seriatim/internal/render/normalize_test.go

package render

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

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

func TestFromOutputArtifactNormalizesSupportedSchemas(t *testing.T) {
	t.Run("full", func(t *testing.T) {
		sourceIndex := 0
		input := schema.Transcript{
			Metadata: schema.Metadata{
				Application:           "seriatim",
				Version:               "v-test",
				InputReader:           "json-files",
				InputFiles:            []string{"a.json"},
				PreprocessingModules:  []string{"validate-raw"},
				PostprocessingModules: []string{"assign-ids", "validate-output"},
				OutputModules:         []string{"json"},
			},
			Segments: []schema.Segment{
				{
					ID:                 1,
					Source:             "a.json",
					SourceSegmentIndex: &sourceIndex,
					Speaker:            "Alice",
					Start:              1,
					End:                2,
					Text:               "hello",
					Categories:         []string{"background"},
				},
			},
			OverlapGroups: []schema.OverlapGroup{},
		}
		model := mustNormalizeOutputArtifact(t, input)
		if model.Schema != artifact.OutputSchemaFull {
			t.Fatalf("schema = %q, want %q", model.Schema, artifact.OutputSchemaFull)
		}
		if len(model.Segments) != 1 {
			t.Fatalf("segment count = %d, want 1", len(model.Segments))
		}
		if model.Segments[0].ID != 1 || model.Segments[0].Speaker != "Alice" || model.Segments[0].Text != "hello" {
			t.Fatalf("unexpected segment: %#v", model.Segments[0])
		}
		if len(model.Segments[0].Categories) != 1 || model.Segments[0].Categories[0] != "background" {
			t.Fatalf("categories = %#v, want [background]", model.Segments[0].Categories)
		}
	})

	t.Run("intermediate", func(t *testing.T) {
		input := schema.IntermediateTranscript{
			Metadata: schema.IntermediateMetadata{
				Application:  "seriatim",
				Version:      "v-test",
				OutputSchema: artifact.OutputSchemaIntermediate,
			},
			Segments: []schema.IntermediateSegment{
				{ID: 1, Start: 1, End: 2, Speaker: "Alice", Text: "one", Categories: []string{}},
				{ID: 2, Start: 2, End: 3, Speaker: "Bob", Text: "two"},
			},
		}
		model := mustNormalizeOutputArtifact(t, input)
		if model.Schema != artifact.OutputSchemaIntermediate {
			t.Fatalf("schema = %q, want %q", model.Schema, artifact.OutputSchemaIntermediate)
		}
		if len(model.Segments[0].Categories) != 0 {
			t.Fatalf("segment[0] categories = %#v, want empty slice", model.Segments[0].Categories)
		}
		if len(model.Segments[1].Categories) != 0 {
			t.Fatalf("segment[1] categories = %#v, want empty slice", model.Segments[1].Categories)
		}
		if model.Segments[0].Categories == nil || model.Segments[1].Categories == nil {
			t.Fatal("expected non-nil empty categories slices")
		}
	})

	t.Run("minimal", func(t *testing.T) {
		input := schema.MinimalTranscript{
			Metadata: schema.MinimalMetadata{
				Application:  "seriatim",
				Version:      "v-test",
				OutputSchema: artifact.OutputSchemaMinimal,
			},
			Segments: []schema.MinimalSegment{
				{ID: 1, Start: 1, End: 2, Speaker: "Alice", Text: "one"},
			},
		}
		model := mustNormalizeOutputArtifact(t, input)
		if model.Schema != artifact.OutputSchemaMinimal {
			t.Fatalf("schema = %q, want %q", model.Schema, artifact.OutputSchemaMinimal)
		}
		if len(model.Segments[0].Categories) != 0 {
			t.Fatalf("categories = %#v, want empty slice", model.Segments[0].Categories)
		}
		if model.Segments[0].Categories == nil {
			t.Fatal("expected non-nil empty categories slice")
		}
	})
}

func TestFromOutputArtifactRejectsMalformedAndRawInput(t *testing.T) {
	_, err := artifact.ParseOutputArtifactJSON([]byte(`{"metadata":`))
	if err == nil {
		t.Fatal("expected malformed JSON error")
	}
	if !strings.Contains(err.Error(), "input JSON is malformed") {
		t.Fatalf("unexpected malformed error: %v", err)
	}

	rawWhisper := []byte(`{"segments":[{"id":0,"start":0.1,"end":1.2,"text":"hello","words":[{"word":"hello"}]}]}`)
	_, err = artifact.ParseOutputArtifactJSON(rawWhisper)
	if err == nil {
		t.Fatal("expected raw input artifact error")
	}
	if !strings.Contains(err.Error(), "not a valid seriatim output artifact") {
		t.Fatalf("unexpected raw input error: %v", err)
	}
}

func mustNormalizeOutputArtifact(t *testing.T, value any) Transcript {
	t.Helper()
	data, err := json.Marshal(value)
	if err != nil {
		t.Fatalf("marshal: %v", err)
	}
	parsed, err := artifact.ParseOutputArtifactJSON(data)
	if err != nil {
		t.Fatalf("parse: %v", err)
	}
	model, err := FromOutputArtifact(parsed)
	if err != nil {
		t.Fatalf("normalize: %v", err)
	}
	return model
}