Merge pull request #4 from MikePone/master

CDCgov · Mar 20, 2024 · f4f826a · f4f826a
2 parents 8b3173f + 387b872
commit f4f826a
Show file tree

Hide file tree

Showing 4 changed files with 120 additions and 5 deletions.
diff --git a/SeqRuler.jar b/SeqRuler.jar
diff --git a/modules/gui-app/pom.xml b/modules/gui-app/pom.xml
@@ -8,6 +8,21 @@
     <artifactId>gui-app</artifactId>
     <version>0.1</version>
     <dependencies>
+		<!-- https://mvnrepository.com/artifact/org.apache.hive/hive-common -->
+		<dependency>
+		    <groupId>org.apache.hive</groupId>
+		    <artifactId>hive-common</artifactId>
+		    <version>3.1.3</version>
+		    <scope>provided</scope>
+		</dependency>
+		<!-- https://mvnrepository.com/artifact/org.apache.hive/hive-exec -->
+		<dependency>
+		    <groupId>org.apache.hive</groupId>
+		    <artifactId>hive-exec</artifactId>
+		    <version>3.1.3</version>
+		    <scope>provided</scope>
+		</dependency>
+
         <dependency>
             <groupId>info.picocli</groupId>
             <artifactId>picocli</artifactId>

diff --git a/modules/gui-app/src/main/java/TN93/TN93.java b/modules/gui-app/src/main/java/TN93/TN93.java
@@ -13,9 +13,6 @@
 //Parallelization
 import java.util.concurrent.*;
 
-
-
-
 import static java.lang.Math.log;
 
 public class TN93 extends Observable {
@@ -53,8 +50,15 @@ public Pair(A first, B second) {
     private boolean use_stdout = false;
     private boolean input_as_pairs = false;
     private boolean enumerate_sequences = false; 
+
+    enum RESOLVE_METHOD {
+    	RESOLVE,
+    	AVERAGE,
+    	GAPMM,
+    	SKIP
+    }
 
-    public void setEdgeThreshold(float edgeThreshold) {
+	public void setEdgeThreshold(float edgeThreshold) {
         this.edgeThreshold = edgeThreshold;
     }
 
@@ -591,7 +595,13 @@ private void update_percent_complete(long total_pairs_to_compute, long current_p
         notifyObservers(percCompleted);
     }
 
-    private double tn93(Seq s1, Seq s2) {
+    /**
+     * Package visibility to allow the UDF direct access to this method.
+     * @param s1
+     * @param s2
+     * @return
+     */
+    double tn93(Seq s1, Seq s2) {
         double[][] nucl_pair_counts = countPairwiseNucl(s1, s2);
         double[] nucl_counts = getNuclCounts(nucl_pair_counts);
 

diff --git a/modules/gui-app/src/main/java/TN93/TN93UDF.java b/modules/gui-app/src/main/java/TN93/TN93UDF.java
@@ -0,0 +1,90 @@
+package TN93;
+
+import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
+import org.apache.hadoop.hive.ql.exec.UDFArgumentLengthException;
+import org.apache.hadoop.hive.ql.metadata.HiveException;
+import org.apache.hadoop.hive.ql.udf.generic.GenericUDF;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector.Category;
+import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector.PrimitiveCategory;
+import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorConverter;
+import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorConverter.StringConverter;
+import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
+import org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableConstantHiveDecimalObjectInspector;
+import org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableConstantStringObjectInspector;
+import org.apache.hadoop.io.DoubleWritable;
+
+public class TN93UDF extends GenericUDF {
+
+    private TN93 tn93 = null; 
+    private transient StringConverter stringConverter;
+
+    /**
+     * Arguments are Seq1, Seq1, resolveMode (average, resolve,gapmm,skip), abiguityFraction,
+     */
+    @Override
+    public ObjectInspector initialize(ObjectInspector[] arguments) throws UDFArgumentException {
+        if (arguments.length != 4) {
+            throw new UDFArgumentLengthException(
+                    "TN93() requires 4 arguments (Seq1, Seq1, resolveMode (average, resolve, gapmm, skip), abiguityFraction), got "
+                            + arguments.length);
+        }
+        tn93 = new TN93();
+
+        for (int i = 0; i < arguments.length; i++) {
+
+            if (arguments[i].getCategory() != Category.PRIMITIVE) {
+                throw new UDFArgumentException("TN93 only takes primitive types, got " +arguments[i].getCategory() + ":" +  arguments[i].getTypeName());
+            }
+        }
+        // make sure ambig fraction param is double
+        PrimitiveObjectInspector ambigArgOI = (PrimitiveObjectInspector) arguments[3];
+        PrimitiveCategory inputType = ambigArgOI.getPrimitiveCategory();
+
+        if (inputType != PrimitiveCategory.DECIMAL) {
+            throw new UDFArgumentException("TN93 ambig fraction should be a decimal, got " + arguments[3].getTypeName());
+        }
+        //initialize TN93 with correct parameters.
+        WritableConstantHiveDecimalObjectInspector ambigFractionArg = (WritableConstantHiveDecimalObjectInspector) arguments[3];
+        tn93.setMaxAmbiguityFraction(ambigFractionArg.getWritableConstantValue().doubleValue());
+        //TN93UDF arg object type : org.apache.hadoop.hive.serde2.objectinspector.primitive.WritableConstantStringObjectInspector
+        WritableConstantStringObjectInspector resolveArg = (WritableConstantStringObjectInspector) arguments[2];
+        tn93.setAmbiguityHandling(resolveArg.getWritableConstantValue().toString());
+
+        //string converter for sequence string args.
+        PrimitiveObjectInspector sequenceArgsOI = (PrimitiveObjectInspector) arguments[0];
+        stringConverter = new PrimitiveObjectInspectorConverter.StringConverter(sequenceArgsOI);
+
+        // output object is a double.
+        ObjectInspector outputOI = PrimitiveObjectInspectorFactory.writableDoubleObjectInspector;
+        return outputOI;
+    }
+
+    @Override
+    public Object evaluate(DeferredObject[] arguments) throws HiveException {
+
+        String val1 = null;
+        String val2 = null;
+        if (arguments[0] != null && arguments[1] != null) {
+          val1 = (String) stringConverter.convert(arguments[0].get());
+          val2 = (String) stringConverter.convert(arguments[1].get());
+        }
+        if (val1 == null || val2 == null) {
+          return null;
+        }
+
+        Seq seq1 = new Seq("1", val1);
+        Seq seq2 = new Seq("2", val2);
+
+        double result = tn93.tn93(seq1,seq2);
+
+        return new DoubleWritable(result);
+    }
+
+    @Override
+    public String getDisplayString(String[] children) {
+        return "TN93 UDF implementation wrapper for SeqRuler.";
+    }
+
+}