Files
seriatim/internal/artifact/output_artifact_test.go

135 lines
3.5 KiB
Go

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
}