Added support for a minimal JSON output schema

internal/cli/merge_test.go

@@ -10,6 +10,7 @@ import (
 
 	"gitea.maximumdirect.net/eric/seriatim/internal/model"
 	"gitea.maximumdirect.net/eric/seriatim/internal/report"
+	"gitea.maximumdirect.net/eric/seriatim/schema"
 )
 
 func TestMergeWritesMergedOutputAndReport(t *testing.T) {
@@ -111,6 +112,64 @@ func TestMergeWritesMergedOutputAndReport(t *testing.T) {
 	}
 }
 
+func TestMergeWritesMinimalOutputSchema(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{
+		"segments": [
+			{"start": 1, "end": 2, "text": " Yeah. "},
+			{"start": 8, "end": 9, "text": " next "}
+		]
+	}`)
+	output := filepath.Join(dir, "merged.json")
+	reportPath := filepath.Join(dir, "report.json")
+
+	err := executeMerge(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", "minimal",
+		"--report-file", reportPath,
+	)
+	if err != nil {
+		t.Fatalf("merge failed: %v", err)
+	}
+
+	var transcript schema.MinimalTranscript
+	readJSON(t, output, &transcript)
+	if transcript.Metadata.Application != "seriatim" {
+		t.Fatalf("application = %q, want seriatim", transcript.Metadata.Application)
+	}
+	if transcript.Metadata.OutputSchema != "minimal" {
+		t.Fatalf("output_schema = %q, want minimal", transcript.Metadata.OutputSchema)
+	}
+	if got, want := len(transcript.Segments), 2; got != want {
+		t.Fatalf("segment count = %d, want %d", got, want)
+	}
+	for index, segment := range transcript.Segments {
+		if segment.ID != index+1 {
+			t.Fatalf("segment %d id = %d, want %d", index, segment.ID, index+1)
+		}
+	}
+	if transcript.Segments[0].Speaker != "input.json" || transcript.Segments[0].Text != "Yeah." {
+		t.Fatalf("first segment = %#v", transcript.Segments[0])
+	}
+
+	outputBytes, err := os.ReadFile(output)
+	if err != nil {
+		t.Fatalf("read output: %v", err)
+	}
+	for _, forbidden := range []string{"overlap_groups", "categories", "source", "derived_from"} {
+		if strings.Contains(string(outputBytes), forbidden) {
+			t.Fatalf("minimal output contains %q:\n%s", forbidden, outputBytes)
+		}
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	if !hasReportEvent(rpt, "postprocessing", "validate-output", "validated 2 output segment(s)") {
+		t.Fatal("expected validate-output report event")
+	}
+}
+
 func TestMergeTieBreakOrder(t *testing.T) {
 	dir := t.TempDir()
 	inputA := writeJSONFile(t, dir, "a.json", `{
@@ -182,6 +241,29 @@ func TestMergeValidateOutputBeforeAssignIDsFails(t *testing.T) {
 	}
 }
 
+func TestMergeValidateMinimalOutputBeforeAssignIDsFails(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{
+		"segments": [
+			{"start": 1, "end": 2, "text": "hello"}
+		]
+	}`)
+	output := filepath.Join(dir, "merged.json")
+
+	err := executeMerge(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", "minimal",
+		"--postprocessing-modules", "validate-output,assign-ids",
+	)
+	if err == nil {
+		t.Fatal("expected validation error")
+	}
+	if !strings.Contains(err.Error(), "validate-output: segment 0 has id 0; want 1") {
+		t.Fatalf("unexpected error: %v", err)
+	}
+}
+
 func TestMergeDetectsOverlapGroups(t *testing.T) {
 	dir := t.TempDir()
 	inputA := writeJSONFile(t, dir, "a.json", `{
@@ -963,6 +1045,24 @@ func TestUnknownModulesFailDuringValidation(t *testing.T) {
 	}
 }
 
+func TestUnknownOutputSchemaFailsDuringValidation(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{"segments":[]}`)
+	output := filepath.Join(dir, "merged.json")
+
+	err := executeMerge(
+		"--input-file", input,
+		"--output-file", output,
+		"--output-schema", "compact",
+	)
+	if err == nil {
+		t.Fatal("expected output schema error")
+	}
+	if !strings.Contains(err.Error(), "--output-schema must be one of") {
+		t.Fatalf("unexpected error: %v", err)
+	}
+}
+
 func TestInvalidPreprocessingOrderFails(t *testing.T) {
 	dir := t.TempDir()
 	input := writeJSONFile(t, dir, "input.json", `{"segments":[]}`)