-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Open
Assignees
@ivan-zaitsev
Description
It is documented here that keyset-filtering requires all the keyset properties to be non-nullable.
But will it actually affect indexing/ordering by adding cb.isNull() condition for some of the properties to https://github.com/spring-projects/spring-data-jpa/blob/main/spring-data-jpa/src/main/java/org/springframework/data/jpa/repository/query/KeysetScrollSpecification.java#L120 ?
Generated query examples:
Map<String, Object> keys = new LinkedHashMap<>();
keys.put("createdAt", entity.getCreatedAt());
keys.put("id", entity.getId());
// Maybe somehow here allow to specify which keys can be null, but at least one key is requred to be not null
KeysetScrollPosition scrollPosition = ScrollPosition.of(keys, ScrollPosition.Direction.FORWARD);
Sort sort = Sort.by(Sort.Direction.ASC, "createdAt", "id")
Function<FluentQuery.FetchableFluentQuery<Entity>, Window<Entity>> queryFunction = query -> query
.limit(10)
.sortBy(sort)
.scroll(scrollPosition);
Specification<Entity> specification = ...;
Window<Entity> result = repository.findBy(specification, queryFunction);
SELECT *
FROM table
WHERE (created_at IS NOT NULL AND created_at > ?) OR
(created_at IS NULL AND id > ?) -- use a fallback key like `id` for rows with NULL `created_at`
ORDER BY created_at ASC, id ASC
LIMIT 10;