Skip to content

[8.x] Fix counted_keyword support in arrays of objects (#121558) #121708

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 4, 2025
Merged

[8.x] Fix counted_keyword support in arrays of objects (#121558) #121708

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 45 additions & 9 deletions ...yword/src/main/java/org/elasticsearch/xpack/countedkeyword/CountedKeywordFieldMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@

package org.elasticsearch.xpack.countedkeyword;

import org.apache.lucene.document.BinaryDocValuesField;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.index.BinaryDocValues;
import org.apache.lucene.index.DocValues;
Expand All @@ -19,6 +18,7 @@
import org.apache.lucene.index.TermsEnum;
import org.apache.lucene.search.SortField;
import org.apache.lucene.util.BytesRef;
import org.elasticsearch.ElasticsearchException;
import org.elasticsearch.common.bytes.BytesArray;
import org.elasticsearch.common.io.stream.ByteArrayStreamInput;
import org.elasticsearch.common.io.stream.BytesStreamOutput;
Expand All @@ -31,6 +31,7 @@
import org.elasticsearch.index.fielddata.plain.AbstractIndexOrdinalsFieldData;
import org.elasticsearch.index.fielddata.plain.AbstractLeafOrdinalsFieldData;
import org.elasticsearch.index.mapper.BinaryFieldMapper;
import org.elasticsearch.index.mapper.CustomDocValuesField;
import org.elasticsearch.index.mapper.DocumentParserContext;
import org.elasticsearch.index.mapper.FieldMapper;
import org.elasticsearch.index.mapper.KeywordFieldMapper;
Expand Down Expand Up @@ -437,15 +438,17 @@ protected void parseCreateField(DocumentParserContext context) throws IOExceptio
return;
}

int i = 0;
int[] counts = new int[values.size()];
for (Map.Entry<String, Integer> value : values.entrySet()) {
context.doc().add(new KeywordFieldMapper.KeywordField(fullPath(), new BytesRef(value.getKey()), fieldType));
counts[i++] = value.getValue();
for (String value : values.keySet()) {
context.doc().add(new KeywordFieldMapper.KeywordField(fullPath(), new BytesRef(value), fieldType));
}
CountsBinaryDocValuesField field = (CountsBinaryDocValuesField) context.doc().getByKey(countFieldMapper.fieldType().name());
if (field == null) {
field = new CountsBinaryDocValuesField(countFieldMapper.fieldType().name());
field.add(values);
context.doc().addWithKey(countFieldMapper.fieldType().name(), field);
} else {
field.add(values);
}
BytesStreamOutput streamOutput = new BytesStreamOutput();
streamOutput.writeVIntArray(counts);
context.doc().add(new BinaryDocValuesField(countFieldMapper.fullPath(), streamOutput.bytes().toBytesRef()));
}

private void parseArray(DocumentParserContext context, SortedMap<String, Integer> values) throws IOException {
Expand Down Expand Up @@ -512,4 +515,37 @@ protected SyntheticSourceSupport syntheticSourceSupport() {
);
}

private class CountsBinaryDocValuesField extends CustomDocValuesField {
private final SortedMap<String, Integer> counts;

CountsBinaryDocValuesField(String name) {
super(name);
counts = new TreeMap<>();
}

public void add(SortedMap<String, Integer> newCounts) {
for (Map.Entry<String, Integer> currCount : newCounts.entrySet()) {
this.counts.put(currCount.getKey(), this.counts.getOrDefault(currCount.getKey(), 0) + currCount.getValue());
}
}

@Override
public BytesRef binaryValue() {
try {
int maxBytesPerVInt = 5;
int bytesSize = (counts.size() + 1) * maxBytesPerVInt;
BytesStreamOutput out = new BytesStreamOutput(bytesSize);
int countsArr[] = new int[counts.size()];
int i = 0;
for (Integer currCount : counts.values()) {
countsArr[i++] = currCount;
}
out.writeVIntArray(countsArr);
return out.bytes().toBytesRef();
} catch (IOException e) {
throw new ElasticsearchException("Failed to get binary value", e);
}
}
}

}
Loading