notarius/internal/modules/dnd/normalize/combatturns/normalizer.go

// Package combatturns normalizes merged D&D combat-turn candidates.
package combatturns

import (
	"context"
	"fmt"
	"sort"
	"strconv"
	"strings"

	"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/npcs/identity"
	npcregistry "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/registry"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
)

const (
	Key                 = "dnd/combat-turns"
	normalizationPolicy = "dnd.combat_turns.normalize.v1"
	NormalizationPolicy = normalizationPolicy

	ReasonCodeFieldsNormalized     = "combat_turn_fields_normalized"
	ReasonCodeActorCanonicalized   = "combat_actor_canonicalized"
	ReasonCodeTargetCanonicalized  = "combat_target_canonicalized"
	ReasonCodeSourceRefsNormalized = "source_references_normalized"
	ReasonCodeTurnsReordered       = "combat_turns_reordered"
	ReasonCodeDuplicateCollapsed   = "duplicate_combat_turn_collapsed"
)

const (
	NPCRegistryReferenceSlot = npcregistry.ReferenceSlot
	NPCRegistryMaxBytes      = npcregistry.MaxBytes
)

var requiredCapabilities = []string{"merged"}
var providedCapabilities = []string{"normalized"}

var _ contracts.Normalizer[dnd.CombatTurnList] = (*Normalizer)(nil)
var _ contracts.ManifestMetadataProvider = (*Normalizer)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Normalizer)(nil)

type Options struct{}

type Normalizer struct {
	npcRegistry *npcregistry.Registry
}

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]
	}
	npcRegistry, err := npcregistry.Resolve(referenceSet)
	if err != nil {
		return nil, normalizerErrorf("prepare NPC registry: %w", err)
	}
	return &Normalizer{npcRegistry: npcRegistry}, 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 {
		return nil
	}
	metadata := map[string]any{
		"normalization_policy": normalizationPolicy,
		"identity_policy":      identity.Policy,
	}
	if n.npcRegistry.Bound() {
		metadata["npc_registry_digest"] = n.npcRegistry.Digest()
		metadata["npc_count"] = n.npcRegistry.Count()
	}
	return metadata
}

func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
	if n == nil {
		return nil
	}
	fingerprints := []pipeline.CheckpointFingerprint{
		{Name: "normalization_policy", Value: normalizationPolicy},
		{Name: "identity_policy", Value: identity.Policy},
	}
	if n.npcRegistry.Bound() {
		fingerprints = append(fingerprints, pipeline.CheckpointFingerprint{Name: "npc_registry", Value: n.npcRegistry.Digest()})
	}
	return fingerprints
}

func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalizeRequest[dnd.CombatTurnList]) (contracts.TypedNormalizeResult[dnd.CombatTurnList], error) {
	if n == nil {
		return contracts.TypedNormalizeResult[dnd.CombatTurnList]{}, normalizerErrorf("normalizer must not be nil")
	}
	if ctx == nil {
		return contracts.TypedNormalizeResult[dnd.CombatTurnList]{}, normalizerErrorf("context must not be nil")
	}
	if err := ctx.Err(); err != nil {
		return contracts.TypedNormalizeResult[dnd.CombatTurnList]{}, normalizerErrorf("context error before normalize: %w", err)
	}

	value, warnings := normalizeList(req.MergeOutput.Value, req.Source, n.npcRegistry)
	return contracts.TypedNormalizeResult[dnd.CombatTurnList]{Value: value, Warnings: warnings}, nil
}

type normalizedRecord struct {
	turn        dnd.CombatTurn
	inputIndex  int
	earliest    int
	hasEvidence bool
}

type targetCanonicalization struct {
	actionIndex int
	targetIndex int
	from        string
	to          string
}

func normalizeList(input dnd.CombatTurnList, doc *source.SourceDocument, registry *npcregistry.Registry) (dnd.CombatTurnList, []contracts.Warning) {
	if input.CombatTurns == nil {
		return dnd.CombatTurnList{}, nil
	}

	records := make([]normalizedRecord, len(input.CombatTurns))
	warnings := make([]contracts.Warning, 0)
	for index, inputTurn := range input.CombatTurns {
		turn, fieldsChanged, actorChange, targetChanges, refsChanged := normalizeTurn(inputTurn, registry)
		earliest, hasEvidence := earliestSourcePosition(doc, turn)
		records[index] = normalizedRecord{
			turn:        turn,
			inputIndex:  index,
			earliest:    earliest,
			hasEvidence: hasEvidence,
		}
		if fieldsChanged {
			warnings = append(warnings, contracts.Warning{
				Scope:      turnScope(index),
				ReasonCode: ReasonCodeFieldsNormalized,
				Message:    fmt.Sprintf("input index %d: combat turn fields normalized", index),
			})
		}
		if actorChange != nil {
			warnings = append(warnings, contracts.Warning{
				Scope:      turnScope(index),
				ReasonCode: ReasonCodeActorCanonicalized,
				Message: fmt.Sprintf("input index %d: actor canonicalized from %s to %s",
					index, diagnostics.Quote(actorChange.from), diagnostics.Quote(actorChange.to)),
			})
		}
		for _, targetChange := range targetChanges {
			warnings = append(warnings, contracts.Warning{
				Scope:      turnScope(index),
				ReasonCode: ReasonCodeTargetCanonicalized,
				Message: fmt.Sprintf("input index %d: action %d target %d canonicalized from %s to %s",
					index, targetChange.actionIndex, targetChange.targetIndex,
					diagnostics.Quote(targetChange.from), diagnostics.Quote(targetChange.to)),
			})
		}
		if refsChanged {
			warnings = append(warnings, contracts.Warning{
				Scope:      turnScope(index),
				ReasonCode: ReasonCodeSourceRefsNormalized,
				Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d)",
					index, len(inputTurn.SourceRefs), len(turn.SourceRefs)),
			})
		}
	}

	sort.SliceStable(records, func(left, right int) bool {
		if records[left].hasEvidence != records[right].hasEvidence {
			return records[left].hasEvidence
		}
		if !records[left].hasEvidence {
			return false
		}
		return records[left].earliest < records[right].earliest
	})
	for position, record := range records {
		if position == record.inputIndex {
			continue
		}
		warnings = append(warnings, contracts.Warning{
			Scope:      turnScope(record.inputIndex),
			ReasonCode: ReasonCodeTurnsReordered,
			Message: fmt.Sprintf("input index %d moved to normalized position %d by source chronology",
				record.inputIndex, position),
		})
	}

	output, duplicateWarnings := collapseDuplicates(records, doc)
	warnings = append(warnings, duplicateWarnings...)
	return dnd.CombatTurnList{CombatTurns: output}, warnings
}

func normalizeTurn(input dnd.CombatTurn, registry *npcregistry.Registry) (dnd.CombatTurn, bool, *targetCanonicalization, []targetCanonicalization, bool) {
	output := cloneCombatTurn(input)
	output.Actor = identity.NormalizeDisplay(input.Actor)
	output.Summary = identity.NormalizeDisplay(input.Summary)

	var actorChange *targetCanonicalization
	if canonical, ok := registry.Lookup(output.Actor); ok {
		canonicalName := identity.NormalizeDisplay(canonical.Name)
		if output.Actor != canonicalName {
			actorChange = &targetCanonicalization{from: output.Actor, to: canonicalName}
			output.Actor = canonicalName
		}
	}

	targetChanges := make([]targetCanonicalization, 0)
	for actionIndex := range output.Actions {
		action := &output.Actions[actionIndex]
		action.Declaration = identity.NormalizeDisplay(action.Declaration)
		if action.Resolution != nil {
			resolution := identity.NormalizeDisplay(*action.Resolution)
			action.Resolution = &resolution
		}
		if action.Targets == nil {
			continue
		}
		targets := make([]string, 0, len(action.Targets))
		seen := make(map[string]struct{}, len(action.Targets))
		for targetIndex, target := range action.Targets {
			normalized := identity.NormalizeDisplay(target)
			if canonical, ok := registry.Lookup(normalized); ok {
				canonicalName := identity.NormalizeDisplay(canonical.Name)
				if normalized != canonicalName {
					targetChanges = append(targetChanges, targetCanonicalization{
						actionIndex: actionIndex,
						targetIndex: targetIndex,
						from:        normalized,
						to:          canonicalName,
					})
				}
				normalized = canonicalName
			}
			key := identity.ComparisonKey(normalized)
			if _, exists := seen[key]; exists {
				continue
			}
			seen[key] = struct{}{}
			targets = append(targets, normalized)
		}
		action.Targets = targets
	}

	fieldsChanged := input.Actor != output.Actor || input.Summary != output.Summary
	if len(input.Actions) != len(output.Actions) {
		fieldsChanged = true
	}
	for index := range output.Actions {
		if input.Actions[index].Declaration != output.Actions[index].Declaration ||
			!stringSlicesEqual(input.Actions[index].Targets, output.Actions[index].Targets) ||
			!stringPointersEqual(input.Actions[index].Resolution, output.Actions[index].Resolution) {
			fieldsChanged = true
			break
		}
	}
	canonicalRefs, _, _ := canonicalizeSourceRefs(input.SourceRefs)
	output.SourceRefs = canonicalRefs
	refsChanged := !sourceRefsEqual(input.SourceRefs, output.SourceRefs)
	return output, fieldsChanged, actorChange, targetChanges, refsChanged
}

func cloneCombatTurn(input dnd.CombatTurn) dnd.CombatTurn {
	output := input
	if input.Round != nil {
		round := *input.Round
		output.Round = &round
	}
	if input.Actions != nil {
		output.Actions = make([]dnd.CombatAction, len(input.Actions))
		for index, action := range input.Actions {
			output.Actions[index] = cloneCombatAction(action)
		}
	}
	if input.SourceRefs != nil {
		output.SourceRefs = make([]source.SourceRef, len(input.SourceRefs))
		copy(output.SourceRefs, input.SourceRefs)
	}
	return output
}

func cloneCombatAction(input dnd.CombatAction) dnd.CombatAction {
	output := input
	if input.Targets != nil {
		output.Targets = make([]string, len(input.Targets))
		copy(output.Targets, input.Targets)
	}
	if input.Resolution != nil {
		resolution := *input.Resolution
		output.Resolution = &resolution
	}
	return output
}

func stringSlicesEqual(left, right []string) bool {
	if (left == nil) != (right == nil) || len(left) != len(right) {
		return false
	}
	for index := range left {
		if left[index] != right[index] {
			return false
		}
	}
	return true
}

func stringPointersEqual(left, right *string) bool {
	if (left == nil) != (right == nil) {
		return false
	}
	return left == nil || *left == *right
}

func sourceRefsEqual(left, right []source.SourceRef) bool {
	if (left == nil) != (right == nil) || len(left) != len(right) {
		return false
	}
	for index := range left {
		if left[index] != right[index] {
			return false
		}
	}
	return true
}

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)
	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
		}
	}

	unique := make([]source.SourceRef, 0, len(canonical))
	for _, ref := range canonical {
		if len(unique) == 0 || unique[len(unique)-1] != ref {
			unique = append(unique, ref)
		}
	}
	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 earliestSourcePosition(doc *source.SourceDocument, turn dnd.CombatTurn) (int, bool) {
	if doc == nil {
		return 0, false
	}
	earliest := 0
	found := false
	for _, ref := range turn.SourceRefs {
		if source.ValidateRef(doc, ref) != nil {
			continue
		}
		index, ok := source.UnitIndex(doc, ref.StartUnitID)
		if !ok || (found && index >= earliest) {
			continue
		}
		earliest = index
		found = true
	}
	return earliest, found
}

type duplicateGroup struct {
	retainedIndex int
	removed       []int
}

func collapseDuplicates(records []normalizedRecord, doc *source.SourceDocument) ([]dnd.CombatTurn, []contracts.Warning) {
	if len(records) == 0 {
		return make([]dnd.CombatTurn, 0), nil
	}

	keep := make([]bool, len(records))
	groups := make([]duplicateGroup, 0)
	groupByKey := make(map[string]int)
	for index, record := range records {
		key, eligible := duplicateKey(record.turn, doc)
		if !eligible {
			keep[index] = true
			continue
		}
		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.CombatTurn, 0, len(records))
	for index, record := range records {
		if keep[index] {
			output = append(output, cloneCombatTurn(record.turn))
		}
	}

	warnings := make([]contracts.Warning, 0)
	for _, group := range groups {
		if len(group.removed) == 0 {
			continue
		}
		warnings = append(warnings, duplicateWarning(group.retainedIndex, group.removed))
	}
	return output, warnings
}

func duplicateKey(turn dnd.CombatTurn, doc *source.SourceDocument) (string, bool) {
	if len(turn.SourceRefs) == 0 {
		return "", false
	}
	for _, ref := range turn.SourceRefs {
		if source.ValidateRef(doc, ref) != nil {
			return "", false
		}
	}

	var key strings.Builder
	writeKeyString(&key, identity.ComparisonKey(turn.Actor))
	writeKeyString(&key, string(turn.TurnKind))
	if turn.Round == nil {
		key.WriteByte('0')
	} else {
		key.WriteByte('1')
		writeKeyInt(&key, *turn.Round)
	}
	for _, ref := range turn.SourceRefs {
		writeKeyString(&key, ref.SourceID)
		writeKeyInt(&key, ref.StartUnitID)
		writeKeyInt(&key, ref.EndUnitID)
	}
	return key.String(), true
}

func writeKeyString(builder *strings.Builder, value string) {
	builder.WriteString(strconv.Itoa(len(value)))
	builder.WriteByte(':')
	builder.WriteString(value)
}

func writeKeyInt(builder *strings.Builder, value int) {
	builder.WriteString(strconv.Itoa(value))
	builder.WriteByte(';')
}

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:      turnScope(retainedIndex),
		ReasonCode: ReasonCodeDuplicateCollapsed,
		Message: diagnostics.Aggregate(
			fmt.Sprintf("duplicate combat turn collapsed; retained input index %d", retainedIndex),
			issues,
		),
	}
}

func turnScope(index int) string { return fmt.Sprintf("combat_turns[%d]", index) }

func referenceSlots() []contracts.ReferenceSlot {
	return []contracts.ReferenceSlot{{
		Name:               NPCRegistryReferenceSlot,
		Description:        "Optional normalized NPC registry used for canonical actor and target grounding.",
		AcceptedMediaTypes: []string{"application/json"},
		MaxBytes:           NPCRegistryMaxBytes,
	}}
}

func ModuleSpec() pipeline.ModuleSpec {
	return pipeline.ModuleSpec{
		Key:            Key,
		Stage:          pipeline.StageNormalize,
		Requires:       append([]string(nil), requiredCapabilities...),
		Provides:       append([]string(nil), providedCapabilities...),
		ArtifactKind:   dnd.CombatTurnListKind,
		ReferenceSlots: referenceSlots(),
	}
}

func Register(registry *pipeline.NormalizerRegistry) error {
	return pipeline.RegisterNormalizerBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Normalizer[dnd.CombatTurnList], error) {
		options, err := DecodeOptions(request.Options)
		if err != nil {
			return nil, err
		}
		return New(options, request.References)
	})
}

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 {
		return Options{}, normalizerErrorf("%w", err)
	}
	return Options{}, nil
}

func normalizerErrorf(format string, args ...any) error {
	return fmt.Errorf("dnd combat turns normalizer: "+format, args...)
}