ESQL: Add TopN support for exponential histograms #137313
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,75 @@ | ||
| /* | ||
| * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one | ||
| * or more contributor license agreements. Licensed under the Elastic License | ||
| * 2.0; you may not use this file except in compliance with the Elastic License | ||
| * 2.0. | ||
| */ | ||
|
|
||
| package org.elasticsearch.compute.operator.topn; | ||
|
|
||
| import org.apache.lucene.util.BytesRef; | ||
| import org.elasticsearch.compute.data.Block; | ||
| import org.elasticsearch.compute.data.BlockFactory; | ||
| import org.elasticsearch.compute.data.ExponentialHistogramBlock; | ||
| import org.elasticsearch.compute.data.ExponentialHistogramBlockBuilder; | ||
|
|
||
| public class ResultBuilderForExponentialHistogram implements ResultBuilder { | ||
|
|
||
| private final ExponentialHistogramBlockBuilder builder; | ||
| private final ReusableTopNEncoderInput reusableInput = new ReusableTopNEncoderInput(); | ||
|
|
||
| ResultBuilderForExponentialHistogram(BlockFactory blockFactory, int positions) { | ||
| this.builder = blockFactory.newExponentialHistogramBlockBuilder(positions); | ||
| } | ||
|
|
||
| @Override | ||
| public void decodeKey(BytesRef keys) { | ||
| throw new AssertionError("ExponentialHistogramBlock can't be a key"); | ||
| } | ||
|
|
||
| @Override | ||
| public void decodeValue(BytesRef values) { | ||
| int count = TopNEncoder.DEFAULT_UNSORTABLE.decodeVInt(values); | ||
| if (count == 0) { | ||
| builder.appendNull(); | ||
| return; | ||
| } | ||
| assert count == 1 : "ExponentialHistogramBlock does not support multi values"; | ||
| reusableInput.inputValues = values; | ||
| builder.deserializeAndAppend(reusableInput); | ||
| } | ||
|
|
||
| @Override | ||
| public Block build() { | ||
| return builder.build(); | ||
| } | ||
|
|
||
| @Override | ||
| public String toString() { | ||
| return "ResultBuilderForExponentialHistogram"; | ||
| } | ||
|
|
||
| @Override | ||
| public void close() { | ||
| builder.close(); | ||
| } | ||
|
|
||
| private class ReusableTopNEncoderInput implements ExponentialHistogramBlock.SerializedInput { | ||
JonasKunz marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| BytesRef inputValues; | ||
|
|
||
| @Override | ||
| public double readDouble() { | ||
| return TopNEncoder.DEFAULT_UNSORTABLE.decodeDouble(inputValues); | ||
| } | ||
|
|
||
| @Override | ||
| public long readLong() { | ||
| return TopNEncoder.DEFAULT_UNSORTABLE.decodeLong(inputValues); | ||
| } | ||
|
|
||
| @Override | ||
| public BytesRef readBytesRef(BytesRef tempBytesRef) { | ||
| return TopNEncoder.DEFAULT_UNSORTABLE.decodeBytesRef(inputValues, tempBytesRef); | ||
| } | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,62 @@ | ||
| /* | ||
| * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one | ||
| * or more contributor license agreements. Licensed under the Elastic License | ||
| * 2.0; you may not use this file except in compliance with the Elastic License | ||
| * 2.0. | ||
| */ | ||
|
|
||
| package org.elasticsearch.compute.operator.topn; | ||
|
|
||
| import org.apache.lucene.util.BytesRef; | ||
| import org.elasticsearch.compute.data.ExponentialHistogramBlock; | ||
| import org.elasticsearch.compute.operator.BreakingBytesRefBuilder; | ||
|
|
||
| public class ValueExtractorForExponentialHistogram implements ValueExtractor { | ||
| private final ExponentialHistogramBlock block; | ||
|
|
||
| private final BytesRef scratch = new BytesRef(); | ||
| private final ReusableTopNEncoderOutput reusableOutput = new ReusableTopNEncoderOutput(); | ||
|
|
||
| ValueExtractorForExponentialHistogram(TopNEncoder encoder, ExponentialHistogramBlock block) { | ||
| assert encoder == TopNEncoder.DEFAULT_UNSORTABLE; | ||
| this.block = block; | ||
| } | ||
|
|
||
| @Override | ||
| public void writeValue(BreakingBytesRefBuilder values, int position) { | ||
| // number of multi-values first for compatibility with ValueExtractorForNull | ||
| if (block.isNull(position)) { | ||
| TopNEncoder.DEFAULT_UNSORTABLE.encodeVInt(0, values); | ||
| } else { | ||
| assert block.getValueCount(position) == 1 : "Multi-valued ExponentialHistogram blocks are not supported in TopN"; | ||
| TopNEncoder.DEFAULT_UNSORTABLE.encodeVInt(1, values); | ||
| int valueIndex = block.getFirstValueIndex(position); | ||
| reusableOutput.target = values; | ||
| block.serializeExponentialHistogram(valueIndex, reusableOutput, scratch); | ||
| } | ||
| } | ||
|
|
||
| @Override | ||
| public String toString() { | ||
| return "ValueExtractorForExponentialHistogram"; | ||
| } | ||
|
|
||
| private static final class ReusableTopNEncoderOutput implements ExponentialHistogramBlock.SerializedOutput { | ||
| BreakingBytesRefBuilder target; | ||
|
|
||
| @Override | ||
| public void appendDouble(double value) { | ||
| TopNEncoder.DEFAULT_UNSORTABLE.encodeDouble(value, target); | ||
| } | ||
|
|
||
| @Override | ||
| public void appendLong(long value) { | ||
| TopNEncoder.DEFAULT_UNSORTABLE.encodeLong(value, target); | ||
| } | ||
|
|
||
| @Override | ||
| public void appendBytesRef(BytesRef value) { | ||
| TopNEncoder.DEFAULT_UNSORTABLE.encodeBytesRef(value, target); | ||
| } | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
valueIndexshould bepositioninstead.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The intended usage pattern for
serializeExponentialHistogramis just like for getters on blocks:So
valueIndexinstead ofpositionis correct here.Right now it is true for exponential histogram blocks that we just use the positions directly as
valueIndex, but that will change when we support multi-values.See also this comment: #133393 (comment)
I'll add a comment in
ExponentialHistogramArrayBlockexplaining the mapping of positions and valueIndices to positions in the sub-blocks.