Skip to content

Correct the condition to use a multi field block loader in text field block loader #126718

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
Apr 22, 2025
Merged

Correct the condition to use a multi field block loader in text field block loader #126718

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
7 changes: 3 additions & 4 deletions server/src/main/java/org/elasticsearch/index/mapper/TextFieldMapper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -967,12 +967,11 @@ public boolean isAggregatable() {
}

/**
* Returns true if the delegate sub-field can be used for loading and querying (ie. either isIndexed or isStored is true)
* Returns true if the delegate sub-field can be used for loading.
* A delegate by definition must have doc_values or be stored so most of the time it can be used for loading.
Copy link
Member

Choose a reason for hiding this comment

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

Suggested change
* A delegate by definition must have doc_values or be stored so most of the time it can be used for loading.
* A delegate by definition must have doc_values or be stored so most of the time it can be used for querying.

I think?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

There already is canUseSyntheticSourceDelegateForQuerying() so "loading" distinguishes the two.

*/
public boolean canUseSyntheticSourceDelegateForLoading() {
return syntheticSourceDelegate != null
&& syntheticSourceDelegate.ignoreAbove() == Integer.MAX_VALUE
&& (syntheticSourceDelegate.isIndexed() || syntheticSourceDelegate.isStored());
return syntheticSourceDelegate != null && syntheticSourceDelegate.ignoreAbove() == Integer.MAX_VALUE;
}

/**
Expand Down
32 changes: 14 additions & 18 deletions ...r/src/test/java/org/elasticsearch/index/mapper/blockloader/TextFieldBlockLoaderTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,20 +35,20 @@ protected Object expected(Map<String, Object> fieldMapping, Object value, TestCo
var fields = (Map<String, Object>) fieldMapping.get("fields");
if (fields != null) {
var keywordMultiFieldMapping = (Map<String, Object>) fields.get("kwd");
Object normalizer = fields.get("normalizer");
boolean docValues = hasDocValues(keywordMultiFieldMapping, true);
boolean index = keywordMultiFieldMapping.getOrDefault("index", true).equals(true);
boolean store = keywordMultiFieldMapping.getOrDefault("store", false).equals(true);
Object ignoreAbove = keywordMultiFieldMapping.get("ignore_above");

// See TextFieldMapper.SyntheticSourceHelper#usingSyntheticSourceDelegate
// See TextFieldMapper.SyntheticSourceHelper#getKeywordFieldMapperForSyntheticSource
// and TextFieldMapper#canUseSyntheticSourceDelegateForLoading().
boolean usingSyntheticSourceDelegate = docValues || store;
boolean canUseSyntheticSourceDelegateForLoading = usingSyntheticSourceDelegate && ignoreAbove == null && (index || store);
boolean usingSyntheticSourceDelegate = normalizer == null && (docValues || store);
boolean canUseSyntheticSourceDelegateForLoading = usingSyntheticSourceDelegate && ignoreAbove == null;
if (canUseSyntheticSourceDelegateForLoading) {
return KeywordFieldBlockLoaderTests.expectedValue(keywordMultiFieldMapping, value, params, testContext);
}

// Even if multi-field is not eligible for loading it can still be used to produce synthetic source
// Even if multi field is not eligible for loading it can still be used to produce synthetic source
// and then we load from the synthetic source.
// Synthetic source is actually different from keyword field block loader results
// because synthetic source includes values exceeding ignore_above and block loader doesn't.
Expand All @@ -66,9 +66,7 @@ protected Object expected(Map<String, Object> fieldMapping, Object value, TestCo
boolean textFieldIndexed = (boolean) fieldMapping.getOrDefault("index", true);

if (value == null) {
if (textFieldIndexed == false
&& nullValue != null
&& (ignoreAbove == null || nullValue.length() <= (int) ignoreAbove)) {
if (textFieldIndexed == false && nullValue != null && nullValue.length() <= (int) ignoreAbove) {
return new BytesRef(nullValue);
}

Expand All @@ -89,7 +87,7 @@ protected Object expected(Map<String, Object> fieldMapping, Object value, TestCo
var indexed = values.stream()
.map(s -> s == null ? nullValue : s)
.filter(Objects::nonNull)
.filter(s -> ignoreAbove == null || s.length() <= (int) ignoreAbove)
.filter(s -> s.length() <= (int) ignoreAbove)
.map(BytesRef::new)
.collect(Collectors.toList());

Expand All @@ -100,22 +98,20 @@ protected Object expected(Map<String, Object> fieldMapping, Object value, TestCo
}

// ignored values always come last
List<BytesRef> ignored = ignoreAbove == null
? List.of()
: values.stream()
.map(s -> s == null ? nullValue : s)
.filter(Objects::nonNull)
.filter(s -> s.length() > (int) ignoreAbove)
.map(BytesRef::new)
.toList();
List<BytesRef> ignored = values.stream()
.map(s -> s == null ? nullValue : s)
.filter(Objects::nonNull)
.filter(s -> s.length() > (int) ignoreAbove)
.map(BytesRef::new)
.toList();

indexed.addAll(ignored);

return maybeFoldList(indexed);
}
}

// Loading from _ignored_source or stored _source
// Loading from stored field, _ignored_source or stored _source
return valuesInSourceOrder(value);
}

Expand Down