Require chunk-local extraction evidence

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

@@ -15,7 +15,7 @@ import (
 const (
 	Key        = "extract/dnd/npc-registry/source_refs"
 	ReasonCode = "invalid_npc_source_refs"
-	policy     = "dnd.npc_registry.validator.source_refs.v1"
+	policy     = "dnd.npc_registry.validator.source_refs.v2"
 )
 
 type Options struct{}
@@ -34,15 +34,26 @@ func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
 }
 
 func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.NPCRegistry]) (contracts.ValidationResult, error) {
+	if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
+		return contracts.ValidationResult{}, fmt.Errorf("NPC source-reference validator requires the current extraction chunk")
+	}
 	if err := npcshape.Validate(req.Value); err != 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 npcIndex, npc := range req.Value.NPCs {
 		for refIndex, ref := range npc.SourceRefs {
 			if err := index.ValidateRef(ref); err != nil {
 				issues = append(issues, fmt.Sprintf("npcs[%d].source_refs[%d]: %s", npcIndex, refIndex, diagnostics.Truncate(err.Error())))
+				continue
+			}
+			if coverage != nil && !coverage.contains(req.Source, ref) {
+				issues = append(issues, fmt.Sprintf("npcs[%d].source_refs[%d]: source reference is outside the current extraction chunk", npcIndex, refIndex))
 			}
 		}
 	}
@@ -52,6 +63,36 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
 	return rejection(diagnostics.Aggregate("invalid NPC 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}
 }