Move item occurrences to canonical namespace

This commit is contained in:
2026-08-05 20:00:20 +00:00
parent 3dfefd0e14
commit a6e176e160
46 changed files with 342 additions and 337 deletions

View File

@@ -0,0 +1,88 @@
// Package sourcerelatedness warns when item-occurrence evidence does not mention its item.
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"
itemoccurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemoccurrences/shape"
)
const (
Key = "extract/dnd/item-occurrences/source_relatedness"
WarningReasonCode = "item_occurrence_source_unrelated"
OmittedReasonCode = "item_occurrence_relatedness_warnings_omitted"
policy = "dnd.item_occurrences.source_relatedness.v1"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.ItemOccurrenceList] = (*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}}
}
// Validate performs advisory source grounding only. Shape and range failures
// are intentionally left to their blocking owners.
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemOccurrenceList]) (contracts.ValidationResult, error) {
if itemoccurrenceshape.Validate(req.Value) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
resolver, err := shared.NewCitationResolver(req.Source)
if err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
warnings := make([]contracts.Warning, 0)
for index, occurrence := range req.Value.Occurrences {
citedText, err := resolver.CitedText(occurrence.SourceRefs)
if err != nil || shared.ContainsTokenSequence(citedText, occurrence.Name) {
continue
}
warnings = append(warnings, contracts.Warning{
Scope: fmt.Sprintf("occurrences[%d]", index),
ReasonCode: WarningReasonCode,
Message: fmt.Sprintf("item occurrence name %s was not found in cited source text", diagnostics.Quote(occurrence.Name)),
})
}
return contracts.ValidationResult{
Approved: true,
Warnings: diagnostics.LimitWarnings(warnings, "item_occurrences", OmittedReasonCode),
}, nil
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemOccurrenceListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemOccurrenceList], 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 +1,73 @@
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"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
)
func TestValidatorMatchesTokenSequencesAcrossRanges(t *testing.T) {
doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{
{ID: 1, Text: "Aria finds a potion,"},
{ID: 2, Text: "of healing in the chest."},
{ID: 3, Text: "The group rests."},
}}
value := dnd.ItemOccurrenceList{Occurrences: []dnd.ItemOccurrence{{ItemID: "item", Name: "POTION OF HEALING", Kind: dnd.ItemOccurrenceKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}, {SourceID: doc.ID, StartUnitID: 2, EndUnitID: 2}}},
{ItemID: "item", Name: "missing-item", Kind: dnd.ItemOccurrenceKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 3, EndUnitID: 3}}},
}}
references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
"glossary": {Items: []contracts.ReferenceItem{{Content: []byte("missing-item")}}},
}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemOccurrenceList]{Source: doc, References: references, Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 1 {
t.Fatalf("Validate() = %#v, %v", result, err)
}
if warning := result.Warnings[0]; warning.Scope != "occurrences[1]" || warning.ReasonCode != WarningReasonCode || !strings.Contains(warning.Message, "missing-item") {
t.Fatalf("warning = %#v", warning)
}
}
func TestValidatorDefersMalformedAndUnreadableEvidence(t *testing.T) {
doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Text: "a potion"}}}
for _, value := range []dnd.ItemOccurrenceList{
{Occurrences: []dnd.ItemOccurrence{{ItemID: "item", Name: "", Kind: dnd.ItemOccurrenceKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 1}}}}},
{Occurrences: []dnd.ItemOccurrence{{ItemID: "item", Name: "potion", Kind: dnd.ItemOccurrenceKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 99, EndUnitID: 99}}}}},
} {
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemOccurrenceList]{Source: doc, Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("deferred result = %#v, %v", result, err)
}
}
}
func TestValidatorBoundsWarningsAndRegistersPolicy(t *testing.T) {
count := diagnostics.MaxWarnings + 5
occurrences := make([]dnd.ItemOccurrence, count)
for index := range occurrences {
occurrences[index] = dnd.ItemOccurrence{ItemID: "item", Name: "missing item", Kind: dnd.ItemOccurrenceKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}
}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemOccurrenceList]{
Source: &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Text: "nothing useful"}}},
Value: dnd.ItemOccurrenceList{Occurrences: occurrences},
})
if err != nil || !result.Approved || len(result.Warnings) != diagnostics.MaxWarnings || result.Warnings[len(result.Warnings)-1].ReasonCode != OmittedReasonCode {
t.Fatalf("Validate() = %#v, %v", result, err)
}
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.Fatalf("Register() error = %v", err)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions() accepted unknown option")
}
}