amansinha100 commented on a change in pull request #1334: DRILL-6385: Support
JPPD feature
URL: https://github.com/apache/drill/pull/1334#discussion_r199334516
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/physical/impl/ScanBatch.java
##########
@@ -226,6 +244,96 @@ public IterOutcome next() {
}
}
+ private void applyRuntimeFilter() throws SchemaChangeException {
+ RuntimeFilterWritable runtimeFilterWritable = context.getRuntimeFilter();
+ if (runtimeFilterWritable == null) {
+ return;
+ }
+ if (recordCount <= 0) {
+ return;
+ }
+ List<BloomFilter> bloomFilters = runtimeFilterWritable.unwrap();
+ if (hash64 == null) {
+ ValueVectorHashHelper hashHelper = new ValueVectorHashHelper(this,
context);
+ try {
+ //generate hash helper
+ this.toFilterFields =
runtimeFilterWritable.getRuntimeFilterBDef().getProbeFieldsList();
+ List<LogicalExpression> hashFieldExps = new ArrayList<>();
+ List<TypedFieldId> typedFieldIds = new ArrayList<>();
+ for (String toFilterField : toFilterFields) {
+ SchemaPath schemaPath = new SchemaPath(new
PathSegment.NameSegment(toFilterField), ExpressionPosition.UNKNOWN);
+ TypedFieldId typedFieldId = container.getValueVectorId(schemaPath);
+ this.field2id.put(toFilterField, typedFieldId.getFieldIds()[0]);
+ typedFieldIds.add(typedFieldId);
+ ValueVectorReadExpression toHashFieldExp = new
ValueVectorReadExpression(typedFieldId);
+ hashFieldExps.add(toHashFieldExp);
+ }
+ hash64 = hashHelper.getHash64(hashFieldExps.toArray(new
LogicalExpression[hashFieldExps.size()]), typedFieldIds.toArray(new
TypedFieldId[typedFieldIds.size()]));
+ } catch (Exception e) {
+ throw UserException.internalError(e).build(logger);
+ }
+ }
+ selectionVector2.allocateNew(recordCount);
+ BitSet bitSet = new BitSet(recordCount);
+ for (int i = 0; i < toFilterFields.size(); i++) {
+ BloomFilter bloomFilter = bloomFilters.get(i);
+ String fieldName = toFilterFields.get(i);
+ computeBitSet(field2id.get(fieldName), bloomFilter, bitSet);
+ }
+ int svIndex = 0;
+ int tmpFilterRows = 0;
+ for (int i = 0; i < recordCount; i++) {
+ boolean contain = bitSet.get(i);
+ if (contain) {
+ selectionVector2.setIndex(svIndex, i);
+ svIndex++;
+ } else {
+ tmpFilterRows++;
+ }
+ }
+ selectionVector2.setRecordCount(svIndex);
+ if (tmpFilterRows > 0 && tmpFilterRows == recordCount) {
+ recordCount = 0;
+ selectionVector2.clear();
+ logger.debug("filter {} rows by the RuntimeFilter", tmpFilterRows);
+ return;
+ }
+ if (tmpFilterRows > 0 && tmpFilterRows != recordCount ) {
+ totalFilterRows = totalFilterRows + tmpFilterRows;
+ recordCount = svIndex;
+ BatchSchema batchSchema = this.schema;
+ VectorContainer backUpContainer = new
VectorContainer(this.oContext.getAllocator(), batchSchema);
+ int fieldCount = batchSchema.getFieldCount();
+ for (int i = 0; i < fieldCount; i++) {
+ ValueVector from =
this.getContainer().getValueVector(i).getValueVector();
+ ValueVector to = backUpContainer.getValueVector(i).getValueVector();
+ to.setInitialCapacity(svIndex);
+ for (int r = 0; r < svIndex; r++) {
+ to.copyEntry(r, from, selectionVector2.getIndex(r));
+ }
+ }
+ this.container.exchange(backUpContainer);
+ backUpContainer.clear();
+ selectionVector2.clear();
+ logger.debug("filter {} rows by the RuntimeFilter", tmpFilterRows);
+ return;
+ }
+ }
+
+
+ private void computeBitSet(int fieldId, BloomFilter bloomFilter, BitSet
bitSet) throws SchemaChangeException {
+ for (int rowIndex = 0; rowIndex < recordCount; rowIndex++) {
+ long hash = hash64.hash64Code(rowIndex, 0, fieldId);
+ boolean contain = bloomFilter.find(hash);
+ if (contain) {
+ bitSet.set(rowIndex, true);
+ bitSet.set(rowIndex);
Review comment:
Why call set() second time ?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
