Add production default pipeline modules

This commit is contained in:
2026-07-04 00:55:18 +00:00
parent bc4203a264
commit 0ad96618fc
15 changed files with 1651 additions and 299 deletions

View File

@@ -0,0 +1,124 @@
package pipeline_test
import (
"context"
"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/chunk/generic"
"gitea.maximumdirect.net/eric/notarius/internal/modules/merge/appendorder"
"gitea.maximumdirect.net/eric/notarius/internal/modules/normalize/noop"
jsonoutput "gitea.maximumdirect.net/eric/notarius/internal/modules/output/json"
)
func TestPipelineConfigResolvesWithProductionDefaultsRegistered(t *testing.T) {
cfg := config.Default()
cfg.Pipelines = map[string]pipeline.PipelineProfile{
"defaults": {
Input: pipeline.Binding("input"),
Artifacts: map[string]pipeline.ArtifactLaneProfile{
"events": {Extract: pipeline.Binding("extract")},
},
},
}
resolved, err := cfg.Resolve(config.ResolveInput{
PipelineID: "defaults",
Catalog: defaultModuleCatalog(t),
})
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
pipeline := resolved.ResolvedPipeline
if pipeline.Chunk.Module != generic.Key {
t.Fatalf("Chunk.Module = %q, want %q", pipeline.Chunk.Module, generic.Key)
}
if pipeline.Output.Module != jsonoutput.Key {
t.Fatalf("Output.Module = %q, want %q", pipeline.Output.Module, jsonoutput.Key)
}
lane := pipeline.ArtifactLanes[0]
if lane.Merge.Module != appendorder.Key {
t.Fatalf("Merge.Module = %q, want %q", lane.Merge.Module, appendorder.Key)
}
if lane.Normalize.Module != noop.Key {
t.Fatalf("Normalize.Module = %q, want %q", lane.Normalize.Module, noop.Key)
}
}
func defaultModuleCatalog(t *testing.T) pipeline.ModuleCatalog {
t.Helper()
inputs := pipeline.NewInputAdapterRegistry()
chunkers := pipeline.NewChunkerRegistry()
extractors := pipeline.NewExtractorRegistry()
mergers := pipeline.NewMergerRegistry()
normalizers := pipeline.NewNormalizerRegistry()
outputs := pipeline.NewOutputEncoderRegistry()
if err := inputs.RegisterWithSpec(pipeline.ModuleSpec{
Key: "input",
Stage: pipeline.StageInput,
Provides: []string{"source"},
}, func() (contracts.InputAdapter, error) {
return defaultInput{}, nil
}); err != nil {
t.Fatalf("register input: %v", err)
}
if err := generic.Register(chunkers); err != nil {
t.Fatalf("register generic chunker: %v", err)
}
if err := extractors.RegisterWithSpec(pipeline.ModuleSpec{
Key: "extract",
Stage: pipeline.StageExtract,
Requires: []string{"chunks"},
Provides: []string{"records"},
}, func() (contracts.Extractor, error) {
return defaultExtractor{}, nil
}); err != nil {
t.Fatalf("register extractor: %v", err)
}
if err := appendorder.Register(mergers); err != nil {
t.Fatalf("register appendorder merger: %v", err)
}
if err := noop.Register(normalizers); err != nil {
t.Fatalf("register noop normalizer: %v", err)
}
if err := jsonoutput.Register(outputs); err != nil {
t.Fatalf("register json output: %v", err)
}
return pipeline.ModuleCatalog{
Inputs: inputs,
Chunkers: chunkers,
Extractors: extractors,
Mergers: mergers,
Normalizers: normalizers,
Outputs: outputs,
}
}
type defaultInput struct{}
func (defaultInput) Key() string { return "input" }
func (defaultInput) Parse(ctx context.Context, req contracts.ParseRequest) (*source.SourceDocument, error) {
return nil, nil
}
type defaultExtractor struct{}
func (defaultExtractor) Key() string { return "extract" }
func (defaultExtractor) ArtifactType() string { return "record" }
func (defaultExtractor) SchemaVersion() string { return "v1" }
func (defaultExtractor) Validators() []contracts.Validator { return nil }
func (defaultExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
return contracts.ExtractionResult{}, nil
}

View File

@@ -1,70 +0,0 @@
package pipeline
import (
"context"
"encoding/json"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)
type AppendOrderMerger struct{}
func (m AppendOrderMerger) Key() string {
return DefaultMergeModule
}
func (m AppendOrderMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
var candidates []artifacts.ArtifactCandidate
for _, chunkArtifacts := range req.ChunkArtifacts {
candidates = append(candidates, copyArtifactCandidates(chunkArtifacts.Candidates)...)
}
return contracts.MergeResult{Candidates: candidates}, nil
}
type NoopNormalizer struct{}
func (n NoopNormalizer) Key() string {
return DefaultNormalizeModule
}
func (n NoopNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
return contracts.NormalizeResult{Candidates: copyArtifactCandidates(req.Candidates)}, nil
}
func copyArtifactCandidates(candidates []artifacts.ArtifactCandidate) []artifacts.ArtifactCandidate {
if len(candidates) == 0 {
return nil
}
copied := make([]artifacts.ArtifactCandidate, 0, len(candidates))
for _, candidate := range candidates {
copied = append(copied, copyArtifactCandidate(candidate))
}
return copied
}
func copyArtifactCandidate(candidate artifacts.ArtifactCandidate) artifacts.ArtifactCandidate {
return artifacts.ArtifactCandidate{
Index: candidate.Index,
ExtractorKey: candidate.ExtractorKey,
ArtifactType: candidate.ArtifactType,
SchemaVersion: candidate.SchemaVersion,
Payload: append(json.RawMessage(nil), candidate.Payload...),
SourceRefs: append([]source.SourceRef(nil), candidate.SourceRefs...),
Metadata: copyArtifactMetadata(candidate.Metadata),
}
}
func copyArtifactMetadata(metadata map[string]any) map[string]any {
if len(metadata) == 0 {
return nil
}
copied := make(map[string]any, len(metadata))
for key, value := range metadata {
copied[key] = value
}
return copied
}

View File

@@ -1,221 +0,0 @@
package pipeline
import (
"context"
"encoding/json"
"reflect"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)
func TestGenericMergeAndNormalizeKeys(t *testing.T) {
merger := AppendOrderMerger{}
normalizer := NoopNormalizer{}
if merger.Key() != DefaultMergeModule {
t.Fatalf("AppendOrderMerger.Key() = %q, want %q", merger.Key(), DefaultMergeModule)
}
if normalizer.Key() != DefaultNormalizeModule {
t.Fatalf("NoopNormalizer.Key() = %q, want %q", normalizer.Key(), DefaultNormalizeModule)
}
}
func TestAppendOrderMergerConcatenatesByChunkAndCandidateOrder(t *testing.T) {
merger := AppendOrderMerger{}
chunks := []contracts.ChunkArtifacts{
{
Chunk: sourceChunk(0),
Candidates: []artifacts.ArtifactCandidate{
candidate(2, "first-b"),
candidate(1, "first-a"),
},
},
{
Chunk: sourceChunk(1),
Candidates: []artifacts.ArtifactCandidate{
candidate(4, "second-b"),
candidate(3, "second-a"),
},
},
}
result, err := merger.Merge(context.Background(), contracts.MergeRequest{ChunkArtifacts: chunks})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
}
if len(result.Warnings) != 0 {
t.Fatalf("Warnings = %#v, want none", result.Warnings)
}
got := candidateNames(result.Candidates)
want := []string{"first-b", "first-a", "second-b", "second-a"}
if !reflect.DeepEqual(got, want) {
t.Fatalf("candidate order = %#v, want %#v", got, want)
}
}
func TestAppendOrderMergerReturnsMutationSafeCandidates(t *testing.T) {
merger := AppendOrderMerger{}
input := []contracts.ChunkArtifacts{
{
Chunk: sourceChunk(0),
Candidates: []artifacts.ArtifactCandidate{
candidate(1, "original"),
},
},
}
result, err := merger.Merge(context.Background(), contracts.MergeRequest{ChunkArtifacts: input})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
}
if len(result.Candidates) != 1 {
t.Fatalf("len(Candidates) = %d, want 1", len(result.Candidates))
}
input[0].Candidates[0].Index = 99
input[0].Candidates[0].Payload[0] = '['
input[0].Candidates[0].SourceRefs[0].StartUnitID = "changed"
input[0].Candidates[0].Metadata["name"] = "changed"
got := result.Candidates[0]
if got.Index != 1 {
t.Fatalf("Index = %d, want 1", got.Index)
}
if string(got.Payload) != `{"name":"original"}` {
t.Fatalf("Payload = %s, want original payload", got.Payload)
}
if got.SourceRefs[0].StartUnitID != "u1" {
t.Fatalf("SourceRefs = %#v, want original source ref", got.SourceRefs)
}
if got.Metadata["name"] != "original" {
t.Fatalf("Metadata = %#v, want original metadata", got.Metadata)
}
}
func TestNoopNormalizerPreservesOrderAndValues(t *testing.T) {
normalizer := NoopNormalizer{}
input := []artifacts.ArtifactCandidate{
candidate(3, "third"),
candidate(1, "first"),
candidate(2, "second"),
}
result, err := normalizer.Normalize(context.Background(), contracts.NormalizeRequest{Candidates: input})
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
}
if len(result.Warnings) != 0 {
t.Fatalf("Warnings = %#v, want none", result.Warnings)
}
got := candidateNames(result.Candidates)
want := []string{"third", "first", "second"}
if !reflect.DeepEqual(got, want) {
t.Fatalf("candidate order = %#v, want %#v", got, want)
}
if !reflect.DeepEqual(result.Candidates[0].SourceRefs, input[0].SourceRefs) {
t.Fatalf("SourceRefs = %#v, want %#v", result.Candidates[0].SourceRefs, input[0].SourceRefs)
}
if !reflect.DeepEqual(result.Candidates[0].Metadata, input[0].Metadata) {
t.Fatalf("Metadata = %#v, want %#v", result.Candidates[0].Metadata, input[0].Metadata)
}
}
func TestNoopNormalizerReturnsMutationSafeCandidates(t *testing.T) {
normalizer := NoopNormalizer{}
input := []artifacts.ArtifactCandidate{candidate(1, "original")}
result, err := normalizer.Normalize(context.Background(), contracts.NormalizeRequest{Candidates: input})
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
}
if len(result.Candidates) != 1 {
t.Fatalf("len(Candidates) = %d, want 1", len(result.Candidates))
}
input[0].Index = 99
input[0].Payload[0] = '['
input[0].SourceRefs[0].EndUnitID = "changed"
input[0].Metadata["name"] = "changed"
got := result.Candidates[0]
if got.Index != 1 {
t.Fatalf("Index = %d, want 1", got.Index)
}
if string(got.Payload) != `{"name":"original"}` {
t.Fatalf("Payload = %s, want original payload", got.Payload)
}
if got.SourceRefs[0].EndUnitID != "u1" {
t.Fatalf("SourceRefs = %#v, want original source ref", got.SourceRefs)
}
if got.Metadata["name"] != "original" {
t.Fatalf("Metadata = %#v, want original metadata", got.Metadata)
}
}
func TestGenericMergeAndNormalizeHandleEmptyInput(t *testing.T) {
merger := AppendOrderMerger{}
normalizer := NoopNormalizer{}
mergeResult, err := merger.Merge(context.Background(), contracts.MergeRequest{})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
}
if len(mergeResult.Candidates) != 0 {
t.Fatalf("len(mergeResult.Candidates) = %d, want 0", len(mergeResult.Candidates))
}
if len(mergeResult.Warnings) != 0 {
t.Fatalf("merge warnings = %#v, want none", mergeResult.Warnings)
}
normalizeResult, err := normalizer.Normalize(context.Background(), contracts.NormalizeRequest{})
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
}
if len(normalizeResult.Candidates) != 0 {
t.Fatalf("len(normalizeResult.Candidates) = %d, want 0", len(normalizeResult.Candidates))
}
if len(normalizeResult.Warnings) != 0 {
t.Fatalf("normalize warnings = %#v, want none", normalizeResult.Warnings)
}
}
func candidate(index int, name string) artifacts.ArtifactCandidate {
return artifacts.ArtifactCandidate{
Index: index,
ExtractorKey: "generic-extractor",
ArtifactType: "generic-artifact",
SchemaVersion: "v1",
Payload: json.RawMessage(`{"name":"` + name + `"}`),
SourceRefs: []source.SourceRef{
{SourceID: "source-1", StartUnitID: "u1", EndUnitID: "u1"},
},
Metadata: map[string]any{
"name": name,
},
}
}
func candidateNames(candidates []artifacts.ArtifactCandidate) []string {
names := make([]string, 0, len(candidates))
for _, candidate := range candidates {
names = append(names, candidate.Metadata["name"].(string))
}
return names
}
func sourceChunk(index int) contracts.SourceChunk {
return contracts.SourceChunk{
ID: "chunk",
SourceID: "source-1",
Index: index,
Units: []source.SourceUnit{
{ID: "u1", Kind: "unit", Text: "Source unit."},
},
}
}

View File

@@ -135,7 +135,7 @@ func walkingSkeletonCatalog(t *testing.T) ModuleCatalog {
Stage: StageMerge,
Requires: []string{"fake_artifacts"},
}, func() (contracts.Merger, error) {
return AppendOrderMerger{}, nil
return walkingSkeletonMerger{}, nil
}); err != nil {
t.Fatalf("register append-order merger: %v", err)
}
@@ -143,7 +143,7 @@ func walkingSkeletonCatalog(t *testing.T) ModuleCatalog {
Key: DefaultNormalizeModule,
Stage: StageNormalize,
}, func() (contracts.Normalizer, error) {
return NoopNormalizer{}, nil
return walkingSkeletonNormalizer{}, nil
}); err != nil {
t.Fatalf("register no-op normalizer: %v", err)
}
@@ -309,6 +309,30 @@ func (client *walkingSkeletonLLMClient) CompleteStructured(ctx context.Context,
}, nil
}
type walkingSkeletonMerger struct{}
func (merger walkingSkeletonMerger) Key() string {
return DefaultMergeModule
}
func (merger walkingSkeletonMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
var candidates []artifacts.ArtifactCandidate
for _, chunkArtifacts := range req.ChunkArtifacts {
candidates = append(candidates, chunkArtifacts.Candidates...)
}
return contracts.MergeResult{Candidates: candidates}, nil
}
type walkingSkeletonNormalizer struct{}
func (normalizer walkingSkeletonNormalizer) Key() string {
return DefaultNormalizeModule
}
func (normalizer walkingSkeletonNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
return contracts.NormalizeResult{Candidates: req.Candidates}, nil
}
type walkingSkeletonOutput struct{}
func (output walkingSkeletonOutput) Key() string {