mirror of
https://gitee.com/milvus-io/milvus.git
synced 2026-01-07 19:31:51 +08:00
b7ee93fc52
related: #36380 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> - Core invariant: aggregation is centralized and schema-aware — all aggregate functions are created via the exec Aggregate registry (milvus::exec::Aggregate) and validated by ValidateAggFieldType, use a single in-memory accumulator layout (Accumulator/RowContainer) and grouping primitives (GroupingSet, HashTable, VectorHasher), ensuring consistent typing, null semantics and offsets across planner → exec → reducer conversion paths (toAggregateInfo, Aggregate::create, GroupingSet, AggResult converters). - Removed / simplified logic: removed ad‑hoc count/group-by and reducer code (CountNode/PhyCountNode, GroupByNode/PhyGroupByNode, cntReducer and its tests) and consolidated into a unified AggregationNode → PhyAggregationNode + GroupingSet + HashTable execution path and centralized reducers (MilvusAggReducer, InternalAggReducer, SegcoreAggReducer). AVG now implemented compositionally (SUM + COUNT) rather than a bespoke operator, eliminating duplicate implementations. - Why this does NOT cause data loss or regressions: existing data-access and serialization paths are preserved and explicitly validated — bulk_subscript / bulk_script_field_data and FieldData creation are used for output materialization; converters (InternalResult2AggResult ↔ AggResult2internalResult, SegcoreResults2AggResult ↔ AggResult2segcoreResult) enforce shape/type/row-count validation; proxy and plan-level checks (MatchAggregationExpression, translateOutputFields, ValidateAggFieldType, translateGroupByFieldIds) reject unsupported inputs (ARRAY/JSON, unsupported datatypes) early. Empty-result generation and explicit error returns guard against silent corruption. - New capability and scope: end-to-end GROUP BY and aggregation support added across the stack — proto (plan.proto, RetrieveRequest fields group_by_field_ids/aggregates), planner nodes (AggregationNode, ProjectNode, SearchGroupByNode), exec operators (PhyAggregationNode, PhyProjectNode) and aggregation core (Aggregate implementations: Sum/Count/Min/Max, SimpleNumericAggregate, RowContainer, GroupingSet, HashTable) plus proxy/querynode reducers and tests — enabling grouped and global aggregation (sum, count, min, max, avg via sum+count) with schema-aware validation and reduction. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: MrPresent-Han <chun.han@gmail.com> Co-authored-by: MrPresent-Han <chun.han@gmail.com>
56 lines
1.8 KiB
Go
56 lines
1.8 KiB
Go
package segments
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
|
|
"github.com/milvus-io/milvus/internal/agg"
|
|
"github.com/milvus-io/milvus/pkg/v2/proto/internalpb"
|
|
"github.com/milvus-io/milvus/pkg/v2/proto/planpb"
|
|
"github.com/milvus-io/milvus/pkg/v2/proto/segcorepb"
|
|
)
|
|
|
|
type InternalAggReducer struct {
|
|
groupAggReducer *agg.GroupAggReducer
|
|
}
|
|
|
|
func NewInternalAggReducer(groupByFieldIds []int64, aggregates []*planpb.Aggregate, groupLimit int64, schema *schemapb.CollectionSchema) *InternalAggReducer {
|
|
return &InternalAggReducer{
|
|
agg.NewGroupAggReducer(groupByFieldIds, aggregates, groupLimit, schema),
|
|
}
|
|
}
|
|
|
|
func (reducer *InternalAggReducer) Reduce(ctx context.Context, results []*internalpb.RetrieveResults) (*internalpb.RetrieveResults, error) {
|
|
reducedAggRes, err := reducer.groupAggReducer.Reduce(ctx, agg.InternalResult2AggResult(results))
|
|
if err != nil || reducedAggRes == nil {
|
|
return nil, err
|
|
}
|
|
return agg.AggResult2internalResult(reducedAggRes), nil
|
|
}
|
|
|
|
type SegcoreAggReducer struct {
|
|
groupAggReducer *agg.GroupAggReducer
|
|
}
|
|
|
|
func NewSegcoreAggReducer(groupByFieldIds []int64, aggregates []*planpb.Aggregate, groupLimit int64, schema *schemapb.CollectionSchema) *SegcoreAggReducer {
|
|
return &SegcoreAggReducer{
|
|
agg.NewGroupAggReducer(groupByFieldIds, aggregates, groupLimit, schema),
|
|
}
|
|
}
|
|
|
|
func (reducer *SegcoreAggReducer) Reduce(ctx context.Context, results []*segcorepb.RetrieveResults, segments []Segment, plan *RetrievePlan) (*segcorepb.RetrieveResults, error) {
|
|
aggRes, err := agg.SegcoreResults2AggResult(results)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
reducedAggRes, err := reducer.groupAggReducer.Reduce(ctx, aggRes)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if reducedAggRes == nil {
|
|
return nil, fmt.Errorf("reduced Segcore Agg Result cannot be nil")
|
|
}
|
|
return agg.AggResult2segcoreResult(reducedAggRes), err
|
|
}
|