbol : this.getSymbolCounts().symbols)
+    {
+      total += getCount(symbol);
+    }
+    return total;
+  }
 }