helios-sitemap 0.1.0 → 0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 36a3e496ed0ede36fbe60b6fe276b5fd11f45b2c3a161bb101aac6202d0e46a8
-  data.tar.gz: 9213f58ce9365b6bc844c2ea4ed3fc62ca12ac60c8cd3647e341b0b0c01102f4
+  metadata.gz: d8cefad961f0f74b3ec173b0b9587185859160cd846fa5ed7e0ac61fc6892a76
+  data.tar.gz: a4eb3cf44d45a91bbc551be41a07d5e4ad2947ef832bea8e282bcd299543fab3
 SHA512:
-  metadata.gz: 5f001b4b6a6fd4fa495452272da7ed859eb19ad9cfd2409466640bc033b2b276256ad259c34df4a44314155b4bd214baa76f29b83981f5613e79ed22f2c24d95
-  data.tar.gz: 49c10dea795a509dd3fb2e3904db5c75d30584a43533054b70693d5a19b1df02dcac0c01a3cc69193377736db52e04376af9546375c2e377740d5098269f4b67
+  metadata.gz: 44600ff4533240069ff39c19205cf0e93862555edbe5f6e6fd62b78a62f8388ba886efef50330536a65e459ae38142b74a22c92082ed005c15055959800a93f8
+  data.tar.gz: 40040ba99a18cd67c4cb7c1fac6241a31fd323baec1226a087848d63c66a4c9ae0f8d44a19828a2f31ac5abf6f4f81b9ea134fd6768537bafc8e1910f0341d56

data/README.md

@@ -12,66 +12,82 @@ Add to your Gemfile:
 gem "helios-sitemap"
 ```
 
-Then `bundle install`.
+Then:
+
+```bash
+bundle install
+bin/rails generate helios:sitemap:install
+```
+
+The install generator creates three files in your app:
+
+- `config/initializers/helios_sitemap.rb` — configuration (host, S3 settings, sitemap entries)
+- `app/jobs/sitemap_refresh_job.rb` — background job that calls the refresh service
+- `app/controllers/sitemap_controller.rb` — proxies the sitemap from S3
+- Adds a `get "sitemap.xml"` route
 
 ## Configuration
 
-Create an initializer at `config/initializers/helios_sitemap.rb`:
+Edit `config/initializers/helios_sitemap.rb`:
 
 ```ruby
 Helios::Sitemap.configure do |config|
   config.default_host = "https://example.com"
 
   # S3 storage (defaults to ENV vars if not set)
-  config.aws_bucket     = ENV["AWS_SITEMAP_BUCKET"]
-  config.aws_region     = ENV["AWS_REGION"]
-  config.aws_access_key_id     = ENV["AWS_ACCESS_KEY_ID"]
-  config.aws_secret_access_key = ENV["AWS_SECRET_ACCESS_KEY"]
-
-  # IndexNow (defaults to ENV vars if not set)
-  config.indexnow_domain  = ENV["INDEXNOW_DOMAIN"]
-  config.indexnow_api_key = ENV["INDEXNOW_API_KEY"]
-
-  # Define what goes in your sitemap
+  # config.aws_bucket     = ENV["AWS_SITEMAP_BUCKET"]
+  # config.aws_region     = ENV["AWS_REGION"]
+  # config.aws_access_key_id     = ENV["AWS_ACCESS_KEY_ID"]
+  # config.aws_secret_access_key = ENV["AWS_SECRET_ACCESS_KEY"]
+  # config.s3_object_key  = "sitemaps/sitemap.xml.gz"
+
+  # Define what goes in your sitemap.
+  # The block receives a SitemapGenerator::Sitemap instance.
   config.sitemap_entries = ->(sitemap) {
     sitemap.add "/", changefreq: "weekly", priority: 1.0
-    Post.published.find_each do |post|
-      sitemap.add "/#{post.slug}", changefreq: "weekly", priority: 0.7
-    end
-  }
 
-  # Define URLs to submit to IndexNow
-  config.indexnow_urls = -> {
-    urls = ["https://example.com/"]
-    Post.published.find_each do |post|
-      urls << "https://example.com/#{post.slug}"
-    end
-    urls
+    # Dynamic entries from your database:
+    # Post.published.find_each do |post|
+    #   sitemap.add "/#{post.slug}", changefreq: "weekly", priority: 0.7
+    # end
   }
+
+  # IndexNow integration (optional)
+  # config.indexnow_domain  = ENV["INDEXNOW_DOMAIN"]
+  # config.indexnow_api_key = ENV["INDEXNOW_API_KEY"]
+  # config.indexnow_urls = -> {
+  #   Page.published.map { |p| "https://example.com/#{p.slug}" }
+  # }
 end
 ```
 
-## Routes
+## Generating & Uploading
 
-Mount the engine in your `config/routes.rb`:
+The installed `SitemapRefreshJob` calls `Helios::Sitemap::RefreshService.call`, which:
 
-```ruby
-mount Helios::Sitemap::Engine, at: "/"
-```
+1. Generates `sitemap.xml.gz` using `sitemap_generator`
+2. Uploads it to your configured S3 bucket
+3. Submits URLs to IndexNow (if configured)
 
-This provides:
-- `GET /sitemap.xml` - Serves the sitemap XML from S3
-- `GET /sitemap.xml.gz` - Serves the gzipped sitemap from S3
+Schedule the job however your app handles recurring work:
 
-## Generating & Uploading
+```ruby
+# Manual trigger
+SitemapRefreshJob.perform_later
 
-Trigger a sitemap refresh by running the job:
+# With sidekiq-scheduler (config/sidekiq.yml):
+# SitemapRefreshJob:
+#   every: ['3d']
+#   class: SitemapRefreshJob
 
-```ruby
-Helios::Sitemap::RefreshJob.perform_later
+# With any other job scheduler or cron
 ```
 
-You can schedule this however you prefer (cron, recurring job, after publishing content, etc.).
+The job lives in your app so you can customize it — add error handling, logging, notifications, or call additional services after the sitemap refreshes.
+
+## Serving the Sitemap
+
+The installed `SitemapController` fetches the gzipped sitemap from S3 and serves it at `/sitemap.xml`. This works on ephemeral-disk platforms where the generated file wouldn't persist between deploys.
 
 ## Environment Variables
 
@@ -81,8 +97,8 @@ You can schedule this however you prefer (cron, recurring job, after publishing
 | `AWS_REGION` | AWS region |
 | `AWS_ACCESS_KEY_ID` | AWS access key |
 | `AWS_SECRET_ACCESS_KEY` | AWS secret key |
-| `INDEXNOW_DOMAIN` | Your domain for IndexNow |
-| `INDEXNOW_API_KEY` | Your IndexNow API key |
+| `INDEXNOW_DOMAIN` | Your domain for IndexNow (optional) |
+| `INDEXNOW_API_KEY` | Your IndexNow API key (optional) |
 
 ## License
 

data/lib/generators/helios/sitemap/install/install_generator.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+module Helios
+  module Sitemap
+    module Generators
+      class InstallGenerator < Rails::Generators::Base
+        source_root File.expand_path("templates", __dir__)
+
+        desc "Installs Helios::Sitemap initializer, job, and controller into your app"
+
+        def copy_initializer
+          template "initializer.rb", "config/initializers/helios_sitemap.rb"
+        end
+
+        def copy_job
+          template "sitemap_refresh_job.rb", "app/jobs/sitemap_refresh_job.rb"
+        end
+
+        def copy_controller
+          template "sitemap_controller.rb", "app/controllers/sitemap_controller.rb"
+        end
+
+        def add_route
+          route 'get "sitemap.xml", to: "sitemap#show"'
+        end
+
+        def print_next_steps
+          say ""
+          say "Helios::Sitemap installed!", :green
+          say ""
+          say "Next steps:"
+          say "  1. Edit config/initializers/helios_sitemap.rb to configure your host and sitemap entries"
+          say "  2. Set these ENV vars: AWS_REGION, AWS_SITEMAP_BUCKET, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY"
+          say "  3. Schedule SitemapRefreshJob in your job runner (e.g. sidekiq-scheduler)"
+          say ""
+        end
+      end
+    end
+  end
+end

data/lib/generators/helios/sitemap/install/templates/initializer.rb

@@ -0,0 +1,32 @@
+# frozen_string_literal: true
+
+Helios::Sitemap.configure do |config|
+  # The canonical host for your sitemap URLs
+  config.default_host = "https://example.com"
+
+  # S3 settings (defaults read from ENV vars)
+  # config.aws_region = ENV["AWS_REGION"]
+  # config.aws_bucket = ENV["AWS_SITEMAP_BUCKET"]
+  # config.aws_access_key_id = ENV["AWS_ACCESS_KEY_ID"]
+  # config.aws_secret_access_key = ENV["AWS_SECRET_ACCESS_KEY"]
+  # config.s3_object_key = "sitemaps/sitemap.xml.gz"
+
+  # Define your sitemap entries.
+  # The block receives a SitemapGenerator::Sitemap instance.
+  config.sitemap_entries = ->(sitemap) {
+    sitemap.add "/", changefreq: "daily", priority: 0.9
+    # sitemap.add "/about", changefreq: "weekly"
+
+    # Dynamic entries from your database:
+    # Page.published.find_each do |page|
+    #   sitemap.add "/#{page.slug}", lastmod: page.updated_at, changefreq: "weekly"
+    # end
+  }
+
+  # IndexNow integration (optional)
+  # config.indexnow_domain = ENV["INDEXNOW_DOMAIN"]
+  # config.indexnow_api_key = ENV["INDEXNOW_API_KEY"]
+  # config.indexnow_urls = -> {
+  #   Page.published.map { |p| "https://example.com/#{p.slug}" }
+  # }
+end

data/lib/generators/helios/sitemap/install/templates/sitemap_controller.rb

@@ -0,0 +1,16 @@
+# frozen_string_literal: true
+
+require "open-uri"
+
+class SitemapController < ApplicationController
+  def show
+    config = Helios::Sitemap.configuration
+    url = "https://#{config.aws_bucket}.s3.#{config.aws_region}.amazonaws.com/#{config.s3_object_key}"
+
+    gz_data = URI.open(url).read
+
+    render plain: gz_data,
+           content_type: "application/gzip",
+           content_disposition: 'attachment; filename="sitemap.xml.gz"'
+  end
+end

data/lib/generators/helios/sitemap/install/templates/sitemap_refresh_job.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+class SitemapRefreshJob < ApplicationJob
+  queue_as :default
+
+  def perform
+    Helios::Sitemap::RefreshService.call
+  end
+end

data/{app/jobs/helios/sitemap/refresh_job.rb → lib/helios/sitemap/refresh_service.rb}

@@ -5,17 +5,17 @@ require "aws-sdk-s3"
 
 module Helios
   module Sitemap
-    class RefreshJob < ApplicationJob
-      queue_as :default
+    class RefreshService
+      def self.call
+        new.call
+      end
 
-      def perform
+      def call
         config = Helios::Sitemap.configuration
 
-        urls = collect_urls(config)
-
         generate_sitemap(config)
         upload_to_s3(config) unless Rails.env.development?
-        submit_to_indexnow(urls)
+        submit_to_indexnow(config)
       end
 
       private
@@ -34,25 +34,21 @@ module Helios
       def upload_to_s3(config)
         file_path = Rails.root.join("public", "sitemap.xml.gz")
 
-        transfer_manager = Aws::S3::TransferManager.new(client: config.s3_client)
-
-        transfer_manager.upload_file(
-          file_path,
-          bucket: config.aws_bucket,
-          key: config.s3_object_key,
-          content_type: "application/gzip"
+        s3 = Aws::S3::Resource.new(
+          region: config.aws_region,
+          credentials: Aws::Credentials.new(config.aws_access_key_id, config.aws_secret_access_key)
         )
 
+        obj = s3.bucket(config.aws_bucket).object(config.s3_object_key)
+        obj.upload_file(file_path.to_s, content_type: "application/gzip")
+
         Rails.logger.info("[helios-sitemap] Uploaded sitemap to s3://#{config.aws_bucket}/#{config.s3_object_key}")
       end
 
-      def collect_urls(config)
-        return [] unless config.indexnow_urls
-
-        config.indexnow_urls.call
-      end
+      def submit_to_indexnow(config)
+        return unless config.indexnow_urls
 
-      def submit_to_indexnow(urls)
+        urls = config.indexnow_urls.call
         return unless urls.any?
 
         Rails.logger.info("[helios-sitemap] Submitting #{urls.count} URLs to IndexNow")

data/lib/helios/sitemap/version.rb

@@ -1,5 +1,5 @@
 module Helios
   module Sitemap
-    VERSION = "0.1.0"
+    VERSION = "0.2"
   end
 end

data/lib/helios/sitemap.rb

@@ -2,6 +2,7 @@ require "helios/sitemap/version"
 require "helios/sitemap/engine"
 require "helios/sitemap/configuration"
 require "helios/sitemap/index_now_service"
+require "helios/sitemap/refresh_service"
 
 module Helios
   module Sitemap

data/lib/helios-sitemap.rb

@@ -0,0 +1 @@
+require "helios/sitemap"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: helios-sitemap
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: '0.2'
 platform: ruby
 authors:
 - Jason Fleetwood-Boldt
@@ -66,16 +66,20 @@ files:
 - app/controllers/helios/sitemap/application_controller.rb
 - app/controllers/helios/sitemap/sitemap_controller.rb
 - app/helpers/helios/sitemap/application_helper.rb
-- app/jobs/helios/sitemap/application_job.rb
-- app/jobs/helios/sitemap/refresh_job.rb
 - app/mailers/helios/sitemap/application_mailer.rb
 - app/models/helios/sitemap/application_record.rb
 - app/views/layouts/helios/sitemap/application.html.erb
 - config/routes.rb
+- lib/generators/helios/sitemap/install/install_generator.rb
+- lib/generators/helios/sitemap/install/templates/initializer.rb
+- lib/generators/helios/sitemap/install/templates/sitemap_controller.rb
+- lib/generators/helios/sitemap/install/templates/sitemap_refresh_job.rb
+- lib/helios-sitemap.rb
 - lib/helios/sitemap.rb
 - lib/helios/sitemap/configuration.rb
 - lib/helios/sitemap/engine.rb
 - lib/helios/sitemap/index_now_service.rb
+- lib/helios/sitemap/refresh_service.rb
 - lib/helios/sitemap/version.rb
 - lib/tasks/helios/sitemap_tasks.rake
 homepage: https://github.com/heliosdev/helios-sitemap

data/app/jobs/helios/sitemap/application_job.rb

@@ -1,6 +0,0 @@
-module Helios
-  module Sitemap
-    class ApplicationJob < ActiveJob::Base
-    end
-  end
-end