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

85 lines
3.2 KiB
Go

// Package sourcerelatedness reports advisory findings when item-occurrence evidence does not mention its item.
package sourcerelatedness
import (
"context"
"fmt"
"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_relatedness"
ReasonCode = "item_occurrence_not_near_source"
policy = "dnd.item_occurrences.source_relatedness.v1"
)
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}}
}
// Validate performs advisory source grounding only. Shape and range failures
// are intentionally left to their blocking owners.
func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.ItemOccurrenceList]) (contracts.ValidationResult, error) {
if itemoccurrenceshape.Validate(req.Value) != nil {
return contracts.ValidationResult{Approved: true}, nil
}
resolver, err := shared.NewCitationResolver(req.Source)
if err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
findings := make([]diagnostics.Finding, 0)
for index, occurrence := range req.Value.Occurrences {
citedText, err := resolver.CitedText(occurrence.SourceRefs)
if err != nil || shared.ContainsTokenSequence(citedText, occurrence.Name) {
continue
}
findings = append(findings, diagnostics.Finding{
Scope: fmt.Sprintf("occurrences[%d]", index),
ReasonCode: ReasonCode,
Message: fmt.Sprintf("item occurrence name %s was not found in cited source text", diagnostics.Quote(occurrence.Name)),
})
}
return diagnostics.DataQualityResult(findings)
}
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 }