jekyll-aeo 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2f7c4d9f203c1e2bc36c2f3c1547d4f6056ed77cd07d250a25ee186a46bd7891
-  data.tar.gz: 88f985556de2aae0ce6a2d0c57fb0be9be36c7a2b8f275910f7ff06e9f04bd3a
+  metadata.gz: a67da5680eb6edabb8dc5d19eac59183bfaa8d9e96d55f3bc61bae32f1ab5a23
+  data.tar.gz: 34e6338c176a2162370077a743dc22ab22a208de99667be9edc9002cd6296103
 SHA512:
-  metadata.gz: 0110becea058f84e0c28790655d695f95d3f4394003795a7c1dafef7ca0c56fcecef12b3e1dfdbcc7a1bd4f194cc5bf5db3b60b0623e98642123265b2e9436b1
-  data.tar.gz: ffaa6971e9bd344a1bb30775e00653dfe0fff53cf8ff4ec8adfcf32899c88df87003fa0b8e3bbd5e9e77507b8cae9b6a932f81adc880a3e6fcb2a6b4685094be
+  metadata.gz: aff3c6403325f75908ba1457350013a8995785c0e0ab851ec51b2ffc55c9a805aefebd8e86532e74043b4245cf7d6fc3c5df8324fcd1b6d722204c07855275d4
+  data.tar.gz: 381bdd47d7a8c4095afd5c40de07152ee756d2031441c15e0be5d51288c55b6234e71055d9d3511fcd4b2c8737039d5e5a73b8e92deeeca545cb45f2756021e4

data/lib/jekyll-aeo/commands/validate.rb

@@ -72,6 +72,7 @@ module JekyllAeo
           content = File.read(llms_path, encoding: "utf-8")
           md_urls = content.scan(/\[.*?\]\(([^)]*\.md)\)/).flatten
 
+          dest_expanded = File.expand_path(dest)
           md_urls.each do |url|
             relative_url = if !baseurl.empty? && url.start_with?(baseurl)
                              url.delete_prefix(baseurl)
@@ -79,6 +80,8 @@ module JekyllAeo
                              url
                            end
             file_path = File.join(dest, relative_url)
+            next unless File.expand_path(file_path).start_with?(dest_expanded)
+
             errors << "Referenced file not found: #{url} (expected at #{file_path})" unless File.exist?(file_path)
           end
         end

data/lib/jekyll-aeo/config.rb

@@ -5,6 +5,8 @@ module JekyllAeo
     DEFAULTS = {
       "enabled" => true,
       "exclude" => [],
+      "include_layouts" => nil,
+      "include_collections" => nil,
       "dotmd" => {
         "link_tag" => "auto",
         "include_last_modified" => true,
@@ -34,7 +36,7 @@ module JekyllAeo
       "url_map" => {
         "enabled" => false,
         "output_filepath" => "docs/Url-Map.md",
-        "columns" => %w[page_id url lang layout path redirects markdown_copy skipped],
+        "columns" => %w[layout url url_dotmd dotmd_mode excluded path page_id lang redirects],
         "show_created_at" => true
       },
       "robots_txt" => {

data/lib/jekyll-aeo/generators/{markdown_page.rb → dot_md_writer.rb}

@@ -4,17 +4,20 @@ require "fileutils"
 
 module JekyllAeo
   module Generators
-    module MarkdownPage
+    module DotMdWriter
       YAML_FRONT_MATTER_REGEXP = /\A(---\s*\n.*?\n?)^(---\s*$\n?)/m
+      LIQUID_PATTERN = /\{[{%]/
 
       def self.process(obj, site)
         config = JekyllAeo::Config.from_site(site)
         dotmd_config = config["dotmd"]
-        source_path = JekyllAeo::Utils::SkipLogic.resolve_source_path(obj, site)
-        return if JekyllAeo::Utils::SkipLogic.skip?(obj, site, config)
+        source_path = JekyllAeo::Utils::IncludeLogic.resolve_source_path(obj, site)
+        return unless JekyllAeo::Utils::IncludeLogic.include?(obj, site, config)
 
         dest_path = md_dest_path(obj, site)
-        body = extract_body(source_path, obj, dotmd_config)
+        body, dotmd_mode = extract_body(source_path, obj, dotmd_config)
+        obj.data["aeo_dotmd_mode"] = dotmd_mode
+        return if body.nil? || body.strip.empty?
 
         if dotmd_config["include_last_modified"] && File.exist?(source_path)
           last_modified = resolve_last_modified(obj, source_path)
@@ -40,15 +43,52 @@ module JekyllAeo
       end
 
       def self.extract_body(source_path, obj, dotmd_config)
+        preferred = obj.data["dotmd_mode"]
+
+        return extract_html2dotmd(obj, dotmd_config) if preferred == "html2dotmd"
+        return extract_explicit_md2dotmd(source_path, obj) if preferred == "md2dotmd" && !File.exist?(source_path)
+
         if File.exist?(source_path)
-          raw = File.read(source_path, encoding: "utf-8")
-          body = raw.sub(YAML_FRONT_MATTER_REGEXP, "")
-          JekyllAeo::Utils::ContentStripper.strip(body, dotmd_config["md2dotmd"])
+          extract_from_source(source_path, obj, dotmd_config, preferred)
         else
-          JekyllAeo::Utils::HtmlConverter.convert(obj.output, dotmd_config["html2dotmd"])
+          html_output = obj.respond_to?(:output) ? obj.output : nil
+          return html2dotmd_result(html_output, dotmd_config) if html_output && !html_output.strip.empty?
+
+          [nil, "html2dotmd"]
         end
       end
 
+      def self.extract_html2dotmd(obj, dotmd_config)
+        html_output = obj.respond_to?(:output) ? obj.output : nil
+        return html2dotmd_result(html_output, dotmd_config) if html_output && !html_output.strip.empty?
+
+        Jekyll.logger.warn "Jekyll-AEO:",
+                           "dotmd_mode: html2dotmd set but no rendered output for #{obj.url}"
+        [nil, "html2dotmd"]
+      end
+
+      def self.extract_explicit_md2dotmd(_source_path, obj)
+        Jekyll.logger.warn "Jekyll-AEO:",
+                           "dotmd_mode: md2dotmd set but no source file for #{obj.url}"
+        [nil, "md2dotmd"]
+      end
+
+      def self.extract_from_source(source_path, obj, dotmd_config, preferred)
+        raw = File.read(source_path, encoding: "utf-8")
+        body = raw.sub(YAML_FRONT_MATTER_REGEXP, "")
+
+        if preferred != "md2dotmd" && body.match?(LIQUID_PATTERN)
+          html_output = obj.respond_to?(:output) ? obj.output : nil
+          return html2dotmd_result(html_output, dotmd_config) if html_output && !html_output.strip.empty?
+        end
+
+        [JekyllAeo::Utils::ContentStripper.strip(body, dotmd_config["md2dotmd"]), "md2dotmd"]
+      end
+
+      def self.html2dotmd_result(html, dotmd_config)
+        [JekyllAeo::Utils::HtmlConverter.convert(html, dotmd_config["html2dotmd"] || {}), "html2dotmd"]
+      end
+
       def self.build_header(obj, body, _config = nil, last_modified: nil)
         header = ""
         title = obj.data["title"]
@@ -142,7 +182,9 @@ module JekyllAeo
 
       private_class_method :build_header, :md_dest_path, :resolve_last_modified,
                            :format_date, :build_metadata_block,
-                           :yaml_safe_scalar, :extract_body, :metadata_fields
+                           :yaml_safe_scalar, :extract_body, :metadata_fields,
+                           :extract_html2dotmd, :extract_explicit_md2dotmd,
+                           :extract_from_source, :html2dotmd_result
     end
   end
 end

data/lib/jekyll-aeo/generators/llms_txt.rb

@@ -23,11 +23,11 @@ module JekyllAeo
         items = []
 
         site.documents.each do |doc|
-          next if JekyllAeo::Utils::SkipLogic.skip?(doc, site, config)
+          next unless JekyllAeo::Utils::IncludeLogic.include?(doc, site, config)
 
           items << {
             obj: doc,
-            title: doc.data["title"] || "",
+            title: title_for(doc),
             description: doc.data["description"] || "",
             url: doc.url,
             collection: doc.collection&.label,
@@ -36,11 +36,11 @@ module JekyllAeo
         end
 
         site.pages.each do |page|
-          next if JekyllAeo::Utils::SkipLogic.skip?(page, site, config)
+          next unless JekyllAeo::Utils::IncludeLogic.include?(page, site, config)
 
           items << {
             obj: page,
-            title: page.data["title"] || "",
+            title: title_for(page),
             description: page.data["description"] || "",
             url: page.url,
             collection: nil,
@@ -114,6 +114,16 @@ module JekyllAeo
         end
       end
 
+      def self.title_for(obj)
+        title = obj.data["title"]
+        return title if title.is_a?(String) && !title.strip.empty?
+
+        segment = obj.url.chomp("/").split("/").last
+        return "Untitled" if segment.nil? || segment.empty?
+
+        segment.split(/[_-]/).map(&:capitalize).join(" ")
+      end
+
       def self.build_llms_txt(site, sections, llms_config, config)
         lines = []
         lines << "# #{site.config['title']}"
@@ -158,8 +168,8 @@ module JekyllAeo
       end
 
       private_class_method :build_custom_sections, :build_auto_sections,
-                           :titleize, :build_llms_txt, :append_full_txt_link,
-                           :append_sections
+                           :titleize, :title_for, :build_llms_txt,
+                           :append_full_txt_link, :append_sections
     end
   end
 end

data/lib/jekyll-aeo/generators/url_map.rb

@@ -7,15 +7,18 @@ module JekyllAeo
     module UrlMap
       COLUMN_HEADERS = {
         "page_id" => "Page ID",
-        "url" => "URL",
+        "url" => "Url",
         "lang" => "Lang",
         "layout" => "Layout",
         "path" => "Path",
         "redirects" => "Redirects",
-        "markdown_copy" => "Markdown Copy",
-        "skipped" => "Skipped"
+        "url_dotmd" => "Url DotMd",
+        "excluded" => "Excluded",
+        "dotmd_mode" => "DotMd Mode"
       }.freeze
 
+      DEFAULT_COLUMNS = %w[layout url url_dotmd dotmd_mode excluded path page_id lang redirects].freeze
+
       def self.generate(site)
         config = JekyllAeo::Config.from_site(site)
         return if config["enabled"] == false
@@ -23,39 +26,46 @@ module JekyllAeo
         url_map_config = config["url_map"] || {}
         return if url_map_config["enabled"] == false
 
-        columns = url_map_config["columns"] || COLUMN_HEADERS.keys
+        columns = url_map_config["columns"] || DEFAULT_COLUMNS
         items = collect_all_items(site, config, columns)
         sections = build_sections(items)
         markdown = build_markdown(sections, columns, url_map_config)
 
-        output_file = File.join(project_root(site), url_map_config["output_filepath"] || "docs/Url-Map.md")
+        root = project_root(site)
+        output_file = File.join(root, url_map_config["output_filepath"] || "docs/Url-Map.md")
+        unless File.expand_path(output_file).start_with?(File.expand_path(root))
+          Jekyll.logger.error "AEO Url Map:", "output_filepath escapes project root — skipped"
+          return
+        end
         FileUtils.mkdir_p(File.dirname(output_file))
         File.write(output_file, markdown)
       end
 
       def self.collect_all_items(site, config, columns)
         items = []
-        needs_skip = columns.include?("skipped")
-        needs_md = columns.include?("markdown_copy")
+        needs_excluded = columns.include?("excluded")
+        needs_md = columns.include?("url_dotmd")
+        needs_mode = columns.include?("dotmd_mode")
         baseurl = site.config["baseurl"].to_s.chomp("/")
 
         site.documents.each do |doc|
+          next if doc.is_a?(Jekyll::StaticFile)
           next unless doc.output_ext == ".html"
-          next if doc.respond_to?(:collection) && doc.collection&.label == "assets"
 
-          items << build_item(doc, doc.collection&.label, site, config, needs_skip, needs_md, baseurl)
+          items << build_item(doc, doc.collection&.label, site, config, needs_excluded, needs_md, needs_mode, baseurl)
         end
 
         site.pages.each do |page|
+          next if page.is_a?(Jekyll::StaticFile)
           next unless page.output_ext == ".html"
 
-          items << build_item(page, nil, site, config, needs_skip, needs_md, baseurl)
+          items << build_item(page, nil, site, config, needs_excluded, needs_md, needs_mode, baseurl)
         end
 
         items
       end
 
-      def self.build_item(obj, collection_label, site, config, needs_skip, needs_md, baseurl = "")
+      def self.build_item(obj, collection_label, site, config, needs_excluded, needs_md, needs_mode, baseurl = "")
         redirect_from = obj.data["redirect_from"]
         redirects_str = case redirect_from
                         when Array then redirect_from.join(", ")
@@ -73,9 +83,10 @@ module JekyllAeo
           collection: collection_label
         }
 
-        item[:skipped] = JekyllAeo::Utils::SkipLogic.skip_reason(obj, site, config) || "" if needs_skip
-        item[:markdown_copy] = md_url(obj.url, baseurl) if needs_md && (!needs_skip || item[:skipped].empty?)
-        item[:markdown_copy] ||= "" if needs_md
+        item[:excluded] = JekyllAeo::Utils::IncludeLogic.exclude_reason(obj, site, config) || "" if needs_excluded
+        item[:url_dotmd] = md_url(obj.url, baseurl) if needs_md && (!needs_excluded || item[:excluded].empty?)
+        item[:url_dotmd] ||= "" if needs_md
+        item[:dotmd_mode] = obj.data["aeo_dotmd_mode"] || "" if needs_mode
 
         item
       end

data/lib/jekyll-aeo/hooks.rb

@@ -17,11 +17,11 @@ Jekyll::Hooks.register :pages, :post_render do |page|
 end
 
 Jekyll::Hooks.register :documents, :post_write do |doc|
-  JekyllAeo::Generators::MarkdownPage.process(doc, doc.site)
+  JekyllAeo::Generators::DotMdWriter.process(doc, doc.site)
 end
 
 Jekyll::Hooks.register :pages, :post_write do |page|
-  JekyllAeo::Generators::MarkdownPage.process(page, page.site)
+  JekyllAeo::Generators::DotMdWriter.process(page, page.site)
 end
 
 Jekyll::Hooks.register :site, :post_write do |site|

data/lib/jekyll-aeo/link_tag.rb

@@ -6,7 +6,7 @@ module JekyllAeo
       config = JekyllAeo::Config.from_site(site)
       dotmd_config = config["dotmd"]
       return unless dotmd_config["link_tag"] == "auto"
-      return if JekyllAeo::Utils::SkipLogic.skip?(obj, site, config)
+      return unless JekyllAeo::Utils::IncludeLogic.include?(obj, site, config)
 
       md_url = JekyllAeo::Utils::MdUrl.for(obj.url, site.config["baseurl"])
       tag = %(<link rel="alternate" type="text/markdown" href="#{md_url}">)
@@ -17,7 +17,7 @@ module JekyllAeo
       config = JekyllAeo::Config.from_site(site)
       dotmd_config = config["dotmd"]
       return unless dotmd_config["link_tag"] == "data"
-      return if JekyllAeo::Utils::SkipLogic.skip?(obj, site, config)
+      return unless JekyllAeo::Utils::IncludeLogic.include?(obj, site, config)
 
       md_url = JekyllAeo::Utils::MdUrl.for(obj.url, site.config["baseurl"])
       obj.data["md_url"] = md_url

data/lib/jekyll-aeo/utils/html_converter.rb

@@ -16,8 +16,9 @@ module JekyllAeo
         return "" unless content_node
 
         STRIP_ELEMENTS.each { |tag| content_node.css(tag).each(&:remove) }
+        promote_code_languages(content_node)
 
-        ReverseMarkdown.convert(content_node.inner_html, unknown_tags: :bypass).strip
+        ReverseMarkdown.convert(content_node.inner_html, unknown_tags: :bypass, github_flavored: true).strip
       end
 
       def self.extract_content(doc, config)
@@ -29,7 +30,18 @@ module JekyllAeo
         end
       end
 
-      private_class_method :extract_content
+      # Jekyll/Rouge: <div class="language-python"><div class="highlight"><pre>…
+      # ReverseMarkdown: reads `highlight-{lang}` from <pre>'s parent
+      def self.promote_code_languages(node)
+        node.css('div[class*="language-"]').each do |div|
+          next unless div["class"] =~ /language-(\S+)/
+
+          pre = div.at_css("pre")
+          pre.parent["class"] = "highlight-#{Regexp.last_match(1)}" if pre&.parent
+        end
+      end
+
+      private_class_method :extract_content, :promote_code_languages
     end
   end
 end

data/lib/jekyll-aeo/utils/{skip_logic.rb → include_logic.rb}

@@ -2,13 +2,15 @@
 
 module JekyllAeo
   module Utils
-    module SkipLogic
-      def self.skip_reason(obj, site, config)
+    module IncludeLogic
+      def self.exclude_reason(obj, site, config)
         return "plugin disabled" if config["enabled"] == false
+        return "static file" if static_file?(obj)
         return "non-HTML output" unless html_output?(obj)
-        return "markdown_copy: false" if obj.data["markdown_copy"] == false
-        return "redirect" if obj.data["redirect_to"]
-        return "assets collection" if assets_collection?(obj)
+
+        reason = filter_reason(obj, config)
+        return reason if reason
+
         return "llms file" if llms_file?(obj, site)
         return "excluded" if excluded?(obj, config)
         return "no source file" unless source_available?(obj, site, config)
@@ -16,8 +18,17 @@ module JekyllAeo
         nil
       end
 
-      def self.skip?(obj, site, config)
-        !skip_reason(obj, site, config).nil?
+      def self.filter_reason(obj, config)
+        return "dotmd_mode: disabled" if obj.data["dotmd_mode"] == "disabled"
+        return "redirect" if obj.data["redirect_to"]
+        return "layout: #{obj.data['layout']}" unless included_layout?(obj, config)
+        return "collection: #{obj.collection.label}" unless included_collection?(obj, config)
+
+        nil
+      end
+
+      def self.include?(obj, site, config)
+        exclude_reason(obj, site, config).nil?
       end
 
       def self.resolve_source_path(obj, site)
@@ -32,8 +43,24 @@ module JekyllAeo
         obj.output_ext == ".html"
       end
 
-      def self.assets_collection?(obj)
-        obj.respond_to?(:collection) && obj.collection&.label == "assets"
+      def self.static_file?(obj)
+        obj.is_a?(Jekyll::StaticFile)
+      end
+
+      def self.included_layout?(obj, config)
+        include_layouts = config["include_layouts"]
+        return true if include_layouts.nil?
+
+        include_layouts.include?(obj.data["layout"])
+      end
+
+      def self.included_collection?(obj, config)
+        return true unless obj.respond_to?(:collection)
+
+        include_collections = config["include_collections"]
+        return true if include_collections.nil?
+
+        include_collections.include?(obj.collection&.label)
       end
 
       def self.llms_file?(obj, site)
@@ -59,7 +86,8 @@ module JekyllAeo
         source_file_exists?(obj, site) || html2dotmd["enabled"]
       end
 
-      private_class_method :html_output?, :assets_collection?, :llms_file?,
+      private_class_method :html_output?, :static_file?, :included_layout?,
+                           :included_collection?, :llms_file?, :filter_reason,
                            :excluded?, :source_file_exists?, :source_available?
     end
   end

data/lib/jekyll-aeo/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module JekyllAeo
-  VERSION = "1.0.0"
+  VERSION = "1.1.0"
 end

data/lib/jekyll-aeo.rb

@@ -4,11 +4,11 @@ require "jekyll"
 require_relative "jekyll-aeo/version"
 require_relative "jekyll-aeo/config"
 require_relative "jekyll-aeo/utils/content_stripper"
-require_relative "jekyll-aeo/utils/skip_logic"
+require_relative "jekyll-aeo/utils/include_logic"
 require_relative "jekyll-aeo/utils/html_converter"
 require_relative "jekyll-aeo/utils/md_url"
 require_relative "jekyll-aeo/link_tag"
-require_relative "jekyll-aeo/generators/markdown_page"
+require_relative "jekyll-aeo/generators/dot_md_writer"
 require_relative "jekyll-aeo/generators/llms_txt"
 require_relative "jekyll-aeo/generators/llms_full_txt"
 require_relative "jekyll-aeo/generators/url_map"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: jekyll-aeo
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Manuel Gruber
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-03-14 00:00:00.000000000 Z
+date: 2026-03-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: jekyll
@@ -105,9 +105,9 @@ files:
 - lib/jekyll-aeo/commands/validate.rb
 - lib/jekyll-aeo/config.rb
 - lib/jekyll-aeo/generators/domain_profile.rb
+- lib/jekyll-aeo/generators/dot_md_writer.rb
 - lib/jekyll-aeo/generators/llms_full_txt.rb
 - lib/jekyll-aeo/generators/llms_txt.rb
-- lib/jekyll-aeo/generators/markdown_page.rb
 - lib/jekyll-aeo/generators/robots_txt.rb
 - lib/jekyll-aeo/generators/url_map.rb
 - lib/jekyll-aeo/hooks.rb
@@ -121,8 +121,8 @@ files:
 - lib/jekyll-aeo/tags/aeo_json_ld.rb
 - lib/jekyll-aeo/utils/content_stripper.rb
 - lib/jekyll-aeo/utils/html_converter.rb
+- lib/jekyll-aeo/utils/include_logic.rb
 - lib/jekyll-aeo/utils/md_url.rb
-- lib/jekyll-aeo/utils/skip_logic.rb
 - lib/jekyll-aeo/version.rb
 homepage: https://zaai.com/jekyll-aeo
 licenses: