Files
notarius/internal/modules/extract/dnd/spells/config_test.go

289 lines
8.9 KiB
Go

package spells
import (
"context"
"os"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"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/input/seriatim"
"gitea.maximumdirect.net/eric/notarius/internal/modules/merge/appendorder"
"gitea.maximumdirect.net/eric/notarius/internal/modules/normalize/noop"
)
func TestPipelineConfigLoadsAndResolvesWithDNDSpellsExtractor(t *testing.T) {
data, err := os.ReadFile("testdata/pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(pipeline.yml) error = %v, want nil", err)
}
fileCfg, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v, want nil", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileCfg); err != nil {
t.Fatalf("ApplyFileConfig() error = %v, want nil", err)
}
resolved, err := cfg.Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
if len(resolved.ResolvedPipeline.ArtifactLanes) != 1 {
t.Fatalf("len(ArtifactLanes) = %d, want 1", len(resolved.ResolvedPipeline.ArtifactLanes))
}
lane := resolved.ResolvedPipeline.ArtifactLanes[0]
if lane.ID != "spells" {
t.Fatalf("lane ID = %q, want spells", lane.ID)
}
if lane.Extract.Module != Key {
t.Fatalf("extract module = %q, want %q", lane.Extract.Module, Key)
}
if resolved.ResolvedPipeline.Digest == "" {
t.Fatal("resolved digest is empty")
}
again, err := cfg.Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err != nil {
t.Fatalf("second Resolve() error = %v, want nil", err)
}
if resolved.ResolvedPipeline.Digest != again.ResolvedPipeline.Digest {
t.Fatalf("resolved digest = %q, second digest = %q; want stable digest", resolved.ResolvedPipeline.Digest, again.ResolvedPipeline.Digest)
}
}
func TestPipelineConfigRejectsMissingTranscriptCapabilityForDNDSpells(t *testing.T) {
inputSpec := seriatim.ModuleSpec()
inputSpec.Provides = withoutCapability(inputSpec.Provides, "source.transcript")
chunkSpec := dndSpellsChunkerSpec()
chunkSpec.Requires = nil
_, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{
input: inputSpec,
chunk: chunkSpec,
}),
})
if err == nil {
t.Fatal("Resolve() error = nil, want missing capability error")
}
if !strings.Contains(err.Error(), "missing capability") ||
!strings.Contains(err.Error(), "source.transcript") ||
!strings.Contains(err.Error(), Key) {
t.Fatalf("Resolve() error = %q, want dnd/spells missing source.transcript capability", err.Error())
}
}
func TestPipelineConfigRejectsMissingSpellCastsCapabilityForAppendOrder(t *testing.T) {
extractorSpec := ModuleSpec()
extractorSpec.Provides = withoutCapability(extractorSpec.Provides, "dnd.spell_casts")
_, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{
extractor: extractorSpec,
}),
})
if err == nil {
t.Fatal("Resolve() error = nil, want missing capability error")
}
if !strings.Contains(err.Error(), "missing capability") ||
!strings.Contains(err.Error(), "dnd.spell_casts") ||
!strings.Contains(err.Error(), pipeline.DefaultMergeModule) {
t.Fatalf("Resolve() error = %q, want appendorder missing dnd.spell_casts capability", err.Error())
}
}
func TestPipelineConfigRejectsUnknownLaneSelection(t *testing.T) {
_, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Only: []string{"missing"},
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err == nil {
t.Fatal("Resolve() error = nil, want unknown lane error")
}
if !strings.Contains(err.Error(), "selected artifact lane") || !strings.Contains(err.Error(), "missing") {
t.Fatalf("Resolve() error = %q, want unknown lane context", err.Error())
}
}
func loadDNDSpellsPipelineConfig(t *testing.T) config.Config {
t.Helper()
data, err := os.ReadFile("testdata/pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(pipeline.yml) error = %v, want nil", err)
}
fileCfg, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v, want nil", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileCfg); err != nil {
t.Fatalf("ApplyFileConfig() error = %v, want nil", err)
}
return cfg
}
type dndSpellsCatalogSpecs struct {
input pipeline.ModuleSpec
chunk pipeline.ModuleSpec
extractor pipeline.ModuleSpec
}
func dndSpellsTestCatalog(t *testing.T, specs dndSpellsCatalogSpecs) pipeline.ModuleCatalog {
t.Helper()
inputs := pipeline.NewInputAdapterRegistry()
chunkers := pipeline.NewChunkerRegistry()
extractors := pipeline.NewExtractorRegistry()
mergers := pipeline.NewMergerRegistry()
normalizers := pipeline.NewNormalizerRegistry()
outputs := pipeline.NewOutputEncoderRegistry()
if specs.input.Key == "" {
if err := seriatim.Register(inputs); err != nil {
t.Fatalf("register seriatim input: %v", err)
}
} else if err := inputs.RegisterWithSpec(specs.input, func() (contracts.InputAdapter, error) {
return seriatim.New(), nil
}); err != nil {
t.Fatalf("register seriatim input override: %v", err)
}
chunkSpec := specs.chunk
if chunkSpec.Key == "" {
chunkSpec = dndSpellsChunkerSpec()
}
if err := chunkers.RegisterWithSpec(chunkSpec, func() (contracts.Chunker, error) {
return dndSpellsChunker{}, nil
}); err != nil {
t.Fatalf("register chunker: %v", err)
}
if specs.extractor.Key == "" {
if err := Register(extractors); err != nil {
t.Fatalf("register dnd spells extractor: %v", err)
}
} else if err := extractors.RegisterWithSpec(specs.extractor, func() (contracts.Extractor, error) {
return New(), nil
}); err != nil {
t.Fatalf("register dnd spells extractor override: %v", err)
}
if err := mergers.RegisterWithSpec(pipeline.ModuleSpec{
Key: pipeline.DefaultMergeModule,
Stage: pipeline.StageMerge,
Requires: []string{"dnd.spell_casts"},
}, func() (contracts.Merger, error) {
return appendorder.New(), nil
}); err != nil {
t.Fatalf("register merger: %v", err)
}
if err := normalizers.RegisterWithSpec(pipeline.ModuleSpec{
Key: pipeline.DefaultNormalizeModule,
Stage: pipeline.StageNormalize,
}, func() (contracts.Normalizer, error) {
return noop.New(), nil
}); err != nil {
t.Fatalf("register normalizer: %v", err)
}
if err := outputs.RegisterWithSpec(pipeline.ModuleSpec{
Key: pipeline.DefaultOutputModule,
Stage: pipeline.StageOutput,
}, func() (contracts.OutputEncoder, error) {
return dndSpellsOutput{}, nil
}); err != nil {
t.Fatalf("register output: %v", err)
}
return pipeline.ModuleCatalog{
Inputs: inputs,
Chunkers: chunkers,
Extractors: extractors,
Mergers: mergers,
Normalizers: normalizers,
ValidatorChains: pipeline.NewValidatorChainRegistry(),
Outputs: outputs,
}
}
func dndSpellsChunkerSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{
Key: "fake/chunk",
Stage: pipeline.StageChunk,
Requires: []string{"source.transcript"},
Provides: []string{"chunks"},
}
}
type dndSpellsChunker struct{}
func (dndSpellsChunker) Key() string {
return "fake/chunk"
}
func (dndSpellsChunker) ReferenceSlots() []contracts.ReferenceSlot {
return nil
}
func (dndSpellsChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
return contracts.ChunkResult{
Chunks: []contracts.SourceChunk{
{
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
StartUnitID: req.Source.Units[0].ID,
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
Content: []byte(`{"units":[1,2,3]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
},
},
}, nil
}
type dndSpellsOutput struct{}
func (dndSpellsOutput) Key() string {
return pipeline.DefaultOutputModule
}
func (dndSpellsOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
return contracts.OutputResult{
Files: []contracts.OutputFile{
{Name: "output.json", ContentType: "application/json", Bytes: []byte(`{"encoded":true}`)},
},
}, nil
}
func withoutCapability(capabilities []string, capability string) []string {
filtered := make([]string, 0, len(capabilities))
for _, candidate := range capabilities {
if candidate != capability {
filtered = append(filtered, candidate)
}
}
return filtered
}
var (
_ contracts.Chunker = dndSpellsChunker{}
_ contracts.OutputEncoder = dndSpellsOutput{}
)