isodoc 0.0.1

data/.rubocop.yml

@@ -0,0 +1,15 @@
+# This project follows the Ribose OSS style guide.
+# https://github.com/riboseinc/oss-guides
+# All project-specific additions and overrides should be specified in this file.
+
+inherit_from:
+  # Thoughtbot's style guide from: https://github.com/thoughtbot/guides
+  - ".rubocop.tb.yml"
+  # Overrides from Ribose
+  - ".rubocop.ribose.yml"
+AllCops:
+  DisplayCopNames: false
+  StyleGuideCopsOnly: false
+  TargetRubyVersion: 2.4
+Rails:
+  Enabled: true

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in ribose.gemspec
+gem "html2doc",
+      git: "https://github.com/riboseinc/html2doc.git"
+gemspec

data/README.adoc

@@ -0,0 +1,32 @@
+= isodoc
+
+This Gem converts documents in the https://github.com/riboseinc/isodoc-models[ISODoc document model] into HTML and Microsoft Word.
+
+The Gem is a class called with a hash of file locations:
+
+htmlstylesheet:: Generic stylesheet for HTML
+wordstylesheet:: Generic stylesheet for Word
+standardsheet:: Stylesheet specific to Standard
+header:: Header file for Word
+htmlcoverpage:: Cover page for HTML
+wordcoverpage:: Cover page for Word
+tmlintropage:: Introductory page for HTML
+wordintropage:: Introductory page for Word
+
+e.g.
+
+[source,ruby]
+--
+        IsoDoc::Convert.new(
+          htmlstylesheet: html_doc_path("htmlstyle.css"),
+          wordstylesheet: nil,
+          standardstylesheet: html_doc_path("isodoc.css"),
+          header: html_doc_path("header.html"),
+          htmlcoverpage: html_doc_path("iso_titlepage.html"),
+          wordcoverpage: html_doc_path("iso_titlepage.html"),
+          htmlintropage: html_doc_path("iso_intro.html"),
+          wordintropage: html_doc_path("iso_intro.html"),
+        )
+--
+
+NOTE: Cover page and Intro page must be XHTML fragments, not HTML fragments. In particular, unlike Word HTML, all HTML attributes need to be quoted: `<p class="MsoToc2">`, not `<p class=MsoToc2>`.

data/isodoc.gemspec

@@ -0,0 +1,51 @@
+# coding: utf-8
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "isodoc/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "isodoc"
+  spec.version       = IsoDoc::VERSION
+  spec.authors       = ["Ribose Inc."]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = "Convert documents in IsoDoc into Word and HTML "\
+    "in AsciiDoc."
+  spec.description   = <<~DESCRIPTION
+    isodoc converts documents in the IsoDoc document model into
+    Microsoft Word and HTML.
+
+    This gem is in active development.
+  DESCRIPTION
+
+  spec.homepage      = "https://github.com/riboseinc/isodoc"
+  spec.license       = "MIT"
+
+  spec.bindir        = "bin"
+  spec.require_paths = ["lib"]
+  spec.files         = `git ls-files`.split("\n")
+  spec.test_files    = `git ls-files -- {spec}/*`.split("\n")
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
+
+  spec.add_dependency "asciimath"
+  spec.add_dependency "htmlentities", "~> 4.3.4"
+  spec.add_dependency "image_size"
+  spec.add_dependency "mime-types"
+  spec.add_dependency "nokogiri", "= 1.8.1"
+  spec.add_dependency "ruby-xslt"
+  spec.add_dependency "thread_safe"
+  spec.add_dependency "uuidtools"
+  spec.add_dependency "html2doc"
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "byebug", "~> 9.1"
+  spec.add_development_dependency "equivalent-xml", "~> 0.6"
+  spec.add_development_dependency "guard", "~> 2.14"
+  spec.add_development_dependency "guard-rspec", "~> 4.7"
+  spec.add_development_dependency "rake", "~> 12.0"
+  spec.add_development_dependency "rspec", "~> 3.6"
+  spec.add_development_dependency "rubocop", "~> 0.50"
+  spec.add_development_dependency "simplecov", "~> 0.15"
+  spec.add_development_dependency "timecop", "~> 0.9"
+end

data/lib/isodoc.rb

@@ -0,0 +1,74 @@
+require_relative "isodoc/version"
+
+require "nokogiri"
+require "asciimath"
+require "xml/xslt"
+require "uuidtools"
+require "base64"
+require "mime/types"
+require "image_size"
+require "set"
+require_relative "isodoc/iso2wordhtml"
+require_relative "isodoc/cleanup"
+require_relative "isodoc/postprocessing"
+require_relative "isodoc/utils"
+require_relative "isodoc/metadata"
+require_relative "isodoc/section"
+require_relative "isodoc/references"
+require_relative "isodoc/terms"
+require_relative "isodoc/blocks"
+require_relative "isodoc/lists"
+require_relative "isodoc/table"
+require_relative "isodoc/inline"
+require_relative "isodoc/xref_gen"
+require_relative "isodoc/html"
+require "pp"
+
+module IsoDoc
+  class Convert
+
+    # htmlstylesheet: Generic stylesheet for HTML
+    # wordstylesheet: Generic stylesheet for Word
+    # standardsheet: Stylesheet specific to Standard
+    # header: Header file for Word
+    # htmlcoverpage: Cover page for HTML
+    # wordcoverpage: Cover page for Word
+    # htmlintropage: Introductory page for HTML
+    # wordintropage: Introductory page for Word
+    def initialize(options)
+      @htmlstylesheet = options[:htmlstylesheet]
+      @wordstylesheet = options[:wordstylesheet]
+      @standardstylesheet = options[:standardstylesheet]
+      @header = options[:header]
+      @htmlcoverpage = options[:htmlcoverpage]
+      @wordcoverpage = options[:wordcoverpage]
+      @htmlintropage = options[:htmlintropage]
+      @wordintropage = options[:wordintropage]
+      @termdomain = ""
+      @termexample = false
+      @note = false
+      @sourcecode = false
+      @anchors = {}
+      @meta = {}
+      @footnotes = []
+      @comments = []
+      @in_footnote = false
+      @in_table = false
+      @in_figure = false
+      @seen_footnote = Set.new
+    end
+
+    def convert(filename)
+      docxml = Nokogiri::XML(File.read(filename))
+      filename, dir = init_file(filename)
+      docxml.root.default_namespace = ""
+      result = noko do |xml|
+        xml.html do |html|
+          html_header(html, docxml, filename, dir)
+          make_body(html, docxml)
+        end
+      end.join("\n")
+      postprocess(result, filename, dir)
+    end
+  end
+end

data/lib/isodoc/blocks.rb

@@ -0,0 +1,184 @@
+module IsoDoc
+  class Convert
+    #attr_accessor :termdomain, :termexample, :sourcecode, :note
+    def set_termdomain(termdomain)
+      @termdomain = termdomain
+    end
+
+    def get_termexample
+      @termexample
+    end
+
+    def set_termexample(value)
+      @termexample = value
+    end
+
+    def in_sourcecode
+      @sourcecode
+    end
+
+    def is_note
+      @note
+    end
+
+    def note_label(node)
+      n = get_anchors()[node["id"]]
+      return "NOTE" if n.nil?
+      n[:label]
+    end
+
+    def note_p_parse(node, div)
+      div.p **{ class: "Note" } do |p|
+        p << note_label(node)
+        insert_tab(p, 1)
+        node.first_element_child.children.each { |n| parse(n, p) }
+      end
+      node.element_children[1..-1].each { |n| parse(n, div) }
+    end
+
+    def note_parse(node, out)
+      @note = true
+      out.div **{ id: node["id"], class: "Note" } do |div|
+        if node.first_element_child.name == "p"
+          note_p_parse(node, div)
+        else
+          div.p **{ class: "Note" } do |p|
+            p << note_label(node)
+            insert_tab(p, 1)
+          end
+          node.children.each { |n| parse(n, div) }
+        end
+      end
+      @note = false
+    end
+
+    def figure_name_parse(node, div, name)
+      div.p **{ class: "FigureTitle", align: "center" } do |p|
+        p.b do |b|
+          b << "#{get_anchors()[node['id']][:label]}&nbsp;&mdash; "
+          b << name.text
+        end
+      end
+    end
+
+    def figure_key(out)
+      out.p do |p| 
+        p.b { |b| b << "Key" }
+      end
+    end
+
+    def figure_parse(node, out)
+      @in_figure = true
+      name = node.at(ns("./name"))
+      out.div **attr_code(id: node["id"], class: "figure") do |div|
+        node.children.each do |n|
+          figure_key(out) if n.name == "dl"
+          parse(n, div) unless n.name == "name"
+        end
+        figure_name_parse(node, div, name) if name
+      end
+      @in_figure = false
+    end
+
+    def sourcecode_name_parse(node, div, name)
+      div.p **{ class: "FigureTitle", align: "center" } do |p|
+        p.b do |b|
+          b << name.text
+        end
+      end
+    end
+
+    def sourcecode_parse(node, out)
+      name = node.at(ns("./name"))
+      out.p **attr_code(id: node["id"], class: "Sourcecode") do |div|
+        @sourcecode = true
+        node.children.each do |n|
+          parse(n, div) unless n.name == "name"
+        end
+        @sourcecode = false
+        sourcecode_name_parse(node, div, name) if name
+      end
+    end
+
+    def annotation_parse(node, out)
+      out.p **{ class: "Sourcecode" } do |li|
+        node.children.each { |n| parse(n, li) }
+      end
+    end
+
+    def admonition_parse(node, out)
+      name = node["type"]
+      out.div **{ class: "Admonition" } do |t|
+        t.p.b { |b| b << name.upcase } if name
+        node.children.each do |n|
+          parse(n, t)
+        end
+      end
+    end
+
+    def formula_parse(node, out)
+      dl = node.at(ns("./dl"))
+      out.div **attr_code(id: node["id"], class: "formula") do |div|
+        parse(node.at(ns("./stem")), out)
+        insert_tab(div, 1)
+        div << "(#{get_anchors()[node['id']][:label]})"
+      end
+      if dl
+        out.p { |p| p << "where" }
+        parse(dl, out) 
+      end
+    end
+
+    def para_attrs(node)
+      classtype = nil
+      classtype = "Note" if @note
+      classtype = "MsoFootnoteText" if in_footnote
+      attrs = { class: classtype }
+      unless node["align"].nil?
+        attrs[:align] = node["align"] unless node["align"] == "justify"
+        attrs[:style] = "text-align:#{node["align"]}"
+      end
+      attrs
+    end
+
+    def para_parse(node, out)
+      out.p **attr_code(para_attrs(node)) do |p|
+        unless @termdomain.empty?
+          p << "&lt;#{@termdomain}&gt; "
+          @termdomain = ""
+        end
+        node.children.each { |n| parse(n, p) }
+      end
+    end
+
+    def quote_attribution(node, out)
+      author = node.at(ns("./author/fullname/"))
+      source = node.at(ns("./source"))
+      # TODO implement
+    end
+
+    def quote_parse(node, out)
+      attrs = para_attrs(node)
+      attrs[:class] = "Quote"
+      out.p **attr_code(attrs) do |p|
+        node.children.each do 
+          |n| parse(n, p) unless ["author", "source"].include? n.name
+        end
+        quote_attribution(node, out)
+      end
+    end
+
+    def image_title_parse(out, caption)
+      unless caption.nil?
+        out.p **{ class: "FigureTitle", align: "center" } do |p|
+          p.b { |b| b << caption.to_s }
+        end
+      end
+    end
+
+    def image_parse(url, out, caption)
+      out.img **attr_code(src: url)
+      image_title_parse(out, caption)
+    end
+  end
+end

data/lib/isodoc/cleanup.rb

@@ -0,0 +1,155 @@
+require "html2doc"
+require "htmlentities"
+require "nokogiri"
+require "pp"
+
+module IsoDoc
+  class Convert
+    def cleanup(docxml)
+      comment_cleanup(docxml)
+      footnote_cleanup(docxml)
+      inline_header_cleanup(docxml)
+      figure_cleanup(docxml)
+      table_cleanup(docxml)
+      docxml
+    end
+
+    def figure_get_or_make_dl(t)
+      dl = t.at(".//dl")
+      if dl.nil?
+        t.add_child("<p><b>Key</b></p><dl></dl>")
+        dl = t.at(".//dl")
+      end
+      dl
+    end
+
+    FIGURE_WITH_FOOTNOTES =
+      "//div[@class = 'figure'][descendant::aside]"\
+      "[not(descendant::div[@class = 'figure'])]".freeze
+
+    def figure_aside_process(f, aside, key)
+      # get rid of footnote link, it is in diagram
+      f.at("./a[@class='zzFootnote']").remove
+      fnref = f.at(".//a[@class='zzFootnote']")
+      dt = key.add_child("<dt></dt>").first
+      dd = key.add_child("<dd></dd>").first
+      fnref.parent = dt
+      aside.xpath(".//p").each do |a| 
+        a.delete("class")
+        a.parent = dd 
+      end
+    end
+
+    def figure_cleanup(docxml)
+      # move footnotes into key, and get rid of footnote reference 
+      # since it is in diagram
+      docxml.xpath(FIGURE_WITH_FOOTNOTES).each do |f|
+        key = figure_get_or_make_dl(f)
+        f.xpath(".//aside").each do |aside|
+          figure_aside_process(f, aside, key)
+        end
+      end
+    end
+
+    def inline_header_cleanup(docxml)
+      docxml.xpath('//span[@class="zzMoveToFollowing"]').each do |x|
+        n = x.next_element
+        if n.nil?
+          html = Nokogiri::XML.fragment("<p></p>")
+          html.parent = x.parent
+          x.parent = html
+        else
+          n.children.first.add_previous_sibling(x.remove)
+        end
+      end
+    end
+
+    def comment_cleanup(docxml)
+      docxml.xpath('//div/span[@style="MsoCommentReference"]').
+        each do |x|
+        prev = x.previous_element
+        if !prev.nil?
+          x.parent = prev
+        end
+      end
+      docxml
+    end
+
+    def footnote_cleanup(docxml)
+      docxml.xpath('//div[@style="mso-element:footnote"]/a').
+        each do |x|
+        n = x.next_element
+        if !n.nil?
+          n.children.first.add_previous_sibling(x.remove)
+        end
+      end
+      docxml
+    end
+
+    def merge_fnref_into_fn_text(a)
+      fn = a.at('.//a[@class="zzFootnote"]')
+      n = fn.next_element
+      n.children.first.add_previous_sibling(fn.remove) unless n.nil?
+    end
+
+    TABLE_WITH_FOOTNOTES = "//table[descendant::aside]".freeze
+
+    def table_footnote_cleanup(docxml)
+      docxml.xpath(TABLE_WITH_FOOTNOTES).each do |t|
+        t.xpath(".//aside").each do |a|
+          merge_fnref_into_fn_text(a)
+          a.name = "div"
+          a["class"] = "Note"
+          t << a.remove
+        end
+      end
+    end
+
+    def remove_bottom_border(td)
+      td["style"] =
+        td["style"].gsub(/border-bottom:[^;]+;/, "border-bottom:0pt;").
+        gsub(/mso-border-bottom-alt:[^;]+;/, "mso-border-bottom-alt:0pt;")
+    end
+
+    def table_get_or_make_tfoot(t)
+      tfoot = t.at(".//tfoot")
+      if tfoot.nil?
+        t.add_child("<tfoot></tfoot>")
+        tfoot = t.at(".//tfoot")
+      else
+        # nuke its bottom border
+        tfoot.xpath(".//td | .//th").each do |td|
+          remove_bottom_border(td)
+        end
+      end
+      tfoot
+    end
+
+    def new_fullcolspan_row(t, tfoot)
+      # how many columns in the table?
+      cols = 0
+      t.at(".//tr").xpath("./td | ./th").each do |td|
+        cols += ( td["colspan"] ? td["colspan"].to_i : 1 )
+      end
+      style = %{border-top:0pt;mso-border-top-alt:0pt;
+      border-bottom:#{SW} 1.5pt;mso-border-bottom-alt:#{SW} 1.5pt;}
+      tfoot.add_child("<tr><td colspan='#{cols}' style='#{style}'/></tr>")
+      tfoot.xpath(".//td").last
+    end
+
+    def table_note_cleanup(docxml)
+      docxml.xpath("//table[div[@class = 'Note']]").each do |t|
+        tfoot = table_get_or_make_tfoot(t)
+        insert_here = new_fullcolspan_row(t, tfoot)
+        t.xpath("div[@class = 'Note']").each do |d|
+          d.parent = insert_here
+        end
+      end
+    end
+
+    def table_cleanup(docxml)
+      table_footnote_cleanup(docxml)
+      table_note_cleanup(docxml)
+    end
+  end
+end