metanorma-iso 2.1.1 → 2.1.4

data/lib/isodoc/iso/word_dis_convert.rb

@@ -1,16 +1,16 @@
+require_relative "word_dis_cleanup"
+
 module IsoDoc
   module Iso
     class WordDISConvert < WordConvert
       def default_file_locations(_options)
-        {
-          wordstylesheet: html_doc_path("wordstyle-dis.scss"),
+        { wordstylesheet: html_doc_path("wordstyle-dis.scss"),
           standardstylesheet: html_doc_path("isodoc-dis.scss"),
           header: html_doc_path("header-dis.html"),
           wordcoverpage: html_doc_path("word_iso_titlepage-dis.html"),
           wordintropage: html_doc_path("word_iso_intro-dis.html"),
           ulstyle: "l3",
-          olstyle: "l2",
-        }
+          olstyle: "l2" }
       end
 
       def initialize(options)
@@ -19,56 +19,20 @@ module IsoDoc
         super
       end
 
-      def init_dis; end
+      def init_dis(options); end
 
-      def style_cleanup(docxml)
+      def convert1(docxml, filename, dir)
+        update_coverpage(docxml)
         super
-        dis_styles(docxml)
       end
 
-      STYLESMAP = {
-        AltTerms: "AdmittedTerm",
-        TableFootnote: "Tablefootnote",
-        formula: "Formula",
-        note: "Note",
-        example: "Example",
-        admonition: "Admonition",
-        admonitiontitle: "AdmonitionTitle",
-        sourcetitle: "SourceTitle",
-        tabletitle: "TableTitle",
-        titlepagesbhead: "TablePageSubhead",
-        NormRef: "RefNorm",
-        Biblio: "BiblioEntry",
-        MsoNormal: "MsoBodyText",
-        FigureTitle: "Figuretitle",
-        zzwarning: "zzWarning",
-        zzwarninghdr: "zzWarningHdr",
-        quoteattribution: "QuoteAttribution",
-      }.freeze
-
-      def dis_styles(docxml)
-        STYLESMAP.each do |k, v|
-          docxml.xpath("//*[@class = '#{k}']").each { |s| s["class"] = v }
-        end
-        docxml.xpath("//h1[@class = 'ForewordTitle' or @class = 'IntroTitle']")
-          .each { |h| h.name = "p" }
-        dis_styles1(docxml)
-        docxml.xpath("//p[not(@class)]").each { |p| p["class"] = "MsoBodyText" }
-      end
-
-      def dis_styles1(docxml)
-        code_style(docxml)
-        figure_style(docxml)
-        example_style(docxml)
-      end
-
-      def example_style(docxml)
-        docxml.xpath("//div[@class = 'Example']").each do |d|
-          d.xpath("./p").each_with_index do |p, i|
-            next if p["class"] && p["class"] != "Example"
-
-            p["class"] = (i.zero? ? "Example" : "Examplecontinued")
-          end
+      def update_coverpage(docxml)
+        stage = docxml.at(ns("//bibdata/status/stage"))&.text
+        substage = docxml.at(ns("//bibdata/status/substage"))&.text
+        if /^9/.match?(stage) || (stage == "60" && substage == "60")
+          @wordcoverpage = html_doc_path("word_iso_titlepage.html")
+        elsif stage == "60" && substage == "00"
+          @wordcoverpage = html_doc_path("word_iso_titlepage-prf.html")
         end
       end
 
@@ -80,13 +44,6 @@ module IsoDoc
         { class: "Tabletitle", style: "text-align:center;" }
       end
 
-      def word_annex_cleanup1(docxml, lvl)
-        docxml.xpath("//h#{lvl}[ancestor::*[@class = 'Section3']]").each do |h2|
-          h2.name = "p"
-          h2["class"] = "a#{lvl}"
-        end
-      end
-
       def span_parse(node, out)
         out.span **{ class: node["class"] } do |x|
           node.children.each { |n| parse(n, x) }
@@ -98,7 +55,7 @@ module IsoDoc
           <span lang="EN-GB"><span
           style='mso-element:field-begin'></span><span
           style='mso-spacerun:yes'>&#xA0;</span>TOC \\o "2-#{level}" \\h \\z \\t
-          "Heading 1;1;ANNEX;1;Biblio Title;1;Foreword Title;1;Intro Title;1;ANNEXN;1;ANNEXZ;1;na2;1;na3;1;na4;1;na5;1;na6;1;Title;1;Base_Heading;1;Box-title;1;Front Head;1;Index Head;1;AMEND Terms Heading;1;AMEND Heading 1 Unnumbered;1"
+          "Heading 1,1,ANNEX,1,Biblio Title,1,Foreword Title,1,Intro Title,1,ANNEXN,1,ANNEXZ,1,na2,1,na3,1,na4,1,na5,1,na6,1,Title,1,Base_Heading,1,Box-title,1,Front Head,1,Index Head,1,AMEND Terms Heading,1,AMEND Heading 1 Unnumbered,1"
            <span style='mso-element:field-separator'></span></span>
         TOC
       end
@@ -109,60 +66,10 @@ module IsoDoc
         ret
       end
 
-      FIGURE_NESTED_STYLES =
-        { Note: "Figurenote", example: "Figureexample" }.freeze
-
-      def figure_style(docxml)
-        docxml.xpath("//div[@class = 'figure']").each do |f|
-          FIGURE_NESTED_STYLES.each do |k, v|
-            f.xpath(".//*[@class = '#{k}']").each { |n| n["class"] = v }
-          end
-          f.xpath("./img").each do |i|
-            i.replace("<p class='FigureGraphic'>#{i.to_xml}</p>")
-          end
-        end
-      end
-
-      def code_style(doc)
-        span_style((doc.xpath("//tt//b") - doc.xpath("//tt//i//b")),
-                   "ISOCodebold")
-        span_style((doc.xpath("//tt//i") - doc.xpath("//tt//b//i")),
-                   "ISOCodeitalic")
-        span_style((doc.xpath("//b//tt") - doc.xpath("//b//i//tt")),
-                   "ISOCodebold")
-        span_style((doc.xpath("//i//tt") - doc.xpath("//i//b//tt")),
-                   "ISOCodeitalic")
-        span_style(doc.xpath("//tt"), "ISOCode")
-      end
-
-      def span_style(xpath, style)
-        xpath.each do |elem|
-          elem.name = "span"
-          elem["class"] = style
-        end
-      end
-
       def make_tr_attr(cell, row, totalrows, header)
         super.merge(header: header)
       end
 
-      def word_cleanup(docxml)
-        word_table_cell_para(docxml)
-        super
-      end
-
-      def word_table_cell_para(docxml)
-        docxml.xpath("//td | //th").each do |t|
-          s = t["header"] == "true" ? "Tableheader" : "Tablebody"
-          t.delete("header")
-          if t.at("./p |./div")
-            t.xpath("./p | ./div").each { |p| p["class"] = s }
-          else
-            t.children = "<div class='#{s}'>#{t.children.to_xml}</div>"
-          end
-        end
-      end
-
       def toWord(result, filename, dir, header)
         result = from_xhtml(word_cleanup(to_xhtml(result)))
           .gsub(/-DOUBLE_HYPHEN_ESCAPE-/, "--")
@@ -178,6 +85,38 @@ module IsoDoc
         header&.unlink
         @wordstylesheet.unlink if @wordstylesheet.is_a?(Tempfile)
       end
+
+      def middle_title(_isoxml, out)
+        middle_title_dis(out)
+      end
+
+      def middle_title_dis(out)
+        out.p(**{ class: "zzSTDTitle" }) do |p|
+          p << @meta.get[:doctitleintro]
+          @meta.get[:doctitleintro] && @meta.get[:doctitlemain] and p << " &#x2014; "
+          p << @meta.get[:doctitlemain]
+          @meta.get[:doctitlemain] && @meta.get[:doctitlepart] and p << " &#x2014; "
+          if @meta.get[:doctitlepart]
+            b = @meta.get[:doctitlepartlabel] and
+              p << "<span style='font-weight:normal'>#{b}</span> "
+            p << " #{@meta.get[:doctitlepart]}"
+          end
+          @meta.get[:doctitleamdlabel] || @meta.get[:doctitleamd] ||
+            @meta.get[:doctitlecorrlabel] and middle_title_dis_amd(p)
+        end
+      end
+
+      def middle_title_dis_amd(para)
+        para.span(**{ style: "font-weight:normal" }) do |p|
+          if a = @meta.get[:doctitleamdlabel]
+            p << " #{a}"
+            a = @meta.get[:doctitleamd] and p << ": #{a}"
+          end
+          if a = @meta.get[:doctitlecorrlabel]
+            p << " #{a}"
+          end
+        end
+      end
     end
   end
 end

data/lib/isodoc/iso/xref.rb

@@ -77,11 +77,10 @@ module IsoDoc
         i = Counter.new
         clause.xpath(ns("./appendix")).each do |c|
           i.increment(c)
-          @anchors[c["id"]] = anchor_struct(i.print, nil, @labels["appendix"],
-                                            "clause")
-          @anchors[c["id"]][:level] = 2
-          @anchors[c["id"]][:subtype] = "annex"
-          @anchors[c["id"]][:container] = clause["id"]
+          @anchors[c["id"]] =
+            anchor_struct(i.print, nil, @labels["appendix"],
+                          "clause").merge(level: 2, subtype: "annex",
+                                          container: clause["id"])
           j = Counter.new
           c.xpath(ns("./clause | ./references")).each do |c1|
             j.increment(c1)
@@ -92,7 +91,7 @@ module IsoDoc
       end
 
       # subclauses are not prefixed with "Clause"
-      # retaining sybtupe for the semantics
+      # retaining subtype for the semantics
       def section_names1(clause, num, level)
         @anchors[clause["id"]] =
           { label: num, level: level, xref: num, subtype: "clause" }
@@ -189,6 +188,35 @@ module IsoDoc
       def annex_name_lbl(clause, num)
         super.sub(%r{<br/>(.*)$}, "<br/><span class='obligation'>\\1</span>")
       end
+
+      def list_anchor_names(sections)
+        sections.each do |s|
+          notes = s.xpath(ns(".//ol")) - s.xpath(ns(".//clause//ol")) -
+            s.xpath(ns(".//appendix//ol")) - s.xpath(ns(".//ol//ol"))
+          c = Counter.new
+          notes.reject { |n| blank?(n["id"]) }.each do |n|
+            @anchors[n["id"]] = anchor_struct(increment_label(notes, n, c), n,
+                                              @labels["list"], "list", false)
+            list_item_anchor_names(n, @anchors[n["id"]], 1, "",
+                                   !single_ol_for_xrefs?(notes))
+          end
+          list_anchor_names(s.xpath(ns(CHILD_SECTIONS)))
+        end
+      end
+
+      # all li in the ol in lists are consecutively numbered through @start
+      def single_ol_for_xrefs?(lists)
+        return true if lists.size == 1
+
+        start = 0
+        lists.each_with_index do |l, i|
+          next if i.zero?
+
+          start += lists[i - 1].xpath(ns("./li")).size
+          return false unless l["start"]&.to_i == start + 1
+        end
+        true
+      end
     end
   end
 end

data/lib/metanorma/iso/base.rb

@@ -25,6 +25,10 @@ module Metanorma
         IsoDoc::Iso::WordConvert.new(doc_extract_attributes(node))
       end
 
+      def doc_extract_attributes(node)
+        super.merge(isowordtemplate: node.attr("iso-word-template"))
+      end
+
       def pdf_converter(node)
         return nil if node.attr("no-pdf")
 
@@ -49,7 +53,16 @@ module Metanorma
 
       def ol_attrs(node)
         attr_code(keep_attrs(node)
-                  .merge(id: ::Metanorma::Utils::anchor_or_uuid(node)))
+                  .merge(id: ::Metanorma::Utils::anchor_or_uuid(node),
+                         start: node.attr("start")))
+      end
+
+      def admonition_name(node)
+        name = super
+        a = node.attr("type") and ["editorial"].each do |t|
+          name = t if a.casecmp(t).zero?
+        end
+        name
       end
 
       def outputs(node, ret)

data/lib/metanorma/iso/biblio.rng

@@ -614,12 +614,103 @@
     <optional>
       <ref name="fetched"/>
     </optional>
-    <choice>
-      <oneOrMore>
-        <ref name="btitle"/>
-      </oneOrMore>
+    <optional>
       <ref name="formattedref"/>
-    </choice>
+    </optional>
+    <oneOrMore>
+      <ref name="btitle"/>
+    </oneOrMore>
+    <zeroOrMore>
+      <ref name="bsource"/>
+    </zeroOrMore>
+    <oneOrMore>
+      <ref name="docidentifier"/>
+    </oneOrMore>
+    <optional>
+      <ref name="docnumber"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="bdate"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="contributor"/>
+    </zeroOrMore>
+    <optional>
+      <ref name="edition"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="version"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="biblionote"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="language"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="script"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="bibabstract"/>
+    </zeroOrMore>
+    <optional>
+      <ref name="status"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="copyright"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="docrelation"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="series"/>
+    </zeroOrMore>
+    <optional>
+      <ref name="medium"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="bplace"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="bprice"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="extent"/>
+    </zeroOrMore>
+    <optional>
+      <ref name="bibliographic_size"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="accesslocation"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="license"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="bclassification"/>
+    </zeroOrMore>
+    <zeroOrMore>
+      <ref name="bkeyword"/>
+    </zeroOrMore>
+    <optional>
+      <ref name="validity"/>
+    </optional>
+  </define>
+  <define name="ReducedBibliographicItem">
+    <optional>
+      <attribute name="type">
+        <ref name="BibItemType"/>
+      </attribute>
+    </optional>
+    <optional>
+      <ref name="fetched"/>
+    </optional>
+    <optional>
+      <ref name="formattedref"/>
+    </optional>
+    <zeroOrMore>
+      <ref name="btitle"/>
+    </zeroOrMore>
     <zeroOrMore>
       <ref name="bsource"/>
     </zeroOrMore>
@@ -638,9 +729,9 @@
     <optional>
       <ref name="edition"/>
     </optional>
-    <optional>
+    <zeroOrMore>
       <ref name="version"/>
-    </optional>
+    </zeroOrMore>
     <zeroOrMore>
       <ref name="biblionote"/>
     </zeroOrMore>
@@ -833,6 +924,12 @@
           <data type="boolean"/>
         </attribute>
       </optional>
+      <optional>
+        <attribute name="language"/>
+      </optional>
+      <optional>
+        <attribute name="script"/>
+      </optional>
       <text/>
     </element>
   </define>
@@ -986,36 +1083,34 @@
           <ref name="SeriesType"/>
         </attribute>
       </optional>
-      <choice>
+      <optional>
         <ref name="formattedref"/>
-        <group>
-          <ref name="btitle"/>
-          <optional>
-            <ref name="bplace"/>
-          </optional>
-          <optional>
-            <ref name="seriesorganization"/>
-          </optional>
-          <optional>
-            <ref name="abbreviation"/>
-          </optional>
-          <optional>
-            <ref name="seriesfrom"/>
-          </optional>
-          <optional>
-            <ref name="seriesto"/>
-          </optional>
-          <optional>
-            <ref name="seriesnumber"/>
-          </optional>
-          <optional>
-            <ref name="seriespartnumber"/>
-          </optional>
-          <optional>
-            <ref name="seriesrun"/>
-          </optional>
-        </group>
-      </choice>
+      </optional>
+      <ref name="btitle"/>
+      <optional>
+        <ref name="bplace"/>
+      </optional>
+      <optional>
+        <ref name="seriesorganization"/>
+      </optional>
+      <optional>
+        <ref name="abbreviation"/>
+      </optional>
+      <optional>
+        <ref name="seriesfrom"/>
+      </optional>
+      <optional>
+        <ref name="seriesto"/>
+      </optional>
+      <optional>
+        <ref name="seriesnumber"/>
+      </optional>
+      <optional>
+        <ref name="seriespartnumber"/>
+      </optional>
+      <optional>
+        <ref name="seriesrun"/>
+      </optional>
     </element>
   </define>
   <define name="SeriesType">
@@ -1174,7 +1269,7 @@
         </element>
       </optional>
       <element name="bibitem">
-        <ref name="BibliographicItem"/>
+        <ref name="ReducedBibliographicItem"/>
       </element>
       <choice>
         <zeroOrMore>
@@ -1199,9 +1294,9 @@
       <optional>
         <ref name="revision-date"/>
       </optional>
-      <zeroOrMore>
+      <optional>
         <ref name="draft"/>
-      </zeroOrMore>
+      </optional>
     </element>
   </define>
   <define name="vedition">

data/lib/metanorma/iso/boilerplate-fr.xml

@@ -1,6 +1,9 @@
 <boilerplate>
   <copyright-statement>
     <clause>
+      {% if stage_int >= 40 %}
+      <title>DOCUMENT PROTÉGÉ PAR COPYRIGHT</title>
+      {% endif %}
       <p id="boilerplate-year">&#xa9; <span class="std_publisher">{{ agency }}</span> <span class="std_docNumber">{{ docyear }}</span></p>
 
   <p id="boilerplate-message">

data/lib/metanorma/iso/boilerplate-ru.xml

@@ -1,6 +1,9 @@
 <boilerplate>
   <copyright-statement>
     <clause>
+      {% if stage_int >= 40 %}
+      <title>ДОКУМЕНТ, ОХРАНЯЕМЫЙ АВТОРСКИМ ПРАВОМ</title>
+      {% endif %}
       <p id="boilerplate-year">&#xa9; <span class="std_publisher">{{ agency }}</span> <span class="std_docNumber">{{ docyear }}</span></p>
 
   <p id="boilerplate-message">

data/lib/metanorma/iso/boilerplate.xml

@@ -1,6 +1,9 @@
 <boilerplate>
   <copyright-statement>
     <clause>
+      {% if stage_int >= 40 %}
+      <title>COPYRIGHT PROTECTED DOCUMENT</title>
+      {% endif %}
       <p id="boilerplate-year">&#xa9; <span class="std_publisher">{{ agency }}</span> <span class="std_docNumber">{{ docyear }}</span></p>
 
   <p id="boilerplate-message">

data/lib/metanorma/iso/cleanup.rb

@@ -1,8 +1,5 @@
 require "date"
-require "nokogiri"
 require "htmlentities"
-require "json"
-require "pathname"
 
 module Metanorma
   module ISO
@@ -15,8 +12,7 @@ module Metanorma
 
       POST_NORMREF_FOOTNOTES =
         "//sections//clause[not(@type = 'scope')]//fn | "\
-        "//annex//fn | "\
-        "//references[@normative = 'false']//fn".freeze
+        "//annex//fn | //references[@normative = 'false']//fn".freeze
 
       def other_footnote_renumber(xmldoc)
         seen = {}
@@ -40,7 +36,7 @@ module Metanorma
         xmldoc.xpath("//bibdata/contributor[role/@type = 'publisher']"\
                      "/organization").each_with_object([]) do |x, prefix|
           x1 = x.at("abbreviation")&.text || x.at("name")&.text
-          #(x1 == "ISO" and prefix.unshift("ISO")) or prefix << x1
+          # (x1 == "ISO" and prefix.unshift("ISO")) or prefix << x1
           prefix << x1
         end
       end
@@ -80,7 +76,8 @@ module Metanorma
         return 2 if bib.at("#{PUBLISHER}[abbreviation = 'IEC']")
         return 2 if bib.at("#{PUBLISHER}[name = 'International "\
                            "Electrotechnical Commission']")
-        return 3 if bib.at("./docidentifier[@type][not(#{OTHERIDS})]")
+        return 3 if bib.at("./docidentifier[@type][not(#{OTHERIDS})]") ||
+          bib.at("./docidentifier[not(@type)]")
 
         4
       end
@@ -102,7 +99,8 @@ module Metanorma
       def sort_biblio_key(bib)
         pubclass = pub_class(bib)
         num = bib&.at("./docnumber")&.text
-        id = bib&.at("./docidentifier[not(#{OTHERIDS})]")
+        id = bib&.at("./docidentifier[@primary]") ||
+          bib&.at("./docidentifier[not(#{OTHERIDS})]")
         metaid = bib&.at("./docidentifier[@type = 'metanorma']")&.text
         abbrid = metaid unless /^\[\d+\]$/.match?(metaid)
         /\d-(?<partid>\d+)/ =~ id&.text
@@ -118,9 +116,7 @@ module Metanorma
         super
         return unless @amd
 
-        xml.xpath("//*[@inline-header]").each do |h|
-          h.delete("inline-header")
-        end
+        xml.xpath("//*[@inline-header]").each { |h| h.delete("inline-header") }
       end
 
       def boilerplate_file(_xmldoc)
@@ -170,8 +166,7 @@ module Metanorma
 
             if id = replacement_standard(b)
               insert_unpub_note(b, @i18n.cancelled_and_replaced.sub(/%/, id))
-            else
-              insert_unpub_note(b, @i18n.withdrawn)
+            else insert_unpub_note(b, @i18n.withdrawn)
             end
           end
       end
@@ -209,6 +204,51 @@ module Metanorma
         @vocab and return
         super
       end
+
+      def bibdata_cleanup(xmldoc)
+        super
+        approval_groups_rename(xmldoc)
+        editorial_groups_agency(xmldoc)
+        editorial_group_types(xmldoc)
+      end
+
+      def approval_groups_rename(xmldoc)
+        %w(technical-committee subcommittee workgroup).each do |v|
+          xmldoc.xpath("//bibdata//approval-#{v}").each { |a| a.name = v }
+        end
+      end
+
+      def editorial_groups_agency(xmldoc)
+        pubs = extract_publishers(xmldoc)
+        xmldoc.xpath("//bibdata/ext/editorialgroup").each do |e|
+          pubs.reverse.each do |p|
+            if e.children.empty? then e << "<agency>#{p}</agency>"
+            else e.children.first.previous = "<agency>#{p}</agency>"
+            end
+          end
+        end
+      end
+
+      def extract_publishers(xmldoc)
+        xmldoc.xpath("//bibdata/contributor[role/@type = 'publisher']/"\
+                     "organization").each_with_object([]) do |p, m|
+          x = p.at("./abbreviation") || p.at("./name") or next
+          m << x.text
+        end
+      end
+
+      DEFAULT_EDGROUP_TYPE = { "technical-committee": "TC",
+                               subcommittee: "SC", workgroup: "WG" }.freeze
+
+      def editorial_group_types(xmldoc)
+        %w(technical-committee subcommittee workgroup).each do |v|
+          xmldoc.xpath("//bibdata//#{v} | //bibdata//approval-#{v}").each do |g|
+            next if g["type"]
+
+            g["type"] = DEFAULT_EDGROUP_TYPE[v.to_sym]
+          end
+        end
+      end
     end
   end
 end