seriatim/internal/trim/artifact_test.go

package trim

import (
	"encoding/json"
	"strings"
	"testing"

	"gitea.maximumdirect.net/eric/seriatim/schema"
)

func TestParseArtifactJSONRejectsMalformedJSON(t *testing.T) {
	_, err := ParseArtifactJSON([]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 TestParseArtifactJSONRejectsDuplicateSegmentIDs(t *testing.T) {
	first := 10
	second := 20
	value := schema.Transcript{
		Metadata: schema.Metadata{
			Application: "seriatim",
			Version:     "v-test",
		},
		Segments: []schema.Segment{
			{ID: 1, Source: "a.json", SourceSegmentIndex: &first, Speaker: "A", Start: 1, End: 2, Text: "one"},
			{ID: 1, Source: "a.json", SourceSegmentIndex: &second, Speaker: "B", Start: 2, End: 3, Text: "two"},
		},
		OverlapGroups: []schema.OverlapGroup{},
	}
	data := mustMarshalJSON(t, value)

	_, err := ParseArtifactJSON(data)
	if err == nil {
		t.Fatal("expected invalid artifact error")
	}
	if !strings.Contains(err.Error(), "not a valid seriatim output artifact") {
		t.Fatalf("unexpected error: %v", err)
	}
}

func TestParseArtifactJSONRejectsNonSequentialSegmentIDs(t *testing.T) {
	first := 10
	second := 20
	value := schema.Transcript{
		Metadata: schema.Metadata{
			Application: "seriatim",
			Version:     "v-test",
		},
		Segments: []schema.Segment{
			{ID: 1, Source: "a.json", SourceSegmentIndex: &first, Speaker: "A", Start: 1, End: 2, Text: "one"},
			{ID: 3, Source: "a.json", SourceSegmentIndex: &second, Speaker: "B", Start: 2, End: 3, Text: "two"},
		},
		OverlapGroups: []schema.OverlapGroup{},
	}
	data := mustMarshalJSON(t, value)

	_, err := ParseArtifactJSON(data)
	if err == nil {
		t.Fatal("expected invalid artifact error")
	}
	if !strings.Contains(err.Error(), "not a valid seriatim output artifact") {
		t.Fatalf("unexpected error: %v", err)
	}
}

func TestConvertArtifactMinimalToIntermediate(t *testing.T) {
	value := schema.MinimalTranscript{
		Metadata: schema.MinimalMetadata{
			Application:  "seriatim",
			Version:      "v-test",
			OutputSchema: SchemaMinimal,
		},
		Segments: []schema.MinimalSegment{
			{ID: 1, Start: 1, End: 2, Speaker: "A", Text: "one"},
			{ID: 2, Start: 2, End: 3, Speaker: "B", Text: "two"},
		},
	}
	artifact := Artifact{
		Schema:  SchemaMinimal,
		Minimal: &value,
	}

	converted, err := ConvertArtifact(artifact, SchemaIntermediate)
	if err != nil {
		t.Fatalf("convert failed: %v", err)
	}
	if converted.Schema != SchemaIntermediate {
		t.Fatalf("schema = %q, want %q", converted.Schema, SchemaIntermediate)
	}
	if converted.Intermediate == nil {
		t.Fatal("expected intermediate artifact")
	}
	if len(converted.Intermediate.Segments) != 2 {
		t.Fatalf("segment count = %d, want 2", len(converted.Intermediate.Segments))
	}
	if converted.Intermediate.Segments[0].ID != 1 || converted.Intermediate.Segments[1].ID != 2 {
		t.Fatalf("unexpected IDs: %#v", converted.Intermediate.Segments)
	}
}

func TestConvertArtifactMinimalToFullFails(t *testing.T) {
	value := schema.MinimalTranscript{
		Metadata: schema.MinimalMetadata{
			Application:  "seriatim",
			Version:      "v-test",
			OutputSchema: SchemaMinimal,
		},
		Segments: []schema.MinimalSegment{
			{ID: 1, Start: 1, End: 2, Speaker: "A", Text: "one"},
		},
	}
	artifact := Artifact{
		Schema:  SchemaMinimal,
		Minimal: &value,
	}

	_, err := ConvertArtifact(artifact, SchemaFull)
	if err == nil {
		t.Fatal("expected conversion error")
	}
	if !strings.Contains(err.Error(), "cannot emit") {
		t.Fatalf("unexpected error: %v", err)
	}
}

func mustMarshalJSON(t *testing.T, value any) []byte {
	t.Helper()
	data, err := json.Marshal(value)
	if err != nil {
		t.Fatalf("marshal: %v", err)
	}
	return data
}