feat: HTML sitemap groups API

- GET /_sitemap/api/v1/html?locale= answers the overview: the listed
  addresses of the XML sitemaps by group, in the order pages, offers,
  services, categories (as a tree), posts (newest first), tags, authors,
  other content types, each with its title in the locale, total, the
  first html_page_size links and more
- GET /_sitemap/api/v1/html/{group}?locale=&page= answers one page of a
  group; past the last page, an unknown group or the HTML sitemap off
  answer 404; every answer is noindex; per-IP bucket sitemap-html
- the HTML sitemap tab: html_enabled, the address per locale (html_paths)
  and html_page_size 50 to 500, with errors.html_path and errors.page_size
- contract.Listing.Settings answers HTMLEnabled, HTMLPaths, HTMLPageSize
  and KeyFile

models/settings.go

@@ -92,7 +92,7 @@ func (Settings) TableName() string { return "golem15_sitemap_settings" }
 
 // Fillable lists the columns the settings form edits.
 func (Settings) Fillable() []string {
-	return []string{"site_url", "file_size", "extra_urls", "images_enabled", "news_enabled", "news_publication", "news_sources", "indexnow_enabled"}
+	return []string{"site_url", "file_size", "extra_urls", "images_enabled", "news_enabled", "news_publication", "news_sources", "indexnow_enabled", "html_enabled", "html_page_size"}
 }
 
 // Rules is empty: the settings controller runs Validate before a save.
@@ -105,6 +105,8 @@ const (
 	errLastmod   = "golem15.sitemap::lang.errors.lastmod"
 	errNewsName  = "golem15.sitemap::lang.errors.news_publication"
 	errNewsSrc   = "golem15.sitemap::lang.errors.news_source"
+	errHTMLPath  = "golem15.sitemap::lang.errors.html_path"
+	errPageSize  = "golem15.sitemap::lang.errors.page_size"
 )
 
 // MaxNewsPublication is the longest publication name.
@@ -128,7 +130,9 @@ func (s Settings) Validate() error {
 // Problems lists the settings' refusals by field (UI-SPEC C26): a site
 // address that AllowedFrontendURL refuses, a file size outside 1..MaxFileSize and an additional
 // address that is not a path or an http(s) URL (extra_urls.<i>.url) or
-// whose lastmod is not a date (extra_urls.<i>.lastmod).
+// whose lastmod is not a date (extra_urls.<i>.lastmod), a publication name
+// over 255 characters, a malformed News source, an HTML sitemap address
+// that ValidHTMLPath refuses (html_path) and a page size outside 50..500.
 func (s Settings) Problems() map[string][]string {
 	out := map[string][]string{}
 	if !AllowedFrontendURL(Text(s.SiteURL)) {
@@ -154,9 +158,42 @@ func (s Settings) Problems() map[string][]string {
 			break
 		}
 	}
+	for _, p := range s.HTMLPaths.Get() {
+		if p = strings.TrimSpace(p); p != "" && !ValidHTMLPath(p) {
+			out["html_path"] = []string{errHTMLPath}
+			break
+		}
+	}
+	if s.HTMLPageSize < MinHTMLPageSize || s.HTMLPageSize > MaxHTMLPageSize {
+		out["html_page_size"] = []string{errPageSize}
+	}
 	return out
 }
 
+// HTMLPathProblem is the refusal of an HTML sitemap address (errors.html_path).
+const HTMLPathProblem = errHTMLPath
+
+// ValidHTMLPath reports whether p may be the HTML sitemap's address: a
+// path that starts with a single /, at most 255 characters of letters,
+// digits and - _ . ~ / (no query, fragment, "//" or ".." segment), and not
+// the site root.
+func ValidHTMLPath(p string) bool {
+	if len(p) < 2 || len(p) > 255 || p[0] != '/' || strings.Contains(p, "//") {
+		return false
+	}
+	for _, seg := range strings.Split(p[1:], "/") {
+		if seg == "." || seg == ".." {
+			return false
+		}
+	}
+	for _, r := range p {
+		if !(r >= 'a' && r <= 'z' || r >= 'A' && r <= 'Z' || r >= '0' && r <= '9' || strings.ContainsRune("-_.~/", r)) {
+			return false
+		}
+	}
+	return true
+}
+
 // The prefixes of the news_sources values (P33-15): type:<type key> and
 // category:<type key>:<id>.
 const (

models/settings/fields.yaml

@@ -127,3 +127,21 @@ fields:
             action: hide
             field: indexnow_enabled
             condition: unchecked
+
+    # The address per locale (html_path, an mltext field) is added after
+    # this switch by the plugin's form extension, stored in html_paths.
+    html_enabled:
+        label: golem15.sitemap::lang.settings.html_enabled
+        comment: golem15.sitemap::lang.settings.html_enabled_comment
+        type: switch
+        default: true
+        span: full
+        tab: golem15.sitemap::lang.settings.tab_html
+
+    html_page_size:
+        label: golem15.sitemap::lang.settings.html_page_size
+        comment: golem15.sitemap::lang.settings.html_page_size_comment
+        type: number
+        default: 150
+        span: right
+        tab: golem15.sitemap::lang.settings.tab_html

models/settings_test.go

@@ -75,6 +75,9 @@ func TestSettingsValidate(t *testing.T) {
 		if s.FileSize == 0 {
 			s.FileSize = 1000
 		}
+		if s.HTMLPageSize == 0 {
+			s.HTMLPageSize = models.DefaultHTMLPageSize
+		}
 		return s
 	}
 	extra := func(urls ...string) lagoon.Jsonable[[]models.ExtraURL] {
@@ -88,8 +91,8 @@ func TestSettingsValidate(t *testing.T) {
 		"null site_url":    ok(models.Settings{}),
 		"empty site_url":   ok(models.Settings{SiteURL: text("")}),
 		"site_url":         ok(models.Settings{SiteURL: text("https://www.ex.pl/")}),
-		"file size 1":      {FileSize: 1},
-		"file size 50 000": {FileSize: 50000},
+		"file size 1":      ok(models.Settings{FileSize: 1}),
+		"file size 50 000": ok(models.Settings{FileSize: 50000}),
 		"extra addresses":  ok(models.Settings{ExtraURLs: extra("/", "/o-nas?x=1&y=2", "https://www.ex.pl/kontakt")}),
 	} {
 		if err := s.Validate(); err != nil {
@@ -103,8 +106,8 @@ func TestSettingsValidate(t *testing.T) {
 		"javascript site_url":  {ok(models.Settings{SiteURL: text("javascript:alert(document.domain)//")}), map[string]any{"site_url": []string{"golem15.sitemap::lang.errors.frontend_url"}}},
 		"attribute site_url":   {ok(models.Settings{SiteURL: text(`https://x"/><y a="`)}), map[string]any{"site_url": []string{"golem15.sitemap::lang.errors.frontend_url"}}},
 		"path site_url":        {ok(models.Settings{SiteURL: text("/x")}), map[string]any{"site_url": []string{"golem15.sitemap::lang.errors.frontend_url"}}},
-		"file size 0":          {models.Settings{}, map[string]any{"file_size": []string{"golem15.sitemap::lang.errors.file_size"}}},
-		"file size 50 001":     {models.Settings{FileSize: 50001}, map[string]any{"file_size": []string{"golem15.sitemap::lang.errors.file_size"}}},
+		"file size 0":          {models.Settings{HTMLPageSize: 150}, map[string]any{"file_size": []string{"golem15.sitemap::lang.errors.file_size"}}},
+		"file size 50 001":     {models.Settings{FileSize: 50001, HTMLPageSize: 150}, map[string]any{"file_size": []string{"golem15.sitemap::lang.errors.file_size"}}},
 		"javascript address":   {ok(models.Settings{ExtraURLs: extra("/", "javascript:alert(1)")}), map[string]any{"extra_urls.1.url": []string{"golem15.sitemap::lang.errors.url_scheme"}}},
 		"protocol-relative":    {ok(models.Settings{ExtraURLs: extra("//evil.test/x")}), map[string]any{"extra_urls.0.url": []string{"golem15.sitemap::lang.errors.url_scheme"}}},
 		"address with a space": {ok(models.Settings{ExtraURLs: extra("/a b")}), map[string]any{"extra_urls.0.url": []string{"golem15.sitemap::lang.errors.url_scheme"}}},