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 +1,121 @@
// Package sourcerefs validates D&D item-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"
itemoccurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemoccurrences/shape"
)
const (
Key = "extract/dnd/item-occurrences/source_refs"
ReasonCode = "invalid_item_occurrence_source_references"
policy = "dnd.item_occurrences.source_refs.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}}
}
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemOccurrenceList]) (contracts.ValidationResult, error) {
if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
return contracts.ValidationResult{}, fmt.Errorf("item occurrence source-reference validator requires the current extraction chunk")
}
if itemoccurrenceshape.Validate(req.Value) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
index := source.NewDocumentIndex(req.Source)
var coverage *chunkCoverage
if req.Stage == string(pipeline.StageExtract) {
coverage = newChunkCoverage(req.Chunk)
}
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 coverage != nil && !coverage.contains(req.Source, 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 item occurrence source references", issues)}, nil
}
type chunkCoverage struct {
sourceID string
unitIDs map[int]struct{}
}
func newChunkCoverage(chunk *source.Chunk) *chunkCoverage {
coverage := &chunkCoverage{
sourceID: chunk.SourceID,
unitIDs: make(map[int]struct{}, len(chunk.Units)),
}
for _, unit := range chunk.Units {
coverage.unitIDs[unit.ID] = struct{}{}
}
return coverage
}
func (coverage *chunkCoverage) contains(doc *source.SourceDocument, ref source.SourceRef) bool {
if coverage == nil || doc == nil || ref.SourceID != coverage.sourceID {
return false
}
start, startOK := source.UnitIndex(doc, ref.StartUnitID)
end, endOK := source.UnitIndex(doc, ref.EndUnitID)
if !startOK || !endOK || start > end {
return false
}
for position := start; position <= end; position++ {
if _, found := coverage.unitIDs[doc.Units[position].ID]; !found {
return false
}
}
return true
}
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 +1,121 @@
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.Occurrences[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{"occurrences[0].source_refs[0]", "occurrences[0].source_refs[1]", "occurrences[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.ItemOccurrenceList]{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.Occurrences[0].SourceRefs = []source.SourceRef{{SourceID: doc.ID, StartUnitID: 2, EndUnitID: 3}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemOccurrenceList]{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)
}
noncontiguousChunk := &source.Chunk{ID: "chunk-1", SourceID: doc.ID, Units: []source.SourceUnit{doc.Units[0], doc.Units[2]}}
spansMissingUnit := validList()
spansMissingUnit.Occurrences[0].SourceRefs = []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 3}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemOccurrenceList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: noncontiguousChunk, Value: spansMissingUnit})
if err != nil || result.Approved || !strings.Contains(result.Message, "outside the current extraction chunk") {
t.Fatalf("partially contained evidence = %#v, %v", result, err)
}
multiRange := validList()
multiRange.Occurrences[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.ItemOccurrenceList]{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.ItemOccurrenceList]{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.ItemOccurrenceList{Occurrences: []dnd.ItemOccurrence{{ItemID: "item", 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.ItemOccurrenceList{Occurrences: make([]dnd.ItemOccurrence, 24)}
for index := range value.Occurrences {
value.Occurrences[index] = dnd.ItemOccurrence{ItemID: "item", Name: "Ring", Kind: dnd.ItemOccurrenceKindDiscovered, 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, "occurrences[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.ItemOccurrenceList) contracts.TypedValidationRequest[dnd.ItemOccurrenceList] {
return contracts.TypedValidationRequest[dnd.ItemOccurrenceList]{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.ItemOccurrenceList {
return dnd.ItemOccurrenceList{Occurrences: []dnd.ItemOccurrence{{ItemID: "item", Name: "Ring", Kind: dnd.ItemOccurrenceKindAcquired, To: "party", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 2}}}}}
}