org.apache.hadoop.hive.ql.exec.vector.expressions.MathFuncLongToDouble Maven / Gradle / Ivy
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.hadoop.hive.ql.exec.vector.expressions;
import java.util.Arrays;
import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
import org.apache.hadoop.hive.ql.metadata.HiveException;
/**
* Implement vectorized math function that takes a double (and optionally additional
* constant argument(s)) and returns long.
* May be used for functions like ROUND(d, N), Pow(a, p) etc.
*
* Do NOT use this for simple math functions like sin/cos/exp etc. that just take
* a single argument. For those, modify the template ColumnUnaryFunc.txt
* and expand the template to generate needed classes.
*/
public abstract class MathFuncLongToDouble extends VectorExpression {
private static final long serialVersionUID = 1L;
private final int colNum;
// Subclasses must override this with a function that implements the desired logic.
protected abstract double func(long l);
public MathFuncLongToDouble(int colNum, int outputColumnNum) {
super(outputColumnNum);
this.colNum = colNum;
}
public MathFuncLongToDouble() {
super();
// Dummy final assignments.
colNum = -1;
}
@Override
public void evaluate(VectorizedRowBatch batch) throws HiveException {
if (childExpressions != null) {
this.evaluateChildren(batch);
}
LongColumnVector inputColVector = (LongColumnVector) batch.cols[colNum];
DoubleColumnVector outputColVector = (DoubleColumnVector) batch.cols[outputColumnNum];
int[] sel = batch.selected;
boolean[] inputIsNull = inputColVector.isNull;
boolean[] outputIsNull = outputColVector.isNull;
int n = batch.size;
long[] vector = inputColVector.vector;
double[] outputVector = outputColVector.vector;
// return immediately if batch is empty
if (n == 0) {
return;
}
// We do not need to do a column reset since we are carefully changing the output.
outputColVector.isRepeating = false;
if (inputColVector.isRepeating) {
if (inputColVector.noNulls || !inputIsNull[0]) {
outputIsNull[0] = false;
outputVector[0] = func(vector[0]);
} else {
outputIsNull[0] = true;
outputColVector.noNulls = false;
}
outputColVector.isRepeating = true;
cleanup(outputColVector, sel, batch.selectedInUse, n);
return;
}
if (inputColVector.noNulls) {
if (batch.selectedInUse) {
// CONSIDER: For large n, fill n or all of isNull array and use the tighter ELSE loop.
if (!outputColVector.noNulls) {
for(int j = 0; j != n; j++) {
final int i = sel[j];
// Set isNull before call in case it changes it mind.
outputIsNull[i] = false;
outputVector[i] = func(vector[i]);
}
} else {
for(int j = 0; j != n; j++) {
final int i = sel[j];
outputVector[i] = func(vector[i]);
}
}
} else {
if (!outputColVector.noNulls) {
// Assume it is almost always a performance win to fill all of isNull so we can
// safely reset noNulls.
Arrays.fill(outputIsNull, false);
outputColVector.noNulls = true;
}
for(int i = 0; i != n; i++) {
outputVector[i] = func(vector[i]);
}
}
} else /* there are nulls in the inputColVector */ {
// Carefully handle NULLs...
outputColVector.noNulls = false;
if (batch.selectedInUse) {
for(int j = 0; j != n; j++) {
int i = sel[j];
outputIsNull[i] = inputIsNull[i];
outputVector[i] = func(vector[i]);
}
} else {
System.arraycopy(inputIsNull, 0, outputIsNull, 0, n);
for(int i = 0; i != n; i++) {
outputVector[i] = func(vector[i]);
}
}
}
cleanup(outputColVector, sel, batch.selectedInUse, n);
}
// override this with a no-op if subclass doesn't need to treat NaN as null
protected void cleanup(DoubleColumnVector outputColVector, int[] sel,
boolean selectedInUse, int n) {
MathExpr.NaNToNull(outputColVector, sel, selectedInUse, n);
}
@Override
public String vectorExpressionParameters() {
return getColumnParamString(0, colNum);
}
}