Add D&D NPC extraction and validation

This commit is contained in:
2026-07-21 02:24:26 +00:00
parent 3ba2c62cc1
commit 3d5fd9dc05
22 changed files with 1700 additions and 0 deletions

View File

@@ -0,0 +1,114 @@
package sourcerelatedness
import (
"context"
"fmt"
"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/npcs/identity"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcs/diagnostics"
npcshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcs/shape"
)
const (
Key = "extract/dnd/npcs/source_relatedness"
WarningReasonCode = "npc_not_near_source"
policy = "dnd.npcs.validator.source_relatedness.v1"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.NPCList] = (*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.NPCList]) (contracts.ValidationResult, error) {
if err := npcshape.Validate(req.Value); err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
var warnings []contracts.Warning
for npcIndex, npc := range req.Value.NPCs {
if npcAppearsInCitedText(req.Source, npc) {
continue
}
warnings = append(warnings, contracts.Warning{
Scope: fmt.Sprintf("npcs[%d]", npcIndex),
ReasonCode: WarningReasonCode,
Message: fmt.Sprintf("NPC %s was not found in cited source text", diagnostics.Quote(npc.Name)),
})
}
return contracts.ValidationResult{Approved: true, Warnings: warnings}, nil
}
func npcAppearsInCitedText(doc *source.SourceDocument, npc dnd.NPC) bool {
cited := citedTextKey(doc, npc.SourceRefs)
if cited == "" {
return false
}
if strings.Contains(cited, identity.ComparisonKey(npc.Name)) {
return true
}
for _, alias := range npc.Aliases {
if strings.Contains(cited, identity.ComparisonKey(alias)) {
return true
}
}
return false
}
func citedTextKey(doc *source.SourceDocument, refs []source.SourceRef) string {
if doc == nil {
return ""
}
var builder strings.Builder
for _, ref := range refs {
if err := source.ValidateRef(doc, ref); err != nil {
continue
}
start, _ := source.UnitIndex(doc, ref.StartUnitID)
end, _ := source.UnitIndex(doc, ref.EndUnitID)
for index := start; index <= end; index++ {
if builder.Len() > 0 {
builder.WriteByte(' ')
}
builder.WriteString(doc.Units[index].Text)
}
}
return identity.ComparisonKey(builder.String())
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.NPCListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.NPCList], 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 }

View File

@@ -0,0 +1,81 @@
package sourcerelatedness
import (
"context"
"strings"
"testing"
"unicode/utf8"
"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"
)
func TestValidatorMatchesCanonicalNamesAndAliasesWithUnicodeVariants(t *testing.T) {
value := dnd.NPCList{NPCs: []dnd.NPC{
{ID: "one", Name: "O'Rin Thorn", Aliases: []string{}, Description: "A ranger.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}},
{ID: "two", Name: "Missing Name", Aliases: []string{"The Greencloak"}, Description: "A guard.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}},
}}
doc := &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{
{ID: 1, Kind: "message", Text: " orin\u2003thorn appears."},
{ID: 2, Kind: "message", Text: "The greencloak watches."},
}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.NPCList]{Source: doc, Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("Validate() = %#v, %v; want alias/canonical relatedness approval", result, err)
}
}
func TestValidatorWarnsAtMostOncePerNPCForUnrelatedCitations(t *testing.T) {
value := dnd.NPCList{NPCs: []dnd.NPC{
{ID: "one", Name: "Missing\nName", Aliases: []string{"Also Missing"}, Description: "A guard.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}, {SourceID: "session", StartUnitID: 1, EndUnitID: 1}}},
}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.NPCList]{Source: relatednessDocument(), Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 1 {
t.Fatalf("Validate() = %#v, %v; want one warning", result, err)
}
warning := result.Warnings[0]
if warning.Scope != "npcs[0]" || warning.ReasonCode != WarningReasonCode || !strings.Contains(warning.Message, `Missing\nName`) || strings.Contains(warning.Message, "Missing\nName") || !utf8.ValidString(warning.Message) {
t.Fatalf("warning = %#v, want safely quoted bounded warning", warning)
}
}
func TestValidatorDefersMalformedShapeAndInvalidRangesDoNotPanic(t *testing.T) {
invalidShape := dnd.NPCList{NPCs: []dnd.NPC{{Name: "Mira Thorn"}}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.NPCList]{Source: relatednessDocument(), Value: invalidShape})
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("shape deferral = %#v, %v; want approval without warning", result, err)
}
invalidRange := dnd.NPCList{NPCs: []dnd.NPC{{ID: "one", Name: "Mira Thorn", Aliases: []string{}, Description: "A ranger.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 99, EndUnitID: 99}}}}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.NPCList]{Source: relatednessDocument(), Value: invalidRange})
if err != nil || !result.Approved || len(result.Warnings) != 1 || result.Warnings[0].ReasonCode != WarningReasonCode {
t.Fatalf("invalid-range relatedness = %#v, %v; want one warning", result, err)
}
}
func TestValidatorUsesOnlyTranscriptEvidenceAndRegistersPolicy(t *testing.T) {
value := dnd.NPCList{NPCs: []dnd.NPC{{ID: "one", Name: "Opaque NPC", Aliases: []string{}, Description: "A guard.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}}}
references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{"glossary": {Items: []contracts.ReferenceItem{{Content: []byte("Opaque NPC")}}}}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.NPCList]{Source: relatednessDocument(), References: references, Value: value})
if err != nil || len(result.Warnings) != 1 {
t.Fatalf("reference-only relatedness = %#v, %v; want warning", result, err)
}
if got := New(Options{}).CheckpointFingerprints(); len(got) != 1 || got[0].Name != "policy" || got[0].Value != "dnd.npcs.validator.source_relatedness.v1" {
t.Fatalf("CheckpointFingerprints() = %#v, want local policy", got)
}
if Spec().ExecutionClass != contracts.ExecutionClassDeterministic {
t.Fatalf("Spec() = %#v, want deterministic validator", Spec())
}
registry := pipeline.NewValidatorRegistry()
if err := Register(registry); err != nil {
t.Fatalf("Register() error = %v", err)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions() accepted unknown option")
}
}
func relatednessDocument() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "The party waits."}}}
}