coradoc 0.1.0

data/lib/coradoc/document/title.rb

@@ -0,0 +1,33 @@
+module Coradoc
+  module Document
+    class Title
+      attr_reader :id, :content, :line_break
+
+      def initialize(content, level, options = {})
+        @level_str = level
+        @content = content.to_s
+        @id = options.fetch(:id, nil).to_s
+        @line_break = options.fetch(:line_break, "")
+      end
+
+      def level
+        @level ||= level_from_string
+      end
+
+      alias :text :content
+
+      private
+
+      attr_reader :level_str
+
+      def level_from_string
+        case @level_str.length
+        when 2 then :heading_two
+        when 3 then :heading_three
+        when 4 then :heading_four
+        else :unknown
+        end
+      end
+    end
+  end
+end

data/lib/coradoc/document.rb

@@ -0,0 +1,46 @@
+require "coradoc/document/title"
+require "coradoc/document/block"
+require "coradoc/document/section"
+require "coradoc/document/attribute"
+require "coradoc/document/admonition"
+require "coradoc/document/text_element"
+require "coradoc/document/author"
+require "coradoc/document/revision"
+require "coradoc/document/header"
+require "coradoc/document/bibdata"
+require "coradoc/document/paragraph"
+require "coradoc/document/table"
+require "coradoc/document/list"
+
+module Coradoc
+  module Document
+    class << self
+      attr_reader :header, :bibdata, :sections
+
+      def from_adoc(filename)
+        ast = Coradoc::Parser.parse(filename)
+        Coradoc::Transformer.transform(ast)
+      end
+
+      def from_ast(elements)
+        @sections = []
+
+        elements.each do |element|
+          if element.is_a?(Coradoc::Document::Bibdata)
+            @bibdata = element
+          end
+
+          if element.is_a?(Coradoc::Document::Header)
+            @header = element
+          end
+
+          if element.is_a?(Coradoc::Document::Section)
+            @sections << element
+          end
+        end
+
+        self
+      end
+    end
+  end
+end

data/lib/coradoc/legacy_parser.rb

@@ -0,0 +1,200 @@
+require "parslet"
+require "parslet/convenience"
+
+module Coradoc
+  class LegacyParser < Parslet::Parser
+    root :document
+
+    # Basic Elements
+    rule(:space) { match('\s') }
+    rule(:space?) { spaces.maybe }
+    rule(:spaces) { space.repeat(1) }
+    rule(:empty_line) { match("^\n") }
+
+    rule(:endline) { newline | any.absent? }
+    rule(:newline) { match["\r\n"].repeat(1) }
+    rule(:line_ending) { match("[\n]") }
+
+    rule(:inline_element) { text }
+    rule(:text) { match("[^\n]").repeat(1) }
+    rule(:digits) { match("[0-9]").repeat(1) }
+    rule(:word) { match("[a-zA-Z0-9_-]").repeat(1) }
+    rule(:special_character) { match("^[*_:=-]") | str("[#") }
+
+    rule(:text_line) do
+      special_character.absent? >>
+      match("[^\n]").repeat(1).as(:text) >>
+      line_ending.as(:break)
+    end
+
+    # Common Helpers
+    rule(:words) { word >> (space? >> word).repeat }
+    rule(:email) { word >> str("@") >> word >> str(".") >> word }
+
+    # Document
+    rule(:document) do
+       (
+         bibdata.repeat(1).as(:bibdata) |
+         section.as(:section) |
+         header.as(:header) |
+         block_with_title.as(:block) |
+         empty_line.repeat(1) |
+         any.as(:unparsed)
+       ).repeat(1).as(:document)
+    end
+
+    # Header
+    rule(:header) do
+      match("=") >> space? >> text.as(:title) >> newline >>
+      author.maybe.as(:author) >> revision.maybe.as(:revision)
+    end
+
+    rule(:author) do
+      words.as(:first_name) >> str(",") >> space? >> words.as(:last_name) >>
+      space? >> str("<") >> email.as(:email) >> str(">") >> endline
+    end
+
+    rule(:revision) do
+      (word >> (str(".") >> word).maybe).as(:number) >>
+      str(",") >> space? >> word.as(:date) >>
+      str(":") >> space? >> words.as(:remark) >> newline
+    end
+
+    # Bibdata
+    rule(:bibdata) do
+      str(":") >> attribute_name.as(:key) >> str(":") >>
+      space? >> attribute_value.as(:value) >> endline
+    end
+
+    # Section
+    rule(:section) do
+      heading.as(:title) >>
+      (list.as(:list) |
+       blocks.as(:blocks) |
+       paragraphs.as(:paragraphs)).maybe
+    end
+
+    # Heading
+    rule(:heading) do
+      (anchor_name >> newline).maybe >>
+      match("=").repeat(2, 8).as(:level) >>
+      space? >> text.as(:text) >> endline.as(:break)
+    end
+
+    rule(:anchor_name) { str("[#") >> keyword.as(:name) >> str("]") }
+
+    # List
+    rule(:list) do
+      unnumbered_list.as(:unnumbered) |
+        definition_list.as(:definition) | numbered_list.as(:numbered)
+    end
+
+    rule(:numbered_list) { nlist_item.repeat(1) }
+    rule(:unnumbered_list) { ulist_item.repeat(1) }
+    rule(:definition_list) { dlist_item.repeat(1) }
+
+    rule(:nlist_item) { match("\.") >> space >> text_line }
+    rule(:ulist_item) { match("\\*") >> space >> text_line }
+    rule(:dlist_item) do
+      str("term") >> space >> digits >> str("::") >> space >> text_line
+    end
+
+    # Block
+    rule(:block) { simple_block | open_block }
+    rule(:attribute_name) { keyword }
+    rule(:attribute_value) { text | str("") }
+    rule(:keyword) { match("[a-zA-Z0-9_-]").repeat(1) }
+    rule(:blocks) { block.repeat(1) >> (newline >> block.repeat(1)).maybe }
+
+    rule(:block_title) { str(".") >> text.as(:title) >> line_ending }
+    rule(:block_type) { str("[") >> keyword.as(:type) >> str("]") >> newline }
+
+    rule(:block_attribute) do
+      str("[")  >> keyword.as(:key) >>
+      str("=") >> keyword.as(:value) >> str("]")
+    end
+
+    rule(:simple_block) do
+      block_attribute.as(:attributes) >> newline >>
+      text_line.repeat(1).as(:lines)
+    end
+
+    rule(:open_block) do
+      block_title >>
+      block_type >>
+      str("--").as(:delimiter) >> newline >>
+      text_line.repeat.as(:lines) >>
+      str("--") >> line_ending
+    end
+
+    rule(:example_block) do
+      block_title >>
+      block_type >>
+      str("====").as(:delimiter) >> newline >>
+      text_line.repeat(1).as(:lines) >>
+      str("====") >> newline
+    end
+
+    rule(:sidebar_block) do
+      block_title >>
+      block_type.maybe >>
+      str("****").as(:delimiter) >> newline >>
+      text_line.repeat(1).as(:lines) >>
+      str("****") >> newline
+    end
+
+    rule(:source_block) do
+      block_title >>
+      str("----").as(:delimiter) >> newline >>
+      text_line.repeat(1).as(:lines) >>
+      str("----") >> newline
+    end
+
+    rule(:quote_block) do
+      block_title >>
+      str("____").as(:delimiter) >> newline >>
+      text_line.repeat.as(:lines) >>
+      str("____") >> newline
+    end
+
+    rule(:block_with_title) do
+      example_block | quote_block |
+        sidebar_block | source_block | open_block |
+        (block_title >> text_line.repeat(1).as(:lines))
+    end
+
+    # Paragraph
+    rule(:paragraphs) do
+      paragraph >> (line_ending.repeat(1) >> paragraph).repeat.maybe
+    end
+
+    rule(:paragraph) { admonitions.repeat(1) | text_line.repeat(1) }
+
+    # Admonition
+    rule(:admonition_type) do
+      (str("NOTE") |
+       str("TIP") |
+       str("EDITOR") |
+       str("DANGER") |
+       str("CAUTION") |
+       str("WARNING") |
+       str("IMPORTANT")).as(:type)
+    end
+
+    rule(:admonitions) { admonition.as(:admonition).repeat(1) }
+    rule(:admonition) { inline_admonition | block_admonition }
+
+    rule(:inline_admonition) do
+      admonition_type >> str(":") >> space? >> text_line >> newline
+    end
+
+    rule(:block_admonition) do
+      str("[") >> admonition_type >> str("]") >> newline >> text_line >> newline
+    end
+
+    def self.parse(filename)
+      content = File.read(filename)
+      new.parse_with_debug(content)
+    end
+  end
+end

data/lib/coradoc/oscal.rb

@@ -0,0 +1,85 @@
+require "yaml"
+
+module Coradoc
+  class Oscal
+    attr_reader :_doc
+
+    def initialize(document)
+      @_doc = document
+    end
+
+    def self.to_oscal(document)
+      new(document).to_oscal
+    end
+
+    def to_oscal
+      {"metadata" => _doc.bibdata.to_hash, "groups" => sections_as_groups}
+    end
+
+    private
+
+    # Organizational controls
+    def sections_as_groups
+      _doc.sections.map do |section|
+        Hash.new.tap do |hash|
+          hash["id"] = section.id
+          hash["title"] = section.title&.content
+          hash["controls"] = build_oscal_controls(section.sections)
+        end
+      end
+    end
+
+    # Clause 5.1
+    def build_oscal_controls(sections)
+      sections.map do |section|
+        Hash.new.tap do |hash|
+          hash["id"] = section.id
+          hash["props"] = build_oscal_props(section.glossaries.items)
+          hash["parts"] = build_oscal_parts(section.sections)
+        end
+      end
+    end
+
+    # Control, Purpose, Guidance
+    def build_oscal_parts(sections)
+      sections.map do |section|
+        Hash.new.tap do |hash|
+          hash["id"] = section.id
+          hash["name"] = section.title&.text
+          hash["prose"] = build_oscal_prose(section.content)
+          hash["parts"] = build_oscal_sub_parts(section.contents)
+        end.compact
+      end
+    end
+
+    def build_oscal_sub_parts(contents)
+      if contents.length > 1
+        parts = contents.select do |content|
+          content if content.is_a?(Coradoc::Document::Paragraph)
+        end
+
+        parts.map do |part|
+          Hash.new.tap do |hash|
+            hash["id"] = part.id
+            hash["prose"] = part.texts.join(" ")
+          end
+        end
+      end
+    end
+
+    def build_oscal_props(attributes)
+      attributes.map do |attribute|
+        Hash.new.tap do |hash|
+          hash["name"] = attribute.key.to_s.downcase
+          hash["value"] = attribute.value
+        end
+      end
+    end
+
+    def build_oscal_prose(paragraph)
+      if paragraph
+        paragraph.texts.join(" ")
+      end
+    end
+  end
+end

data/lib/coradoc/parser/asciidoc/base.rb

@@ -0,0 +1,84 @@
+module Coradoc
+  module Parser
+    module Asciidoc
+      module Base
+        def space?
+          space.maybe
+        end
+
+        def space
+          match('\s').repeat(1)
+        end
+
+        def text
+          match("[^\n]").repeat(1)
+        end
+
+        def line_ending
+          match("[\n]")
+        end
+
+        def endline
+          newline | any.absent?
+        end
+
+        def newline
+          match["\r\n"].repeat(1)
+        end
+
+        # def line_break
+        #   match["\r\n"]
+        # end
+
+        def keyword
+          (match("[a-zA-Z0-9_-]") | str(".")).repeat(1)
+        end
+
+        # def text_line
+        #   special_character.absent? >>
+        #   match("[^\n]").repeat(1).as(:text) >>
+        #   line_ending.as(:break)
+        # end
+
+        # rule(:space) { match('\s') }
+        # rule(:space?) { spaces.maybe }
+        # rule(:spaces) { space.repeat(1) }
+        def empty_line
+          match("^\n")
+        end
+        #
+
+        #
+        # rule(:inline_element) { text }
+        # rule(:text) { match("[^\n]").repeat(1) }
+        def digits
+          match("[0-9]").repeat(1)
+        end
+
+        def word
+          match("[a-zA-Z0-9_-]").repeat(1)
+        end
+
+        def words
+          word >> (space? >> word).repeat
+        end
+
+        def email
+          word >> str("@") >> word >> str(".") >> word
+        end
+
+        def attribute_name
+          match("[a-zA-Z0-9_-]").repeat(1)
+        end
+
+        def attribute_value
+          text | str("")
+        end
+
+        def special_character
+          match("^[*_:=-]") | str("[#") | str("[[")
+        end
+      end
+    end
+  end
+end

data/lib/coradoc/parser/asciidoc/bibdata.rb

@@ -0,0 +1,19 @@
+module Coradoc
+  module Parser
+    module Asciidoc
+      module Bibdata
+        include Coradoc::Parser::Asciidoc::Base
+
+        # Bibdata
+        def bibdatas
+          bibdata.repeat(1)
+        end
+
+        def bibdata
+          str(":") >> attribute_name.as(:key) >> str(":") >>
+          space? >> attribute_value.as(:value) >> line_ending
+        end
+      end
+    end
+  end
+end

data/lib/coradoc/parser/asciidoc/content.rb

@@ -0,0 +1,143 @@
+module Coradoc
+  module Parser
+    module Asciidoc
+      module Content
+        include Coradoc::Parser::Asciidoc::Base
+
+        def paragraph
+          text_line.repeat(1)
+        end
+
+        def glossaries
+          glossary.repeat(1)
+        end
+
+        # List
+        def list
+          unnumbered_list.as(:unnumbered) |
+            definition_list.as(:definition) | numbered_list.as(:numbered)
+        end
+
+        def contents
+          (
+            example_block.as(:example) |
+            list.as(:list) |
+            table.as(:table) |
+            highlight.as(:highlight) |
+            glossaries.as(:glossaries) |
+            paragraph.as(:paragraph) | empty_line
+          ).repeat(1)
+        end
+
+        def example_block
+          str("[example]") >> newline >>
+          str("=").repeat(4).capture(:delimiter) >> newline >>
+          dynamic do |source, context|
+            (str(context.captures[:delimiter]).absent? >> text.as(:text) >> endline).repeat(1) >>
+            str(context.captures[:delimiter]) >> endline
+          end
+        end
+
+        def highlight
+          text_id >> newline >>
+          underline >> highlight_text >> newline
+        end
+
+        def underline
+          str("[underline]") | str("[.underline]")
+        end
+
+        def highlight_text
+          str("#") >> words.as(:text) >> str("#")
+        end
+
+        # Table
+        def table
+          block_title >>
+          str("|===") >> line_ending >>
+          table_row.repeat(1).as(:rows) >>
+          str("|===") >> line_ending
+        end
+
+        def table_row
+          (literal_space? >> str("|") >> (cell_content | empty_cell_content)).
+            repeat(1).as(:cols) >> line_ending
+        end
+
+        # Extended
+        def word
+          (match("[a-zA-Z0-9_-]") | str(".") | str("*") | match("@")).repeat(1)
+        end
+
+        def empty_cell_content
+          str("|").absent? >> literal_space.as(:text)
+        end
+
+        def cell_content
+          str("|").absent? >> literal_space? >> words.as(:text)
+        end
+
+        def literal_space
+          (match[' '] | match[' \t']).repeat(1)
+        end
+
+        # Override
+        def literal_space?
+          literal_space.maybe
+        end
+
+        def block_title
+          str(".") >> text.as(:title) >> line_ending
+        end
+
+        # Text
+        def text_line
+          (asciidoc_char_with_id.absent? | text_id) >> literal_space? >>
+          text.as(:text) >> line_ending.as(:break)
+        end
+
+        def asciidoc_char
+          match("^[*_:=-]")
+        end
+
+        def asciidoc_char_with_id
+          asciidoc_char | str("[#") | str("[[")
+        end
+
+        def text_id
+          str("[[") >> keyword.as(:id) >> str("]]") |
+            str("[#") >> keyword.as(:id) >> str("]")
+        end
+
+        def glossary
+          keyword.as(:key) >> str("::") >> space? >>
+          text.as(:value) >> line_ending.as(:break)
+        end
+
+        def numbered_list
+          nlist_item.repeat(1)
+        end
+
+        def unnumbered_list
+          (ulist_item >> newline.maybe).repeat(1)
+        end
+
+        def definition_list
+          dlist_item.repeat(1)
+        end
+
+        def nlist_item
+          match("\.") >> space >> text_line
+        end
+
+        def ulist_item
+          match("\\*") >> space >> text_line
+        end
+
+        def dlist_item
+          str("term") >> space >> digits >> str("::") >> space >> text_line
+        end
+      end
+    end
+  end
+end

data/lib/coradoc/parser/asciidoc/header.rb

@@ -0,0 +1,30 @@
+require "coradoc/parser/asciidoc/base"
+
+module Coradoc
+  module Parser
+    module Asciidoc
+      module Header
+        include Coradoc::Parser::Asciidoc::Base
+
+        # Header
+        def header
+          match("=") >> space? >> text.as(:title) >> newline >>
+          author.maybe.as(:author) >> revision.maybe.as(:revision)
+        end
+
+        # Author
+        def author
+          words.as(:first_name) >> str(",") >> space? >> words.as(:last_name) >>
+          space? >> str("<") >> email.as(:email) >> str(">") >> endline
+        end
+
+        # Revision
+        def revision
+          (word >> (str(".") >> word).maybe).as(:number) >>
+          str(",") >> space? >> word.as(:date) >>
+          str(":") >> space? >> words.as(:remark) >> newline
+        end
+      end
+    end
+  end
+end

data/lib/coradoc/parser/asciidoc/section.rb

@@ -0,0 +1,60 @@
+require "coradoc/parser/asciidoc/base"
+require "coradoc/parser/asciidoc/content"
+
+module Coradoc
+  module Parser
+    module Asciidoc
+      module Section
+        include Coradoc::Parser::Asciidoc::Base
+        include Coradoc::Parser::Asciidoc::Content
+
+        def section_block(level = 2)
+          section_id.maybe >>
+          section_title(level).as(:title) >>
+          contents.as(:contents).maybe
+        end
+
+        # Section id
+        def section_id
+          (str("[[") >> keyword.as(:id) >> str("]]") |
+           str("[#") >> keyword.as(:id) >> str("]")) >> newline
+        end
+
+        # Heading
+        def section_title(level = 2, max_level = 8)
+          match("=").repeat(level, max_level).as(:level) >>
+          space? >> text.as(:text) >> endline.as(:break)
+        end
+
+        # section
+        def section
+          section_block >> second_level_section.repeat.maybe.as(:sections)
+        end
+
+        def sub_section(level)
+          newline.maybe >> section_block(level)
+        end
+
+        def second_level_section
+          sub_section(3) >> third_level_section.repeat.maybe.as(:sections)
+        end
+
+        def third_level_section
+          sub_section(4) >> fourth_level_section.repeat.maybe.as(:sections)
+        end
+
+        def fourth_level_section
+          sub_section(5) >> fifth_level_section.repeat.maybe.as(:sections)
+        end
+
+        def fifth_level_section
+          sub_section(6) >> sixth_level_section.repeat.maybe.as(:sections)
+        end
+
+        def sixth_level_section
+          sub_section(7) >> sub_section(8).repeat.maybe.as(:sections)
+        end
+      end
+    end
+  end
+end