notarius/internal/modules/dnd/normalize/scenedescriptions/normalizer_test.go

package scenedescriptions

import (
	"context"
	"fmt"
	"reflect"
	"strings"
	"testing"

	"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 TestNormalizeTrimsOrdersDeduplicatesAndOwnsOutput(t *testing.T) {
	doc := testDocument()
	input := dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{
		scene("later", 3, 3, dnd.SceneKindNarrative, "  Return ", " The party returns. "),
		scene("first-b", 1, 1, dnd.SceneKindMeta, " Rules ", " The table checks rules. "),
		scene("first-a", 1, 1, dnd.SceneKindMeta, " Rules ", " The table checks rules. "),
		scene("later", 3, 3, dnd.SceneKindNarrative, "  Return ", " The party returns. "),
	}}
	before := cloneList(input)
	result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(input, doc))
	if err != nil {
		t.Fatalf("Normalize() error = %v, want nil", err)
	}
	want := []dnd.SceneDescription{
		scene("first-a", 1, 1, dnd.SceneKindMeta, "Rules", "The table checks rules."),
		scene("first-b", 1, 1, dnd.SceneKindMeta, "Rules", "The table checks rules."),
		scene("later", 3, 3, dnd.SceneKindNarrative, "Return", "The party returns."),
	}
	if !reflect.DeepEqual(result.Value.Scenes, want) {
		t.Fatalf("scenes = %#v, want %#v", result.Value.Scenes, want)
	}
	if len(result.Diagnostics) != 3 || result.Diagnostics[0].ReasonCode != ReasonCodeProseNormalized || result.Diagnostics[0].OccurrenceCount != 4 || result.Diagnostics[1].ReasonCode != ReasonCodeOrderNormalized || result.Diagnostics[1].OccurrenceCount != 2 || result.Diagnostics[2].ReasonCode != ReasonCodeDuplicateCollapsed || result.Diagnostics[2].OccurrenceCount != 1 {
		t.Fatalf("diagnostics = %#v, want grouped prose, order, and duplicate observations", result.Diagnostics)
	}
	if !reflect.DeepEqual(input, before) {
		t.Fatalf("Normalize() mutated input: %#v", input)
	}
	result.Value.Scenes[0].Title = "changed"
	if input.Scenes[0].Title == "changed" {
		t.Fatal("normalized output aliases input storage")
	}
	second, err := New(Options{}).Normalize(context.Background(), normalizeRequest(dnd.SceneDescriptionList{Scenes: want}, doc))
	if err != nil {
		t.Fatalf("second Normalize() error = %v", err)
	}
	if !reflect.DeepEqual(second.Value.Scenes, want) || len(second.Diagnostics) != 0 {
		t.Fatalf("second normalization = %#v, want unchanged value without diagnostics", second)
	}
}

func TestNormalizeLimitsCombinedSceneMutationFindings(t *testing.T) {
	count := contracts.MaxDiagnosticSamples + 1
	doc := &source.SourceDocument{ID: "session", Units: make([]source.SourceUnit, count)}
	input := dnd.SceneDescriptionList{Scenes: make([]dnd.SceneDescription, count)}
	for index := range input.Scenes {
		unitID := count - index
		doc.Units[index] = source.SourceUnit{ID: index + 1}
		input.Scenes[index] = scene(fmt.Sprintf("scene-%02d", unitID), unitID, unitID, dnd.SceneKindNarrative, " Arrival ", " The party arrives. ")
	}
	result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(input, doc))
	if err != nil {
		t.Fatalf("Normalize() error = %v", err)
	}
	if len(result.Value.Scenes) != count || result.Value.Scenes[0].SourceRef.StartUnitID != 1 {
		t.Fatalf("normalized scenes = %#v, want unchanged canonical values", result.Value.Scenes)
	}
	if len(result.Diagnostics) != 2 || result.Diagnostics[0].ReasonCode != ReasonCodeProseNormalized || result.Diagnostics[0].Disposition != contracts.DiagnosticDispositionObservation || result.Diagnostics[0].OccurrenceCount != count || len(result.Diagnostics[0].Samples) != contracts.MaxDiagnosticSamples || result.Diagnostics[1].ReasonCode != ReasonCodeOrderNormalized || result.Diagnostics[1].OccurrenceCount != count {
		t.Fatalf("diagnostics = %#v", result.Diagnostics)
	}
}

func TestNormalizeRejectsInvalidCandidatesAndConflicts(t *testing.T) {
	doc := testDocument()
	valid := scene("one", 1, 1, dnd.SceneKindNarrative, "Arrival", "The party arrives.")
	for _, test := range []struct {
		name  string
		input dnd.SceneDescriptionList
	}{
		{name: "nil list", input: dnd.SceneDescriptionList{}},
		{name: "empty list", input: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{}}},
		{name: "blank ID", input: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{Kind: dnd.SceneKindNarrative, Title: "Arrival", Summary: "The party arrives.", SourceRef: valid.SourceRef}}}},
		{name: "invalid kind", input: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{ID: "one", Kind: "other", Title: "Arrival", Summary: "The party arrives.", SourceRef: valid.SourceRef}}}},
		{name: "invalid range", input: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{{ID: "one", Kind: dnd.SceneKindNarrative, Title: "Arrival", Summary: "The party arrives.", SourceRef: source.SourceRef{SourceID: doc.ID, StartUnitID: 9, EndUnitID: 9}}}}},
		{name: "same ID conflict", input: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{valid, scene("one", 2, 2, dnd.SceneKindNarrative, "Departure", "The party leaves.")}}},
		{name: "same range conflict", input: dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{valid, scene("two", 1, 1, dnd.SceneKindCombat, "Ambush", "Bandits strike.")}}},
	} {
		t.Run(test.name, func(t *testing.T) {
			if _, err := New(Options{}).Normalize(context.Background(), normalizeRequest(test.input, doc)); err == nil {
				t.Fatal("Normalize() error = nil, want rejection")
			}
		})
	}
}

func TestNormalizeUsesDocumentOrderRatherThanNumericUnitID(t *testing.T) {
	doc := &source.SourceDocument{ID: "session", Units: []source.SourceUnit{
		{ID: 20, Text: "The party arrives."},
		{ID: 10, Text: "The party departs."},
	}}
	input := dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{
		scene("later", 10, 10, dnd.SceneKindNarrative, "Departure", "The party departs."),
		scene("first", 20, 20, dnd.SceneKindNarrative, "Arrival", "The party arrives."),
	}}
	result, err := New(Options{}).Normalize(context.Background(), normalizeRequest(input, doc))
	if err != nil {
		t.Fatalf("Normalize() error = %v", err)
	}
	if got, want := []string{result.Value.Scenes[0].ID, result.Value.Scenes[1].ID}, []string{"first", "later"}; !reflect.DeepEqual(got, want) {
		t.Fatalf("scene order = %#v, want %#v", got, want)
	}
}

func TestNormalizerContractAndCancellation(t *testing.T) {
	if _, err := DecodeOptions(nil); err != nil {
		t.Fatalf("DecodeOptions(nil) error = %v", err)
	}
	if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
		t.Fatal("DecodeOptions() accepted unknown options")
	}
	want := pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, ExecutionClass: contracts.ExecutionClassDeterministic, Requires: []string{"merged"}, Provides: []string{"normalized"}, ArtifactKind: dnd.SceneDescriptionListKind}
	if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
		t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
	}
	registry := pipeline.NewNormalizerRegistry()
	if err := Register(registry); err != nil {
		t.Fatalf("Register() error = %v", err)
	}
	normalizer := New(Options{})
	if metadata := normalizer.ManifestMetadata(); metadata["normalizer_policy"] != normalizerPolicy {
		t.Fatalf("metadata = %#v", metadata)
	}
	if got, want := normalizer.CheckpointFingerprints(), []pipeline.CheckpointFingerprint{{Name: "normalizer_policy", Value: normalizerPolicy}}; !reflect.DeepEqual(got, want) {
		t.Fatalf("fingerprints = %#v, want %#v", got, want)
	}
	canceled, cancel := context.WithCancel(context.Background())
	cancel()
	if _, err := normalizer.Normalize(canceled, normalizeRequest(dnd.SceneDescriptionList{}, testDocument())); err == nil || !strings.Contains(err.Error(), "context") {
		t.Fatalf("canceled Normalize() error = %v", err)
	}
	if _, err := normalizer.Normalize(context.Background(), normalizeRequest(dnd.SceneDescriptionList{Scenes: []dnd.SceneDescription{scene("one", 1, 1, dnd.SceneKindNarrative, "Arrival", "The party arrives.")}}, nil)); err == nil || !strings.Contains(err.Error(), "source document") {
		t.Fatalf("nil source Normalize() error = %v", err)
	}
}

func normalizeRequest(value dnd.SceneDescriptionList, doc *source.SourceDocument) contracts.TypedNormalizeRequest[dnd.SceneDescriptionList] {
	return contracts.TypedNormalizeRequest[dnd.SceneDescriptionList]{Source: doc, MergeOutput: contracts.MergeArtifact[dnd.SceneDescriptionList]{Value: value}}
}

func testDocument() *source.SourceDocument {
	return &source.SourceDocument{ID: "session", Units: []source.SourceUnit{{ID: 1, Text: "Rules are discussed."}, {ID: 2, Text: "The party travels."}, {ID: 3, Text: "The party returns."}}}
}

func scene(id string, start, end int, kind dnd.SceneKind, title, summary string) dnd.SceneDescription {
	return dnd.SceneDescription{ID: id, SourceRef: source.SourceRef{SourceID: "session", StartUnitID: start, EndUnitID: end}, Kind: kind, Title: title, Summary: summary}
}

func cloneList(value dnd.SceneDescriptionList) dnd.SceneDescriptionList {
	if value.Scenes != nil {
		value.Scenes = append([]dnd.SceneDescription(nil), value.Scenes...)
	}
	return value
}