Add D&D location occurrence validators

This commit is contained in:
2026-08-04 00:33:39 +00:00
parent dd61a4efda
commit a168c13b85
14 changed files with 1034 additions and 3 deletions

View File

@@ -0,0 +1,92 @@
// Package sourcerefs validates location occurrence 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/shared/diagnostics"
occurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationoccurrences/shape"
)
const (
Key = "extract/dnd/location-occurrences/source_refs"
ReasonCode = "invalid_location_occurrence_source_refs"
policy = "dnd.location_occurrences.validator.source_refs.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 req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
return contracts.ValidationResult{}, fmt.Errorf("location occurrence source-reference validator requires the current extraction chunk")
}
if occurrenceshape.Validate(req.Value) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
index := source.NewDocumentIndex(req.Source)
issues := make([]string, 0)
for occurrenceIndex, occurrence := range req.Value.Occurrences {
for refIndex, ref := range occurrence.SourceRefs {
if err := index.ValidateRef(ref); err != nil {
issues = append(issues, fmt.Sprintf("occurrences[%d].source_refs[%d]: %s", occurrenceIndex, refIndex, diagnostics.Truncate(err.Error())))
continue
}
if req.Stage == string(pipeline.StageExtract) && !chunkContainsRef(req.Chunk, ref) {
issues = append(issues, fmt.Sprintf("occurrences[%d].source_refs[%d]: source reference is outside the current extraction chunk", occurrenceIndex, refIndex))
}
}
}
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: diagnostics.Aggregate("invalid location occurrence source references", issues)}, nil
}
func chunkContainsRef(chunk *source.Chunk, ref source.SourceRef) bool {
if chunk == nil || ref.SourceID != chunk.SourceID {
return false
}
startFound, endFound := false, 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.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 }

View File

@@ -0,0 +1,66 @@
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 TestValidatorRejectsInvalidAndOutOfChunkEvidenceWithoutMutation(t *testing.T) {
doc := document()
value := occurrenceList()
value.Occurrences[0].SourceRefs = []source.SourceRef{{SourceID: "foreign", StartUnitID: 1, EndUnitID: 1}, {SourceID: "session", StartUnitID: 2, EndUnitID: 2}}
before := cloneList(value)
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.LocationOccurrenceList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: &source.Chunk{SourceID: "session", Units: []source.SourceUnit{{ID: 1}}}, Value: value})
if err != nil || result.Approved || result.ReasonCode != ReasonCode || !strings.Contains(result.Message, "occurrences[0].source_refs[0]") || !strings.Contains(result.Message, "outside the current extraction chunk") {
t.Fatalf("Validate() = %#v, %v", result, err)
}
if !reflect.DeepEqual(value, before) || len(result.Message) > 4096 || !utf8.ValidString(result.Message) {
t.Fatal("validation mutated value or returned unsafe diagnostics")
}
}
func TestValidatorRequiresChunkDuringExtractionAndDefersShape(t *testing.T) {
_, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.LocationOccurrenceList]{Stage: string(pipeline.StageExtract), Source: document(), Value: occurrenceList()})
if err == nil || !strings.Contains(err.Error(), "requires the current extraction chunk") {
t.Fatalf("missing chunk error = %v", err)
}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.LocationOccurrenceList]{Source: document(), Value: dnd.LocationOccurrenceList{Occurrences: []dnd.LocationOccurrence{{Name: "Missing"}}}})
if err != nil || !result.Approved {
t.Fatalf("shape deferral = %#v, %v", result, err)
}
}
func TestValidatorRegisters(t *testing.T) {
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatal(err)
}
if got, ok := registry.Spec(Key); !ok || got != Spec() || got.ExecutionClass != contracts.ExecutionClassDeterministic {
t.Fatalf("registered spec = %#v, ok = %t", got, ok)
}
if got := New(Options{}).CheckpointFingerprints(); len(got) != 1 || got[0].Value != policy {
t.Fatalf("fingerprints = %#v", got)
}
}
func document() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1}, {ID: 2}}}
}
func occurrenceList() dnd.LocationOccurrenceList {
return dnd.LocationOccurrenceList{Occurrences: []dnd.LocationOccurrence{{LocationID: "id", Name: "Moon Gate", Kind: dnd.LocationOccurrenceKindVisited, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
}
func cloneList(value dnd.LocationOccurrenceList) dnd.LocationOccurrenceList {
cloned := dnd.LocationOccurrenceList{Occurrences: append([]dnd.LocationOccurrence(nil), value.Occurrences...)}
for index := range cloned.Occurrences {
cloned.Occurrences[index].SourceRefs = append([]source.SourceRef(nil), value.Occurrences[index].SourceRefs...)
}
return cloned
}