Add D&D scene description validation

This commit is contained in:
2026-07-23 20:17:18 +00:00
parent cd29265d5d
commit ad89782c9b
10 changed files with 1024 additions and 0 deletions

View File

@@ -0,0 +1,90 @@
// Package sourcerefs validates D&D scene-description source identity.
package sourcerefs
import (
"context"
"fmt"
"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/shared/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/scenedescriptions/shape"
)
const (
Key = "extract/dnd/scene-descriptions/source_refs"
ReasonCode = "invalid_scene_description_source_refs"
policy = "dnd.scene_descriptions.validator.source_refs.v1"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.SceneDescriptionList] = (*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.SceneDescriptionList]) (contracts.ValidationResult, error) {
if shape.ValidateForStage(req.Value, req.Stage) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
issues := make([]string, 0)
if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
issues = append(issues, "current extraction chunk must not be nil")
}
for index, scene := range req.Value.Scenes {
prefix := fmt.Sprintf("scenes[%d]", index)
if err := source.ValidateRef(req.Source, scene.SourceRef); err != nil {
issues = append(issues, prefix+".source_ref: "+diagnostics.Truncate(err.Error()))
continue
}
if req.Stage == string(pipeline.StageExtract) && req.Chunk != nil {
if scene.ID != req.Chunk.ID {
issues = append(issues, prefix+".id must equal the current extraction chunk ID")
}
if scene.SourceRef != req.Chunk.Ref {
issues = append(issues, prefix+".source_ref must equal the current extraction chunk range")
}
}
}
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
return contracts.ValidationResult{
Approved: false, ReasonCode: ReasonCode,
Message: diagnostics.Aggregate("invalid scene description source references", issues),
}, nil
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.SceneDescriptionListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.SceneDescriptionList], 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 }

View File

@@ -0,0 +1,59 @@
package sourcerefs
import (
"context"
"reflect"
"testing"
"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"
)
func TestValidatorRequiresExactExtractionChunkIdentity(t *testing.T) {
doc := document()
chunk := &source.Chunk{ID: "chunk-1", SourceID: doc.ID, Ref: source.SourceRef{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 2}}
valid := dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{ID: chunk.ID, SourceRef: chunk.Ref, Kind: dnd.SceneKindNarrative, Title: "Arrival", Summary: "The party arrives."}}}
validator := New(Options{})
for _, test := range []struct {
name string
request contracts.TypedValidationRequest[dnd.SceneDescriptionList]
approved bool
}{
{name: "exact extraction identity", request: contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: chunk, Value: valid}, approved: true},
{name: "wrong ID", request: contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: chunk, Value: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{ID: "other", SourceRef: chunk.Ref, Kind: dnd.SceneKindNarrative, Title: "Arrival", Summary: "The party arrives."}}}}},
{name: "contained but unequal range", request: contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: chunk, Value: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{ID: chunk.ID, SourceRef: source.SourceRef{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}, Kind: dnd.SceneKindNarrative, Title: "Arrival", Summary: "The party arrives."}}}}},
{name: "missing chunk", request: contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Stage: string(pipeline.StageExtract), Source: doc, Value: valid}},
{name: "normalization needs no chunk", request: contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Stage: string(pipeline.StageNormalize), Source: doc, Value: valid}, approved: true},
{name: "invalid current source", request: contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Source: doc, Value: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{ID: "chunk", SourceRef: source.SourceRef{SourceID: doc.ID, StartUnitID: 7, EndUnitID: 7}, Kind: dnd.SceneKindNarrative, Title: "Arrival", Summary: "The party arrives."}}}}},
} {
t.Run(test.name, func(t *testing.T) {
result, err := validator.Validate(context.Background(), test.request)
if err != nil || result.Approved != test.approved {
t.Fatalf("Validate() = %#v, %v; want approved=%t", result, err, test.approved)
}
})
}
}
func TestValidatorDefersMalformedShapeAndRegistersPolicy(t *testing.T) {
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.SceneDescriptionList]{Value: dnd.SceneDescriptionList{}})
if err != nil || !result.Approved {
t.Fatalf("Validate() = %#v, %v; want malformed shape deferred", result, err)
}
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatal(err)
}
if _, ok := registry.Spec(Key); !ok {
t.Fatalf("registry missing %q", Key)
}
if got, want := New(Options{}).CheckpointFingerprints(), []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}; !reflect.DeepEqual(got, want) {
t.Fatalf("fingerprints = %#v, want %#v", got, want)
}
}
func document() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Text: "The party arrives."}, {ID: 2, Text: "They investigate."}}}
}