Hive UDF/UDAF 总结

import org.apache.hadoop.hive.ql.exec.UDF;
public class CustomUDF extends UDF{
    public String evaluate(String s){
        if (s == null) return null;
        return s.toString().toLowerCase();
    }
}

public class DefaultUDFMethodResolver implements UDFMethodResolver {
  private final Class<? extends UDF> udfClass;

  public DefaultUDFMethodResolver(Class<? extends UDF> udfClass) {
    this.udfClass = udfClass;
  }

  public Method getEvalMethod(List<TypeInfo> argClasses) throws UDFArgumentException {
    return FunctionRegistry.getMethodInternal(this.udfClass, "evaluate", false, argClasses);
  }
}

public class ScoreUDF extends GenericUDF {
    @Override
    public ObjectInspector initialize(ObjectInspector[] arguments) throws UDFArgumentException {
    }

    @Override
    public Object evaluate(DeferredObject[] arguments) throws HiveException {
    }

    @Override
    public String getDisplayString(String[] children) {
    }
}

public ObjectInspector initialize(ObjectInspector[] arguments) throws UDFArgumentException {
    if (arguments.length != 2) {
      throw new UDFArgumentLengthException("arrayContainsExample only takes 2 arguments: List<T>, T");
    }
    // 1. Check we received the right object types.
    ObjectInspector arg0 = arguments[0];
    ObjectInspector arg1 = arguments[1];
    if (!(arg0 instanceof ListObjectInspector) || !(arg1 instanceof StringObjectInspector)) {
      throw new UDFArgumentException("first argument must be a list / array, second argument must be a string");
    }
    this.listOI = (ListObjectInspector) arg0;
    this.elementOI = (StringObjectInspector) arg1;

    // 2. Check that the list contains strings
    if(!(listOI.getListElementObjectInspector() instanceof StringObjectInspector)) {
      throw new UDFArgumentException("first argument must be a list of strings");
    }

    // the return type of our function is a boolean, so we provide the correct object inspector
    return PrimitiveObjectInspectorFactory.javaBooleanObjectInspector;
}

public interface ObjectInspector extends Cloneable {
    public static enum Category {
        PRIMITIVE, LIST, MAP, STRUCT, UNION
    };
    String getTypeName();
    Category getCategory();
}

enum PrimitiveCategory {
    VOID, BOOLEAN, BYTE, SHORT, INT, LONG, FLOAT, DOUBLE, STRING,
    DATE, TIMESTAMP, TIMESTAMPLOCALTZ, BINARY, DECIMAL, VARCHAR, CHAR,
    INTERVAL_YEAR_MONTH, INTERVAL_DAY_TIME, UNKNOWN
}

import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDAF;
import org.apache.hadoop.hive.ql.exec.UDAFEvaluator;

@Description(name = "example_avg",
value = "_FUNC_(col) - Example UDAF to compute average")
public final class UDAFExampleAvg extends UDAF {

  /**
   * The internal state of an aggregation for average.
   *
   * Note that this is only needed if the internal state cannot be represented
   * by a primitive.
   *
   * The internal state can also contains fields with types like
   * ArrayList<String> and HashMap<String,Double> if needed.
   */
  public static class UDAFAvgState {
    private long mCount;
    private double mSum;
  }

  /**
   * The actual class for doing the aggregation. Hive will automatically look
   * for all internal classes of the UDAF that implements UDAFEvaluator.
   */
  public static class UDAFExampleAvgEvaluator implements UDAFEvaluator {

    UDAFAvgState state;

    public UDAFExampleAvgEvaluator() {
      super();
      state = new UDAFAvgState();
      init();
    }

    /**
     * Reset the state of the aggregation.
     */
    public void init() {
      state.mSum = 0;
      state.mCount = 0;
    }

    /**
     * Iterate through one row of original data.
     *
     * The number and type of arguments need to the same as we call this UDAF
     * from Hive command line.
     *
     * This function should always return true.
     */
    public boolean iterate(Double o) {
      if (o != null) {
        state.mSum += o;
        state.mCount++;
      }
      return true;
    }

    /**
     * Terminate a partial aggregation and return the state. If the state is a
     * primitive, just return primitive Java classes like Integer or String.
     */
    public UDAFAvgState terminatePartial() {
      // This is SQL standard - average of zero items should be null.
      return state.mCount == 0 ? null : state;
    }

    /**
     * Merge with a partial aggregation.
     *
     * This function should always have a single argument which has the same
     * type as the return value of terminatePartial().
     */
    public boolean merge(UDAFAvgState o) {
      if (o != null) {
        state.mSum += o.mSum;
        state.mCount += o.mCount;
      }
      return true;
    }

    /**
     * Terminates the aggregation and return the final result.
     */
    public Double terminate() {
      // This is SQL standard - average of zero items should be null.
      return state.mCount == 0 ? null : Double.valueOf(state.mSum
          / state.mCount);
    }
  }

}