Files

92 lines
3.2 KiB
Go
Raw Permalink Normal View History

2026-07-21 02:24:26 +00:00
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"
2026-07-21 14:37:12 +00:00
"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/npcregistry/shape"
2026-07-21 02:24:26 +00:00
)
const (
Key = "extract/dnd/npc-registry/source_relatedness"
ReasonCode = "npc_not_near_source"
policy = "dnd.npc_registry.validator.source_relatedness.v2"
2026-07-21 02:24:26 +00:00
)
type Options struct{}
type Validator struct{}
2026-08-05 18:25:04 +00:00
var _ contracts.TypedValidator[dnd.NPCRegistry] = (*Validator)(nil)
2026-07-21 02:24:26 +00:00
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}}
}
2026-08-05 18:25:04 +00:00
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.NPCRegistry]) (contracts.ValidationResult, error) {
2026-07-21 02:24:26 +00:00
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
}
2026-07-21 14:37:12 +00:00
citedTexts := make([]string, len(req.Value.NPCs))
for npcIndex, npc := range req.Value.NPCs {
citedText, err := resolver.CitedText(npc.SourceRefs)
2026-07-21 14:37:12 +00:00
if err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
citedTexts[npcIndex] = citedText
}
var findings []diagnostics.Finding
2026-07-21 02:24:26 +00:00
for npcIndex, npc := range req.Value.NPCs {
2026-07-21 14:37:12 +00:00
if npcAppearsInCitedText(citedTexts[npcIndex], npc) {
2026-07-21 02:24:26 +00:00
continue
}
findings = append(findings, diagnostics.Finding{
2026-07-21 02:24:26 +00:00
Scope: fmt.Sprintf("npcs[%d]", npcIndex),
ReasonCode: ReasonCode,
2026-07-21 02:24:26 +00:00
Message: fmt.Sprintf("NPC %s was not found in cited source text", diagnostics.Quote(npc.Name)),
})
}
return diagnostics.DataQualityResult(findings)
2026-07-21 02:24:26 +00:00
}
2026-07-21 14:37:12 +00:00
func npcAppearsInCitedText(citedText string, npc dnd.NPC) bool {
2026-07-22 18:51:26 +00:00
return shared.ContainsTokenSequence(citedText, npc.Name)
2026-07-21 02:24:26 +00:00
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
2026-08-05 18:25:04 +00:00
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.NPCRegistryKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.NPCRegistry], error) {
2026-07-21 02:24:26 +00:00
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 }