Share D&D cited source traversal

This commit is contained in:
2026-07-21 14:37:12 +00:00
parent 732b13669f
commit 07460341e3
11 changed files with 322 additions and 129 deletions

View File

@@ -3,13 +3,11 @@ 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/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
npcshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcs/shape"
)
@@ -39,9 +37,17 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
if err := npcshape.Validate(req.Value); err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
citedTexts := make([]string, len(req.Value.NPCs))
for npcIndex, npc := range req.Value.NPCs {
citedText, err := shared.CitedText(req.Source, npc.SourceRefs)
if err != nil {
return contracts.ValidationResult{Approved: true}, nil
}
citedTexts[npcIndex] = citedText
}
var warnings []contracts.Warning
for npcIndex, npc := range req.Value.NPCs {
if npcAppearsInCitedText(req.Source, npc) {
if npcAppearsInCitedText(citedTexts[npcIndex], npc) {
continue
}
warnings = append(warnings, contracts.Warning{
@@ -53,43 +59,18 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
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)) {
func npcAppearsInCitedText(citedText string, npc dnd.NPC) bool {
if shared.ContainsTokenSequence(citedText, npc.Name) {
return true
}
for _, alias := range npc.Aliases {
if strings.Contains(cited, identity.ComparisonKey(alias)) {
if shared.ContainsTokenSequence(citedText, 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}
}

View File

@@ -14,7 +14,11 @@ import (
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: "one", Name: "O'Rin Thorn", Aliases: []string{}, Description: "A ranger.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{
{SourceID: "session", StartUnitID: 2, EndUnitID: 2},
{SourceID: "session", StartUnitID: 1, EndUnitID: 2},
{SourceID: "session", StartUnitID: 1, EndUnitID: 2},
}},
{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{
@@ -41,6 +45,17 @@ func TestValidatorWarnsAtMostOncePerNPCForUnrelatedCitations(t *testing.T) {
}
}
func TestValidatorDoesNotMatchShortNameSubstring(t *testing.T) {
value := dnd.NPCList{NPCs: []dnd.NPC{{
ID: "one", Name: "Art", Aliases: []string{}, Description: "A guard.", Relationships: []dnd.NPCRelationship{}, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}},
}}}
doc := &source.SourceDocument{ID: "session", Kind: "transcript", Format: "application/json", Digest: "sha256:session", Units: []source.SourceUnit{{ID: 1, Kind: "message", Text: "A cart rolls past."}}}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.NPCList]{Source: doc, Value: value})
if err != nil || !result.Approved || len(result.Warnings) != 1 {
t.Fatalf("Validate() = %#v, %v; want short-name boundary warning", result, err)
}
}
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})
@@ -49,8 +64,8 @@ func TestValidatorDefersMalformedShapeAndInvalidRangesDoNotPanic(t *testing.T) {
}
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)
if err != nil || !result.Approved || len(result.Warnings) != 0 {
t.Fatalf("invalid-range relatedness = %#v, %v; want approval without warning", result, err)
}
}