Add normalize report diagnostics

internal/cli/normalize_test.go

@@ -1,12 +1,14 @@
 package cli
 
 import (
+	"encoding/json"
 	"os"
 	"path/filepath"
 	"strings"
 	"testing"
 
 	"gitea.maximumdirect.net/eric/seriatim/internal/config"
+	"gitea.maximumdirect.net/eric/seriatim/internal/report"
 	"gitea.maximumdirect.net/eric/seriatim/schema"
 )
 
@@ -292,8 +294,139 @@ func TestNormalizeSelectedOutputSchemaIsHonored(t *testing.T) {
 	}
 }
 
+func TestNormalizeReportFileWrittenAndContainsObjectInputShape(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")
+	reportPath := filepath.Join(dir, "report.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--report-file", reportPath,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	audit := extractNormalizeAudit(t, rpt)
+	if audit.InputShape != "object_with_segments" {
+		t.Fatalf("input shape = %q, want object_with_segments", audit.InputShape)
+	}
+	if audit.InputSegmentCount != 1 {
+		t.Fatalf("input segment count = %d, want 1", audit.InputSegmentCount)
+	}
+	if audit.OutputSchema != config.OutputSchemaIntermediate {
+		t.Fatalf("output schema = %q, want %q", audit.OutputSchema, config.OutputSchemaIntermediate)
+	}
+	if len(audit.OutputModules) != 1 || audit.OutputModules[0] != "json" {
+		t.Fatalf("output modules = %v, want [json]", audit.OutputModules)
+	}
+}
+
+func TestNormalizeReportIncludesBareArrayShape(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `[{"start":1,"end":2,"speaker":"A","text":"one"}]`)
+	output := filepath.Join(dir, "normalized.json")
+	reportPath := filepath.Join(dir, "report.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--report-file", reportPath,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	audit := extractNormalizeAudit(t, rpt)
+	if audit.InputShape != "bare_segments_array" {
+		t.Fatalf("input shape = %q, want bare_segments_array", audit.InputShape)
+	}
+}
+
+func TestNormalizeReportEmptyInputEmitsWarning(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{"segments":[]}`)
+	output := filepath.Join(dir, "normalized.json")
+	reportPath := filepath.Join(dir, "report.json")
+
+	err := executeNormalize(
+		"--input-file", input,
+		"--output-file", output,
+		"--report-file", reportPath,
+	)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	var rpt report.Report
+	readJSON(t, reportPath, &rpt)
+	found := false
+	for _, event := range rpt.Events {
+		if event.Stage == "normalize" && event.Module == "normalize" && event.Severity == report.SeverityWarning &&
+			strings.Contains(event.Message, "zero segments") {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Fatalf("expected empty transcript warning event, got %#v", rpt.Events)
+	}
+}
+
+func TestNormalizeReportWriteFailureReturnsClearError(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,
+		"--report-file", dir,
+	)
+	if err == nil {
+		t.Fatal("expected report write failure")
+	}
+	if !strings.Contains(err.Error(), "write --report-file") {
+		t.Fatalf("unexpected error: %v", err)
+	}
+}
+
 func executeNormalize(args ...string) error {
 	cmd := NewRootCommand()
 	cmd.SetArgs(append([]string{"normalize"}, args...))
 	return cmd.Execute()
 }
+
+type normalizeAudit struct {
+	Command                string   `json:"command"`
+	InputFile              string   `json:"input_file"`
+	OutputFile             string   `json:"output_file"`
+	InputShape             string   `json:"input_shape"`
+	InputSegmentCount      int      `json:"input_segment_count"`
+	OutputSchema           string   `json:"output_schema"`
+	OutputModules          []string `json:"output_modules"`
+	IDsReassigned          bool     `json:"ids_reassigned"`
+	SortingChangedInput    bool     `json:"sorting_changed_input_order"`
+	SegmentsWithCategories int      `json:"segments_with_categories"`
+}
+
+func extractNormalizeAudit(t *testing.T, rpt report.Report) normalizeAudit {
+	t.Helper()
+	for _, event := range rpt.Events {
+		if event.Stage == "normalize" && event.Module == "normalize-audit" {
+			var audit normalizeAudit
+			if err := json.Unmarshal([]byte(event.Message), &audit); err != nil {
+				t.Fatalf("decode normalize audit: %v", err)
+			}
+			return audit
+		}
+	}
+	t.Fatalf("missing normalize-audit event: %#v", rpt.Events)
+	return normalizeAudit{}
+}