Add D&D location validators
This commit is contained in:
@@ -0,0 +1,76 @@
|
||||
// Package identity validates stable, evidence-anchored location identity.
|
||||
package identity
|
||||
|
||||
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"
|
||||
domainidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
|
||||
locationshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locations/shape"
|
||||
)
|
||||
|
||||
const (
|
||||
Key = "normalize/dnd/locations/identity"
|
||||
ReasonCode = "invalid_location_identity"
|
||||
policy = domainidentity.Policy
|
||||
)
|
||||
|
||||
type Options struct{}
|
||||
type Validator struct{}
|
||||
|
||||
var _ contracts.TypedValidator[dnd.LocationList] = (*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.LocationList]) (contracts.ValidationResult, error) {
|
||||
if err := locationshape.Validate(req.Value); err != nil {
|
||||
return contracts.ValidationResult{Approved: true}, nil
|
||||
}
|
||||
identityIssues := domainidentity.ValidateList(req.Value)
|
||||
if len(identityIssues) == 0 {
|
||||
return contracts.ValidationResult{Approved: true}, nil
|
||||
}
|
||||
issues := make([]string, len(identityIssues))
|
||||
for index, issue := range identityIssues {
|
||||
issues[index] = fmt.Sprintf("locations[%d] %s: %s", issue.RecordIndex, issue.Code, diagnostics.Quote(issue.Value))
|
||||
}
|
||||
return contracts.ValidationResult{
|
||||
Approved: false, ReasonCode: ReasonCode,
|
||||
Message: diagnostics.Aggregate("invalid location identity", 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.LocationListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.LocationList], 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 }
|
||||
@@ -0,0 +1,70 @@
|
||||
package identity
|
||||
|
||||
import (
|
||||
"context"
|
||||
"reflect"
|
||||
"strings"
|
||||
"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"
|
||||
domainidentity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
|
||||
)
|
||||
|
||||
func TestValidatorAllowsSameNameAtDistinctEvidence(t *testing.T) {
|
||||
refs := []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}
|
||||
otherRefs := []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}
|
||||
value := dnd.LocationList{Locations: []dnd.Location{
|
||||
{ID: domainidentity.DeriveID("Watchtower", refs), Name: "Watchtower", SourceRefs: refs},
|
||||
{ID: domainidentity.DeriveID("Watchtower", otherRefs), Name: "Watchtower", SourceRefs: otherRefs},
|
||||
}}
|
||||
before := value
|
||||
result, err := New(Options{}).Validate(context.Background(), request(value))
|
||||
if err != nil || !result.Approved || !reflect.DeepEqual(value, before) {
|
||||
t.Fatalf("Validate() = %#v, %v; want non-mutating approval", result, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestValidatorDefersShapeAndRejectsDerivationAndDuplicateID(t *testing.T) {
|
||||
result, err := New(Options{}).Validate(context.Background(), request(dnd.LocationList{Locations: []dnd.Location{{Name: "Missing"}}}))
|
||||
if err != nil || !result.Approved {
|
||||
t.Fatalf("shape-invalid result = %#v, %v; want deferral", result, err)
|
||||
}
|
||||
refs := []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}
|
||||
value := dnd.LocationList{Locations: []dnd.Location{
|
||||
{ID: "not-an-id", Name: "Gate", SourceRefs: refs},
|
||||
{ID: domainidentity.DeriveID("Gate", refs), Name: "Other Gate", SourceRefs: refs},
|
||||
{ID: domainidentity.DeriveID("Gate", refs), Name: "Gate", SourceRefs: refs},
|
||||
}}
|
||||
result, err = New(Options{}).Validate(context.Background(), request(value))
|
||||
if err != nil || result.Approved || result.ReasonCode != ReasonCode {
|
||||
t.Fatalf("identity result = %#v, %v; want rejection", result, err)
|
||||
}
|
||||
for _, want := range []string{"invalid_id", "id_mismatch", "duplicate_id", "locations["} {
|
||||
if !strings.Contains(result.Message, want) {
|
||||
t.Fatalf("message %q missing %q", result.Message, want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestValidatorRegistersIdentityPolicy(t *testing.T) {
|
||||
if got := New(Options{}).CheckpointFingerprints(); len(got) != 1 || got[0].Value != domainidentity.Policy {
|
||||
t.Fatalf("fingerprints = %#v", got)
|
||||
}
|
||||
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 _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
|
||||
t.Fatal("DecodeOptions() accepted an unknown option")
|
||||
}
|
||||
}
|
||||
|
||||
func request(value dnd.LocationList) contracts.TypedValidationRequest[dnd.LocationList] {
|
||||
return contracts.TypedValidationRequest[dnd.LocationList]{Value: value}
|
||||
}
|
||||
97
internal/modules/dnd/validate/locations/shape/validator.go
Normal file
97
internal/modules/dnd/validate/locations/shape/validator.go
Normal file
@@ -0,0 +1,97 @@
|
||||
// Package shape validates the required extracted location fields.
|
||||
package shape
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"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"
|
||||
)
|
||||
|
||||
const (
|
||||
Key = "extract/dnd/locations/shape"
|
||||
ReasonCode = "invalid_location_shape"
|
||||
policy = "dnd.locations.validator.shape.v1"
|
||||
)
|
||||
|
||||
type Options struct{}
|
||||
type Validator struct{}
|
||||
|
||||
var _ contracts.TypedValidator[dnd.LocationList] = (*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.LocationList]) (contracts.ValidationResult, error) {
|
||||
issues := issuesFor(req.Value)
|
||||
if len(issues) > 0 {
|
||||
return rejection(diagnostics.Aggregate("invalid location shape", issues)), nil
|
||||
}
|
||||
return contracts.ValidationResult{Approved: true}, nil
|
||||
}
|
||||
|
||||
func Validate(value dnd.LocationList) error {
|
||||
issues := issuesFor(value)
|
||||
if len(issues) == 0 {
|
||||
return nil
|
||||
}
|
||||
return fmt.Errorf("%s", diagnostics.Aggregate("invalid location shape", issues))
|
||||
}
|
||||
|
||||
func issuesFor(value dnd.LocationList) []string {
|
||||
if value.Locations == nil {
|
||||
return []string{"locations must be present"}
|
||||
}
|
||||
issues := make([]string, 0)
|
||||
for index, location := range value.Locations {
|
||||
prefix := fmt.Sprintf("locations[%d]", index)
|
||||
if strings.TrimSpace(location.ID) == "" {
|
||||
issues = append(issues, prefix+".id must not be empty")
|
||||
}
|
||||
if strings.TrimSpace(location.Name) == "" {
|
||||
issues = append(issues, prefix+".name must not be empty")
|
||||
}
|
||||
if len(location.SourceRefs) == 0 {
|
||||
issues = append(issues, prefix+".source_refs must not be empty")
|
||||
}
|
||||
}
|
||||
return issues
|
||||
}
|
||||
|
||||
func Spec() pipeline.ValidatorSpec {
|
||||
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
|
||||
}
|
||||
|
||||
func Register(registry *pipeline.ValidatorRegistry) error {
|
||||
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.LocationListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.LocationList], 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}
|
||||
}
|
||||
@@ -0,0 +1,58 @@
|
||||
package shape
|
||||
|
||||
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 TestValidatorRejectsMissingRequiredFieldsWithoutMutation(t *testing.T) {
|
||||
value := dnd.LocationList{Locations: []dnd.Location{{Name: strings.Repeat("火", 220), SourceRefs: []source.SourceRef{}}}}
|
||||
before := value
|
||||
result, err := New(Options{}).Validate(context.Background(), requestWithValue(value))
|
||||
if err != nil || result.Approved || result.ReasonCode != ReasonCode || !strings.Contains(result.Message, "id must not be empty") || !strings.Contains(result.Message, "source_refs must not be empty") {
|
||||
t.Fatalf("Validate() = %#v, %v; want shape 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: %#v", value)
|
||||
}
|
||||
result, err = New(Options{}).Validate(context.Background(), requestWithValue(dnd.LocationList{}))
|
||||
if err != nil || result.Approved || !strings.Contains(result.Message, "locations must be present") {
|
||||
t.Fatalf("missing locations = %#v, %v; want rejection", result, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestValidatorApprovesAndRegisters(t *testing.T) {
|
||||
result, err := New(Options{}).Validate(context.Background(), requestWithValue(validLocationList()))
|
||||
if err != nil || !result.Approved {
|
||||
t.Fatalf("Validate() = %#v, %v; want approval", result, err)
|
||||
}
|
||||
if got := New(Options{}).CheckpointFingerprints(); len(got) != 1 || got[0].Name != "policy" || got[0].Value != policy {
|
||||
t.Fatalf("CheckpointFingerprints() = %#v", got)
|
||||
}
|
||||
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 _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
|
||||
t.Fatal("DecodeOptions() accepted an unknown option")
|
||||
}
|
||||
}
|
||||
|
||||
func requestWithValue(value dnd.LocationList) contracts.TypedValidationRequest[dnd.LocationList] {
|
||||
return contracts.TypedValidationRequest[dnd.LocationList]{Value: value}
|
||||
}
|
||||
|
||||
func validLocationList() dnd.LocationList {
|
||||
return dnd.LocationList{Locations: []dnd.Location{{ID: "candidate", Name: "Moon Gate", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
|
||||
}
|
||||
@@ -0,0 +1,81 @@
|
||||
// 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/locations/shape"
|
||||
)
|
||||
|
||||
const (
|
||||
Key = "extract/dnd/locations/source_refs"
|
||||
ReasonCode = "invalid_location_source_refs"
|
||||
policy = "dnd.locations.validator.source_refs.v1"
|
||||
)
|
||||
|
||||
type Options struct{}
|
||||
type Validator struct{}
|
||||
|
||||
var _ contracts.TypedValidator[dnd.LocationList] = (*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.LocationList]) (contracts.ValidationResult, error) {
|
||||
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())))
|
||||
}
|
||||
}
|
||||
}
|
||||
if len(issues) == 0 {
|
||||
return contracts.ValidationResult{Approved: true}, nil
|
||||
}
|
||||
return rejection(diagnostics.Aggregate("invalid location 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.LocationListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.LocationList], 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}
|
||||
}
|
||||
@@ -0,0 +1,63 @@
|
||||
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 := validLocationList()
|
||||
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(), validLocationList()))
|
||||
if err != nil || !result.Approved {
|
||||
t.Fatalf("valid references = %#v, %v", result, err)
|
||||
}
|
||||
result, err = New(Options{}).Validate(context.Background(), request(nil, dnd.LocationList{Locations: []dnd.Location{{Name: "Missing"}}}))
|
||||
if err != nil || !result.Approved || result.ReasonCode != "" {
|
||||
t.Fatalf("malformed shape = %#v, %v; want deferral", result, 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.LocationList) contracts.TypedValidationRequest[dnd.LocationList] {
|
||||
return contracts.TypedValidationRequest[dnd.LocationList]{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 validLocationList() dnd.LocationList {
|
||||
return dnd.LocationList{Locations: []dnd.Location{{ID: "candidate", Name: "Moon Gate", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
|
||||
}
|
||||
@@ -0,0 +1,87 @@
|
||||
// Package sourcerelatedness warns when cited source text does not mention a location.
|
||||
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"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
|
||||
locationshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/locations/shape"
|
||||
)
|
||||
|
||||
const (
|
||||
Key = "extract/dnd/locations/source_relatedness"
|
||||
WarningReasonCode = "location_not_near_source"
|
||||
policy = "dnd.locations.validator.source_relatedness.v1"
|
||||
)
|
||||
|
||||
type Options struct{}
|
||||
type Validator struct{}
|
||||
|
||||
var _ contracts.TypedValidator[dnd.LocationList] = (*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.LocationList]) (contracts.ValidationResult, error) {
|
||||
if err := locationshape.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
|
||||
}
|
||||
citedTexts := make([]string, len(req.Value.Locations))
|
||||
for locationIndex, location := range req.Value.Locations {
|
||||
citedText, err := resolver.CitedText(location.SourceRefs)
|
||||
if err != nil {
|
||||
return contracts.ValidationResult{Approved: true}, nil
|
||||
}
|
||||
citedTexts[locationIndex] = citedText
|
||||
}
|
||||
warnings := make([]contracts.Warning, 0)
|
||||
for locationIndex, location := range req.Value.Locations {
|
||||
if shared.ContainsTokenSequence(citedTexts[locationIndex], location.Name) {
|
||||
continue
|
||||
}
|
||||
warnings = append(warnings, contracts.Warning{
|
||||
Scope: fmt.Sprintf("locations[%d]", locationIndex), ReasonCode: WarningReasonCode,
|
||||
Message: fmt.Sprintf("Location %s was not found in cited source text", diagnostics.Quote(location.Name)),
|
||||
})
|
||||
}
|
||||
return contracts.ValidationResult{Approved: true, Warnings: warnings}, nil
|
||||
}
|
||||
|
||||
func Spec() pipeline.ValidatorSpec {
|
||||
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
|
||||
}
|
||||
|
||||
func Register(registry *pipeline.ValidatorRegistry) error {
|
||||
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.LocationListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.LocationList], 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 }
|
||||
@@ -0,0 +1,63 @@
|
||||
package sourcerelatedness
|
||||
|
||||
import (
|
||||
"context"
|
||||
"reflect"
|
||||
"strings"
|
||||
"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 TestValidatorUsesOnlyCitedTranscriptText(t *testing.T) {
|
||||
value := dnd.LocationList{Locations: []dnd.Location{{ID: "candidate", Name: "O'Rin's Gate", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
|
||||
doc := &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "The party enters o’rin’s gate."}, {ID: 2, Kind: "message", Text: "Unrelated location."}}}
|
||||
result, err := New(Options{}).Validate(context.Background(), request(doc, value, contracts.ReferenceSet{}))
|
||||
if err != nil || !result.Approved || len(result.Warnings) != 0 {
|
||||
t.Fatalf("cited match = %#v, %v; want approval without warnings", result, err)
|
||||
}
|
||||
value.Locations[0].Name = "Glossary Keep"
|
||||
before := value
|
||||
references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{"glossary": {Items: []contracts.ReferenceItem{{Content: []byte("Glossary Keep")}}}}}
|
||||
result, err = New(Options{}).Validate(context.Background(), request(doc, value, references))
|
||||
if err != nil || !result.Approved || len(result.Warnings) != 1 || result.Warnings[0].ReasonCode != WarningReasonCode || !strings.Contains(result.Warnings[0].Message, "Glossary Keep") || !reflect.DeepEqual(value, before) {
|
||||
t.Fatalf("reference-only match = %#v, %v; want advisory warning", result, err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestValidatorDefersMalformedOrUnreadableCitations(t *testing.T) {
|
||||
invalid := dnd.LocationList{Locations: []dnd.Location{{Name: "Missing"}}}
|
||||
result, err := New(Options{}).Validate(context.Background(), request(document(), invalid, contracts.ReferenceSet{}))
|
||||
if err != nil || !result.Approved || len(result.Warnings) != 0 {
|
||||
t.Fatalf("shape deferral = %#v, %v", result, err)
|
||||
}
|
||||
value := dnd.LocationList{Locations: []dnd.Location{{ID: "candidate", Name: "Missing", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 99, EndUnitID: 99}}}}}
|
||||
result, err = New(Options{}).Validate(context.Background(), request(document(), value, contracts.ReferenceSet{}))
|
||||
if err != nil || !result.Approved || len(result.Warnings) != 0 {
|
||||
t.Fatalf("unreadable citation = %#v, %v", result, 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.LocationList, references contracts.ReferenceSet) contracts.TypedValidationRequest[dnd.LocationList] {
|
||||
return contracts.TypedValidationRequest[dnd.LocationList]{Source: doc, References: references, Value: value}
|
||||
}
|
||||
|
||||
func document() *source.SourceDocument {
|
||||
return &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "The party waits."}}}
|
||||
}
|
||||
Reference in New Issue
Block a user