khosra/internal/content/content_test.go

package content

import (
	"io/fs"
	"os"
	"path/filepath"
	"testing"
	"testing/fstest"
)

func TestSplitNameDerivesKeyAndLang(t *testing.T) {
	cases := []struct {
		name, key, lang string
		ok              bool
	}{
		{name: "pages/about.md", key: "pages/about", lang: "en", ok: true},
		{name: "pages/about.en.md", key: "pages/about", lang: "en", ok: true},
		{name: "pages/about.bn.md", key: "pages/about", lang: "bn", ok: true},
		{name: "posts/hello/index.md", key: "posts/hello", lang: "en", ok: true},
		{name: "posts/hello/index.bn.md", key: "posts/hello", lang: "bn", ok: true},
		{name: "comics/monsoon/_index.md", key: "comics/monsoon", lang: "en", ok: true},
		{name: "posts/my.post.md", key: "posts/my.post", lang: "en", ok: true},
		{name: "posts/notes.txt", ok: false},
	}
	for _, c := range cases {
		key, lang, ok := splitName(c.name)
		if ok != c.ok {
			t.Errorf("%s: ok = %v, want %v", c.name, ok, c.ok)
			continue
		}
		if ok && (key != c.key || lang != c.lang) {
			t.Errorf("%s: got %q/%q, want %q/%q", c.name, key, lang, c.key, c.lang)
		}
	}
}

func TestParseSplitsFrontmatterAndKeepsUnknownKeys(t *testing.T) {
	b, err := Parse("posts/hello.md", []byte("---\ntitle: Hello\nmood: cheerful\ntags: [a, b]\n---\n\nBody text.\n"))
	if err != nil {
		t.Fatal(err)
	}
	if b.Title != "Hello" {
		t.Errorf("title = %q", b.Title)
	}
	if got := string(b.Body); got != "Body text.\n" {
		t.Errorf("body = %q", got)
	}
	if b.Extra["mood"] != "cheerful" {
		t.Error("an unnamed frontmatter key did not land in Extra")
	}
	if len(b.Tags) != 2 || b.Tags[0] != "a" {
		t.Errorf("tags = %v, want [a b] lifted into the named field", b.Tags)
	}
	if _, leaked := b.Extra["tags"]; leaked {
		t.Error("tags should be lifted out of Extra, not duplicated")
	}
	if _, ok := b.Extra["title"]; ok {
		t.Error("title should be lifted out of Extra, not duplicated")
	}
}

func TestParseWithoutFrontmatterIsAllBody(t *testing.T) {
	b, err := Parse("pages/now.md", []byte("Just prose.\n"))
	if err != nil {
		t.Fatal(err)
	}
	if b.Title != "" || string(b.Body) != "Just prose.\n" {
		t.Errorf("got title %q body %q", b.Title, b.Body)
	}
}

func TestParseRejectsBrokenFrontmatter(t *testing.T) {
	if _, err := Parse("posts/bad.md", []byte("---\ntitle: [unclosed\n---\nbody\n")); err == nil {
		t.Fatal("want an error for unparseable YAML")
	}
}

func TestParseMissingTitleIsLegal(t *testing.T) {
	b, err := Parse("status/note.md", []byte("---\ndate: 2026-07-30\n---\nhi\n"))
	if err != nil {
		t.Fatalf("a titleless bundle must parse: %v", err)
	}
	if b.Title != "" {
		t.Errorf("title = %q, want empty", b.Title)
	}
}

func TestScanSkipsBadBundlesAndUnderscoreDirs(t *testing.T) {
	fsys := fstest.MapFS{
		"content/pages/about.md":       {Data: []byte("---\ntitle: About\n---\nx\n")},
		"content/posts/hello/index.md": {Data: []byte("---\ntitle: Hello\n---\ny\n")},
		"content/posts/broken.md":      {Data: []byte("---\ntitle: [oops\n---\nz\n")},
		"content/_drafts/secret.md":    {Data: []byte("---\ntitle: Secret\n---\nq\n")},
		"content/pages/notes.txt":      {Data: []byte("not markdown")},
	}
	got, err := Scan(fsys)
	if err != nil {
		t.Fatal(err)
	}
	keys := map[string]bool{}
	for _, b := range got {
		keys[b.Key] = true
	}
	if len(got) != 2 || !keys["pages/about"] || !keys["posts/hello"] {
		t.Fatalf("got %d bundles %v, want pages/about and posts/hello only", len(got), keys)
	}
}

func TestScanDropsAmbiguousVariants(t *testing.T) {
	fsys := fstest.MapFS{
		"content/pages/about.md":    {Data: []byte("---\ntitle: A\n---\n")},
		"content/pages/about.en.md": {Data: []byte("---\ntitle: B\n---\n")},
		"content/pages/now.md":      {Data: []byte("---\ntitle: Now\n---\n")},
	}
	got, err := Scan(fsys)
	if err != nil {
		t.Fatal(err)
	}
	if len(got) != 1 || got[0].Key != "pages/now" {
		t.Fatalf("got %+v, want only pages/now: two spellings of one variant are ambiguous", got)
	}
}

func TestNormaliseFoldsDecomposedBengali(t *testing.T) {
	decomposed := "\u0995\u09c7\u09be" // ka + vowel sign e + vowel sign aa
	composed := "\u0995\u09cb"         // ka + vowel sign o
	if decomposed == composed {
		t.Skip("inputs are already identical; nothing to prove")
	}
	if Normalise(decomposed) != composed {
		t.Errorf("NFC(%q) = %q, want %q", decomposed, Normalise(decomposed), composed)
	}
}

// TestOpenSiteRefusesSymlinkEscape is the path-traversal guard's evidence: os.DirFS would happily
// follow this symlink, os.Root does not (ADR-0031).
func TestOpenSiteRefusesSymlinkEscape(t *testing.T) {
	tmp := t.TempDir()
	site := filepath.Join(tmp, "site")
	if err := os.MkdirAll(filepath.Join(site, "content"), 0o755); err != nil {
		t.Fatal(err)
	}
	secret := filepath.Join(tmp, "secret.txt")
	if err := os.WriteFile(secret, []byte("private"), 0o600); err != nil {
		t.Fatal(err)
	}
	if err := os.Symlink("../secret.txt", filepath.Join(site, "escape.txt")); err != nil {
		t.Skipf("symlinks unavailable: %v", err)
	}

	fsys, err := OpenSite(site)
	if err != nil {
		t.Fatal(err)
	}
	if data, err := fs.ReadFile(fsys, "escape.txt"); err == nil {
		t.Fatalf("read outside the site root succeeded with %q", data)
	}
	if _, err := fs.ReadFile(fsys, "../secret.txt"); err == nil {
		t.Fatal("traversal with .. succeeded")
	}
}

func TestSiteLookupFindsDefaultVariant(t *testing.T) {
	fsys := fstest.MapFS{
		"content/pages/about.md":    {Data: []byte("---\ntitle: About\n---\nhi\n")},
		"content/pages/about.bn.md": {Data: []byte("---\ntitle: পরিচিতি\n---\nহাই\n")},
	}
	bundles, err := Scan(fsys)
	if err != nil {
		t.Fatal(err)
	}
	site := NewSite(bundles)
	if site.Len() != 2 {
		t.Fatalf("indexed %d bundles, want 2", site.Len())
	}
	b, served, ok := site.Lookup("pages/about", "en")
	if !ok || b.Title != "About" || served != "en" {
		t.Fatalf("Lookup gave %+v %q %v, want the English variant", b, served, ok)
	}
	if _, _, ok := site.Lookup("pages/missing", "en"); ok {
		t.Error("Lookup invented a bundle")
	}
}

func TestLookupFallsBackThroughLanguages(t *testing.T) {
	fsys := fstest.MapFS{
		"content/pages/about.md":    {Data: []byte("---\ntitle: About\n---\n")},
		"content/pages/about.bn.md": {Data: []byte("---\ntitle: পরিচিতি\n---\n")},
		"content/posts/only.bn.md":  {Data: []byte("---\ntitle: শুধু\n---\n")},
		"content/posts/plain.md":    {Data: []byte("---\ntitle: Plain\n---\n")},
	}
	bundles, err := Scan(fsys)
	if err != nil {
		t.Fatal(err)
	}
	site := NewSite(bundles)
	cases := []struct{ key, want, served string }{
		{"pages/about", "পরিচিতি", "bn"}, // the requested language exists
		{"posts/plain", "Plain", "en"},   // falls back to the default
		{"posts/only", "শুধু", "bn"},     // no default either: any variant beats a 404
	}
	for _, c := range cases {
		b, served, ok := site.Lookup(c.key, "bn")
		if !ok || b.Title != c.want || served != c.served {
			t.Errorf("Lookup(%q, bn) = %q/%q ok=%v, want %q/%q", c.key, b.Title, served, ok, c.want, c.served)
		}
	}
	if got := site.Variants("pages/about"); len(got) != 2 || got[0] != "bn" || got[1] != "en" {
		t.Errorf("Variants = %v, want [bn en]", got)
	}
	if !site.HasLang("bn") || site.HasLang("fr") {
		t.Error("HasLang misreported")
	}
}

func TestURLPrefixesOnlyNonDefaultLanguages(t *testing.T) {
	cases := map[string]string{"en": "/pages/about/", "": "/pages/about/", "bn": "/bn/pages/about/"}
	for lang, want := range cases {
		if got := URL("pages/about", lang); got != want {
			t.Errorf("URL(pages/about, %q) = %q, want %q", lang, got, want)
		}
	}
}

func TestAliasesAreParsedAndIndexed(t *testing.T) {
	fsys := fstest.MapFS{
		"content/posts/new-name.md": {Data: []byte("---\ntitle: New\naliases: [/posts/old-name/, posts/older]\n---\n")},
		"content/pages/single.md":   {Data: []byte("---\ntitle: Single\naliases: pages/one\n---\n")},
	}
	bundles, err := Scan(fsys)
	if err != nil {
		t.Fatal(err)
	}
	site := NewSite(bundles)
	for alias, want := range map[string]string{
		"posts/old-name": "posts/new-name",
		"posts/older":    "posts/new-name",
		"pages/one":      "pages/single",
	} {
		got, ok := site.Alias(alias)
		if !ok || got != want {
			t.Errorf("Alias(%q) = %q %v, want %q", alias, got, ok, want)
		}
	}
	for _, b := range bundles {
		if _, leaked := b.Extra["aliases"]; leaked {
			t.Error("aliases should be lifted out of Extra, not duplicated")
		}
	}
}

func TestAmbiguousAliasesAreDropped(t *testing.T) {
	fsys := fstest.MapFS{
		"content/pages/real.md": {Data: []byte("---\ntitle: Real\n---\n")},
		"content/pages/a.md":    {Data: []byte("---\ntitle: A\naliases: [pages/real, pages/shared]\n---\n")},
		"content/pages/b.md":    {Data: []byte("---\ntitle: B\naliases: [pages/shared]\n---\n")},
	}
	site := NewSite(mustScan(t, fsys))
	if _, ok := site.Alias("pages/real"); ok {
		t.Error("an alias naming a real bundle must be dropped, not shadow it")
	}
	if _, ok := site.Alias("pages/shared"); ok {
		t.Error("an alias claimed by two bundles must be dropped, not picked arbitrarily")
	}
	if _, _, ok := site.Lookup("pages/real", "en"); !ok {
		t.Error("the real bundle must keep its URL")
	}
}

func mustScan(t *testing.T, fsys fstest.MapFS) []Bundle {
	t.Helper()
	b, err := Scan(fsys)
	if err != nil {
		t.Fatal(err)
	}
	return b
}

func TestTagSlugPreservesScriptAndFoldsCase(t *testing.T) {
	cases := map[string]string{
		"Long Monsoon":   "long-monsoon",
		"WATERCOLOUR":    "watercolour",
		"জলরঙ":           "জলরঙ",
		"  spaced  out ": "spaced-out",
	}
	for in, want := range cases {
		if got := TagSlug(in); got != want {
			t.Errorf("TagSlug(%q) = %q, want %q", in, got, want)
		}
	}
}

func TestQueryFiltersByTagAndSection(t *testing.T) {
	fsys := fstest.MapFS{
		"content/posts/a.md":   {Data: []byte("---\ntitle: A\ndate: 2026-01-03\ntags: [Monsoon, prose]\n---\n")},
		"content/posts/b.md":   {Data: []byte("---\ntitle: B\ndate: 2026-01-02\ntags: [prose]\n---\n")},
		"content/comics/c.md":  {Data: []byte("---\ntitle: C\ndate: 2026-01-01\ntags: [monsoon]\n---\n")},
		"content/writing/d.md": {Data: []byte("---\ntitle: D\n---\n")},
	}
	site := NewSite(mustScan(t, fsys))
	got := func(q Query) []string {
		var titles []string
		for _, b := range site.Run(q) {
			titles = append(titles, b.Title)
		}
		return titles
	}
	if titles := got(Query{Tag: "monsoon", Lang: "en"}); len(titles) != 2 || titles[0] != "A" || titles[1] != "C" {
		t.Errorf("global tag query = %v, want [A C] — a tag spans sections and case does not matter", titles)
	}
	if titles := got(Query{Section: "posts", Tag: "monsoon", Lang: "en"}); len(titles) != 1 || titles[0] != "A" {
		t.Errorf("section-narrowed tag query = %v, want [A]", titles)
	}
	if titles := got(Query{Tag: "nothing", Lang: "en"}); titles != nil {
		t.Errorf("unknown tag = %v, want none", titles)
	}
}