Add D&D NPC extraction and validation

internal/modules/dnd/validate/npcs/source_relatedness/validator.go

@@ -0,0 +1,114 @@
+package sourcerelatedness
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"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/npcs/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcs/diagnostics"
+	npcshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcs/shape"
+)
+
+const (
+	Key               = "extract/dnd/npcs/source_relatedness"
+	WarningReasonCode = "npc_not_near_source"
+	policy            = "dnd.npcs.validator.source_relatedness.v1"
+)
+
+type Options struct{}
+type Validator struct{}
+
+var _ contracts.TypedValidator[dnd.NPCList] = (*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.NPCList]) (contracts.ValidationResult, error) {
+	if err := npcshape.Validate(req.Value); err != nil {
+		return contracts.ValidationResult{Approved: true}, nil
+	}
+	var warnings []contracts.Warning
+	for npcIndex, npc := range req.Value.NPCs {
+		if npcAppearsInCitedText(req.Source, npc) {
+			continue
+		}
+		warnings = append(warnings, contracts.Warning{
+			Scope:      fmt.Sprintf("npcs[%d]", npcIndex),
+			ReasonCode: WarningReasonCode,
+			Message:    fmt.Sprintf("NPC %s was not found in cited source text", diagnostics.Quote(npc.Name)),
+		})
+	}
+	return contracts.ValidationResult{Approved: true, Warnings: warnings}, nil
+}
+
+func npcAppearsInCitedText(doc *source.SourceDocument, npc dnd.NPC) bool {
+	cited := citedTextKey(doc, npc.SourceRefs)
+	if cited == "" {
+		return false
+	}
+	if strings.Contains(cited, identity.ComparisonKey(npc.Name)) {
+		return true
+	}
+	for _, alias := range npc.Aliases {
+		if strings.Contains(cited, identity.ComparisonKey(alias)) {
+			return true
+		}
+	}
+	return false
+}
+
+func citedTextKey(doc *source.SourceDocument, refs []source.SourceRef) string {
+	if doc == nil {
+		return ""
+	}
+	var builder strings.Builder
+	for _, ref := range refs {
+		if err := source.ValidateRef(doc, ref); err != nil {
+			continue
+		}
+		start, _ := source.UnitIndex(doc, ref.StartUnitID)
+		end, _ := source.UnitIndex(doc, ref.EndUnitID)
+		for index := start; index <= end; index++ {
+			if builder.Len() > 0 {
+				builder.WriteByte(' ')
+			}
+			builder.WriteString(doc.Units[index].Text)
+		}
+	}
+	return identity.ComparisonKey(builder.String())
+}
+
+func Spec() pipeline.ValidatorSpec {
+	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
+}
+
+func Register(registry *pipeline.ValidatorRegistry) error {
+	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.NPCListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.NPCList], 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 }