Minimize D&D NPC extraction contracts

This commit is contained in:
2026-07-22 18:51:26 +00:00
parent 14991cf58b
commit a263a0840c
43 changed files with 486 additions and 1395 deletions

View File

@@ -92,9 +92,7 @@ func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
{Name: "identity_policy", Value: identity.Policy},
}
seeded := n.npcResolver.Seeded()
if seeded.Bound() {
fingerprints = append(fingerprints, pipeline.CheckpointFingerprint{Name: "npc_registry", Value: seeded.Digest()})
}
fingerprints = append(fingerprints, pipeline.CheckpointFingerprint{Name: "npc_registry", Value: seeded.ProjectionDigest()})
return fingerprints
}

View File

@@ -26,12 +26,12 @@ func TestNormalizeCanonicalizesFieldsAndRegistryIdentities(t *testing.T) {
}
resolution := " the target is hit "
input := dnd.CombatTurnList{CombatTurns: []dnd.CombatTurn{{
Actor: " storm ",
Actor: " aria ",
TurnKind: dnd.CombatTurnKindTurn,
Actions: []dnd.CombatAction{{
Category: dnd.CombatActionCategoryAttack,
Declaration: " attacks\n with a sword ",
Targets: []string{" minion ", "goblin", " unknown combatant "},
Targets: []string{" goblin ", "goblin", " unknown combatant "},
Resolution: &resolution,
}},
Summary: " Aria\n attacks ",
@@ -77,10 +77,10 @@ func TestNormalizeResolvesOperationNPCOverrideWithoutSingletonMetadata(t *testin
t.Fatalf("New() error = %v", err)
}
input := dnd.CombatTurnList{CombatTurns: []dnd.CombatTurn{{
Actor: "Storm",
Actor: "aria",
TurnKind: dnd.CombatTurnKindTurn,
Actions: []dnd.CombatAction{{Category: dnd.CombatActionCategoryAttack, Declaration: "attacks", Targets: []string{"Minion"}}},
Summary: "Storm attacks",
Actions: []dnd.CombatAction{{Category: dnd.CombatActionCategoryAttack, Declaration: "attacks", Targets: []string{"goblin"}}},
Summary: "Aria attacks",
SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}},
}}}
result, err := normalizer.Normalize(context.Background(), contracts.TypedNormalizeRequest[dnd.CombatTurnList]{
@@ -222,7 +222,7 @@ func TestNormalizerPreparationMetadataFingerprintsAndModuleContract(t *testing.T
if metadata := unbound.ManifestMetadata(); metadata["npc_registry_digest"] != nil || metadata["npc_count"] != nil || metadata["normalization_policy"] != normalizationPolicy || metadata["identity_policy"] != identity.Policy {
t.Fatalf("unbound metadata = %#v", metadata)
}
if got := unbound.CheckpointFingerprints(); len(got) != 2 || got[0].Name != "normalization_policy" || got[1].Name != "identity_policy" {
if got := unbound.CheckpointFingerprints(); len(got) != 3 || got[0].Name != "normalization_policy" || got[1].Name != "identity_policy" || got[2].Name != "npc_registry" || got[2].Value == "" {
t.Fatalf("unbound fingerprints = %#v", got)
}
@@ -305,8 +305,8 @@ func testDocument() *source.SourceDocument {
func npcReferences(t *testing.T) contracts.ReferenceSet {
t.Helper()
npcs := dnd.NPCList{NPCs: []dnd.NPC{
{ID: identity.DeriveID("Aria"), Name: "Aria", Aliases: []string{"Storm"}, Description: "a fighter", Relationships: []dnd.NPCRelationship{{Target: "Goblin", Relationship: "fights"}}, SourceRefs: []source.SourceRef{{SourceID: "npc-run", StartUnitID: 1, EndUnitID: 1}}},
{ID: identity.DeriveID("Goblin"), Name: "Goblin", Aliases: []string{"Minion"}, Description: "a goblin", Relationships: []dnd.NPCRelationship{{Target: "Aria", Relationship: "fights"}}, SourceRefs: []source.SourceRef{{SourceID: "npc-run", StartUnitID: 1, EndUnitID: 1}}},
{ID: identity.DeriveID("Aria"), Name: "Aria", SourceRefs: []source.SourceRef{{SourceID: "npc-run", StartUnitID: 1, EndUnitID: 1}}},
{ID: identity.DeriveID("Goblin"), Name: "Goblin", SourceRefs: []source.SourceRef{{SourceID: "npc-run", StartUnitID: 1, EndUnitID: 1}}},
}}
content, err := npccodec.New().Encode(npcs)
if err != nil {

View File

@@ -22,11 +22,10 @@ const (
normalizationPolicy = "dnd.npcs.normalize.v1"
NormalizationPolicy = normalizationPolicy
ReasonCodeNPCFieldsNormalized = "npc_fields_normalized"
ReasonCodeNPCIDRecomputed = "npc_id_recomputed"
ReasonCodeSourceReferencesNormalized = "source_references_normalized"
ReasonCodeDuplicateNPCCollapsed = "duplicate_npc_collapsed"
ReasonCodeRelationshipTargetCanonicalized = "relationship_target_canonicalized"
ReasonCodeNPCFieldsNormalized = "npc_fields_normalized"
ReasonCodeNPCIDRecomputed = "npc_id_recomputed"
ReasonCodeSourceReferencesNormalized = "source_references_normalized"
ReasonCodeDuplicateNPCCollapsed = "duplicate_npc_collapsed"
)
var requiredCapabilities = []string{"merged"}
@@ -37,23 +36,17 @@ var _ contracts.ManifestMetadataProvider = (*Normalizer)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Normalizer)(nil)
type Options struct{}
type Normalizer struct{}
func New(Options) *Normalizer { return &Normalizer{} }
func (n *Normalizer) Key() string { return Key }
func New(Options) *Normalizer { return &Normalizer{} }
func (n *Normalizer) Key() string { return Key }
func (n *Normalizer) ReferenceSlots() []contracts.ReferenceSlot { return nil }
func (n *Normalizer) ManifestMetadata() map[string]any {
if n == nil {
return nil
}
return map[string]any{
"identity_policy": identity.Policy,
"normalization_policy": normalizationPolicy,
}
return map[string]any{"identity_policy": identity.Policy, "normalization_policy": normalizationPolicy}
}
func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
@@ -76,193 +69,106 @@ func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalize
if err := ctx.Err(); err != nil {
return contracts.TypedNormalizeResult[dnd.NPCList]{}, normalizerErrorf("context error before normalize: %w", err)
}
value, warnings := normalizeList(req.MergeOutput.Value)
return contracts.TypedNormalizeResult[dnd.NPCList]{Value: value, Warnings: warnings}, nil
}
type normalizedRecord struct {
npc dnd.NPC
fieldsChanged bool
referencesChanged bool
npc dnd.NPC
}
func normalizeList(input dnd.NPCList) (dnd.NPCList, []contracts.Warning) {
if input.NPCs == nil {
return dnd.NPCList{}, nil
}
records := make([]normalizedRecord, len(input.NPCs))
warnings := make([]contracts.Warning, 0)
for index, inputNPC := range input.NPCs {
npc, fieldsChanged, referencesChanged := normalizeRecord(inputNPC)
records[index] = normalizedRecord{
npc: npc,
fieldsChanged: fieldsChanged,
referencesChanged: referencesChanged,
}
records[index] = normalizedRecord{npc: npc}
if fieldsChanged {
warnings = append(warnings, contracts.Warning{
Scope: npcScope(index),
ReasonCode: ReasonCodeNPCFieldsNormalized,
Message: fmt.Sprintf("input index %d: NPC fields normalized for %s",
index, diagnostics.Quote(inputNPC.Name)),
})
warnings = append(warnings, contracts.Warning{Scope: npcScope(index), ReasonCode: ReasonCodeNPCFieldsNormalized, Message: fmt.Sprintf("input index %d: NPC name normalized for %s", index, diagnostics.Quote(inputNPC.Name))})
}
if referencesChanged {
warnings = append(warnings, contracts.Warning{
Scope: npcScope(index),
ReasonCode: ReasonCodeSourceReferencesNormalized,
Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d)",
index, len(inputNPC.SourceRefs), len(npc.SourceRefs)),
})
warnings = append(warnings, contracts.Warning{Scope: npcScope(index), ReasonCode: ReasonCodeSourceReferencesNormalized, Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d)", index, len(inputNPC.SourceRefs), len(npc.SourceRefs))})
}
if inputNPC.ID != npc.ID {
warnings = append(warnings, contracts.Warning{
Scope: npcScope(index),
ReasonCode: ReasonCodeNPCIDRecomputed,
Message: fmt.Sprintf("input index %d: NPC ID recomputed from %s",
index, diagnostics.Quote(npc.Name)),
})
warnings = append(warnings, contracts.Warning{Scope: npcScope(index), ReasonCode: ReasonCodeNPCIDRecomputed, Message: fmt.Sprintf("input index %d: NPC ID recomputed from %s", index, diagnostics.Quote(npc.Name))})
}
}
components := identityComponents(records)
output := dnd.NPCList{NPCs: make([]dnd.NPC, 0, len(components))}
retainedIndexes := make([]int, 0, len(components))
for _, members := range components {
consolidated, sourceChanged := consolidate(records, members)
groups := canonicalNameGroups(records)
output := dnd.NPCList{NPCs: make([]dnd.NPC, 0, len(groups))}
for _, members := range groups {
consolidated, referencesChanged := consolidate(records, members)
retainedIndex := members[0]
output.NPCs = append(output.NPCs, consolidated)
retainedIndexes = append(retainedIndexes, retainedIndex)
if sourceChanged {
warnings = append(warnings, contracts.Warning{
Scope: npcScope(retainedIndex),
ReasonCode: ReasonCodeSourceReferencesNormalized,
Message: fmt.Sprintf("input index %d: source references normalized during identity consolidation (final count %d)",
retainedIndex, len(consolidated.SourceRefs)),
})
if referencesChanged {
warnings = append(warnings, contracts.Warning{Scope: npcScope(retainedIndex), ReasonCode: ReasonCodeSourceReferencesNormalized, Message: fmt.Sprintf("input index %d: source references normalized during identity consolidation (final count %d)", retainedIndex, len(consolidated.SourceRefs))})
}
if len(members) > 1 {
warnings = append(warnings, duplicateWarning(retainedIndex, members[1:]))
}
}
warnings = append(warnings, canonicalizeRelationshipTargets(&output, retainedIndexes)...)
return output, warnings
}
func normalizeRecord(input dnd.NPC) (dnd.NPC, bool, bool) {
output := cloneNPC(input)
output.Name = identity.NormalizeDisplay(input.Name)
output.Aliases = normalizeAliases(input.Aliases, output.Name)
output.Description = strings.TrimSpace(input.Description)
output.Relationships = normalizeRelationships(input.Relationships)
output.SourceRefs, _, _ = canonicalizeSourceRefs(input.SourceRefs)
output.ID = identity.DeriveID(output.Name)
fieldsChanged := input.Name != output.Name ||
!reflect.DeepEqual(input.Aliases, output.Aliases) ||
input.Description != output.Description ||
!reflect.DeepEqual(input.Relationships, output.Relationships)
referencesChanged := !reflect.DeepEqual(input.SourceRefs, output.SourceRefs)
return output, fieldsChanged, referencesChanged
return output, input.Name != output.Name, !reflect.DeepEqual(input.SourceRefs, output.SourceRefs)
}
func cloneNPC(input dnd.NPC) dnd.NPC {
output := input
if input.Aliases != nil {
output.Aliases = make([]string, len(input.Aliases))
copy(output.Aliases, input.Aliases)
}
if input.Relationships != nil {
output.Relationships = make([]dnd.NPCRelationship, len(input.Relationships))
copy(output.Relationships, input.Relationships)
}
if input.SourceRefs != nil {
output.SourceRefs = make([]source.SourceRef, len(input.SourceRefs))
copy(output.SourceRefs, input.SourceRefs)
}
return output
input.SourceRefs = cloneSourceRefs(input.SourceRefs)
return input
}
func normalizeAliases(input []string, canonicalName string) []string {
if input == nil {
return nil
}
canonicalKey := identity.ComparisonKey(canonicalName)
output := make([]string, 0, len(input))
seen := make(map[string]struct{}, len(input))
for _, alias := range input {
normalized := identity.NormalizeDisplay(alias)
key := identity.ComparisonKey(normalized)
if canonicalKey != "" && key == canonicalKey {
continue
func canonicalNameGroups(records []normalizedRecord) [][]int {
groups := make([][]int, 0, len(records))
ownerByKey := make(map[string]int, len(records))
for index, record := range records {
key := identity.ComparisonKey(record.npc.Name)
if key != "" {
if groupIndex, ok := ownerByKey[key]; ok {
groups[groupIndex] = append(groups[groupIndex], index)
continue
}
ownerByKey[key] = len(groups)
}
if _, exists := seen[key]; exists {
continue
}
seen[key] = struct{}{}
output = append(output, normalized)
groups = append(groups, []int{index})
}
return output
return groups
}
func normalizeRelationships(input []dnd.NPCRelationship) []dnd.NPCRelationship {
if input == nil {
return nil
}
output := make([]dnd.NPCRelationship, 0, len(input))
seen := make(map[relationshipIdentity]struct{}, len(input))
for _, relationship := range input {
normalized := dnd.NPCRelationship{
Target: identity.NormalizeDisplay(relationship.Target),
Relationship: strings.TrimSpace(relationship.Relationship),
}
key := relationshipKey(normalized)
if _, exists := seen[key]; exists {
continue
}
seen[key] = struct{}{}
output = append(output, normalized)
}
return output
}
type relationshipIdentity struct {
target string
relationship string
}
func relationshipKey(relationship dnd.NPCRelationship) relationshipIdentity {
return relationshipIdentity{
target: identity.ComparisonKey(relationship.Target),
relationship: identity.ComparisonKey(relationship.Relationship),
func consolidate(records []normalizedRecord, members []int) (dnd.NPC, bool) {
output := cloneNPC(records[members[0]].npc)
originalRefs := cloneSourceRefs(output.SourceRefs)
for _, member := range members[1:] {
output.SourceRefs = append(output.SourceRefs, records[member].npc.SourceRefs...)
}
output.SourceRefs, _, _ = canonicalizeSourceRefs(output.SourceRefs)
output.ID = identity.DeriveID(output.Name)
return output, !reflect.DeepEqual(originalRefs, output.SourceRefs)
}
func canonicalizeSourceRefs(input []source.SourceRef) ([]source.SourceRef, bool, int) {
if input == nil {
return nil, false, 0
}
canonical := make([]source.SourceRef, len(input))
copy(canonical, input)
canonical := cloneSourceRefs(input)
sort.SliceStable(canonical, func(left, right int) bool {
return sourceRefLess(canonical[left], canonical[right])
})
orderChanged := false
for index := range input {
if input[index] != canonical[index] {
orderChanged = true
break
if canonical[left].SourceID != canonical[right].SourceID {
return canonical[left].SourceID < canonical[right].SourceID
}
}
if canonical[left].StartUnitID != canonical[right].StartUnitID {
return canonical[left].StartUnitID < canonical[right].StartUnitID
}
return canonical[left].EndUnitID < canonical[right].EndUnitID
})
orderChanged := !reflect.DeepEqual(input, canonical)
unique := make([]source.SourceRef, 0, len(canonical))
for _, ref := range canonical {
if len(unique) == 0 || unique[len(unique)-1] != ref {
@@ -272,219 +178,11 @@ func canonicalizeSourceRefs(input []source.SourceRef) ([]source.SourceRef, bool,
return unique, orderChanged, len(input) - len(unique)
}
func sourceRefLess(left, right source.SourceRef) bool {
if left.SourceID != right.SourceID {
return left.SourceID < right.SourceID
}
if left.StartUnitID != right.StartUnitID {
return left.StartUnitID < right.StartUnitID
}
return left.EndUnitID < right.EndUnitID
}
func identityComponents(records []normalizedRecord) [][]int {
parent := make([]int, len(records))
for index := range parent {
parent[index] = index
}
for left := 0; left < len(records); left++ {
for right := left + 1; right < len(records); right++ {
if recordsCanMerge(records[left].npc, records[right].npc) {
union(parent, left, right)
}
}
}
byRoot := make(map[int][]int, len(records))
for index := range records {
root := find(parent, index)
byRoot[root] = append(byRoot[root], index)
}
roots := make([]int, 0, len(byRoot))
for root := range byRoot {
roots = append(roots, root)
}
sort.Slice(roots, func(left, right int) bool {
return byRoot[roots[left]][0] < byRoot[roots[right]][0]
})
components := make([][]int, 0, len(roots))
for _, root := range roots {
components = append(components, byRoot[root])
}
return components
}
func recordsCanMerge(left, right dnd.NPC) bool {
leftCanonical := identity.ComparisonKey(left.Name)
rightCanonical := identity.ComparisonKey(right.Name)
return leftCanonical == rightCanonical ||
containsAliasKey(right.Aliases, leftCanonical) ||
containsAliasKey(left.Aliases, rightCanonical)
}
func containsAliasKey(aliases []string, wanted string) bool {
for _, alias := range aliases {
if identity.ComparisonKey(alias) == wanted {
return true
}
}
return false
}
func find(parent []int, index int) int {
for parent[index] != index {
parent[index] = parent[parent[index]]
index = parent[index]
}
return index
}
func union(parent []int, left, right int) {
leftRoot := find(parent, left)
rightRoot := find(parent, right)
if leftRoot == rightRoot {
return
}
if leftRoot < rightRoot {
parent[rightRoot] = leftRoot
} else {
parent[leftRoot] = rightRoot
}
}
func consolidate(records []normalizedRecord, members []int) (dnd.NPC, bool) {
output := cloneNPC(records[members[0]].npc)
originalRefs := cloneSourceRefs(output.SourceRefs)
canonicalKey := identity.ComparisonKey(output.Name)
for _, member := range members[1:] {
candidate := records[member].npc
appendAlias(&output.Aliases, candidate.Name, canonicalKey)
for _, alias := range candidate.Aliases {
appendAlias(&output.Aliases, alias, canonicalKey)
}
for _, relationship := range candidate.Relationships {
appendRelationship(&output.Relationships, relationship)
}
output.SourceRefs = append(output.SourceRefs, candidate.SourceRefs...)
}
output.SourceRefs, _, _ = canonicalizeSourceRefs(output.SourceRefs)
output.ID = identity.DeriveID(output.Name)
return output, !reflect.DeepEqual(originalRefs, output.SourceRefs)
}
func cloneSourceRefs(input []source.SourceRef) []source.SourceRef {
if input == nil {
return nil
}
output := make([]source.SourceRef, len(input))
copy(output, input)
return output
}
func appendAlias(aliases *[]string, value, canonicalKey string) {
key := identity.ComparisonKey(value)
if canonicalKey != "" && key == canonicalKey {
return
}
for _, existing := range *aliases {
if identity.ComparisonKey(existing) == key {
return
}
}
*aliases = append(*aliases, value)
}
func appendRelationship(relationships *[]dnd.NPCRelationship, relationship dnd.NPCRelationship) {
key := relationshipKey(relationship)
for _, existing := range *relationships {
if relationshipKey(existing) == key {
return
}
}
*relationships = append(*relationships, relationship)
}
func canonicalizeRelationshipTargets(list *dnd.NPCList, retainedIndexes []int) []contracts.Warning {
if list == nil || len(list.NPCs) == 0 {
return nil
}
owners := make(map[string][]int)
for index, npc := range list.NPCs {
if key := identity.ComparisonKey(npc.Name); key != "" {
owners[key] = append(owners[key], index)
}
for _, alias := range npc.Aliases {
if key := identity.ComparisonKey(alias); key != "" {
owners[key] = appendUniqueIndex(owners[key], index)
}
}
}
warnings := make([]contracts.Warning, 0)
for outputIndex := range list.NPCs {
npc := &list.NPCs[outputIndex]
originalRelationshipCount := len(npc.Relationships)
for relationshipIndex := range npc.Relationships {
relationship := &npc.Relationships[relationshipIndex]
key := identity.ComparisonKey(relationship.Target)
if key == "" || len(owners[key]) != 1 {
continue
}
target := list.NPCs[owners[key][0]].Name
if relationship.Target == target {
continue
}
oldTarget := relationship.Target
relationship.Target = target
warnings = append(warnings, contracts.Warning{
Scope: npcScope(retainedIndexes[outputIndex]),
ReasonCode: ReasonCodeRelationshipTargetCanonicalized,
Message: fmt.Sprintf("input index %d: relationship target canonicalized from %s to %s",
retainedIndexes[outputIndex], diagnostics.Quote(oldTarget), diagnostics.Quote(target)),
})
}
npc.Relationships = deduplicateRelationships(npc.Relationships)
if len(npc.Relationships) != originalRelationshipCount {
warnings = append(warnings, contracts.Warning{
Scope: npcScope(retainedIndexes[outputIndex]),
ReasonCode: ReasonCodeNPCFieldsNormalized,
Message: fmt.Sprintf("input index %d: duplicate relationships removed after target canonicalization",
retainedIndexes[outputIndex]),
})
}
}
return warnings
}
func deduplicateRelationships(input []dnd.NPCRelationship) []dnd.NPCRelationship {
if input == nil {
return nil
}
output := make([]dnd.NPCRelationship, 0, len(input))
seen := make(map[relationshipIdentity]struct{}, len(input))
for _, relationship := range input {
key := relationshipKey(relationship)
if _, exists := seen[key]; exists {
continue
}
seen[key] = struct{}{}
output = append(output, relationship)
}
return output
}
func appendUniqueIndex(values []int, wanted int) []int {
for _, value := range values {
if value == wanted {
return values
}
}
return append(values, wanted)
return append([]source.SourceRef(nil), input...)
}
func duplicateWarning(retainedIndex int, removed []int) contracts.Warning {
@@ -497,28 +195,17 @@ func duplicateWarning(retainedIndex int, removed []int) contracts.Warning {
for index, removedIndex := range displayed {
indices[index] = strconv.Itoa(removedIndex)
}
message := fmt.Sprintf("retained input index %d; removed input indices [%s]", retainedIndex, strings.Join(indices, ", "))
if omitted := len(removed) - len(displayed); omitted > 0 {
message += fmt.Sprintf("; %d additional removed input indices omitted", omitted)
}
return contracts.Warning{
Scope: npcScope(retainedIndex),
ReasonCode: ReasonCodeDuplicateNPCCollapsed,
Message: message,
}
return contracts.Warning{Scope: npcScope(retainedIndex), ReasonCode: ReasonCodeDuplicateNPCCollapsed, Message: message}
}
func npcScope(index int) string { return fmt.Sprintf("npcs[%d]", index) }
func ModuleSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{
Key: Key,
Stage: pipeline.StageNormalize,
Requires: append([]string(nil), requiredCapabilities...),
Provides: append([]string(nil), providedCapabilities...),
ArtifactKind: dnd.NPCListKind,
}
return pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, Requires: append([]string(nil), requiredCapabilities...), Provides: append([]string(nil), providedCapabilities...), ArtifactKind: dnd.NPCListKind}
}
func Register(registry *pipeline.NormalizerRegistry) error {
@@ -531,10 +218,7 @@ func Register(registry *pipeline.NormalizerRegistry) error {
})
}
func validateOptions(options map[string]any) error {
_, err := DecodeOptions(options)
return err
}
func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }
func DecodeOptions(options map[string]any) (Options, error) {
if err := pipeline.RejectUnknownOptions(options); err != nil {

View File

@@ -10,223 +10,91 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
identity "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
)
func TestModuleContractAndIdentity(t *testing.T) {
if _, err := DecodeOptions(nil); err != nil {
t.Fatalf("DecodeOptions(nil) error = %v, want nil", err)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil || !strings.Contains(err.Error(), "unknown option") {
t.Fatalf("DecodeOptions() error = %v, want unknown option error", err)
}
want := pipeline.ModuleSpec{
Key: Key,
Stage: pipeline.StageNormalize,
Requires: []string{"merged"},
Provides: []string{"normalized"},
ArtifactKind: dnd.NPCListKind,
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions() accepted unknown option")
}
want := pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, Requires: []string{"merged"}, Provides: []string{"normalized"}, ArtifactKind: dnd.NPCListKind}
if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
}
if slots := New(Options{}).ReferenceSlots(); slots != nil {
t.Fatalf("ReferenceSlots() = %#v, want nil", slots)
}
registry := pipeline.NewNormalizerRegistry()
if err := Register(registry); err != nil {
t.Fatalf("Register() error = %v, want nil", err)
t.Fatalf("Register() error = %v", err)
}
if registered, ok := registry.SpecForArtifact(Key, dnd.NPCListKind); !ok || !reflect.DeepEqual(registered, want) {
t.Fatalf("registered spec = %#v, ok = %t, want %#v", registered, ok, want)
}
if err := Register(nil); err == nil || !strings.Contains(err.Error(), "normalizer registry") {
t.Fatalf("Register(nil) error = %v, want registry error", err)
}
normalizer := New(Options{})
metadata := normalizer.ManifestMetadata()
if metadata["identity_policy"] != identity.Policy || metadata["normalization_policy"] != normalizationPolicy {
t.Fatalf("metadata = %#v, want identity and normalization policies", metadata)
if metadata := normalizer.ManifestMetadata(); metadata["identity_policy"] != identity.Policy || metadata["normalization_policy"] != normalizationPolicy {
t.Fatalf("metadata = %#v", metadata)
}
fingerprints := normalizer.CheckpointFingerprints()
wantFingerprints := []pipeline.CheckpointFingerprint{
{Name: "identity_policy", Value: identity.Policy},
{Name: "normalization_policy", Value: normalizationPolicy},
}
if !reflect.DeepEqual(fingerprints, wantFingerprints) {
t.Fatalf("fingerprints = %#v, want %#v", fingerprints, wantFingerprints)
}
fingerprints[0].Value = "changed"
wantFingerprints := []pipeline.CheckpointFingerprint{{Name: "identity_policy", Value: identity.Policy}, {Name: "normalization_policy", Value: normalizationPolicy}}
if got := normalizer.CheckpointFingerprints(); !reflect.DeepEqual(got, wantFingerprints) {
t.Fatalf("fingerprints were not defensive: %#v", got)
t.Fatalf("fingerprints = %#v, want %#v", got, wantFingerprints)
}
}
func TestNormalizePerRecordFieldsAndEvidence(t *testing.T) {
func TestNormalizeNamesEvidenceAndIDs(t *testing.T) {
input := dnd.NPCList{NPCs: []dnd.NPC{{
ID: "wrong",
Name: " Lady\tAsh ",
Aliases: []string{" Ash ", " L.A. ", "l.a.", " Lady Ash "},
Description: " first description\n",
Relationships: []dnd.NPCRelationship{
{Target: " Lord\nOak ", Relationship: " friend "},
{Target: "lord oak", Relationship: "friend"},
},
SourceRefs: []source.SourceRef{
ID: "wrong", Name: " Lady\tAsh ", SourceRefs: []source.SourceRef{
{SourceID: "b", StartUnitID: 2, EndUnitID: 3},
{SourceID: "a", StartUnitID: 4, EndUnitID: 4},
{SourceID: "b", StartUnitID: 2, EndUnitID: 3},
},
}}}
result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
t.Fatalf("Normalize() error = %v", err)
}
got := result.Value.NPCs[0]
if got.Name != "Lady Ash" || got.Description != "first description" {
t.Fatalf("normalized fields = %#v, want normalized display and description", got)
want := dnd.NPC{ID: identity.DeriveID("Lady Ash"), Name: "Lady Ash", SourceRefs: []source.SourceRef{{SourceID: "a", StartUnitID: 4, EndUnitID: 4}, {SourceID: "b", StartUnitID: 2, EndUnitID: 3}}}
if !reflect.DeepEqual(result.Value.NPCs[0], want) {
t.Fatalf("NPC = %#v, want %#v", result.Value.NPCs[0], want)
}
if !reflect.DeepEqual(got.Aliases, []string{"Ash", "L.A."}) {
t.Fatalf("aliases = %#v, want canonical alias removal and deduplication", got.Aliases)
}
wantRelationships := []dnd.NPCRelationship{{Target: "Lord Oak", Relationship: "friend"}}
if !reflect.DeepEqual(got.Relationships, wantRelationships) {
t.Fatalf("relationships = %#v, want %#v", got.Relationships, wantRelationships)
}
wantRefs := []source.SourceRef{
{SourceID: "a", StartUnitID: 4, EndUnitID: 4},
{SourceID: "b", StartUnitID: 2, EndUnitID: 3},
}
if !reflect.DeepEqual(got.SourceRefs, wantRefs) {
t.Fatalf("source refs = %#v, want %#v", got.SourceRefs, wantRefs)
}
if got.ID != identity.DeriveID("Lady Ash") {
t.Fatalf("ID = %q, want derived ID", got.ID)
}
if !hasWarning(result.Warnings, ReasonCodeNPCFieldsNormalized, "npcs[0]") ||
!hasWarning(result.Warnings, ReasonCodeSourceReferencesNormalized, "npcs[0]") ||
!hasWarning(result.Warnings, ReasonCodeNPCIDRecomputed, "npcs[0]") {
t.Fatalf("warnings = %#v, want field, source, and ID warnings", result.Warnings)
for _, reason := range []string{ReasonCodeNPCFieldsNormalized, ReasonCodeSourceReferencesNormalized, ReasonCodeNPCIDRecomputed} {
if !hasWarning(result.Warnings, reason, "npcs[0]") {
t.Fatalf("warnings = %#v, want %s", result.Warnings, reason)
}
}
}
func TestNormalizeConsolidatesIdentityComponentsInStableOrder(t *testing.T) {
func TestNormalizeConsolidatesCanonicalNamesOnlyAndUnionsEvidence(t *testing.T) {
input := dnd.NPCList{NPCs: []dnd.NPC{
{
Name: " Captain Vale ",
Description: "first description",
Aliases: []string{"Vale"},
Relationships: []dnd.NPCRelationship{{Target: "Archivist", Relationship: "knows"}},
SourceRefs: []source.SourceRef{{SourceID: "a", StartUnitID: 1, EndUnitID: 1}},
},
{
Name: "Captain Vale",
Description: "second description",
Aliases: []string{"CV"},
SourceRefs: []source.SourceRef{{SourceID: "b", StartUnitID: 1, EndUnitID: 1}},
},
{
Name: "The Sage",
Description: "sage description",
Aliases: []string{"Archivist"},
SourceRefs: []source.SourceRef{{SourceID: "c", StartUnitID: 1, EndUnitID: 1}},
},
{
Name: "Archivist",
Description: "later sage description",
Aliases: []string{"Chronicler"},
SourceRefs: []source.SourceRef{{SourceID: "d", StartUnitID: 1, EndUnitID: 1}},
},
{
Name: "North",
Description: "north description",
SourceRefs: []source.SourceRef{{SourceID: "e", StartUnitID: 1, EndUnitID: 1}},
},
{
Name: "North Old",
Description: "old north description",
Aliases: []string{"North"},
SourceRefs: []source.SourceRef{{SourceID: "f", StartUnitID: 1, EndUnitID: 1}},
},
{
Name: "North Renamed",
Description: "renamed north description",
Aliases: []string{"North Old"},
SourceRefs: []source.SourceRef{{SourceID: "g", StartUnitID: 1, EndUnitID: 1}},
},
{Name: "Red", Description: "red", Aliases: []string{"Shared"}, SourceRefs: []source.SourceRef{{SourceID: "h", StartUnitID: 1, EndUnitID: 1}}},
{Name: "Blue", Description: "blue", Aliases: []string{"Shared"}, SourceRefs: []source.SourceRef{{SourceID: "i", StartUnitID: 1, EndUnitID: 1}}},
{Name: " Captain Vale ", SourceRefs: []source.SourceRef{{SourceID: "a", StartUnitID: 1, EndUnitID: 1}}},
{Name: "captain vale", SourceRefs: []source.SourceRef{{SourceID: "b", StartUnitID: 2, EndUnitID: 2}}},
{Name: "The Captain", SourceRefs: []source.SourceRef{{SourceID: "c", StartUnitID: 3, EndUnitID: 3}}},
}}
result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
t.Fatalf("Normalize() error = %v", err)
}
if got := len(result.Value.NPCs); got != 5 {
t.Fatalf("normalized NPC count = %d, want five components", got)
if len(result.Value.NPCs) != 2 || result.Value.NPCs[0].Name != "Captain Vale" || result.Value.NPCs[1].Name != "The Captain" {
t.Fatalf("NPCs = %#v, want name-only stable consolidation", result.Value.NPCs)
}
first := result.Value.NPCs[0]
if first.Name != "Captain Vale" || first.Description != "first description" || !reflect.DeepEqual(first.Aliases, []string{"Vale", "CV"}) {
t.Fatalf("first component = %#v, want first description and ordered aliases", first)
if refs := result.Value.NPCs[0].SourceRefs; len(refs) != 2 || refs[0].SourceID != "a" || refs[1].SourceID != "b" {
t.Fatalf("source refs = %#v, want evidence union", refs)
}
if !reflect.DeepEqual(first.SourceRefs, []source.SourceRef{
{SourceID: "a", StartUnitID: 1, EndUnitID: 1},
{SourceID: "b", StartUnitID: 1, EndUnitID: 1},
}) {
t.Fatalf("first provenance = %#v, want unioned refs", first.SourceRefs)
}
second := result.Value.NPCs[1]
if second.Name != "The Sage" || !reflect.DeepEqual(second.Aliases, []string{"Archivist", "Chronicler"}) || second.Description != "sage description" {
t.Fatalf("canonical-to-alias component = %#v, want consolidated sage", second)
}
if first.Relationships[0].Target != "The Sage" {
t.Fatalf("relationship target = %q, want The Sage", first.Relationships[0].Target)
}
if !hasWarning(result.Warnings, ReasonCodeRelationshipTargetCanonicalized, "npcs[0]") ||
!hasWarning(result.Warnings, ReasonCodeDuplicateNPCCollapsed, "npcs[0]") ||
!hasWarning(result.Warnings, ReasonCodeDuplicateNPCCollapsed, "npcs[2]") {
t.Fatalf("warnings = %#v, want collapse and target warnings", result.Warnings)
}
if got := result.Value.NPCs[2].Aliases; !reflect.DeepEqual(got, []string{"North Old", "North Renamed"}) {
t.Fatalf("transitive aliases = %#v, want ordered canonical members", got)
}
if result.Value.NPCs[3].Name != "Red" || result.Value.NPCs[4].Name != "Blue" {
t.Fatalf("shared-alias ordering = %#v, want Red then Blue", result.Value.NPCs[3:])
if !hasWarning(result.Warnings, ReasonCodeDuplicateNPCCollapsed, "npcs[0]") {
t.Fatalf("warnings = %#v, want duplicate collapse", result.Warnings)
}
}
func TestNormalizePreservesInvalidEvidenceAndDoesNotAliasInput(t *testing.T) {
invalid := dnd.NPCList{NPCs: []dnd.NPC{{
Name: " ",
Aliases: []string{""},
Description: " ",
Relationships: []dnd.NPCRelationship{{Target: " ", Relationship: " "}},
SourceRefs: []source.SourceRef{{SourceID: "source", StartUnitID: 9, EndUnitID: 9}},
}}}
original := cloneNPCListForTest(invalid)
result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(invalid))
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
func TestNormalizePreservesInvalidCandidatesAndDoesNotAliasInput(t *testing.T) {
input := dnd.NPCList{NPCs: []dnd.NPC{{Name: " ", SourceRefs: []source.SourceRef{{SourceID: "source", StartUnitID: 0, EndUnitID: -1}}}}}
before := dnd.NPCList{NPCs: []dnd.NPC{{Name: " ", SourceRefs: []source.SourceRef{{SourceID: "source", StartUnitID: 0, EndUnitID: -1}}}}}
result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil || !reflect.DeepEqual(input, before) {
t.Fatalf("Normalize() = %#v, %v; input mutated to %#v", result, err, input)
}
if !reflect.DeepEqual(invalid, original) {
t.Fatalf("normalizer mutated input: got %#v, want %#v", invalid, original)
if result.Value.NPCs[0].Name != "" || result.Value.NPCs[0].SourceRefs[0].EndUnitID != -1 {
t.Fatalf("candidate = %#v, want invalid semantics preserved", result.Value.NPCs[0])
}
if result.Value.NPCs[0].Name != "" || result.Value.NPCs[0].Aliases[0] != "" || result.Value.NPCs[0].Relationships[0].Target != "" {
t.Fatalf("invalid evidence was unexpectedly removed: %#v", result.Value.NPCs[0])
}
result.Value.NPCs[0].Aliases[0] = "changed"
result.Value.NPCs[0].Relationships[0].Target = "changed"
result.Value.NPCs[0].SourceRefs[0].SourceID = "changed"
if invalid.NPCs[0].Aliases[0] != "" || invalid.NPCs[0].Relationships[0].Target != " " || invalid.NPCs[0].SourceRefs[0].SourceID != "source" {
t.Fatalf("output aliases input storage: input = %#v", invalid)
if input.NPCs[0].SourceRefs[0].SourceID != "source" {
t.Fatal("output aliases input evidence")
}
}
@@ -234,52 +102,17 @@ func TestNormalizeHandlesNilAndCanceledCalls(t *testing.T) {
normalizer := New(Options{})
result, err := normalizer.Normalize(context.Background(), normalizeRequest(dnd.NPCList{NPCs: nil}))
if err != nil || result.Value.NPCs != nil {
t.Fatalf("nil list result = %#v, error = %v, want nil NPC slice", result.Value, err)
t.Fatalf("nil list result = %#v, error = %v", result.Value, err)
}
canceled, cancel := context.WithCancel(context.Background())
cancel()
if _, err := normalizer.Normalize(canceled, normalizeRequest(dnd.NPCList{})); err == nil || !strings.Contains(err.Error(), "context error") {
t.Fatalf("canceled Normalize() error = %v, want context error", err)
}
if _, err := normalizer.Normalize(nil, normalizeRequest(dnd.NPCList{})); err == nil || !strings.Contains(err.Error(), "context must not be nil") {
t.Fatalf("nil context Normalize() error = %v, want context error", err)
}
var nilNormalizer *Normalizer
if _, err := nilNormalizer.Normalize(context.Background(), normalizeRequest(dnd.NPCList{})); err == nil {
t.Fatal("nil normalizer Normalize() error = nil, want error")
}
}
func TestNormalizePreservesPresentEmptyAliases(t *testing.T) {
result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(dnd.NPCList{NPCs: []dnd.NPC{{
Name: "Hooded Guard",
Aliases: []string{},
Description: "A distinguishable sentry.",
SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}},
}}}))
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
}
if result.Value.NPCs[0].Aliases == nil || len(result.Value.NPCs[0].Aliases) != 0 {
t.Fatalf("aliases = %#v, want present empty array", result.Value.NPCs[0].Aliases)
t.Fatalf("canceled Normalize() error = %v", err)
}
}
func normalizeRequest(value dnd.NPCList) contracts.TypedNormalizeRequest[dnd.NPCList] {
return contracts.TypedNormalizeRequest[dnd.NPCList]{
MergeOutput: contracts.MergeArtifact[dnd.NPCList]{Value: value},
}
}
func cloneNPCListForTest(input dnd.NPCList) dnd.NPCList {
output := dnd.NPCList{}
if input.NPCs != nil {
output.NPCs = make([]dnd.NPC, len(input.NPCs))
for index, npc := range input.NPCs {
output.NPCs[index] = cloneNPC(npc)
}
}
return output
return contracts.TypedNormalizeRequest[dnd.NPCList]{MergeOutput: contracts.MergeArtifact[dnd.NPCList]{Value: value}}
}
func hasWarning(warnings []contracts.Warning, reason, scope string) bool {