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

255 lines
8.7 KiB
Go

// Package itemevents normalizes merged D&D item-event candidates.
package itemevents
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"
itemeventmodel "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/itemevents"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
)
const (
Key = "dnd/item-events"
normalizationPolicy = "dnd.item_events.normalize.v1"
NormalizationPolicy = normalizationPolicy
ReasonCodeDisplayNormalized = "item_event_display_normalized"
ReasonCodeSourceRefsNormalized = "source_references_normalized"
ReasonCodeEventsReordered = "item_events_reordered"
ReasonCodeDuplicateCollapsed = "duplicate_item_event_collapsed"
ReasonCodeWarningsOmitted = "item_event_normalization_warnings_omitted"
)
var requiredCapabilities = []string{"merged"}
var providedCapabilities = []string{"normalized"}
var _ contracts.Normalizer[dnd.ItemEventList] = (*Normalizer)(nil)
var _ contracts.ManifestMetadataProvider = (*Normalizer)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Normalizer)(nil)
// Options deliberately has no fields: item-event normalization has no
// generated-reference dependency or configurable semantic behavior.
type Options struct{}
type Normalizer struct{}
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{"normalization_policy": normalizationPolicy}
}
func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
if n == nil {
return nil
}
return []pipeline.CheckpointFingerprint{{Name: "normalization_policy", Value: normalizationPolicy}}
}
func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalizeRequest[dnd.ItemEventList]) (contracts.TypedNormalizeResult[dnd.ItemEventList], error) {
if n == nil {
return contracts.TypedNormalizeResult[dnd.ItemEventList]{}, normalizerErrorf("normalizer must not be nil")
}
if ctx == nil {
return contracts.TypedNormalizeResult[dnd.ItemEventList]{}, normalizerErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedNormalizeResult[dnd.ItemEventList]{}, normalizerErrorf("context error before normalize: %w", err)
}
index := source.NewDocumentIndex(req.Source)
value, warnings := normalizeList(req.MergeOutput.Value, index, shared.NewSourceRefOrderFromIndex(index))
return contracts.TypedNormalizeResult[dnd.ItemEventList]{Value: value, Warnings: warnings}, nil
}
type normalizedRecord struct {
event dnd.ItemEvent
inputIndex int
}
func normalizeList(input dnd.ItemEventList, index source.DocumentIndex, order shared.SourceRefOrder) (dnd.ItemEventList, []contracts.Warning) {
if input.Events == nil {
return dnd.ItemEventList{}, nil
}
records := make([]normalizedRecord, len(input.Events))
warnings := make([]contracts.Warning, 0)
for index, inputEvent := range input.Events {
event, changedFields, refsChanged := normalizeEvent(inputEvent, order)
records[index] = normalizedRecord{event: event, inputIndex: index}
if len(changedFields) != 0 {
warnings = append(warnings, contracts.Warning{
Scope: eventScope(index),
ReasonCode: ReasonCodeDisplayNormalized,
Message: fmt.Sprintf("input index %d: normalized display whitespace in %s", index,
diagnostics.Aggregate("fields", changedFields)),
})
}
if refsChanged {
warnings = append(warnings, contracts.Warning{
Scope: eventScope(index),
ReasonCode: ReasonCodeSourceRefsNormalized,
Message: fmt.Sprintf("input index %d: source references normalized (original count %d, final count %d)",
index, len(inputEvent.SourceRefs), len(event.SourceRefs)),
})
}
}
sort.SliceStable(records, func(left, right int) bool {
return itemeventmodel.Less(order, records[left].event, records[right].event)
})
for position, record := range records {
if position == record.inputIndex {
continue
}
warnings = append(warnings, contracts.Warning{
Scope: eventScope(record.inputIndex),
ReasonCode: ReasonCodeEventsReordered,
Message: fmt.Sprintf("input index %d moved to normalized position %d", record.inputIndex, position),
})
}
output, duplicateWarnings := collapseDuplicates(records, index, order)
warnings = append(warnings, duplicateWarnings...)
return dnd.ItemEventList{Events: output}, diagnostics.LimitWarnings(warnings, "item_events", ReasonCodeWarningsOmitted)
}
func normalizeEvent(input dnd.ItemEvent, order shared.SourceRefOrder) (dnd.ItemEvent, []string, bool) {
output := cloneEvent(input)
changedFields := make([]string, 0, 3)
for _, field := range []struct {
name string
value *string
}{
{name: "name", value: &output.Name},
{name: "from", value: &output.From},
{name: "to", value: &output.To},
} {
trimmed := itemeventmodel.DisplayValue(*field.value)
if *field.value != trimmed {
*field.value = trimmed
changedFields = append(changedFields, field.name)
}
}
output.SourceRefs = order.Canonicalize(input.SourceRefs)
return output, changedFields, !itemeventmodel.SourceRefsEqual(input.SourceRefs, output.SourceRefs)
}
func cloneEvent(input dnd.ItemEvent) dnd.ItemEvent {
output := input
if input.Quantity != nil {
quantity := *input.Quantity
output.Quantity = &quantity
}
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, index source.DocumentIndex, order shared.SourceRefOrder) ([]dnd.ItemEvent, []contracts.Warning) {
if len(records) == 0 {
return make([]dnd.ItemEvent, 0), nil
}
keep := make([]bool, len(records))
groups := make([]duplicateGroup, 0)
groupByKey := make(map[string]int)
for recordIndex, record := range records {
if !itemeventmodel.ValidSourceRefs(index, record.event.SourceRefs) {
keep[recordIndex] = true
continue
}
key := itemeventmodel.ExactIdentity(order, record.event)
groupIndex, exists := groupByKey[key]
if !exists {
groupByKey[key] = len(groups)
groups = append(groups, duplicateGroup{retainedIndex: record.inputIndex})
keep[recordIndex] = true
continue
}
groups[groupIndex].removed = append(groups[groupIndex].removed, record.inputIndex)
}
output := make([]dnd.ItemEvent, 0, len(records))
for recordIndex, record := range records {
if keep[recordIndex] {
output = append(output, cloneEvent(record.event))
}
}
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: eventScope(retainedIndex),
ReasonCode: ReasonCodeDuplicateCollapsed,
Message: diagnostics.Aggregate(
fmt.Sprintf("duplicate item event collapsed; retained input index %d", retainedIndex), issues),
}
}
func eventScope(index int) string { return fmt.Sprintf("events[%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.ItemEventListKind,
}
}
func Register(registry *pipeline.NormalizerRegistry) error {
return pipeline.RegisterNormalizerBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Normalizer[dnd.ItemEventList], 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{}, 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 item events normalizer: "+format, args...)
}