Implement artifact-level render command with Markdown output and update docs

This commit is contained in:
2026-05-24 22:55:56 +00:00
parent a90859114a
commit c37ea70dcb
28 changed files with 1619 additions and 99 deletions

View File

@@ -0,0 +1,178 @@
package artifact
import (
"encoding/json"
"fmt"
"gitea.maximumdirect.net/eric/seriatim/schema"
)
const (
OutputSchemaMinimal = schema.OutputSchemaMinimal
OutputSchemaIntermediate = schema.OutputSchemaIntermediate
OutputSchemaFull = schema.OutputSchemaFull
)
// OutputArtifact stores a parsed seriatim output artifact of one supported schema.
type OutputArtifact struct {
Schema string
Full *schema.Transcript
Intermediate *schema.IntermediateTranscript
Minimal *schema.MinimalTranscript
}
// ParseOutputArtifactJSON parses and validates serialized seriatim output JSON.
func ParseOutputArtifactJSON(data []byte) (OutputArtifact, error) {
var decoded any
if err := json.Unmarshal(data, &decoded); err != nil {
return OutputArtifact{}, fmt.Errorf("input JSON is malformed: %w", err)
}
var full schema.Transcript
if err := json.Unmarshal(data, &full); err == nil {
if err := schema.ValidateTranscript(full); err == nil {
return OutputArtifact{
Schema: OutputSchemaFull,
Full: &full,
}, nil
}
}
var intermediate schema.IntermediateTranscript
if err := json.Unmarshal(data, &intermediate); err == nil {
if err := schema.ValidateIntermediateTranscript(intermediate); err == nil {
return OutputArtifact{
Schema: OutputSchemaIntermediate,
Intermediate: &intermediate,
}, nil
}
}
var minimal schema.MinimalTranscript
if err := json.Unmarshal(data, &minimal); err == nil {
if err := schema.ValidateMinimalTranscript(minimal); err == nil {
return OutputArtifact{
Schema: OutputSchemaMinimal,
Minimal: &minimal,
}, nil
}
}
return OutputArtifact{}, fmt.Errorf("input JSON is not a valid seriatim output artifact")
}
// Value returns the output payload value for serialization.
func (artifact OutputArtifact) Value() any {
switch artifact.Schema {
case OutputSchemaFull:
if artifact.Full == nil {
return schema.Transcript{}
}
return *artifact.Full
case OutputSchemaIntermediate:
if artifact.Intermediate == nil {
return schema.IntermediateTranscript{}
}
return *artifact.Intermediate
case OutputSchemaMinimal:
if artifact.Minimal == nil {
return schema.MinimalTranscript{}
}
return *artifact.Minimal
default:
return nil
}
}
// SegmentCount returns the number of segments in the output artifact.
func (artifact OutputArtifact) SegmentCount() int {
switch artifact.Schema {
case OutputSchemaFull:
if artifact.Full == nil {
return 0
}
return len(artifact.Full.Segments)
case OutputSchemaIntermediate:
if artifact.Intermediate == nil {
return 0
}
return len(artifact.Intermediate.Segments)
case OutputSchemaMinimal:
if artifact.Minimal == nil {
return 0
}
return len(artifact.Minimal.Segments)
default:
return 0
}
}
// Application returns output artifact metadata application name.
func (artifact OutputArtifact) Application() string {
switch artifact.Schema {
case OutputSchemaFull:
if artifact.Full == nil {
return ""
}
return artifact.Full.Metadata.Application
case OutputSchemaIntermediate:
if artifact.Intermediate == nil {
return ""
}
return artifact.Intermediate.Metadata.Application
case OutputSchemaMinimal:
if artifact.Minimal == nil {
return ""
}
return artifact.Minimal.Metadata.Application
default:
return ""
}
}
// Version returns output artifact metadata version.
func (artifact OutputArtifact) Version() string {
switch artifact.Schema {
case OutputSchemaFull:
if artifact.Full == nil {
return ""
}
return artifact.Full.Metadata.Version
case OutputSchemaIntermediate:
if artifact.Intermediate == nil {
return ""
}
return artifact.Intermediate.Metadata.Version
case OutputSchemaMinimal:
if artifact.Minimal == nil {
return ""
}
return artifact.Minimal.Metadata.Version
default:
return ""
}
}
// FullPayload returns the full-schema payload when present.
func (artifact OutputArtifact) FullPayload() (*schema.Transcript, error) {
if artifact.Full == nil {
return nil, fmt.Errorf("full artifact payload is missing")
}
return artifact.Full, nil
}
// IntermediatePayload returns the intermediate-schema payload when present.
func (artifact OutputArtifact) IntermediatePayload() (*schema.IntermediateTranscript, error) {
if artifact.Intermediate == nil {
return nil, fmt.Errorf("intermediate artifact payload is missing")
}
return artifact.Intermediate, nil
}
// MinimalPayload returns the minimal-schema payload when present.
func (artifact OutputArtifact) MinimalPayload() (*schema.MinimalTranscript, error) {
if artifact.Minimal == nil {
return nil, fmt.Errorf("minimal artifact payload is missing")
}
return artifact.Minimal, nil
}

View File

@@ -0,0 +1,134 @@
package artifact
import (
"encoding/json"
"strings"
"testing"
"gitea.maximumdirect.net/eric/seriatim/schema"
)
func TestParseOutputArtifactJSONParsesFullIntermediateAndMinimal(t *testing.T) {
t.Run("full", func(t *testing.T) {
first := 0
value := schema.Transcript{
Metadata: schema.Metadata{
Application: "seriatim",
Version: "v-test",
InputReader: "json-files",
InputFiles: []string{"input.json"},
PreprocessingModules: []string{"validate-raw"},
PostprocessingModules: []string{"assign-ids", "validate-output"},
OutputModules: []string{"json"},
},
Segments: []schema.Segment{
{
ID: 1,
Source: "input.json",
SourceSegmentIndex: &first,
Speaker: "Alice",
Start: 1,
End: 2,
Text: "hello",
Categories: []string{"backchannel"},
},
},
OverlapGroups: []schema.OverlapGroup{},
}
parsed := mustParseOutputArtifact(t, value)
if parsed.Schema != OutputSchemaFull {
t.Fatalf("schema = %q, want %q", parsed.Schema, OutputSchemaFull)
}
if parsed.Full == nil {
t.Fatal("expected full payload")
}
})
t.Run("intermediate", func(t *testing.T) {
value := schema.IntermediateTranscript{
Metadata: schema.IntermediateMetadata{
Application: "seriatim",
Version: "v-test",
OutputSchema: OutputSchemaIntermediate,
},
Segments: []schema.IntermediateSegment{
{ID: 1, Start: 1, End: 2, Speaker: "Alice", Text: "hello", Categories: []string{"filler"}},
},
}
parsed := mustParseOutputArtifact(t, value)
if parsed.Schema != OutputSchemaIntermediate {
t.Fatalf("schema = %q, want %q", parsed.Schema, OutputSchemaIntermediate)
}
if parsed.Intermediate == nil {
t.Fatal("expected intermediate payload")
}
})
t.Run("minimal", func(t *testing.T) {
value := schema.MinimalTranscript{
Metadata: schema.MinimalMetadata{
Application: "seriatim",
Version: "v-test",
OutputSchema: OutputSchemaMinimal,
},
Segments: []schema.MinimalSegment{
{ID: 1, Start: 1, End: 2, Speaker: "Alice", Text: "hello"},
},
}
parsed := mustParseOutputArtifact(t, value)
if parsed.Schema != OutputSchemaMinimal {
t.Fatalf("schema = %q, want %q", parsed.Schema, OutputSchemaMinimal)
}
if parsed.Minimal == nil {
t.Fatal("expected minimal payload")
}
})
}
func TestParseOutputArtifactJSONRejectsMalformedJSON(t *testing.T) {
_, err := ParseOutputArtifactJSON([]byte(`{"metadata":`))
if err == nil {
t.Fatal("expected malformed JSON error")
}
if !strings.Contains(err.Error(), "input JSON is malformed") {
t.Fatalf("unexpected error: %v", err)
}
}
func TestParseOutputArtifactJSONRejectsRawWhisperXLikeInput(t *testing.T) {
data := []byte(`{
"segments": [
{
"id": 0,
"start": 0.1,
"end": 1.2,
"text": "hello",
"words": [{"word":"hello","start":0.1,"end":0.8}]
}
]
}`)
_, err := ParseOutputArtifactJSON(data)
if err == nil {
t.Fatal("expected artifact validation error")
}
if !strings.Contains(err.Error(), "not a valid seriatim output artifact") {
t.Fatalf("unexpected error: %v", err)
}
}
func mustParseOutputArtifact(t *testing.T, value any) OutputArtifact {
t.Helper()
data, err := json.Marshal(value)
if err != nil {
t.Fatalf("marshal: %v", err)
}
parsed, err := ParseOutputArtifactJSON(data)
if err != nil {
t.Fatalf("parse: %v", err)
}
return parsed
}