Im/sitemap (#4332)

* WIP

Signed-off-by: Ian Maddaus <[email protected]>

* Additional sitemap-main layout updates

Signed-off-by: Ian Maddaus <[email protected]>

* Update main sitemap layout

Signed-off-by: Ian Maddaus <[email protected]>

* Update sitemaps param

Signed-off-by: Ian Maddaus <[email protected]>

---------

Signed-off-by: Ian Maddaus <[email protected]>

Author: IanMadd

config/_default/params.toml

@@ -17,9 +17,20 @@ menuOrder = [
   "legacy",
   "extra"
 ]
+
 enable_search = true
 robots = ''
 
+# sitemaps lists sitemaps that are indexed by the main sitemap layout.
+# see:
+# - layouts/_default/sitemap.xml
+# - layouts/_default/home.sitemap-main.xml
+
+sitemaps = [
+  "https://docs.chef.io/sitemap-main.xml",
+  "https://docs.chef.io/360/1.0/sitemap.xml"
+]
+
 [chef-web-docs]
   gh_path = "https://github.com/chef/chef-web-docs/blob/main/content/"
 

generated/config.toml

@@ -1,6 +1,6 @@
 ## Config file for generated dir.
 
-disableKinds = [ "sitemap", "taxonomy", "term", "RSS", "sitemap"]
+disableKinds = [ "sitemap", "taxonomy", "term", "RSS"]
 publishDir = "generated_content"
 
 [module]

hugo.toml

@@ -7,24 +7,34 @@ pluralizeListTitles = false
 disableKinds = ["taxonomy", "term"]
 configDir = "config"
 
-# We do redirects using Netlify's _redirects file, generated by Hugo (see "outputs" below).
 disableAliases = true
 # Summary length
 summaryLength = 20
+
+# We do redirects using Netlify's _redirects file, generated by Hugo.
+# See the REDIR output and output format and the text/netlify mediatype.
 [outputs]
-home = [ "HTML", "RSS", "REDIR" ]
-section = [ "HTML", "RSS" ]
+  home = [ "HTML", "RSS", "REDIR", "SITEMAP-MAIN" ]
+  section = [ "HTML", "RSS" ]
 
 [mediaTypes]
-[mediaTypes."text/netlify"]
-delimiter = ""
+  [mediaTypes."text/netlify"]
+    delimiter = ""
 
 [outputFormats]
-[outputFormats.REDIR]
-mediatype = "text/netlify"
-baseName = "_redirects"
-isPlainText = true
-notAlternative = true
+  [outputFormats.REDIR]
+    mediatype = "text/netlify"
+    baseName = "_redirects"
+    isPlainText = true
+    notAlternative = true
+
+  [outputFormats.SITEMAP-MAIN]
+    MediaType = "application/xml"
+    BaseName = "sitemap-main"
+    IsHTML = false
+    IsPlainText = true
+    Rel = "sitemap"
+    protocol = "xml://"
 
 [markup]
   [markup.goldmark]

layouts/_default/home.sitemap-main.xml

@@ -0,0 +1,26 @@
+{{  printf "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\" ?>" | safeHTML }}
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
+  xmlns:xhtml="http://www.w3.org/1999/xhtml">
+{{ range .Site.Pages }}
+  {{- if or (eq (isset .Params "sitemapexclude") false) (ne .Params.sitemapExclude true) }}
+    <url>
+      <loc>{{ .Permalink }}</loc>{{ if not .Lastmod.IsZero }}
+      <lastmod>{{ safeHTML ( .Lastmod.Format "2006-01-02T15:04:05-07:00" ) }}</lastmod>{{ end }}{{ with .Sitemap.ChangeFreq }}
+      <changefreq>{{ . }}</changefreq>{{ end }}{{ if ge .Sitemap.Priority 0.0 }}
+      <priority>{{ .Sitemap.Priority }}</priority>{{ end }}{{ if .IsTranslated }}{{ range .Translations }}
+      <xhtml:link
+                  rel="alternate"
+                  hreflang="{{ .Language.Lang }}"
+                  href="{{ .Permalink }}"
+                  />{{ end }}
+      <xhtml:link
+                  rel="alternate"
+                  hreflang="{{ .Language.Lang }}"
+                  href="{{ .Permalink }}"
+                  />{{ end }}
+    </url>
+  {{- end }}
+{{  end }}
+</urlset>
+
+<!-- From https://dereckcurry.com/posts/excluding-pages-from-the-sitemap/ -->

layouts/_default/sitemap.xml

@@ -0,0 +1,11 @@
+{{ printf "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\"?>" | safeHTML }}
+<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+{{- range .Site.Params.sitemaps }}
+  <sitemap>
+    <loc>{{ . }}</loc>
+  </sitemap>
+{{ end -}}
+</sitemapindex>
+
+<!-- https://developers.google.com/search/docs/crawling-indexing/sitemaps/large-sitemaps -->
+<!-- https://swiftype.com/documentation/site-search/crawler-configuration/sitemap -->