milvus/internal/parser/planparserv2/plan_parser_v2.go
Tianx 2c0c5ef41e
feat: timestamptz expression & index & timezone (#44080)
issue: https://github.com/milvus-io/milvus/issues/27467

>My plan is as follows.
>- [x] M1 Create collection with timestamptz field
>- [x] M2 Insert timestamptz field data
>- [x] M3 Retrieve timestamptz field data
>- [x] M4 Implement handoff
>- [x] M5 Implement compare operator
>- [x] M6 Implement extract operator
 >- [x] M8 Support database/collection level default timezone
>- [x] M7 Support STL-SORT index for datatype timestamptz

---

The third PR of issue: https://github.com/milvus-io/milvus/issues/27467,
which completes M5, M6, M7, M8 described above.

## M8 Default Timezone

We will be able to use alter_collection() and alter_database() in a
future Python SDK release to modify the default timezone at the
collection or database level.

For insert requests, the timezone will be resolved using the following
order of precedence: String Literal-> Collection Default -> Database
Default.
For retrieval requests, the timezone will be resolved in this order:
Query Parameters -> Collection Default -> Database Default.
In both cases, the final fallback timezone is UTC.


## M5: Comparison Operators

We can now use the following expression format to filter on the
timestamptz field:

- `timestamptz_field [+/- INTERVAL 'interval_string'] {comparison_op}
ISO 'iso_string' `

- The interval_string follows the ISO 8601 duration format, for example:
P1Y2M3DT1H2M3S.

- The iso_string follows the ISO 8601 timestamp format, for example:
2025-01-03T00:00:00+08:00.

- Example expressions: "tsz + INTERVAL 'P0D' != ISO
'2025-01-03T00:00:00+08:00'" or "tsz != ISO
'2025-01-03T00:00:00+08:00'".

## M6: Extract

We will be able to extract sepecific time filed by kwargs in a future
Python SDK release.
The key is `time_fields`, and value should be one or more of "year,
month, day, hour, minute, second, microsecond", seperated by comma or
space. Then the result of each record would be an array of int64.



## M7: Indexing Support

Expressions without interval arithmetic can be accelerated using an
STL-SORT index. However, expressions that include interval arithmetic
cannot be indexed. This is because the result of an interval calculation
depends on the specific timestamp value. For example, adding one month
to a date in February results in a different number of added days than
adding one month to a date in March.

--- 

After this PR, the input / output type of timestamptz would be iso
string. Timestampz would be stored as timestamptz data, which is int64_t
finally.

> for more information, see https://en.wikipedia.org/wiki/ISO_8601

---------

Signed-off-by: xtx <xtianx@smail.nju.edu.cn>
2025-09-23 10:24:12 +08:00

387 lines
12 KiB
Go

package planparserv2
import (
"fmt"
"strconv"
"time"
"github.com/antlr4-go/antlr/v4"
"github.com/hashicorp/golang-lru/v2/expirable"
"github.com/samber/lo"
"go.uber.org/zap"
"github.com/milvus-io/milvus-proto/go-api/v2/schemapb"
planparserv2 "github.com/milvus-io/milvus/internal/parser/planparserv2/generated"
"github.com/milvus-io/milvus/internal/util/function/rerank"
"github.com/milvus-io/milvus/pkg/v2/common"
"github.com/milvus-io/milvus/pkg/v2/log"
"github.com/milvus-io/milvus/pkg/v2/proto/planpb"
"github.com/milvus-io/milvus/pkg/v2/util/funcutil"
"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
"github.com/milvus-io/milvus/pkg/v2/util/typeutil"
)
var (
exprCache = expirable.NewLRU[string, any](1024, nil, time.Minute*10)
trueLiteral = &ExprWithType{
dataType: schemapb.DataType_Bool,
expr: alwaysTrueExpr(),
}
)
type ExprParams struct {
UseJSONStats bool
}
func ParseExprParams(vals map[string]*schemapb.TemplateValue) *ExprParams {
ep := &ExprParams{
UseJSONStats: paramtable.Get().CommonCfg.UsingJSONStatsForQuery.GetAsBool(),
}
if vals != nil {
if v, ok := vals[common.ExprUseJSONStatsKey]; ok && v != nil {
ep.UseJSONStats = v.GetBoolVal()
}
}
return ep
}
func handleInternal(exprStr string) (ast planparserv2.IExprContext, err error) {
val, ok := exprCache.Get(exprStr)
if ok {
switch v := val.(type) {
case planparserv2.IExprContext:
return v, nil
case error:
return nil, v
default:
return nil, fmt.Errorf("unknown cache error: %v", v)
}
}
// Note that the errors will be cached, too.
defer func() {
if err != nil {
exprCache.Add(exprStr, err)
}
}()
exprNormal := convertHanToASCII(exprStr)
listener := &errorListenerImpl{}
inputStream := antlr.NewInputStream(exprNormal)
lexer := getLexer(inputStream, listener)
if err = listener.Error(); err != nil {
return
}
parser := getParser(lexer, listener)
if err = listener.Error(); err != nil {
return
}
ast = parser.Expr()
if err = listener.Error(); err != nil {
return
}
if parser.GetCurrentToken().GetTokenType() != antlr.TokenEOF {
log.Info("invalid expression", zap.String("expr", exprStr))
err = fmt.Errorf("invalid expression: %s", exprStr)
return
}
// lexer & parser won't be used by this thread, can be put into pool.
putLexer(lexer)
putParser(parser)
exprCache.Add(exprStr, ast)
return
}
func handleExprInternal(schema *typeutil.SchemaHelper, exprStr string, visitorArgs *ParserVisitorArgs) (result interface{}) {
defer func() {
if r := recover(); r != nil {
result = fmt.Errorf("unsupported expression: %s", exprStr)
}
}()
if isEmptyExpression(exprStr) {
return trueLiteral
}
ast, err := handleInternal(exprStr)
if err != nil {
return err
}
visitor := NewParserVisitor(schema, visitorArgs)
return ast.Accept(visitor)
}
func handleExpr(schema *typeutil.SchemaHelper, exprStr string) (result interface{}) {
return handleExprInternal(schema, exprStr, &ParserVisitorArgs{})
}
func parseExprInner(schema *typeutil.SchemaHelper, exprStr string, exprTemplateValues map[string]*schemapb.TemplateValue, visitorArgs *ParserVisitorArgs) (*planpb.Expr, error) {
ret := handleExprInternal(schema, exprStr, visitorArgs)
if err := getError(ret); err != nil {
return nil, fmt.Errorf("cannot parse expression: %s, error: %s", exprStr, err)
}
predicate := getExpr(ret)
if predicate == nil {
return nil, fmt.Errorf("cannot parse expression: %s", exprStr)
}
if !canBeExecuted(predicate) {
return nil, fmt.Errorf("predicate is not a boolean expression: %s, data type: %s", exprStr, predicate.dataType)
}
valueMap, err := UnmarshalExpressionValues(exprTemplateValues)
if err != nil {
return nil, err
}
if err := FillExpressionValue(predicate.expr, valueMap); err != nil {
return nil, err
}
return predicate.expr, nil
}
func ParseExpr(schema *typeutil.SchemaHelper, exprStr string, exprTemplateValues map[string]*schemapb.TemplateValue) (*planpb.Expr, error) {
return parseExprInner(schema, exprStr, exprTemplateValues, &ParserVisitorArgs{})
}
func parseIdentifierInner(schema *typeutil.SchemaHelper, identifier string, checkFunc func(*planpb.Expr) error, visitorArgs *ParserVisitorArgs) error {
ret := handleExprInternal(schema, identifier, visitorArgs)
if err := getError(ret); err != nil {
return fmt.Errorf("cannot parse identifier: %s, error: %s", identifier, err)
}
predicate := getExpr(ret)
if predicate == nil {
return fmt.Errorf("cannot parse identifier: %s", identifier)
}
if predicate.expr.GetColumnExpr() == nil {
return fmt.Errorf("cannot parse identifier: %s", identifier)
}
return checkFunc(predicate.expr)
}
func ParseIdentifier(schema *typeutil.SchemaHelper, identifier string, checkFunc func(*planpb.Expr) error) error {
visitorArgs := &ParserVisitorArgs{}
return parseIdentifierInner(schema, identifier, checkFunc, visitorArgs)
}
func CreateRetrievePlanArgs(schema *typeutil.SchemaHelper, exprStr string, exprTemplateValues map[string]*schemapb.TemplateValue, visitorArgs *ParserVisitorArgs) (*planpb.PlanNode, error) {
expr, err := parseExprInner(schema, exprStr, exprTemplateValues, visitorArgs)
if err != nil {
return nil, err
}
exprParams := ParseExprParams(exprTemplateValues)
planNode := &planpb.PlanNode{
Node: &planpb.PlanNode_Query{
Query: &planpb.QueryPlanNode{
Predicates: expr,
},
},
PlanOptions: &planpb.PlanOption{
ExprUseJsonStats: exprParams.UseJSONStats,
},
}
return planNode, nil
}
func CreateRetrievePlan(schema *typeutil.SchemaHelper, exprStr string, exprTemplateValues map[string]*schemapb.TemplateValue) (*planpb.PlanNode, error) {
visitorArgs := &ParserVisitorArgs{}
return CreateRetrievePlanArgs(schema, exprStr, exprTemplateValues, visitorArgs)
}
func CreateSearchPlanArgs(schema *typeutil.SchemaHelper, exprStr string, vectorFieldName string, queryInfo *planpb.QueryInfo, exprTemplateValues map[string]*schemapb.TemplateValue, functionScorer *schemapb.FunctionScore, visitorArgs *ParserVisitorArgs) (*planpb.PlanNode, error) {
parse := func() (*planpb.Expr, error) {
if len(exprStr) <= 0 {
return nil, nil
}
return parseExprInner(schema, exprStr, exprTemplateValues, visitorArgs)
}
expr, err := parse()
if err != nil {
log.Info("CreateSearchPlan failed", zap.Error(err))
return nil, err
}
vectorField, err := schema.GetFieldFromName(vectorFieldName)
if err != nil {
log.Info("CreateSearchPlan failed", zap.Error(err))
return nil, err
}
// plan ok with schema, check ann field
fieldID := vectorField.FieldID
dataType := vectorField.DataType
elementType := vectorField.ElementType
var vectorType planpb.VectorType
if !typeutil.IsVectorType(dataType) {
return nil, fmt.Errorf("field (%s) to search is not of vector data type", vectorFieldName)
}
switch dataType {
case schemapb.DataType_BinaryVector:
vectorType = planpb.VectorType_BinaryVector
case schemapb.DataType_FloatVector:
vectorType = planpb.VectorType_FloatVector
case schemapb.DataType_Float16Vector:
vectorType = planpb.VectorType_Float16Vector
case schemapb.DataType_BFloat16Vector:
vectorType = planpb.VectorType_BFloat16Vector
case schemapb.DataType_SparseFloatVector:
vectorType = planpb.VectorType_SparseFloatVector
case schemapb.DataType_Int8Vector:
vectorType = planpb.VectorType_Int8Vector
case schemapb.DataType_ArrayOfVector:
switch elementType {
case schemapb.DataType_FloatVector:
vectorType = planpb.VectorType_EmbListFloatVector
default:
log.Error("Invalid elementType", zap.Any("elementType", elementType))
return nil, err
}
default:
log.Error("Invalid dataType", zap.Any("dataType", dataType))
return nil, err
}
scorers, err := CreateSearchScorers(schema, functionScorer, exprTemplateValues)
if err != nil {
return nil, err
}
if len(scorers) != 0 && (queryInfo.GroupByFieldId != -1 || queryInfo.SearchIteratorV2Info != nil) {
return nil, fmt.Errorf("don't support use segment scorer with group_by or search_iterator")
}
exprParams := ParseExprParams(exprTemplateValues)
planNode := &planpb.PlanNode{
Node: &planpb.PlanNode_VectorAnns{
VectorAnns: &planpb.VectorANNS{
VectorType: vectorType,
Predicates: expr,
QueryInfo: queryInfo,
PlaceholderTag: "$0",
FieldId: fieldID,
},
},
Scorers: scorers,
PlanOptions: &planpb.PlanOption{
ExprUseJsonStats: exprParams.UseJSONStats,
},
}
return planNode, nil
}
func CreateSearchScorer(schema *typeutil.SchemaHelper, function *schemapb.FunctionSchema, exprTemplateValues map[string]*schemapb.TemplateValue) (*planpb.ScoreFunction, error) {
rerankerName := rerank.GetRerankName(function)
switch rerankerName {
case rerank.BoostName:
scorer := &planpb.ScoreFunction{}
filter, ok := funcutil.TryGetAttrByKeyFromRepeatedKV(rerank.FilterKey, function.GetParams())
if ok {
expr, err := ParseExpr(schema, filter, exprTemplateValues)
if err != nil {
return nil, fmt.Errorf("parse expr failed with error: {%v}", err)
}
scorer.Filter = expr
}
weightStr, ok := funcutil.TryGetAttrByKeyFromRepeatedKV(rerank.WeightKey, function.GetParams())
if !ok {
return nil, fmt.Errorf("must set weight params for weight scorer")
}
weight, err := strconv.ParseFloat(weightStr, 32)
if err != nil {
return nil, fmt.Errorf("parse function scorer weight params failed with error: {%v}", err)
}
scorer.Weight = float32(weight)
return scorer, nil
default:
// if not boost scorer, regard as normal function scorer
// will be checked at ranker
// return nil here
return nil, nil
}
}
func CreateSearchScorers(schema *typeutil.SchemaHelper, functionScore *schemapb.FunctionScore, exprTemplateValues map[string]*schemapb.TemplateValue) ([]*planpb.ScoreFunction, error) {
scorers := []*planpb.ScoreFunction{}
for _, function := range functionScore.GetFunctions() {
// create scorer for search plan
scorer, err := CreateSearchScorer(schema, function, exprTemplateValues)
if err != nil {
return nil, err
}
if scorer != nil {
scorers = append(scorers, scorer)
}
}
if len(scorers) == 0 {
return nil, nil
}
return scorers, nil
}
func CreateSearchPlan(schema *typeutil.SchemaHelper, exprStr string, vectorFieldName string, queryInfo *planpb.QueryInfo, exprTemplateValues map[string]*schemapb.TemplateValue, functionScorer *schemapb.FunctionScore) (*planpb.PlanNode, error) {
visitorArgs := &ParserVisitorArgs{}
return CreateSearchPlanArgs(schema, exprStr, vectorFieldName, queryInfo, exprTemplateValues, functionScorer, visitorArgs)
}
func CreateRequeryPlan(pkField *schemapb.FieldSchema, ids *schemapb.IDs) *planpb.PlanNode {
var values []*planpb.GenericValue
switch ids.GetIdField().(type) {
case *schemapb.IDs_IntId:
values = lo.Map(ids.GetIntId().GetData(), func(id int64, _ int) *planpb.GenericValue {
return &planpb.GenericValue{
Val: &planpb.GenericValue_Int64Val{
Int64Val: id,
},
}
})
case *schemapb.IDs_StrId:
values = lo.Map(ids.GetStrId().GetData(), func(id string, _ int) *planpb.GenericValue {
return &planpb.GenericValue{
Val: &planpb.GenericValue_StringVal{
StringVal: id,
},
}
})
}
return &planpb.PlanNode{
Node: &planpb.PlanNode_Query{
Query: &planpb.QueryPlanNode{
Predicates: &planpb.Expr{
Expr: &planpb.Expr_TermExpr{
TermExpr: &planpb.TermExpr{
ColumnInfo: &planpb.ColumnInfo{
FieldId: pkField.GetFieldID(),
DataType: pkField.GetDataType(),
IsPrimaryKey: true,
IsAutoID: pkField.GetAutoID(),
IsPartitionKey: pkField.GetIsPartitionKey(),
},
Values: values,
},
},
},
IsCount: false,
Limit: int64(len(values)),
},
},
}
}