[
https://issues.apache.org/jira/browse/HIVE-12827?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15102304#comment-15102304
]
Sergey Shelukhin commented on HIVE-12827:
-----------------------------------------
+1. Did the fill() on the main path get committed, and does it need to be
removed with this patch?
> Vectorization: VectorCopyRow/VectorAssignRow/VectorDeserializeRow assign
> needs explicit isNull[offset] modification
> -------------------------------------------------------------------------------------------------------------------
>
> Key: HIVE-12827
> URL: https://issues.apache.org/jira/browse/HIVE-12827
> Project: Hive
> Issue Type: Bug
> Reporter: Gopal V
> Assignee: Gopal V
> Attachments: HIVE-12827.2.patch
>
>
> Some scenarios do set Double.NaN instead of isNull=true, but all types aren't
> consistent.
> Examples of un-set isNull for the valid values are
> {code}
> private class FloatReader extends AbstractDoubleReader {
> FloatReader(int columnIndex) {
> super(columnIndex);
> }
> @Override
> void apply(VectorizedRowBatch batch, int batchIndex) throws IOException {
> DoubleColumnVector colVector = (DoubleColumnVector)
> batch.cols[columnIndex];
> if (deserializeRead.readCheckNull()) {
> VectorizedBatchUtil.setNullColIsNullValue(colVector, batchIndex);
> } else {
> float value = deserializeRead.readFloat();
> colVector.vector[batchIndex] = (double) value;
> }
> }
> }
> {code}
> {code}
> private class DoubleCopyRow extends CopyRow {
> DoubleCopyRow(int inColumnIndex, int outColumnIndex) {
> super(inColumnIndex, outColumnIndex);
> }
> @Override
> void copy(VectorizedRowBatch inBatch, int inBatchIndex,
> VectorizedRowBatch outBatch, int outBatchIndex) {
> DoubleColumnVector inColVector = (DoubleColumnVector)
> inBatch.cols[inColumnIndex];
> DoubleColumnVector outColVector = (DoubleColumnVector)
> outBatch.cols[outColumnIndex];
> if (inColVector.isRepeating) {
> if (inColVector.noNulls || !inColVector.isNull[0]) {
> outColVector.vector[outBatchIndex] = inColVector.vector[0];
> } else {
> VectorizedBatchUtil.setNullColIsNullValue(outColVector,
> outBatchIndex);
> }
> } else {
> if (inColVector.noNulls || !inColVector.isNull[inBatchIndex]) {
> outColVector.vector[outBatchIndex] =
> inColVector.vector[inBatchIndex];
> } else {
> VectorizedBatchUtil.setNullColIsNullValue(outColVector,
> outBatchIndex);
> }
> }
> }
> }
> {code}
> {code}
> private static abstract class VectorDoubleColumnAssign
> extends VectorColumnAssignVectorBase<DoubleColumnVector> {
> protected void assignDouble(double value, int destIndex) {
> outCol.vector[destIndex] = value;
> }
> }
> {code}
> The pattern to imitate would be the earlier code from VectorBatchUtil
> {code}
> case DOUBLE: {
> DoubleColumnVector dcv = (DoubleColumnVector) batch.cols[offset +
> colIndex];
> if (writableCol != null) {
> dcv.vector[rowIndex] = ((DoubleWritable) writableCol).get();
> dcv.isNull[rowIndex] = false;
> } else {
> dcv.vector[rowIndex] = Double.NaN;
> setNullColIsNullValue(dcv, rowIndex);
> }
> }
> break;
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
