Add Markdown HTML publication

This commit is contained in:
2026-05-31 02:28:48 +00:00
parent e296361042
commit 5408f14195
21 changed files with 628 additions and 47 deletions

View File

@@ -0,0 +1,57 @@
package markdown
import (
"bytes"
"context"
"fmt"
"strings"
"github.com/yuin/goldmark"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/transform"
)
type Transformer struct {
renderer goldmark.Markdown
}
func New() *Transformer {
return &Transformer{renderer: goldmark.New()}
}
func (t *Transformer) Generate(ctx context.Context, req transform.Request) ([]transform.Output, error) {
if t.renderer == nil {
t.renderer = goldmark.New()
}
var outputs []transform.Output
for _, file := range req.SourceBundle.Manifest.Files {
if !strings.HasSuffix(file.Path, ".md") {
continue
}
sourcePath, err := storage.Join(req.SourceBundle.RootRelativePath, file.Path)
if err != nil {
return nil, err
}
data, err := req.SourceBackend.ReadFile(ctx, sourcePath)
if err != nil {
return nil, fmt.Errorf("read markdown source %q: %w", file.Path, err)
}
var rendered bytes.Buffer
if err := t.renderer.Convert(data, &rendered); err != nil {
return nil, fmt.Errorf("render markdown source %q: %w", file.Path, err)
}
html := wrapHTML(rendered.Bytes())
outputPath := strings.TrimSuffix(file.Path, ".md") + ".html"
outputs = append(outputs, transform.Output{
Path: outputPath,
SourcePath: file.Path,
Transform: transform.MarkdownToHTML,
Data: html,
SHA256: bundle.FileDigest(html),
Size: int64(len(html)),
})
}
return outputs, nil
}

View File

@@ -0,0 +1,113 @@
package markdown
import (
"context"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
"gitea.maximumdirect.net/eric/distributor/internal/transform"
)
func TestGenerateMarkdownSidecar(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\nHello.\n")
outputs, err := New().Generate(context.Background(), transform.Request{SourceBackend: backend, SourceBundle: sourceBundle})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
if got, want := len(outputs), 1; got != want {
t.Fatalf("output count = %d, want %d", got, want)
}
output := outputs[0]
if output.Path != "report.html" {
t.Fatalf("path = %q, want report.html", output.Path)
}
if output.SourcePath != "report.md" || output.Transform != transform.MarkdownToHTML {
t.Fatalf("metadata = %#v", output)
}
html := string(output.Data)
for _, want := range []string{"<!doctype html>", "<h1>Title</h1>", "<p>Hello.</p>"} {
if !strings.Contains(html, want) {
t.Fatalf("html = %q, want substring %q", html, want)
}
}
if output.SHA256 != bundle.FileDigest(output.Data) || output.Size != int64(len(output.Data)) {
t.Fatalf("digest/size metadata = %s/%d", output.SHA256, output.Size)
}
}
func TestGenerateIgnoresNonMarkdown(t *testing.T) {
backend := fake.New()
if _, err := backend.WriteFile(context.Background(), "summary.txt", []byte("Summary\n"), storage.WriteOptions{}); err != nil {
t.Fatalf("WriteFile() error = %v", err)
}
sourceBundle := bundle.Bundle{Manifest: bundle.Manifest{
SchemaVersion: 1,
ID: "bundle",
Created: time.Date(2026, 5, 30, 11, 10, 0, 0, time.UTC),
Files: []bundle.ManifestFile{{Path: "summary.txt", SHA256: bundle.FileDigest([]byte("Summary\n")), Size: 8}},
}}
outputs, err := New().Generate(context.Background(), transform.Request{SourceBackend: backend, SourceBundle: sourceBundle})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
if len(outputs) != 0 {
t.Fatalf("outputs = %#v, want none", outputs)
}
}
func TestGenerateDoesNotPassRawHTML(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\n<script>alert('x')</script>\n")
outputs, err := New().Generate(context.Background(), transform.Request{SourceBackend: backend, SourceBundle: sourceBundle})
if err != nil {
t.Fatalf("Generate() error = %v", err)
}
html := string(outputs[0].Data)
if strings.Contains(html, "<script>") {
t.Fatalf("html contains raw script: %q", html)
}
if !strings.Contains(html, "raw HTML omitted") && !strings.Contains(html, "&lt;script&gt;") {
t.Fatalf("html = %q, want raw HTML disabled or escaped", html)
}
}
func TestGenerateDeterministicOutput(t *testing.T) {
backend, sourceBundle := markdownFixture(t, "# Title\n\nHello.\n")
first, err := New().Generate(context.Background(), transform.Request{SourceBackend: backend, SourceBundle: sourceBundle})
if err != nil {
t.Fatalf("first Generate() error = %v", err)
}
second, err := New().Generate(context.Background(), transform.Request{SourceBackend: backend, SourceBundle: sourceBundle})
if err != nil {
t.Fatalf("second Generate() error = %v", err)
}
if string(first[0].Data) != string(second[0].Data) {
t.Fatalf("outputs differ:\n%s\n%s", first[0].Data, second[0].Data)
}
}
func markdownFixture(t *testing.T, markdown string) (*fake.Backend, bundle.Bundle) {
t.Helper()
backend := fake.New()
if _, err := backend.WriteFile(context.Background(), "report.md", []byte(markdown), storage.WriteOptions{}); err != nil {
t.Fatalf("WriteFile() error = %v", err)
}
if _, err := backend.WriteFile(context.Background(), "summary.txt", []byte("Summary\n"), storage.WriteOptions{}); err != nil {
t.Fatalf("WriteFile() error = %v", err)
}
files := []bundle.ManifestFile{
{Path: "report.md", SHA256: bundle.FileDigest([]byte(markdown)), Size: int64(len(markdown))},
{Path: "summary.txt", SHA256: bundle.FileDigest([]byte("Summary\n")), Size: 8},
}
manifest := bundle.Manifest{
SchemaVersion: 1,
ID: "bundle",
Created: time.Date(2026, 5, 30, 11, 10, 0, 0, time.UTC),
Files: files,
}
manifest.Digest = bundle.BundleDigest(manifest.Files)
return backend, bundle.Bundle{Manifest: manifest}
}

View File

@@ -0,0 +1,11 @@
package markdown
import "bytes"
func wrapHTML(body []byte) []byte {
var buf bytes.Buffer
buf.WriteString("<!doctype html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<title></title>\n</head>\n<body>\n")
buf.Write(body)
buf.WriteString("</body>\n</html>\n")
return buf.Bytes()
}

View File

@@ -0,0 +1,3 @@
package transform
const MarkdownToHTML = "markdown_to_html"

View File

@@ -0,0 +1,30 @@
package transform
import "fmt"
type Registry struct {
transformers map[string]Transformer
}
func NewRegistry() *Registry {
return &Registry{transformers: make(map[string]Transformer)}
}
func (r *Registry) Register(name string, transformer Transformer) error {
if name == "" {
return fmt.Errorf("transform name is required")
}
if transformer == nil {
return fmt.Errorf("transformer %s is nil", name)
}
if _, exists := r.transformers[name]; exists {
return fmt.Errorf("transform %s is already registered", name)
}
r.transformers[name] = transformer
return nil
}
func (r *Registry) Get(name string) (Transformer, bool) {
transformer, ok := r.transformers[name]
return transformer, ok
}

View File

@@ -0,0 +1,26 @@
package transform
import (
"context"
"gitea.maximumdirect.net/eric/distributor/internal/bundle"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
)
type Output struct {
Path string
SourcePath string
Transform string
Data []byte
SHA256 string
Size int64
}
type Request struct {
SourceBundle bundle.Bundle
SourceBackend storage.Backend
}
type Transformer interface {
Generate(ctx context.Context, req Request) ([]Output, error)
}