Add D&D item event validators

This commit is contained in:
2026-07-25 21:52:59 +00:00
parent f51b22bea7
commit da83510234
4 changed files with 433 additions and 0 deletions

View File

@@ -0,0 +1,112 @@
// Package sourcerefs validates D&D item-event transcript evidence.
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/itemevents"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
itemeventshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/shape"
)
const (
Key = "extract/dnd/item-events/source_refs"
ReasonCode = "invalid_item_event_source_references"
policy = "dnd.item_events.source_refs.v1"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.ItemEventList] = (*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.ItemEventList]) (contracts.ValidationResult, error) {
if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
return contracts.ValidationResult{}, fmt.Errorf("item event source-reference validator requires the current extraction chunk")
}
if itemeventshape.Validate(req.Value) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
index := source.NewDocumentIndex(req.Source)
issues := make([]string, 0)
for eventIndex, event := range req.Value.Events {
if itemevents.ValidSourceRefs(index, event.SourceRefs) {
if req.Stage != string(pipeline.StageExtract) || refsFitChunk(req.Chunk, event.SourceRefs) {
continue
}
}
for refIndex, ref := range event.SourceRefs {
if err := index.ValidateRef(ref); err != nil {
issues = append(issues, fmt.Sprintf("events[%d].source_refs[%d]: %s", eventIndex, refIndex, diagnostics.Truncate(err.Error())))
continue
}
if req.Stage == string(pipeline.StageExtract) && !chunkContainsRef(req.Chunk, ref) {
issues = append(issues, fmt.Sprintf("events[%d].source_refs[%d]: source reference is outside the current extraction chunk", eventIndex, refIndex))
}
}
}
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: diagnostics.Aggregate("invalid item event source references", issues)}, nil
}
func refsFitChunk(chunk *source.Chunk, refs []source.SourceRef) bool {
for _, ref := range refs {
if !chunkContainsRef(chunk, ref) {
return false
}
}
return true
}
func chunkContainsRef(chunk *source.Chunk, ref source.SourceRef) bool {
if chunk == nil || ref.SourceID != chunk.SourceID {
return false
}
startFound := false
endFound := false
for _, unit := range chunk.Units {
startFound = startFound || unit.ID == ref.StartUnitID
endFound = endFound || unit.ID == ref.EndUnitID
}
return startFound && endFound
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemEventListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemEventList], 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 +1,113 @@
package sourcerefs
import (
"context"
"reflect"
"strings"
"testing"
"unicode/utf8"
"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 TestValidatorOwnsSourceAndRangeValidation(t *testing.T) {
value := validList()
result, err := New(Options{}).Validate(context.Background(), request(document(), value))
if err != nil || !result.Approved {
t.Fatalf("valid result = %#v, %v", result, err)
}
value.Events[0].SourceRefs = []source.SourceRef{
{SourceID: "foreign", StartUnitID: 1, EndUnitID: 1},
{SourceID: "session", StartUnitID: 99, EndUnitID: 99},
{SourceID: "session", StartUnitID: 2, EndUnitID: 1},
}
result, err = New(Options{}).Validate(context.Background(), request(document(), value))
if err != nil || result.Approved || result.ReasonCode != ReasonCode {
t.Fatalf("invalid result = %#v, %v", result, err)
}
for _, index := range []string{"events[0].source_refs[0]", "events[0].source_refs[1]", "events[0].source_refs[2]"} {
if !strings.Contains(result.Message, index) {
t.Fatalf("validation message = %q, missing %q", result.Message, index)
}
}
}
func TestValidatorEnforcesChunkOnlyDuringExtraction(t *testing.T) {
doc := document()
chunk := &source.Chunk{ID: "chunk-0", SourceID: doc.ID, Units: append([]source.SourceUnit(nil), doc.Units[:2]...)}
contained := validList()
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: chunk, Value: contained})
if err != nil || !result.Approved {
t.Fatalf("contained evidence = %#v, %v", result, err)
}
crossesChunk := validList()
crossesChunk.Events[0].SourceRefs = []source.SourceRef{{SourceID: doc.ID, StartUnitID: 2, EndUnitID: 3}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: chunk, Value: crossesChunk})
if err != nil || result.Approved || !strings.Contains(result.Message, "outside the current extraction chunk") {
t.Fatalf("out-of-chunk evidence = %#v, %v", result, err)
}
multiRange := validList()
multiRange.Events[0].SourceRefs = []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 2}, {SourceID: doc.ID, StartUnitID: 3, EndUnitID: 4}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: doc, Value: multiRange})
if err != nil || !result.Approved {
t.Fatalf("post-merge evidence = %#v, %v", result, err)
}
}
func TestValidatorRequiresChunkDuringExtractionAndDefersShape(t *testing.T) {
_, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Stage: string(pipeline.StageExtract), Source: document(), Value: validList()})
if err == nil || !strings.Contains(err.Error(), "requires the current extraction chunk") {
t.Fatalf("Validate() error = %v", err)
}
malformed := dnd.ItemEventList{Events: []dnd.ItemEvent{{Name: "Ring"}}}
result, err := New(Options{}).Validate(context.Background(), request(document(), malformed))
if err != nil || !result.Approved {
t.Fatalf("shape deferral = %#v, %v", result, err)
}
}
func TestValidatorBoundsDiagnosticsAndRegistration(t *testing.T) {
value := dnd.ItemEventList{Events: make([]dnd.ItemEvent, 24)}
for index := range value.Events {
value.Events[index] = dnd.ItemEvent{Name: "Ring", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: "foreign", StartUnitID: index + 1, EndUnitID: index + 1}}}
}
result, err := New(Options{}).Validate(context.Background(), request(document(), value))
if err != nil || result.Approved || result.ReasonCode != ReasonCode || len([]byte(result.Message)) > 4096 || !utf8.ValidString(result.Message) || !strings.Contains(result.Message, "events[0].source_refs[0]") || !strings.Contains(result.Message, "additional issue(s) omitted") {
t.Fatalf("Validate() = %#v, %v", result, err)
}
before := validList()
copy := before
if _, err := New(Options{}).Validate(context.Background(), request(document(), before)); err != nil || !reflect.DeepEqual(before, copy) {
t.Fatal("Validate() mutated input")
}
if got := New(Options{}).CheckpointFingerprints(); !reflect.DeepEqual(got, []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}) {
t.Fatalf("CheckpointFingerprints() = %#v", got)
}
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatal(err)
}
if got, ok := registry.Spec(Key); !ok || !reflect.DeepEqual(got, Spec()) {
t.Fatalf("registry spec = %#v, %t", got, ok)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions() accepted unknown option")
}
}
func request(doc *source.SourceDocument, value dnd.ItemEventList) contracts.TypedValidationRequest[dnd.ItemEventList] {
return contracts.TypedValidationRequest[dnd.ItemEventList]{Source: doc, Value: value}
}
func document() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1}, {ID: 2}, {ID: 3}, {ID: 4}}}
}
func validList() dnd.ItemEventList {
return dnd.ItemEventList{Events: []dnd.ItemEvent{{Name: "Ring", Kind: dnd.ItemEventKindAcquired, To: "party", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 2}}}}}
}