Github user paul-rogers commented on a diff in the pull request:
https://github.com/apache/drill/pull/906#discussion_r134301372
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/physical/impl/ScanBatch.java
---
@@ -152,97 +157,75 @@ public void kill(boolean sendUpstream) {
}
}
- private void releaseAssets() {
- container.zeroVectors();
- }
-
- private void clearFieldVectorMap() {
- for (final ValueVector v : mutator.fieldVectorMap().values()) {
- v.clear();
- }
- }
-
@Override
public IterOutcome next() {
if (done) {
return IterOutcome.NONE;
}
oContext.getStats().startProcessing();
try {
- try {
- injector.injectChecked(context.getExecutionControls(),
"next-allocate", OutOfMemoryException.class);
-
- currentReader.allocate(mutator.fieldVectorMap());
- } catch (OutOfMemoryException e) {
- clearFieldVectorMap();
- throw UserException.memoryError(e).build(logger);
- }
- while ((recordCount = currentReader.next()) == 0) {
+ while (true) {
try {
- if (!readers.hasNext()) {
- // We're on the last reader, and it has no (more) rows.
- currentReader.close();
- releaseAssets();
- done = true; // have any future call to next() return NONE
-
- if (mutator.isNewSchema()) {
- // This last reader has a new schema (e.g., we have a
zero-row
- // file or other source). (Note that some sources have a
non-
- // null/non-trivial schema even when there are no rows.)
+ injector.injectChecked(context.getExecutionControls(),
"next-allocate", OutOfMemoryException.class);
+ currentReader.allocate(mutator.fieldVectorMap());
+ } catch (OutOfMemoryException e) {
+ clearFieldVectorMap();
+ throw UserException.memoryError(e).build(logger);
+ }
- container.buildSchema(SelectionVectorMode.NONE);
- schema = container.getSchema();
+ recordCount = currentReader.next();
+ Preconditions.checkArgument(recordCount >= 0,
+ "recordCount from RecordReader.next() should not be negative");
- return IterOutcome.OK_NEW_SCHEMA;
- }
- return IterOutcome.NONE;
- }
- // At this point, the reader that hit its end is not the last
reader.
+ boolean isNewRegularSchema = mutator.isNewSchema();
+ // We should skip the reader, when recordCount = 0 && !
isNewRegularSchema.
+ // Add/set implicit column vectors, only when reader gets > 0 row,
or
+ // when reader gets 0 row but with a schema with new field added
+ if (recordCount > 0 || isNewRegularSchema) {
+ addImplicitVectors();
+ populateImplicitVectors();
+ }
- // If all the files we have read so far are just empty, the
schema is not useful
- if (! hasReadNonEmptyFile) {
- container.clear();
- clearFieldVectorMap();
- mutator.clear();
- }
+ boolean isNewImplicitSchema = mutator.isNewSchema();
+ for (VectorWrapper<?> w : container) {
+ w.getValueVector().getMutator().setValueCount(recordCount);
+ }
+ final boolean isNewSchema = isNewRegularSchema ||
isNewImplicitSchema;
+ oContext.getStats().batchReceived(0, recordCount, isNewSchema);
+ if (recordCount == 0) {
currentReader.close();
- currentReader = readers.next();
- implicitValues = implicitColumns.hasNext() ?
implicitColumns.next() : null;
- currentReader.setup(oContext, mutator);
- try {
- currentReader.allocate(mutator.fieldVectorMap());
- } catch (OutOfMemoryException e) {
- clearFieldVectorMap();
- throw UserException.memoryError(e).build(logger);
+ if (isNewSchema) {
+ // current reader presents a new schema in mutator even though
it has 0 row.
--- End diff --
Thanks for the comments here and in the PR. I wonder, can the PR
description be moved into a class Javadoc comment so that it is available for
future readers? Also, makes it easier to review since the description is close
to the code.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
