perf(8.0): negation/absence where-operators via roaring-bitmap difference
The JS metadata index served `ne`, `exists:false`, and `missing:true` by materializing the ENTIRE id universe as an array of UUID strings, building a Set of the excluded ids, and filtering — O(N) heap and two full passes on the open-core path, on the most common shape (`deleted !== true`). Compute the complement as a roaring-bitmap difference over the int-id universe instead (`complementIds(excludeInts)` = universe \ exclude), converting only the result back to UUIDs. The exclude set is small (the matching value), so this avoids the full-corpus string materialization entirely. Behaviour is unchanged, including the load-bearing soft-delete semantic that `field !== value` includes entities with no such field. New focused tests pin `ne`/`exists:false`/ `missing:true`/`exists:true` result sets and that the complement reflects deletes. Full gate green: unit 1520, integration 607. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
parent
72df5572b7
commit
5f974abc8a
2 changed files with 90 additions and 23 deletions
|
|
@ -1888,19 +1888,17 @@ export class MetadataIndexManager implements MetadataIndexProvider {
|
|||
// Canonical: 'ne' | Alias: 'notEquals'
|
||||
case 'notEquals': // Alias for 'ne'
|
||||
case 'ne': {
|
||||
// For notEquals, we need all IDs EXCEPT those matching the value
|
||||
// This is especially important for soft delete: deleted !== true
|
||||
// should include items without a deleted field
|
||||
|
||||
// Use EntityIdMapper universe (in-memory) instead of getAllIds() storage scan
|
||||
const allKnownIds = this.idMapper.intsIterableToUuids(this.idMapper.getAllIntIds())
|
||||
|
||||
// Then get IDs that match the value we want to exclude
|
||||
const excludeIds = await this.getIds(field, operand)
|
||||
const excludeSet = new Set(excludeIds)
|
||||
|
||||
// Return all IDs except those to exclude
|
||||
fieldResults = allKnownIds.filter(id => !excludeSet.has(id))
|
||||
// All ids EXCEPT those matching the value. Important for soft delete:
|
||||
// `deleted !== true` must include items WITHOUT a deleted field. The
|
||||
// excluded set is typically small (the matching value); compute the
|
||||
// complement as a bitmap difference over the int-id universe rather
|
||||
// than materializing the whole corpus as UUID strings to filter it.
|
||||
const excludeInts: number[] = []
|
||||
for (const uuid of await this.getIds(field, operand)) {
|
||||
const intId = this.idMapper.getInt(uuid)
|
||||
if (intId !== undefined) excludeInts.push(intId)
|
||||
}
|
||||
fieldResults = this.complementIds(excludeInts)
|
||||
break
|
||||
}
|
||||
|
||||
|
|
@ -1972,11 +1970,8 @@ export class MetadataIndexManager implements MetadataIndexProvider {
|
|||
// exists: true — entities that HAVE this field
|
||||
fieldResults = this.idMapper.intsIterableToUuids(existsBitmap)
|
||||
} else {
|
||||
// exists: false — entities that DON'T have this field
|
||||
const allKnownIds = this.idMapper.intsIterableToUuids(this.idMapper.getAllIntIds())
|
||||
const existsUuids = this.idMapper.intsIterableToUuids(existsBitmap)
|
||||
const existsSet = new Set(existsUuids)
|
||||
fieldResults = allKnownIds.filter(id => !existsSet.has(id))
|
||||
// exists: false — entities that DON'T have this field (universe \ has-field)
|
||||
fieldResults = this.complementIds(existsBitmap)
|
||||
}
|
||||
break
|
||||
}
|
||||
|
|
@ -1989,11 +1984,8 @@ export class MetadataIndexManager implements MetadataIndexProvider {
|
|||
: await this.getExistsBitmapLegacy(field)
|
||||
|
||||
if (operand) {
|
||||
// missing: true — entities that DON'T have this field (same as exists: false)
|
||||
const allKnownIds = this.idMapper.intsIterableToUuids(this.idMapper.getAllIntIds())
|
||||
const existsUuids = this.idMapper.intsIterableToUuids(missingBitmap)
|
||||
const existsSet = new Set(existsUuids)
|
||||
fieldResults = allKnownIds.filter(id => !existsSet.has(id))
|
||||
// missing: true — entities that DON'T have this field (universe \ has-field)
|
||||
fieldResults = this.complementIds(missingBitmap)
|
||||
} else {
|
||||
// missing: false — entities that HAVE this field (same as exists: true)
|
||||
fieldResults = this.idMapper.intsIterableToUuids(missingBitmap)
|
||||
|
|
@ -2066,6 +2058,21 @@ export class MetadataIndexManager implements MetadataIndexProvider {
|
|||
* @returns Roaring bitmap of entity int IDs (or iterable for compatibility)
|
||||
* @private
|
||||
*/
|
||||
/**
|
||||
* All ids EXCEPT the excluded int-id set, computed as a roaring-bitmap difference
|
||||
* over the int-id universe. Used by the negation/absence operators (`ne`,
|
||||
* `exists:false`, `missing:true`) so they don't first materialize the ENTIRE
|
||||
* corpus as an array of UUID strings (plus a Set, plus an O(N) filter pass) just
|
||||
* to remove a small subset — only the final result is converted back to UUIDs.
|
||||
*/
|
||||
private complementIds(excludeInts: Iterable<number>): string[] {
|
||||
const universe = new RoaringBitmap32()
|
||||
for (const intId of this.idMapper.getAllIntIds()) universe.add(intId)
|
||||
const exclude = new RoaringBitmap32()
|
||||
for (const intId of excludeInts) exclude.add(intId)
|
||||
return this.idMapper.intsIterableToUuids(RoaringBitmap32.andNot(universe, exclude))
|
||||
}
|
||||
|
||||
private async getExistsBitmapLegacy(field: string): Promise<Iterable<number>> {
|
||||
const allIntIds = new Set<number>()
|
||||
const sparseIndex = await this.loadSparseIndex(field)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue