Move item occurrences to canonical namespace

internal/modules/dnd/validate/itemoccurrences/source_refs/validator.go

@@ -0,0 +1,121 @@
+// Package sourcerefs validates D&D item-occurrence transcript evidence.
+package sourcerefs
+
+import (
+	"context"
+	"fmt"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
+	itemoccurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemoccurrences/shape"
+)
+
+const (
+	Key        = "extract/dnd/item-occurrences/source_refs"
+	ReasonCode = "invalid_item_occurrence_source_references"
+	policy     = "dnd.item_occurrences.source_refs.v1"
+)
+
+type Options struct{}
+type Validator struct{}
+
+var _ contracts.TypedValidator[dnd.ItemOccurrenceList] = (*Validator)(nil)
+var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)
+
+func New(Options) *Validator      { return &Validator{} }
+func (v *Validator) Name() string { return Key }
+func (v *Validator) ExecutionClass() contracts.ExecutionClass {
+	return contracts.ExecutionClassDeterministic
+}
+func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
+	return []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}
+}
+
+func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemOccurrenceList]) (contracts.ValidationResult, error) {
+	if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
+		return contracts.ValidationResult{}, fmt.Errorf("item occurrence source-reference validator requires the current extraction chunk")
+	}
+	if itemoccurrenceshape.Validate(req.Value) != nil {
+		return contracts.ValidationResult{Approved: true}, nil
+	}
+	index := source.NewDocumentIndex(req.Source)
+	var coverage *chunkCoverage
+	if req.Stage == string(pipeline.StageExtract) {
+		coverage = newChunkCoverage(req.Chunk)
+	}
+	issues := make([]string, 0)
+	for occurrenceIndex, occurrence := range req.Value.Occurrences {
+		for refIndex, ref := range occurrence.SourceRefs {
+			if err := index.ValidateRef(ref); err != nil {
+				issues = append(issues, fmt.Sprintf("occurrences[%d].source_refs[%d]: %s", occurrenceIndex, refIndex, diagnostics.Truncate(err.Error())))
+				continue
+			}
+			if coverage != nil && !coverage.contains(req.Source, ref) {
+				issues = append(issues, fmt.Sprintf("occurrences[%d].source_refs[%d]: source reference is outside the current extraction chunk", occurrenceIndex, refIndex))
+			}
+		}
+	}
+	if len(issues) == 0 {
+		return contracts.ValidationResult{Approved: true}, nil
+	}
+	return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: diagnostics.Aggregate("invalid item occurrence source references", issues)}, nil
+}
+
+type chunkCoverage struct {
+	sourceID string
+	unitIDs  map[int]struct{}
+}
+
+func newChunkCoverage(chunk *source.Chunk) *chunkCoverage {
+	coverage := &chunkCoverage{
+		sourceID: chunk.SourceID,
+		unitIDs:  make(map[int]struct{}, len(chunk.Units)),
+	}
+	for _, unit := range chunk.Units {
+		coverage.unitIDs[unit.ID] = struct{}{}
+	}
+	return coverage
+}
+
+func (coverage *chunkCoverage) contains(doc *source.SourceDocument, ref source.SourceRef) bool {
+	if coverage == nil || doc == nil || ref.SourceID != coverage.sourceID {
+		return false
+	}
+	start, startOK := source.UnitIndex(doc, ref.StartUnitID)
+	end, endOK := source.UnitIndex(doc, ref.EndUnitID)
+	if !startOK || !endOK || start > end {
+		return false
+	}
+	for position := start; position <= end; position++ {
+		if _, found := coverage.unitIDs[doc.Units[position].ID]; !found {
+			return false
+		}
+	}
+	return true
+}
+
+func Spec() pipeline.ValidatorSpec {
+	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
+}
+
+func Register(registry *pipeline.ValidatorRegistry) error {
+	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemOccurrenceListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemOccurrenceList], error) {
+		options, err := DecodeOptions(request.Options)
+		if err != nil {
+			return nil, err
+		}
+		return New(options), nil
+	})
+}
+
+func DecodeOptions(options map[string]any) (Options, error) {
+	if err := pipeline.RejectUnknownOptions(options); err != nil {
+		return Options{}, err
+	}
+	return Options{}, nil
+}
+
+func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }