Files
notarius/internal/modules/dnd/validate/itemoccurrences/source_refs/validator.go

99 lines
4.3 KiB
Go

// Package sourcerefs validates D&D item-occurrence transcript evidence.
package sourcerefs
import (
"context"
"fmt"
"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"
itemoccurrenceshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemoccurrences/shape"
)
const (
Key = "extract/dnd/item-occurrences/source_refs"
ReasonCode = "invalid_item_occurrence_source_references"
policy = "dnd.item_occurrences.source_refs.v2"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.ItemOccurrenceList] = (*Validator)(nil)
var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)
func New(Options) *Validator { return &Validator{} }
func (v *Validator) Name() string { return Key }
func (v *Validator) ExecutionClass() contracts.ExecutionClass {
return contracts.ExecutionClassDeterministic
}
func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
return []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}
}
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemOccurrenceList]) (contracts.ValidationResult, error) {
if req.Stage == string(pipeline.StageExtract) && req.Chunk == nil {
return contracts.ValidationResult{}, fmt.Errorf("item occurrence source-reference validator requires the current extraction chunk")
}
if itemoccurrenceshape.Validate(req.Value) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
index := source.NewDocumentIndex(req.Source)
var coverage shared.ChunkCoverage
if req.Stage == string(pipeline.StageExtract) {
coverage = shared.NewChunkCoverage(req.Chunk)
}
issues := make([]string, 0)
var corrections diagnostics.Corrections
for occurrenceIndex, occurrence := range req.Value.Occurrences {
for refIndex, ref := range occurrence.SourceRefs {
record := fmt.Sprintf("Affected %s occurrence for item %s, citing %s.", diagnostics.Quote(string(occurrence.Kind)), diagnostics.Quote(occurrence.Name), diagnostics.SourceRefRange(ref))
if err := index.ValidateRef(ref); err != nil {
issues = append(issues, fmt.Sprintf("occurrences[%d].source_refs[%d]: %s", occurrenceIndex, refIndex, diagnostics.Truncate(err.Error())))
corrections.Add("valid-range", "Use positive source range endpoints that occur in the supplied transcript, with the earlier unit first.", record)
continue
}
if req.Stage == string(pipeline.StageExtract) && !coverage.Contains(index, req.Source, ref) {
issues = append(issues, fmt.Sprintf("occurrences[%d].source_refs[%d]: source reference is outside the current extraction chunk", occurrenceIndex, refIndex))
corrections.Add("chunk-range", "Use only source ranges wholly contained in the supplied extraction chunk.", record)
}
}
}
if len(issues) == 0 {
return contracts.ValidationResult{Approved: true}, nil
}
return contracts.ValidationResult{
Approved: false,
ReasonCode: ReasonCode,
Message: diagnostics.Aggregate("invalid item occurrence source references", issues),
CorrectionGuidance: corrections.Guidance("Correct every rejected item-occurrence citation and return the complete replacement occurrence list"),
}, nil
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemOccurrenceListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemOccurrenceList], 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{}, err
}
return Options{}, nil
}
func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }