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

package sourcerelatedness

import (
	"context"
	"fmt"

	"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"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/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.v2"
)

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
	}
	resolver, err := shared.NewCitationResolver(req.Source)
	if err != nil {
		return contracts.ValidationResult{Approved: true}, nil
	}
	citedTexts := make([]string, len(req.Value.NPCs))
	for npcIndex, npc := range req.Value.NPCs {
		citedText, err := resolver.CitedText(npc.SourceRefs)
		if err != nil {
			return contracts.ValidationResult{Approved: true}, nil
		}
		citedTexts[npcIndex] = citedText
	}
	var warnings []contracts.Warning
	for npcIndex, npc := range req.Value.NPCs {
		if npcAppearsInCitedText(citedTexts[npcIndex], 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(citedText string, npc dnd.NPC) bool {
	return shared.ContainsTokenSequence(citedText, npc.Name)
}

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 }