asciidoctor 2.0.7 → 2.0.8

data/lib/asciidoctor/abstract_block.rb

@@ -38,12 +38,13 @@ class AbstractBlock < AbstractNode
     @blocks = []
     @subs = []
     @id = @title = @caption = @numeral = @style = @default_subs = @source_location = nil
-    case context
-    when :document, :section
+    if context == :document || context == :section
       @level = @next_section_index = 0
       @next_section_ordinal = 1
+    elsif AbstractBlock === parent
+      @level = parent.level
     else
-      @level = AbstractBlock === parent ? parent.level : nil
+      @level = nil
     end
   end
 

data/lib/asciidoctor/abstract_node.rb

@@ -310,14 +310,10 @@ class AbstractNode
   # Returns A String reference or data URI for the target image
   def image_uri(target_image, asset_dir_key = 'imagesdir')
     if (doc = @document).safe < SafeMode::SECURE && (doc.attr? 'data-uri')
-      if ((Helpers.uriish? target_image) && (target_image = Helpers.encode_uri target_image)) ||
+      if ((Helpers.uriish? target_image) && (target_image = Helpers.encode_spaces_in_uri target_image)) ||
           (asset_dir_key && (images_base = doc.attr asset_dir_key) && (Helpers.uriish? images_base) &&
           (target_image = normalize_web_path target_image, images_base, false))
-        if doc.attr? 'allow-uri-read'
-          generate_data_uri_from_uri target_image, (doc.attr? 'cache-uri')
-        else
-          target_image
-        end
+        (doc.attr? 'allow-uri-read') ? (generate_data_uri_from_uri target_image, (doc.attr? 'cache-uri')) : target_image
       else
         generate_data_uri target_image, asset_dir_key
       end
@@ -474,7 +470,7 @@ class AbstractNode
   # Returns the resolved [String] path
   def normalize_web_path(target, start = nil, preserve_uri_target = true)
     if preserve_uri_target && (Helpers.uriish? target)
-      Helpers.encode_uri target
+      Helpers.encode_spaces_in_uri target
     else
       @document.path_resolver.web_path target, start
     end

data/lib/asciidoctor/converter.rb

@@ -148,7 +148,7 @@ module Converter
     #
     # Returns nothing.
     def register_for *backends
-      Converter.register self, *backends
+      Converter.register self, *(backends.map {|backend| backend.to_s })
     end
   end
 

data/lib/asciidoctor/converter/docbook5.rb

@@ -25,8 +25,8 @@ class Converter::DocBook5Converter < Converter::Base
   MANPAGE_SECTION_TAGS = { 'section' => 'refsection', 'synopsis' => 'refsynopsisdiv' }
   TABLE_PI_NAMES = ['dbhtml', 'dbfo', 'dblatex']
 
-  CopyrightRx = /^(.+?)(?: ((?:\d{4}\-)?\d{4}))?$/
-  ImageMacroRx = /^image::?(.+?)\[(.*?)\]$/
+  CopyrightRx = /^(#{CC_ANY}+?)(?: ((?:\d{4}\-)?\d{4}))?$/
+  ImageMacroRx = /^image::?(\S|\S#{CC_ANY}*?\S)\[(#{CC_ANY}+)?\]$/
 
   def initialize backend, opts = {}
     @backend = backend
@@ -35,20 +35,8 @@ class Converter::DocBook5Converter < Converter::Base
 
   def convert_document node
     result = ['<?xml version="1.0" encoding="UTF-8"?>']
-    if node.attr? 'toc'
-      if node.attr? 'toclevels'
-        result << %(<?asciidoc-toc maxdepth="#{node.attr 'toclevels'}"?>)
-      else
-        result << '<?asciidoc-toc?>'
-      end
-    end
-    if node.attr? 'sectnums'
-      if node.attr? 'sectnumlevels'
-        result << %(<?asciidoc-numbered maxdepth="#{node.attr 'sectnumlevels'}"?>)
-      else
-        result << '<?asciidoc-numbered?>'
-      end
-    end
+    result << ((node.attr? 'toclevels') ? %(<?asciidoc-toc maxdepth="#{node.attr 'toclevels'}"?>) : '<?asciidoc-toc?>') if node.attr? 'toc'
+    result << ((node.attr? 'sectnumlevels') ? %(<?asciidoc-numbered maxdepth="#{node.attr 'sectnumlevels'}"?>) : '<?asciidoc-numbered?>') if node.attr? 'sectnums'
     lang_attribute = (node.attr? 'nolang') ? '' : %( xml:lang="#{node.attr 'lang', 'en'}")
     if (root_tag_name = node.doctype) == 'manpage'
       root_tag_name = 'refentry'
@@ -634,7 +622,7 @@ class Converter::DocBook5Converter < Converter::Base
       if (reftext.include? '<') && ((reftext = reftext.gsub XmlSanitizeRx, '').include? ' ')
         reftext = (reftext.squeeze ' ').strip
       end
-      reftext = (reftext.gsub '"', '&quot;') if reftext.include? '"'
+      reftext = reftext.gsub '"', '&quot;' if reftext.include? '"'
       %(#{attrs} xreflabel="#{reftext}")
     else
       attrs
@@ -742,7 +730,7 @@ class Converter::DocBook5Converter < Converter::Base
       if (cover_image.include? ':') && ImageMacroRx =~ cover_image
         attrlist = $2
         cover_image = doc.image_uri $1
-        unless attrlist.empty?
+        if attrlist
           attrs = (AttributeList.new attrlist).parse ['alt', 'width', 'height']
           if attrs.key? 'scaledwidth'
             # NOTE scalefit="1" is the default in this case

data/lib/asciidoctor/converter/html5.rb

@@ -23,9 +23,15 @@ class Converter::Html5Converter < Converter::Base
 
   DropAnchorRx = /<(?:a[^>+]+|\/a)>/
   StemBreakRx = / *\\\n(?:\\?\n)*|\n\n+/
-  SvgPreambleRx = /\A.*?(?=<svg\b)/m
-  SvgStartTagRx = /\A<svg[^>]*>/
-  DimensionAttributeRx = /\s(?:width|height|style)=(["']).*?\1/
+  if RUBY_ENGINE == 'opal'
+    # NOTE In JavaScript, ^ matches the start of the string when the m flag is not set
+    SvgPreambleRx = /^#{CC_ALL}*?(?=<svg\b)/
+    SvgStartTagRx = /^<svg[^>]*>/
+  else
+    SvgPreambleRx = /\A.*?(?=<svg\b)/m
+    SvgStartTagRx = /\A<svg[^>]*>/
+  end
+  DimensionAttributeRx = /\s(?:width|height|style)=(["'])#{CC_ANY}*?\1/
 
   def initialize backend, opts = {}
     @backend = backend

data/lib/asciidoctor/converter/manpage.rb

@@ -17,7 +17,7 @@ class Converter::ManPageConverter < Converter::Base
 
   LiteralBackslashRx = /(?:\A|[^#{ESC}])\\/
   LeadingPeriodRx = /^\./
-  EscapedMacroRx = /^(?:#{ESC}\\c\n)?#{ESC}\.((?:URL|MTO) ".*?" ".*?" )( |[^\s]*)(.*?)(?: *#{ESC}\\c)?$/
+  EscapedMacroRx = /^(?:#{ESC}\\c\n)?#{ESC}\.((?:URL|MTO) "#{CC_ANY}*?" "#{CC_ANY}*?" )( |[^\s]*)(#{CC_ANY}*?)(?: *#{ESC}\\c)?$/
   MockBoundaryRx = /<\/?BOUNDARY>/
   EmDashCharRefRx = /&#8212;(?:&#8203;)?/
   EllipsisCharRefRx = /&#8230;(?:&#8203;)?/

data/lib/asciidoctor/converter/template.rb

@@ -34,8 +34,8 @@ class Converter::TemplateConverter < Converter::Base
   }
 
   begin
-    require 'concurrent/hash' unless defined? ::Concurrent::Hash
-    @caches = { scans: ::Concurrent::Hash.new, templates: ::Concurrent::Hash.new }
+    require 'concurrent/map' unless defined? ::Concurrent::Map
+    @caches = { scans: ::Concurrent::Map.new, templates: ::Concurrent::Map.new }
   rescue ::LoadError
     @caches = { scans: {}, templates: {} }
   end
@@ -71,7 +71,7 @@ class Converter::TemplateConverter < Converter::Base
     end
     case opts[:template_cache]
     when true
-      logger.warn 'optional gem \'concurrent-ruby\' is not available. This gem is recommended when using the default template cache.' unless defined? ::Concurrent::Hash
+      logger.warn 'optional gem \'concurrent-ruby\' is not available. This gem is recommended when using the default template cache.' unless defined? ::Concurrent::Map
       @caches = self.class.caches
     when ::Hash
       @caches = opts[:template_cache]

data/lib/asciidoctor/extensions.rb

@@ -622,7 +622,7 @@ module Extensions
 
     def resolve_regexp name, format
       raise ::ArgumentError, %(invalid name for inline macro: #{name}) unless MacroNameRx.match? name
-      @@rx_cache[[name, format]] ||= /\\?#{name}:#{format == :short ? '(){0}' : '(\S+?)'}\[(|.*?[^\\])\]/
+      @@rx_cache[[name, format]] ||= /\\?#{name}:#{format == :short ? '(){0}' : '(\S+?)'}\[(|#{CC_ANY}*?[^\\])\]/
     end
   end
 

data/lib/asciidoctor/helpers.rb

@@ -2,7 +2,9 @@
 module Asciidoctor
 # Internal: Except where noted, a module that contains internal helper functions.
 module Helpers
-  # Internal: Require the specified library using Kernel#require.
+  module_function
+
+  # Public: Require the specified library using Kernel#require.
   #
   # Attempts to load the library specified in the first argument using the
   # Kernel#require. Rescues the LoadError if the library is not available and
@@ -21,7 +23,7 @@ module Helpers
   # Otherwise, if on_failure is :abort, Kernel#raise is called with an appropriate message.
   # Otherwise, if on_failure is :warn, Kernel#warn is called with an appropriate message and nil returned.
   # Otherwise, nil is returned.
-  def self.require_library name, gem_name = true, on_failure = :abort
+  def require_library name, gem_name = true, on_failure = :abort
     require name
   rescue ::LoadError
     include Logging unless include? Logging
@@ -57,7 +59,7 @@ module Helpers
   # data - the source data Array to prepare (no nil entries allowed)
   #
   # returns a String Array of prepared lines
-  def self.prepare_source_array data
+  def prepare_source_array data
     return [] if data.empty?
     if (leading_2_bytes = (leading_bytes = (first = data[0]).unpack 'C3').slice 0, 2) == BOM_BYTES_UTF_16LE
       data[0] = first.byteslice 2, first.bytesize
@@ -87,7 +89,7 @@ module Helpers
   # data - the source data String to prepare
   #
   # returns a String Array of prepared lines
-  def self.prepare_source_string data
+  def prepare_source_string data
     return [] if data.nil_or_empty?
     if (leading_2_bytes = (leading_bytes = data.unpack 'C3').slice 0, 2) == BOM_BYTES_UTF_16LE
       data = (data.byteslice 2, data.bytesize).encode UTF_8, ::Encoding::UTF_16LE
@@ -110,29 +112,17 @@ module Helpers
   # str - the String to check
   #
   # returns true if the String is a URI, false if it is not
-  def self.uriish? str
+  def uriish? str
     (str.include? ':') && (UriSniffRx.match? str)
   end
 
-  # Internal: Efficiently retrieves the URI prefix of the specified String
-  #
-  # Uses the Asciidoctor::UriSniffRx regex to match the URI prefix in the
-  # specified String (e.g., http://), if present.
-  #
-  # str - the String to check
-  #
-  # returns the string URI prefix if the string is a URI, otherwise nil
-  def self.uri_prefix str
-    (str.include? ':') && UriSniffRx =~ str ? $& : nil
-  end
-
   # Internal: Encode a URI component String for safe inclusion in a URI.
   #
   # str - the URI component String to encode
   #
   # Returns the String with all reserved URI characters encoded (e.g., /, &, =, space, etc).
   if RUBY_ENGINE == 'opal'
-    def self.encode_uri_component str
+    def encode_uri_component str
       # patch necessary to adhere with RFC-3986 (and thus CGI.escape)
       # see https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/encodeURIComponent#Description
       %x(
@@ -143,17 +133,17 @@ module Helpers
     end
   else
     CGI = ::CGI
-    def self.encode_uri_component str
+    def encode_uri_component str
       CGI.escape str
     end
   end
 
-  # Internal: Encode a URI String (namely the path portion).
+  # Internal: Apply URI path encoding to spaces in the specified string (i.e., convert spaces to %20).
   #
   # str - the String to encode
   #
-  # Returns the String with all spaces replaced with %20.
-  def self.encode_uri str
+  # Returns the specified String with all spaces replaced with %20.
+  def encode_spaces_in_uri str
     (str.include? ' ') ? (str.gsub ' ', '%20') : str
   end
 
@@ -167,7 +157,7 @@ module Helpers
   #   # => "part1/chapter1"
   #
   # Returns the String filename with the file extension removed
-  def self.rootname filename
+  def rootname filename
     if (last_dot_idx = filename.rindex '.')
       (filename.index '/', last_dot_idx) ? filename : (filename.slice 0, last_dot_idx)
     else
@@ -190,7 +180,7 @@ module Helpers
   #   # => "tiger"
   #
   # Returns the String filename with leading directories removed and, if specified, the extension removed
-  def self.basename filename, drop_ext = nil
+  def basename filename, drop_ext = nil
     if drop_ext
       ::File.basename filename, (drop_ext == true ? (extname filename) : drop_ext)
     else
@@ -203,7 +193,7 @@ module Helpers
   # path - The path String to check; expects a posix path
   #
   # Returns true if the path has a file extension, false otherwise
-  def self.extname? path
+  def extname? path
     (last_dot_idx = path.rindex '.') && !(path.index '/', last_dot_idx)
   end
 
@@ -217,7 +207,7 @@ module Helpers
   #
   # Returns the String file extension (with the leading dot included) or the fallback value if the path has no file extension.
   if ::File::ALT_SEPARATOR
-    def self.extname path, fallback = ''
+    def extname path, fallback = ''
       if (last_dot_idx = path.rindex '.')
         (path.index '/', last_dot_idx) || (path.index ::File::ALT_SEPARATOR, last_dot_idx) ? fallback : (path.slice last_dot_idx, path.length)
       else
@@ -225,7 +215,7 @@ module Helpers
       end
     end
   else
-    def self.extname path, fallback = ''
+    def extname path, fallback = ''
       if (last_dot_idx = path.rindex '.')
         (path.index '/', last_dot_idx) ? fallback : (path.slice last_dot_idx, path.length)
       else
@@ -235,7 +225,7 @@ module Helpers
   end
 
   # Internal: Make a directory, ensuring all parent directories exist.
-  def self.mkdir_p dir
+  def mkdir_p dir
     unless ::File.directory? dir
       unless (parent_dir = ::File.dirname dir) == '.'
         mkdir_p parent_dir
@@ -252,13 +242,14 @@ module Helpers
     'M' => 1000, 'CM' => 900, 'D' => 500, 'CD' => 400, 'C' => 100, 'XC' => 90,
     'L' => 50, 'XL' => 40, 'X' => 10, 'IX' => 9, 'V' => 5, 'IV' => 4, 'I' => 1
   }
+  private_constant :ROMAN_NUMERALS
 
   # Internal: Converts an integer to a Roman numeral.
   #
   # val - the [Integer] value to convert
   #
   # Returns the [String] roman numeral for this integer
-  def self.int_to_roman val
+  def int_to_roman val
     ROMAN_NUMERALS.map do |l, i|
       repeat, val = val.divmod i
       l * repeat
@@ -272,7 +263,7 @@ module Helpers
   # current - the value to increment as a String or Integer
   #
   # returns the next value in the sequence according to the current value's type
-  def self.nextval current
+  def nextval current
     if ::Integer === current
       current + 1
     else
@@ -291,14 +282,14 @@ module Helpers
   #
   # Returns a Class if the specified object is a Class (but not a Module) or
   # a String that resolves to a Class; otherwise, nil
-  def self.resolve_class object
+  def resolve_class object
     ::Class === object ? object : (::String === object ? (class_for_name object) : nil)
   end
 
   # Internal: Resolves a Class object (not a Module) for the qualified name.
   #
   # Returns Class
-  def self.class_for_name qualified_name
+  def class_for_name qualified_name
     raise unless ::Class === (resolved = ::Object.const_get qualified_name, false)
     resolved
   rescue

data/lib/asciidoctor/path_resolver.rb

@@ -476,25 +476,15 @@ class PathResolver
   def web_path target, start = nil
     target = posixify target
     start = posixify start
-    uri_prefix = nil
 
     unless start.nil_or_empty? || (web_root? target)
-      target = (start.end_with? SLASH) ? %(#{start}#{target}) : %(#{start}#{SLASH}#{target})
-      if (uri_prefix = Helpers.uri_prefix target)
-        target = target[uri_prefix.length..-1]
-      end
+      target, uri_prefix = extract_uri_prefix %(#{start}#{(start.end_with? SLASH) ? '' : SLASH}#{target})
     end
 
     # use this logic instead if we want to normalize target if it contains a URI
     #unless web_root? target
-    #  if preserve_uri_target && (uri_prefix = Helpers.uri_prefix target)
-    #    target = target[uri_prefix.length..-1]
-    #  elsif !start.nil_or_empty?
-    #    target = %(#{start}#{SLASH}#{target})
-    #    if (uri_prefix = Helpers.uri_prefix target)
-    #      target = target[uri_prefix.length..-1]
-    #    end
-    #  end
+    #  target, uri_prefix = extract_uri_prefix target if preserve_uri_target
+    #  target, uri_prefix = extract_uri_prefix %(#{start}#{SLASH}#{target}) unless uri_prefix || start.nil_or_empty?
     #end
 
     target_segments, target_root = partition_path target, true
@@ -521,5 +511,23 @@ class PathResolver
 
     uri_prefix ? %(#{uri_prefix}#{resolved_path}) : resolved_path
   end
+
+  private
+
+  # Internal: Efficiently extracts the URI prefix from the specified String if the String is a URI
+  #
+  # Uses the Asciidoctor::UriSniffRx regex to match the URI prefix in the specified String (e.g., http://). If present,
+  # the prefix is removed.
+  #
+  # str - the String to check
+  #
+  # returns a tuple containing the specified string without the URI prefix, if present, and the extracted URI prefix.
+  def extract_uri_prefix str
+    if (str.include? ':') && UriSniffRx =~ str
+      [(str.slice $&.length, str.length), $&]
+    else
+      str
+    end
+  end
 end
 end

data/lib/asciidoctor/rx.rb

@@ -0,0 +1,720 @@
+module Asciidoctor
+  # A collection of regular expression constants used by the parser. (For speed, these are not defined in the Rx module,
+  # but rather directly in the Asciidoctor module).
+  #
+  # NOTE The following pattern, which appears frequently, captures the contents between square brackets, ignoring
+  # escaped closing brackets (closing brackets prefixed with a backslash '\' character)
+  #
+  #   Pattern: \[(|#{CC_ALL}*?[^\\])\]
+  #   Matches: [enclosed text] and [enclosed [text\]], not [enclosed text \\] or [\\] (as these require a trailing space)
+  module Rx; end
+
+  ## Document header
+
+  # Matches the author info line immediately following the document title.
+  #
+  # Examples
+  #
+  #   Doc Writer <doc@example.com>
+  #   Mary_Sue Brontë
+  #
+  AuthorInfoLineRx = /^(#{CG_WORD}[#{CC_WORD}\-'.]*)(?: +(#{CG_WORD}[#{CC_WORD}\-'.]*))?(?: +(#{CG_WORD}[#{CC_WORD}\-'.]*))?(?: +<([^>]+)>)?$/
+
+  # Matches the delimiter that separates multiple authors.
+  #
+  # Examples
+  #
+  #   Doc Writer; Junior Writer
+  #
+  AuthorDelimiterRx = /;(?: |$)/
+
+  # Matches the revision info line, which appears immediately following
+  # the author info line beneath the document title.
+  #
+  # Examples
+  #
+  #   v1.0
+  #   2013-01-01
+  #   v1.0, 2013-01-01: Ring in the new year release
+  #   1.0, Jan 01, 2013
+  #
+  RevisionInfoLineRx = /^(?:[^\d{]*(#{CC_ANY}*?),)? *(?!:)(#{CC_ANY}*?)(?: *(?!^),?: *(#{CC_ANY}*))?$/
+
+  # Matches the title and volnum in the manpage doctype.
+  #
+  # Examples
+  #
+  #   = asciidoctor(1)
+  #   = asciidoctor ( 1 )
+  #
+  ManpageTitleVolnumRx = /^(#{CC_ANY}+?) *\( *(#{CC_ANY}+?) *\)$/
+
+  # Matches the name and purpose in the manpage doctype.
+  #
+  # Examples
+  #
+  #   asciidoctor - converts AsciiDoc source files to HTML, DocBook and other formats
+  #
+  ManpageNamePurposeRx = /^(#{CC_ANY}+?) +- +(#{CC_ANY}+)$/
+
+  ## Preprocessor directives
+
+  # Matches a conditional preprocessor directive (e.g., ifdef, ifndef, ifeval and endif).
+  #
+  # Examples
+  #
+  #   ifdef::basebackend-html[]
+  #   ifndef::theme[]
+  #   ifeval::["{asciidoctor-version}" >= "0.1.0"]
+  #   ifdef::asciidoctor[Asciidoctor!]
+  #   endif::theme[]
+  #   endif::basebackend-html[]
+  #   endif::[]
+  #
+  ConditionalDirectiveRx = /^(\\)?(ifdef|ifndef|ifeval|endif)::(\S*?(?:([,+])\S*?)?)\[(#{CC_ANY}+)?\]$/
+
+  # Matches a restricted (read as safe) eval expression.
+  #
+  # Examples
+  #
+  #   "{asciidoctor-version}" >= "0.1.0"
+  #
+  EvalExpressionRx = /^(#{CC_ANY}+?) *([=!><]=|[><]) *(#{CC_ANY}+)$/
+
+  # Matches an include preprocessor directive.
+  #
+  # Examples
+  #
+  #   include::chapter1.ad[]
+  #   include::example.txt[lines=1;2;5..10]
+  #
+  IncludeDirectiveRx = /^(\\)?include::([^\[][^\[]*)\[(#{CC_ANY}+)?\]$/
+
+  # Matches a trailing tag directive in an include file.
+  #
+  # Examples
+  #
+  #   // tag::try-catch[]
+  #   try {
+  #     someMethod();
+  #   catch (Exception e) {
+  #     log(e);
+  #   }
+  #   // end::try-catch[]
+  # NOTE m flag is required for Asciidoctor.js
+  TagDirectiveRx = /\b(?:tag|(e)nd)::(\S+?)\[\](?=$|[ \r])/m
+
+  ## Attribute entries and references
+
+  # Matches a document attribute entry.
+  #
+  # Examples
+  #
+  #   :foo: bar
+  #   :First Name: Dan
+  #   :sectnums!:
+  #   :!toc:
+  #   :long-entry: Attribute value lines ending in ' \' \
+  #                are joined together as a single value, \
+  #                collapsing the line breaks and indentation to \
+  #                a single space.
+  #
+  AttributeEntryRx = /^:(!?#{CG_WORD}[^:]*):(?:[ \t]+(#{CC_ANY}*))?$/
+
+  # Matches invalid characters in an attribute name.
+  InvalidAttributeNameCharsRx = /[^#{CC_WORD}-]/
+
+  # Matches a pass inline macro that surrounds the value of an attribute
+  # entry once it has been parsed.
+  #
+  # Examples
+  #
+  #   pass:[text]
+  #   pass:a[{a} {b} {c}]
+  #
+  if RUBY_ENGINE == 'opal'
+    # NOTE In JavaScript, ^ and $ match the boundaries of the string when the m flag is not set
+    AttributeEntryPassMacroRx = /^pass:([a-z]+(?:,[a-z-]+)*)?\[(#{CC_ALL}*)\]$/
+  else
+    AttributeEntryPassMacroRx = /\Apass:([a-z]+(?:,[a-z-]+)*)?\[(.*)\]\Z/m
+  end
+
+  # Matches an inline attribute reference.
+  #
+  # Examples
+  #
+  #   {foobar} or {app_name} or {product-version}
+  #   {counter:sequence-name:1}
+  #   {set:foo:bar}
+  #   {set:name!}
+  #
+  AttributeReferenceRx = /(\\)?\{(#{CG_WORD}[#{CC_WORD}-]*|(set|counter2?):#{CC_ANY}+?)(\\)?\}/
+
+  ## Paragraphs and delimited blocks
+
+  # Matches an anchor (i.e., id + optional reference text) on a line above a block.
+  #
+  # Examples
+  #
+  #   [[idname]]
+  #   [[idname,Reference Text]]
+  #
+  BlockAnchorRx = /^\[\[(?:|([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)(?:, *(#{CC_ANY}+))?)\]\]$/
+
+  # Matches an attribute list above a block element.
+  #
+  # Examples
+  #
+  #   # strictly positional
+  #   [quote, Adam Smith, Wealth of Nations]
+  #
+  #   # name/value pairs
+  #   [NOTE, caption="Good to know"]
+  #
+  #   # as attribute reference
+  #   [{lead}]
+  #
+  BlockAttributeListRx = /^\[(|[#{CC_WORD}.#%{,"']#{CC_ANY}*)\]$/
+
+  # A combined pattern that matches either a block anchor or a block attribute list.
+  #
+  # TODO this one gets hit a lot, should be optimized as much as possible
+  BlockAttributeLineRx = /^\[(?:|[#{CC_WORD}.#%{,"']#{CC_ANY}*|\[(?:|[#{CC_ALPHA}_:][#{CC_WORD}\-:.]*(?:, *#{CC_ANY}+)?)\])\]$/
+
+  # Matches a title above a block.
+  #
+  # Examples
+  #
+  #   .Title goes here
+  #
+  BlockTitleRx = /^\.(\.?[^ \t.]#{CC_ANY}*)$/
+
+  # Matches an admonition label at the start of a paragraph.
+  #
+  # Examples
+  #
+  #   NOTE: Just a little note.
+  #   TIP: Don't forget!
+  #
+  AdmonitionParagraphRx = /^(#{ADMONITION_STYLES.to_a.join '|'}):[ \t]+/
+
+  # Matches a literal paragraph, which is a line of text preceded by at least one space.
+  #
+  # Examples
+  #
+  #   <SPACE>Foo
+  #   <TAB>Foo
+  LiteralParagraphRx = /^([ \t]+#{CC_ANY}*)$/
+
+  # Matches a comment block.
+  #
+  # Examples
+  #
+  #   ////
+  #   This is a block comment.
+  #   It can span one or more lines.
+  #   ////
+  #CommentBlockRx = %r(^/{4,}$)
+
+  # Matches a comment line.
+  #
+  # Examples
+  #
+  #   // note to author
+  #
+  #CommentLineRx = %r(^//(?=[^/]|$))
+
+  ## Section titles
+
+  # Matches an Atx (single-line) section title.
+  #
+  # Examples
+  #
+  #   == Foo
+  #   // ^ a level 1 (h2) section title
+  #
+  #   == Foo ==
+  #   // ^ also a level 1 (h2) section title
+  #
+  AtxSectionTitleRx = /^(=={0,5})[ \t]+(#{CC_ANY}+?)(?:[ \t]+\1)?$/
+
+  # Matches an extended Atx section title that includes support for the Markdown variant.
+  ExtAtxSectionTitleRx = /^(=={0,5}|#\#{0,5})[ \t]+(#{CC_ANY}+?)(?:[ \t]+\1)?$/
+
+  # Matches the title only (first line) of an Setext (two-line) section title.
+  # The title cannot begin with a dot and must have at least one alphanumeric character.
+  SetextSectionTitleRx = /^((?!\.)#{CC_ANY}*?#{CG_ALNUM}#{CC_ANY}*)$/
+
+  # Matches an anchor (i.e., id + optional reference text) inside a section title.
+  #
+  # Examples
+  #
+  #   Section Title [[idname]]
+  #   Section Title [[idname,Reference Text]]
+  #
+  InlineSectionAnchorRx = / (\\)?\[\[([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)(?:, *(#{CC_ANY}+))?\]\]$/
+
+  # Matches invalid ID characters in a section title.
+  #
+  # NOTE uppercase chars not included since expression is only run on a lowercase string
+  InvalidSectionIdCharsRx = /<[^>]+>|&(?:[a-z][a-z]+\d{0,2}|#\d\d\d{0,4}|#x[\da-f][\da-f][\da-f]{0,3});|[^ #{CC_WORD}\-.]+?/
+
+  # Matches an explicit section level style like sect1
+  #
+  SectionLevelStyleRx = /^sect\d$/
+
+  ## Lists
+
+  # Detects the start of any list item.
+  #
+  # NOTE we only have to check as far as the blank character because we know it means non-whitespace follows.
+  # IMPORTANT if this regexp does not agree with the regexp for each list type, the parser will hang.
+  AnyListRx = %r(^(?:[ \t]*(?:-|\*\**|\.\.*|\u2022|\d+\.|[a-zA-Z]\.|[IVXivx]+\))[ \t]|(?!//[^/])[ \t]*[^ \t]#{CC_ANY}*?(?::::{0,2}|;;)(?:$|[ \t])|<?\d+>[ \t]))
+
+  # Matches an unordered list item (one level for hyphens, up to 5 levels for asterisks).
+  #
+  # Examples
+  #
+  #   * Foo
+  #   - Foo
+  #
+  # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
+  UnorderedListRx = /^[ \t]*(-|\*\**|\u2022)[ \t]+(#{CC_ANY}*)$/
+
+  # Matches an ordered list item (explicit numbering or up to 5 consecutive dots).
+  #
+  # Examples
+  #
+  #   . Foo
+  #   .. Foo
+  #   1. Foo (arabic, default)
+  #   a. Foo (loweralpha)
+  #   A. Foo (upperalpha)
+  #   i. Foo (lowerroman)
+  #   I. Foo (upperroman)
+  #
+  # NOTE leading space match is not always necessary, but is used for list reader
+  # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
+  OrderedListRx = /^[ \t]*(\.\.*|\d+\.|[a-zA-Z]\.|[IVXivx]+\))[ \t]+(#{CC_ANY}*)$/
+
+  # Matches the ordinals for each type of ordered list.
+  OrderedListMarkerRxMap = {
+    arabic: /\d+\./,
+    loweralpha: /[a-z]\./,
+    lowerroman: /[ivx]+\)/,
+    upperalpha: /[A-Z]\./,
+    upperroman: /[IVX]+\)/,
+    #lowergreek: /[a-z]\]/,
+  }
+
+  # Matches a description list entry.
+  #
+  # Examples
+  #
+  #   foo::
+  #   bar:::
+  #   baz::::
+  #   blah;;
+  #
+  #   # the term may be followed by a description on the same line...
+  #
+  #   foo:: The metasyntactic variable that commonly accompanies 'bar' (see also, <<bar>>).
+  #
+  #   # ...or on a separate line, which may optionally be indented
+  #
+  #   foo::
+  #     The metasyntactic variable that commonly accompanies 'bar' (see also, <<bar>>).
+  #
+  #   # attribute references may be used in both the term and the description
+  #
+  #   {foo-term}:: {foo-desc}
+  #
+  # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
+  # NOTE must skip line comment when looking for next list item inside list
+  DescriptionListRx = %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?)(:::{0,2}|;;)(?:$|[ \t]+(#{CC_ANY}*)$))
+
+  # Matches a sibling description list item (excluding the delimiter specified by the key).
+  # NOTE must skip line comment when looking for sibling list item
+  DescriptionListSiblingRx = {
+    '::' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?[^:]|[^ \t:])(::)(?:$|[ \t]+(#{CC_ANY}*)$)),
+    ':::' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?[^:]|[^ \t:])(:::)(?:$|[ \t]+(#{CC_ANY}*)$)),
+    '::::' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?[^:]|[^ \t:])(::::)(?:$|[ \t]+(#{CC_ANY}*)$)),
+    ';;' => %r(^(?!//[^/])[ \t]*([^ \t]#{CC_ANY}*?)(;;)(?:$|[ \t]+(#{CC_ANY}*)$))
+  }
+
+  # Matches a callout list item.
+  #
+  # Examples
+  #
+  #   <1> Explanation
+  #
+  # or
+  #
+  #   <.> Explanation with automatic number
+  #
+  # NOTE we know trailing (.*) will match at least one character because we strip trailing spaces
+  CalloutListRx = /^<(\d+|\.)>[ \t]+(#{CC_ANY}*)$/
+
+  # Matches a callout reference inside literal text.
+  #
+  # Examples
+  #   <1> (optionally prefixed by //, #, -- or ;; line comment chars)
+  #   <1> <2> (multiple callouts on one line)
+  #   <!--1--> (for XML-based languages)
+  #   <.> (auto-numbered)
+  #
+  # NOTE extract regexps are applied line-by-line, so we can use $ as end-of-line char
+  CalloutExtractRx = %r(((?://|#|--|;;) ?)?(\\)?<!?(|--)(\d+|\.)\3>(?=(?: ?\\?<!?\3(?:\d+|\.)\3>)*$))
+  CalloutExtractRxt = '(\\\\)?<()(\\d+|\\.)>(?=(?: ?\\\\?<(?:\\d+|\\.)>)*$)'
+  CalloutExtractRxMap = ::Hash.new {|h, k| h[k] = /(#{k.empty? ? '' : "#{::Regexp.escape k} ?"})?#{CalloutExtractRxt}/ }
+  # NOTE special characters have not been replaced when scanning
+  CalloutScanRx = /\\?<!?(|--)(\d+|\.)\1>(?=(?: ?\\?<!?\1(?:\d+|\.)\1>)*#{CC_EOL})/
+  # NOTE special characters have already been replaced when converting to an SGML format
+  CalloutSourceRx = %r(((?://|#|--|;;) ?)?(\\)?&lt;!?(|--)(\d+|\.)\3&gt;(?=(?: ?\\?&lt;!?\3(?:\d+|\.)\3&gt;)*#{CC_EOL}))
+  CalloutSourceRxt = "(\\\\)?&lt;()(\\d+|\\.)&gt;(?=(?: ?\\\\?&lt;(?:\\d+|\\.)&gt;)*#{CC_EOL})"
+  CalloutSourceRxMap = ::Hash.new {|h, k| h[k] = /(#{k.empty? ? '' : "#{::Regexp.escape k} ?"})?#{CalloutSourceRxt}/ }
+
+  # A Hash of regexps for lists used for dynamic access.
+  ListRxMap = { ulist: UnorderedListRx, olist: OrderedListRx, dlist: DescriptionListRx, colist: CalloutListRx }
+
+  ## Tables
+
+  # Parses the column spec (i.e., colspec) for a table.
+  #
+  # Examples
+  #
+  #   1*h,2*,^3e
+  #
+  ColumnSpecRx = /^(?:(\d+)\*)?([<^>](?:\.[<^>]?)?|(?:[<^>]?\.)?[<^>])?(\d+%?|~)?([a-z])?$/
+
+  # Parses the start and end of a cell spec (i.e., cellspec) for a table.
+  #
+  # Examples
+  #
+  #   2.3+<.>m
+  #
+  # FIXME use step-wise scan (or treetop) rather than this mega-regexp
+  CellSpecStartRx = /^[ \t]*(?:(\d+(?:\.\d*)?|(?:\d*\.)?\d+)([*+]))?([<^>](?:\.[<^>]?)?|(?:[<^>]?\.)?[<^>])?([a-z])?$/
+  CellSpecEndRx = /[ \t]+(?:(\d+(?:\.\d*)?|(?:\d*\.)?\d+)([*+]))?([<^>](?:\.[<^>]?)?|(?:[<^>]?\.)?[<^>])?([a-z])?$/
+
+  # Block macros
+
+  # Matches the custom block macro pattern.
+  #
+  # Examples
+  #
+  #   gist::123456[]
+  #
+  #--
+  # NOTE we've relaxed the match for target to accomodate the short format (e.g., name::[attrlist])
+  CustomBlockMacroRx = /^(#{CG_WORD}[#{CC_WORD}-]*)::(|\S|\S#{CC_ANY}*?\S)\[(#{CC_ANY}+)?\]$/
+
+  # Matches an image, video or audio block macro.
+  #
+  # Examples
+  #
+  #   image::filename.png[Caption]
+  #   video::http://youtube.com/12345[Cats vs Dogs]
+  #
+  BlockMediaMacroRx = /^(image|video|audio)::(\S|\S#{CC_ANY}*?\S)\[(#{CC_ANY}+)?\]$/
+
+  # Matches the TOC block macro.
+  #
+  # Examples
+  #
+  #   toc::[]
+  #   toc::[levels=2]
+  #
+  BlockTocMacroRx = /^toc::\[(#{CC_ANY}+)?\]$/
+
+  ## Inline macros
+
+  # Matches an anchor (i.e., id + optional reference text) in the flow of text.
+  #
+  # Examples
+  #
+  #   [[idname]]
+  #   [[idname,Reference Text]]
+  #   anchor:idname[]
+  #   anchor:idname[Reference Text]
+  #
+  InlineAnchorRx = /(\\)?(?:\[\[([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)(?:, *(#{CC_ANY}+?))?\]\]|anchor:([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)\[(?:\]|(#{CC_ANY}*?[^\\])\]))/
+
+  # Scans for a non-escaped anchor (i.e., id + optional reference text) in the flow of text.
+  InlineAnchorScanRx = /(?:^|[^\\\[])\[\[([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)(?:, *(#{CC_ANY}+?))?\]\]|(?:^|[^\\])anchor:([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)\[(?:\]|(#{CC_ANY}*?[^\\])\])/
+
+  # Scans for a leading, non-escaped anchor (i.e., id + optional reference text).
+  LeadingInlineAnchorRx = /^\[\[([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)(?:, *(#{CC_ANY}+?))?\]\]/
+
+  # Matches a bibliography anchor at the start of the list item text (in a bibliography list).
+  #
+  # Examples
+  #
+  #   [[[Fowler_1997]]] Fowler M. ...
+  #
+  InlineBiblioAnchorRx = /^\[\[\[([#{CC_ALPHA}_:][#{CC_WORD}\-:.]*)(?:, *(#{CC_ANY}+?))?\]\]\]/
+
+  # Matches an inline e-mail address.
+  #
+  #   doc.writer@example.com
+  #
+  InlineEmailRx = %r(([\\>:/])?#{CG_WORD}(?:&amp;|[#{CC_WORD}\-.%+])*@#{CG_ALNUM}[#{CC_ALNUM}_\-.]*\.[a-zA-Z]{2,5}\b)
+
+  # Matches an inline footnote macro, which is allowed to span multiple lines.
+  #
+  # Examples
+  #   footnote:[text] (not referenceable)
+  #   footnote:id[text] (referenceable)
+  #   footnote:id[] (reference)
+  #   footnoteref:[id,text] (legacy)
+  #   footnoteref:[id] (legacy)
+  #
+  InlineFootnoteMacroRx = /\\?footnote(?:(ref):|:([#{CC_WORD}-]+)?)\[(?:|(#{CC_ALL}*?[^\\]))\]/m
+
+  # Matches an image or icon inline macro.
+  #
+  # Examples
+  #
+  #   image:filename.png[Alt Text]
+  #   image:http://example.com/images/filename.png[Alt Text]
+  #   image:filename.png[More [Alt\] Text] (alt text becomes "More [Alt] Text")
+  #   icon:github[large]
+  #
+  # NOTE be as non-greedy as possible by not allowing newline or left square bracket in target
+  InlineImageMacroRx = /\\?i(?:mage|con):([^:\s\[](?:[^\n\[]*[^\s\[])?)\[(|#{CC_ALL}*?[^\\])\]/m
+
+  # Matches an indexterm inline macro, which may span multiple lines.
+  #
+  # Examples
+  #
+  #   indexterm:[Tigers,Big cats]
+  #   (((Tigers,Big cats)))
+  #   indexterm2:[Tigers]
+  #   ((Tigers))
+  #
+  InlineIndextermMacroRx = /\\?(?:(indexterm2?):\[(#{CC_ALL}*?[^\\])\]|\(\((#{CC_ALL}+?)\)\)(?!\)))/m
+
+  # Matches either the kbd or btn inline macro.
+  #
+  # Examples
+  #
+  #   kbd:[F3]
+  #   kbd:[Ctrl+Shift+T]
+  #   kbd:[Ctrl+\]]
+  #   kbd:[Ctrl,T]
+  #   btn:[Save]
+  #
+  InlineKbdBtnMacroRx = /(\\)?(kbd|btn):\[(#{CC_ALL}*?[^\\])\]/m
+
+  # Matches an implicit link and some of the link inline macro.
+  #
+  # Examples
+  #
+  #   https://github.com
+  #   https://github.com[GitHub]
+  #   <https://github.com>
+  #   link:https://github.com[]
+  #
+  # FIXME revisit! the main issue is we need different rules for implicit vs explicit
+  InlineLinkRx = %r((^|link:|#{CG_BLANK}|&lt;|[>\(\)\[\];])(\\?(?:https?|file|ftp|irc)://[^\s\[\]<]*([^\s.,\[\]<]))(?:\[(|#{CC_ALL}*?[^\\])\])?)m
+
+  # Match a link or e-mail inline macro.
+  #
+  # Examples
+  #
+  #   link:path[label]
+  #   mailto:doc.writer@example.com[]
+  #
+  # NOTE be as non-greedy as possible by not allowing space or left square bracket in target
+  InlineLinkMacroRx = /\\?(?:link|(mailto)):(|[^:\s\[][^\s\[]*)\[(|#{CC_ALL}*?[^\\])\]/m
+
+  # Matches the name of a macro.
+  #
+  MacroNameRx = /^#{CG_WORD}[#{CC_WORD}-]*$/
+
+  # Matches a stem (and alternatives, asciimath and latexmath) inline macro, which may span multiple lines.
+  #
+  # Examples
+  #
+  #   stem:[x != 0]
+  #   asciimath:[x != 0]
+  #   latexmath:[\sqrt{4} = 2]
+  #
+  InlineStemMacroRx = /\\?(stem|(?:latex|ascii)math):([a-z]+(?:,[a-z-]+)*)?\[(#{CC_ALL}*?[^\\])\]/m
+
+  # Matches a menu inline macro.
+  #
+  # Examples
+  #
+  #   menu:File[Save As...]
+  #   menu:View[Page Style > No Style]
+  #   menu:View[Page Style, No Style]
+  #
+  InlineMenuMacroRx = /\\?menu:(#{CG_WORD}|[#{CC_WORD}&][^\n\[]*[^\s\[])\[ *(#{CC_ALL}*?[^\\])?\]/m
+
+  # Matches an implicit menu inline macro.
+  #
+  # Examples
+  #
+  #   "File > New..."
+  #
+  InlineMenuRx = /\\?"([#{CC_WORD}&][^"]*?[ \n]+&gt;[ \n]+[^"]*)"/
+
+  # Matches an inline passthrough, which may span multiple lines.
+  #
+  # Examples
+  #
+  #   +text+
+  #   `text` (compat)
+  #
+  # NOTE we always capture the attributes so we know when to use compatible (i.e., legacy) behavior
+  InlinePassRx = {
+    false => ['+', '`', /(^|[^#{CC_WORD};:])(?:\[([^\]]+)\])?(\\?(\+|`)(\S|\S#{CC_ALL}*?\S)\4)(?!#{CG_WORD})/m],
+    true  => ['`', nil, /(^|[^`#{CC_WORD}])(?:\[([^\]]+)\])?(\\?(`)([^`\s]|[^`\s]#{CC_ALL}*?\S)\4)(?![`#{CC_WORD}])/m]
+  }
+
+  # Matches an inline plus passthrough spanning multiple lines, but only when it occurs directly
+  # inside constrained monospaced formatting in non-compat mode.
+  #
+  # Examples
+  #
+  #   +text+
+  #
+  SinglePlusInlinePassRx = /^(\\)?\+(\S|\S#{CC_ALL}*?\S)\+$/m
+
+  # Matches several variants of the passthrough inline macro, which may span multiple lines.
+  #
+  # Examples
+  #
+  #   +++text+++
+  #   $$text$$
+  #   pass:quotes[text]
+  #
+  # NOTE we have to support an empty pass:[] for compatibility with AsciiDoc Python
+  InlinePassMacroRx = /(?:(?:(\\?)\[([^\]]+)\])?(\\{0,2})(\+\+\+?|\$\$)(#{CC_ALL}*?)\4|(\\?)pass:([a-z]+(?:,[a-z-]+)*)?\[(|#{CC_ALL}*?[^\\])\])/m
+
+  # Matches an xref (i.e., cross-reference) inline macro, which may span multiple lines.
+  #
+  # Examples
+  #
+  #   <<id,reftext>>
+  #   xref:id[reftext]
+  #
+  # NOTE special characters have already been escaped, hence the entity references
+  # NOTE { is included in start characters to support target that begins with attribute reference in title content
+  InlineXrefMacroRx = %r(\\?(?:&lt;&lt;([#{CC_WORD}#/.:{]#{CC_ALL}*?)&gt;&gt;|xref:([#{CC_WORD}#/.:{]#{CC_ALL}*?)\[(?:\]|(#{CC_ALL}*?[^\\])\])))m
+
+  ## Layout
+
+  # Matches a trailing + preceded by at least one space character,
+  # which forces a hard line break (<br> tag in HTML output).
+  #
+  # NOTE AsciiDoc Python allows + to be preceded by TAB; Asciidoctor does not
+  #
+  # Examples
+  #
+  #   Humpty Dumpty sat on a wall, +
+  #   Humpty Dumpty had a great fall.
+  #
+  if RUBY_ENGINE == 'opal'
+    # NOTE In JavaScript, ^ and $ only match the start and end of line if the multiline flag is present
+    HardLineBreakRx = /^(#{CC_ANY}*) \+$/m
+  else
+    # NOTE In Ruby, ^ and $ always match start and end of line
+    HardLineBreakRx = /^(.*) \+$/
+  end
+
+  # Matches a Markdown horizontal rule.
+  #
+  # Examples
+  #
+  #   --- or - - -
+  #   *** or * * *
+  #   ___ or _ _ _
+  #
+  MarkdownThematicBreakRx = /^ {0,3}([-*_])( *)\1\2\1$/
+
+  # Matches an AsciiDoc or Markdown horizontal rule or AsciiDoc page break.
+  #
+  # Examples
+  #
+  #   ''' (horizontal rule)
+  #   <<< (page break)
+  #   --- or - - - (horizontal rule, Markdown)
+  #   *** or * * * (horizontal rule, Markdown)
+  #   ___ or _ _ _ (horizontal rule, Markdown)
+  #
+  ExtLayoutBreakRx = /^(?:'{3,}|<{3,}|([-*_])( *)\1\2\1)$/
+
+  ## General
+
+  # Matches consecutive blank lines.
+  #
+  # Examples
+  #
+  #   one
+  #
+  #   two
+  #
+  BlankLineRx = /\n{2,}/
+
+  # Matches a comma or semi-colon delimiter.
+  #
+  # Examples
+  #
+  #   one,two
+  #   three;four
+  #
+  #DataDelimiterRx = /[,;]/
+
+  # Matches whitespace (space, tab, newline) escaped by a backslash.
+  #
+  # Examples
+  #
+  #   three\ blind\ mice
+  #
+  EscapedSpaceRx = /\\([ \t\n])/
+
+  # Detects if text is a possible candidate for the replacements substitution.
+  #
+  ReplaceableTextRx = /[&']|--|\.\.\.|\([CRT]M?\)/
+
+  # Matches a whitespace delimiter, a sequence of spaces, tabs, and/or newlines.
+  # Matches the parsing rules of %w strings in Ruby.
+  #
+  # Examples
+  #
+  #   one two	 three   four
+  #   five	six
+  #
+  # TODO change to /(?<!\\)[ \t\n]+/ once lookbehind assertions are implemented in all modern browsers
+  SpaceDelimiterRx = /([^\\])[ \t\n]+/
+
+  # Matches a + or - modifier in a subs list
+  #
+  SubModifierSniffRx = /[+-]/
+
+  # Matches one or more consecutive digits at the end of a line.
+  #
+  # Examples
+  #
+  #   docbook5
+  #   html5
+  #
+  TrailingDigitsRx = /\d+$/
+
+  # Detects strings that resemble URIs.
+  #
+  # Examples
+  #   http://domain
+  #   https://domain
+  #   file:///path
+  #   data:info
+  #
+  #   not c:/sample.adoc or c:\sample.adoc
+  #
+  UriSniffRx = %r(^#{CG_ALPHA}[#{CC_ALNUM}.+-]+:/{0,2})
+
+  # Detects XML tags
+  XmlSanitizeRx = /<[^>]+>/
+end