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

212 lines
8.2 KiB
Go

// Package scenedescriptions normalizes merged D&D scene descriptions.
package scenedescriptions
import (
"context"
"fmt"
"sort"
"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/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/scenedescriptions/shape"
)
const (
Key = "dnd/scene-descriptions"
normalizerPolicy = "dnd.scene_descriptions.normalizer.v1"
ReasonCodeProseNormalized = "scene_description_prose_normalized"
ReasonCodeOrderNormalized = "scene_description_order_normalized"
ReasonCodeDuplicateCollapsed = "scene_description_duplicate_collapsed"
ReasonCodeNormalizationWarningsOmitted = "scene_description_normalization_warnings_omitted"
)
var requiredCapabilities = []string{"merged"}
var providedCapabilities = []string{"normalized"}
var _ contracts.Normalizer[dnd.SceneDescriptionList] = (*Normalizer)(nil)
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 (n *Normalizer) ReferenceSlots() []contracts.ReferenceSlot { return nil }
func (n *Normalizer) ManifestMetadata() map[string]any {
if n == nil {
return nil
}
return map[string]any{"normalizer_policy": normalizerPolicy}
}
func (n *Normalizer) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
if n == nil {
return nil
}
return []pipeline.CheckpointFingerprint{{Name: "normalizer_policy", Value: normalizerPolicy}}
}
func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalizeRequest[dnd.SceneDescriptionList]) (contracts.TypedNormalizeResult[dnd.SceneDescriptionList], error) {
if n == nil {
return contracts.TypedNormalizeResult[dnd.SceneDescriptionList]{}, normalizerErrorf("normalizer must not be nil")
}
if ctx == nil {
return contracts.TypedNormalizeResult[dnd.SceneDescriptionList]{}, normalizerErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedNormalizeResult[dnd.SceneDescriptionList]{}, normalizerErrorf("context error before normalize: %w", err)
}
value, warnings, err := normalizeList(req.MergeOutput.Value, req.Source)
if err != nil {
return contracts.TypedNormalizeResult[dnd.SceneDescriptionList]{}, normalizerErrorf("normalize scenes: %w", err)
}
return contracts.TypedNormalizeResult[dnd.SceneDescriptionList]{
Value: value,
Warnings: diagnostics.LimitWarnings(warnings, "scenes", ReasonCodeNormalizationWarningsOmitted),
}, nil
}
type normalizedScene struct {
scene dnd.SceneDescription
inputIndex int
}
func normalizeList(input dnd.SceneDescriptionList, doc *source.SourceDocument) (dnd.SceneDescriptionList, []contracts.Warning, error) {
if doc == nil {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("source document must not be nil")
}
if input.Scenes == nil {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("scenes must be present")
}
if len(input.Scenes) == 0 {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("scenes must not be empty")
}
documentIndex := source.NewDocumentIndex(doc)
records := make([]normalizedScene, len(input.Scenes))
warnings := make([]contracts.Warning, 0)
for sceneIndex, scene := range input.Scenes {
originalTitle, originalSummary := scene.Title, scene.Summary
scene.Title = strings.TrimSpace(scene.Title)
scene.Summary = strings.TrimSpace(scene.Summary)
if err := shape.Validate(dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{scene}}); err != nil {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("scenes[%d]: %w", sceneIndex, err)
}
if err := documentIndex.ValidateRef(scene.SourceRef); err != nil {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("scenes[%d].source_ref: %s", sceneIndex, diagnostics.Truncate(err.Error()))
}
if originalTitle != scene.Title || originalSummary != scene.Summary {
warnings = append(warnings, contracts.Warning{
Scope: sceneScope(sceneIndex),
ReasonCode: ReasonCodeProseNormalized,
Message: fmt.Sprintf("input index %d: title and/or summary whitespace normalized", sceneIndex),
})
}
records[sceneIndex] = normalizedScene{scene: scene, inputIndex: sceneIndex}
}
sort.SliceStable(records, func(left, right int) bool {
leftStart, _ := documentIndex.Position(records[left].scene.SourceRef.StartUnitID)
rightStart, _ := documentIndex.Position(records[right].scene.SourceRef.StartUnitID)
if leftStart != rightStart {
return leftStart < rightStart
}
return records[left].scene.ID < records[right].scene.ID
})
for position, record := range records {
if position == record.inputIndex {
continue
}
warnings = append(warnings, contracts.Warning{
Scope: sceneScope(record.inputIndex),
ReasonCode: ReasonCodeOrderNormalized,
Message: fmt.Sprintf("input index %d moved to normalized position %d by canonical scene order",
record.inputIndex, position),
})
}
unique := make([]dnd.SceneDescription, 0, len(records))
byID := make(map[string]dnd.SceneDescription, len(records))
byRange := make(map[source.SourceRef]dnd.SceneDescription, len(records))
seen := make(map[dnd.SceneDescription]int, len(records))
for _, record := range records {
scene := record.scene
if previous, ok := byID[scene.ID]; ok && !identical(previous, scene) {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("scene ID %s has conflicting records", diagnostics.Quote(scene.ID))
}
if previous, ok := byRange[scene.SourceRef]; ok && !sameModelContent(previous, scene) {
return dnd.SceneDescriptionList{}, nil, fmt.Errorf("source range %s has conflicting records", sourceRefLabel(scene.SourceRef))
}
if retainedIndex, ok := seen[scene]; ok {
warnings = append(warnings, contracts.Warning{
Scope: sceneScope(record.inputIndex),
ReasonCode: ReasonCodeDuplicateCollapsed,
Message: fmt.Sprintf("input index %d: exact duplicate scene collapsed; retained input index %d",
record.inputIndex, retainedIndex),
})
continue
}
byID[scene.ID] = scene
byRange[scene.SourceRef] = scene
seen[scene] = record.inputIndex
unique = append(unique, scene)
}
return dnd.SceneDescriptionList{Scenes: unique}, warnings, nil
}
func sceneScope(index int) string { return fmt.Sprintf("scenes[%d]", index) }
func identical(left, right dnd.SceneDescription) bool {
return left == right
}
func sameModelContent(left, right dnd.SceneDescription) bool {
return left.Kind == right.Kind && left.Title == right.Title && left.Summary == right.Summary
}
func sourceRefLabel(ref source.SourceRef) string {
return fmt.Sprintf("%s:%d-%d", diagnostics.Quote(ref.SourceID), ref.StartUnitID, ref.EndUnitID)
}
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.SceneDescriptionListKind,
}
}
func Register(registry *pipeline.NormalizerRegistry) error {
return pipeline.RegisterNormalizerBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Normalizer[dnd.SceneDescriptionList], 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 scene descriptions normalizer: "+format, args...)
}