crawlscope 0.6.0 → 0.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cb1ed58c5dc558d7d7efcb357870fc4764a1d6d5caeb5ddc30e466334c986421
-  data.tar.gz: 9e90845271e781a0586c30c5c3f2c770b4a0c837474d78e8a19afa89c5b2fb6d
+  metadata.gz: 34b82022958c0d4bbc782e95ee899e555932d764050bb20f940c6ffaeb754cc1
+  data.tar.gz: 2587fd40b220f51d9752196323953abd2af194c95e480e52aa432259ec9f263b
 SHA512:
-  metadata.gz: cd645a628045089499e213491a08157e5268b2238007c86e20eeff996dcb0246037915dce0019554995ade10c57eae31ffc79d1b256a123160f728a7f6e74722
-  data.tar.gz: d12723425911cc2c6184f6f2f31f8d0dbe6fde8bc021c3c45c0b5490e500906be6f49da74c3457e04778bb6ed0c50438489fd1875191090de702cf6d0ed494f0
+  metadata.gz: 589b924f5f5a627e988156a77ca280c7f8a8ae4a8602bb0ff9fb4d59b449b18c546eab14fbbeb22ad02aee1d2ccfb79a9e5e2e5af870d06c15e057a30c404187
+  data.tar.gz: 327e346ca6a0702ae37b37cdf413443b578042f06a43306b87d14d8fc0d165480c952da6ba36ef483d1cec76125bbc1226d6e8ae3acf3c836dc737e3970330e1

data/CHANGELOG.md

@@ -5,6 +5,26 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.7.1] - 2026-07-21
+
+
+### Added
+
+- add lazy install generator
+
+
+
+## [0.7.0] - 2026-07-21
+
+
+### Added
+
+- add commitlint and lefthook
+
+- add lazy Rails task entrypoint
+
+
+
 ## [0.6.0] - 2026-06-01
 
 

data/README.md

@@ -37,9 +37,13 @@ Crawlscope requires Ruby 3.3 or newer.
 Add this line to your application's Gemfile:
 
 ```ruby
-gem "crawlscope"
+gem "crawlscope", require: false
 ```
 
+`require: false` keeps Crawlscope and its crawl stack out of normal Rails web
+and job process boot. Require `crawlscope` at the application boundary that
+runs an audit, or use the task setup below.
+
 And then execute:
 
 ```bash
@@ -142,7 +146,18 @@ puts result.issues.to_a.map(&:message)
 
 ## Rails Usage
 
-In an initializer:
+Run the install generator after adding the gem:
+
+```bash
+bin/rails generate crawlscope:install
+```
+
+The generator creates `config/initializers/crawlscope.rb` with an idempotent
+`CrawlscopeConfiguration.apply` loader and adds conditional `crawlscope/tasks`
+loading to the application's `Rakefile`. This preserves `bin/rails --tasks` and
+the `crawlscope:*` tasks without loading Crawlscope during normal Rails boot.
+
+Customize the `Crawlscope.configure` block inside the generated initializer:
 
 ```ruby
 Crawlscope.configure do |config|
@@ -153,6 +168,17 @@ Crawlscope.configure do |config|
 end
 ```
 
+Runtime callers must apply the generated configuration before using
+Crawlscope:
+
+```ruby
+CrawlscopeConfiguration.apply
+Crawlscope.configuration.audit
+```
+
+Rake tasks apply it automatically because `crawlscope/tasks` loads the gem
+before Rails evaluates the initializer.
+
 Then run:
 
 ```bash

data/lib/crawlscope/railtie.rb

@@ -3,7 +3,7 @@
 module Crawlscope
   class Railtie < Rails::Railtie
     rake_tasks do
-      load File.expand_path("../tasks/crawlscope_tasks.rake", __dir__)
+      require "crawlscope/tasks"
     end
   end
 end

data/lib/crawlscope/tasks.rb

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+require "crawlscope"
+require "rake"
+
+unless Rake::Task.task_defined?("crawlscope:validate")
+  load File.expand_path("../tasks/crawlscope_tasks.rake", __dir__)
+end

data/lib/crawlscope/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Crawlscope
-  VERSION = "0.6.0"
+  VERSION = "0.7.1"
 end

data/lib/crawlscope.rb

@@ -27,8 +27,10 @@ module Crawlscope
 end
 
 Crawlscope.instance_variable_set(:@loader, Zeitwerk::Loader.for_gem)
+Crawlscope.loader.ignore("#{__dir__}/generators")
 Crawlscope.loader.ignore("#{__dir__}/tasks")
 Crawlscope.loader.ignore("#{__dir__}/crawlscope/railtie.rb")
+Crawlscope.loader.ignore("#{__dir__}/crawlscope/tasks.rb")
 Crawlscope.loader.setup
 
 require "crawlscope/railtie" if defined?(Rails::Railtie)

data/lib/generators/crawlscope/install_generator.rb

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+
+require "rails/generators"
+
+module Crawlscope
+  module Generators
+    class InstallGenerator < Rails::Generators::Base
+      source_root File.expand_path("templates", __dir__)
+
+      desc "Create a lazy-safe Crawlscope initializer and task loader"
+
+      def create_initializer
+        template "initializer.rb.tt", "config/initializers/crawlscope.rb"
+      end
+
+      def configure_rakefile
+        rakefile = File.join(destination_root, "Rakefile")
+        return unless File.exist?(rakefile)
+        return if File.read(rakefile).include?('require "crawlscope/tasks"')
+
+        inject_into_file "Rakefile", rakefile_setup, before: /^require_relative ["']config\/application["']/
+      end
+
+      private
+
+      def rakefile_setup
+        <<~RUBY
+          crawlscope_tasks_requested = Rake.application.options.show_tasks ||
+            ARGV.any? { |argument| ["-T", "--tasks"].include?(argument) }
+          require "crawlscope/tasks" if crawlscope_tasks_requested ||
+            ARGV.any? { |argument| argument.start_with?("crawlscope:") }
+
+        RUBY
+      end
+    end
+  end
+end

data/lib/generators/crawlscope/templates/initializer.rb.tt

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+module CrawlscopeConfiguration
+  MUTEX = Mutex.new
+
+  def self.apply
+    return if @applied
+
+    MUTEX.synchronize do
+      return if @applied
+
+      require "crawlscope"
+
+      Crawlscope.configure do |config|
+        config.base_url = -> { ENV.fetch("CRAWLSCOPE_BASE_URL", "http://localhost:3000") }
+        config.sitemap_path = lambda {
+          ENV.fetch("SITEMAP", Rails.public_path.join("sitemap.xml").to_s)
+        }
+        config.site_name = ENV.fetch("CRAWLSCOPE_SITE_NAME", "Application")
+      end
+
+      @applied = true
+    end
+  end
+end
+
+CrawlscopeConfiguration.apply if defined?(Crawlscope)

data/test/crawlscope/install_generator_test.rb

@@ -0,0 +1,58 @@
+# frozen_string_literal: true
+
+require "test_helper"
+require "generators/crawlscope/install_generator"
+require "open3"
+require "rbconfig"
+
+class CrawlscopeInstallGeneratorTest < Minitest::Test
+  def test_generates_lazy_initializer_and_task_loader
+    Dir.mktmpdir do |destination|
+      File.write(File.join(destination, "Rakefile"), <<~RUBY)
+        require_relative "config/application"
+        Rails.application.load_tasks
+      RUBY
+
+      Crawlscope::Generators::InstallGenerator.start([], destination_root: destination)
+
+      initializer = File.join(destination, "config/initializers/crawlscope.rb")
+      rakefile = File.read(File.join(destination, "Rakefile"))
+
+      assert File.exist?(initializer)
+      assert_includes File.read(initializer), "module CrawlscopeConfiguration"
+      assert_includes File.read(initializer), "CrawlscopeConfiguration.apply if defined?(Crawlscope)"
+      assert_includes rakefile, 'require "crawlscope/tasks"'
+      assert_operator rakefile.index('require "crawlscope/tasks"'), :<, rakefile.index('require_relative "config/application"')
+
+      _stdout, stderr, status = Open3.capture3(RbConfig.ruby, initializer)
+      assert status.success?, stderr
+
+      script = <<~RUBY
+        require "pathname"
+
+        module Rails
+          def self.public_path
+            Pathname.new("public")
+          end
+        end
+
+        require "crawlscope"
+        load ARGV.fetch(0)
+
+        configuration = Crawlscope.configuration
+        CrawlscopeConfiguration.apply
+        abort "configuration replaced" unless Crawlscope.configuration.equal?(configuration)
+        abort "base URL missing" unless configuration.base_url == "http://localhost:3000"
+        abort "sitemap missing" unless configuration.sitemap_path == "public/sitemap.xml"
+      RUBY
+      _stdout, stderr, status = Open3.capture3(
+        RbConfig.ruby,
+        "-I#{File.expand_path("../../lib", __dir__)}",
+        "-e",
+        script,
+        initializer
+      )
+      assert status.success?, stderr
+    end
+  end
+end

data/test/crawlscope/loader_test.rb

@@ -1,6 +1,8 @@
 # frozen_string_literal: true
 
 require "test_helper"
+require "open3"
+require "rbconfig"
 
 class CrawlscopeLoaderTest < Minitest::Test
   def test_eager_loads_cleanly
@@ -8,4 +10,39 @@ class CrawlscopeLoaderTest < Minitest::Test
       Crawlscope.loader.eager_load
     end
   end
+
+  def test_entrypoint_does_not_load_crawl_dependencies
+    script = <<~RUBY
+      require "crawlscope"
+
+      loaded = $LOADED_FEATURES.grep(%r{/(?:async|faraday|json-schema|nokogiri)(?:/|\\.rb)})
+      abort loaded.join("\\n") unless loaded.empty?
+    RUBY
+
+    _stdout, stderr, status = Open3.capture3(
+      RbConfig.ruby,
+      "-I#{File.expand_path("../../lib", __dir__)}",
+      "-e",
+      script
+    )
+
+    assert status.success?, stderr
+  end
+
+  def test_task_entrypoint_registers_tasks
+    script = <<~RUBY
+      require "crawlscope/tasks"
+
+      abort "task missing" unless Rake::Task.task_defined?("crawlscope:validate")
+    RUBY
+
+    _stdout, stderr, status = Open3.capture3(
+      RbConfig.ruby,
+      "-I#{File.expand_path("../../lib", __dir__)}",
+      "-e",
+      script
+    )
+
+    assert status.success?, stderr
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: crawlscope
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.7.1
 platform: ruby
 authors:
 - Paulo Fidalgo
@@ -256,8 +256,11 @@ files:
 - lib/crawlscope/structured_data/report.rb
 - lib/crawlscope/structured_data/reporter.rb
 - lib/crawlscope/structured_data/writer.rb
+- lib/crawlscope/tasks.rb
 - lib/crawlscope/url.rb
 - lib/crawlscope/version.rb
+- lib/generators/crawlscope/install_generator.rb
+- lib/generators/crawlscope/templates/initializer.rb.tt
 - lib/tasks/crawlscope_tasks.rake
 - test/crawlscope/browser_test.rb
 - test/crawlscope/cli_test.rb
@@ -268,6 +271,7 @@ files:
 - test/crawlscope/fetch_executor_test.rb
 - test/crawlscope/http_test.rb
 - test/crawlscope/indexability_rule_test.rb
+- test/crawlscope/install_generator_test.rb
 - test/crawlscope/links_rule_test.rb
 - test/crawlscope/loader_test.rb
 - test/crawlscope/metadata_rule_test.rb
@@ -318,7 +322,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.10
+rubygems_version: 4.0.16
 specification_version: 4
 summary: Audit sitemap URLs for metadata, structured data, uniqueness, and links
 test_files: []