serve robots.txt and sitemap.xml

Two exact paths a crawler asks for by name, so they are mux entries rather than
resolver cases — no bundle can collide, since a key always sits under a section.

robots.txt at the site root is served verbatim, because a site that ships one has
said something deliberate; otherwise the engine emits the minimum that is true and
points at the sitemap. The sitemap lists every bundle in every language it exists
in, since each variant is separately reachable, with lastmod only where a bundle
has a date. Every URL comes from content.URL like every other path the engine
emits, so a sitemap cannot disagree with what is actually served.

Both need a declared base. Without one the sitemap answers 404 rather than listing
paths no crawler can resolve, and robots omits the Sitemap line rather than
writing a relative one.

write() was setting text/html for every caller, and headers only go out with the
first byte — so a handler setting its own type would have had it silently replaced,
which is how a sitemap gets served as a web page. It now splits into write and
writeAs, and the tests assert the content types rather than only the bodies.

internal/render/render_test.go

@@ -9,7 +9,7 @@ import (
 )
 
 func TestBundleRendersMarkdownIntoTheTheme(t *testing.T) {
-	r, err := New(nil, nil)
+	r, err := New(nil, content.Settings{}, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -33,7 +33,7 @@ func TestBundleRendersMarkdownIntoTheTheme(t *testing.T) {
 }
 
 func TestBundleWithoutTitleFallsBackToKey(t *testing.T) {
-	r, err := New(nil, nil)
+	r, err := New(nil, content.Settings{}, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -54,7 +54,7 @@ func TestSiteOverridesOneBlockAndInheritsTheRest(t *testing.T) {
 	siteFS := fstest.MapFS{
 		"templates/page.html": {Data: []byte(`{{define "main"}}<section class="mine">{{.Title}}</section>{{end}}`)},
 	}
-	r, err := New(siteFS, nil)
+	r, err := New(siteFS, content.Settings{}, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -82,7 +82,7 @@ func TestAListingOverrideDoesNotLeakIntoBundlePages(t *testing.T) {
 	siteFS := fstest.MapFS{
 		"templates/list.html": {Data: []byte(`{{define "main"}}LISTING ONLY{{end}}`)},
 	}
-	r, err := New(siteFS, nil)
+	r, err := New(siteFS, content.Settings{}, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -101,7 +101,7 @@ func TestAListingOverrideDoesNotLeakIntoBundlePages(t *testing.T) {
 
 func TestSiteStylesheetReplacesTheReferenceOne(t *testing.T) {
 	siteFS := fstest.MapFS{"templates/theme.css": {Data: []byte("body{color:rebeccapurple}")}}
-	r, err := New(siteFS, nil)
+	r, err := New(siteFS, content.Settings{}, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -114,3 +114,50 @@ func TestSiteStylesheetReplacesTheReferenceOne(t *testing.T) {
 		t.Error("the site stylesheet should replace the reference one")
 	}
 }
+
+func TestADeclaredBaseMakesMachineReadableURLsAbsolute(t *testing.T) {
+	// A canonical link and an hreflang are read by machines that resolve neither against the page, so both
+	// go absolute as soon as the site says where it lives (ADR-0039).
+	r, err := New(nil, content.Settings{Base: "https://khosra.example", Title: "Khosra"}, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	b, err := content.Parse("posts/hello.md", []byte("---\ntitle: Hello\n---\nhi\n"))
+	if err != nil {
+		t.Fatal(err)
+	}
+	out, err := r.Bundle(b, "en", []string{"en", "bn"}, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	got := string(out)
+	for _, want := range []string{
+		`rel="canonical" href="https://khosra.example/posts/hello/"`,
+		`hreflang="bn" href="https://khosra.example/bn/posts/hello/"`,
+		`property="og:url" content="https://khosra.example/posts/hello/"`,
+		`<title>Hello · Khosra</title>`,
+	} {
+		if !strings.Contains(got, want) {
+			t.Errorf("missing %q:\n%s", want, got)
+		}
+	}
+}
+
+func TestWithoutABaseEverythingStaysRelative(t *testing.T) {
+	r, err := New(nil, content.Settings{}, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	b, _ := content.Parse("posts/hello.md", []byte("---\ntitle: Hello\n---\nhi\n"))
+	out, err := r.Bundle(b, "en", []string{"en"}, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	got := string(out)
+	if !strings.Contains(got, `rel="canonical" href="/posts/hello/"`) {
+		t.Errorf("a site that declared no base still links to itself:\n%s", got)
+	}
+	if strings.Contains(got, "og:site_name") {
+		t.Error("no declared title means no site_name tag, rather than an empty one")
+	}
+}