Merge pull request #1078 from fpsvogel/filter-external-content-source-files

Author: fpsvogel

Gemfile.lock

@@ -98,6 +98,7 @@ GEM
       faraday (>= 1, < 3)
     faraday-net_http (3.4.2)
       net-http (~> 0.5)
+    ffi (1.17.2-arm64-darwin)
     ffi (1.17.2-x86_64-linux-gnu)
     fiber-annotation (0.2.0)
     fiber-local (1.1.0)
@@ -141,8 +142,11 @@ GEM
     minitest-stub_any_instance (1.0.3)
     net-http (0.8.0)
       uri (>= 0.11.1)
+    nokogiri (1.18.10-arm64-darwin)
+      racc (~> 1.4)
     nokogiri (1.18.10-x86_64-linux-gnu)
       racc (~> 1.4)
+    nokolexbor (0.6.2-arm64-darwin)
     nokolexbor (0.6.2-x86_64-linux)
     observer (0.1.2)
     ostruct (0.6.3)
@@ -267,6 +271,7 @@ GEM
     zeitwerk (2.7.3)
 
 PLATFORMS
+  arm64-darwin-24
   x86_64-linux
 
 DEPENDENCIES

bridgetown-core/lib/bridgetown-core/readers/plugin_content_reader.rb

@@ -23,6 +23,7 @@ def read
       end
     end
 
+    # rubocop:disable Metrics/MethodLength, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
     def read_content_root(collection_name, content_dir)
       collection = site.collections[collection_name]
       unless collection
@@ -35,17 +36,31 @@ def read_content_root(collection_name, content_dir)
 
       Find.find(content_dir) do |path|
         if File.directory?(path)
-          Find.prune if EntryFilter::SPECIAL_LEADING_CHAR_REGEX.match?(File.basename(path))
+          if rejected_by_external_sources_filter?(path, collection_name) ||
+              EntryFilter::SPECIAL_LEADING_CHAR_REGEX.match?(File.basename(path))
+            Find.prune
+          end
+
           next
         end
 
+        next if rejected_by_external_sources_filter?(path, collection_name)
+
         if File.symlink?(path)
           Bridgetown.logger.warn "Plugin content reader:", "Ignored symlinked asset: #{path}"
         else
           read_content_file(content_dir, path, collection)
         end
       end
     end
+    # rubocop:enable Metrics/MethodLength, Metrics/CyclomaticComplexity, Metrics/PerceivedComplexity
+
+    def rejected_by_external_sources_filter?(path, collection_name)
+      filter = site.config.external_sources_filters&.dig(collection_name)
+      return false unless filter
+
+      !filter.call(File.basename(path), path)
+    end
 
     # @param collection [Bridgetown::Collection]
     def read_content_file(content_dir, path, collection)

bridgetown-core/lib/bridgetown-core/utils/initializers.rb

@@ -13,7 +13,7 @@
   end
 end
 
-Bridgetown.initializer :external_sources do |config, contents:|
+Bridgetown.initializer :external_sources do |config, contents:, filters: nil|
   Bridgetown::ExternalSources = Module.new
 
   contents.each do |coll, path|
@@ -35,6 +35,13 @@
   contents.each_value do |path|
     config.additional_watch_paths << path
   end
+
+  if filters
+    config.external_sources_filters = {}
+    filters.each do |coll, filter|
+      config.external_sources_filters[coll] = filter
+    end
+  end
 end
 
 Bridgetown.initializer :parse_routes do |config|

bridgetown-core/test/external_sources_folder/skipme_subfolder/notes.md

@@ -0,0 +1 @@
+This content should be filtered out because it's in a folder that's filtered out.

bridgetown-core/test/external_sources_folder/subfolder/notes.md

@@ -0,0 +1 @@
+This content should NOT be filtered out.

bridgetown-core/test/external_sources_folder/subfolder/skipme_notes.md

@@ -0,0 +1 @@
+This content should be filtered out.

bridgetown-core/test/external_sources_folder_not_filtered/skipme_actually_dont.md

@@ -0,0 +1 @@
+This content should NOT be filtered out.

bridgetown-core/test/features/test_external_sources.rb

@@ -7,13 +7,25 @@ class TestExternalSources < BridgetownFeatureTest
   describe "external_sources initializer" do
     it "renders ERB file" do
       sources_folder = File.expand_path("../external_sources_folder", __dir__)
+      other_sources_folder = File.expand_path("../external_sources_folder_not_filtered", __dir__)
 
       create_directory "config"
       create_file "config/initializers.rb", <<~RUBY
         Bridgetown.configure do |config|
+          collections do
+            other_pages do
+              output true
+            end
+          end
+
           init :external_sources do
             contents do
               pages "#{sources_folder}"
+              other_pages "#{other_sources_folder}"
+            end
+
+            filters do
+              pages ->(name, path) { !name.start_with?("skipme_") }
             end
           end
 
@@ -35,6 +47,10 @@ class TestExternalSources < BridgetownFeatureTest
       assert_file_contains "<head><title>Marked Down</title></head><body><h1 id=\"marked-down\">Marked Down</h1>\n\n<p>This is <strong>Markdown</strong> text. It’s as easy as 1, 2, 3!</p>\n",
                            "output/marked_down/index.html"
       refute_exist "output/.ignore"
+      refute_exist "output/subfolder/skipme_notes/index.html"
+      assert_file_contains "This content should NOT be filtered out.", "output/subfolder/notes/index.html"
+      refute_exist "output/skipme_subfolder"
+      assert_file_contains "This content should NOT be filtered out.", "output/other_pages/skipme_actually_dont/index.html"
     end
   end
 end

bridgetown-website/src/_docs/content/external-sources.md

@@ -5,7 +5,7 @@ top_section: Writing Content
 category: resources
 ---
 
-There are times you may want Bridgetown to include resources you've created which live outside of your site project folder hierarchy. In particular, you may have a folder(s) of Markdown files already saved somewhere and would like those to be included in your site build. 
+There are times you may want Bridgetown to include resources you've created which live outside of your site project folder hierarchy. In particular, you may have a folder(s) of Markdown files already saved somewhere and would like those to be included in your site build.
 
 To add a new content source to your project, use the `external_sources` plugin initializer in your `config/initializers.rb` file:
 
@@ -43,6 +43,20 @@ init :external_sources do
 end
 ```
 
+If you want to include only certain files from an external source, you can do so in a `filters` block. For example, here is how to add a filter to external sources to the `pages` collection, so as to include only files and folders whose name does not start with an underscore:
+
+```ruby
+init :external_sources do
+  contents do
+    pages "path/to/folder"
+  end
+
+  filters do
+    pages ->(name, path) { !name.start_with?("_") }
+  end
+end
+```
+
 ## Loading Markdown Content from Other Applications
 
 Unlike with standard Bridgetown content files within `src` where you must use front matter if you wish Markdown files get processed as resources instead of static files, Markdown files in external sources don't require any front matter. However, in order to ensure those files are rendered with a layout, you'll need to set up [front matter defaults](/docs/content/front-matter-defaults) (as shown in the example above).