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 +1,97 @@
package appendorder
import (
"context"
"encoding/json"
"fmt"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
const Key = "appendorder"
var _ contracts.Merger = (*Merger)(nil)
type Merger struct{}
func New() *Merger {
return &Merger{}
}
func (m *Merger) Key() string {
return Key
}
func (m *Merger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
if m == nil {
return contracts.MergeResult{}, mergerErrorf("merger must not be nil")
}
if ctx == nil {
return contracts.MergeResult{}, mergerErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.MergeResult{}, mergerErrorf("context error before merge: %w", err)
}
var candidates []artifacts.ArtifactCandidate
for _, chunkArtifacts := range req.ChunkArtifacts {
candidates = append(candidates, cloneCandidates(chunkArtifacts.Candidates)...)
}
return contracts.MergeResult{Candidates: candidates}, nil
}
func ModuleSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{
Key: Key,
Stage: pipeline.StageMerge,
Provides: []string{"merged"},
}
}
func Register(registry *pipeline.MergerRegistry) error {
return registry.RegisterWithSpec(ModuleSpec(), func() (contracts.Merger, error) {
return New(), nil
})
}
func cloneCandidates(candidates []artifacts.ArtifactCandidate) []artifacts.ArtifactCandidate {
if len(candidates) == 0 {
return nil
}
out := make([]artifacts.ArtifactCandidate, 0, len(candidates))
for _, candidate := range candidates {
out = append(out, cloneCandidate(candidate))
}
return out
}
func cloneCandidate(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: cloneMetadata(candidate.Metadata),
}
}
func cloneMetadata(metadata map[string]any) map[string]any {
if len(metadata) == 0 {
return nil
}
out := make(map[string]any, len(metadata))
for key, value := range metadata {
out[key] = value
}
return out
}
func mergerErrorf(format string, args ...any) error {
return fmt.Errorf("appendorder merger: "+format, args...)
}

View File

@@ -0,0 +1,147 @@
package appendorder
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"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func TestModuleSpecAndRegister(t *testing.T) {
want := pipeline.ModuleSpec{
Key: Key,
Stage: pipeline.StageMerge,
Provides: []string{"merged"},
}
if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
}
registry := pipeline.NewMergerRegistry()
if err := Register(registry); err != nil {
t.Fatalf("Register() error = %v, want nil", err)
}
spec, ok := registry.Spec(Key)
if !ok {
t.Fatalf("Spec(%q) ok = false, want true", Key)
}
if !reflect.DeepEqual(spec, want) {
t.Fatalf("registered spec = %#v, want %#v", spec, want)
}
}
func TestMergePreservesChunkAndCandidateOrder(t *testing.T) {
result, err := New().Merge(context.Background(), contracts.MergeRequest{
ChunkArtifacts: []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")},
},
},
})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
}
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)
}
if len(result.Warnings) != 0 {
t.Fatalf("Warnings = %#v, want none", result.Warnings)
}
}
func TestMergeDefensivelyCopiesCandidates(t *testing.T) {
input := []contracts.ChunkArtifacts{
{
Chunk: sourceChunk(0),
Candidates: []artifacts.ArtifactCandidate{candidate(1, "original")},
},
}
result, err := New().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 TestMergeHandlesEmptyInput(t *testing.T) {
result, err := New().Merge(context.Background(), contracts.MergeRequest{})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
}
if len(result.Candidates) != 0 {
t.Fatalf("len(Candidates) = %d, want 0", len(result.Candidates))
}
if len(result.Warnings) != 0 {
t.Fatalf("Warnings = %#v, want none", result.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."},
},
}
}