Implement normalize output conversion

internal/cli/normalize_test.go

@@ -1,9 +1,13 @@
 package cli
 
 import (
+	"os"
 	"path/filepath"
 	"strings"
 	"testing"
+
+	"gitea.maximumdirect.net/eric/seriatim/internal/config"
+	"gitea.maximumdirect.net/eric/seriatim/schema"
 )
 
 func TestNormalizeCommandIsRecognized(t *testing.T) {
@@ -80,7 +84,171 @@ func TestNormalizeInvalidOutputModuleFails(t *testing.T) {
 	}
 }
 
-func TestNormalizeValidFlagsReachNotImplementedBoundary(t *testing.T) {
+func TestNormalizeDefaultOutputSchemaIsIntermediate(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{
+		"segments": [
+			{"id": 99, "start": 5, "end": 6, "speaker": "Bob", "text": "second", "categories": ["filler"]},
+			{"id": 10, "start": 1, "end": 2, "speaker": "Alice", "text": "first", "categories": ["backchannel"]}
+		]
+	}`)
+	output := filepath.Join(dir, "normalized.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var transcript schema.IntermediateTranscript
+	readJSON(t, output, &transcript)
+	if transcript.Metadata.OutputSchema != config.OutputSchemaIntermediate {
+		t.Fatalf("output schema = %q, want %q", transcript.Metadata.OutputSchema, config.OutputSchemaIntermediate)
+	}
+	if len(transcript.Segments) != 2 {
+		t.Fatalf("segment count = %d, want 2", len(transcript.Segments))
+	}
+	if transcript.Segments[0].ID != 1 || transcript.Segments[1].ID != 2 {
+		t.Fatalf("segment IDs = %d,%d, want 1,2", transcript.Segments[0].ID, transcript.Segments[1].ID)
+	}
+	if transcript.Segments[0].Text != "first" || transcript.Segments[1].Text != "second" {
+		t.Fatalf("unexpected sort order: %#v", transcript.Segments)
+	}
+	if len(transcript.Segments[0].Categories) != 1 || transcript.Segments[0].Categories[0] != "backchannel" {
+		t.Fatalf("expected categories preserved on first segment, got %#v", transcript.Segments[0].Categories)
+	}
+}
+
+func TestNormalizeBareArrayInputToIntermediateOutput(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `[
+		{"start": 2, "end": 3, "speaker": "Bob", "text": "second"},
+		{"start": 1, "end": 2, "speaker": "Alice", "text": "first"}
+	]`)
+	output := filepath.Join(dir, "normalized.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", config.OutputSchemaIntermediate,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var transcript schema.IntermediateTranscript
+	readJSON(t, output, &transcript)
+	if len(transcript.Segments) != 2 {
+		t.Fatalf("segment count = %d, want 2", len(transcript.Segments))
+	}
+	if transcript.Segments[0].Speaker != "Alice" || transcript.Segments[1].Speaker != "Bob" {
+		t.Fatalf("unexpected sorted speakers: %#v", transcript.Segments)
+	}
+}
+
+func TestNormalizeInputIndexTieBreakerIsDeterministic(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `[
+		{"start": 1, "end": 2, "speaker": "Zulu", "text": "first in"},
+		{"start": 1, "end": 2, "speaker": "Alpha", "text": "second in"}
+	]`)
+	output := filepath.Join(dir, "normalized.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var transcript schema.IntermediateTranscript
+	readJSON(t, output, &transcript)
+	if transcript.Segments[0].Speaker != "Zulu" || transcript.Segments[1].Speaker != "Alpha" {
+		t.Fatalf("tie-break order mismatch: %#v", transcript.Segments)
+	}
+}
+
+func TestNormalizeMinimalSchemaOmitsCategories(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{
+		"segments": [
+			{"start": 1, "end": 2, "speaker": "Alice", "text": "first", "categories": ["filler"]}
+		]
+	}`)
+	output := filepath.Join(dir, "normalized.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", config.OutputSchemaMinimal,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var transcript schema.MinimalTranscript
+	readJSON(t, output, &transcript)
+	if transcript.Metadata.OutputSchema != config.OutputSchemaMinimal {
+		t.Fatalf("output schema = %q, want %q", transcript.Metadata.OutputSchema, config.OutputSchemaMinimal)
+	}
+	if len(transcript.Segments) != 1 || transcript.Segments[0].ID != 1 {
+		t.Fatalf("unexpected minimal output: %#v", transcript.Segments)
+	}
+	bytes, readErr := os.ReadFile(output)
+	if readErr != nil {
+		t.Fatalf("read output: %v", readErr)
+	}
+	if strings.Contains(string(bytes), "categories") {
+		t.Fatalf("minimal output unexpectedly contains categories:\n%s", string(bytes))
+	}
+}
+
+func TestNormalizeFullSchemaOutputValidatesAndHasProvenanceFallback(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `[
+		{"start": 1, "end": 2, "speaker": "Alice", "text": "first"},
+		{"start": 3, "end": 4, "speaker": "Bob", "text": "second", "source":"custom.json", "source_segment_index": 7}
+	]`)
+	output := filepath.Join(dir, "normalized.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", config.OutputSchemaFull,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var transcript schema.Transcript
+	readJSON(t, output, &transcript)
+	if err := schema.ValidateTranscript(transcript); err != nil {
+		t.Fatalf("full output should validate: %v", err)
+	}
+	if len(transcript.Segments) != 2 {
+		t.Fatalf("segment count = %d, want 2", len(transcript.Segments))
+	}
+	if transcript.Segments[0].Source != filepath.Base(input) {
+		t.Fatalf("source fallback = %q, want %q", transcript.Segments[0].Source, filepath.Base(input))
+	}
+	if transcript.Segments[0].SourceSegmentIndex == nil || *transcript.Segments[0].SourceSegmentIndex != 0 {
+		t.Fatalf("source_segment_index fallback = %v, want 0", transcript.Segments[0].SourceSegmentIndex)
+	}
+	if transcript.Segments[1].Source != "custom.json" {
+		t.Fatalf("explicit source preserved = %q, want custom.json", transcript.Segments[1].Source)
+	}
+	if transcript.Segments[1].SourceSegmentIndex == nil || *transcript.Segments[1].SourceSegmentIndex != 7 {
+		t.Fatalf("explicit source_segment_index preserved = %v, want 7", transcript.Segments[1].SourceSegmentIndex)
+	}
+	if transcript.OverlapGroups == nil || len(transcript.OverlapGroups) != 0 {
+		t.Fatalf("overlap_groups = %#v, want empty array", transcript.OverlapGroups)
+	}
+}
+
+func TestNormalizeEmptySegmentsArrayProducesValidOutput(t *testing.T) {
 	dir := t.TempDir()
 	input := writeJSONFile(t, dir, "input.json", `{"segments":[]}`)
 	output := filepath.Join(dir, "normalized.json")
@@ -89,11 +257,38 @@ func TestNormalizeValidFlagsReachNotImplementedBoundary(t *testing.T) {
 		"--input-file", input,
 		"--output-file", output,
 	)
-	if err == nil {
+	if err != nil {
-		t.Fatal("expected not implemented error")
+		t.Fatalf("normalize failed: %v", err)
 	}
-	if !strings.Contains(err.Error(), "not implemented") {
+
-		t.Fatalf("unexpected error: %v", err)
+	var transcript schema.IntermediateTranscript
+	readJSON(t, output, &transcript)
+	if len(transcript.Segments) != 0 {
+		t.Fatalf("segment count = %d, want 0", len(transcript.Segments))
+	}
+	if err := schema.ValidateIntermediateTranscript(transcript); err != nil {
+		t.Fatalf("intermediate output should validate: %v", err)
+	}
+}
+
+func TestNormalizeSelectedOutputSchemaIsHonored(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{"segments":[{"start":1,"end":2,"speaker":"A","text":"one"}]}`)
+	output := filepath.Join(dir, "normalized.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", config.OutputSchemaMinimal,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var transcript schema.MinimalTranscript
+	readJSON(t, output, &transcript)
+	if transcript.Metadata.OutputSchema != config.OutputSchemaMinimal {
+		t.Fatalf("output schema = %q, want %q", transcript.Metadata.OutputSchema, config.OutputSchemaMinimal)
 	}
 }
 

internal/normalize/build.go

@@ -0,0 +1,158 @@
+package normalize
+
+import (
+	"fmt"
+	"path/filepath"
+	"sort"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/seriatim/internal/artifact"
+	"gitea.maximumdirect.net/eric/seriatim/internal/buildinfo"
+	"gitea.maximumdirect.net/eric/seriatim/internal/config"
+	"gitea.maximumdirect.net/eric/seriatim/schema"
+)
+
+// Build converts parsed normalize input into a selected seriatim output schema.
+func Build(parsed ParsedTranscript, cfg config.NormalizeConfig) (any, error) {
+	ordered := sortedSegments(parsed.Segments)
+
+	switch cfg.OutputSchema {
+	case config.OutputSchemaMinimal:
+		output := buildMinimal(ordered)
+		if err := schema.ValidateMinimalTranscript(output); err != nil {
+			return nil, fmt.Errorf("validate normalize output: %w", err)
+		}
+		return output, nil
+	case config.OutputSchemaIntermediate:
+		output := buildIntermediate(ordered)
+		if err := schema.ValidateIntermediateTranscript(output); err != nil {
+			return nil, fmt.Errorf("validate normalize output: %w", err)
+		}
+		return output, nil
+	case config.OutputSchemaFull:
+		output := buildFull(ordered, cfg)
+		if err := schema.ValidateTranscript(output); err != nil {
+			return nil, fmt.Errorf("validate normalize output: %w", err)
+		}
+		return output, nil
+	default:
+		return nil, fmt.Errorf("unsupported output schema %q", cfg.OutputSchema)
+	}
+}
+
+func sortedSegments(input []InputSegment) []InputSegment {
+	ordered := make([]InputSegment, len(input))
+	copy(ordered, input)
+	sort.SliceStable(ordered, func(i, j int) bool {
+		left := ordered[i]
+		right := ordered[j]
+		if left.Start != right.Start {
+			return left.Start < right.Start
+		}
+		if left.End != right.End {
+			return left.End < right.End
+		}
+		if left.InputIndex != right.InputIndex {
+			return left.InputIndex < right.InputIndex
+		}
+		return left.Speaker < right.Speaker
+	})
+	return ordered
+}
+
+func buildMinimal(segments []InputSegment) schema.MinimalTranscript {
+	outputSegments := make([]schema.MinimalSegment, len(segments))
+	for index, segment := range segments {
+		outputSegments[index] = schema.MinimalSegment{
+			ID:      index + 1,
+			Start:   segment.Start,
+			End:     segment.End,
+			Speaker: segment.Speaker,
+			Text:    segment.Text,
+		}
+	}
+
+	return schema.MinimalTranscript{
+		Metadata: schema.MinimalMetadata{
+			Application:  artifact.ApplicationName,
+			Version:      buildinfo.Version,
+			OutputSchema: config.OutputSchemaMinimal,
+		},
+		Segments: outputSegments,
+	}
+}
+
+func buildIntermediate(segments []InputSegment) schema.IntermediateTranscript {
+	outputSegments := make([]schema.IntermediateSegment, len(segments))
+	for index, segment := range segments {
+		outputSegments[index] = schema.IntermediateSegment{
+			ID:         index + 1,
+			Start:      segment.Start,
+			End:        segment.End,
+			Speaker:    segment.Speaker,
+			Text:       segment.Text,
+			Categories: append([]string(nil), segment.Categories...),
+		}
+	}
+
+	return schema.IntermediateTranscript{
+		Metadata: schema.IntermediateMetadata{
+			Application:  artifact.ApplicationName,
+			Version:      buildinfo.Version,
+			OutputSchema: config.OutputSchemaIntermediate,
+		},
+		Segments: outputSegments,
+	}
+}
+
+func buildFull(segments []InputSegment, cfg config.NormalizeConfig) schema.Transcript {
+	defaultSource := filepath.Base(cfg.InputFile)
+	outputSegments := make([]schema.Segment, len(segments))
+	for index, segment := range segments {
+		source := strings.TrimSpace(segment.Source)
+		if source == "" {
+			source = defaultSource
+		}
+
+		sourceSegmentIndex := copyIntPtr(segment.SourceSegmentIndex)
+		if sourceSegmentIndex == nil {
+			fallback := segment.InputIndex
+			sourceSegmentIndex = &fallback
+		}
+
+		outputSegments[index] = schema.Segment{
+			ID:                 index + 1,
+			Source:             source,
+			SourceSegmentIndex: sourceSegmentIndex,
+			SourceRef:          segment.SourceRef,
+			DerivedFrom:        append([]string(nil), segment.DerivedFrom...),
+			Speaker:            segment.Speaker,
+			Start:              segment.Start,
+			End:                segment.End,
+			Text:               segment.Text,
+			Categories:         append([]string(nil), segment.Categories...),
+		}
+	}
+
+	return schema.Transcript{
+		Metadata: schema.Metadata{
+			Application:           artifact.ApplicationName,
+			Version:               buildinfo.Version,
+			InputReader:           "normalize-input",
+			InputFiles:            []string{cfg.InputFile},
+			PreprocessingModules:  []string{},
+			PostprocessingModules: []string{},
+			OutputModules:         append([]string(nil), cfg.OutputModules...),
+		},
+		Segments:      outputSegments,
+		OverlapGroups: []schema.OverlapGroup{},
+	}
+}
+
+func copyIntPtr(value *int) *int {
+	if value == nil {
+		return nil
+	}
+	copied := *value
+	return &copied
+}

internal/normalize/normalize.go

@@ -2,7 +2,9 @@ package normalize
 
 import (
 	"context"
+	"encoding/json"
 	"fmt"
+	"os"
 
 	"gitea.maximumdirect.net/eric/seriatim/internal/config"
 )
@@ -14,10 +16,34 @@ func Run(ctx context.Context, cfg config.NormalizeConfig) error {
 		return err
 	}
 
-	if _, err := ParseFile(cfg.InputFile); err != nil {
+	parsed, err := ParseFile(cfg.InputFile)
+	if err != nil {
 		return err
 	}
 
-	// TODO: Implement transcript normalization transformation.
+	output, err := Build(parsed, cfg)
-	return fmt.Errorf("normalize command is not implemented yet")
+	if err != nil {
+		return err
+	}
+
+	if err := writeOutputJSON(cfg.OutputFile, output); err != nil {
+		return err
+	}
+
+	return nil
+}
+
+func writeOutputJSON(path string, value any) error {
+	file, err := os.Create(path)
+	if err != nil {
+		return err
+	}
+	defer file.Close()
+
+	encoder := json.NewEncoder(file)
+	encoder.SetIndent("", "  ")
+	if err := encoder.Encode(value); err != nil {
+		return fmt.Errorf("encode normalize output JSON: %w", err)
+	}
+	return nil
 }