Skip to content
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.

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

Two queries for keyword script field #59527

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,17 @@
import org.elasticsearch.script.Script;
import org.elasticsearch.xpack.runtimefields.StringScriptFieldScript;
import org.elasticsearch.xpack.runtimefields.fielddata.ScriptBinaryFieldData;
import org.elasticsearch.xpack.runtimefields.query.StringScriptFieldExistsQuery;
import org.elasticsearch.xpack.runtimefields.query.StringScriptFieldTermQuery;
import org.elasticsearch.xpack.runtimefields.query.StringScriptFieldTermsQuery;

import java.io.IOException;
import java.util.List;
import java.util.Map;
import java.util.Objects;
import java.util.Set;

import static java.util.stream.Collectors.toSet;

public final class RuntimeKeywordMappedFieldType extends MappedFieldType {

Expand Down Expand Up @@ -57,18 +63,24 @@ public ScriptBinaryFieldData.Builder fielddataBuilder(String fullyQualifiedIndex
return new ScriptBinaryFieldData.Builder(scriptFactory);
}

private StringScriptFieldScript.LeafFactory leafFactory(QueryShardContext context) {
return scriptFactory.newFactory(script.getParams(), context.lookup());
}

@Override
public Query existsQuery(QueryShardContext context) {
return new StringScriptFieldExistsQuery(leafFactory(context), name());
}

@Override
public Query termQuery(Object value, QueryShardContext context) {
return new StringScriptFieldTermQuery(
scriptFactory.newFactory(script.getParams(), context.lookup()),
name(),
BytesRefs.toString(Objects.requireNonNull(value))
);
return new StringScriptFieldTermQuery(leafFactory(context), name(), BytesRefs.toString(Objects.requireNonNull(value)));
}

@Override
public Query existsQuery(QueryShardContext context) {
return null;
public Query termsQuery(List<?> values, QueryShardContext context) {
Set<String> terms = values.stream().map(v -> BytesRefs.toString(Objects.requireNonNull(v))).collect(toSet());
return new StringScriptFieldTermsQuery(leafFactory(context), name(), terms);
}

void doXContentBody(XContentBuilder builder, boolean includeDefaults, Params params) throws IOException {
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
/*
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
* or more contributor license agreements. Licensed under the Elastic License;
* you may not use this file except in compliance with the Elastic License.
*/

package org.elasticsearch.xpack.runtimefields.query;

import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.search.ConstantScoreScorer;
import org.apache.lucene.search.ConstantScoreWeight;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreMode;
import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.TwoPhaseIterator;
import org.apache.lucene.search.Weight;
import org.elasticsearch.xpack.runtimefields.StringScriptFieldScript;
import org.elasticsearch.xpack.runtimefields.StringScriptFieldScript.LeafFactory;

import java.io.IOException;
import java.util.List;
import java.util.Objects;

/**
* Abstract base class for building queries based on {@link StringScriptFieldScript}.
*/
abstract class AbstractStringScriptFieldQuery extends Query {
private final StringScriptFieldScript.LeafFactory leafFactory;
private final String fieldName;

AbstractStringScriptFieldQuery(LeafFactory leafFactory, String fieldName) {
this.leafFactory = Objects.requireNonNull(leafFactory);
this.fieldName = Objects.requireNonNull(fieldName);
}

/**
* Does the value match this query?
*/
public abstract boolean matches(List<String> values);

@Override
public final Weight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException {
return new ConstantScoreWeight(this, boost) {
@Override
public boolean isCacheable(LeafReaderContext ctx) {
return false; // scripts aren't really cacheable at this point
}

@Override
public Scorer scorer(LeafReaderContext ctx) throws IOException {
StringScriptFieldScript script = leafFactory.newInstance(ctx);
DocIdSetIterator approximation = DocIdSetIterator.all(ctx.reader().maxDoc());
TwoPhaseIterator twoPhase = new TwoPhaseIterator(approximation) {
@Override
public boolean matches() throws IOException {
return AbstractStringScriptFieldQuery.this.matches(script.resultsForDoc(approximation().docID()));
}

@Override
public float matchCost() {
// TODO we don't have a good way of estimating the complexity of the script so we just go with 9000
return 9000f;
}
};
return new ConstantScoreScorer(this, score(), scoreMode, twoPhase);
}
};
}

protected final String fieldName() {
return fieldName;
}

@Override
public int hashCode() {
// TODO should leafFactory be here? Something about the script probably should be!
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

good point. what do we need to address this TODO? Would we need to pass in the Script itself?

return Objects.hash(getClass(), fieldName);
}

@Override
public boolean equals(Object obj) {
if (obj == null || getClass() != obj.getClass()) {
return false;
}
// TODO should leafFactory be here? Something about the script probably should be!
AbstractStringScriptFieldQuery other = (AbstractStringScriptFieldQuery) obj;
return fieldName.equals(other.fieldName);
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
/*
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
* or more contributor license agreements. Licensed under the Elastic License;
* you may not use this file except in compliance with the Elastic License.
*/

package org.elasticsearch.xpack.runtimefields.query;

import org.elasticsearch.xpack.runtimefields.StringScriptFieldScript;

import java.util.List;

public class StringScriptFieldExistsQuery extends AbstractStringScriptFieldQuery {
public StringScriptFieldExistsQuery(StringScriptFieldScript.LeafFactory leafFactory, String fieldName) {
super(leafFactory, fieldName);
}

@Override
public boolean matches(List<String> values) {
return false == values.isEmpty();
}

@Override
public final String toString(String field) {
if (fieldName().contentEquals(field)) {
return "*";
}
return fieldName() + ":*";
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I thought we said we would adapt toString for the exists query to be something more aligned with DocValuesFieldExistsQuery in lucene

}

// Superclass's equals and hashCode are great for this class
}
Original file line number Diff line number Diff line change
Expand Up @@ -6,92 +6,59 @@

package org.elasticsearch.xpack.runtimefields.query;

import org.apache.lucene.index.LeafReaderContext;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.ConstantScoreScorer;
import org.apache.lucene.search.ConstantScoreWeight;
import org.apache.lucene.search.DocIdSetIterator;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.QueryVisitor;
import org.apache.lucene.search.ScoreMode;
import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.TwoPhaseIterator;
import org.apache.lucene.search.Weight;
import org.elasticsearch.xpack.runtimefields.StringScriptFieldScript;

import java.io.IOException;
import java.util.List;
import java.util.Objects;

public class StringScriptFieldTermQuery extends Query {
private final StringScriptFieldScript.LeafFactory leafFactory;
private final String fieldName;
public class StringScriptFieldTermQuery extends AbstractStringScriptFieldQuery {
private final String term;

public StringScriptFieldTermQuery(StringScriptFieldScript.LeafFactory leafFactory, String fieldName, String term) {
this.leafFactory = leafFactory;
this.fieldName = fieldName;
this.term = term;
super(leafFactory, fieldName);
this.term = Objects.requireNonNull(term);
}

@Override
public final Weight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException {
return new ConstantScoreWeight(this, boost) {
@Override
public boolean isCacheable(LeafReaderContext ctx) {
return false; // scripts aren't really cacheable at this point
public boolean matches(List<String> values) {
for (String value : values) {
if (term.equals(value)) {
return true;
}

@Override
public Scorer scorer(LeafReaderContext ctx) throws IOException {
StringScriptFieldScript script = leafFactory.newInstance(ctx);
DocIdSetIterator approximation = DocIdSetIterator.all(ctx.reader().maxDoc());
TwoPhaseIterator twoPhase = new TwoPhaseIterator(approximation) {
@Override
public boolean matches() throws IOException {
for (String result : script.resultsForDoc(approximation().docID())) {
if (term.equals(result)) {
return true;
}
}
return false;
}

@Override
public float matchCost() {
// TODO we don't have a good way of estimating the complexity of the script so we just go with 9000
return 9000f;
}
};
return new ConstantScoreScorer(this, score(), scoreMode, twoPhase);
}
};
}
return false;
}

@Override
public void visit(QueryVisitor visitor) {
visitor.consumeTerms(this, new Term(fieldName, term));
visitor.consumeTerms(this, new Term(fieldName(), term));
}

@Override
public final String toString(String field) {
if (fieldName.contentEquals(field)) {
if (fieldName().contentEquals(field)) {
return term;
}
return fieldName + ":" + term;
return fieldName() + ":" + term;
}

@Override
public int hashCode() {
return Objects.hash(fieldName, term);
return Objects.hash(super.hashCode(), term);
}

@Override
public boolean equals(Object obj) {
if (obj == null || getClass() != obj.getClass()) {
if (false == super.equals(obj)) {
return false;
}
StringScriptFieldTermQuery other = (StringScriptFieldTermQuery) obj;
return fieldName.equals(other.fieldName) && term.equals(other.term);
return term.equals(other.term);
}

String term() {
return term;
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,69 @@
/*
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
* or more contributor license agreements. Licensed under the Elastic License;
* you may not use this file except in compliance with the Elastic License.
*/

package org.elasticsearch.xpack.runtimefields.query;

import org.apache.lucene.index.Term;
import org.apache.lucene.search.QueryVisitor;
import org.elasticsearch.xpack.runtimefields.StringScriptFieldScript;

import java.util.List;
import java.util.Objects;
import java.util.Set;

public class StringScriptFieldTermsQuery extends AbstractStringScriptFieldQuery {
private final Set<String> terms;

public StringScriptFieldTermsQuery(StringScriptFieldScript.LeafFactory leafFactory, String fieldName, Set<String> terms) {
super(leafFactory, fieldName);
this.terms = terms;
}

@Override
public boolean matches(List<String> values) {
for (String value : values) {
if (terms.contains(value)) {
return true;
}
}
return false;
}

@Override
public void visit(QueryVisitor visitor) {
if (visitor.acceptField(fieldName())) {
for (String term : terms) {
visitor.consumeTerms(this, new Term(fieldName(), term));
}
}
}

@Override
public final String toString(String field) {
if (fieldName().contentEquals(field)) {
return terms.toString();
}
return fieldName() + ":" + terms;
}

@Override
public int hashCode() {
return Objects.hash(super.hashCode(), terms);
}

@Override
public boolean equals(Object obj) {
if (false == super.equals(obj)) {
return false;
}
StringScriptFieldTermsQuery other = (StringScriptFieldTermsQuery) obj;
return terms.equals(other.terms);
}

Set<String> terms() {
return terms;
}
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we have unit tests for equals/hashcode , toString and visit for all the queries that we introduce?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

possibly also matches but that is already tested

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah. equals and hashcode are cache keys. toString probably isn't all that important but we may as well do it while we're there. Visit is important for highlighting, or, at least, it will be. So we should do it too.

}
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,17 @@ public void collect(int doc) throws IOException {
}
}

public void testExistsQuery() throws IOException {
try (Directory directory = newDirectory(); RandomIndexWriter iw = new RandomIndexWriter(random(), directory)) {
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": [1]}"))));
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": []}"))));
try (DirectoryReader reader = iw.getReader()) {
IndexSearcher searcher = newSearcher(reader);
assertThat(searcher.count(build("for (def v : source.foo) { value(v.toString())}").existsQuery(mockContext())), equalTo(1));
}
}
}

public void testTermQuery() throws IOException {
try (Directory directory = newDirectory(); RandomIndexWriter iw = new RandomIndexWriter(random(), directory)) {
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": 1}"))));
Expand All @@ -102,6 +113,19 @@ public void testTermQuery() throws IOException {
}
}

public void testTermsQuery() throws IOException {
try (Directory directory = newDirectory(); RandomIndexWriter iw = new RandomIndexWriter(random(), directory)) {
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": 1}"))));
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": 2}"))));
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": 3}"))));
iw.addDocument(List.of(new StoredField("_source", new BytesRef("{\"foo\": 4}"))));
try (DirectoryReader reader = iw.getReader()) {
IndexSearcher searcher = newSearcher(reader);
assertThat(searcher.count(build("value(source.foo.toString())").termsQuery(List.of("1", "2"), mockContext())), equalTo(2));
}
}
}

private RuntimeKeywordMappedFieldType build(String code) throws IOException {
Script script = new Script(code);
PainlessPlugin painlessPlugin = new PainlessPlugin();
Expand Down
Loading