isodoc 0.4.5 → 0.5.5

data/lib/isodoc/metadata.rb

@@ -2,15 +2,12 @@ require "htmlentities"
 
 module IsoDoc
   class Convert
-
     def init_metadata
-      @meta = {
-        tc: "XXXX",
-        sc: "XXXX",
-        wg: "XXXX",
-        editorialgroup: [],
-        secretariat: "XXXX",
-      }
+      @meta = { tc: "XXXX", sc: "XXXX", wg: "XXXX",
+                editorialgroup: [],
+                secretariat: "XXXX",
+                obsoletes: nil,
+                obsoletes_part: nil }
       %w{published accessed created activated obsoleted}.each do |w|
         @meta["#{w}date".to_sym] = "XXX"
       end
@@ -57,7 +54,7 @@ module IsoDoc
       wg_num = xml.at(ns("//editorialgroup/workgroup/@number"))
       wg_type = xml.at(ns("//editorialgroup/workgroup/@type"))&.text || "WG"
       if wg_num
-        wgid =  "#{wg_type} #{wg_num.text}"
+        wgid = "#{wg_type} #{wg_num.text}"
         set_metadata(:wg, wgid)
         set_metadata(:editorialgroup, get_metadata[:editorialgroup] << wgid)
       end
@@ -70,32 +67,37 @@ module IsoDoc
 
     def bibdate(isoxml, _out)
       isoxml.xpath(ns("//bibdata/date")).each do |d|
-        set_metadata("#{d["type"]}date".to_sym, d.text)
+        set_metadata("#{d['type']}date".to_sym, d.text)
       end
     end
 
     def agency(xml)
       agency = ""
-      pub = xml.xpath(ns("//bibdata/contributor"\
-                         "[xmlns:role/@type = 'publisher']/"\
-                         "organization/name")).each do |org|
+      xml.xpath(ns("//bibdata/contributor[xmlns:role/@type = 'publisher']/"\
+                   "organization/name")).each do |org|
         agency = org.text == "ISO" ? "ISO/#{agency}" : "#{agency}#{org.text}/"
       end
       set_metadata(:agency, agency.sub(%r{/$}, ""))
     end
 
-    def id(isoxml, _out)
+    def docnumber(isoxml)
       docnumber = isoxml.at(ns("//project-number"))
       partnumber = isoxml.at(ns("//project-number/@part"))
-      documentstatus = isoxml.at(ns("//status/stage"))
-      dn = docnumber.text
+      subpartnumber = isoxml.at(ns("//project-number/@subpart"))
+      dn = docnumber&.text || ""
       dn += "-#{partnumber.text}" if partnumber
+      dn += "-#{subpartnumber.text}" if subpartnumber
+      dn
+    end
+
+    def id(isoxml, _out)
+      dn = docnumber(isoxml)
+      documentstatus = isoxml.at(ns("//status/stage"))
       if documentstatus
         set_metadata(:stage, documentstatus.text)
         abbr = stage_abbreviation(documentstatus.text)
         set_metadata(:stageabbr, abbr)
-        documentstatus.text.to_i < 60 and
-          dn = abbr + " " + dn
+        (documentstatus.text.to_i < 60) && dn = abbr + " " + dn
       end
       set_metadata(:docnumber, dn)
     end
@@ -103,38 +105,42 @@ module IsoDoc
     def draftinfo(draft, revdate)
       draftinfo = ""
       if draft
-        draftinfo = " (draft #{draft.text}"
+        draftinfo = " (#{@draft_lbl} #{draft.text}"
         draftinfo += ", #{revdate.text}" if revdate
         draftinfo += ")"
       end
-      draftinfo
+      l10n(draftinfo)
     end
 
     def version(isoxml, _out)
-      yr = isoxml.at(ns("//copyright/from"))
-      set_metadata(:docyear, yr.text)
-      draft = isoxml.at(ns("//version/draft"))
-      set_metadata(:draft, draft.nil? ? nil : draft.text)
-      revdate = isoxml.at(ns("//version/revision-date"))
-      set_metadata(:revdate, revdate.nil? ? nil : revdate.text)
-      draftinfo = draftinfo(draft, revdate)
-      set_metadata(:draftinfo, draftinfo(draft, revdate))
-    end
-
+      set_metadata(:docyear, isoxml&.at(ns("//copyright/from"))&.text)
+      # draft = isoxml.at(ns("//version/draft"))
+      # set_metadata(:draft, draft.nil? ? nil : draft.text)
+      set_metadata(:draft, isoxml&.at(ns("//version/draft"))&.text)
+      # revdate = isoxml.at(ns("//version/revision-date"))
+      #set_metadata(:revdate, revdate.nil? ? nil : revdate.text)
+      set_metadata(:revdate, isoxml&.at(ns("//version/revision-date"))&.text)
+      #set_metadata(:draftinfo, draftinfo(draft, revdate))
+      set_metadata(:draftinfo,
+                   draftinfo(get_metadata[:draft], get_metadata[:revdate]))
+    end
+
+    # we don't leave this to i18n.rb, because we have both English and
+    # French titles in the same document
     def part_label(lang)
       case lang
       when "en" then "Part"
-      when "fr" then "Part"
+      when "fr" then "Partie"
       end
     end
 
-    def compose_title(main, intro, part, partnum, lang)
-      c = HTMLEntities.new
-      main = c.encode(main.text, :hexadecimal)
+    def compose_title(main, intro, part, partnum, subpartnum, lang)
+      main = main.nil? ? "" : @c.encode(main.text, :hexadecimal)
       intro &&
-        main = "#{c.encode(intro.text, :hexadecimal)}&nbsp;&mdash; #{main}"
+        main = "#{@c.encode(intro.text, :hexadecimal)}&nbsp;&mdash; #{main}"
       if part
-        suffix = c.encode(part.text, :hexadecimal)
+        suffix = @c.encode(part.text, :hexadecimal)
+        partnum = "#{partnum}&ndash;#{subpartnum}" if partnum && subpartnum
         suffix = "#{part_label(lang)}&nbsp;#{partnum}: " + suffix if partnum
         main = "#{main}&nbsp;&mdash; #{suffix}"
       end
@@ -146,7 +152,8 @@ module IsoDoc
       main = isoxml.at(ns("//title-main[@language='en']"))
       part = isoxml.at(ns("//title-part[@language='en']"))
       partnumber = isoxml.at(ns("//project-number/@part"))
-      main = compose_title(main, intro, part, partnumber, "en")
+      subpartnumber = isoxml.at(ns("//project-number/@subpart"))
+      main = compose_title(main, intro, part, partnumber, subpartnumber, "en")
       set_metadata(:doctitle, main)
     end
 
@@ -155,8 +162,17 @@ module IsoDoc
       main = isoxml.at(ns("//title-main[@language='fr']"))
       part = isoxml.at(ns("//title-part[@language='fr']"))
       partnumber = isoxml.at(ns("//project-number/@part"))
-      main = compose_title(main, intro, part, partnumber, "fr")
+      subpartnumber = isoxml.at(ns("//project-number/@subpart"))
+      main = compose_title(main, intro, part, partnumber, subpartnumber, "fr")
       set_metadata(:docsubtitle, main)
     end
+
+    def relations(isoxml, _out)
+      std = isoxml.at(ns("//bibdata/relation[@type = 'obsoletes']")) || return
+      locality = std.at(ns(".//locality"))
+      id = std.at(ns(".//docidentifier"))
+      set_metadata(:obsoletes, id.text)
+      set_metadata(:obsoletes_part, locality.text)
+    end
   end
 end

data/lib/isodoc/notes.rb

@@ -40,7 +40,7 @@ module IsoDoc
       end.join("\n")
     end
 
-    def make_generic_footnote_text(node, fnid, fn_ref)
+    def make_generic_footnote_text(node, fnid)
       noko do |xml|
         xml.aside **{ id: "ftn#{fnid}" } do |div|
           node.children.each { |n| parse(n, div) }
@@ -69,12 +69,12 @@ module IsoDoc
     def footnote_parse(node, out)
       return table_footnote_parse(node, out) if @in_table || @in_figure
       fn = node["reference"]
-      out.a **{"epub:type": "footnote", href: "#ftn#{fn}" } do |a|
+      out.a **{ "epub:type": "footnote", href: "#ftn#{fn}" } do |a|
         a.sup { |sup| sup << fn }
       end
-      return if @seen_footnote.include?(fn) 
+      return if @seen_footnote.include?(fn)
       @in_footnote = true
-      @footnotes << make_generic_footnote_text(node, fn, fn)
+      @footnotes << make_generic_footnote_text(node, fn)
       @in_footnote = false
       @seen_footnote << fn
     end
@@ -94,28 +94,28 @@ module IsoDoc
       @in_comment = false
     end
 
+    def comment_link_attrs(fn, node)
+      { style: "MsoCommentReference", target: fn,
+        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 **{ style: "MsoCommentReference", target: fn,
-                   class: "commentLink", from: node['from'],
-                   to: node['to']} do |s1|
-                     s1.span **{ lang: "EN-GB", style: "font-size:9.0pt"} do |s2|
-                       s2.a **{ style: "mso-comment-reference:SMC_#{fn};"\
-                                "mso-comment-date:#{node['date']}"}
-                       s2.span **{ style: "mso-special-character:comment",
-                                   target: fn } # do |s|
-                       #s << "&nbsp;"
-                       #end
-                     end
-                   end
+      out.span(**comment_link_attrs(fn, node)) do |s1|
+        s1.span **{ lang: "EN-GB", style: "font-size:9.0pt" } do |s2|
+          s2.a **{ style: "mso-comment-reference:SMC_#{fn};"\
+                   "mso-comment-date:#{node['date']}" }
+          s2.span **{ style: "mso-special-character:comment",
+                      target: fn } # do |s|
+        end
+      end
     end
 
     def make_comment_target(out)
       out.span **{ style: "MsoCommentReference" } do |s1|
-        s1.span **{ lang: "EN-GB", style: "font-size:9.0pt"} do |s2|
-          s2.span **{ style: "mso-special-character:comment" } # do |s|
-          # s << "&nbsp;"
-          # end
+        s1.span **{ lang: "EN-GB", style: "font-size:9.0pt" } do |s2|
+          s2.span **{ style: "mso-special-character:comment" }
         end
       end
     end
@@ -123,7 +123,7 @@ module IsoDoc
     def make_comment_text(node, fn)
       noko do |xml|
         xml.div **{ style: "mso-element:comment", id: fn } do |div|
-          div.span **{ style: %{mso-comment-author:"#{node["reviewer"]}"} }
+          div.span **{ style: %{mso-comment-author:"#{node['reviewer']}"} }
           make_comment_target(div)
           node.children.each { |n| parse(n, div) }
         end
@@ -138,7 +138,7 @@ module IsoDoc
 
     COMMENT_IN_COMMENT_LIST =
       '//div[@style="mso-element:comment-list"]//'\
-      'span[@style="MsoCommentReference"]'
+      'span[@style="MsoCommentReference"]'.freeze
 
     def embed_comment_in_comment_list(docxml)
       docxml.xpath(COMMENT_IN_COMMENT_LIST).each do |x|
@@ -148,7 +148,7 @@ module IsoDoc
       docxml
     end
 
-    def move_comment_link_to_from1(x, fromlink, docxml)
+    def move_comment_link_to_from1(x, fromlink)
       x.remove
       link = x.at(".//a")
       fromlink.replace(x)
@@ -156,10 +156,10 @@ module IsoDoc
     end
 
     def comment_attributes(docxml, x)
-      fromlink = docxml.at("//*[@id='#{x["from"]}']")
+      fromlink = docxml.at("//*[@id='#{x['from']}']")
       return(nil) if fromlink.nil?
-      tolink = docxml.at("//*[@id='#{x["to"]}']") || fromlink
-      target = docxml.at("//*[@id='#{x["target"]}']")
+      tolink = docxml.at("//*[@id='#{x['to']}']") || fromlink
+      target = docxml.at("//*[@id='#{x['target']}']")
       { from: fromlink, to: tolink, target: target }
     end
 
@@ -172,7 +172,7 @@ module IsoDoc
       from["style"] != "mso-special-character:comment"
     end
 
-    def insert_comment_cont(from, to, target, docxml)
+    def insert_comment_cont(from, to, target)
       # includes_to = from.at(".//*[@id='#{to}']")
       while !from.nil? && from["id"] != to
         following = from.xpath("./following::*")
@@ -187,8 +187,8 @@ module IsoDoc
     def move_comment_link_to_from(docxml)
       docxml.xpath('//span[@style="MsoCommentReference"][@from]').each do |x|
         attrs = comment_attributes(docxml, x) || next
-        move_comment_link_to_from1(x, attrs[:from], docxml)
-        insert_comment_cont(attrs[:from], x["to"], x["target"], docxml)
+        move_comment_link_to_from1(x, attrs[:from])
+        insert_comment_cont(attrs[:from], x["to"], x["target"])
       end
     end
 
@@ -199,11 +199,11 @@ module IsoDoc
         comments << { text: c.remove.to_s, id: c["id"] }
       end
       comments.sort! { |a, b| link_order[a[:id]] <=> link_order[b[:id]] }
-      comments
+      # comments
     end
 
     COMMENT_TARGET_XREFS =
-      "//span[@style='mso-special-character:comment']/@target"
+      "//span[@style='mso-special-character:comment']/@target".freeze
 
     def reorder_comments_by_comment_link(docxml)
       link_order = {}
@@ -211,7 +211,7 @@ module IsoDoc
         link_order[target.value] = i
       end
       comments = get_comments_from_text(docxml, link_order)
-      list = docxml.at("//*[@style='mso-element:comment-list']") or return
+      list = docxml.at("//*[@style='mso-element:comment-list']") || return
       list.children = comments.map { |c| c[:text] }.join("\n")
     end
   end

data/lib/isodoc/postprocessing.rb

@@ -6,7 +6,6 @@ require "pp"
 
 module IsoDoc
   class Convert
-
     def postprocess(result, filename, dir)
       generate_header(filename, dir)
       result = from_xhtml(cleanup(to_xhtml(result)))
@@ -15,49 +14,70 @@ module IsoDoc
     end
 
     def toWord(result, filename, dir)
-      result = from_xhtml(wordCleanup(to_xhtml(result)))
+      result = from_xhtml(word_cleanup(to_xhtml(result)))
       result = populate_template(result, :word)
-      Html2Doc.process(result, filename, @wordstylesheet, "header.html", 
-                       dir, ['`', '`'])
+      Html2Doc.process(result, filename: filename, stylesheet: @wordstylesheet,
+                       header_file: "header.html", dir: dir,
+                       asciimathdelims: [@openmathdelim, @closemathdelim],
+                       liststyles: { ul: @ulstyle, ol: @olstyle })
     end
 
-    def wordCleanup(docxml)
-      wordPreface(docxml)
-      wordAnnexCleanup(docxml)
+    def word_cleanup(docxml)
+      word_preface(docxml)
+      word_annex_cleanup(docxml)
+      word_dl_cleanup(docxml)
       docxml
     end
 
+    def word_dl_cleanup1(dtd, tr)
+      dtd[:dt].name = "td"
+      dtd[:dt]["valign"] = "top"
+      dtd[:dt].parent = tr
+      dtd[:dd].name = "td"
+      dtd[:dd]["valign"] = "top"
+      dtd[:dd].parent = tr
+    end
+
+    def word_dl_cleanup(docxml)
+      docxml.xpath("//dl").each do |dl|
+        dl.name = "table"
+        extract_symbols_list(dl).each do |dtd|
+          tr = dl.add_child("<tr></tr>").first
+          word_dl_cleanup1(dtd, tr)
+        end
+      end
+    end
+
     # force Annex h2 to be p.h2Annex, so it is not picked up by ToC
-    def wordAnnexCleanup(docxml)
-      d = docxml.xpath("//h2[ancestor::*[@class = 'Section3']]").each do |h2|
+    def word_annex_cleanup(docxml)
+      docxml.xpath("//h2[ancestor::*[@class = 'Section3']]").each do |h2|
         h2.name = "p"
         h2["class"] = "h2Annex"
       end
     end
 
-    def wordPreface(docxml)
+    def word_preface(docxml)
       cover = to_xhtml_fragment(File.read(@wordcoverpage, encoding: "UTF-8"))
-      d = docxml.at('//div[@class="WordSection1"]')
-      d.children.first.add_previous_sibling cover.to_xml(encoding: 'US-ASCII')
-      intro = to_xhtml_fragment(
-        File.read(@wordintropage, encoding: "UTF-8").
-        sub(/WORDTOC/, makeWordToC(docxml)))
-      d = docxml.at('//div[@class="WordSection2"]')
-      d.children.first.add_previous_sibling intro.to_xml(encoding: 'US-ASCII')
+      docxml.at('//div[@class="WordSection1"]').children.first.previous =
+        cover.to_xml(encoding: "US-ASCII")
+      intro = to_xhtml_fragment(File.read(@wordintropage, encoding: "UTF-8").
+                                sub(/WORDTOC/, make_WordToC(docxml)))
+      docxml.at('//div[@class="WordSection2"]').children.first.previous =
+        intro.to_xml(encoding: "US-ASCII")
     end
 
     def populate_template(docxml, _format)
       meta = get_metadata
-      docxml.
-        gsub(/\[TERMREF\]\s*/, "[SOURCE: ").
-        gsub(/\s*\[\/TERMREF\]\s*/, "]").
-        gsub(/\s*\[ISOSECTION\]/, ", ").
-        gsub(/\s*\[MODIFICATION\]/, ", modified &mdash; ")
+      docxml = docxml.
+        gsub(/\[TERMREF\]\s*/, l10n("[#{@source_lbl}: ")).
+        gsub(/\s*\[\/TERMREF\]\s*/, l10n("]")).
+        gsub(/\s*\[ISOSECTION\]/, l10n(", ")).
+        gsub(/\s*\[MODIFICATION\]/, l10n(", #{@modified_lbl} &mdash; "))
       template = Liquid::Template.parse(docxml)
       template.render(meta.map { |k, v| [k.to_s, v] }.to_h)
     end
 
-    def generate_header(filename, dir)
+    def generate_header(filename, _dir)
       template = Liquid::Template.parse(File.read(@header, encoding: "UTF-8"))
       meta = get_metadata
       meta[:filename] = filename
@@ -76,9 +96,10 @@ module IsoDoc
 
     # isodoc.css overrides any CSS injected by Html2Doc, which
     # is inserted before this CSS.
-    def define_head(html, filename, dir)
+    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)
@@ -92,50 +113,49 @@ module IsoDoc
       div.parent.add_child titlepage
     end
 
-    def wordTocEntry(toclevel, heading)
+    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">
+        <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><span lang="EN-GB" class="MsoTocTextSpan">
         <span style='mso-element:field-begin'></span></span>
-        <span lang="EN-GB" 
+        <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 
+          <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
+    WORD_TOC_PREFACE = <<~TOC.freeze
       <span lang="EN-GB"><span
-        style='mso-element:field-begin'></span><span 
+        style='mso-element:field-begin'></span><span
         style='mso-spacerun:yes'>&#xA0;</span>TOC
-        \\o &quot;1-2&quot; \\h \\z \\u <span 
+        \\o &quot;1-2&quot; \\h \\z \\u <span
         style='mso-element:field-separator'></span></span>
     TOC
 
-    WORD_TOC_SUFFIX = <<~TOC
-      <p class="MsoToc1"><span lang="EN-GB"><span 
-        style='mso-element:field-end'></span></span><span 
+    WORD_TOC_SUFFIX = <<~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 header_strip(h)
       h = h.to_s.gsub(%r{<br/>}, " ").
         sub(/<h[12][^>]*>/, "").sub(%r{</h[12]>}, "")
-      h1 = to_xhtml_fragment(h)    
-      #h1.xpath(".//*[@style = 'MsoCommentReference']").each do |x|
+      h1 = to_xhtml_fragment(h)
       h1.xpath(".//*").each do |x|
-        if x.name == "span" && x['style'] == "MsoCommentReference"
+        if x.name == "span" && x["style"] == "MsoCommentReference"
           x.children.remove
           x.content = ""
         end
@@ -143,15 +163,14 @@ module IsoDoc
       from_xhtml(h1)
     end
 
-    def makeWordToC(docxml)
+    def make_WordToC(docxml)
       toc = ""
       docxml.xpath("//h1 | //h2[not(ancestor::*[@class = 'Section3'])]").
         each do |h|
-        toc += wordTocEntry(h.name == "h1" ? 1 : 2, header_strip(h))
+        toc += word_toc_entry(h.name == "h1" ? 1 : 2, header_strip(h))
       end
-      toc.sub(/(<p class="MsoToc1">)/, 
+      toc.sub(/(<p class="MsoToc1">)/,
               %{\\1#{WORD_TOC_PREFACE}}) + WORD_TOC_SUFFIX
     end
-
   end
 end