notarius/internal/framework/pipeline/validator_registry.go

package pipeline

import (
	"fmt"
	"reflect"
	"sort"
	"strings"

	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)

type LegacyRawValidatorConstructor func() (contracts.LegacyRawValidator, error)

type ValidatorSpec struct {
	Key            string                   `json:"key"`
	ExecutionClass contracts.ExecutionClass `json:"execution_class"`
}

type SerializedValidatorSpec struct {
	ValidatorSpec
	SupportsChunks    bool `json:"supports_chunks,omitempty"`
	SupportsArtifacts bool `json:"supports_artifacts,omitempty"`
}

type ValidatorTarget string

const (
	ValidatorTargetLegacyRaw  ValidatorTarget = "legacy_raw"
	ValidatorTargetChunk      ValidatorTarget = "chunk"
	ValidatorTargetSerialized ValidatorTarget = "serialized"
	ValidatorTargetTyped      ValidatorTarget = "typed"
)

type ValidatorRegistry struct {
	legacyConstructors map[string]LegacyRawValidatorConstructor
	legacySpecs        map[string]ValidatorSpec
	typedEntries       map[artifactVariantKey]typedValidatorEntry
	chunkEntries       map[string]chunkValidatorEntry
	serializedEntries  map[string]serializedValidatorEntry
}

type typedValidatorEntry struct {
	spec        ValidatorSpec
	kind        contracts.ArtifactKind
	valueType   reflect.Type
	constructor func() (any, error)
}

type chunkValidatorEntry struct {
	spec        ValidatorSpec
	constructor func() (contracts.ChunkValidator, error)
}

type serializedValidatorEntry struct {
	spec        SerializedValidatorSpec
	constructor func() (contracts.SerializedValidator, error)
}

func NewValidatorRegistry() *ValidatorRegistry {
	return &ValidatorRegistry{
		legacyConstructors: make(map[string]LegacyRawValidatorConstructor),
		legacySpecs:        make(map[string]ValidatorSpec),
		typedEntries:       make(map[artifactVariantKey]typedValidatorEntry),
		chunkEntries:       make(map[string]chunkValidatorEntry),
		serializedEntries:  make(map[string]serializedValidatorEntry),
	}
}

func (r *ValidatorRegistry) RegisterLegacyRaw(key string, constructor LegacyRawValidatorConstructor) error {
	return r.RegisterLegacyRawWithSpec(ValidatorSpec{Key: key, ExecutionClass: contracts.ExecutionClassDeterministic}, constructor)
}

func (r *ValidatorRegistry) RegisterLegacyRawWithSpec(spec ValidatorSpec, constructor LegacyRawValidatorConstructor) error {
	if r == nil {
		return fmt.Errorf("validator registry must not be nil")
	}
	normalizedSpec, err := normalizeValidatorSpec(spec)
	if err != nil {
		return err
	}
	if constructor == nil {
		return fmt.Errorf("validator constructor for %q must not be nil", normalizedSpec.Key)
	}
	if _, ok := r.legacyConstructors[normalizedSpec.Key]; ok {
		return fmt.Errorf("legacy raw validator %q is already registered", normalizedSpec.Key)
	}
	if r.legacyConstructors == nil {
		r.legacyConstructors = make(map[string]LegacyRawValidatorConstructor)
	}
	if r.legacySpecs == nil {
		r.legacySpecs = make(map[string]ValidatorSpec)
	}
	r.legacyConstructors[normalizedSpec.Key] = constructor
	r.legacySpecs[normalizedSpec.Key] = normalizedSpec
	return nil
}

func RegisterTypedValidator[T any](registry *ValidatorRegistry, kind contracts.ArtifactKind, spec ValidatorSpec, constructor func() (contracts.TypedValidator[T], error)) error {
	if registry == nil {
		return fmt.Errorf("validator registry must not be nil")
	}
	normalizedSpec, err := normalizeValidatorSpec(spec)
	if err != nil {
		return err
	}
	kind = normalizeArtifactKind(kind)
	if kind == "" {
		return fmt.Errorf("typed validator %q artifact kind must not be empty", normalizedSpec.Key)
	}
	if constructor == nil {
		return fmt.Errorf("validator constructor for %q must not be nil", normalizedSpec.Key)
	}
	key := artifactVariantKey{module: normalizedSpec.Key, kind: kind}
	if _, ok := registry.typedEntries[key]; ok {
		return fmt.Errorf("validator %q variant for artifact kind %q is already registered", key.module, key.kind)
	}
	if registry.typedEntries == nil {
		registry.typedEntries = make(map[artifactVariantKey]typedValidatorEntry)
	}
	registry.typedEntries[key] = typedValidatorEntry{
		spec:      normalizedSpec,
		kind:      kind,
		valueType: reflect.TypeFor[T](),
		constructor: func() (any, error) {
			return constructor()
		},
	}
	return nil
}

func RegisterChunkValidator(registry *ValidatorRegistry, spec ValidatorSpec, constructor func() (contracts.ChunkValidator, error)) error {
	if registry == nil {
		return fmt.Errorf("validator registry must not be nil")
	}
	normalizedSpec, err := normalizeValidatorSpec(spec)
	if err != nil {
		return err
	}
	if constructor == nil {
		return fmt.Errorf("validator constructor for %q must not be nil", normalizedSpec.Key)
	}
	if _, ok := registry.chunkEntries[normalizedSpec.Key]; ok {
		return fmt.Errorf("chunk validator %q is already registered", normalizedSpec.Key)
	}
	if registry.chunkEntries == nil {
		registry.chunkEntries = make(map[string]chunkValidatorEntry)
	}
	registry.chunkEntries[normalizedSpec.Key] = chunkValidatorEntry{spec: normalizedSpec, constructor: constructor}
	return nil
}

func RegisterSerializedValidator(registry *ValidatorRegistry, spec SerializedValidatorSpec, constructor func() (contracts.SerializedValidator, error)) error {
	if registry == nil {
		return fmt.Errorf("validator registry must not be nil")
	}
	normalizedValidatorSpec, err := normalizeValidatorSpec(spec.ValidatorSpec)
	if err != nil {
		return err
	}
	spec.ValidatorSpec = normalizedValidatorSpec
	if !spec.SupportsChunks && !spec.SupportsArtifacts {
		return fmt.Errorf("serialized validator %q must support chunks, artifacts, or both", spec.Key)
	}
	if constructor == nil {
		return fmt.Errorf("validator constructor for %q must not be nil", spec.Key)
	}
	if _, ok := registry.serializedEntries[spec.Key]; ok {
		return fmt.Errorf("serialized validator %q is already registered", spec.Key)
	}
	if registry.serializedEntries == nil {
		registry.serializedEntries = make(map[string]serializedValidatorEntry)
	}
	registry.serializedEntries[spec.Key] = serializedValidatorEntry{spec: spec, constructor: constructor}
	return nil
}

func (r *ValidatorRegistry) BuildLegacyRaw(key string) (contracts.LegacyRawValidator, error) {
	if r == nil {
		return nil, fmt.Errorf("validator registry must not be nil")
	}
	normalizedKey := strings.TrimSpace(key)
	if normalizedKey == "" {
		return nil, fmt.Errorf("validator key must not be empty")
	}
	constructor, ok := r.legacyConstructors[normalizedKey]
	if !ok {
		return nil, fmt.Errorf("legacy raw validator %q is not registered", normalizedKey)
	}
	validator, err := constructor()
	if err != nil {
		return nil, fmt.Errorf("build validator %q: %w", normalizedKey, err)
	}
	if validator == nil {
		return nil, fmt.Errorf("validator %q constructor returned nil", normalizedKey)
	}
	if validator.Name() != normalizedKey {
		return nil, fmt.Errorf("validator %q returned name %q", normalizedKey, validator.Name())
	}
	spec := r.legacySpecs[normalizedKey]
	if validator.ExecutionClass() != spec.ExecutionClass {
		return nil, fmt.Errorf("validator %q returned execution class %q, want %q", normalizedKey, validator.ExecutionClass(), spec.ExecutionClass)
	}
	return validator, nil
}

func (r *ValidatorRegistry) Spec(key string) (ValidatorSpec, bool) {
	if r == nil {
		return ValidatorSpec{}, false
	}
	spec, ok := r.legacySpecs[strings.TrimSpace(key)]
	return spec, ok
}

func (r *ValidatorRegistry) typedEntry(key string, kind contracts.ArtifactKind) (typedValidatorEntry, bool) {
	if r == nil {
		return typedValidatorEntry{}, false
	}
	entry, ok := r.typedEntries[artifactVariantKey{module: strings.TrimSpace(key), kind: normalizeArtifactKind(kind)}]
	return entry, ok
}

func (r *ValidatorRegistry) chunkEntry(key string) (chunkValidatorEntry, bool) {
	if r == nil {
		return chunkValidatorEntry{}, false
	}
	entry, ok := r.chunkEntries[strings.TrimSpace(key)]
	return entry, ok
}

func (r *ValidatorRegistry) serializedEntry(key string) (serializedValidatorEntry, bool) {
	if r == nil {
		return serializedValidatorEntry{}, false
	}
	entry, ok := r.serializedEntries[strings.TrimSpace(key)]
	return entry, ok
}

func (r *ValidatorRegistry) registeredTypedKinds(key string) []contracts.ArtifactKind {
	if r == nil {
		return nil
	}
	module := strings.TrimSpace(key)
	kinds := make([]contracts.ArtifactKind, 0)
	for variant := range r.typedEntries {
		if variant.module == module {
			kinds = append(kinds, variant.kind)
		}
	}
	sortArtifactKinds(kinds)
	return kinds
}

func (r *ValidatorRegistry) RegisteredSpecs() []ValidatorSpec {
	if r == nil || len(r.legacySpecs) == 0 {
		return nil
	}
	keys := sortedRegistryKeys(r.legacySpecs)
	specs := make([]ValidatorSpec, 0, len(keys))
	for _, key := range keys {
		specs = append(specs, r.legacySpecs[key])
	}
	return specs
}

func (r *ValidatorRegistry) RegisteredKeys() []string {
	if r == nil {
		return nil
	}
	keys := make(map[string]struct{})
	for key := range r.legacySpecs {
		keys[key] = struct{}{}
	}
	for key := range r.typedEntries {
		keys[key.module] = struct{}{}
	}
	for key := range r.chunkEntries {
		keys[key] = struct{}{}
	}
	for key := range r.serializedEntries {
		keys[key] = struct{}{}
	}
	return sortedRegistryKeys(keys)
}

func normalizeValidatorSpec(spec ValidatorSpec) (ValidatorSpec, error) {
	normalized := ValidatorSpec{Key: strings.TrimSpace(spec.Key), ExecutionClass: spec.ExecutionClass}
	if normalized.Key == "" {
		return ValidatorSpec{}, fmt.Errorf("validator key must not be empty")
	}
	switch normalized.ExecutionClass {
	case contracts.ExecutionClassDeterministic, contracts.ExecutionClassLLMBacked:
	default:
		return ValidatorSpec{}, fmt.Errorf("validator %q execution class %q is not supported", normalized.Key, normalized.ExecutionClass)
	}
	return normalized, nil
}

func sortValidatorSpecs(specs []ValidatorSpec) {
	sort.Slice(specs, func(i, j int) bool { return specs[i].Key < specs[j].Key })
}