isodoc 1.6.4 → 1.6.5

data/lib/isodoc/html_convert.rb

@@ -1,8 +1,9 @@
 require_relative "html_function/comments"
 require_relative "html_function/footnotes"
 require_relative "html_function/html"
-require_relative "html_function/form"
 require_relative "html_function/postprocess"
+require_relative "html_function/sectionsplit"
+require_relative "html_function/form"
 
 module IsoDoc
   class HtmlConvert < ::IsoDoc::Convert
@@ -23,6 +24,9 @@ module IsoDoc
     end
 
     def convert(filename, file = nil, debug = false, output_filename = nil)
+      @sectionsplit and
+        return sectionsplit_convert(filename, file, debug, output_filename)
+
       ret = super
       Dir.exists?(tmpimagedir) and Dir["#{tmpimagedir}/*"].empty? and
         FileUtils.rm_r tmpimagedir

data/lib/isodoc/html_function/comments.rb

@@ -24,16 +24,16 @@ module IsoDoc::HtmlFunction
 =end
     end
 
-    def comment_link_attrs(fn, node)
-      { style: "MsoCommentReference", target: fn,
+    def comment_link_attrs(fnote, node)
+      { style: "MsoCommentReference", target: fnote,
         class: "commentLink", from: node["from"],
         to: node["to"] }
     end
 
     # add in from and to links to move the comment into place
-    def make_comment_link(out, fn, node)
-      out.span(**comment_link_attrs(fn, node)) do |s1|
-          s1.a **{ style: "mso-comment-reference:SMC_#{fn};"\
+    def make_comment_link(out, fnote, node)
+      out.span(**comment_link_attrs(fnote, node)) do |s1|
+          s1.a **{ style: "mso-comment-reference:SMC_#{fnote};"\
                    "mso-comment-date:#{node['date'].gsub(/[-:Z]/, '')}" }
         end
     end
@@ -44,9 +44,9 @@ module IsoDoc::HtmlFunction
         end
     end
 
-    def make_comment_text(node, fn)
+    def make_comment_text(node, fnote)
       noko do |xml|
-        xml.div **{ style: "mso-element:comment", id: fn } do |div|
+        xml.div **{ style: "mso-element:comment", id: fnote } do |div|
           div.span **{ style: %{mso-comment-author:"#{node['reviewer']}"} }
           make_comment_target(div)
           node.children.each { |n| parse(n, div) }
@@ -99,13 +99,13 @@ module IsoDoc::HtmlFunction
       from["style"] != "mso-special-character:comment"
     end
 
-    def insert_comment_cont(from, to, target)
-      # includes_to = from.at(".//*[@id='#{to}']")
-      while !from.nil? && from["id"] != to
+    def insert_comment_cont(from, upto, target)
+      # includes_to = from.at(".//*[@id='#{upto}']")
+      while !from.nil? && from["id"] != upto
         following = from.xpath("./following::*")
-        (from = following.shift) && incl_to = from.at(".//*[@id='#{to}']")
+        (from = following.shift) && incl_to = from.at(".//*[@id='#{upto}']")
         while !incl_to.nil? && !from.nil? && skip_comment_wrap(from)
-          (from = following.shift) && incl_to = from.at(".//*[@id='#{to}']")
+          (from = following.shift) && incl_to = from.at(".//*[@id='#{upto}']")
         end
         wrap_comment_cont(from, target) if !from.nil?
       end

data/lib/isodoc/html_function/html.rb

@@ -64,8 +64,8 @@ module IsoDoc::HtmlFunction
         <script type="text/javascript">#{toclevel}</script>
 
         <!--Google fonts-->
-          <link rel="preconnect" href="https://fonts.gstatic.com">#{' '}
-          #{googlefonts}
+        <link rel="preconnect" href="https://fonts.gstatic.com">#{' '}
+        #{googlefonts}
         <!--Font awesome import for the link icon-->
         <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.0.8/css/solid.css" integrity="sha384-v2Tw72dyUXeU3y4aM2Y0tBJQkGfplr39mxZqlTBDUZAb9BGoC40+rdFCG0m10lXk" crossorigin="anonymous">
         <link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.0.8/css/fontawesome.css" integrity="sha384-q3jl8XQu1OpdLgGFvNRnPdj5VIlCvgsDQTQB6owSOHWlAurxul7f+JpUOVdAiJ5P" crossorigin="anonymous">

data/lib/isodoc/html_function/postprocess.rb

@@ -1,227 +1,233 @@
 require "isodoc/html_function/mathvariant_to_plain"
 require_relative "postprocess_footnotes"
 
-module IsoDoc::HtmlFunction
-  module Html
-    def postprocess(result, filename, _dir)
-      result = from_xhtml(cleanup(to_xhtml(textcleanup(result))))
-      toHTML(result, filename)
-      @files_to_delete.each { |f| FileUtils.rm_rf f }
-    end
+module IsoDoc
+  module HtmlFunction
+    module Html
+      def postprocess(result, filename, _dir)
+        result = from_xhtml(cleanup(to_xhtml(textcleanup(result))))
+        toHTML(result, filename)
+        @files_to_delete.each { |f| FileUtils.rm_rf f }
+      end
 
-    def script_cdata(result)
-      result.gsub(%r{<script([^>]*)>\s*<!\[CDATA\[}m, "<script\\1>")
-        .gsub(%r{\]\]>\s*</script>}, "</script>")
-        .gsub(%r{<!\[CDATA\[\s*<script([^>]*)>}m, "<script\\1>")
-        .gsub(%r{</script>\s*\]\]>}, "</script>")
-    end
+      def script_cdata(result)
+        result.gsub(%r{<script([^>]*)>\s*<!\[CDATA\[}m, "<script\\1>")
+          .gsub(%r{\]\]>\s*</script>}, "</script>")
+          .gsub(%r{<!\[CDATA\[\s*<script([^>]*)>}m, "<script\\1>")
+          .gsub(%r{</script>\s*\]\]>}, "</script>")
+      end
 
-    def toHTML(result, filename)
-      result = from_xhtml(html_cleanup(to_xhtml(result)))
-      # result = populate_template(result, :html)
-      result = from_xhtml(move_images(to_xhtml(result)))
-      result = html5(script_cdata(inject_script(result)))
-      File.open(filename, "w:UTF-8") { |f| f.write(result) }
-    end
+      def toHTML(result, filename)
+        result = from_xhtml(html_cleanup(to_xhtml(result)))
+        # result = populate_template(result, :html)
+        result = from_xhtml(move_images(to_xhtml(result)))
+        result = html5(script_cdata(inject_script(result)))
+        File.open(filename, "w:UTF-8") { |f| f.write(result) }
+      end
 
-    def html5(doc)
-      doc.sub(%r{<!DOCTYPE html [^>]+>}, "<!DOCTYPE html>")
-        .sub(%r{<\?xml[^>]+>}, "")
-    end
+      def html5(doc)
+        doc.sub(%r{<!DOCTYPE html [^>]+>}, "<!DOCTYPE html>")
+          .sub(%r{<\?xml[^>]+>}, "")
+      end
 
-    def html_cleanup(html)
-      mathml(
-        footnote_format(
-          footnote_backlinks(
-            html_toc(
-              term_header(html_footnote_filter(html_preface(htmlstyle(html)))),
-            ),
-          ),
-        ),
-      )
-    end
+      def html_cleanup(html)
+        html = term_header(html_footnote_filter(html_preface(htmlstyle(html))))
+        html = footnote_format(footnote_backlinks(html_toc(html)))
+        mathml(html_list_clean(html))
+      end
 
-    def mathml(docxml)
-      IsoDoc::HtmlFunction::MathvariantToPlain.new(docxml).convert
-    end
+      def html_list_clean(html)
+        html.xpath("//ol/div | //ul/div").each do |div|
+          li = div&.xpath("./preceding-sibling::li")&.last ||
+            div.at("./following-sibling::li")
+          div.parent = li
+        end
+        html
+      end
 
-    def htmlstylesheet(file)
-      return if file.nil?
+      def mathml(docxml)
+        IsoDoc::HtmlFunction::MathvariantToPlain.new(docxml).convert
+      end
 
-      file.open if file.is_a?(Tempfile)
-      stylesheet = file.read
-      xml = Nokogiri::XML("<style/>")
-      xml.children.first << Nokogiri::XML::Comment.new(xml, "\n#{stylesheet}\n")
-      file.close
-      file.unlink if file.is_a?(Tempfile)
-      xml.root.to_s
-    end
+      def htmlstylesheet(file)
+        return if file.nil?
+
+        file.open if file.is_a?(Tempfile)
+        stylesheet = file.read
+        xml = Nokogiri::XML("<style/>")
+        xml.children.first << Nokogiri::XML::Comment
+          .new(xml, "\n#{stylesheet}\n")
+        file.close
+        file.unlink if file.is_a?(Tempfile)
+        xml.root.to_s
+      end
 
-    def htmlstyle(docxml)
-      return docxml unless @htmlstylesheet
+      def htmlstyle(docxml)
+        return docxml unless @htmlstylesheet
 
-      head = docxml.at("//*[local-name() = 'head']")
-      head << htmlstylesheet(@htmlstylesheet)
-      s = htmlstylesheet(@htmlstylesheet_override) and head << s
-      docxml
-    end
+        head = docxml.at("//*[local-name() = 'head']")
+        head << htmlstylesheet(@htmlstylesheet)
+        s = htmlstylesheet(@htmlstylesheet_override) and head << s
+        docxml
+      end
 
-    def html_preface(docxml)
-      html_cover(docxml) if @htmlcoverpage && !@bare
-      html_intro(docxml) if @htmlintropage && !@bare
-      docxml.at("//body") << mathjax(@openmathdelim, @closemathdelim)
-      docxml.at("//body") << sourcecode_highlighter
-      html_main(docxml)
-      authority_cleanup(docxml)
-      docxml
-    end
+      def html_preface(docxml)
+        html_cover(docxml) if @htmlcoverpage && !@bare
+        html_intro(docxml) if @htmlintropage && !@bare
+        docxml.at("//body") << mathjax(@openmathdelim, @closemathdelim)
+        docxml.at("//body") << sourcecode_highlighter
+        html_main(docxml)
+        authority_cleanup(docxml)
+        docxml
+      end
 
-    def authority_cleanup1(docxml, klass)
-      dest = docxml.at("//div[@id = 'boilerplate-#{klass}-destination']")
-      auth = docxml.at("//div[@id = 'boilerplate-#{klass}' or "\
-                       "@class = 'boilerplate-#{klass}']")
-      auth&.xpath(".//h1[not(text())] | .//h2[not(text())]")&.each(&:remove)
-      auth&.xpath(".//h1 | .//h2")&.each { |h| h["class"] = "IntroTitle" }
-      dest and auth and dest.replace(auth.remove)
-    end
+      def authority_cleanup1(docxml, klass)
+        dest = docxml.at("//div[@id = 'boilerplate-#{klass}-destination']")
+        auth = docxml.at("//div[@id = 'boilerplate-#{klass}' or "\
+                         "@class = 'boilerplate-#{klass}']")
+        auth&.xpath(".//h1[not(text())] | .//h2[not(text())]")&.each(&:remove)
+        auth&.xpath(".//h1 | .//h2")&.each { |h| h["class"] = "IntroTitle" }
+        dest and auth and dest.replace(auth.remove)
+      end
 
-    def authority_cleanup(docxml)
-      %w(copyright license legal feedback).each do |t|
-        authority_cleanup1(docxml, t)
+      def authority_cleanup(docxml)
+        %w(copyright license legal feedback).each do |t|
+          authority_cleanup1(docxml, t)
+        end
       end
-    end
 
-    def html_cover(docxml)
-      doc = to_xhtml_fragment(File.read(@htmlcoverpage, encoding: "UTF-8"))
-      d = docxml.at('//div[@class="title-section"]')
-      # d.children.first.add_previous_sibling doc.to_xml(encoding: "US-ASCII")
-      d.children.first.add_previous_sibling(
-        populate_template(doc.to_xml(encoding: "US-ASCII"), :html),
-      )
-    end
+      def html_cover(docxml)
+        doc = to_xhtml_fragment(File.read(@htmlcoverpage, encoding: "UTF-8"))
+        d = docxml.at('//div[@class="title-section"]')
+        # d.children.first.add_previous_sibling doc.to_xml(encoding: "US-ASCII")
+        d.children.first.add_previous_sibling(
+          populate_template(doc.to_xml(encoding: "US-ASCII"), :html),
+        )
+      end
 
-    def html_intro(docxml)
-      doc = to_xhtml_fragment(File.read(@htmlintropage, encoding: "UTF-8"))
-      d = docxml.at('//div[@class="prefatory-section"]')
-      # d.children.first.add_previous_sibling doc.to_xml(encoding: "US-ASCII")
-      d.children.first.add_previous_sibling(
-        populate_template(doc.to_xml(encoding: "US-ASCII"), :html),
-      )
-    end
+      def html_intro(docxml)
+        doc = to_xhtml_fragment(File.read(@htmlintropage, encoding: "UTF-8"))
+        d = docxml.at('//div[@class="prefatory-section"]')
+        # d.children.first.add_previous_sibling doc.to_xml(encoding: "US-ASCII")
+        d.children.first.add_previous_sibling(
+          populate_template(doc.to_xml(encoding: "US-ASCII"), :html),
+        )
+      end
 
-    def html_toc_entry(level, header)
-      %(<li class="#{level}"><a href="##{header['id']}">\
+      def html_toc_entry(level, header)
+        %(<li class="#{level}"><a href="##{header['id']}">\
       #{header_strip(header)}</a></li>)
-    end
-
-    def toclevel_classes
-      (1..@htmlToClevels).reduce([]) { |m, i| m << "h#{i}" }
-    end
+      end
 
-    def toclevel
-      ret = toclevel_classes.map do |l|
-        "#{l}:not(:empty):not(.TermNum):not(.noTOC)"
+      def toclevel_classes
+        (1..@htmlToClevels).reduce([]) { |m, i| m << "h#{i}" }
       end
-      <<~HEAD.freeze
-        function toclevel() { return "#{ret.join(',')}";}
-      HEAD
-    end
 
-    # needs to be same output as toclevel
-    def html_toc(docxml)
-      (idx = docxml.at("//div[@id = 'toc']")) or (return docxml)
-      toc = "<ul>"
-      path = toclevel_classes.map do |l|
-        "//main//#{l}[not(@class = 'TermNum')][not(@class = 'noTOC')][text()]"
+      def toclevel
+        ret = toclevel_classes.map do |l|
+          "#{l}:not(:empty):not(.TermNum):not(.noTOC)"
+        end
+        <<~HEAD.freeze
+          function toclevel() { return "#{ret.join(',')}";}
+        HEAD
       end
-      docxml.xpath(path.join(" | ")).each_with_index do |h, tocidx|
-        h["id"] ||= "toc#{tocidx}"
-        toc += html_toc_entry(h.name, h)
+
+      # needs to be same output as toclevel
+      def html_toc(docxml)
+        idx = docxml.at("//div[@id = 'toc']") or return docxml
+        toc = "<ul>"
+        path = toclevel_classes.map do |l|
+          "//main//#{l}[not(@class = 'TermNum')][not(@class = 'noTOC')][text()]"
+        end
+        docxml.xpath(path.join(" | ")).each_with_index do |h, tocidx|
+          h["id"] ||= "toc#{tocidx}"
+          toc += html_toc_entry(h.name, h)
+        end
+        idx.children = "#{toc}</ul>"
+        docxml
       end
-      idx.children = "#{toc}</ul>"
-      docxml
-    end
 
-    # presupposes that the image source is local
-    def move_images(docxml)
-      FileUtils.rm_rf tmpimagedir
-      FileUtils.mkdir tmpimagedir
-      docxml.xpath("//*[local-name() = 'img']").each do |i|
-        i["width"], i["height"] = Html2Doc.image_resize(i, image_localfile(i),
-                                                        @maxheight, @maxwidth)
-        next if /^data:/.match? i["src"]
+      # presupposes that the image source is local
+      def move_images(docxml)
+        FileUtils.rm_rf tmpimagedir
+        FileUtils.mkdir tmpimagedir
+        docxml.xpath("//*[local-name() = 'img']").each do |i|
+          i["width"], i["height"] = Html2Doc.image_resize(i, image_localfile(i),
+                                                          @maxheight, @maxwidth)
+          next if /^data:/.match? i["src"]
 
-        @datauriimage ? datauri(i) : move_image1(i)
+          @datauriimage ? datauri(i) : move_image1(i)
+        end
+        docxml
       end
-      docxml
-    end
 
-    def datauri(img)
-      type = img["src"].split(".")[-1]
-      supertype = type == "xml" ? "application" : "image"
-      bin = IO.binread(image_localfile(img))
-      data = Base64.strict_encode64(bin)
-      img["src"] = "data:#{supertype}/#{type};base64,#{data}"
-    end
+      def datauri(img)
+        type = img["src"].split(".")[-1]
+        supertype = type == "xml" ? "application" : "image"
+        bin = IO.binread(image_localfile(img))
+        data = Base64.strict_encode64(bin)
+        img["src"] = "data:#{supertype}/#{type};base64,#{data}"
+      end
 
-    def image_suffix(img)
-      type = img["mimetype"]&.sub(%r{^[^/*]+/}, "")
-      matched = /\.(?<suffix>[^. \r\n\t]+)$/.match img["src"]
-      type and !type.empty? and return type
+      def image_suffix(img)
+        type = img["mimetype"]&.sub(%r{^[^/*]+/}, "")
+        matched = /\.(?<suffix>[^. \r\n\t]+)$/.match img["src"]
+        type and !type.empty? and return type
 
-      !matched.nil? and matched[:suffix] and return matched[:suffix]
-      "png"
-    end
+        !matched.nil? and matched[:suffix] and return matched[:suffix]
+        "png"
+      end
 
-    def move_image1(img)
-      suffix = image_suffix(img)
-      uuid = UUIDTools::UUID.random_create.to_s
-      fname = "#{uuid}.#{suffix}"
-      new_full_filename = File.join(tmpimagedir, fname)
-      local_filename = image_localfile(img)
-      FileUtils.cp local_filename, new_full_filename
-      img["src"] = File.join(rel_tmpimagedir, fname)
-    end
+      def move_image1(img)
+        suffix = image_suffix(img)
+        uuid = UUIDTools::UUID.random_create.to_s
+        fname = "#{uuid}.#{suffix}"
+        new_full_filename = File.join(tmpimagedir, fname)
+        local_filename = image_localfile(img)
+        FileUtils.cp local_filename, new_full_filename
+        img["src"] = File.join(rel_tmpimagedir, fname)
+      end
 
-    def inject_script(doc)
-      return doc unless @scripts
+      def inject_script(doc)
+        return doc unless @scripts
 
-      scripts = File.read(@scripts, encoding: "UTF-8")
-      scripts_override = ""
-      @scripts_override and
-        scripts_override = File.read(@scripts_override, encoding: "UTF-8")
-      a = doc.split(%r{</body>})
-      "#{a[0]}#{scripts}#{scripts_override}</body>#{a[1]}"
-    end
+        scripts = File.read(@scripts, encoding: "UTF-8")
+        scripts_override = ""
+        @scripts_override and
+          scripts_override = File.read(@scripts_override, encoding: "UTF-8")
+        a = doc.split(%r{</body>})
+        "#{a[0]}#{scripts}#{scripts_override}</body>#{a[1]}"
+      end
 
-    def sourcecode_highlighter
-      '<script src="https://cdn.rawgit.com/google/code-prettify/master/'\
-        'loader/run_prettify.js"></script>'
-    end
+      def sourcecode_highlighter
+        '<script src="https://cdn.rawgit.com/google/code-prettify/master/'\
+          'loader/run_prettify.js"></script>'
+      end
 
-    MATHJAX_ADDR =
-      "https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js".freeze
-    MATHJAX = <<~"MATHJAX".freeze
-      <script type="text/x-mathjax-config">
-        MathJax.Hub.Config({
-          "HTML-CSS": { preferredFont: "STIX" },
-          asciimath2jax: { delimiters: [['OPEN', 'CLOSE']] }
-       });
-      </script>
-      <script src="#{MATHJAX_ADDR}?config=MML_HTMLorMML-full" async="async"></script>
-    MATHJAX
-
-    def mathjax(open, close)
-      MATHJAX.gsub("OPEN", open).gsub("CLOSE", close)
-    end
+      MATHJAX_ADDR =
+        "https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js".freeze
+      MATHJAX = <<~"MATHJAX".freeze
+        <script type="text/x-mathjax-config">
+          MathJax.Hub.Config({
+            "HTML-CSS": { preferredFont: "STIX" },
+            asciimath2jax: { delimiters: [['OPEN', 'CLOSE']] }
+         });
+        </script>
+        <script src="#{MATHJAX_ADDR}?config=MML_HTMLorMML-full" async="async"></script>
+      MATHJAX
+
+      def mathjax(open, close)
+        MATHJAX.gsub("OPEN", open).gsub("CLOSE", close)
+      end
 
-    def term_header(docxml)
-      %w(h1 h2 h3 h4 h5 h6 h7 h8).each do |h|
-        docxml.xpath("//p[@class = 'TermNum'][../#{h}]").each do |p|
-          p.name = "h#{h[1].to_i + 1}"
+      def term_header(docxml)
+        %w(h1 h2 h3 h4 h5 h6 h7 h8).each do |h|
+          docxml.xpath("//p[@class = 'TermNum'][../#{h}]").each do |p|
+            p.name = "h#{h[1].to_i + 1}"
+          end
         end
+        docxml
       end
-      docxml
     end
   end
 end