Generate sitemap.xml

Gemfile

@@ -141,6 +141,5 @@ gem 'prawn'
 gem 'prawn-svg', '~> 0.35'
 
 gem 'carrierwave-aws', '~> 1.6'
-gem 'sitemap_generator', '~> 7.1'
 
 gem 'solid_cache', '~> 1.0'

Gemfile.lock

@@ -551,8 +551,6 @@ GEM
       activemodel (>= 7.0)
     simplecov (1.1.1)
     simplecov-lcov (0.9.0)
-    sitemap_generator (7.1.1)
-      builder (~> 3.0)
     slop (3.6.0)
     snaky_hash (2.0.6)
       hashie (>= 0.1.0, < 6)
@@ -710,7 +708,6 @@ DEPENDENCIES
   simple_form
   simplecov
   simplecov-lcov
-  sitemap_generator (~> 7.1)
   solid_cache (~> 1.0)
   sprockets-rails
   stimulus-rails
@@ -930,7 +927,6 @@ CHECKSUMS
   simple_form (5.4.1) sha256=58c3d229034c7e5545035c3271b6f030ef730c340b9d7d8eb730e0a385b20808
   simplecov (1.1.1) sha256=25825ef13f0b2e74694d769817dad6ab8e90131dabdaa666e522fea105521e78
   simplecov-lcov (0.9.0) sha256=7a77a31e200a595ed4b0249493056efd0c920601f53d2ef135ca34ee796346cd
-  sitemap_generator (7.1.1) sha256=ab2a133d512a7b33ed713a27a9977f61d8379c9943e3b79900243fc1c4f7f81d
   slop (3.6.0) sha256=76ccab03be66bfcab4838cdc07cab019cd3e192a3538266246749e79e4788803
   snaky_hash (2.0.6) sha256=3663cae48cdef582b517025cf8a39d8789996eaf0b4ed89e2f0624836505654a
   solid_cache (1.0.10) sha256=bc05a2fb3ac78a6f43cbb5946679cf9db67dd30d22939ededc385cb93e120d41

app/controllers/sitemaps_controller.rb

@@ -0,0 +1,8 @@
+class SitemapsController < ApplicationController
+  def show
+    # Crawler-facing endpoint; let CDNs absorb repeat fetches. The fragment
+    # caches still bound the DB cost of a cache-miss render.
+    expires_in 1.hour, public: true
+    render xml: render_to_string(formats: [:xml])
+  end
+end

app/helpers/sitemaps_helper.rb

@@ -0,0 +1,17 @@
+module SitemapsHelper
+  def sitemap_static_urls
+    [root_url, code_of_conduct_url, coaches_url, teaching_guide_url, faq_url,
+     attendance_policy_url, student_guide_url, privacy_policy_url, cookie_policy_url,
+     breach_code_of_conduct_url, volunteer_url, fundraise_url, donate_url,
+     codebar_stories_podcast_url]
+  end
+
+  def sitemap_record_sections
+    [
+      { name: 'chapters', records: Chapter.active, url: ->(chapter) { chapter_url(chapter.slug) } },
+      { name: 'workshops', records: Workshop.all, url: ->(workshop) { workshop_url(workshop) } },
+      { name: 'events', records: Event.all, url: ->(event) { event_url(event) } },
+      { name: 'meetings', records: Meeting.all, url: ->(meeting) { meeting_url(meeting) } }
+    ]
+  end
+end

app/views/sitemaps/show.xml.builder

@@ -0,0 +1,21 @@
+xml.instruct!
+
+# `maximum(:updated_at).to_f` — a raw Time in a cache key is stringified with
+# second precision, so changes made within the same second would be missed.
+# expires_in makes sections stale after record deletions self-heal.
+xml.urlset('xmlns' => 'http://www.sitemaps.org/schemas/sitemap/0.9') do
+  cache 'sitemap/static', expires_in: 1.week do
+    sitemap_static_urls.each { |url| xml.url { xml.loc(url) } }
+  end
+
+  sitemap_record_sections.each do |section|
+    cache ['sitemap', section[:name], section[:records].maximum(:updated_at).to_f], expires_in: 1.day do
+      section[:records].find_each do |record|
+        xml.url do
+          xml.loc(section[:url].call(record))
+          xml.lastmod(record.updated_at.utc.iso8601)
+        end
+      end
+    end
+  end
+end

config/nginx.conf.erb

@@ -36,6 +36,15 @@ http {
     set $plausible_script_url https://plausible.io/js/pa-PFruVsE_br97UUCRXE_6f.js;
     set $plausible_event_url https://plausible.io/api/event;
 
+    # Gzip: the Heroku router does not compress, and Cloudflare only re-compresses
+    # when the origin has not already. Compress proxied responses here.
+    gzip on;
+    gzip_vary on;
+    gzip_proxied any;
+    gzip_comp_level 5;
+    gzip_min_length 1024;
+    gzip_types application/xml application/json text/plain text/css application/javascript text/javascript;
+
     # Plausible: Proxy script.js (cached)
     location = /js/script.js {
       proxy_cache plausible_cache;

config/routes.rb

@@ -192,6 +192,8 @@
   post "check-in/w/:code" => "check_ins#create"
   get  "check-in/w/:code/confirm" => "check_ins#confirm", as: :check_in_w_confirm
 
+  get 'sitemap.xml', to: 'sitemaps#show', as: :sitemap
+
   get 'cookie-policy' => 'pages#show', id: 'cookie-policy'
   get 'privacy-policy' => 'pages#show', id: 'privacy-policy'
   get 'breach-code-of-conduct' => 'pages#show', id: 'breach-code-of-conduct'

db/migrate/20260916120000_add_updated_at_indexes_for_sitemap_cache_keys.rb

@@ -0,0 +1,9 @@
+class AddUpdatedAtIndexesForSitemapCacheKeys < ActiveRecord::Migration[8.1]
+  disable_ddl_transaction!
+
+  def change
+    add_index :workshops, :updated_at, algorithm: :concurrently
+    add_index :events, :updated_at, algorithm: :concurrently
+    add_index :meetings, :updated_at, algorithm: :concurrently
+  end
+end

db/schema.rb

@@ -10,7 +10,7 @@
 #
 # It's strongly recommended that you check this file into your version control system.
 
-ActiveRecord::Schema[8.1].define(version: 2026_09_08_085057) do
+ActiveRecord::Schema[8.1].define(version: 2026_09_16_120000) do
   # These are extensions that must be enabled in order to support this database
   enable_extension "pg_catalog.plpgsql"
 
@@ -235,6 +235,7 @@
     t.index ["check_in_code"], name: "index_events_on_check_in_code", unique: true
     t.index ["date_and_time"], name: "index_events_on_date_and_time"
     t.index ["slug"], name: "index_events_on_slug", unique: true
+    t.index ["updated_at"], name: "index_events_on_updated_at"
     t.index ["venue_id"], name: "index_events_on_venue_id"
   end
 
@@ -415,6 +416,7 @@
     t.datetime "updated_at", precision: nil
     t.integer "venue_id"
     t.index ["slug"], name: "index_meetings_on_slug", unique: true
+    t.index ["updated_at"], name: "index_meetings_on_updated_at"
     t.index ["venue_id"], name: "index_meetings_on_venue_id"
   end
 
@@ -652,6 +654,7 @@
     t.index ["check_in_code"], name: "index_workshops_on_check_in_code", unique: true
     t.index ["created_by_id"], name: "index_workshops_on_created_by_id"
     t.index ["date_and_time"], name: "index_workshops_on_date_and_time"
+    t.index ["updated_at"], name: "index_workshops_on_updated_at"
   end
 
   add_foreign_key "invitation_log_entries", "invitation_logs"

public/robots.txt

@@ -1,2 +1,2 @@
 # See https://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file
-Sitemap: https://codebar.io/sitemap.xml.gz
+Sitemap: https://codebar.io/sitemap.xml

spec/requests/sitemap_spec.rb

@@ -0,0 +1,77 @@
+require 'rails_helper'
+
+RSpec.describe 'Sitemap' do
+  let!(:chapter) { Fabricate(:chapter) }
+  let!(:workshop) { Fabricate(:workshop_no_sponsor, chapter:) }
+  let!(:event) { Fabricate(:event) }
+  let!(:meeting) { Fabricate(:meeting) }
+
+  it 'serves the sitemap as XML' do
+    get '/sitemap.xml'
+
+    expect(response).to have_http_status(:ok)
+    expect(response.media_type).to eq('application/xml')
+  end
+
+  it 'lists chapters, workshops, events, meetings and static pages' do
+    get '/sitemap.xml'
+
+    body = response.body
+    expect(body).to include(root_url)
+    expect(body).to include(chapter_url(chapter.slug))
+    expect(body).to include(workshop_url(workshop))
+    expect(body).to include(event_url(event))
+    expect(body).to include(meeting_url(meeting))
+    expect(body).to include(code_of_conduct_url)
+    expect(body).to include(faq_url)
+    expect(body).to include(privacy_policy_url)
+  end
+
+  it 'includes lastmod for records' do
+    get '/sitemap.xml'
+
+    expect(response.body).to include("<lastmod>#{workshop.reload.updated_at.utc.iso8601}</lastmod>")
+    expect(response.headers['Cache-Control']).to include('public')
+  end
+
+  it 'includes new records once their section cache key changes' do
+    with_fragment_caching do
+      get '/sitemap.xml'
+      expect(response.body).to include(workshop_url(workshop))
+
+      new_workshop = Fabricate(:workshop_no_sponsor, chapter:)
+      get '/sitemap.xml'
+
+      expect(response.body).to include(workshop_url(new_workshop))
+    end
+  end
+
+  it 'stops listing a deleted record once the section cache expires' do
+    Fabricate(:workshop_no_sponsor, chapter:)
+    workshop.update_columns(updated_at: 1.hour.ago)
+    with_fragment_caching do
+      get '/sitemap.xml'
+      expect(response.body).to include(workshop_url(workshop))
+
+      workshop.destroy
+      travel 2.days do
+        get '/sitemap.xml'
+      end
+
+      expect(response.body).not_to include(workshop_url(workshop))
+    end
+  end
+
+  def with_fragment_caching
+    old_cache = Rails.cache
+    old_perform_caching = ActionController::Base.perform_caching
+    Rails.cache = ActiveSupport::Cache::MemoryStore.new
+    ActionController::Base.cache_store = Rails.cache
+    ActionController::Base.perform_caching = true
+    yield
+  ensure
+    Rails.cache = old_cache
+    ActionController::Base.cache_store = old_cache
+    ActionController::Base.perform_caching = old_perform_caching
+  end
+end