eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement raw module output contracts

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-07 18:58:23 +00:00
parent 9e3f8809b3
commit c05ecb58d8
33 changed files with 1166 additions and 1780 deletions
Download Patch File Download Diff File Expand all files Collapse all files

169
internal/modules/output/json/encoder.go
View File

@@ -8,8 +8,6 @@ import (
"sort"
"strings"
"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"
)
@@ -18,7 +16,7 @@ const Key = "json"
const contentTypeJSON = "application/json"
var safeArtifactFileChar = regexp.MustCompile(`[^A-Za-z0-9._-]`)
var safeOutputFileChar = regexp.MustCompile(`[^A-Za-z0-9._-]`)
var _ contracts.OutputEncoder = (*Encoder)(nil)
@@ -66,24 +64,24 @@ func Register(registry *pipeline.OutputEncoderRegistry) error {
}
type indexFile struct {
ManifestFile string `json:"manifest_file"`
ArtifactFiles []artifactFileIndex `json:"artifact_files"`
RejectedFile string `json:"rejected_file"`
WarningsFile string `json:"warnings_file"`
ManifestFile string `json:"manifest_file"`
OutputFiles []outputFileIndex `json:"output_files"`
RejectedFile string `json:"rejected_file"`
WarningsFile string `json:"warnings_file"`
}
type artifactFileIndex struct {
ArtifactType string `json:"artifact_type"`
File string `json:"file"`
}
type artifactFile struct {
ArtifactType string `json:"artifact_type"`
Artifacts []artifacts.Artifact `json:"artifacts"`
type outputFileIndex struct {
LaneID string `json:"lane_id"`
MediaType string `json:"media_type,omitempty"`
File string `json:"file"`
ModuleKey string `json:"module_key,omitempty"`
SchemaID string `json:"schema_id,omitempty"`
SchemaName string `json:"schema_name,omitempty"`
SchemaVer string `json:"schema_version,omitempty"`
}
type rejectedFile struct {
Rejected []artifacts.RejectedArtifact `json:"rejected"`
Rejected []contracts.RejectedOutput `json:"rejected"`
}
type warningsFile struct {
@@ -91,43 +89,39 @@ type warningsFile struct {
}
func logicalFiles(req contracts.OutputRequest) ([]contracts.OutputFile, error) {
artifactsByType := make(map[string][]artifacts.Artifact)
for _, artifact := range req.Approved {
artifactsByType[artifact.ArtifactType] = append(artifactsByType[artifact.ArtifactType], cloneArtifact(artifact))
}
outputs := cloneNormalizeOutputs(req.NormalizeOutputs)
sort.SliceStable(outputs, func(i, j int) bool {
return outputs[i].LaneID < outputs[j].LaneID
})
artifactTypes := make([]string, 0, len(artifactsByType))
for artifactType := range artifactsByType {
artifactTypes = append(artifactTypes, artifactType)
}
sort.Strings(artifactTypes)
artifactIndexes := make([]artifactFileIndex, 0, len(artifactTypes))
files := make([]contracts.OutputFile, 0, len(artifactTypes)+4)
outputIndexes := make([]outputFileIndex, 0, len(outputs))
files := make([]contracts.OutputFile, 0, len(outputs)+4)
manifestFile, err := jsonFile("manifest.json", req.Manifest)
if err != nil {
return nil, err
}
files = append(files, manifestFile)
usedArtifactFiles := make(map[string]string, len(artifactTypes))
for _, artifactType := range artifactTypes {
name, err := artifactFileName(artifactType)
usedOutputFiles := make(map[string]string, len(outputs))
for _, output := range outputs {
name, err := outputFileName(output.LaneID)
if err != nil {
return nil, err
}
if existingType, ok := usedArtifactFiles[name]; ok {
return nil, encoderErrorf("artifact types %q and %q produce duplicate output file %q", existingType, artifactType, name)
if existingLane, ok := usedOutputFiles[name]; ok {
return nil, encoderErrorf("lanes %q and %q produce duplicate output file %q", existingLane, output.LaneID, name)
}
usedArtifactFiles[name] = artifactType
artifactIndexes = append(artifactIndexes, artifactFileIndex{
ArtifactType: artifactType,
File: name,
})
file, err := jsonFile(name, artifactFile{
ArtifactType: artifactType,
Artifacts: artifactsByType[artifactType],
usedOutputFiles[name] = output.LaneID
outputIndexes = append(outputIndexes, outputFileIndex{
LaneID: output.LaneID,
MediaType: output.Payload.MediaType,
File: name,
ModuleKey: output.NormalizerKey,
SchemaID: output.Schema.ID,
SchemaName: output.Schema.Name,
SchemaVer: output.Schema.Version,
})
file, err := rawOutputFile(name, output.Payload)
if err != nil {
return nil, err
}
@@ -135,10 +129,10 @@ func logicalFiles(req contracts.OutputRequest) ([]contracts.OutputFile, error) {
}
index := indexFile{
ManifestFile: "manifest.json",
ArtifactFiles: artifactIndexes,
RejectedFile: "rejected.json",
WarningsFile: "warnings.json",
ManifestFile: "manifest.json",
OutputFiles: outputIndexes,
RejectedFile: "rejected.json",
WarningsFile: "warnings.json",
}
indexOutput, err := jsonFile("index.json", index)
if err != nil {
@@ -159,6 +153,32 @@ func logicalFiles(req contracts.OutputRequest) ([]contracts.OutputFile, error) {
return files, nil
}
func rawOutputFile(name string, payload contracts.RawPayload) (contracts.OutputFile, error) {
content := append([]byte(nil), payload.Content...)
if len(content) == 0 {
content = []byte("null")
}
if payload.MediaType == contentTypeJSON && stdjson.Valid(content) {
var decoded any
if err := stdjson.Unmarshal(content, &decoded); err == nil {
pretty, err := marshalPretty(decoded)
if err != nil {
return contracts.OutputFile{}, err
}
content = pretty
}
}
mediaType := strings.TrimSpace(payload.MediaType)
if mediaType == "" {
mediaType = "application/octet-stream"
}
return contracts.OutputFile{
Name: name,
ContentType: mediaType,
Bytes: append([]byte(nil), content...),
}, nil
}
func jsonFile(name string, value any) (contracts.OutputFile, error) {
data, err := marshalPretty(value)
if err != nil {
@@ -179,57 +199,46 @@ func marshalPretty(value any) ([]byte, error) {
return append(data, '\n'), nil
}
func artifactFileName(artifactType string) (string, error) {
sanitized := safeArtifactFileChar.ReplaceAllString(strings.TrimSpace(artifactType), "_")
func outputFileName(laneID string) (string, error) {
sanitized := safeOutputFileChar.ReplaceAllString(strings.TrimSpace(laneID), "_")
for strings.Contains(sanitized, "..") {
sanitized = strings.ReplaceAll(sanitized, "..", "__")
}
sanitized = strings.Trim(sanitized, "._")
if sanitized == "" {
return "", encoderErrorf("artifact type %q cannot produce a safe file name", artifactType)
return "", encoderErrorf("lane id %q cannot produce a safe file name", laneID)
}
return "artifacts/" + sanitized + ".json", nil
return "outputs/" + sanitized + ".json", nil
}
func cloneArtifact(artifact artifacts.Artifact) artifacts.Artifact {
return artifacts.Artifact{
ExtractorKey: artifact.ExtractorKey,
ArtifactType: artifact.ArtifactType,
SchemaVersion: artifact.SchemaVersion,
Payload: append(stdjson.RawMessage(nil), artifact.Payload...),
SourceRefs: append([]source.SourceRef(nil), artifact.SourceRefs...),
Metadata: cloneMetadata(artifact.Metadata),
func cloneNormalizeOutputs(outputs []contracts.NormalizeOutput) []contracts.NormalizeOutput {
if len(outputs) == 0 {
return nil
}
}
func cloneRejected(rejected []artifacts.RejectedArtifact) []artifacts.RejectedArtifact {
if len(rejected) == 0 {
return []artifacts.RejectedArtifact{}
}
out := make([]artifacts.RejectedArtifact, 0, len(rejected))
for _, item := range rejected {
out = append(out, artifacts.RejectedArtifact{
Candidate: cloneCandidate(item.Candidate),
ValidatorName: item.ValidatorName,
ReasonCode: item.ReasonCode,
Message: item.Message,
})
out := make([]contracts.NormalizeOutput, 0, len(outputs))
for _, output := range outputs {
output.Payload = cloneRawPayload(output.Payload)
out = append(out, output)
}
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(stdjson.RawMessage(nil), candidate.Payload...),
SourceRefs: append([]source.SourceRef(nil), candidate.SourceRefs...),
Metadata: cloneMetadata(candidate.Metadata),
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...),
}
}
func cloneRejected(rejected []contracts.RejectedOutput) []contracts.RejectedOutput {
if len(rejected) == 0 {
return []contracts.RejectedOutput{}
}
return append([]contracts.RejectedOutput(nil), rejected...)
}
func cloneWarnings(warnings []contracts.Warning) []contracts.Warning {
if len(warnings) == 0 {
return []contracts.Warning{}