Files
notarius/internal/modules/dnd/normalize/npcinteractions/normalizer.go

311 lines
12 KiB
Go

// Package npcinteractions normalizes merged D&D NPC interaction candidates.
package npcinteractions
import (
"context"
"fmt"
"sort"
"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"
interactionmodel "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcinteractions"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
npcregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/registry"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
)
const (
Key = "dnd/npc-interactions"
normalizationPolicy = "dnd.npc_interactions.normalize.v2"
NormalizationPolicy = normalizationPolicy
ReasonCodeNameCanonicalized = "npc_interaction_name_canonicalized"
ReasonCodeSourceRefsNormalized = "source_references_normalized"
ReasonCodeInteractionsReordered = "npc_interactions_reordered"
ReasonCodeDuplicateCollapsed = "duplicate_npc_interaction_collapsed"
ReasonCodeWarningsOmitted = "npc_interaction_normalization_warnings_omitted"
)
const (
NPCRegistryReferenceSlot = npcregistry.ReferenceSlot
NPCRegistryMaxBytes = npcregistry.MaxBytes
)
var requiredCapabilities = []string{"merged"}
var providedCapabilities = []string{"normalized"}
var referenceSlotDescriptions = shared.ReferenceSlotDescriptions{
Glossary: "Optional campaign glossary reference material used only for interaction disambiguation.",
Party: "Optional party roster reference material used only for interaction disambiguation.",
Players: "Optional player list reference material used only for interaction disambiguation.",
Roster: "Deprecated alias for party roster reference material used only for interaction disambiguation.",
}
var _ contracts.Normalizer[dnd.NPCInteractionList] = (*Normalizer)(nil)
var _ contracts.ManifestMetadataProvider = (*Normalizer)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Normalizer)(nil)
type Options struct{}
type Normalizer struct {
npcResolver *npcregistry.Resolver
}
func New(_ Options, references ...contracts.ReferenceSet) (*Normalizer, error) {
if len(references) > 1 {
return nil, normalizerErrorf("at most one reference set may be supplied")
}
var referenceSet contracts.ReferenceSet
if len(references) == 1 {
referenceSet = references[0]
}
resolver, err := npcregistry.NewResolver(referenceSet)
if err != nil {
return nil, normalizerErrorf("prepare NPC registry: %w", err)
}
return &Normalizer{npcResolver: resolver}, nil
}
func (n *Normalizer) Key() string { return Key }
func (n *Normalizer) ReferenceSlots() []contracts.ReferenceSlot { return referenceSlots() }
func (n *Normalizer) ManifestMetadata() map[string]any {
if n == nil || n.npcResolver == nil {
return nil
}
metadata := map[string]any{
"normalization_policy": normalizationPolicy,
"identity_policy": identity.Policy,
}
seeded := n.npcResolver.Seeded()
if seeded.Bound() {
metadata["npc_registry_digest"] = seeded.Digest()
metadata["npc_count"] = seeded.Count()
}
return metadata
}
func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
if n == nil || n.npcResolver == nil {
return nil
}
return []pipeline.CheckpointFingerprint{
{Name: "normalization_policy", Value: normalizationPolicy},
{Name: "identity_policy", Value: identity.Policy},
{Name: "npc_registry", Value: n.npcResolver.Seeded().ProjectionDigest()},
}
}
func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalizeRequest[dnd.NPCInteractionList]) (contracts.TypedNormalizeResult[dnd.NPCInteractionList], error) {
if n == nil || n.npcResolver == nil {
return contracts.TypedNormalizeResult[dnd.NPCInteractionList]{}, normalizerErrorf("normalizer must not be nil")
}
if ctx == nil {
return contracts.TypedNormalizeResult[dnd.NPCInteractionList]{}, normalizerErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedNormalizeResult[dnd.NPCInteractionList]{}, normalizerErrorf("context error before normalize: %w", err)
}
registry, err := n.npcResolver.Resolve(req.References)
if err != nil {
return contracts.TypedNormalizeResult[dnd.NPCInteractionList]{}, normalizerErrorf("resolve NPC registry: %w", err)
}
if !registry.Bound() {
return contracts.TypedNormalizeResult[dnd.NPCInteractionList]{}, normalizerErrorf("NPC registry reference is required")
}
index := source.NewDocumentIndex(req.Source)
order := shared.NewSourceRefOrderFromIndex(index)
value, warnings := normalizeList(req.MergeOutput.Value, index, order, registry)
return contracts.TypedNormalizeResult[dnd.NPCInteractionList]{Value: value, Warnings: warnings}, nil
}
type normalizedRecord struct {
interaction dnd.NPCInteraction
inputIndex int
}
type nameCanonicalization struct {
from string
to string
}
func normalizeList(input dnd.NPCInteractionList, documentIndex source.DocumentIndex, order shared.SourceRefOrder, registry *npcregistry.Registry) (dnd.NPCInteractionList, []contracts.Warning) {
if input.Interactions == nil {
return dnd.NPCInteractionList{}, nil
}
records := make([]normalizedRecord, len(input.Interactions))
warnings := make([]contracts.Warning, 0)
for index, inputInteraction := range input.Interactions {
interaction, nameChange, refsChanged := normalizeInteraction(inputInteraction, order, registry)
records[index] = normalizedRecord{interaction: interaction, inputIndex: index}
if nameChange != nil {
warnings = append(warnings, contracts.Warning{
Scope: interactionScope(index),
ReasonCode: ReasonCodeNameCanonicalized,
Message: fmt.Sprintf("input index %d: NPC name canonicalized from %s to %s",
index, diagnostics.Quote(nameChange.from), diagnostics.Quote(nameChange.to)),
})
}
if refsChanged {
warnings = append(warnings, contracts.Warning{
Scope: interactionScope(index),
ReasonCode: ReasonCodeSourceRefsNormalized,
Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d)",
index, len(inputInteraction.SourceRefs), len(interaction.SourceRefs)),
})
}
}
sort.SliceStable(records, func(left, right int) bool {
return interactionmodel.Less(order, records[left].interaction, records[right].interaction)
})
for position, record := range records {
if position == record.inputIndex {
continue
}
warnings = append(warnings, contracts.Warning{
Scope: interactionScope(record.inputIndex),
ReasonCode: ReasonCodeInteractionsReordered,
Message: fmt.Sprintf("input index %d moved to normalized position %d by source chronology", record.inputIndex, position),
})
}
output, duplicateWarnings := collapseDuplicates(records, documentIndex)
warnings = append(warnings, duplicateWarnings...)
return dnd.NPCInteractionList{Interactions: output},
diagnostics.LimitWarnings(warnings, "npc_interactions", ReasonCodeWarningsOmitted)
}
func normalizeInteraction(input dnd.NPCInteraction, order shared.SourceRefOrder, registry *npcregistry.Registry) (dnd.NPCInteraction, *nameCanonicalization, bool) {
output := cloneInteraction(input)
if canonical, ok := registry.Lookup(identity.NormalizeDisplay(input.Name)); ok {
output.Name = canonical.Name
}
var nameChange *nameCanonicalization
if input.Name != output.Name {
nameChange = &nameCanonicalization{from: input.Name, to: output.Name}
}
output.SourceRefs = order.Canonicalize(input.SourceRefs)
return output, nameChange, !interactionmodel.SourceRefsEqual(input.SourceRefs, output.SourceRefs)
}
func cloneInteraction(input dnd.NPCInteraction) dnd.NPCInteraction {
output := input
if input.SourceRefs != nil {
output.SourceRefs = append([]source.SourceRef(nil), input.SourceRefs...)
}
return output
}
type duplicateGroup struct {
retainedIndex int
removed []int
}
func collapseDuplicates(records []normalizedRecord, documentIndex source.DocumentIndex) ([]dnd.NPCInteraction, []contracts.Warning) {
if len(records) == 0 {
return make([]dnd.NPCInteraction, 0), nil
}
keep := make([]bool, len(records))
groups := make([]duplicateGroup, 0)
groupByKey := make(map[string]int)
for index, record := range records {
if !interactionmodel.ValidSourceRefs(documentIndex, record.interaction.SourceRefs) {
keep[index] = true
continue
}
key := interactionmodel.ExactIdentity(record.interaction)
groupIndex, exists := groupByKey[key]
if !exists {
groupByKey[key] = len(groups)
groups = append(groups, duplicateGroup{retainedIndex: record.inputIndex})
keep[index] = true
continue
}
groups[groupIndex].removed = append(groups[groupIndex].removed, record.inputIndex)
}
output := make([]dnd.NPCInteraction, 0, len(records))
for index, record := range records {
if keep[index] {
output = append(output, cloneInteraction(record.interaction))
}
}
warnings := make([]contracts.Warning, 0)
for _, group := range groups {
if len(group.removed) != 0 {
warnings = append(warnings, duplicateWarning(group.retainedIndex, group.removed))
}
}
return output, warnings
}
func duplicateWarning(retainedIndex int, removed []int) contracts.Warning {
issues := make([]string, len(removed))
for index, removedIndex := range removed {
issues[index] = fmt.Sprintf("removed input index %d", removedIndex)
}
return contracts.Warning{
Scope: interactionScope(retainedIndex),
ReasonCode: ReasonCodeDuplicateCollapsed,
Message: diagnostics.Aggregate(
fmt.Sprintf("duplicate NPC interaction collapsed; retained input index %d", retainedIndex), issues),
}
}
func interactionScope(index int) string { return fmt.Sprintf("interactions[%d]", index) }
func referenceSlots() []contracts.ReferenceSlot {
slots := shared.ReferenceSlots(referenceSlotDescriptions)
slots = append(slots, contracts.ReferenceSlot{
Name: NPCRegistryReferenceSlot,
Description: "Required normalized NPC registry used only for interaction identity grounding, never as interaction evidence.",
Required: true,
AcceptedMediaTypes: []string{"application/json"},
AcceptedArtifactKinds: []contracts.ArtifactKind{dnd.NPCListKind},
MaxBytes: NPCRegistryMaxBytes,
})
sort.Slice(slots, func(left, right int) bool { return slots[left].Name < slots[right].Name })
return slots
}
func ModuleSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{
Key: Key,
Stage: pipeline.StageNormalize,
ExecutionClass: contracts.ExecutionClassDeterministic,
Requires: append([]string(nil), requiredCapabilities...),
Provides: append([]string(nil), providedCapabilities...),
ArtifactKind: dnd.NPCInteractionListKind,
ReferenceSlots: referenceSlots(),
}
}
func Register(registry *pipeline.NormalizerRegistry) error {
return pipeline.RegisterNormalizerBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Normalizer[dnd.NPCInteractionList], error) {
options, err := DecodeOptions(request.Options)
if err != nil {
return nil, err
}
return New(options, request.References)
})
}
func DecodeOptions(options map[string]any) (Options, error) {
if err := pipeline.RejectUnknownOptions(options); err != nil {
return Options{}, normalizerErrorf("%w", err)
}
return Options{}, nil
}
func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }
func normalizerErrorf(format string, args ...any) error {
return fmt.Errorf("dnd NPC interactions normalizer: "+format, args...)
}