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

package spells

import (
	"context"
	"fmt"
	"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/shared"
	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
	spellcatalog "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/spells/catalog"
	"golang.org/x/text/cases"
)

const (
	Key                 = "dnd/spells"
	normalizationPolicy = "dnd.spells.normalize.v2"
	NormalizationPolicy = normalizationPolicy
)

const (
	ReasonCodeSpellNameCanonicalized      = "spell_name_canonicalized"
	ReasonCodeSpellNameUnresolved         = "spell_name_unresolved"
	ReasonCodeSourceReferencesNormalized  = "source_references_normalized"
	ReasonCodeDuplicateSpellCastCollapsed = "duplicate_spell_cast_collapsed"
	ReasonCodeWarningsOmitted             = "spell_normalization_warnings_omitted"
)

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

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

type Options struct{}

type Normalizer struct {
	effectiveCatalog spellcatalog.EffectiveCatalog
}

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]
	}
	effectiveCatalog, err := spellcatalog.ResolveEffectiveCatalog(referenceSet)
	if err != nil {
		return nil, normalizerErrorf("resolve effective spell catalog: %w", err)
	}
	return &Normalizer{effectiveCatalog: effectiveCatalog}, 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
	}
	return map[string]any{
		"catalog_base_id":      n.effectiveCatalog.BaseID(),
		"catalog_digest":       n.effectiveCatalog.Digest(),
		"catalog_overlay_ids":  append([]string(nil), n.effectiveCatalog.OverlayIDs()...),
		"normalization_policy": normalizationPolicy,
	}
}

func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
	if n == nil {
		return nil
	}
	return []pipeline.CheckpointFingerprint{
		{Name: "effective_catalog", Value: n.effectiveCatalog.Digest()},
		{Name: "normalization_policy", Value: normalizationPolicy},
	}
}

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

	index := source.NewDocumentIndex(req.Source)
	order := shared.NewSourceRefOrderFromIndex(index)
	value, warnings := normalizeSpellList(req.MergeOutput.Value, n.effectiveCatalog, order)
	value, duplicateWarnings := collapseDuplicateSpellCasts(value, index, n.effectiveCatalog)
	warnings = append(warnings, duplicateWarnings...)
	return contracts.TypedNormalizeResult[dnd.SpellList]{
		Value:    value,
		Warnings: diagnostics.LimitWarnings(warnings, "spell_casts", ReasonCodeWarningsOmitted),
	}, nil
}

func normalizeSpellList(input dnd.SpellList, catalog spellcatalog.EffectiveCatalog, order shared.SourceRefOrder) (dnd.SpellList, []contracts.Warning) {
	var warnings []contracts.Warning
	if input.SpellCasts == nil {
		return dnd.SpellList{}, nil
	}

	output := dnd.SpellList{SpellCasts: make([]dnd.SpellCast, len(input.SpellCasts))}
	for index, inputCast := range input.SpellCasts {
		cast := cloneSpellCast(inputCast)
		if canonicalName, ok := catalog.Lookup(inputCast.Spell); ok {
			if inputCast.Spell != canonicalName {
				warnings = append(warnings, contracts.Warning{
					Scope:      spellCastScope(index),
					ReasonCode: ReasonCodeSpellNameCanonicalized,
					Message: fmt.Sprintf("input index %d: spell name canonicalized from %q to %q",
						index, boundedName(inputCast.Spell), boundedName(canonicalName)),
				})
			}
			cast.Spell = canonicalName
		} else {
			warnings = append(warnings, contracts.Warning{
				Scope:      spellCastScope(index),
				ReasonCode: ReasonCodeSpellNameUnresolved,
				Message: fmt.Sprintf("input index %d: spell name %q could not be resolved in the effective catalog",
					index, boundedName(inputCast.Spell)),
			})
		}

		canonicalRefs, orderChanged, duplicateCount := canonicalizeSourceRefs(order, inputCast.SourceRefs)
		cast.SourceRefs = canonicalRefs
		if orderChanged || duplicateCount > 0 {
			warnings = append(warnings, contracts.Warning{
				Scope:      spellCastScope(index),
				ReasonCode: ReasonCodeSourceReferencesNormalized,
				Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d, order changed %t, duplicates removed %d)",
					index, len(inputCast.SourceRefs), len(canonicalRefs), orderChanged, duplicateCount),
			})
		}
		output.SpellCasts[index] = cast
	}
	return output, warnings
}

func cloneSpellCast(input dnd.SpellCast) dnd.SpellCast {
	output := input
	if input.SourceRefs != nil {
		output.SourceRefs = make([]source.SourceRef, len(input.SourceRefs))
		copy(output.SourceRefs, input.SourceRefs)
	}
	return output
}

func canonicalizeSourceRefs(order shared.SourceRefOrder, input []source.SourceRef) ([]source.SourceRef, bool, int) {
	orderChanged := false
	for index := 1; index < len(input); index++ {
		if order.Less(input[index], input[index-1]) {
			orderChanged = true
			break
		}
	}
	canonical := order.Canonicalize(input)
	return canonical, orderChanged, len(input) - len(canonical)
}

type duplicateGroup struct {
	retainedIndex int
	removed       []int
}

func collapseDuplicateSpellCasts(input dnd.SpellList, documentIndex source.DocumentIndex, catalog spellcatalog.EffectiveCatalog) (dnd.SpellList, []contracts.Warning) {
	if len(input.SpellCasts) == 0 {
		return input, nil
	}

	keep := make([]bool, len(input.SpellCasts))
	groups := make([]duplicateGroup, 0)
	groupByKey := make(map[string]int)
	for index, cast := range input.SpellCasts {
		key, eligible := duplicateKey(cast, documentIndex, catalog)
		if !eligible {
			keep[index] = true
			continue
		}
		groupIndex, exists := groupByKey[key]
		if !exists {
			groupByKey[key] = len(groups)
			groups = append(groups, duplicateGroup{retainedIndex: index})
			keep[index] = true
			continue
		}
		groups[groupIndex].removed = append(groups[groupIndex].removed, index)
	}

	removedAny := false
	for _, group := range groups {
		if len(group.removed) > 0 {
			removedAny = true
			break
		}
	}
	if !removedAny {
		return input, nil
	}

	output := dnd.SpellList{SpellCasts: make([]dnd.SpellCast, 0, len(input.SpellCasts))}
	for index, cast := range input.SpellCasts {
		if keep[index] {
			output.SpellCasts = append(output.SpellCasts, cast)
		}
	}

	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(cast dnd.SpellCast, documentIndex source.DocumentIndex, catalog spellcatalog.EffectiveCatalog) (string, bool) {
	canonicalName, resolved := catalog.Lookup(cast.Spell)
	if !resolved || len(cast.SourceRefs) == 0 {
		return "", false
	}
	for _, ref := range cast.SourceRefs {
		if documentIndex.ValidateRef(ref) != nil {
			return "", false
		}
	}

	var key strings.Builder
	writeKeyString(&key, canonicalName)
	writeKeyString(&key, cases.Fold().String(strings.Join(strings.Fields(cast.Caster), " ")))
	for _, ref := range cast.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 {
	const maxDisplayedIndices = 20
	displayed := removed
	if len(displayed) > maxDisplayedIndices {
		displayed = displayed[:maxDisplayedIndices]
	}
	indices := make([]string, len(displayed))
	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:      spellCastScope(retainedIndex),
		ReasonCode: ReasonCodeDuplicateSpellCastCollapsed,
		Message:    message,
	}
}

func boundedName(name string) string {
	runes := []rune(name)
	if len(runes) <= 128 {
		return string(runes)
	}
	return string(runes[:127]) + "…"
}

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

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.SpellListKind,
		ReferenceSlots: referenceSlots(),
	}
}

func Register(registry *pipeline.NormalizerRegistry) error {
	return pipeline.RegisterNormalizerBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Normalizer[dnd.SpellList], 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 referenceSlots() []contracts.ReferenceSlot {
	return []contracts.ReferenceSlot{{
		Name:               spellcatalog.SpellCatalogReferenceSlot,
		Description:        "Optional canonical spell-name catalog used for normalization and duplicate identity.",
		AcceptedMediaTypes: []string{"application/json"},
		MaxBytes:           1048576,
	}}
}

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