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

package sourcerelatedness

import (
	"context"
	"fmt"
	"strings"

	"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"
	spellshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/spells/shape"
)

const (
	Key        = "extract/dnd/spells/source_relatedness"
	ReasonCode = "spell_not_near_source"
	policy     = "dnd.spells.validator.source_relatedness.v1"
)

type Options struct{}
type Validator struct{}

var _ contracts.TypedValidator[dnd.SpellList] = (*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.SpellList]) (contracts.ValidationResult, error) {
	if err := spellshape.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.SpellCasts))
	for spellIndex, spell := range req.Value.SpellCasts {
		citedText, err := resolver.CitedText(spell.SourceRefs)
		if err != nil {
			return contracts.ValidationResult{Approved: true}, nil
		}
		citedTexts[spellIndex] = citedText
	}
	var findings []diagnostics.Finding
	for spellIndex, spell := range req.Value.SpellCasts {
		if !spellAppearsInCitedText(citedTexts[spellIndex], spell) {
			findings = append(findings, diagnostics.Finding{Scope: fmt.Sprintf("spell_casts[%d]", spellIndex), ReasonCode: ReasonCode, Message: fmt.Sprintf("spell %s was not found in cited source text", diagnostics.Quote(strings.TrimSpace(spell.Spell)))})
		}
	}
	return diagnostics.DataQualityResult(findings)
}
func spellAppearsInCitedText(citedText string, spell dnd.SpellCast) bool {
	name := strings.TrimSpace(spell.Spell)
	if name == "" {
		return true
	}
	return shared.ContainsTokenSequence(citedText, name)
}
func Spec() pipeline.ValidatorSpec {
	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.SpellListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.SpellList], 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 }