First cut at declarative parser and renderer information for Asciidoctor.

asciidoc.yml

:admonition_styles: &ADMONITION_STYLES [NOTE, TIP, IMPORTANT, WARNING, CAUTION]
:default_doctype: article
:default_backend: html5
:headings:
  :oneline:
    # examples:
    #
    # = Document Title
    #
    # == First Section ==
    :lines: 1
    :levels: ['=', '==', '===', '====', '=====']
    :pattern: !ruby/regexp '/^(={1,5})\s+(\S.*?)\s*(\s\1)?$/'
  :twoline:
    # examples:
    #
    # Document Title
    # ==============
    # 
    # First Section
    # -------------
    :lines: 2
    :levels: ['=', '-', '~', '^', '+']
    :patterns:
      - !ruby/regexp '/^\s*.*\w.*\s*$/'
      - !ruby/regexp '/^([=\-~^\+]){2,}\s*$/'
# NOTE: process block macros first, in order, then blockmeta, in order, then blocks, in order
:blocks:
  :comment:
    # examples:
    #
    # ////
    # block comment
    # ////
    :auto: true
    :style: comment
    :delimiter:
      :char: '/'
      :pattern: !ruby/regexp '/^\/{4,}\s*$/'
    :skip: true
  :sidebar:
    # examples:
    #
    # ****
    # Sidebar
    # ****
    :auto: true
    :style: sidebar
    :posattrs: [style]
    :delimiter:
      :char: '*'
      :pattern: !ruby/regexp '/^\*{4,}\s*$/'
    :section_body: true
  :example:
    # examples:
    #
    # ====
    # Example
    # ====
    #
    # [NOTE]
    # ====
    # Multi-paragraph...
    #
    # ...note.
    # ====
    :auto: true
    :style: example
    #:alt_styles: *ADMONITION_STYLES
    :posattrs: [style]
    :delimiter:
      :char: '='
      :pattern: !ruby/regexp '/^={4,}\s*$/'
    :section_body: true
  :listing:
    # examples:
    #
    # ----
    # code here
    # ----
    #
    # [source, ruby]
    # ----
    # puts "Program happy!"
    # ----
    :auto: true
    :style: listing
    :posattrs: [style, language, linenums]
    :delimiter:
      :char: '-'
      :pattern: !ruby/regexp '/^-{4,}\s*$/'
    :section_body: false
    :subs: [specialchars, callouts]
    # this could also be verbatim, then imply it
    :postprocess: [chomp_last]
  :literal:
    # examples:
    #
    # ....
    # literally
    # ....
    :auto: true
    :style: literal
    :alt_styles: [listing]
    :posattrs: [style]
    :delimiter:
      :char: '.'
      :pattern: !ruby/regexp '/^\.{4,}\s*$/'
    :section_body: false
    :subs: [specialchars]
    :postprocess: [chomp_last]
  :quote:
    # examples:
    #
    # [quote, Sir Arthur Conan Doyle, The Adventures of Sherlock Holmes]
    # ____
    # When you have eliminated all which is impossible, then whatever remains, however improbable, must be the truth.
    # ____
    #
    # [verse]
    # ____
    # La la la
    #
    # La la la
    # ____
    :auto: true
    :style: quote
    :alt_styles: [verse]
    :posattrs: [style, attribution, citetitle]
    :delimiter:
      :char: '_'
      :pattern: !ruby/regexp '/^_{4,}\s*$/'
    :section_body: true
    :subs: [attributes, strip, htmlify]
  # TODO could get to verse via reference from quote
  :verse:
    :style: verse
    :section_body: false
    :subs: [attributes]
  :admonition:
    :subs: [attributes]
  :pass:
    :auto: true
    :style: pass
    :posattrs: [style]
    :delimiter:
      :char: '+'
      :pattern: !ruby/regexp '/^\+{4,}\s*$/'
    :section_body: false
    :subs: []
  :open:
    :style: default
    :alt_styles: '*'
    :posattrs: [style]
    :delimiter:
      :char: '-'
      :pattern: !ruby/regexp '/^-{2,}\s*$/'
  :literalparagraph:
    # Examples:
    #
    #  Indented by at least one character.
    #
    #  Multiple lines
    #  will be joined as one block
    :style: literal
    :posattrs: [style]
    :postprocess: [chomp_last]
  :paragraph:
    # Examples:
    #
    # Paragraph one.
    #
    # Paragraph two.
    :style: normal
    :alt_styles: '*'
    :posattrs: [style]
    :delimiter:
      :pattern: !ruby/regexp '/^\S.*$/'
      :break_on_blank_lines: true
    :section_body: false
:blockmeta:
  :single:
    :anchor:
      # examples:
      #
      # [[defs]]
      :pattern: !ruby/regexp '/^\[\[([^\[\]]+)\]\]\s*$/'
      :validate_pattern: !ruby/regexp '/^[:_a-z][-\.:_a-z0-9]*$/i'
      :reference: true
      :assignments:
        -
          # this should probably set id attribute instead
          :type: local
          :capture_group: 1
          :target: anchor
  :multiple:
    :attributes:
      # examples:
      #
      # [quote, Adam Smith, Wealth of Nations]
      #
      # [NOTE, caption="Good to know"]
      :pattern: !ruby/regexp '/^\[(\w.*)\]$/'
      :capture:
        :attributes: 1
    :title:
      # examples:
      #
      # .Title
      # ! . Title
      # ! ..Title
      :pattern: !ruby/regexp '/^\.([^\s\.].*)\s*$/'
      :assignments:
        -
          :type: local
          :capture_group: 1
          :target: title
:lists:
  :ulist:
    # examples:
    #
    # * Item
    # - Item
    # ! *Item
    # ! -Item
    :pattern: !ruby/regexp '/^\s*(-|\*{1,5})\s+(.*)\s*$/'
  :olist:
    # examples:
    #
    # . Item
    # 1.Item
    # 1. Item
    :pattern: !ruby/regexp '/^\s*(\d+\.|\. )(.*)$/'
  :dlist:
    # examples
    #
    # term:: def
    # term::
    #   def
    # term::
    # def
    # term;; def
    # term::: def
    # term:::: def
    :pattern: !ruby/regexp '/^\s*(?:\[\[([^\]]*)\]\])?(\w.*?)(:{2,4}|;;)(\s+(.*))?$/'
    :sibling_patterns:
      '::': '/^\s*(?:\[\[([^\]]*)\]\])?(\w(?:.*[^:])?)(::)(\s+(.*))?$/'
      ':::': '/^\s*(?:\[\[([^\]]*)\]\])?(\w(?:.*[^:])?)(:::)(\s+(.*))?$/'
      '::::': '/^\s*(?:\[\[([^\]]*)\]\])?(\w(?:.*[^:])?)(::::)(\s+(.*))?$/'
      ';;': '/^\s*(?:\[\[([^\]]*)\]\])?(\w.*)(;;)(\s+(.*))?$/'
  :colist:
    :pattern: !ruby/regexp '/^(\<\d+\>)\s*(.*)/'
:macros:
  :block:
    :comment:
      # examples:
      #
      # // line comment
      # //line comment w/o a leading space
      :pattern: !ruby/regexp '/^\/\/([^\/].*|)$/' 
      :skip: true
    :ruler:
      # examples:
      #
      # '''
      :pattern: !ruby/regexp '/^''{3,}\s*$/'
    :image:
      # examples:
      #
      # image::tiger.png[Tiger]
      :pattern: !ruby/regexp '/^image::(\S+?)\[(.*?)\]$/'
      :posattrs: [alt, width, height]
      :capture:
        :attributes: 2
      :attributes:
        target: 1
:attributes:
  startsb:          '['
  endsb:            ']'
  brvbar:           '|'
  caret:            '^'
  asterisk:         '*'
  tilde:            '~'
  litdd:            '--'
  plus:             '+'
  apos:             ''''
  backslash:        '\'
  backtick:         '`'
  empty:            ''
  sp:               ' '
  'two-colons':     '::'
  'two-semicolons': ';;'
  nbsp:             '&#160;'
  deg:              '&#176;'
  zwsp:             '&#8203;'
  lsquo:            '&#8216;'
  rsquo:            '&#8217;'
  ldquo:            '&#8220;'
  rdquo:            '&#8221;'
  wj:               '&#8288;'
  amp:              '&'
  lt:               '<'
  gt:               '>'
:subs:
  :special:
    '<': '&lt;'
    '>': '&gt;'
    '&': '&amp;'
  :replacements:
    -
      :pattern: !ruby/regexp '/\(C\)/'
      :text: '&#169;'