Implement artifact-level render command with Markdown output and update docs

2026-05-24 22:55:56 +00:00
parent a90859114a
commit c37ea70dcb
28 changed files with 1619 additions and 99 deletions
--- a/internal/cli/render.go
+++ b/internal/cli/render.go
@@ -0,0 +1,39 @@
+package cli
+
+import (
+	"github.com/spf13/cobra"
+
+	"gitea.maximumdirect.net/eric/seriatim/internal/config"
+	"gitea.maximumdirect.net/eric/seriatim/internal/render"
+)
+
+func newRenderCommand() *cobra.Command {
+	opts := config.RenderOptions{
+		Title:             config.DefaultRenderTitle,
+		IncludeTimestamps: true,
+	}
+
+	cmd := &cobra.Command{
+		Use:   "render",
+		Short: "Render a seriatim transcript artifact into human-readable output",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			cfg, err := config.NewRenderConfig(opts)
+			if err != nil {
+				return err
+			}
+
+			return render.Run(cmd.Context(), cfg)
+		},
+	}
+
+	flags := cmd.Flags()
+	flags.StringVar(&opts.InputFile, "input-file", "", "input seriatim transcript artifact JSON file")
+	flags.StringVar(&opts.OutputFile, "output-file", "", "rendered output file path")
+	flags.StringVar(&opts.Format, "format", "", "output format (markdown)")
+	flags.StringVar(&opts.Title, "title", config.DefaultRenderTitle, "document title")
+	flags.BoolVar(&opts.IncludeTimestamps, "include-timestamps", true, "include segment timestamps")
+	flags.BoolVar(&opts.IncludeSegmentIDs, "include-segment-ids", false, "include segment IDs")
+	flags.BoolVar(&opts.IncludeMetadata, "include-metadata", false, "include artifact metadata")
+
+	return cmd
+}
--- a/internal/cli/render_test.go
+++ b/internal/cli/render_test.go
@@ -0,0 +1,208 @@
+package cli
+
+import (
+	"bytes"
+	"os"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/seriatim/internal/config"
+)
+
+func TestRenderCommandIsRecognized(t *testing.T) {
+	cmd := NewRootCommand()
+	cmd.SetArgs([]string{"render", "--help"})
+	if err := cmd.Execute(); err != nil {
+		t.Fatalf("render command should be recognized: %v", err)
+	}
+}
+
+func TestRootHelpIncludesRender(t *testing.T) {
+	cmd := NewRootCommand()
+	var out bytes.Buffer
+	cmd.SetOut(&out)
+	cmd.SetErr(&out)
+	cmd.SetArgs([]string{"--help"})
+	if err := cmd.Execute(); err != nil {
+		t.Fatalf("help failed: %v", err)
+	}
+	if !strings.Contains(out.String(), "render") {
+		t.Fatalf("root help missing render command:\n%s", out.String())
+	}
+}
+
+func TestRenderEndToEndMarkdownOutput(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{
+		"metadata": {
+			"application": "seriatim",
+			"version": "v-test",
+			"output_schema": "seriatim-intermediate"
+		},
+		"segments": [
+			{"id": 1, "start": 1, "end": 4, "speaker": "Eric", "text": "Hello there."},
+			{"id": 2, "start": 5, "end": 8, "speaker": "Mike", "text": "Yeah.", "categories": ["backchannel"]}
+		]
+	}`)
+	output := writeJSONFile(t, dir, "output.md", "")
+
+	err := executeRender(
+		"--input-file", input,
+		"--output-file", output,
+		"--format", config.RenderFormatMarkdown,
+		"--title", "Transcript",
+	)
+	if err != nil {
+		t.Fatalf("render failed: %v", err)
+	}
+
+	data := readFile(t, output)
+	if !strings.Contains(data, "# Transcript") {
+		t.Fatalf("missing title:\n%s", data)
+	}
+	if !strings.Contains(data, "[00:00:01–00:00:04] **Eric:** Hello there.") {
+		t.Fatalf("missing first segment:\n%s", data)
+	}
+	if !strings.Contains(data, "[00:00:05–00:00:08] **Mike:** *Yeah.*") {
+		t.Fatalf("missing italicized backchannel segment:\n%s", data)
+	}
+}
+
+func TestRenderRejectsUnsupportedFormat(t *testing.T) {
+	dir := t.TempDir()
+	input := writeJSONFile(t, dir, "input.json", `{"metadata":{"application":"seriatim","version":"v-test","output_schema":"seriatim-minimal"},"segments":[]}`)
+	output := writeJSONFile(t, dir, "output.md", "")
+
+	err := executeRender(
+		"--input-file", input,
+		"--output-file", output,
+		"--format", "txt",
+	)
+	if err == nil {
+		t.Fatal("expected format error")
+	}
+	if !strings.Contains(err.Error(), "--format must be") {
+		t.Fatalf("unexpected error: %v", err)
+	}
+}
+
+func TestRenderRejectsMalformedAndRawInput(t *testing.T) {
+	dir := t.TempDir()
+	output := writeJSONFile(t, dir, "output.md", "")
+
+	malformed := writeJSONFile(t, dir, "malformed.json", `{"metadata":`)
+	err := executeRender(
+		"--input-file", malformed,
+		"--output-file", output,
+		"--format", config.RenderFormatMarkdown,
+	)
+	if err == nil {
+		t.Fatal("expected malformed input error")
+	}
+	if !strings.Contains(err.Error(), "input JSON is malformed") {
+		t.Fatalf("unexpected malformed input error: %v", err)
+	}
+
+	raw := writeJSONFile(t, dir, "raw.json", `{"segments":[{"id":0,"start":0.1,"end":1.1,"text":"hello","words":[{"word":"hello"}]}]}`)
+	err = executeRender(
+		"--input-file", raw,
+		"--output-file", output,
+		"--format", config.RenderFormatMarkdown,
+	)
+	if err == nil {
+		t.Fatal("expected artifact validation error")
+	}
+	if !strings.Contains(err.Error(), "not a valid seriatim output artifact") {
+		t.Fatalf("unexpected raw input error: %v", err)
+	}
+}
+
+func TestRenderSupportsMinimalIntermediateAndFullInputs(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+	}{
+		{
+			name: "minimal",
+			content: `{
+				"metadata": {
+					"application": "seriatim",
+					"version": "v-test",
+					"output_schema": "seriatim-minimal"
+				},
+				"segments": [{"id":1,"start":1,"end":2,"speaker":"A","text":"one"}]
+			}`,
+		},
+		{
+			name: "intermediate",
+			content: `{
+				"metadata": {
+					"application": "seriatim",
+					"version": "v-test",
+					"output_schema": "seriatim-intermediate"
+				},
+				"segments": [{"id":1,"start":1,"end":2,"speaker":"A","text":"one","categories":["filler"]}]
+			}`,
+		},
+		{
+			name: "full",
+			content: `{
+				"metadata": {
+					"application": "seriatim",
+					"version": "v-test",
+					"input_reader": "json-files",
+					"input_files": ["input.json"],
+					"preprocessing_modules": [],
+					"postprocessing_modules": [],
+					"output_modules": ["json"]
+				},
+				"segments": [{
+					"id":1,
+					"source":"input.json",
+					"source_segment_index":0,
+					"speaker":"A",
+					"start":1,
+					"end":2,
+					"text":"one"
+				}],
+				"overlap_groups": []
+			}`,
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			dir := t.TempDir()
+			input := writeJSONFile(t, dir, "input.json", test.content)
+			output := writeJSONFile(t, dir, "output.md", "")
+
+			err := executeRender(
+				"--input-file", input,
+				"--output-file", output,
+				"--format", config.RenderFormatMarkdown,
+			)
+			if err != nil {
+				t.Fatalf("render failed: %v", err)
+			}
+			data := readFile(t, output)
+			if !strings.Contains(data, "**A:**") {
+				t.Fatalf("missing rendered segment for %s input:\n%s", test.name, data)
+			}
+		})
+	}
+}
+
+func executeRender(args ...string) error {
+	cmd := NewRootCommand()
+	cmd.SetArgs(append([]string{"render"}, args...))
+	return cmd.Execute()
+}
+
+func readFile(t *testing.T, path string) string {
+	t.Helper()
+	data, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("read %s: %v", path, err)
+	}
+	return string(data)
+}
--- a/internal/cli/root.go
+++ b/internal/cli/root.go
@@ -10,7 +10,7 @@ import (
 func NewRootCommand() *cobra.Command {
 	cmd := &cobra.Command{
 		Use:           "seriatim",
-		Short:         "Merge, trim, and normalize transcript artifacts",
+		Short:         "Merge, trim, normalize, and render transcript artifacts",
 		Version:       buildinfo.Version,
 		SilenceErrors: true,
 		SilenceUsage:  true,
@@ -18,6 +18,7 @@ func NewRootCommand() *cobra.Command {

 	cmd.AddCommand(newMergeCommand())
 	cmd.AddCommand(newNormalizeCommand())
+	cmd.AddCommand(newRenderCommand())
 	cmd.AddCommand(newTrimCommand())
 	return cmd
 }