Add D&D item event normalization

This commit is contained in:
2026-07-25 22:00:32 +00:00
parent da83510234
commit 5711f8b9e3
6 changed files with 735 additions and 11 deletions

View File

@@ -0,0 +1,131 @@
// Package invariants validates normalized D&D item-event artifacts.
package invariants
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"
itemeventmodel "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/itemevents"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
itemeventshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/itemevents/shape"
)
const (
Key = "normalize/dnd/item-events/invariants"
ReasonCode = "invalid_normalized_item_event_invariants"
policy = "dnd.item_events.normalize_invariants.v1"
)
type Options struct{}
type Validator struct{}
var _ contracts.TypedValidator[dnd.ItemEventList] = (*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.ItemEventList]) (contracts.ValidationResult, error) {
if err := Validate(req.Source, req.Value); err != nil {
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: err.Error()}, nil
}
return contracts.ValidationResult{Approved: true}, nil
}
// Validate checks only invariants introduced by item-event normalization.
// Shape and source-reference failures remain owned by their earlier validators.
func Validate(doc *source.SourceDocument, value dnd.ItemEventList) error {
if itemeventshape.Validate(value) != nil {
return nil
}
index := source.NewDocumentIndex(doc)
if !sourceRefsValid(index, value) {
return nil
}
issues := issuesFor(shared.NewSourceRefOrderFromIndex(index), value)
if len(issues) == 0 {
return nil
}
return fmt.Errorf("%s", diagnostics.Aggregate("invalid normalized item event invariants", issues))
}
func issuesFor(order shared.SourceRefOrder, value dnd.ItemEventList) []string {
issues := make([]string, 0)
seenIdentity := make(map[string]int)
for eventIndex, event := range value.Events {
prefix := fmt.Sprintf("events[%d]", eventIndex)
if event.Name != itemeventmodel.DisplayValue(event.Name) {
issues = append(issues, prefix+".name is not display-normalized")
}
if event.From != itemeventmodel.DisplayValue(event.From) {
issues = append(issues, prefix+".from is not display-normalized")
}
if event.To != itemeventmodel.DisplayValue(event.To) {
issues = append(issues, prefix+".to is not display-normalized")
}
for refIndex := 1; refIndex < len(event.SourceRefs); refIndex++ {
previous := event.SourceRefs[refIndex-1]
current := event.SourceRefs[refIndex]
if order.Less(current, previous) {
issues = append(issues, fmt.Sprintf("%s.source_refs are not in canonical order at index %d", prefix, refIndex))
} else if current == previous {
issues = append(issues, fmt.Sprintf("%s.source_refs[%d] duplicates the previous reference", prefix, refIndex))
}
}
key := itemeventmodel.ExactIdentity(order, event)
if previous, exists := seenIdentity[key]; exists {
issues = append(issues, fmt.Sprintf("%s duplicates item event %d under normalized identity", prefix, previous))
} else {
seenIdentity[key] = eventIndex
}
}
for eventIndex := 1; eventIndex < len(value.Events); eventIndex++ {
if itemeventmodel.Less(order, value.Events[eventIndex], value.Events[eventIndex-1]) {
issues = append(issues, fmt.Sprintf("events[%d] is out of canonical order", eventIndex))
}
}
return issues
}
func sourceRefsValid(index source.DocumentIndex, value dnd.ItemEventList) bool {
for _, event := range value.Events {
if !itemeventmodel.ValidSourceRefs(index, event.SourceRefs) {
return false
}
}
return true
}
func Spec() pipeline.ValidatorSpec {
return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
}
func Register(registry *pipeline.ValidatorRegistry) error {
return pipeline.RegisterTypedValidatorBuilder(registry, dnd.ItemEventListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.ItemEventList], 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 +1,129 @@
package invariants
import (
"context"
"reflect"
"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"
normalizeitemevents "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemevents"
)
func TestValidatorApprovesNormalizerOutput(t *testing.T) {
doc := invariantDocument()
input := dnd.ItemEventList{Events: []dnd.ItemEvent{
{Name: " Coin ", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}},
{Name: "Arrow", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}},
}}
normalized, err := normalizeitemevents.New(normalizeitemevents.Options{}).Normalize(context.Background(), contracts.TypedNormalizeRequest[dnd.ItemEventList]{Source: doc, MergeOutput: contracts.MergeArtifact[dnd.ItemEventList]{Value: input}})
if err != nil {
t.Fatal(err)
}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: doc, Value: normalized.Value})
if err != nil || !result.Approved {
t.Fatalf("Validate() = %#v, %v; want approval", result, err)
}
}
func TestValidateRejectsOwnedNormalizedInvariants(t *testing.T) {
tests := []struct {
name string
mutate func(*dnd.ItemEventList)
want string
}{
{name: "name whitespace", mutate: func(value *dnd.ItemEventList) { value.Events[0].Name = " Coin " }, want: ".name is not display-normalized"},
{name: "from whitespace", mutate: func(value *dnd.ItemEventList) {
value.Events[0].Kind = dnd.ItemEventKindLost
value.Events[0].From = " Aria "
}, want: ".from is not display-normalized"},
{name: "to whitespace", mutate: func(value *dnd.ItemEventList) {
value.Events[0].Kind = dnd.ItemEventKindAcquired
value.Events[0].To = " Aria "
}, want: ".to is not display-normalized"},
{name: "reference order", mutate: func(value *dnd.ItemEventList) {
value.Events[0].SourceRefs = []source.SourceRef{{SourceID: "session", StartUnitID: 20, EndUnitID: 20}, {SourceID: "session", StartUnitID: 10, EndUnitID: 10}}
}, want: "not in canonical order"},
{name: "duplicate reference", mutate: func(value *dnd.ItemEventList) {
value.Events[0].SourceRefs = append(value.Events[0].SourceRefs, value.Events[0].SourceRefs[0])
}, want: "duplicates the previous reference"},
{name: "list order", mutate: func(value *dnd.ItemEventList) { value.Events = []dnd.ItemEvent{value.Events[1], value.Events[0]} }, want: "out of canonical order"},
{name: "duplicate event", mutate: func(value *dnd.ItemEventList) { value.Events = append(value.Events, value.Events[0]) }, want: "duplicates item event"},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
value := normalizedList()
test.mutate(&value)
err := Validate(invariantDocument(), value)
if err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Validate() error = %v, want %q", err, test.want)
}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: invariantDocument(), Value: value})
if err != nil || result.Approved || result.ReasonCode != ReasonCode {
t.Fatalf("validator result = %#v, %v", result, err)
}
})
}
}
func TestValidateUsesSourceDocumentOrderAndDefersEarlierFailures(t *testing.T) {
doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 30}, {ID: 10}}}
value := dnd.ItemEventList{Events: []dnd.ItemEvent{{
Name: "Coin", Kind: dnd.ItemEventKindDiscovered,
SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}, {SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}},
}}}
if err := Validate(doc, value); err == nil || !strings.Contains(err.Error(), "not in canonical order") {
t.Fatalf("Validate() error = %v, want document-order rejection", err)
}
shapeInvalid := normalizedList()
shapeInvalid.Events[0].Name = " "
if err := Validate(invariantDocument(), shapeInvalid); err != nil {
t.Fatalf("shape failure must be deferred, got %v", err)
}
sourceInvalid := normalizedList()
sourceInvalid.Events[0].SourceRefs[0].StartUnitID = 999
if err := Validate(invariantDocument(), sourceInvalid); err != nil {
t.Fatalf("source-reference failure must be deferred, got %v", err)
}
}
func TestValidatorContractAndBoundedDiagnostics(t *testing.T) {
value := normalizedList()
value.Events = make([]dnd.ItemEvent, 30)
for index := range value.Events {
value.Events[index] = normalizedList().Events[0]
value.Events[index].Name = strings.Repeat("火", 300)
}
result, err := New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: invariantDocument(), Value: value})
if err != nil || result.Approved || !utf8.ValidString(result.Message) || len([]byte(result.Message)) > 4096 || !strings.Contains(result.Message, "additional issue(s) omitted") {
t.Fatalf("bounded result = %#v, %v", result, err)
}
if got := New(Options{}).CheckpointFingerprints(); !reflect.DeepEqual(got, []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}) {
t.Fatalf("CheckpointFingerprints() = %#v", got)
}
if spec := Spec(); spec.Key != Key || spec.ExecutionClass != contracts.ExecutionClassDeterministic {
t.Fatalf("Spec() = %#v", 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 normalizedList() dnd.ItemEventList {
return dnd.ItemEventList{Events: []dnd.ItemEvent{
{Name: "Arrow", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 10, EndUnitID: 10}}},
{Name: "Coin", Kind: dnd.ItemEventKindDiscovered, SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 20, EndUnitID: 20}}},
}}
}
func invariantDocument() *source.SourceDocument {
return &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 10}, {ID: 20}}}
}

View File

@@ -46,7 +46,7 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
issues := make([]string, 0)
for eventIndex, event := range req.Value.Events {
if itemevents.ValidSourceRefs(index, event.SourceRefs) {
if req.Stage != string(pipeline.StageExtract) || refsFitChunk(req.Chunk, event.SourceRefs) {
if req.Stage != string(pipeline.StageExtract) || refsFitChunk(req.Source, req.Chunk, event.SourceRefs) {
continue
}
}
@@ -55,7 +55,7 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
issues = append(issues, fmt.Sprintf("events[%d].source_refs[%d]: %s", eventIndex, refIndex, diagnostics.Truncate(err.Error())))
continue
}
if req.Stage == string(pipeline.StageExtract) && !chunkContainsRef(req.Chunk, ref) {
if req.Stage == string(pipeline.StageExtract) && !chunkContainsRef(req.Source, req.Chunk, ref) {
issues = append(issues, fmt.Sprintf("events[%d].source_refs[%d]: source reference is outside the current extraction chunk", eventIndex, refIndex))
}
}
@@ -66,26 +66,34 @@ func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationReq
return contracts.ValidationResult{Approved: false, ReasonCode: ReasonCode, Message: diagnostics.Aggregate("invalid item event source references", issues)}, nil
}
func refsFitChunk(chunk *source.Chunk, refs []source.SourceRef) bool {
func refsFitChunk(doc *source.SourceDocument, chunk *source.Chunk, refs []source.SourceRef) bool {
for _, ref := range refs {
if !chunkContainsRef(chunk, ref) {
if !chunkContainsRef(doc, chunk, ref) {
return false
}
}
return true
}
func chunkContainsRef(chunk *source.Chunk, ref source.SourceRef) bool {
func chunkContainsRef(doc *source.SourceDocument, chunk *source.Chunk, ref source.SourceRef) bool {
if chunk == nil || ref.SourceID != chunk.SourceID {
return false
}
startFound := false
endFound := false
for _, unit := range chunk.Units {
startFound = startFound || unit.ID == ref.StartUnitID
endFound = endFound || unit.ID == ref.EndUnitID
start, startOK := source.UnitIndex(doc, ref.StartUnitID)
end, endOK := source.UnitIndex(doc, ref.EndUnitID)
if !startOK || !endOK || start > end {
return false
}
return startFound && endFound
units := make(map[int]struct{}, len(chunk.Units))
for _, unit := range chunk.Units {
units[unit.ID] = struct{}{}
}
for position := start; position <= end; position++ {
if _, found := units[doc.Units[position].ID]; !found {
return false
}
}
return true
}
func Spec() pipeline.ValidatorSpec {

View File

@@ -51,6 +51,14 @@ func TestValidatorEnforcesChunkOnlyDuringExtraction(t *testing.T) {
t.Fatalf("out-of-chunk evidence = %#v, %v", result, err)
}
noncontiguousChunk := &source.Chunk{ID: "chunk-1", SourceID: doc.ID, Units: []source.SourceUnit{doc.Units[0], doc.Units[2]}}
spansMissingUnit := validList()
spansMissingUnit.Events[0].SourceRefs = []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 3}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Stage: string(pipeline.StageExtract), Source: doc, Chunk: noncontiguousChunk, Value: spansMissingUnit})
if err != nil || result.Approved || !strings.Contains(result.Message, "outside the current extraction chunk") {
t.Fatalf("partially contained evidence = %#v, %v", result, err)
}
multiRange := validList()
multiRange.Events[0].SourceRefs = []source.SourceRef{{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 2}, {SourceID: doc.ID, StartUnitID: 3, EndUnitID: 4}}
result, err = New(Options{}).Validate(context.Background(), contracts.TypedValidationRequest[dnd.ItemEventList]{Source: doc, Value: multiRange})