Files
notarius/internal/framework/pipeline/validator_registry.go

339 lines
12 KiB
Go

package pipeline
import (
"context"
"fmt"
"reflect"
"sort"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)
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 (
ValidatorTargetChunk ValidatorTarget = "chunk"
ValidatorTargetSerialized ValidatorTarget = "serialized"
ValidatorTargetTyped ValidatorTarget = "typed"
)
type ValidatorRegistry struct {
typedEntries map[artifactVariantKey]typedValidatorEntry
chunkEntries map[string]chunkValidatorEntry
serializedEntries map[string]serializedValidatorEntry
}
type typedValidatorEntry struct {
spec ValidatorSpec
kind contracts.ArtifactKind
valueType reflect.Type
validateOptions OptionValidator
builder func(BuildRequest) (any, error)
validate typedValidateOperation
}
type chunkValidatorEntry struct {
spec ValidatorSpec
validateOptions OptionValidator
builder func(BuildRequest) (contracts.ChunkValidator, error)
}
type serializedValidatorEntry struct {
spec SerializedValidatorSpec
validateOptions OptionValidator
builder func(BuildRequest) (contracts.SerializedValidator, error)
}
func NewValidatorRegistry() *ValidatorRegistry {
return &ValidatorRegistry{
typedEntries: make(map[artifactVariantKey]typedValidatorEntry),
chunkEntries: make(map[string]chunkValidatorEntry),
serializedEntries: make(map[string]serializedValidatorEntry),
}
}
func RegisterTypedValidator[T any](registry *ValidatorRegistry, kind contracts.ArtifactKind, spec ValidatorSpec, constructor func() (contracts.TypedValidator[T], error)) error {
if constructor == nil {
return fmt.Errorf("validator constructor for %q must not be nil", strings.TrimSpace(spec.Key))
}
return RegisterTypedValidatorBuilder(registry, kind, spec, rejectUnconfiguredOptions, func(BuildRequest) (contracts.TypedValidator[T], error) {
return constructor()
})
}
func RegisterTypedValidatorBuilder[T any](registry *ValidatorRegistry, kind contracts.ArtifactKind, spec ValidatorSpec, validateOptions OptionValidator, builder func(BuildRequest) (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 validateOptions == nil {
return fmt.Errorf("validator option validator for %q must not be nil", normalizedSpec.Key)
}
if builder == nil {
return fmt.Errorf("validator builder 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](),
validateOptions: validateOptions,
builder: func(request BuildRequest) (any, error) {
return builder(cloneBuildRequest(request))
},
validate: func(ctx context.Context, implementation any, target typedValidationTarget) (contracts.ValidationResult, error) {
validator, ok := implementation.(contracts.TypedValidator[T])
if !ok {
return contracts.ValidationResult{}, fmt.Errorf("validator %q has incompatible implementation %T", normalizedSpec.Key, implementation)
}
value, err := exactTypedValue[T]("validate artifact value", target.value)
if err != nil {
return contracts.ValidationResult{}, err
}
return validator.Validate(ctx, contracts.TypedValidationRequest[T]{Stage: string(target.stage), LaneID: target.laneID, ModuleKey: target.moduleKey, Source: target.source, SourceID: target.sourceID, SourceInput: target.sourceInput, SessionID: target.sessionID, References: target.references, LLMProfile: target.llmProfile, Metadata: target.metadata, Chunk: target.chunk, Chunks: target.chunks, Ref: target.ref, Value: value})
},
}
return nil
}
func RegisterChunkValidator(registry *ValidatorRegistry, spec ValidatorSpec, constructor func() (contracts.ChunkValidator, error)) error {
if constructor == nil {
return fmt.Errorf("validator constructor for %q must not be nil", strings.TrimSpace(spec.Key))
}
return RegisterChunkValidatorBuilder(registry, spec, rejectUnconfiguredOptions, func(BuildRequest) (contracts.ChunkValidator, error) {
return constructor()
})
}
func RegisterChunkValidatorBuilder(registry *ValidatorRegistry, spec ValidatorSpec, validateOptions OptionValidator, builder func(BuildRequest) (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 validateOptions == nil {
return fmt.Errorf("validator option validator for %q must not be nil", normalizedSpec.Key)
}
if builder == nil {
return fmt.Errorf("validator builder 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,
validateOptions: validateOptions,
builder: func(request BuildRequest) (contracts.ChunkValidator, error) {
return builder(cloneBuildRequest(request))
},
}
return nil
}
func RegisterSerializedValidator(registry *ValidatorRegistry, spec SerializedValidatorSpec, constructor func() (contracts.SerializedValidator, error)) error {
if constructor == nil {
return fmt.Errorf("validator constructor for %q must not be nil", strings.TrimSpace(spec.Key))
}
return RegisterSerializedValidatorBuilder(registry, spec, rejectUnconfiguredOptions, func(BuildRequest) (contracts.SerializedValidator, error) {
return constructor()
})
}
func RegisterSerializedValidatorBuilder(registry *ValidatorRegistry, spec SerializedValidatorSpec, validateOptions OptionValidator, builder func(BuildRequest) (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 validateOptions == nil {
return fmt.Errorf("validator option validator for %q must not be nil", spec.Key)
}
if builder == nil {
return fmt.Errorf("validator builder 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,
validateOptions: validateOptions,
builder: func(request BuildRequest) (contracts.SerializedValidator, error) {
return builder(cloneBuildRequest(request))
},
}
return nil
}
func (r *ValidatorRegistry) validateOptions(resolved ResolvedValidator) error {
if r == nil {
return fmt.Errorf("validator registry must not be nil")
}
key := strings.TrimSpace(resolved.Binding.Module)
var validator OptionValidator
switch resolved.Target {
case ValidatorTargetTyped:
entry, ok := r.typedEntry(key, resolved.ArtifactKind)
if ok {
validator = entry.validateOptions
}
case ValidatorTargetChunk:
entry, ok := r.chunkEntry(key)
if ok {
validator = entry.validateOptions
}
case ValidatorTargetSerialized:
entry, ok := r.serializedEntry(key)
if ok {
validator = entry.validateOptions
}
}
if validator == nil {
return fmt.Errorf("validator %q construction entry is not registered", key)
}
return validateRegisteredOptions(validator, resolved.Binding.Options)
}
func (r *ValidatorRegistry) Spec(key string) (ValidatorSpec, bool) {
if r == nil {
return ValidatorSpec{}, false
}
normalized := strings.TrimSpace(key)
if entry, found := r.chunkEntries[normalized]; found {
return entry.spec, true
}
if entry, found := r.serializedEntries[normalized]; found {
return entry.spec.ValidatorSpec, true
}
if kinds := r.registeredTypedKinds(normalized); len(kinds) > 0 {
entry, found := r.typedEntry(normalized, kinds[0])
return entry.spec, found
}
return ValidatorSpec{}, false
}
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 {
return nil
}
keys := r.RegisteredKeys()
specs := make([]ValidatorSpec, 0, len(keys))
for _, key := range keys {
if spec, ok := r.Spec(key); ok {
specs = append(specs, spec)
}
}
return specs
}
func (r *ValidatorRegistry) RegisteredKeys() []string {
if r == nil {
return nil
}
keys := make(map[string]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 })
}