Files
signoz/pkg/querybuilder/exists_expr.go
Srikanth Chekuri 9c886be120 chore(querybuilder): compile every signal through one storage contract (#12802)
The semantic convention family as first call citizen revealed that the
current state of the query builder needs a bit refactoring for long term
maintenance.

The `FieldMapper` and `ConditionBuilder` are now one abstraction
`Storage`.

A storage now answers
- what the compiler cannot know i.e one read per field key (the bare
SQL, the membership present or absent, what an absent row reads, and
whether the read keeps its type or filters only).
- the fallback for a key metadata does not report
- its traits
- and one Condition compilation part.

And we introduce a new type to use in the system, `Resolved`

```
// Resolved is what resolution produces for one key: its meanings, and how
// they came to be. It is the only thing the compilers receive. Compile it
// with the operator and value it was resolved with.
type Resolved struct {
	Key    *telemetrytypes.TelemetryFieldKey
	Fields []*telemetrytypes.LogicalField
	// FromFallback: the fields came from the storage's fallback, not from
	// metadata matches.
	FromFallback bool
	// Ambiguous: the matches held several interpretations.
	Ambiguous bool
	// Skipped: the storage contributes nothing for this key.
	Skipped  bool
	Warnings []string
}
```

The prepared SQL has no changes, where it changed, it specifically made
the expression better by removing the redundant part.

- The prepared SQL remains identical with this refactoring
- No changes to integration tests


Assisted-by: Claude Fable 5.1
2026-09-15 11:36:06 +00:00

112 lines
4.3 KiB
Go

package querybuilder
import (
"fmt"
schema "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
"github.com/SigNoz/signoz/pkg/clickhousesql"
"github.com/SigNoz/signoz/pkg/errors"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
)
// ExistsExpression renders the existence predicate for a key resolved to the given
// columns (negated when exists is false). Comparisons are against constants rendered
// as literals, so the expression carries no bind args and can guard column expressions
// directly. Signal-specific presence checks (body JSON paths, label maps) are handled
// by the field mappers before falling through to this.
func ExistsExpression(columns []*schema.Column, key *telemetrytypes.TelemetryFieldKey, tsStart, tsEnd uint64, fieldExpression string, exists bool) (string, error) {
newColumns, evolutionsEntries, err := qbtypes.SelectEvolutionsForColumns(columns, key.Evolutions, tsStart, tsEnd)
if err != nil {
return "", err
}
if len(newColumns) == 0 {
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "no valid evolution found for field %s in the given time range", key.Name)
}
comparison := func(operator string, value string) string {
return fmt.Sprintf("%s %s %s", fieldExpression, operator, value)
}
if len(newColumns) > 1 {
if exists {
return fieldExpression + " IS NOT NULL", nil
}
return fieldExpression + " IS NULL", nil
}
column := newColumns[0]
switch column.Type.GetType() {
case schema.ColumnTypeEnumJSON:
// the ::String cast in the value expression folds NULL to '', so the
// presence check must address the raw JSON path
columnName := column.Name
if len(evolutionsEntries) > 0 && evolutionsEntries[0] != nil {
columnName = evolutionsEntries[0].ColumnName
}
rawPath := fmt.Sprintf("%s.%s", columnName, clickhousesql.Identifier(key.Name))
if exists {
return rawPath + " IS NOT NULL", nil
}
return rawPath + " IS NULL", nil
case schema.ColumnTypeEnumString,
schema.ColumnTypeEnumFixedString:
if exists {
return comparison("<>", "''"), nil
}
return comparison("=", "''"), nil
case schema.ColumnTypeEnumDateTime64:
zero := fmt.Sprintf("toDateTime64(0, %d)", column.Type.(schema.DateTime64ColumnType).Precision)
if exists {
return comparison("<>", zero), nil
}
return comparison("=", zero), nil
case schema.ColumnTypeEnumLowCardinality:
switch elementType := column.Type.(schema.LowCardinalityColumnType).ElementType; elementType.GetType() {
case schema.ColumnTypeEnumString:
if exists {
return comparison("<>", "''"), nil
}
return comparison("=", "''"), nil
default:
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "exists operator is not supported for low cardinality column type %s", elementType)
}
case schema.ColumnTypeEnumUInt64,
schema.ColumnTypeEnumUInt32,
schema.ColumnTypeEnumUInt8,
schema.ColumnTypeEnumInt8,
schema.ColumnTypeEnumInt16,
schema.ColumnTypeEnumBool:
if exists {
return comparison("<>", "0"), nil
}
return comparison("=", "0"), nil
case schema.ColumnTypeEnumArray:
if exists {
return fmt.Sprintf("notEmpty(%s)", fieldExpression), nil
}
return fmt.Sprintf("empty(%s)", fieldExpression), nil
case schema.ColumnTypeEnumMap:
keyType := column.Type.(schema.MapColumnType).KeyType
if _, ok := keyType.(schema.LowCardinalityColumnType); !ok {
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "key type %s is not supported for map column type %s", keyType, column.Type)
}
switch valueType := column.Type.(schema.MapColumnType).ValueType; valueType.GetType() {
case schema.ColumnTypeEnumString, schema.ColumnTypeEnumBool, schema.ColumnTypeEnumFloat64:
leftOperand := fmt.Sprintf("mapContains(%s, %s)", column.Name, clickhousesql.StringLiteral(key.Name))
if key.Materialized {
leftOperand = telemetrytypes.FieldKeyToMaterializedColumnNameForExists(key)
}
if exists {
return leftOperand, nil
}
return "NOT " + leftOperand, nil
default:
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "exists operator is not supported for map column type %s", valueType)
}
default:
return "", errors.NewInvalidInputf(errors.CodeInvalidInput, "exists operator is not supported for column type %s", column.Type)
}
}