isodoc 0.5.8 → 0.5.9

data/lib/isodoc/inline.rb

@@ -33,13 +33,13 @@ module IsoDoc
     end
 
     def get_linkend(node)
-      linkend = anchor_linkend(node, node["target"] || node["citeas"])
-      linkend += eref_localities(node.xpath(ns("./locality")))
+      link = anchor_linkend(node, docid_l10n(node["target"] || node["citeas"]))
+      link += eref_localities(node.xpath(ns("./locality")))
       text = node.children.select { |c| c.text? && !c.text.empty? }
-      linkend = text.join(" ") unless text.nil? || text.empty?
+      link = text.join(" ") unless text.nil? || text.empty?
       # so not <origin bibitemid="ISO7301" citeas="ISO 7301">
       # <locality type="section"><reference>3.1</reference></locality></origin>
-      linkend
+      link
     end
 
     def xref_parse(node, out)
@@ -50,8 +50,7 @@ module IsoDoc
     def eref_localities(refs)
       ret = ""
       refs.each do |r|
-        ret += if r["type"] == "whole"
-                 l10n(", #{@whole_of_text}")
+        ret += if r["type"] == "whole" then l10n(", #{@whole_of_text}")
                else
                  eref_localities1(r["type"], r.at(ns("./referenceFrom")),
                                   r.at(ns("./referenceTo")), @lang)

data/lib/isodoc/iso2wordhtml.rb

@@ -82,7 +82,9 @@ module IsoDoc
     def info(isoxml, out)
       title isoxml, out
       subtitle isoxml, out
-      id isoxml, out
+      docstatus isoxml, out
+      docid isoxml, out
+      doctype isoxml, out
       author isoxml, out
       bibdate isoxml, out
       relations isoxml, out
@@ -97,10 +99,10 @@ module IsoDoc
 
     def middle(isoxml, out)
       middle_title(out)
-      scope isoxml, out
-      norm_ref isoxml, out
-      terms_defs isoxml, out
-      symbols_abbrevs isoxml, out
+      i = scope isoxml, out, 0
+      i = norm_ref isoxml, out, i
+      i = terms_defs isoxml, out, i
+      i = symbols_abbrevs isoxml, out, i
       clause isoxml, out
       annex isoxml, out
       bibliography isoxml, out
@@ -142,7 +144,8 @@ module IsoDoc
         when "callout" then callout_parse(node, out)
         when "stem" then stem_parse(node, out)
         when "clause" then clause_parse(node, out)
-        when "subsection" 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)
         when "origin" then eref_parse(node, out)

data/lib/isodoc/lists.rb

@@ -22,7 +22,6 @@ module IsoDoc
     # We don't really want users to specify type of ordered list;
     # we will use a fixed hierarchy as practiced by ISO (though not
     # fully spelled out): a) 1) i) A) I) 
-    #
    
     def ol_depth(node)
       depth = node.ancestors("ul, ol").size + 1
@@ -58,17 +57,20 @@ module IsoDoc
       end
     end
 
+    def dt_dd?(n)
+      %w{dt dd}.include? n.name
+    end
+
     def dl_parse(node, out)
       out.dl do |v|
-        node.elements.each_slice(2) do |dt, dd|
-          v.dt do |term|
-            dt_parse(dt, term)
-          end
+        node.elements.select { |n| dt_dd? n }.each_slice(2) do |dt, dd|
+          v.dt { |term| dt_parse(dt, term) }
           v.dd do |listitem|
             dd.children.each { |n| parse(n, listitem) }
           end
         end
       end
+      node.elements.reject { |n| dt_dd? n }.each { |n| parse(n, out) }
     end
   end
 end

data/lib/isodoc/metadata.rb

@@ -2,15 +2,16 @@ require "htmlentities"
 
 module IsoDoc
   class Convert
+    DATETYPES = %w{published accessed created implemented obsoleted confirmed
+    updated issued}.freeze
+
     def init_metadata
       @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
+      DATETYPES.each { |w| @meta["#{w}date".to_sym] = "XXX" }
     end
 
     def get_metadata
@@ -79,6 +80,13 @@ module IsoDoc
       end
     end
 
+    def doctype(isoxml, _out)
+      b = isoxml.at(ns("//bibdata")) || return
+      return unless b["type"]
+      t = b["type"].split(/-/).map{ |w| w.capitalize }.join(" ")
+      set_metadata(:doctype, t)
+    end
+
     def iso?(org)
       name = org&.at(ns("./name"))&.text
       abbrev = org&.at(ns("./abbreviation"))&.text
@@ -108,14 +116,23 @@ module IsoDoc
       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)
+    def docstatus(isoxml, _out)
+      docstatus = isoxml.at(ns("//status/stage"))
+      if docstatus
+        set_metadata(:stage, docstatus.text)
+        abbr = stage_abbrev(docstatus.text, isoxml.at(ns("//status/iteration")),
+                            isoxml.at(ns("//version/draft")))
         set_metadata(:stageabbr, abbr)
-        (documentstatus.text.to_i < 60) && dn = abbr + " " + dn
+      end
+    end
+
+    def docid(isoxml, _out)
+      dn = docnumber(isoxml)
+      docstatus = get_metadata[:stage]
+      if docstatus
+        abbr = get_metadata[:stageabbr]
+        docstatus = get_metadata[:stage]
+        (docstatus.to_i < 60) && dn = abbr + " " + dn
       end
       set_metadata(:docnumber, dn)
     end

data/lib/isodoc/references.rb

@@ -1,6 +1,7 @@
 module IsoDoc
   class Convert
     def docid_l10n(x)
+      return x if x.nil?
       x.gsub(/All Parts/, @all_parts_lbl)
     end
 
@@ -106,19 +107,24 @@ module IsoDoc
       div.p pref
     end
 
-    def norm_ref(isoxml, out)
-      q = "./*/references[title = 'Normative References']"
-      f = isoxml.at(ns(q)) || return
+    def norm_ref(isoxml, out, num)
+      q = "//bibliography/references[title = 'Normative References']"
+      f = isoxml.at(ns(q)) or return num
       out.div do |div|
-        clause_name("2.", @normref_lbl, div, nil)
+        num = num + 1
+        clause_name("#{num}.", @normref_lbl, div, nil)
         norm_ref_preface(f, div)
         biblio_list(f, div, false)
       end
+      num
     end
 
+    BIBLIOGRAPHY_XPATH = "//bibliography/clause[title = 'Bibliography'] | "\
+      "//bibliography/references[title = 'Bibliography']".freeze
+
+
     def bibliography(isoxml, out)
-      q = "//clause[title = 'Bibliography'][descendant::references] | //references[title = 'Bibliography']"
-      f = isoxml.at(ns(q)) || return
+      f = isoxml.at(ns(BIBLIOGRAPHY_XPATH)) || return
       page_break(out)
       out.div do |div|
         div.h1 @bibliography_lbl, **{ class: "Section3" }

data/lib/isodoc/section.rb

@@ -83,14 +83,16 @@ module IsoDoc
       end
     end
 
-    def scope(isoxml, out)
-      f = isoxml.at(ns("//clause[title = 'Scope']")) || return
+    def scope(isoxml, out, num)
+      f = isoxml.at(ns("//clause[title = 'Scope']")) or return num
       out.div **attr_code(id: f["id"]) do |div|
-        clause_name("1.", @scope_lbl, div, nil)
+        num = num + 1
+        clause_name("#{num}.", @scope_lbl, div, nil)
         f.elements.each do |e|
           parse(e, div) unless e.name == "title"
         end
       end
+      num
     end
 
     def external_terms_boilerplate(sources)
@@ -111,7 +113,7 @@ module IsoDoc
     end
 
     def term_defs_boilerplate_cont(src, term)
-      sources = sentence_join(src.map { |s| s["citeas"] })
+      sources = sentence_join(src.map { |s| @anchors[s["target"]][:xref] })
       if src.empty?
         @internal_terms_boilerplate
       elsif term.nil?
@@ -130,16 +132,18 @@ module IsoDoc
     TERM_CLAUSE = "//sections/terms | "\
       "//sections/clause[descendant::terms]".freeze
 
-    def terms_defs(isoxml, out)
-      f = isoxml.at(ns(TERM_CLAUSE)) || return
+    def terms_defs(isoxml, out, num)
+      f = isoxml.at(ns(TERM_CLAUSE)) or return num
       out.div **attr_code(id: f["id"]) do |div|
-        clause_name("3.", terms_defs_title(f), div, nil)
+        num = num + 1
+        clause_name("#{num}.", terms_defs_title(f), div, nil)
         term_defs_boilerplate(div, isoxml.xpath(ns(".//termdocsource")),
                               f.at(ns(".//term")))
         f.elements.each do |e|
           parse(e, div) unless %w{title source}.include? e.name
         end
       end
+      num
     end
 
     # subclause
@@ -147,14 +151,16 @@ module IsoDoc
       clause_parse(isoxml, out)
     end
 
-    def symbols_abbrevs(isoxml, out)
-      f = isoxml.at(ns("//sections/symbols-abbrevs")) || return
+    def symbols_abbrevs(isoxml, out, num)
+      f = isoxml.at(ns("//sections/symbols-abbrevs")) or return num
       out.div **attr_code(id: f["id"], class: "Symbols") do |div|
-        clause_name("4.", @symbols_lbl, div, nil)
+        num = num + 1
+        clause_name("#{num}.", @symbols_lbl, div, nil)
         f.elements.each do |e|
           parse(e, div) unless e.name == "title"
         end
       end
+      num
     end
 
     # subclause
@@ -166,7 +172,7 @@ module IsoDoc
 
     def introduction(isoxml, out)
       f = isoxml.at(ns("//introduction")) || return
-      num = f.at(ns(".//subsection")) ? "0." : nil
+      num = f.at(ns(".//clause")) ? "0." : nil
       title_attr = { class: "IntroTitle" }
       page_break(out)
       out.div **{ class: "Section3", id: f["id"] } do |div|

data/lib/isodoc/table.rb

@@ -3,10 +3,8 @@ module IsoDoc
     def table_title_parse(node, out)
       name = node.at(ns("./name"))
       out.p **{ class: "TableTitle", align: "center" } do |p|
-        p.b do |b|
-          b << l10n("#{@table_lbl} #{get_anchors[node['id']][:label]}")
-          b << l10n("&nbsp;&mdash; #{name.text}") if name
-        end
+        p << l10n("#{@table_lbl} #{get_anchors[node['id']][:label]}")
+        p << l10n("&nbsp;&mdash; #{name.text}") if name
       end
     end
 

data/lib/isodoc/terms.rb

@@ -11,20 +11,20 @@ module IsoDoc
     end
 
     def deprecated_term_parse(node, out)
-      out.p **{ class: "DeprecatedTerms" } do |p|
+      out.p **{ class: "DeprecatedTerms", style:"text-align:left;" } do |p|
         p << l10n("#{@deprecated_lbl}: ")
         node.children.each { |c| parse(c, p) }
       end
     end
 
     def admitted_term_parse(node, out)
-      out.p **{ class: "AltTerms" } do |p|
+      out.p **{ class: "AltTerms", style:"text-align:left;" } do |p|
         node.children.each { |c| parse(c, p) }
       end
     end
 
     def term_parse(node, out)
-      out.p **{ class: "Terms" } do |p|
+      out.p **{ class: "Terms", style:"text-align:left;" } do |p|
         node.children.each { |c| parse(c, p) }
       end
     end

data/lib/isodoc/utils.rb

@@ -3,8 +3,8 @@ module IsoDoc
     def ns(xpath)
       xpath.gsub(%r{/([a-zA-z])}, "/xmlns:\\1").
         gsub(%r{::([a-zA-z])}, "::xmlns:\\1").
-        gsub(%r{\[([a-zA-z]+ ?=)}, "[xmlns:\\1").
-        gsub(%r{\[([a-zA-z]+\])}, "[xmlns:\\1")
+        gsub(%r{\[([a-zA-z][a-z0-9A-Z@/]* ?=)}, "[xmlns:\\1").
+        gsub(%r{\[([a-zA-z][a-z0-9A-Z@/]*\])}, "[xmlns:\\1")
     end
 
     def insert_tab(out, n)
@@ -23,8 +23,11 @@ module IsoDoc
       "95": "(Withdrawal)",
     }.freeze
 
-    def stage_abbreviation(stage)
-      STAGE_ABBRS[stage.to_sym] || "??"
+    def stage_abbrev(stage, iter, draft)
+      stage = STAGE_ABBRS[stage.to_sym] || "??"
+      stage += iter.text if iter
+      stage = "Pre" + stage if draft&.text =~ /^0\./
+      stage
     end
 
     NOKOHEAD = <<~HERE.freeze
@@ -73,11 +76,10 @@ module IsoDoc
     end
 
     CLAUSE_ANCESTOR =
-      ".//ancestor::*[local-name() = 'subsection' or "\
-      "local-name() = 'foreword' or "\
+      ".//ancestor::*[local-name() = 'annex' or "\
+      "local-name() = 'appendix' or local-name() = 'foreword' or "\
       "local-name() = 'introduction' or local-name() = 'terms' or "\
-      "local-name() = 'clause' or local-name() = 'references' or "\
-      "local-name() = 'annex']/@id".freeze
+      "local-name() = 'clause' or local-name() = 'references']/@id".freeze
 
     def get_clause_id(node)
       clause = node.xpath(CLAUSE_ANCESTOR)
@@ -85,13 +87,12 @@ module IsoDoc
     end
 
     NOTE_CONTAINER_ANCESTOR =
-      ".//ancestor::*[local-name() = 'subsection' or "\
-      "local-name() = 'foreword' or "\
+      ".//ancestor::*[local-name() = 'annex' or "\
+      "local-name() = 'foreword' or local-name() = 'appendix' or "\
       "local-name() = 'introduction' or local-name() = 'terms' or "\
       "local-name() = 'clause' or local-name() = 'references' or "\
-      "local-name() = 'annex' or local-name() = 'formula' or "\
-      "local-name() = 'table' or local-name() = 'example' or "\
-      "local-name() = 'figure']/@id".freeze
+      "local-name() = 'figure' or local-name() = 'formula' or "\
+      "local-name() = 'table' or local-name() = 'example']/@id".freeze
 
     def get_note_container_id(node)
       container = node.xpath(NOTE_CONTAINER_ANCESTOR)
@@ -132,7 +133,7 @@ module IsoDoc
     end
 
     def populate_template(docxml, _format)
-      meta = get_metadata
+      meta = get_metadata.merge(@labels)
       docxml = docxml.
         gsub(/\[TERMREF\]\s*/, l10n("[#{@source_lbl}: ")).
         gsub(/\s*\[\/TERMREF\]\s*/, l10n("]")).

data/lib/isodoc/version.rb

@@ -1,3 +1,3 @@
 module IsoDoc
-  VERSION = "0.5.8".freeze
+  VERSION = "0.5.9".freeze
 end

data/lib/isodoc/wordconvert/comments.rb

@@ -36,7 +36,7 @@ def make_comment_link(out, fn, node)
   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']}" }
+               "mso-comment-date:#{node['date'].gsub(/[:-]+/, '')}" }
       s2.span **{ style: "mso-special-character:comment",
                   target: fn } # do |s|
     end

data/lib/isodoc/wordconvert/wordconvertmodule.rb

@@ -71,20 +71,22 @@ def page_break(out)
   }
 end
 
+WORD_DT_ATTRS = {class: @note ? "Note" : nil, align: "left",
+                 style: "margin-left:0pt;text-align:left;"}.freeze
+
 def dt_parse(dt, term)
-  if dt.elements.empty?
-    term.p **attr_code(class: note? ? "Note" : nil,
-                       style: "text-align: left;") do |p|
+  term.p **attr_code(WORD_DT_ATTRS) do |p|
+    if dt.elements.empty?
       p << dt.text
+    else
+      dt.children.each { |n| parse(n, p) }
     end
-  else
-    dt.children.each { |n| parse(n, term) }
   end
 end
 
 def dl_parse(node, out)
   out.table **{ class: "dl" } do |v|
-    node.elements.each_slice(2) do |dt, dd|
+    node.elements.select { |n| dt_dd? n }.each_slice(2) do |dt, dd|
       v.tr do |tr|
         tr.td **{ valign: "top", align: "left" } do |term|
           dt_parse(dt, term)
@@ -94,20 +96,52 @@ def dl_parse(node, out)
         end
       end
     end
+    dl_parse_notes(node, v)
   end
 end
 
+def dl_parse_notes(node, v)
+  return if node.elements.reject { |n| dt_dd? n }.empty?
+  v.tr do |tr|
+    tr.td **{ rowspan: 2 } do |td|
+      node.elements.reject { |n| dt_dd? n }.each { |n| parse(n, td) }
+    end
+  end
+end
 
+def figure_get_or_make_dl(t)
+  dl = t.at(".//table[@class = 'dl']")
+  if dl.nil?
+    t.add_child("<p><b>#{@key_lbl}</b></p><table class='dl'></table>")
+    dl = t.at(".//table[@class = 'dl']")
+  end
+  dl
+end
+
+def figure_aside_process(f, aside, key)
+  # get rid of footnote link, it is in diagram
+  f&.at("./a[@class='TableFootnoteRef']")&.remove
+  fnref = f.at(".//a[@class='TableFootnoteRef']")
+  tr = key.add_child("<tr></tr>").first
+  dt = tr.add_child("<td valign='top' align='left'></td>").first
+  dd = tr.add_child("<td valign='top'></td>").first
+  fnref.parent = dt
+  aside.xpath(".//p").each do |a|
+    a.delete("class")
+    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 = from_xhtml(word_cleanup(to_xhtml(result)))
   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],
@@ -134,16 +168,20 @@ def word_preface(docxml)
 end
 
 def word_cover(docxml)
-  cover = to_xhtml_fragment(File.read(@wordcoverpage, encoding: "UTF-8"))
+  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 =
-    cover.to_xml(encoding: "US-ASCII")
+    coverxml.to_xml(encoding: "US-ASCII")
 end
 
 def word_intro(docxml)
-  intro = to_xhtml_fragment(File.read(@wordintropage, encoding: "UTF-8").
-                            sub(/WORDTOC/, make_WordToC(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 =
-    intro.to_xml(encoding: "US-ASCII")
+    introxml.to_xml(encoding: "US-ASCII")
 end
 
 def generate_header(filename, _dir)
@@ -155,6 +193,7 @@ def generate_header(filename, _dir)
   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)