Move location registry modules to canonical namespace

This commit is contained in:
2026-08-05 19:13:37 +00:00
parent c006b163d5
commit e8965ebbbb
58 changed files with 172 additions and 144 deletions

View File

@@ -0,0 +1,101 @@
// Package sourcerefs validates location citations against the current source.
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"
locationshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locationregistry/shape"
)
const (
Key = "extract/dnd/location-registry/source_refs"
ReasonCode = "invalid_location_source_refs"
policy = "dnd.location_registry.validator.source_refs.v2"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.LocationRegistry] = (*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.LocationRegistry]) (contracts.ValidationResult, error) {
if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
return contracts.ValidationResult{}, fmt.Errorf("location source-reference validator requires the current extraction chunk")
}
if err := locationshape.Validate(req.Value); err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
index := source.NewDocumentIndex(req.Source)
issues := make([]string, 0)
for locationIndex, location := range req.Value.Locations {
for refIndex, ref := range location.SourceRefs {
if err := index.ValidateRef(ref); err != nil {
issues = append(issues, fmt.Sprintf("locations[%d].source_refs[%d]: %s", locationIndex, refIndex, diagnostics.Truncate(err.Error())))
continue
}
if req.Stage == string(pipeline.StageExtract) && !chunkContainsRef(req.Chunk, ref) {
issues = append(issues, fmt.Sprintf("locations[%d].source_refs[%d]: source reference is outside the current extraction chunk", locationIndex, refIndex))
}
}
}
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
return rejection(diagnostics.Aggregate("invalid location source references", issues)), nil
}
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.LocationRegistryKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.LocationRegistry], 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 }
func rejection(message string) contracts.ValidationResult {
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: message}
}

View File

@@ -0,0 +1,87 @@
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 TestValidatorRejectsForeignAndOutOfRangeReferencesWithoutMutation(t *testing.T) {
value := validLocationRegistry()
value.Locations[0].SourceRefs = []source.SourceRef{{SourceID: "foreign", StartUnitID: 1, EndUnitID: 1}, {SourceID: "session", StartUnitID: 9, EndUnitID: 9}}
before := value
result, err := New(Options{}).Validate(context.Background(), request(validDocument(), value))
if err != nil || result.Approved || result.ReasonCode != ReasonCode || !strings.Contains(result.Message, "locations[0].source_refs[0]") {
t.Fatalf("Validate() = %#v, %v; want source-reference rejection", result, err)
}
if len(result.Message) > 4096 || !utf8.ValidString(result.Message) || !reflect.DeepEqual(value, before) {
t.Fatalf("Validate() produced unsafe diagnostics or mutated value")
}
}
func TestValidatorApprovesValidReferencesAndDefersMalformedShape(t *testing.T) {
result, err := New(Options{}).Validate(context.Background(), request(validDocument(), validLocationRegistry()))
if err != nil || !result.Approved {
t.Fatalf("valid references = %#v, %v", result, err)
}
result, err = New(Options{}).Validate(context.Background(), request(nil, dnd.LocationRegistry{Locations: []dnd.Location{{Name: "Missing"}}}))
if err != nil || !result.Approved || result.ReasonCode != "" {
t.Fatalf("malformed shape = %#v, %v; want deferral", result, err)
}
}
func TestValidatorRequiresCurrentChunkAndRejectsEvidenceOutsideIt(t *testing.T) {
doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1}, {ID: 2}}}
value := validLocationRegistry()
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.LocationRegistry]{
Stage: string(pipeline.StageExtract), Source: doc,
Chunk: &source.Chunk{SourceID: "session", Units: []source.SourceUnit{{ID: 1}}}, Value: value,
})
if err != nil || !result.Approved {
t.Fatalf("contained extraction evidence = %#v, %v", result, err)
}
value.Locations[0].SourceRefs[0].EndUnitID = 2
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.LocationRegistry]{
Stage: string(pipeline.StageExtract), Source: doc,
Chunk: &source.Chunk{SourceID: "session", Units: []source.SourceUnit{{ID: 1}}}, Value: value,
})
if err != nil || result.Approved || !strings.Contains(result.Message, "outside the current extraction chunk") {
t.Fatalf("out-of-chunk extraction evidence = %#v, %v", result, err)
}
_, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.LocationRegistry]{Stage: string(pipeline.StageExtract), Source: doc, Value: validLocationRegistry()})
if err == nil || !strings.Contains(err.Error(), "requires the current extraction chunk") {
t.Fatalf("missing chunk error = %v", err)
}
}
func TestValidatorRegisters(t *testing.T) {
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatalf("Register() error = %v", 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 request(doc *source.SourceDocument, value dnd.LocationRegistry) contracts.TypedValidationRequest[dnd.LocationRegistry] {
return contracts.TypedValidationRequest[dnd.LocationRegistry]{Source: doc, Value: value}
}
func validDocument() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "Moon Gate opens."}}}
}
func validLocationRegistry() dnd.LocationRegistry {
return dnd.LocationRegistry{Locations: []dnd.Location{{ID: "candidate", Name: "Moon Gate", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
}