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

// Package sourcerelatedness reports advisory findings when cited source text does not mention a location occurrence.
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"
	occurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/shape"
)

const (
	Key        = "extract/dnd/location-occurrences/source_relatedness"
	ReasonCode = "location_occurrence_not_near_source"
	policy     = "dnd.location_occurrences.validator.source_relatedness.v1"
)

type Options struct{}
type Validator struct{}

var _ contracts.TypedValidator[dnd.LocationOccurrenceList] = (*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.LocationOccurrenceList]) (contracts.ValidationResult, error) {
	if occurrenceshape.Validate(req.Value) != 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.Occurrences))
	for index, occurrence := range req.Value.Occurrences {
		citedText, err := resolver.CitedText(occurrence.SourceRefs)
		if err != nil {
			return contracts.ValidationResult{Approved: true}, nil
		}
		citedTexts[index] = citedText
	}
	findings := make([]diagnostics.Finding, 0)
	for index, occurrence := range req.Value.Occurrences {
		if shared.ContainsTokenSequence(citedTexts[index], occurrence.Name) {
			continue
		}
		findings = append(findings, diagnostics.Finding{Scope: fmt.Sprintf("occurrences[%d]", index), ReasonCode: ReasonCode, Message: fmt.Sprintf("Location occurrence name %s was not found in cited source text", diagnostics.Quote(occurrence.Name))})
	}
	return diagnostics.DataQualityResult(findings)
}
func Spec() pipeline.ValidatorSpec {
	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.LocationOccurrenceListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.LocationOccurrenceList], 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 }