isodoc 1.0.15 → 1.0.16

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6a664c3da9b6df6b4e533371a17c3a407423cafaeb043eacc92a14ff0282113b
-  data.tar.gz: a01075ddc20896c5347367c296379a2ade09177804f37631b386ea92046fd740
+  metadata.gz: 9b8b0f152601a2bbeb84c54de21063c1c8a3153b80a8d7c9e7e72af587afadf2
+  data.tar.gz: 8e3f19d7bc9d426db9bd2bd49ebd4005bc24ba03ce9add831341780cf2f24b7d
 SHA512:
-  metadata.gz: 901a72db1d909f98dc6e2813ddb5d6ad7eec9feb870f0545d473fd5fc58e9c3e0d065f99c82dac964d06398af988c68b5c0743b19e51bf339ca085bcb7574125
-  data.tar.gz: fb8143ee5d1f5fb2a49c40f1218eeaa0e36a6c9fb9ba0c1abda1ca10154f0816aa0ac76072a2bd58e539c255d6dc85ca28888385a7407992a6502a988a511d03
+  metadata.gz: fac36a308df3caa41ed65253c0248f74d6bd21cd1341f7996ef30195ac8cadbd2679ac6806c82dbabe9b2f355c39e42c2687d0569c35de8a29e3f16d8f077755
+  data.tar.gz: ad99d78fcce5692491b593e3d415f1520120e32a2440d350504040a779dc2bd9b636a316d6e27851c72fb5ec314dab4ad4c41abf06e87b773102ee950a681c3a

data/lib/isodoc/convert.rb

@@ -133,10 +133,6 @@ module IsoDoc
                                     "lib", "isodoc")
       SassC.load_paths << File.dirname(filename)
       engine = SassC::Engine.new(fontheader + stylesheet, syntax: :scss)
-      #outname = File.basename(filename, ".*") + ".css"
-      #File.open(outname, "w:UTF-8") { |f| f.write(engine.render) }
-      #@files_to_delete << outname
-      #outname
       Tempfile.open([File.basename(filename, ".*"), "css"],
                     :encoding => "utf-8") do |f|
         f.write(engine.render)

data/lib/isodoc/function/cleanup.rb

@@ -1,5 +1,13 @@
 module IsoDoc::Function
   module Cleanup
+    def textcleanup(docxml)
+      docxml.
+        gsub(/\[TERMREF\]\s*/, l10n("[#{@source_lbl}: ")).
+        gsub(/\s*\[MODIFICATION\]\s*\[\/TERMREF\]/, l10n(", #{@modified_lbl} [/TERMREF]")).
+        gsub(/\s*\[\/TERMREF\]\s*/, l10n("]")).
+        gsub(/\s*\[MODIFICATION\]/, l10n(", #{@modified_lbl} — "))
+    end
+
     def cleanup(docxml)
       comment_cleanup(docxml)
       footnote_cleanup(docxml)

data/lib/isodoc/function/inline.rb

@@ -8,6 +8,10 @@ module IsoDoc::Function
       out.br
     end
 
+    def pagebreak_parse(_node, out)
+      out.br
+    end
+
     def hr_parse(node, out)
       out.hr
     end

data/lib/isodoc/function/section.rb

@@ -25,7 +25,7 @@ module IsoDoc::Function
       if node["inline-header"] == "true"
         inline_header_title(out, node, c1)
       else
-        div.send "h#{anchor(node['id'], :level) || '1'}" do |h|
+        div.send "h#{anchor(node['id'], :level, false) || '1'}" do |h|
           lbl = anchor(node['id'], :label, false)
           h << "#{lbl}#{clausedelim}" if lbl && !@suppressheadingnumbers
           clausedelimspace(out) if lbl && !@suppressheadingnumbers

data/lib/isodoc/function/to_word_html.rb

@@ -43,7 +43,6 @@ module IsoDoc::Function
     def define_head(head, filename, _dir)
       if @standardstylesheet
         head.style do |style|
-          #stylesheet = File.read(@standardstylesheet, encoding: "utf-8").
           @standardstylesheet.open
           stylesheet = @standardstylesheet.read.
             gsub("FILENAME", File.basename(filename))
@@ -150,7 +149,7 @@ module IsoDoc::Function
         when "br" then br_parse(node, out)
         when "hr" then hr_parse(node, out)
         when "bookmark" then bookmark_parse(node, out)
-        when "pagebreak" then page_break(out)
+        when "pagebreak" then pagebreak_parse(node, out)
         when "callout" then callout_parse(node, out)
         when "stem" then stem_parse(node, out)
         when "clause" then clause_parse(node, out)

data/lib/isodoc/function/utils.rb

@@ -140,11 +140,6 @@ module IsoDoc::Function
 
     def populate_template(docxml, _format)
       meta = @meta.get.merge(@labels || {})
-      docxml = docxml.
-        gsub(/\[TERMREF\]\s*/, l10n("[#{@source_lbl}: ")).
-        gsub(/\s*\[MODIFICATION\]\s*\[\/TERMREF\]/, l10n(", #{@modified_lbl} [/TERMREF]")).
-        gsub(/\s*\[\/TERMREF\]\s*/, l10n("]")).
-        gsub(/\s*\[MODIFICATION\]/, l10n(", #{@modified_lbl} — "))
       template = liquid(docxml)
       template.render(meta.map { |k, v| [k.to_s, empty2nil(v)] }.to_h).
         gsub('<', '<').gsub('>', '>').gsub('&', '&')
@@ -152,12 +147,6 @@ module IsoDoc::Function
 
     def save_dataimage(uri, relative_dir = true)
       %r{^data:image/(?<imgtype>[^;]+);base64,(?<imgdata>.+)$} =~ uri
-      #uuid = UUIDTools::UUID.random_create.to_s
-      #fname = "#{uuid}.#{imgtype}"
-      #new_file = File.join(tmpimagedir, fname)
-      #@files_to_delete << new_file
-      #File.open(new_file, "wb") { |f| f.write(Base64.strict_decode64(imgdata)) }
-      #File.join(relative_dir ? rel_tmpimagedir : tmpimagedir, fname)
       imgtype = "png" unless /^[a-z0-9]+$/.match imgtype
       Tempfile.open(["image", ".#{imgtype}"]) do |f|
         f.binmode

data/lib/isodoc/function/xref_sect_gen.rb

@@ -36,12 +36,14 @@ module IsoDoc::Function
       ret
     end
 
+    SUBCLAUSES = "./clause | ./references | ./term  | ./terms | ./definitions".freeze
+
     # in StanDoc, prefaces have no numbering; they are referenced only by title
     def preface_names(clause)
       return if clause.nil?
       @anchors[clause["id"]] =
         { label: nil, level: 1, xref: preface_clause_name(clause), type: "clause" }
-      clause.xpath(ns("./clause | ./terms | ./term | ./definitions | ./references")).each_with_index do |c, i|
+      clause.xpath(ns(SUBCLAUSES)).each_with_index do |c, i|
         preface_names1(c, c.at(ns("./title"))&.text, "#{preface_clause_name(clause)}, #{i+1}", 2)
       end
     end
@@ -50,7 +52,7 @@ module IsoDoc::Function
       label = title || parent_title
       @anchors[clause["id"]] =
         { label: nil, level: level, xref: label, type: "clause" }
-      clause.xpath(ns("./clause | ./terms | ./term | ./definitions | ./references")).
+      clause.xpath(ns(SUBCLAUSES)).
         each_with_index do |c, i|
         preface_names1(c, c.at(ns("./title"))&.text, "#{label} #{i+1}", level + 1)
       end
@@ -77,7 +79,7 @@ module IsoDoc::Function
       num = num + 1
       @anchors[clause["id"]] =
         { label: num.to_s, xref: l10n("#{@clause_lbl} #{num}"), level: lvl, type: "clause" }
-      clause.xpath(ns("./clause | ./term  | ./terms | ./definitions | ./references")).
+      clause.xpath(ns(SUBCLAUSES)).
         each_with_index do |c, i|
         section_names1(c, "#{num}.#{i + 1}", lvl + 1)
       end
@@ -87,7 +89,7 @@ module IsoDoc::Function
     def section_names1(clause, num, level)
       @anchors[clause["id"]] =
         { label: num, level: level, xref: l10n("#{@clause_lbl} #{num}"), type: "clause" }
-      clause.xpath(ns("./clause | ./terms | ./term | ./definitions | ./references")).
+      clause.xpath(ns(SUBCLAUSES)).
         each_with_index do |c, i|
         section_names1(c, "#{num}.#{i + 1}", level + 1)
       end
@@ -102,7 +104,7 @@ module IsoDoc::Function
     def annex_names(clause, num)
       @anchors[clause["id"]] = { label: annex_name_lbl(clause, num), type: "clause",
                                  xref: "#{@annex_lbl} #{num}", level: 1 }
-      clause.xpath(ns("./clause | ./references | ./term  | ./terms | ./definitions")).each_with_index do |c, i|
+      clause.xpath(ns(SUBCLAUSES)).each_with_index do |c, i|
         annex_names1(c, "#{num}.#{i + 1}", 2)
       end
       hierarchical_asset_names(clause, num)
@@ -111,7 +113,7 @@ module IsoDoc::Function
     def annex_names1(clause, num, level)
       @anchors[clause["id"]] = { label: num, xref: "#{@annex_lbl} #{num}",
                                  level: level, type: "clause" }
-      clause.xpath(ns("./clause | ./references | ./term  | ./terms | ./definitions")).each_with_index do |c, i|
+      clause.xpath(ns(SUBCLAUSES)).each_with_index do |c, i|
         annex_names1(c, "#{num}.#{i + 1}", level + 1)
       end
     end

data/lib/isodoc/html_function/html.rb

@@ -38,7 +38,7 @@ module IsoDoc::HtmlFunction
 
     def html_head()
       <<~HEAD.freeze
-    <title>{{ doctitle }}</title>
+    <title>#{@meta&.get&.dig(:doctitle)}</title>
     <script type="text/javascript" src="https://ajax.googleapis.com/ajax/libs/jquery/3.3.1/jquery.min.js"></script>
 
     <!--TOC script import-->

data/lib/isodoc/html_function/postprocess.rb

@@ -1,7 +1,7 @@
 module IsoDoc::HtmlFunction
   module Html
     def postprocess(result, filename, dir)
-      result = from_xhtml(cleanup(to_xhtml(result)))
+      result = from_xhtml(cleanup(to_xhtml(textcleanup(result))))
       toHTML(result, filename)
       @files_to_delete.each { |f| FileUtils.rm_rf f }
     end
@@ -15,7 +15,7 @@ module IsoDoc::HtmlFunction
 
     def toHTML(result, filename)
       result = (from_xhtml(html_cleanup(to_xhtml(result))))
-      result = populate_template(result, :html)
+      #result = populate_template(result, :html)
       result = from_xhtml(move_images(to_xhtml(result)))
       result = html5(script_cdata(inject_script(result)))
       File.open("#{filename}.html", "w:UTF-8") { |f| f.write(result) }
@@ -62,6 +62,7 @@ module IsoDoc::HtmlFunction
     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 { |h| h.remove }
       auth&.xpath(".//h1 | .//h2")&.each { |h| h["class"] = "IntroTitle" }
       dest and auth and dest.replace(auth.remove)
     end
@@ -75,26 +76,15 @@ module IsoDoc::HtmlFunction
     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 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")
-    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")
-    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 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)

data/lib/isodoc/version.rb

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "1.0.15".freeze
+  VERSION = "1.0.16".freeze
 end

data/lib/isodoc/word_function/body.rb

@@ -1,3 +1,5 @@
+require_relative "./table.rb"
+
 module IsoDoc::WordFunction
   module Body
     def define_head(head, filename, _dir)
@@ -56,39 +58,6 @@ module IsoDoc::WordFunction
       classtype
     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
-
-    SW1 = "solid windowtext".freeze
-
-    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:#{SW1} 1.5pt;mso-border-bottom-alt:#{SW1} 1.5pt;"
-      tfoot.add_child("<tr><td colspan='#{cols}' style='#{style}'/></tr>")
-      tfoot.xpath(".//td").last
-    end
-
-    def make_tr_attr(td, row, totalrows, _header)
-      style = td.name == "th" ? "font-weight:bold;" : ""
-      rowmax = td["rowspan"] ? row + td["rowspan"].to_i - 1 : row
-      style += <<~STYLE
-        border-top:#{row.zero? ? "#{SW1} 1.5pt;" : 'none;'}
-        mso-border-top-alt:#{row.zero? ? "#{SW1} 1.5pt;" : 'none;'}
-        border-bottom:#{SW1} #{rowmax == totalrows ? '1.5' : '1.0'}pt;
-        mso-border-bottom-alt:#{SW1} #{rowmax == totalrows ? '1.5' : '1.0'}pt;
-      STYLE
-      { rowspan: td["rowspan"], colspan: td["colspan"],
-        align: td["align"], style: style.gsub(/\n/, "") }
-    end
-
     def section_break(body)
       body.p do |p|
         p.br **{ clear: "all", class: "section" }
@@ -103,6 +72,14 @@ module IsoDoc::WordFunction
       end
     end
 
+    def pagebreak_parse(node, out)
+      return page_break(out) if node["orientation"].nil?
+      out.p do |p|
+        p.br **{clear: "all", class: "section", 
+                orientation: node["orientation"] }
+      end
+    end
+
     WORD_DT_ATTRS = {class: @note ? "Note" : nil, align: "left",
                      style: "margin-left:0pt;text-align:left;"}.freeze
 
@@ -238,30 +215,5 @@ module IsoDoc::WordFunction
         "mso-table-overlap:never;border-collapse:collapse;"
       })
     end
-
-    def make_table_attr(node)
-      super.merge(attr_code({
-        summary: node["summary"],
-        style: "mso-table-lspace:15.0cm;margin-left:423.0pt;"\
-        "mso-table-rspace:15.0cm;margin-right:423.0pt;"\
-        "mso-table-anchor-horizontal:column;"\
-        "mso-table-overlap:never;border-spacing:0;border-width:1px;"
-      }))
-    end
-
-    def table_parse(node, out)
-      @in_table = true
-      table_title_parse(node, out)
-      out.div **{ align: "center", class: "table_container" } do |div|
-        div.table **make_table_attr(node) do |t|
-          thead_parse(node, t)
-          tbody_parse(node, t)
-          tfoot_parse(node, t)
-          (dl = node.at(ns("./dl"))) && parse(dl, out)
-          node.xpath(ns("./note")).each { |n| parse(n, out) }
-        end
-      end
-      @in_table = false
-    end
   end
 end

data/lib/isodoc/word_function/postprocess.rb

@@ -1,4 +1,5 @@
 require "fileutils"
+require_relative "./postprocess_cover.rb"
 
 module IsoDoc::WordFunction
   module Postprocess
@@ -32,14 +33,19 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
 
     def postprocess(result, filename, dir)
       header = generate_header(filename, dir)
-      result = from_xhtml(cleanup(to_xhtml(result)))
+      result = from_xhtml(cleanup(to_xhtml(textcleanup(result))))
       toWord(result, filename, dir, header)
       @files_to_delete.each { |f| FileUtils.rm_f f }
     end
 
     def toWord(result, filename, dir, header)
-      result = populate_template(result, :word)
+      #result = populate_template(result, :word)
       result = from_xhtml(word_cleanup(to_xhtml(result)))
+      unless @landscapestyle.empty?
+        @wordstylesheet&.open
+        @wordstylesheet&.write(@landscapestyle)
+        @wordstylesheet&.close
+      end
       Html2Doc.process(result, filename: filename, stylesheet: @wordstylesheet&.path,
                        header_file: header&.path, dir: dir,
                        asciimathdelims: [@openmathdelim, @closemathdelim],
@@ -65,6 +71,7 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       word_example_cleanup(docxml)
       word_pseudocode_cleanup(docxml)
       word_image_caption(docxml)
+      word_section_breaks(docxml)
       authority_cleanup(docxml)
       docxml
     end
@@ -72,6 +79,7 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
     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 { |h| h.remove }
       auth&.xpath(".//h1 | .//h2")&.each do |h|
         h.name = "p"
         h["class"] = "TitlePageSubhead"
@@ -162,32 +170,6 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       end
     end
 
-    def word_preface(docxml)
-      word_cover(docxml) if @wordcoverpage
-      word_intro(docxml, @wordToClevels) if @wordintropage
-    end
-
-    def word_cover(docxml)
-      cover = File.read(@wordcoverpage, encoding: "UTF-8")
-      cover = populate_template(cover, :word)
-      coverxml = to_word_xhtml_fragment(cover)
-      docxml.at('//div[@class="WordSection1"]').children.first.previous =
-        coverxml.to_xml(encoding: "US-ASCII")
-    end
-
-    def insert_toc(intro, docxml, level)
-      intro.sub(/WORDTOC/, make_WordToC(docxml, level))
-    end
-
-    def word_intro(docxml, level)
-      intro = insert_toc(File.read(@wordintropage, encoding: "UTF-8"),
-                         docxml, level)
-      intro = populate_template(intro, :word)
-      introxml = to_word_xhtml_fragment(intro)
-      docxml.at('//div[@class="WordSection2"]').children.first.previous =
-        introxml.to_xml(encoding: "US-ASCII")
-    end
-
     def generate_header(filename, _dir)
       return nil unless @header
       template = IsoDoc::Common.liquid(File.read(@header, encoding: "UTF-8"))
@@ -200,54 +182,31 @@ xmlns:m="http://schemas.microsoft.com/office/2004/12/omml">
       end
     end
 
-    def word_toc_entry(toclevel, heading)
-      bookmark = bookmarkid # Random.rand(1000000000)
-      <<~TOC
-        <p class="MsoToc#{toclevel}"><span class="MsoHyperlink"><span
-        lang="EN-GB" style='mso-no-proof:yes'>
-        <a href="#_Toc#{bookmark}">#{heading}<span lang="EN-GB"
-        class="MsoTocTextSpan">
-        <span style='mso-tab-count:1 dotted'>. </span>
-        </span><span lang="EN-GB" class="MsoTocTextSpan">
-        <span style='mso-element:field-begin'></span></span>
-        <span lang="EN-GB"
-        class="MsoTocTextSpan"> PAGEREF _Toc#{bookmark} \\h </span>
-          <span lang="EN-GB" class="MsoTocTextSpan"><span
-          style='mso-element:field-separator'></span></span><span
-          lang="EN-GB" class="MsoTocTextSpan">1</span>
-          <span lang="EN-GB"
-          class="MsoTocTextSpan"></span><span
-          lang="EN-GB" class="MsoTocTextSpan"><span
-          style='mso-element:field-end'></span></span></a></span></span></p>
-
-      TOC
-    end
-
-    def word_toc_preface(level) 
-      <<~TOC.freeze
-      <span lang="EN-GB"><span
-        style='mso-element:field-begin'></span><span
-        style='mso-spacerun:yes'>&#xA0;</span>TOC
-        \\o &quot;1-#{level}&quot; \\h \\z \\u <span
-        style='mso-element:field-separator'></span></span>
-      TOC
-    end
-
-    WORD_TOC_SUFFIX1 = <<~TOC.freeze
-      <p class="MsoToc1"><span lang="EN-GB"><span
-        style='mso-element:field-end'></span></span><span
-        lang="EN-GB"><o:p>&nbsp;</o:p></span></p>
-    TOC
-
-    def make_WordToC(docxml, level)
-      toc = ""
-      #docxml.xpath("//h1 | //h2[not(ancestor::*[@class = 'Section3'])]").
-      xpath = (1..level).each.map { |i| "//h#{i}" }.join (" | ")
-      docxml.xpath(xpath).each do |h|
-        toc += word_toc_entry(h.name[1].to_i, header_strip(h))
+    def word_section_breaks(docxml)
+      @landscapestyle = ""
+      word_section_breaks1(docxml, "WordSection2")
+      word_section_breaks1(docxml, "WordSection3")
+    end
+
+    def word_section_breaks1(docxml, sect)
+      docxml.xpath("//div[@class = '#{sect}']//br[@orientation]").reverse.
+        each_with_index do |br, i|
+        @landscapestyle += "\ndiv.#{sect}_#{i} {page:#{sect}"\
+          "#{br["orientation"] == "landscape" ? "L" : "P"};}\n"
+        br.delete("orientation")
+        split_at_section_break(docxml, sect, br, i)
+      end
+    end
+
+    def split_at_section_break(docxml, sect, br, i)
+      move = br.parent.xpath("following::node()") &
+        br.document.xpath("//div[@class = '#{sect}']//*")
+      ins = docxml.at("//div[@class = '#{sect}']").
+        after("<div class='#{sect}_#{i}'/>").next_element
+      move.each do |m|
+        next if m.at("./ancestor::div[@class = '#{sect}_#{i}']")
+        ins << m.remove
       end
-      toc.sub(/(<p class="MsoToc1">)/,
-              %{\\1#{word_toc_preface(level)}}) +  WORD_TOC_SUFFIX1
     end
   end
 end

data/lib/isodoc/word_function/postprocess_cover.rb

@@ -0,0 +1,79 @@
+module IsoDoc::WordFunction
+  module Postprocess
+    def word_preface(docxml)
+      word_cover(docxml) if @wordcoverpage
+      word_intro(docxml, @wordToClevels) if @wordintropage
+    end
+
+    def word_cover(docxml)
+      cover = File.read(@wordcoverpage, encoding: "UTF-8")
+      cover = populate_template(cover, :word)
+      coverxml = to_word_xhtml_fragment(cover)
+      docxml.at('//div[@class="WordSection1"]').children.first.previous =
+        coverxml.to_xml(encoding: "US-ASCII")
+    end
+
+    def word_intro(docxml, level)
+      intro = insert_toc(File.read(@wordintropage, encoding: "UTF-8"),
+                         docxml, level)
+      intro = populate_template(intro, :word)
+      introxml = to_word_xhtml_fragment(intro)
+      docxml.at('//div[@class="WordSection2"]').children.first.previous =
+        introxml.to_xml(encoding: "US-ASCII")
+    end
+
+    def insert_toc(intro, docxml, level)
+      intro.sub(/WORDTOC/, make_WordToC(docxml, level))
+    end
+
+    def word_toc_entry(toclevel, heading)
+      bookmark = bookmarkid # Random.rand(1000000000)
+      <<~TOC
+        <p class="MsoToc#{toclevel}"><span class="MsoHyperlink"><span
+        lang="EN-GB" style='mso-no-proof:yes'>
+        <a href="#_Toc#{bookmark}">#{heading}<span lang="EN-GB"
+        class="MsoTocTextSpan">
+        <span style='mso-tab-count:1 dotted'>. </span>
+        </span><span lang="EN-GB" class="MsoTocTextSpan">
+        <span style='mso-element:field-begin'></span></span>
+        <span lang="EN-GB"
+        class="MsoTocTextSpan"> PAGEREF _Toc#{bookmark} \\h </span>
+          <span lang="EN-GB" class="MsoTocTextSpan"><span
+          style='mso-element:field-separator'></span></span><span
+          lang="EN-GB" class="MsoTocTextSpan">1</span>
+          <span lang="EN-GB"
+          class="MsoTocTextSpan"></span><span
+          lang="EN-GB" class="MsoTocTextSpan"><span
+          style='mso-element:field-end'></span></span></a></span></span></p>
+
+      TOC
+    end
+
+    def word_toc_preface(level)
+      <<~TOC.freeze
+      <span lang="EN-GB"><span
+        style='mso-element:field-begin'></span><span
+        style='mso-spacerun:yes'>&#xA0;</span>TOC
+        \\o &quot;1-#{level}&quot; \\h \\z \\u <span
+        style='mso-element:field-separator'></span></span>
+      TOC
+    end
+
+    WORD_TOC_SUFFIX1 = <<~TOC.freeze
+      <p class="MsoToc1"><span lang="EN-GB"><span
+        style='mso-element:field-end'></span></span><span
+        lang="EN-GB"><o:p>&nbsp;</o:p></span></p>
+    TOC
+
+    def make_WordToC(docxml, level)
+      toc = ""
+      #docxml.xpath("//h1 | //h2[not(ancestor::*[@class = 'Section3'])]").
+      xpath = (1..level).each.map { |i| "//h#{i}" }.join (" | ")
+      docxml.xpath(xpath).each do |h|
+        toc += word_toc_entry(h.name[1].to_i, header_strip(h))
+      end
+      toc.sub(/(<p class="MsoToc1">)/,
+              %{\\1#{word_toc_preface(level)}}) +  WORD_TOC_SUFFIX1
+    end
+  end
+end

data/lib/isodoc/word_function/table.rb

@@ -0,0 +1,61 @@
+module IsoDoc::WordFunction
+  module Body
+    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
+
+    SW1 = "solid windowtext".freeze
+
+    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:#{SW1} 1.5pt;mso-border-bottom-alt:#{SW1} 1.5pt;"
+      tfoot.add_child("<tr><td colspan='#{cols}' style='#{style}'/></tr>")
+      tfoot.xpath(".//td").last
+    end
+
+    def make_tr_attr(td, row, totalrows, _header)
+      style = td.name == "th" ? "font-weight:bold;" : ""
+      rowmax = td["rowspan"] ? row + td["rowspan"].to_i - 1 : row
+      style += <<~STYLE
+        border-top:#{row.zero? ? "#{SW1} 1.5pt;" : 'none;'}
+        mso-border-top-alt:#{row.zero? ? "#{SW1} 1.5pt;" : 'none;'}
+        border-bottom:#{SW1} #{rowmax == totalrows ? '1.5' : '1.0'}pt;
+        mso-border-bottom-alt:#{SW1} #{rowmax == totalrows ? '1.5' : '1.0'}pt;
+      STYLE
+      { rowspan: td["rowspan"], colspan: td["colspan"],
+        align: td["align"], style: style.gsub(/\n/, "") }
+    end
+
+    def make_table_attr(node)
+      super.merge(attr_code({
+        summary: node["summary"],
+        style: "mso-table-lspace:15.0cm;margin-left:423.0pt;"\
+        "mso-table-rspace:15.0cm;margin-right:423.0pt;"\
+        "mso-table-anchor-horizontal:column;"\
+        "mso-table-overlap:never;border-spacing:0;border-width:1px;"
+      }))
+    end
+
+    def table_parse(node, out)
+      @in_table = true
+      table_title_parse(node, out)
+      out.div **{ align: "center", class: "table_container" } do |div|
+        div.table **make_table_attr(node) do |t|
+          thead_parse(node, t)
+          tbody_parse(node, t)
+          tfoot_parse(node, t)
+          (dl = node.at(ns("./dl"))) && parse(dl, out)
+          node.xpath(ns("./note")).each { |n| parse(n, out) }
+        end
+      end
+      @in_table = false
+    end
+  end
+end

data/spec/isodoc/cleanup_spec.rb

@@ -762,4 +762,5 @@ INPUT
 
     OUTPUT
   end
+
 end

data/spec/isodoc/inline_spec.rb

@@ -8,7 +8,7 @@ RSpec.describe IsoDoc do
     <p>
     <em>A</em> <strong>B</strong> <sup>C</sup> <sub>D</sub> <tt>E</tt>
     <strike>F</strike> <smallcap>G</smallcap> <keyword>I</keyword> <br/> <hr/>
-    <bookmark id="H"/> <pagebreak/>
+    <bookmark id="H"/> <pagebreak/> <pagebreak orientation="landscape"/>
     </p>
     </foreword></preface>
     <sections>
@@ -21,7 +21,7 @@ RSpec.describe IsoDoc do
                  <p>
        <i>A</i> <b>B</b> <sup>C</sup> <sub>D</sub> <tt>E</tt>
        <s>F</s> <span style="font-variant:small-caps;">G</span> <span class="keyword">I</span> <br/> <hr/>
-       <a id="H"/> <br/>
+       <a id="H"/> <br/> <br/>
        </p>
                </div>
                <p class="zzSTDTitle1"/>
@@ -31,6 +31,49 @@ RSpec.describe IsoDoc do
     OUTPUT
   end
 
+    it "processes inline formatting (Word)" do
+    expect(xmlpp(IsoDoc::WordConvert.new({}).convert("test", <<~"INPUT", true))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface/><sections><clause>
+    <p>
+    <em>A</em> <strong>B</strong> <sup>C</sup> <sub>D</sub> <tt>E</tt>
+    <strike>F</strike> <smallcap>G</smallcap> <keyword>I</keyword> <br/> <hr/>
+    <bookmark id="H"/> <pagebreak/> <pagebreak orientation="landscape"/>
+    </p>
+    </clause></sections>
+    </iso-standard>
+    INPUT
+    #{WORD_HDR}
+      <p class='zzSTDTitle1'/>
+      <div>
+        <h1/>
+        <p>
+          <i>A</i>
+          <b>B</b>
+          <sup>C</sup>
+          <sub>D</sub>
+          <tt>E</tt>
+          <s>F</s>
+          <span style='font-variant:small-caps;'>G</span>
+          <span class='keyword'>I</span>
+          <br/>
+          <hr/>
+          <a id='H'/>
+          <p>
+            <br clear='all' style='mso-special-character:line-break;page-break-before:always'/>
+          </p>
+          <p>
+            <br clear='all' class='section' orientation='landscape'/>
+          </p>
+        </p>
+      </div>
+    </div>
+  </body>
+</html>
+
+    OUTPUT
+  end
+
     it "ignores index entries" do
     expect(xmlpp(IsoDoc::HtmlConvert.new({}).convert("test", <<~"INPUT", true))).to be_equivalent_to xmlpp(<<~"OUTPUT")
     <iso-standard xmlns="http://riboseinc.com/isoxml">

data/spec/isodoc/postproc_spec.rb

@@ -25,6 +25,44 @@ RSpec.describe IsoDoc do
     expect(html).to match(/delimiters: \[\['\(#\(', '\)#\)'\]\]/)
   end
 
+  it "ignores Liquid markup in the document body" do
+    FileUtils.rm_f "test.doc"
+    FileUtils.rm_f "test.html"
+    IsoDoc::HtmlConvert.new({wordstylesheet: "spec/assets/word.css"}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+        <bibdata>
+        <title language="en">test</title>
+        </bibdata>
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">{% elif %}These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+INPUT
+expect(File.exist?("test.html")).to be true
+    html = File.read("test.html")
+  end
+
+    it "ignores Liquid markup in the document body (Word)" do
+    FileUtils.rm_f "test.doc"
+    FileUtils.rm_f "test.html"
+    IsoDoc::WordConvert.new({wordstylesheet: "spec/assets/word.css"}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+        <bibdata>
+        <title language="en">test</title>
+        </bibdata>
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">{% elif %}These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+INPUT
+expect(File.exist?("test.doc")).to be true
+    html = File.read("test.doc")
+  end
+
   it "generates HTML output docs with null configuration" do
     FileUtils.rm_f "test.doc"
     FileUtils.rm_f "test.html"
@@ -1221,4 +1259,186 @@ OUTPUT
     OUTPUT
   end
 
+      it "deals with landscape and portrait pagebreaks (Word)" do
+        FileUtils.rm_f "test.doc"
+        IsoDoc::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css", filename: "test"}).convert("test", <<~"INPUT", false)
+        <standard-document xmlns="http://riboseinc.com/isoxml">
+       <bibdata type="standard">
+         <title language="en" format="text/plain">Document title</title>
+         <version>
+           <draft>1.2</draft>
+         </version>
+         <language>en</language>
+         <script>Latn</script>
+         <status><stage>published</stage></status>
+         <ext>
+         <doctype>article</doctype>
+         </ext>
+       </bibdata>
+       <preface>
+       <introduction><title>Preface 1</title>
+       <p align="center">This is a <pagebreak orientation="landscape"/> paragraph</p>
+       <table>
+       <tbody>
+       <tr><td>A</td><td>B</td></tr>
+       </tbody>
+       </table>
+       <clause><title>Preface 1.1</title>
+       <p>On my side</p>
+       <pagebreak orientation="portrait"/>
+       <p>Upright again</p>
+       </clause>
+       <clause><title>Preface 1.3</title>
+       <p>And still upright</p>
+       </clause>
+       </introduction>
+       </preface>
+       <sections><clause><title>Foreword</title>
+       <note>
+       <p id="_">For further information on the Foreword, see <strong>ISO/IEC Directives, Part 2, 2016, Clause 12.</strong></p>
+       <pagebreak orientation="landscape"/>
+       <table id="_c09a7e60-b0c7-4418-9bfc-2ef0bc09a249">
+<thead>
+<tr>
+<th align="left">A</th>
+<th align="left">B</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td align="left">C</td>
+<td align="left">D</td>
+</tr>
+</tbody>
+<note id="_8fff1596-290e-4314-b03c-7a8aab97eebe">
+<p id="_32c22439-387a-48cf-a006-5ab3b934ba73">B</p>
+</note></table>
+       <pagebreak orientation="portrait"/>
+       <p>And up</p>
+       </note>
+        </clause></sections>
+       </standard-document>
+   INPUT
+   expect(File.exist?("test.doc")).to be true
+    html = File.read("test.doc", encoding: "UTF-8")
+    expect(html).to include "div.WordSection2_0 {page:WordSection2P;}"
+expect(html).to include "div.WordSection2_1 {page:WordSection2L;}"
+    expect(html).to include "div.WordSection3_0 {page:WordSection3P;}"
+expect(html).to include "div.WordSection3_1 {page:WordSection3L;}"
+
+expect(xmlpp(html.sub(/^.*<body /m, "<body ").sub(%r{</body>.*$}m, "</body>"))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+       <body lang='EN-US' xml:lang='EN-US' link='blue' vlink='#954F72'>
+         <div class='WordSection1'>
+           <p class='MsoNormal'>&#xA0;</p>
+         </div>
+         <p class='MsoNormal'>
+           <br clear='all' class='section'/>
+         </p>
+         <div class='WordSection2'>
+           <p class='MsoNormal'>
+             <br clear='all' style='mso-special-character:line-break;page-break-before:always'/>
+           </p>
+           <div class='Section3' id=''>
+             <h1 class='IntroTitle'>Introduction</h1>
+             <p align='center' style='text-align:center' class='MsoNormal'>
+               This is a 
+               <p class='MsoNormal'>
+                 <br clear='all' class='section'/>
+               </p>
+                paragraph
+             </p>
+           </div>
+         </div>
+         <div class='WordSection2_1'>
+           <div align='center' class='table_container'>
+             <table class='MsoISOTable' style='mso-table-lspace:15.0cm;margin-left:423.0pt;mso-table-rspace:15.0cm;margin-right:423.0pt;mso-table-anchor-horizontal:column;mso-table-overlap:never;border-spacing:0;border-width:1px;'>
+               <tbody>
+                 <tr>
+                   <td style='border-top:solid windowtext 1.5pt;mso-border-top-alt:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>A</td>
+                   <td style='border-top:solid windowtext 1.5pt;mso-border-top-alt:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>B</td>
+                 </tr>
+               </tbody>
+             </table>
+           </div>
+           <div>
+             <h1>Preface 1.1</h1>
+             <p class='MsoNormal'>On my side</p>
+             <p class='MsoNormal'>
+               <br clear='all' class='section'/>
+             </p>
+           </div>
+         </div>
+         <div class='WordSection2_0'>
+           <p class='MsoNormal'>Upright again</p>
+           <div>
+             <h1>Preface 1.3</h1>
+             <p class='MsoNormal'>And still upright</p>
+           </div>
+           <p class='MsoNormal'>&#xA0;</p>
+         </div>
+         <p class='MsoNormal'>
+           <br clear='all' class='section'/>
+         </p>
+         <div class='WordSection3'>
+           <p class='zzSTDTitle1'>Document title</p>
+           <div>
+             <h1>Foreword</h1>
+             <div id='' class='Note'>
+               <p class='Note'>
+                 <span class='note_label'>NOTE 1</span>
+                 <span style='mso-tab-count:1'>&#xA0; </span>
+                 For further information on the Foreword, see 
+                 <b>ISO/IEC Directives, Part 2, 2016, Clause 12.</b>
+               </p>
+               <p class='Note'>
+                 <br clear='all' class='section'/>
+               </p>
+             </div>
+           </div>
+         </div>
+         <div class='WordSection3_1'>
+           <p class='TableTitle' style='text-align:center;'>Table 1</p>
+           <div align='center' class='table_container'>
+             <table class='MsoISOTable' style='mso-table-lspace:15.0cm;margin-left:423.0pt;mso-table-rspace:15.0cm;margin-right:423.0pt;mso-table-anchor-horizontal:column;mso-table-overlap:never;border-spacing:0;border-width:1px;'>
+               <a name='_c09a7e60-b0c7-4418-9bfc-2ef0bc09a249' id='_c09a7e60-b0c7-4418-9bfc-2ef0bc09a249'/>
+               <thead>
+                 <tr>
+                   <th align='left' style='font-weight:bold;border-top:solid windowtext 1.5pt;mso-border-top-alt:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>A</th>
+                   <th align='left' style='font-weight:bold;border-top:solid windowtext 1.5pt;mso-border-top-alt:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>B</th>
+                 </tr>
+               </thead>
+               <tbody>
+                 <tr>
+                   <td align='left' style='border-top:solid windowtext 1.5pt;mso-border-top-alt:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>C</td>
+                   <td align='left' style='border-top:solid windowtext 1.5pt;mso-border-top-alt:solid windowtext 1.5pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>D</td>
+                 </tr>
+               </tbody>
+               <tfoot>
+                 <tr>
+                   <td colspan='2' style='border-top:0pt;mso-border-top-alt:0pt;border-bottom:solid windowtext 1.5pt;mso-border-bottom-alt:solid windowtext 1.5pt;'>
+                     <div class='Note'>
+                       <a name='_8fff1596-290e-4314-b03c-7a8aab97eebe' id='_8fff1596-290e-4314-b03c-7a8aab97eebe'/>
+                       <p class='Note'>
+                         <span class='note_label'>NOTE</span>
+                         <span style='mso-tab-count:1'>&#xA0; </span>
+                         B
+                       </p>
+                     </div>
+                   </td>
+                 </tr>
+               </tfoot>
+             </table>
+           </div>
+           <p class='Note'>
+             <br clear='all' class='section'/>
+           </p>
+         </div>
+         <div class='WordSection3_0'>
+           <p class='Note'>And up</p>
+         </div>
+         <div style='mso-element:footnote-list'/>
+       </body>
+OUTPUT
+      end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: isodoc
 version: !ruby/object:Gem::Version
-  version: 1.0.15
+  version: 1.0.16
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-01-30 00:00:00.000000000 Z
+date: 2020-02-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: asciimath
@@ -351,6 +351,8 @@ files:
 - lib/isodoc/word_function/comments.rb
 - lib/isodoc/word_function/footnotes.rb
 - lib/isodoc/word_function/postprocess.rb
+- lib/isodoc/word_function/postprocess_cover.rb
+- lib/isodoc/word_function/table.rb
 - spec/assets/header.html
 - spec/assets/html.css
 - spec/assets/htmlcover.html