isodoc 0.5.9 → 0.6.0

data/lib/isodoc/iso/wordconvert.rb

@@ -0,0 +1,34 @@
+module IsoDoc
+  module Iso
+    class WordConvert < IsoDoc::Convert
+      include IsoDoc::WordConvertModule
+
+      def default_fonts(options)
+        b = options[:bodyfont] ||
+          (options[:script] == "Hans" ? '"SimSun",serif' :
+           '"Cambria",serif')
+        h = options[:headerfont] ||
+          (options[:script] == "Hans" ? '"SimHei",sans-serif' :
+           '"Cambria",serif')
+        m = options[:monospacefont] || '"Courier New",monospace'
+        "$bodyfont: #{b};\n$headerfont: #{h};\n$monospacefont: #{m};\n"
+      end
+
+      def html_doc_path(file)
+        File.join(File.dirname(__FILE__), File.join("html", file))
+      end
+
+      def initialize(options)
+        super
+        @wordstylesheet = generate_css(html_doc_path("wordstyle.scss"), false, default_fonts(options))
+        @standardstylesheet = generate_css(html_doc_path("isodoc.scss"), false, default_fonts(options))
+        @header = html_doc_path("header.html")
+        @wordcoverpage = html_doc_path("word_iso_titlepage.html")
+        @wordintropage = html_doc_path("word_iso_intro.html")
+        @ulstyle = "l3"
+        @olstyle = "l2"
+      end
+
+    end
+  end
+end

data/lib/isodoc/iso2wordhtml.rb

@@ -24,23 +24,17 @@ module IsoDoc
       [filename, dir]
     end
 
-    # these are in fact preprocess,
-    # but they are extraneous to main HTML file
-    def html_header(html, docxml, filename, dir)
-      anchor_names docxml
-      define_head html, filename, dir
-    end
-
     # isodoc.css overrides any CSS injected by Html2Doc, which
     # is inserted before this CSS.
     def define_head(html, filename, _dir)
       html.head do |head|
         head.title { |t| t << filename }
-        return unless @standardstylesheet
-        head.style do |style|
-          stylesheet = File.read(@standardstylesheet).
-            gsub("FILENAME", filename)
-          style.comment "\n#{stylesheet}\n"
+        if @standardstylesheet
+          head.style do |style|
+            stylesheet = File.read(@standardstylesheet).
+              gsub("FILENAME", filename)
+            style.comment "\n#{stylesheet}\n"
+          end
         end
       end
     end
@@ -64,8 +58,6 @@ module IsoDoc
     def make_body2(body, docxml)
       body.div **{ class: "WordSection2" } do |div2|
         info docxml, div2
-        foreword docxml, div2
-        introduction docxml, div2
         div2.p { |p| p << "&nbsp;" } # placeholder
       end
       section_break(body)
@@ -73,6 +65,8 @@ module IsoDoc
 
     def make_body3(body, docxml)
       body.div **{ class: "WordSection3" } do |div3|
+        foreword docxml, div3
+        introduction docxml, div3
         middle docxml, div3
         footnotes div3
         comments div3
@@ -110,13 +104,13 @@ module IsoDoc
 
     def smallcap_parse(node, xml)
       xml.span **{ style: "font-variant:small-caps;" } do |s|
-        s << node.text
+        s << node.inner_html
       end
     end
 
     def text_parse(node, out)
       return if node.nil? || node.text.nil?
-      text = node.text
+      text = node.to_s
       text = text.gsub("\n", "<br/>").gsub(" ", "&nbsp;") if in_sourcecode
       out << text
     end
@@ -130,12 +124,12 @@ module IsoDoc
         text_parse(node, out)
       else
         case node.name
-        when "em" then out.i { |e| e << node.text }
-        when "strong" then out.b { |e| e << node.text }
-        when "sup" then out.sup { |e| e << node.text }
-        when "sub" then out.sub { |e| e << node.text }
-        when "tt" then out.tt { |e| e << node.text }
-        when "strike" then out.s { |e| e << node.text }
+        when "em" then out.i { |e| e << node.inner_html }
+        when "strong" then out.b { |e| e << node.inner_html }
+        when "sup" then out.sup { |e| e << node.inner_html }
+        when "sub" then out.sub { |e| e << node.inner_html }
+        when "tt" then out.tt { |e| e << node.inner_html }
+        when "strike" then out.s { |e| e << node.inner_html }
         when "smallcap" then smallcap_parse(node, out)
         when "br" then out.br
         when "hr" then out.hr
@@ -144,7 +138,7 @@ module IsoDoc
         when "callout" then callout_parse(node, out)
         when "stem" then stem_parse(node, out)
         when "clause" then clause_parse(node, out)
-        # when "subclause" then clause_parse(node, out)
+          # when "subclause" then clause_parse(node, out)
         when "appendix" then clause_parse(node, out)
         when "xref" then xref_parse(node, out)
         when "eref" then eref_parse(node, out)

data/lib/isodoc/section.rb

@@ -113,7 +113,7 @@ module IsoDoc
     end
 
     def term_defs_boilerplate_cont(src, term)
-      sources = sentence_join(src.map { |s| @anchors[s["target"]][:xref] })
+      sources = sentence_join(src.map { |s| @anchors[s["bibitemid"]][:xref] })
       if src.empty?
         @internal_terms_boilerplate
       elsif term.nil?

data/lib/isodoc/version.rb

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "0.5.9".freeze
+  VERSION = "0.6.0".freeze
 end

data/lib/isodoc/wordconvert/comments.rb

@@ -1,11 +1,3 @@
-#require "uuidtools"
-
-#module IsoDoc
-  #class WordConvert
-  #module WordConvertModule
-    #def self.included base
-#base.class_eval do
-
 def in_comment
   @in_comment
 end
@@ -67,7 +59,6 @@ def comment_cleanup(docxml)
   embed_comment_in_comment_list(docxml)
 end
 
-#COMMENT_IN_COMMENT_LIST =
 COMMENT_IN_COMMENT_LIST1 =
   '//div[@style="mso-element:comment-list"]//'\
   'span[@style="MsoCommentReference"]'.freeze
@@ -135,13 +126,11 @@ def get_comments_from_text(docxml, link_order)
   # comments
 end
 
-#COMMENT_TARGET_XREFS =
 COMMENT_TARGET_XREFS1 =
   "//span[@style='mso-special-character:comment']/@target".freeze
 
 def reorder_comments_by_comment_link(docxml)
   link_order = {}
-  #docxml.xpath(COMMENT_TARGET_XREFS).each_with_index do |target, i|
   docxml.xpath(COMMENT_TARGET_XREFS1).each_with_index do |target, i|
     link_order[target.value] = i
   end
@@ -149,7 +138,3 @@ def reorder_comments_by_comment_link(docxml)
   list = docxml.at("//*[@style='mso-element:comment-list']") || return
   list.children = comments.map { |c| c[:text] }.join("\n")
 end
-      #end
-    #end
-  #end
-#end

data/lib/isodoc/wordconvert/convert.rb

@@ -20,6 +20,7 @@ module IsoDoc
         eval File.open(File.join(File.dirname(__FILE__),"wordconvertmodule.rb")).read
         eval File.open(File.join(File.dirname(__FILE__),"comments.rb")).read
         eval File.open(File.join(File.dirname(__FILE__),"footnotes.rb")).read
+        eval File.open(File.join(File.dirname(__FILE__),"postprocess.rb")).read
       end
     end
   end

data/lib/isodoc/wordconvert/footnotes.rb

@@ -1,11 +1,3 @@
-#require "uuidtools"
-
-#module IsoDoc
-  #class WordConvert
-  #module WordConvertModule
-    #def self.included base
-#base.class_eval do
-
 def footnotes(div)
   return if @footnotes.empty?
   @footnotes.each { |fn| div.parent << fn }
@@ -74,7 +66,3 @@ def footnote_parse(node, out)
   @in_footnote = false
   @seen_footnote << fn
 end
-      #end
-    #end
-  #end
-#end

data/lib/isodoc/wordconvert/postprocess.rb

@@ -0,0 +1,110 @@
+def postprocess(result, filename, dir)
+  generate_header(filename, dir)
+  result = from_xhtml(cleanup(to_xhtml(result)))
+  toWord(result, filename, dir)
+  @files_to_delete.each { |f| system "rm #{f}" }
+end
+
+def toWord(result, filename, dir)
+  result = populate_template(result, :word)
+  result = from_xhtml(word_cleanup(to_xhtml(result)))
+  Html2Doc.process(result, filename: filename, stylesheet: @wordstylesheet,
+                   header_file: "header.html", dir: dir,
+                   asciimathdelims: [@openmathdelim, @closemathdelim],
+                   liststyles: { ul: @ulstyle, ol: @olstyle })
+end
+
+def word_cleanup(docxml)
+  word_preface(docxml)
+  word_annex_cleanup(docxml)
+  docxml
+end
+
+# force Annex h2 to be p.h2Annex, so it is not picked up by ToC
+def word_annex_cleanup(docxml)
+  docxml.xpath("//h2[ancestor::*[@class = 'Section3']]").each do |h2|
+    h2.name = "p"
+    h2["class"] = "h2Annex"
+  end
+end
+
+def word_preface(docxml)
+  word_cover(docxml) if @wordcoverpage
+  word_intro(docxml) if @wordintropage
+end
+
+def word_cover(docxml)
+  cover = File.read(@wordcoverpage, encoding: "UTF-8")
+  cover = populate_template(cover, :word)
+  coverxml = to_xhtml_fragment(cover)
+  docxml.at('//div[@class="WordSection1"]').children.first.previous =
+    coverxml.to_xml(encoding: "US-ASCII")
+end
+
+def word_intro(docxml)
+  intro = File.read(@wordintropage, encoding: "UTF-8").
+    sub(/WORDTOC/, make_WordToC(docxml))
+  intro = populate_template(intro, :word)
+  introxml = to_xhtml_fragment(intro)
+  docxml.at('//div[@class="WordSection2"]').children.first.previous =
+    introxml.to_xml(encoding: "US-ASCII")
+end
+
+def generate_header(filename, _dir)
+  return unless @header
+  template = Liquid::Template.parse(File.read(@header, encoding: "UTF-8"))
+  meta = get_metadata
+  meta[:filename] = filename
+  params = meta.map { |k, v| [k.to_s, v] }.to_h
+  File.open("header.html", "w") do |f|
+    f.write(template.render(params))
+  end
+  @files_to_delete << "header.html"
+end
+
+def word_toc_entry(toclevel, heading)
+  bookmark = 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
+
+WORD_TOC_PREFACE1 = <<~TOC.freeze
+      <span lang="EN-GB"><span
+        style='mso-element:field-begin'></span><span
+        style='mso-spacerun:yes'>&#xA0;</span>TOC
+        \\o &quot;1-2&quot; \\h \\z \\u <span
+        style='mso-element:field-separator'></span></span>
+TOC
+
+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)
+  toc = ""
+  docxml.xpath("//h1 | //h2[not(ancestor::*[@class = 'Section3'])]").
+    each do |h|
+    toc += word_toc_entry(h.name == "h1" ? 1 : 2, header_strip(h))
+  end
+  toc.sub(/(<p class="MsoToc1">)/,
+          %{\\1#{WORD_TOC_PREFACE1}}) +  WORD_TOC_SUFFIX1
+end

data/lib/isodoc/wordconvert/wordconvertmodule.rb

@@ -1,12 +1,21 @@
+def make_body2(body, docxml)
+  body.div **{ class: "WordSection2" } do |div2|
+    info docxml, div2
+    foreword docxml, div2
+    introduction docxml, div2
+    div2.p { |p| p << "&nbsp;" } # placeholder
+  end
+  section_break(body)
+end
 
-#require "html2doc"
-#require "liquid"
+def make_body3(body, docxml)
+  body.div **{ class: "WordSection3" } do |div3|
+    middle docxml, div3
+    footnotes div3
+    comments div3
+  end
+end
 
-#module IsoDoc
-#class WordConvert < Convert
-#module WordConvertModule
-#def self.included base 
-#base.class_eval do
 def insert_tab(out, n)
   out.span **attr_code(style: "mso-tab-count:#{n}") do |span|
     [1..n].each { span << "&#xA0; " }
@@ -32,7 +41,6 @@ def remove_bottom_border(td)
     gsub(/mso-border-bottom-alt:[^;]+;/, "mso-border-bottom-alt:0pt;")
 end
 
-#SW1 = IsoDoc::SW
 SW1 = "solid windowtext".freeze
 
 def new_fullcolspan_row(t, tfoot)
@@ -65,10 +73,8 @@ def section_break(body)
 end
 
 def page_break(out)
-  out.br **{
-    clear: "all",
-    style: "mso-special-character:line-break;page-break-before:always",
-  }
+  out.br **{ clear: "all",
+             style: "mso-special-character:line-break;page-break-before:always" }
 end
 
 WORD_DT_ATTRS = {class: @note ? "Note" : nil, align: "left",
@@ -131,121 +137,3 @@ def figure_aside_process(f, aside, key)
     a.parent = dd
   end
 end
-
-def postprocess(result, filename, dir)
-  generate_header(filename, dir)
-  result = from_xhtml(cleanup(to_xhtml(result)))
-  toWord(result, filename, dir)
-  @files_to_delete.each { |f| system "rm #{f}" }
-end
-
-def toWord(result, filename, dir)
-  result = populate_template(result, :word)
-  result = from_xhtml(word_cleanup(to_xhtml(result)))
-  Html2Doc.process(result, filename: filename, stylesheet: @wordstylesheet,
-                   header_file: "header.html", dir: dir,
-                   asciimathdelims: [@openmathdelim, @closemathdelim],
-                   liststyles: { ul: @ulstyle, ol: @olstyle })
-end
-
-def word_cleanup(docxml)
-  word_preface(docxml)
-  word_annex_cleanup(docxml)
-  docxml
-end
-
-# force Annex h2 to be p.h2Annex, so it is not picked up by ToC
-def word_annex_cleanup(docxml)
-  docxml.xpath("//h2[ancestor::*[@class = 'Section3']]").each do |h2|
-    h2.name = "p"
-    h2["class"] = "h2Annex"
-  end
-end
-
-def word_preface(docxml)
-  word_cover(docxml) if @wordcoverpage
-  word_intro(docxml) if @wordintropage
-end
-
-def word_cover(docxml)
-  cover = File.read(@wordcoverpage, encoding: "UTF-8")
-  cover = populate_template(cover, :word)
-  coverxml = to_xhtml_fragment(cover)
-  docxml.at('//div[@class="WordSection1"]').children.first.previous =
-    coverxml.to_xml(encoding: "US-ASCII")
-end
-
-def word_intro(docxml)
-  intro = File.read(@wordintropage, encoding: "UTF-8").
-                            sub(/WORDTOC/, make_WordToC(docxml))
-  intro = populate_template(intro, :word)
-  introxml = to_xhtml_fragment(intro)
-  docxml.at('//div[@class="WordSection2"]').children.first.previous =
-    introxml.to_xml(encoding: "US-ASCII")
-end
-
-def generate_header(filename, _dir)
-  return unless @header
-  template = Liquid::Template.parse(File.read(@header, encoding: "UTF-8"))
-  meta = get_metadata
-  meta[:filename] = filename
-  params = meta.map { |k, v| [k.to_s, v] }.to_h
-  File.open("header.html", "w") do |f|
-    f.write(template.render(params))
-  end
-  @files_to_delete << "header.html"
-end
-
-def word_toc_entry(toclevel, heading)
-  bookmark = 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
-
-#WORD_TOC_PREFACE = <<~TOC.freeze
-WORD_TOC_PREFACE1 = <<~TOC.freeze
-      <span lang="EN-GB"><span
-        style='mso-element:field-begin'></span><span
-        style='mso-spacerun:yes'>&#xA0;</span>TOC
-        \\o &quot;1-2&quot; \\h \\z \\u <span
-        style='mso-element:field-separator'></span></span>
-TOC
-
-#WORD_TOC_SUFFIX = <<~TOC.freeze
-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)
-  toc = ""
-  docxml.xpath("//h1 | //h2[not(ancestor::*[@class = 'Section3'])]").
-    each do |h|
-    toc += word_toc_entry(h.name == "h1" ? 1 : 2, header_strip(h))
-  end
-  toc.sub(/(<p class="MsoToc1">)/,
-          #%{\\1#{WORD_TOC_PREFACE}}) + WORD_TOC_SUFFIX
-          %{\\1#{WORD_TOC_PREFACE1}}) +  WORD_TOC_SUFFIX1
-end
-#end
-#end
-#end
-#end