Implement raw module output contracts

This commit is contained in:
2026-07-07 18:58:23 +00:00
parent 9e3f8809b3
commit c05ecb58d8
33 changed files with 1166 additions and 1780 deletions

View File

@@ -5,8 +5,6 @@ import (
"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"
)
@@ -36,11 +34,34 @@ func (m *Merger) Merge(ctx context.Context, req contracts.MergeRequest) (contrac
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)...)
if len(req.ExtractOutputs) == 1 {
payload := cloneRawPayload(req.ExtractOutputs[0].Payload)
return contracts.MergeResult{
Output: contracts.MergeOutput{
LaneID: req.LaneID,
MergerKey: Key,
SourceID: req.ExtractOutputs[0].SourceID,
Schema: req.ExtractOutputs[0].Schema,
Payload: payload,
},
}, nil
}
return contracts.MergeResult{Candidates: candidates}, nil
content, err := orderedContent(req.ExtractOutputs)
if err != nil {
return contracts.MergeResult{}, err
}
return contracts.MergeResult{
Output: contracts.MergeOutput{
LaneID: req.LaneID,
MergerKey: Key,
SourceID: sourceID(req.ExtractOutputs),
Payload: contracts.RawPayload{
Content: content,
MediaType: "application/json",
},
},
}, nil
}
func ModuleSpec() pipeline.ModuleSpec {
@@ -57,27 +78,45 @@ func Register(registry *pipeline.MergerRegistry) error {
})
}
func cloneCandidates(candidates []artifacts.ArtifactCandidate) []artifacts.ArtifactCandidate {
if len(candidates) == 0 {
return nil
func orderedContent(outputs []contracts.ExtractOutput) ([]byte, error) {
items := make([]map[string]any, 0, len(outputs))
for _, output := range outputs {
item := map[string]any{
"chunk_id": output.ChunkID,
"chunk_index": output.ChunkIndex,
"media_type": output.Payload.MediaType,
}
if json.Valid(output.Payload.Content) {
item["content"] = json.RawMessage(append([]byte(nil), output.Payload.Content...))
} else {
item["content"] = string(output.Payload.Content)
}
items = append(items, item)
}
out := make([]artifacts.ArtifactCandidate, 0, len(candidates))
for _, candidate := range candidates {
out = append(out, cloneCandidate(candidate))
content, err := json.Marshal(struct {
Outputs []map[string]any `json:"outputs"`
}{Outputs: items})
if err != nil {
return nil, mergerErrorf("encode merged output: %w", err)
}
return out
return content, nil
}
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 sourceID(outputs []contracts.ExtractOutput) string {
for _, output := range outputs {
if output.SourceID != "" {
return output.SourceID
}
}
return ""
}
func cloneRawPayload(payload contracts.RawPayload) contracts.RawPayload {
return contracts.RawPayload{
Content: append([]byte(nil), payload.Content...),
MediaType: payload.MediaType,
Metadata: cloneMetadata(payload.Metadata),
Warnings: append([]contracts.Warning(nil), payload.Warnings...),
}
}

View File

@@ -6,8 +6,6 @@ import (
"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"
)
@@ -35,113 +33,102 @@ func TestModuleSpecAndRegister(t *testing.T) {
}
}
func TestMergePreservesChunkAndCandidateOrder(t *testing.T) {
func TestMergePassesThroughSingleExtractOutput(t *testing.T) {
input := extractOutput("chunk-0", 0, `{"name":"original"}`)
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")},
},
},
LaneID: "events",
ExtractOutputs: []contracts.ExtractOutput{input},
})
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 result.Output.LaneID != "events" || result.Output.MergerKey != Key {
t.Fatalf("output provenance = %#v, want lane and merger", result.Output)
}
if len(result.Warnings) != 0 {
t.Fatalf("Warnings = %#v, want none", result.Warnings)
if string(result.Output.Payload.Content) != `{"name":"original"}` {
t.Fatalf("content = %s, want original content", result.Output.Payload.Content)
}
if result.Output.Payload.Metadata["name"] != "chunk-0" {
t.Fatalf("metadata = %#v, want original metadata", result.Output.Payload.Metadata)
}
}
func TestMergeDefensivelyCopiesCandidates(t *testing.T) {
input := []contracts.ChunkArtifacts{
{
Chunk: sourceChunk(0),
Candidates: []artifacts.ArtifactCandidate{candidate(1, "original")},
},
}
func TestMergeDefensivelyCopiesRawPayload(t *testing.T) {
input := extractOutput("chunk-0", 0, `{"name":"original"}`)
result, err := New().Merge(context.Background(), contracts.MergeRequest{ChunkArtifacts: input})
result, err := New().Merge(context.Background(), contracts.MergeRequest{
LaneID: "events",
ExtractOutputs: []contracts.ExtractOutput{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.Payload.Content[0] = '['
input.Payload.Metadata["name"] = "changed"
if string(result.Output.Payload.Content) != `{"name":"original"}` {
t.Fatalf("content changed after input mutation: %s", result.Output.Payload.Content)
}
if result.Output.Payload.Metadata["name"] != "chunk-0" {
t.Fatalf("metadata changed after input mutation: %#v", result.Output.Payload.Metadata)
}
}
func TestMergeWrapsMultipleOutputsInChunkOrder(t *testing.T) {
result, err := New().Merge(context.Background(), contracts.MergeRequest{
LaneID: "events",
ExtractOutputs: []contracts.ExtractOutput{
extractOutput("chunk-0", 0, `{"name":"first"}`),
extractOutput("chunk-1", 1, `{"name":"second"}`),
},
})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
}
if result.Output.Payload.MediaType != "application/json" {
t.Fatalf("MediaType = %q, want application/json", result.Output.Payload.MediaType)
}
input[0].Candidates[0].Index = 99
input[0].Candidates[0].Payload[0] = '['
input[0].Candidates[0].SourceRefs[0].StartUnitID = 99
input[0].Candidates[0].Metadata["name"] = "changed"
got := result.Candidates[0]
if got.Index != 1 {
t.Fatalf("Index = %d, want 1", got.Index)
var decoded struct {
Outputs []struct {
ChunkID string `json:"chunk_id"`
ChunkIndex int `json:"chunk_index"`
Content json.RawMessage `json:"content"`
} `json:"outputs"`
}
if string(got.Payload) != `{"name":"original"}` {
t.Fatalf("Payload = %s, want original payload", got.Payload)
if err := json.Unmarshal(result.Output.Payload.Content, &decoded); err != nil {
t.Fatalf("Unmarshal() error = %v, want nil", err)
}
if got.SourceRefs[0].StartUnitID != 1 {
t.Fatalf("SourceRefs = %#v, want original source ref", got.SourceRefs)
}
if got.Metadata["name"] != "original" {
t.Fatalf("Metadata = %#v, want original metadata", got.Metadata)
if len(decoded.Outputs) != 2 || decoded.Outputs[0].ChunkID != "chunk-0" || decoded.Outputs[1].ChunkID != "chunk-1" {
t.Fatalf("outputs = %#v, want chunk order", decoded.Outputs)
}
}
func TestMergeHandlesEmptyInput(t *testing.T) {
result, err := New().Merge(context.Background(), contracts.MergeRequest{})
result, err := New().Merge(context.Background(), contracts.MergeRequest{LaneID: "events"})
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)
if string(result.Output.Payload.Content) != `{"outputs":[]}` {
t.Fatalf("content = %s, want empty outputs", result.Output.Payload.Content)
}
}
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: 1, EndUnitID: 1},
},
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: 1, Kind: "unit", Text: "Source unit."},
func extractOutput(chunkID string, chunkIndex int, content string) contracts.ExtractOutput {
return contracts.ExtractOutput{
LaneID: "events",
ExtractorKey: "extract",
SourceID: "source-1",
ChunkID: chunkID,
ChunkIndex: chunkIndex,
Schema: contracts.ResponseSchema{ID: "schema-id", Name: "schema-name", Version: "v1"},
Payload: contracts.RawPayload{
Content: []byte(content),
MediaType: "application/json",
Metadata: map[string]any{"name": chunkID},
},
}
}