jekyll-wikilinks 0.0.7 → 0.0.11

data/lib/jekyll-wikilinks/util/parser.rb

@@ -1,4 +1,6 @@
+require "nokogiri"
 require_relative "regex"
+require_relative "wikilink"
 
 module Jekyll
   module WikiLinks
@@ -14,145 +16,55 @@ module Jekyll
 
       def initialize(site)
         @context ||= Jekyll::WikiLinks::Context.new(site)
+        # do not use @dm in parser -- it is only meant to be passed down into wikilink classes. 
         @doc_manager ||= site.doc_mngr
         @markdown_converter ||= site.find_converter_instance(CONVERTER_CLASS)
-        @wikilink_blocks, @wikilink_inlines = [], [], []
+        @wikilink_blocks, @wikilink_inlines = [], []
       end
 
       # parsing
 
-      def parse(doc_content)
-        @wikilink_blocks, @wikilink_inlines = [], [], []
+      def parse(doc_filename, doc_content)
+        @wikilink_blocks, @wikilink_inlines = [], []
         if !$wiki_conf.disabled_attributes?
-          self.parse_block_singles(doc_content)
-          self.parse_block_lists_mkdn(doc_content)
-          self.parse_block_lists_comma(doc_content)
+          self.parse_blocks(doc_filename, doc_content)
         end
-        self.parse_inlines(doc_content)
-      end
-
-      def parse_block_singles(doc_content)
-        bullet_type = ""
-        typed_link_block_matches = doc_content.scan(REGEX_TYPED_LINK_BLOCK)
-        if !typed_link_block_matches.nil? && typed_link_block_matches.size != 0
-          typed_link_block_matches.each do |wl_match|
-            link_type = wl_match[0]
-            filename = wl_match[1]
-            typed_link_block_wikilink = WikiLinkBlock.new(
-              link_type,
-              bullet_type,
-              filename,
+        self.parse_inlines(doc_filename, doc_content)
+      end
+
+      def parse_blocks(doc_filename, doc_content)
+        block_matches = doc_content.scan(REGEX_WIKI_LINK_BLOCKS)
+        if !block_matches.nil? && block_matches.size != 0
+          block_matches.each do |wl_match|
+            # init block wikilink
+            wikilink_block = WikiLinkBlock.new(
+              @doc_manager,
+              doc_filename,
+              wl_match[0], # link_type
+              wl_match[2], # bullet_type
             )
-            @wikilink_blocks << typed_link_block_wikilink
-            doc_content.gsub!(typed_link_block_wikilink.md_regex, "\n")
-          end
-        end
-      end
-
-      def parse_block_lists_comma(doc_content)
-        processing_link_type = nil
-        processing_wikilink_list = nil
-        bullet_type = ","
-        typed_link_block_list_item_matches = doc_content.scan(REGEX_TYPED_LINK_BLOCK_LIST_COMMA)
-        if !typed_link_block_list_item_matches.nil? && typed_link_block_list_item_matches.size != 0
-          # Match 1
-          #   link-type-txt	link-type
-          #   filename	link
-          #   3.	alink
-          # Match 2
-          #   link-type-txt
-          #   filename
-          #   3.	blink
-          # Match 3
-          #   link-type-txt
-          #   filename
-          #   3.	clink
-          typed_link_block_list_item_matches.each do |wl_match|
-            link_type = wl_match[0]
-            link_filename_1 = wl_match[1]
-            link_filename_2 = wl_match[2]
-            if !link_type.nil?
-              # process previous wikilink_list
-              if !processing_wikilink_list.nil? && processing_wikilink_list.has_items?
-                @wikilink_blocks << processing_wikilink_list
-                doc_content.gsub!(processing_wikilink_list.md_regex, "\n")
+            # extract + add filenames
+            items = wl_match[1]
+            filename_matches = items.scan(/#{REGEX_LINK_LEFT}#{REGEX_FILENAME}#{REGEX_LINK_RIGHT}/i)
+            filename_matches.each do |match|
+              match.each do |fname|
+                wikilink_block.add_item(fname)
               end
-              processing_link_type = link_type
-              processing_wikilink_list = WikiLinkBlock.new(processing_link_type, bullet_type, link_filename_1)
-              processing_wikilink_list.add_item(bullet_type, link_filename_2) if !link_filename_2.nil?
-            else
-              Jekyll.logger.error("'processing_wikilink_list' was nil") if processing_wikilink_list.nil?
-              processing_wikilink_list.add_item(bullet_type, link_filename_2)
             end
-          end
-          # process previous wikilink_list
-          if !processing_wikilink_list.nil? && processing_wikilink_list.has_items?
-            @wikilink_blocks << processing_wikilink_list
-            doc_content.gsub!(processing_wikilink_list.md_regex, "\n")
+            # replace text
+            doc_content.gsub!(wikilink_block.md_regex, "\n")
+            @wikilink_blocks << wikilink_block
           end
         end
       end
 
-      def parse_block_lists_mkdn(doc_content)
-        processing_link_type = nil
-        processing_wikilink_list = nil
-        bullet_type = nil
-        typed_link_block_list_item_matches = doc_content.scan(REGEX_TYPED_LINK_BLOCK_LIST_MKDN)
-        if !typed_link_block_list_item_matches.nil? && typed_link_block_list_item_matches.size != 0
-          # Match 1
-          #   link-type-txt	more-types
-          #   bullet
-          #   filename
-          # Match 2
-          #   link-type-txt
-          #   bullet	*
-          #   filename	alink
-          # Match 3
-          #   link-type-txt
-          #   bullet	*
-          #   filename	blink
-          # Match 4
-          #   link-type-txt	more-types
-          #   bullet
-          #   filename
-          # Match 5
-          #   link-type-txt
-          #   bullet	+
-          #   filename	alink
-          # Match 6
-          #   link-type-txt
-          #   bullet	+
-          #   filename	blink
-          typed_link_block_list_item_matches.each do |wl_match|
-            link_type = wl_match[0]
-            bullet_type = wl_match[1]
-            link_filename = wl_match[2]
-            if !link_type.nil?
-              # process previous wikilink_list
-              if !processing_wikilink_list.nil? && processing_wikilink_list.has_items?
-                @wikilink_blocks << processing_wikilink_list
-                doc_content.gsub!(processing_wikilink_list.md_regex, "\n")
-              end
-              processing_link_type = link_type
-              processing_wikilink_list = WikiLinkBlock.new(processing_link_type)
-            else
-              Jekyll.logger.error("'processing_wikilink_list' was nil") if processing_wikilink_list.nil?
-              processing_wikilink_list.add_item(bullet_type, link_filename)
-            end
-          end
-          # process previous wikilink_list
-          if !processing_wikilink_list.nil? && processing_wikilink_list.has_items?
-            @wikilink_blocks << processing_wikilink_list
-            doc_content.gsub!(processing_wikilink_list.md_regex, "\n")
-          end
-        end
-      end
-
-      def parse_inlines(doc_content)
-        wikilink_matches = doc_content.scan(REGEX_WIKI_LINKS)
-        if !wikilink_matches.nil? && wikilink_matches.size != 0
-          wikilink_matches.each do |wl_match|
+      def parse_inlines(doc_filename, doc_content)
+        inline_matches = doc_content.scan(REGEX_WIKI_LINK_INLINES)
+        if !inline_matches.nil? && inline_matches.size != 0
+          inline_matches.each do |wl_match|
             @wikilink_inlines << WikiLinkInline.new(
+              @doc_manager,
+              doc_filename,
               wl_match[0],
               wl_match[1],
               wl_match[2],
@@ -164,10 +76,12 @@ module Jekyll
         end
         # replace text
         return if @wikilink_inlines.nil?
+        # process typed wikilinks first so we don't accidentally 
+        # overwrite them when handling untyped wikilinks
         self.sort_typed_first
         @wikilink_inlines.each do |wikilink|
           doc_content.gsub!(
-            wikilink.md_link_regex,
+            wikilink.md_regex,
             self.build_html(wikilink)
           )
         end
@@ -198,50 +112,53 @@ module Jekyll
           end
           return "<p><span class=\"#{$wiki_conf.css_name("embed_image_wrapper")}\">#{svg_content}</span></p>"
         else
-          return "<p><span class=\"#{$wiki_conf.css_name("embed_image_wrapper")}\"><img class=\"#{$wiki_conf.css_name("embed_image")}\" src=\"#{relative_url(static_doc.relative_path)}\"/></span></p>"
+          return "<p><span class=\"#{$wiki_conf.css_name("embed_image_wrapper")}\"><img class=\"#{$wiki_conf.css_name("embed_image")}\" src=\"#{relative_url(static_doc.relative_path)}\"></span></p>"
         end
       end
 
   		def build_html(wikilink)
-        if wikilink.is_img?
-  			  linked_static_doc = @doc_manager.get_image_by_fname(wikilink.filename)
-          if wikilink.embedded? && wikilink.is_img?
-            return build_html_img_embed(linked_static_doc, is_svg=wikilink.is_img_svg?)
-          end
+        if !wikilink.is_valid?
+          return '<span class="' + $wiki_conf.css_name("invalid_wiki") + '">' + wikilink.md_str + '</span>'
         end
-        linked_doc = @doc_manager.get_doc_by_fname(wikilink.filename)
-  			if !linked_doc.nil?
-          link_type = wikilink.typed? ? " #{$wiki_conf.css_name("typed")} #{wikilink.link_type}" : ""
-
-  				# label
-  				wikilink_inner_txt = wikilink.clean_label_txt if wikilink.labelled?
-
-  				lnk_doc_rel_url = relative_url(linked_doc.url)
-          # TODO not sure about downcase
-  				fname_inner_txt = linked_doc['title'].downcase if wikilink_inner_txt.nil?
-
-          link_lvl = wikilink.describe['level']
-  				if (link_lvl == "file")
-  					wikilink_inner_txt = "#{fname_inner_txt}" if wikilink_inner_txt.nil?
-            return build_html_embed(
-              linked_doc['title'],
-              @doc_manager.get_doc_content(wikilink.filename),
-              lnk_doc_rel_url
-            ) if wikilink.embedded?
-  				elsif (link_lvl == "header" && DocManager.doc_has_header?(linked_doc, wikilink.header_txt))
-            # from: https://github.com/jekyll/jekyll/blob/6855200ebda6c0e33f487da69e4e02ec3d8286b7/Rakefile#L74
-  					lnk_doc_rel_url += "\#" + Jekyll::Utils.slugify(wikilink.header_txt)
-  					wikilink_inner_txt = "#{fname_inner_txt} > #{wikilink.header_txt}" if wikilink_inner_txt.nil?
-  				elsif (link_lvl == "block" && DocManager.doc_has_block_id?(linked_doc, wikilink.block_id))
-  					lnk_doc_rel_url += "\#" + wikilink.block_id.downcase
-  					wikilink_inner_txt = "#{fname_inner_txt} > ^#{wikilink.block_id}" if wikilink_inner_txt.nil?
-  				else
-  					return '<span class="' + $wiki_conf.css_name("invalid_wiki") + '">' + wikilink.md_link_str + '</span>'
-  				end
-  				return '<a class="' + $wiki_conf.css_name("wiki") + link_type + '" href="' + lnk_doc_rel_url + '">' + wikilink_inner_txt + '</a>'
-  			else
-  				return '<span class="' + $wiki_conf.css_name("invalid_wiki") + '">' + wikilink.md_link_str + '</span>'
-  			end
+        # image processing
+        if wikilink.embedded? && wikilink.is_img?
+          return build_html_img_embed(wikilink.linked_img, is_svg=wikilink.is_img_svg?)
+        end
+        # markdown file processing
+        linked_doc = wikilink.linked_doc
+        link_type_txt = wikilink.is_typed? ? " #{$wiki_conf.css_name("typed")} #{wikilink.link_type}" : ""
+        lnk_doc_rel_url = relative_url(linked_doc.url)
+        if wikilink.labelled?
+          inner_txt = wikilink.label_txt
+        elsif linked_doc.data.keys.include?('title')
+          inner_txt = linked_doc.data['title'].downcase
+        # in case there is no 'title' frontmatter attribute 
+        # (i'm seeing deprecation warnings, but there might 
+        #  be bugs caused by not using this...)
+        elsif linked_doc.respond_to?(:title)
+          inner_txt = linked_doc.title.downcase
+        # pages don't have automatically generated titles
+        else
+          inner_txt = Jekyll::Utils.slugify(linked_doc.basename)
+        end
+        # level-specific
+        if (wikilink.level == "file_path" || wikilink.level == "filename")
+          return build_html_embed(
+            linked_doc.title,
+            linked_doc.content,
+            lnk_doc_rel_url
+          ) if wikilink.embedded?
+        elsif (wikilink.level == "header")
+          # from: https://github.com/jekyll/jekyll/blob/6855200ebda6c0e33f487da69e4e02ec3d8286b7/Rakefile#L74
+          lnk_doc_rel_url += "\#" + Jekyll::Utils.slugify(wikilink.header_txt)
+          inner_txt += " > #{wikilink.header_txt.downcase}" if !wikilink.labelled?
+        elsif (wikilink.level == "block")
+          lnk_doc_rel_url += "\#" + wikilink.block_id
+          inner_txt += " > ^#{wikilink.block_id}" if !wikilink.labelled?
+        else
+          Jekyll.logger.error("Jekyll-Wikilinks: Invalid wikilink level")
+        end
+        return '<a class="' + $wiki_conf.css_name("wiki") + link_type_txt + '" href="' + lnk_doc_rel_url + '">' + inner_txt + '</a>'
   		end
 
       # helpers
@@ -254,210 +171,11 @@ module Jekyll
         #  appears as both untyped and typed in a document)
         temp = @wikilink_inlines.dup
         @wikilink_inlines.clear()
-        typed_wikilinks = temp.select { |wl| wl.typed? }
-        untyped_wikilinks = temp.select { |wl| !wl.typed? }
+        typed_wikilinks = temp.select { |wl| wl.is_typed? }
+        untyped_wikilinks = temp.select { |wl| !wl.is_typed? }
         @wikilink_inlines = typed_wikilinks.concat(untyped_wikilinks)
       end
     end
 
-    # validation
-
-    def has_target_attr?(attribute)
-      attribute.list_item.each do |li|
-        return false if @doc_manager.get_doc_by_fname(li[1]).nil?
-      end
-      return true
-    end
-
-    def has_target_wl?(wikilink)
-      level = wikilink.describe['level']
-      linked_doc = @doc_manager.get_doc_by_fname(wikilink.filename)
-      return false if linked_doc.nil?
-      return false if level == "header" && !DocManager.doc_has_header?(linked_doc, wikilink.header_txt)
-      return false if level == "block" && !DocManager.doc_has_block_id?(linked_doc, wikilink.block_id)
-      return true
-    end
-
-    # wikilinks
-
-    class WikiLinkBlock
-      attr_accessor :link_type, :list_items
-
-      # parameters ordered by appearance in regex
-      def initialize(link_type, bullet_type=nil, filename=nil)
-        @link_type ||= link_type
-        @list_items = [] # li[0] = bullet_type; li[1] = filename
-        @list_items << [ bullet_type, filename ] if !bullet_type.nil? && !filename.nil?
-      end
-
-      def add_item(bullet_type, filename)
-        return if bullet_type.nil? || bullet_type.empty? || filename.nil? || filename.empty?
-        @list_items << [ bullet_type, filename ]
-      end
-
-      def md_regex
-        if typed? && has_items?
-          # single
-          if bullet_type?.empty?
-            link_type = %r{#{@link_type}#{REGEX_LINK_TYPE}}
-            list_item_strs = @list_items.map { |li| /#{REGEX_LINK_LEFT}#{li[1]}#{REGEX_LINK_RIGHT}\n/i }
-            md_link_regex = /#{link_type}#{list_item_strs.join("")}/i
-          # list (comma)
-          elsif bullet_type? == ","
-            tmp_list_items = @list_items.dup
-            first_item = tmp_list_items.shift()
-            link_type = /#{@link_type}#{REGEX_LINK_TYPE}#{REGEX_LINK_LEFT}#{first_item[1]}#{REGEX_LINK_RIGHT}\s*/i
-            list_item_strs = tmp_list_items.map { |li| /#{li[0]}\s*#{REGEX_LINK_LEFT}#{li[1]}#{REGEX_LINK_RIGHT}\s*/i }
-            md_link_regex = /#{link_type}#{list_item_strs.join('')}/i
-          # list (md)
-          elsif !bullet_type?.match(REGEX_BULLET).nil?
-            link_type = %r{#{@link_type}#{REGEX_LINK_TYPE}\n}
-            list_item_strs = @list_items.map { |li| /#{Regexp.escape(li[0])}\s#{REGEX_LINK_LEFT}#{li[1]}#{REGEX_LINK_RIGHT}\n/i }
-            md_link_regex = /#{link_type}#{list_item_strs.join("")}/i
-          else
-            Jekyll.logger.error("bullet_types not uniform or invalid: #{bullet_type?}")
-          end
-          return md_link_regex
-        else
-          Jekyll.logger.error("WikiLinkBlockList.md_regex error")
-        end
-      end
-
-      def md_str
-        if typed? && has_items?
-          if bullet_type? == ","
-            link_type = "#{@link_type}::"
-            list_item_strs = @list_items.map { |li| "\[\[#{li[1]}\]\]#{li[0]}" }
-            md_link_str = (link_type + list_item_strs.join('')).delete_suffix(",")
-          elsif "+*-".include?(bullet_type?)
-            link_type = "#{@link_type}::\n"
-            list_item_strs = @list_items.map { |li| li[0] + " \[\[#{li[1]}\]\]\n" }
-            md_link_str = link_type + list_item_strs.join('')
-          else
-            Jekyll.logger.error("Not a valid bullet_type: #{bullet_type?}")
-          end
-          return md_link_str
-        else
-          Jekyll.logger.error("WikiLinkBlockList.md_str error")
-        end
-      end
-
-      def bullet_type?
-        bullets = @list_items.map { |li| li[0] }
-        return bullets.uniq.first if bullets.uniq.size == 1
-      end
-
-      def has_items?
-        return !@list_items.nil? && !@list_items.empty?
-      end
-
-      def typed?
-        return !@link_type.nil? && !@link_type.empty?
-      end
-    end
-
-    # the wikilink class knows everything about the original markdown syntax and its semantic meaning
-    class WikiLinkInline
-      attr_accessor :embed, :link_type, :filename, :header_txt, :block_id, :label_txt
-
-      FILENAME = "filename"
-      HEADER_TXT = "header_txt"
-      BLOCK_ID = "block_id"
-
-      # parameters ordered by appearance in regex
-      def initialize(embed, link_type, filename, header_txt, block_id, label_txt)
-        @embed ||= embed
-        @link_type ||= link_type
-        @filename ||= filename
-        @header_txt ||= header_txt
-        @block_id ||= block_id
-        @label_txt ||= label_txt
-      end
-
-      # labels are really flexible, so we need to handle them with a bit more care
-      def clean_label_txt
-        return @label_txt.sub("[", "\\[").sub("]", "\\]")
-      end
-
-      # TODO: remove this once parsing is migrated to nokogiri...?
-      def md_link_str
-        embed = embedded? ? "!" : ""
-        link_type = typed? ? "#{@link_type}::" : ""
-        filename = described?(FILENAME) ? @filename : ""
-        if described?(HEADER_TXT)
-          header = "\##{@header_txt}"
-          block = ""
-        elsif described?(BLOCK_ID)
-          header = ""
-          block = "\#\^#{@block_id}"
-        elsif !described?(FILENAME)
-          Jekyll.logger.error "Invalid link level in 'md_link_str'. See WikiLink's 'md_link_str' for details"
-        end
-        label_ = labelled? ? "\|#{@label_txt}" : ""
-        return "#{embed}#{link_type}\[\[#{filename}#{header}#{block}#{label_}\]\]"
-      end
-
-      def md_link_regex
-        regex_embed = embedded? ? REGEX_LINK_EMBED : %r{}
-        regex_link_type = typed? ? %r{#{@link_type}#{REGEX_LINK_TYPE}} : %r{}
-        filename = described?(FILENAME) ? @filename : ""
-        if described?(HEADER_TXT)
-          header = %r{#{REGEX_LINK_HEADER}#{@header_txt}}
-          block = %r{}
-        elsif described?(BLOCK_ID)
-          header = %r{}
-          block = %r{#{REGEX_LINK_BLOCK}#{@block_id}}
-        elsif !described?(FILENAME)
-          Jekyll.logger.error "Invalid link level in regex. See WikiLink's 'md_link_regex' for details"
-        end
-        label_ =  labelled? ? %r{#{REGEX_LINK_LABEL}#{clean_label_txt}} : %r{}
-        return %r{#{regex_embed}#{regex_link_type}#{REGEX_LINK_LEFT}#{filename}#{header}#{block}#{label_}#{REGEX_LINK_RIGHT}}
-      end
-
-      def describe
-        return {
-          'level' => level,
-          'labelled' => labelled?,
-          'embedded' => embedded?,
-          'typed_link' => typed?,
-        }
-      end
-
-      def labelled?
-        return !@label_txt.nil? && !@label_txt.empty?
-      end
-
-      def typed?
-        return !@link_type.nil? && !@link_type.empty?
-      end
-
-      def embedded?
-        return !@embed.nil? && @embed == "!"
-      end
-
-      def is_img?
-        # github supported image formats: https://docs.github.com/en/github/managing-files-in-a-repository/working-with-non-code-files/rendering-and-diffing-images
-        return SUPPORTED_IMG_FORMATS.any?{ |ext| ext == File.extname(@filename).downcase }
-      end
-
-      def is_img_svg?
-        return File.extname(@filename).downcase == ".svg"
-      end
-
-      def described?(chunk)
-        return (!@filename.nil? && !@filename.empty?) if chunk == FILENAME
-        return (!@header_txt.nil? && !@header_txt.empty?) if chunk == HEADER_TXT
-        return (!@block_id.nil? && !@block_id.empty?) if chunk == BLOCK_ID
-        Jekyll.logger.error "There is no link level '#{chunk}' in WikiLink Struct"
-      end
-
-      def level
-        return "file" if described?(FILENAME) && !described?(HEADER_TXT) && !described?(BLOCK_ID)
-        return "header" if described?(FILENAME) && described?(HEADER_TXT) && !described?(BLOCK_ID)
-        return "block" if described?(FILENAME) && !described?(HEADER_TXT) && described?(BLOCK_ID)
-        return "invalid"
-      end
-    end
-
   end
 end

data/lib/jekyll-wikilinks/util/regex.rb

@@ -12,37 +12,43 @@ module Jekyll
     SUPPORTED_IMG_FORMATS = Set.new(['.png', '.jpg', '.gif', '.psd', '.svg'])
 
     # wikilink constants
-  	REGEX_LINK_LEFT = /\[\[/
-    REGEX_LINK_RIGHT = /\]\]/
-    REGEX_LINK_EMBED = /(?<embed>(\!))/
-    REGEX_LINK_TYPE = /\s*::\s*/
-    REGEX_LINK_HEADER = /\#/
-    REGEX_LINK_BLOCK = /\#\^/
-    REGEX_LINK_LABEL = /\|/
+  	REGEX_LINK_LEFT       = /\[\[/
+    REGEX_LINK_RIGHT      = /\]\]/
+    REGEX_LINK_EMBED      = /(?<embed>\!)/
+    REGEX_LINK_TYPE       = /\s*::\s*/
+    REGEX_LINK_HEADER     = /\#/
+    REGEX_LINK_BLOCK      = /\#\^/
+    REGEX_LINK_LABEL      = /\|/
 
-    # wikilink usable char requirements
-    REGEX_LINK_TYPE_TXT = /(?<link-type-txt>([^\n\s\!\#\^\|\]]+))/i
-    REGEX_FILENAME = /(?<filename>([^\\\/:\#\^\|\[\]]+))/i
-    REGEX_HEADER_TXT = /(?<header-txt>([^\!\#\^\|\[\]]+))/i
-    REGEX_BLOCK_ID_TXT = /(?<block-id>([^\\\/:\!\#\^\|\[\]^\n]+))/i
-    REGEX_LABEL_TXT = /(?<label-txt>((.+?)(?=\]\])))/i
+    # wikitext usable char requirements
+    REGEX_LINK_TYPE_CHARS = /[^\n\s\!\#\^\|\]]+/i
+    REGEX_FILENAME_CHARS  = /[^\\:\#\^\|\[\]]+/i
+    REGEX_HEADER_CHARS    = /[^\!\#\^\|\[\]]+/i
+    REGEX_BLOCK_ID_CHARS  = /[^\\\/:\!\#\^\|\[\]^\n]+/i
+    REGEX_LABEL_CHARS     = /(.+?)(?=\]{2}[^\]])/i
+
+    # capture groups
+    REGEX_LINK_TYPE_TXT   = /(?<link-type-txt>#{REGEX_LINK_TYPE_CHARS})/i
+    REGEX_FILENAME        = /(?<filename>#{REGEX_FILENAME_CHARS})/i
+    REGEX_HEADER_TXT      = /(?<header-txt>#{REGEX_HEADER_CHARS})/i
+    REGEX_BLOCK_ID_TXT    = /(?<block-id>#{REGEX_BLOCK_ID_CHARS})/i
+    REGEX_LABEL_TXT       = /(?<label-txt>#{REGEX_LABEL_CHARS})/i
 
     # target markdown text (headers, lists, and blocks)
     ## kramdown regexes
     ### atx header: https://github.com/gettalong/kramdown/blob/master/lib/kramdown/parser/kramdown/header.rb#L29
-    REGEX_ATX_HEADER = /^\#{1,6}[\t ]*([^ \t].*)\n/i
+    REGEX_ATX_HEADER      = /^\#{1,6}[\t ]*([^ \t].*)\n/i
     ### setext header: https://github.com/gettalong/kramdown/blob/master/lib/kramdown/parser/kramdown/header.rb#L17
-    REGEX_SETEXT_HEADER = /^ {0,3}([^ \t].*)\n[-=][-=]*[ \t\r\f\v]*\n/i
+    REGEX_SETEXT_HEADER   = /^\s{0,3}([^ \t].*)\n[-=][-=]*[ \t\r\f\v]*\n/i
     ## list item: https://github.com/gettalong/kramdown/blob/master/lib/kramdown/parser/kramdown/list.rb#L49
-    REGEX_BULLET = /(?<bullet>[+*-])/i
-    # REGEX_LIST_ITEM = /(^ {0,3}[+*-])([\t| ].*?\n)/i
-    REGEX_LIST_ITEM = /(^ {0,3}#{REGEX_BULLET})(\s(?:#{REGEX_LINK_LEFT}#{REGEX_FILENAME}#{REGEX_LINK_RIGHT}))/i
-    ## new-markdown-style
-    REGEX_BLOCK = /.*\s\^#{REGEX_BLOCK_ID_TXT}/i
+    REGEX_BULLET          = /(?<bullet>[+*-])/i
+    ## markdown-style block-reference
+    REGEX_BLOCK           = /.*\s\^#{REGEX_BLOCK_ID_TXT}/i
 
     # wikilinks
+
     ## inline
-    REGEX_WIKI_LINKS = %r{                            # capture indeces
+    REGEX_WIKI_LINK_INLINES = %r{                     # capture indeces
       (#{REGEX_LINK_EMBED})?                          # 0
       (#{REGEX_LINK_TYPE_TXT}#{REGEX_LINK_TYPE})?     # 1
       #{REGEX_LINK_LEFT}
@@ -52,15 +58,15 @@ module Jekyll
         (#{REGEX_LINK_LABEL}#{REGEX_LABEL_TXT})?      # 5
       #{REGEX_LINK_RIGHT}
     }x
-    ## block
-    REGEX_TYPED_LINK_BLOCK = /#{REGEX_LINK_TYPE_TXT}#{REGEX_LINK_TYPE}#{REGEX_LINK_LEFT}#{REGEX_FILENAME}#{REGEX_LINK_RIGHT}\n/i
-    # TODO: keep an eye on this -- using REGEX_FILENAME in two places
-    REGEX_TYPED_LINK_BLOCK_LIST_COMMA = /(?:#{REGEX_LINK_TYPE_TXT}#{REGEX_LINK_TYPE}\s*(?:#{REGEX_LINK_LEFT}#{REGEX_FILENAME}#{REGEX_LINK_RIGHT})\s*|\G)\s*(?:,\s*#{REGEX_LINK_LEFT}#{REGEX_FILENAME}#{REGEX_LINK_RIGHT})\s*/i
-    REGEX_TYPED_LINK_BLOCK_LIST_MKDN = /#{REGEX_LINK_TYPE_TXT}#{REGEX_LINK_TYPE}\n|\G(?:#{REGEX_LIST_ITEM}\n)/i
-
-    # parsing for wikilinks in html
-    # identify missing links in doc via .invalid-wiki-link class and nested doc-text.
-    REGEX_INVALID_WIKI_LINK = /invalid-wiki-link(?:[^\]]+)\[\[(?<wiki-text>([^\]]+))\]\]/i
 
+    ## block
+    ### single
+    REGEX_SINGLE           = /#{REGEX_LINK_LEFT}#{REGEX_FILENAME_CHARS}#{REGEX_LINK_RIGHT}/i
+    ### list (comma is responsible for catching the single case)
+    REGEX_LIST_COMMA       = /((?:\s*#{REGEX_SINGLE}\s*)(?:,\s*#{REGEX_SINGLE}\s*)*)/i
+    REGEX_LIST_MKDN        = /((?<=\n)\s{0,3}#{REGEX_BULLET}\s#{REGEX_SINGLE}\s*)+/i # (see REGEX_LIST_ITEM)
+    ### process
+    REGEX_BLOCK_TYPES      = /((?<!\n)(?:#{REGEX_LIST_COMMA})|#{REGEX_LIST_MKDN})/i
+    REGEX_WIKI_LINK_BLOCKS = /^\s{0,3}#{REGEX_LINK_TYPE_TXT}#{REGEX_LINK_TYPE}(?:\s*|\G)(?<items>#{REGEX_BLOCK_TYPES})\n/i
   end
 end