266 lines
7.8 KiB
Go
266 lines
7.8 KiB
Go
package pipeline
|
|
|
|
import (
|
|
"context"
|
|
"reflect"
|
|
"testing"
|
|
|
|
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
|
|
)
|
|
|
|
func TestRunnerUsesRegistries(t *testing.T) {
|
|
var built []string
|
|
var executed []string
|
|
registries := integrationRegistries(t, &built, &executed)
|
|
|
|
output, err := New(registries).Run(context.Background(), RunInput{
|
|
Pipeline: integrationPipeline(),
|
|
SourceID: "source-1",
|
|
RawInput: []byte("source text"),
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("Run() error = %v, want nil", err)
|
|
}
|
|
|
|
wantBuilt := []string{"input", "chunk", "extract-first", "merge", "normalize", "extract-second", "merge", "normalize", "output"}
|
|
if !reflect.DeepEqual(built, wantBuilt) {
|
|
t.Fatalf("built = %#v, want %#v", built, wantBuilt)
|
|
}
|
|
if !reflect.DeepEqual(executed, []string{"extract-first:chunk-0", "extract-second:chunk-0"}) {
|
|
t.Fatalf("executed = %#v, want extractor chunk execution", executed)
|
|
}
|
|
if got := normalizeOutputKeys(output.NormalizeOutputs); !reflect.DeepEqual(got, []string{"normalize", "normalize"}) {
|
|
t.Fatalf("normalize output keys = %#v, want one output from each lane", got)
|
|
}
|
|
if len(output.Rejected) != 0 {
|
|
t.Fatalf("len(Rejected) = %d, want none", len(output.Rejected))
|
|
}
|
|
}
|
|
|
|
func integrationRegistries(t *testing.T, built, executed *[]string) Registries {
|
|
t.Helper()
|
|
|
|
registries := Registries{
|
|
Inputs: NewInputAdapterRegistry(),
|
|
Chunkers: NewChunkerRegistry(),
|
|
ArtifactCodecs: NewArtifactCodecRegistry(),
|
|
Extractors: NewExtractorRegistry(),
|
|
Mergers: NewMergerRegistry(),
|
|
Normalizers: NewNormalizerRegistry(),
|
|
Outputs: NewOutputEncoderRegistry(),
|
|
}
|
|
if err := registries.Inputs.Register("input", func() (contracts.InputAdapter, error) {
|
|
*built = append(*built, "input")
|
|
return integrationInput{}, nil
|
|
}); err != nil {
|
|
t.Fatalf("register input: %v", err)
|
|
}
|
|
if err := registries.Chunkers.Register("chunk", func() (contracts.Chunker, error) {
|
|
*built = append(*built, "chunk")
|
|
return integrationChunker{}, nil
|
|
}); err != nil {
|
|
t.Fatalf("register chunker: %v", err)
|
|
}
|
|
registerIntegrationExtractor(t, registries.Extractors, "extract-first", built, executed)
|
|
registerIntegrationExtractor(t, registries.Extractors, "extract-second", built, executed)
|
|
if err := registries.Mergers.Register("merge", func() (contracts.Merger, error) {
|
|
*built = append(*built, "merge")
|
|
return integrationMerger{}, nil
|
|
}); err != nil {
|
|
t.Fatalf("register merger: %v", err)
|
|
}
|
|
if err := registries.Normalizers.Register("normalize", func() (contracts.Normalizer, error) {
|
|
*built = append(*built, "normalize")
|
|
return integrationNormalizer{}, nil
|
|
}); err != nil {
|
|
t.Fatalf("register normalizer: %v", err)
|
|
}
|
|
if err := registries.Outputs.Register("output", func() (contracts.OutputEncoder, error) {
|
|
*built = append(*built, "output")
|
|
return integrationOutput{}, nil
|
|
}); err != nil {
|
|
t.Fatalf("register output: %v", err)
|
|
}
|
|
return registries
|
|
}
|
|
|
|
func registerIntegrationExtractor(t *testing.T, registry *ExtractorRegistry, key string, built, executed *[]string) {
|
|
t.Helper()
|
|
|
|
if err := registry.Register(key, func() (contracts.Extractor, error) {
|
|
*built = append(*built, key)
|
|
return integrationExtractor{key: key, executed: executed}, nil
|
|
}); err != nil {
|
|
t.Fatalf("Register(%q) error = %v, want nil", key, err)
|
|
}
|
|
}
|
|
|
|
type integrationInput struct{}
|
|
|
|
func (input integrationInput) Key() string {
|
|
return "input"
|
|
}
|
|
|
|
func (input integrationInput) Parse(ctx context.Context, req contracts.ParseRequest) (*source.SourceDocument, error) {
|
|
return integrationSourceDocument(), nil
|
|
}
|
|
|
|
type integrationChunker struct{}
|
|
|
|
func (chunker integrationChunker) Key() string {
|
|
return "chunk"
|
|
}
|
|
|
|
func (chunker integrationChunker) ReferenceSlots() []contracts.ReferenceSlot {
|
|
return nil
|
|
}
|
|
|
|
func (chunker integrationChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
|
|
return contracts.ChunkResult{
|
|
Chunks: []source.Chunk{
|
|
{
|
|
ID: "chunk-0",
|
|
SourceID: req.Source.ID,
|
|
Index: 0,
|
|
Ref: source.SourceRef{
|
|
SourceID: req.Source.ID,
|
|
StartUnitID: req.Source.Units[0].ID,
|
|
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
|
|
},
|
|
Content: []byte(`{"units":[1]}`),
|
|
MediaType: "application/json",
|
|
Units: req.Source.Units,
|
|
},
|
|
},
|
|
}, nil
|
|
}
|
|
|
|
type integrationExtractor struct {
|
|
key string
|
|
executed *[]string
|
|
}
|
|
|
|
func (extractor integrationExtractor) Key() string {
|
|
return extractor.key
|
|
}
|
|
|
|
func (extractor integrationExtractor) ReferenceSlots() []contracts.ReferenceSlot {
|
|
return nil
|
|
}
|
|
|
|
func (extractor integrationExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
|
|
*extractor.executed = append(*extractor.executed, extractor.key+":"+req.Chunk.ID)
|
|
return contracts.ExtractionResult{
|
|
Output: contracts.ExtractOutput{
|
|
Schema: contracts.ResponseSchema{ID: "integration", Name: "integration", Version: "v1"},
|
|
Payload: contracts.RawPayload{
|
|
Content: []byte(`{"value":true}`),
|
|
MediaType: "application/json",
|
|
},
|
|
},
|
|
}, nil
|
|
}
|
|
|
|
type integrationNormalizer struct{}
|
|
|
|
type integrationMerger struct{}
|
|
|
|
func (merger integrationMerger) Key() string {
|
|
return "merge"
|
|
}
|
|
|
|
func (merger integrationMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
|
|
output := contracts.MergeOutput{
|
|
LaneID: req.LaneID,
|
|
Schema: contracts.ResponseSchema{ID: "integration", Name: "integration", Version: "v1"},
|
|
Payload: contracts.RawPayload{
|
|
Content: []byte(`{"merged":true}`),
|
|
MediaType: "application/json",
|
|
},
|
|
}
|
|
if len(req.ExtractOutputs) > 0 {
|
|
output.SourceID = req.ExtractOutputs[0].SourceID
|
|
output.Schema = req.ExtractOutputs[0].Schema
|
|
output.Payload = req.ExtractOutputs[0].Payload
|
|
}
|
|
return contracts.MergeResult{Output: output}, nil
|
|
}
|
|
|
|
func (normalizer integrationNormalizer) Key() string {
|
|
return "normalize"
|
|
}
|
|
|
|
func (normalizer integrationNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
|
|
return nil
|
|
}
|
|
|
|
func (normalizer integrationNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
|
|
return contracts.NormalizeResult{
|
|
Output: contracts.NormalizeOutput{
|
|
LaneID: req.LaneID,
|
|
SourceID: req.MergeOutput.SourceID,
|
|
Schema: req.MergeOutput.Schema,
|
|
Payload: req.MergeOutput.Payload,
|
|
},
|
|
}, nil
|
|
}
|
|
|
|
type integrationOutput struct{}
|
|
|
|
func (output integrationOutput) Key() string {
|
|
return "output"
|
|
}
|
|
|
|
func (output integrationOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
|
|
return contracts.OutputResult{
|
|
Files: []contracts.OutputFile{
|
|
{Name: "output.json", ContentType: "application/json", Bytes: []byte(`{}`)},
|
|
},
|
|
}, nil
|
|
}
|
|
|
|
func integrationPipeline() ResolvedPipeline {
|
|
return ResolvedPipeline{
|
|
ID: "pipeline-1",
|
|
Digest: "sha256:pipeline",
|
|
Input: Binding("input"),
|
|
Chunk: Binding("chunk"),
|
|
ArtifactLanes: []ResolvedArtifactLane{
|
|
{
|
|
ID: "first",
|
|
Extract: Binding("extract-first"),
|
|
Merge: Binding("merge"),
|
|
Normalize: Binding("normalize"),
|
|
},
|
|
{
|
|
ID: "second",
|
|
Extract: Binding("extract-second"),
|
|
Merge: Binding("merge"),
|
|
Normalize: Binding("normalize"),
|
|
},
|
|
},
|
|
Output: Binding("output"),
|
|
}
|
|
}
|
|
|
|
func integrationSourceDocument() *source.SourceDocument {
|
|
return &source.SourceDocument{
|
|
ID: "source-1",
|
|
Kind: "document",
|
|
Format: "text/plain",
|
|
Digest: "sha256:abc123",
|
|
Units: []source.SourceUnit{
|
|
{ID: 1, Kind: "unit", Text: "Source unit.", Ref: source.SourceRef{SourceID: "source-1", StartUnitID: 1, EndUnitID: 1}},
|
|
},
|
|
}
|
|
}
|
|
|
|
func normalizeOutputKeys(outputs []contracts.NormalizeOutput) []string {
|
|
keys := make([]string, 0, len(outputs))
|
|
for _, output := range outputs {
|
|
keys = append(keys, output.NormalizerKey)
|
|
}
|
|
return keys
|
|
}
|