metanorma-iso 1.10.4 → 2.0.1

data/lib/isodoc/iso/metadata.rb

@@ -21,9 +21,8 @@ module IsoDoc
           stage = "DTS" if stage == "DIS"
           stage = "FDTS" if stage == "FDIS"
         end
-        if %w(PWI NWIP WD CD).include?(stage) && iter
+        %w(PWI NWIP WD CD).include?(stage) && iter and
           stage += iter
-        end
         stage = "Pre#{stage}" if /^0\./.match?(draft)
         stage
       end
@@ -31,20 +30,25 @@ module IsoDoc
       def docstatus(isoxml, _out)
         docstatus = isoxml.at(ns("//bibdata/status/stage"))
         set(:unpublished, false)
-        if docstatus
-          set(:stage, docstatus.text)
-          set(:stage_int, docstatus.text.to_i)
-          set(:unpublished, unpublished(docstatus.text))
-          set(:statusabbr, status_abbrev(docstatus["abbreviation"] || "??",
-                                         isoxml&.at(ns("//bibdata/status/substage"))&.text,
-                                         isoxml&.at(ns("//bibdata/status/iteration"))&.text,
-                                         isoxml&.at(ns("//bibdata/version/draft"))&.text,
-                                         isoxml&.at(ns("//bibdata/ext/doctype"))&.text))
-          unpublished(docstatus.text) and
-            set(:stageabbr, docstatus["abbreviation"])
-        end
         revdate = isoxml.at(ns("//bibdata/version/revision-date"))
         set(:revdate, revdate&.text)
+        if docstatus
+          docstatus1(isoxml, docstatus)
+        end
+      end
+
+      def docstatus1(isoxml, docstatus)
+        set(:stage, docstatus.text)
+        set(:stage_int, docstatus.text.to_i)
+        set(:unpublished, unpublished(docstatus.text))
+        set(:statusabbr,
+            status_abbrev(docstatus["abbreviation"] || "??",
+                          isoxml&.at(ns("//bibdata/status/substage"))&.text,
+                          isoxml&.at(ns("//bibdata/status/iteration"))&.text,
+                          isoxml&.at(ns("//bibdata/version/draft"))&.text,
+                          isoxml&.at(ns("//bibdata/ext/doctype"))&.text))
+        unpublished(docstatus.text) and
+          set(:stageabbr, docstatus["abbreviation"])
       end
 
       def unpublished(status)
@@ -73,8 +77,7 @@ module IsoDoc
 
       def amd_label(lang)
         case lang
-        when "en" then "AMENDMENT"
-        when "fr" then "AMENDMENT"
+        when "en", "fr" then "AMENDMENT"
         end
       end
 
@@ -183,10 +186,10 @@ module IsoDoc
       end
 
       def tc(xml)
-        tc_num = xml.at(ns("//bibdata/ext/editorialgroup/technical-committee/@number"))
-        tc_type = xml.at(ns("//bibdata/ext/editorialgroup/technical-committee/@type"))
-          &.text || "TC"
-        if tc_num
+        tc_type = xml.at(ns("//bibdata/ext/editorialgroup/technical-committee/"\
+                            "@type"))&.text || "TC"
+        if tc_num = xml.at(ns("//bibdata/ext/editorialgroup/"\
+                              "technical-committee/@number"))
           tcid = "#{tc_type} #{tc_num.text}"
           set(:tc,  tcid)
           set(:editorialgroup, get[:editorialgroup] << tcid)
@@ -195,7 +198,8 @@ module IsoDoc
 
       def sc(xml)
         sc_num = xml.at(ns("//bibdata/ext/editorialgroup/subcommittee/@number"))
-        sc_type = xml.at(ns("//bibdata/ext/editorialgroup/subcommittee/@type"))&.text || "SC"
+        sc_type = xml.at(ns("//bibdata/ext/editorialgroup/subcommittee/"\
+                            "@type"))&.text || "SC"
         if sc_num
           scid = "#{sc_type} #{sc_num.text}"
           set(:sc, scid)
@@ -205,7 +209,8 @@ module IsoDoc
 
       def wg(xml)
         wg_num = xml.at(ns("//bibdata/ext/editorialgroup/workgroup/@number"))
-        wg_type = xml.at(ns("//bibdata/ext/editorialgroup/workgroup/@type"))&.text || "WG"
+        wg_type = xml.at(ns("//bibdata/ext/editorialgroup/workgroup/"\
+                            "@type"))&.text || "WG"
         if wg_num
           wgid = "#{wg_type} #{wg_num.text}"
           set(:wg, wgid)

data/lib/isodoc/iso/presentation_xml_convert.rb

@@ -113,28 +113,29 @@ module IsoDoc
       end
 
       def concept(docxml)
-        docxml.xpath(ns("//term//concept")).each_with_object({}) do |f, m|
-          concept_term(f, m)
-        end
+        concept_term(docxml)
         docxml.xpath(ns("//concept")).each do |node|
-          concept_render(node, ital: node["ital"] || "false",
-                               ref: node["ref"] || "false",
-                               linkref: node["linkref"] || "true",
-                               linkmention: node["linkmention"] || "false")
+          concept_render(node, ital: "false", ref: "false",
+                               linkref: "true", linkmention: "false")
+        end
+      end
+
+      def concept_term(docxml)
+        docxml.xpath(ns("//term")).each do |f|
+          m = {}
+          f.xpath(ns(".//concept")).each do |c|
+            concept_term1(c, m)
+          end
         end
       end
 
-      def concept_term(node, seen)
+      def concept_term1(node, seen)
         term = node&.at(ns("./refterm"))&.to_xml
         if term && seen[term]
-          concept_render(node, ital: node["ital"] || "false",
-                               ref: node["ref"] || "false",
-                               linkref: node["linkref"] || "true",
-                               linkmention: node["linkmention"] || "false")
-        else concept_render(node, ital: node["ital"] || "true",
-                                  ref: node["ref"] || "true",
-                                  linkref: node["linkref"] || "true",
-                                  linkmention: node["linkmention"] || "false")
+          concept_render(node, ital: "false", ref: "false",
+                               linkref: "true", linkmention: "false")
+        else concept_render(node, ital: "true", ref: "true",
+                                  linkref: "true", linkmention: "false")
         end
         seen[term] = true if term
         seen
@@ -184,6 +185,30 @@ module IsoDoc
           "<#{d.remove.children.to_xml}> "
       end
 
+      def insertall_after_here(node, insert, name)
+        node.children.each do |n|
+          next unless n.name == name
+
+          insert.next = n.remove
+          insert = n
+        end
+        insert
+      end
+
+      def termexamples_before_termnotes(node)
+        return unless insert = node.at(ns("./definition"))
+
+        insert = insertall_after_here(node, insert, "termexample")
+        insertall_after_here(node, insert, "termnote")
+      end
+
+      def terms(docxml)
+        docxml.xpath(ns("//term[termnote][termexample]")).each do |node|
+          termexamples_before_termnotes(node)
+        end
+        super
+      end
+
       include Init
     end
   end

data/lib/isodoc/iso/sts_convert.rb

@@ -20,10 +20,8 @@ module IsoDoc
           end
         FileUtils.rm_rf dir
         MnConvert.convert(in_fname,
-                          {
-                            input_format: MnConvert::InputFormat::MN,
-                            output_file: out_fname || "#{filename}.#{@suffix}",
-                          })
+                          { input_format: MnConvert::InputFormat::MN,
+                            output_file: out_fname || "#{filename}.#{@suffix}" })
       end
     end
   end

data/lib/isodoc/iso/word_convert.rb

@@ -154,11 +154,13 @@ module IsoDoc
       end
 
       def annex_name(_annex, name, div)
+        preceding_floating_titles(name, div)
         return if name.nil?
 
         name&.at(ns("./strong"))&.remove # supplied by CSS list numbering
         div.h1 **{ class: "Annex" } do |t|
           name.children.each { |c2| parse(c2, t) }
+          clause_parse_subtitle(name, t)
         end
       end
 

data/lib/metanorma/iso/base.rb

@@ -0,0 +1,70 @@
+require "date"
+require "nokogiri"
+require "json"
+require "pathname"
+require "open-uri"
+require "isodoc"
+require "fileutils"
+
+module Metanorma
+  module ISO
+    class Converter < Standoc::Converter
+      XML_ROOT_TAG = "iso-standard".freeze
+      XML_NAMESPACE = "https://www.metanorma.org/ns/iso".freeze
+
+      def html_converter(node)
+        IsoDoc::Iso::HtmlConvert.new(html_extract_attributes(node))
+      end
+
+      def html_converter_alt(node)
+        IsoDoc::Iso::HtmlConvert.new(html_extract_attributes(node)
+                                     .merge(alt: true))
+      end
+
+      def doc_converter(node)
+        IsoDoc::Iso::WordConvert.new(doc_extract_attributes(node))
+      end
+
+      def pdf_converter(node)
+        return nil if node.attr("no-pdf")
+
+        IsoDoc::Iso::PdfConvert.new(pdf_extract_attributes(node))
+      end
+
+      def sts_converter(node)
+        return nil if node.attr("no-pdf")
+
+        IsoDoc::Iso::StsConvert.new(html_extract_attributes(node))
+      end
+
+      def presentation_xml_converter(node)
+        IsoDoc::Iso::PresentationXMLConvert.new(html_extract_attributes(node))
+      end
+
+      def init(node)
+        super
+        @amd = %w(amendment technical-corrigendum).include? doctype(node)
+        @vocab = node.attr("docsubtype") == "vocabulary"
+      end
+
+      def ol_attrs(node)
+        attr_code(keep_attrs(node)
+                  .merge(id: ::Metanorma::Utils::anchor_or_uuid(node)))
+      end
+
+      def outputs(node, ret)
+        File.open("#{@filename}.xml", "w:UTF-8") { |f| f.write(ret) }
+        presentation_xml_converter(node).convert("#{@filename}.xml")
+        html_converter_alt(node).convert("#{@filename}.presentation.xml",
+                                         nil, false, "#{@filename}_alt.html")
+        html_converter(node).convert("#{@filename}.presentation.xml",
+                                     nil, false, "#{@filename}.html")
+        doc_converter(node).convert("#{@filename}.presentation.xml",
+                                    nil, false, "#{@filename}.doc")
+        pdf_converter(node)&.convert("#{@filename}.presentation.xml",
+                                     nil, false, "#{@filename}.pdf")
+        # sts_converter(node)&.convert(@filename + ".xml")
+      end
+    end
+  end
+end

data/lib/metanorma/iso/cleanup.rb

@@ -0,0 +1,176 @@
+require "date"
+require "nokogiri"
+require "htmlentities"
+require "json"
+require "pathname"
+
+module Metanorma
+  module ISO
+    class Converter < Standoc::Converter
+      PRE_NORMREF_FOOTNOTES = "//preface//fn | "\
+                              "//clause[@type = 'scope']//fn".freeze
+
+      NORMREF_FOOTNOTES =
+        "//references[@normative = 'true']//fn".freeze
+
+      POST_NORMREF_FOOTNOTES =
+        "//sections//clause[not(@type = 'scope')]//fn | "\
+        "//annex//fn | "\
+        "//references[@normative = 'false']//fn".freeze
+
+      def other_footnote_renumber(xmldoc)
+        seen = {}
+        i = 0
+        [PRE_NORMREF_FOOTNOTES, NORMREF_FOOTNOTES,
+         POST_NORMREF_FOOTNOTES].each do |xpath|
+          xmldoc.xpath(xpath).each do |fn|
+            i, seen = other_footnote_renumber1(fn, i, seen)
+          end
+        end
+      end
+
+      def id_prefix(prefix, id)
+        # we're just inheriting the prefixes from parent doc
+        return id.text if @amd
+
+        prefix.join("/") + (id.text.match?(%{^/}) ? "" : " ") + id.text
+      end
+
+      def get_id_prefix(xmldoc)
+        prefix = []
+        xmldoc.xpath("//bibdata/contributor[role/@type = 'publisher']"\
+                     "/organization").each do |x|
+          x1 = x.at("abbreviation")&.text || x.at("name")&.text
+          (x1 == "ISO" and prefix.unshift("ISO")) or prefix << x1
+        end
+        prefix
+      end
+
+      # ISO as a prefix goes first
+      def docidentifier_cleanup(xmldoc)
+        prefix = get_id_prefix(xmldoc)
+        id = xmldoc.at("//bibdata/docidentifier[@type = 'ISO']") or return
+        id.content = id_prefix(prefix, id)
+        id = xmldoc.at("//bibdata/ext/structuredidentifier/project-number") and
+          id.content = id_prefix(prefix, id)
+        id = xmldoc.at("//bibdata/docidentifier[@type = 'iso-with-lang']") and
+          id.content = id_prefix(prefix, id)
+        id = xmldoc.at("//bibdata/docidentifier[@type = 'iso-reference']") and
+          id.content = id_prefix(prefix, id)
+      end
+
+      def format_ref(ref, type)
+        ref = ref.sub(/ \(All Parts\)/i, "")
+        super
+      end
+
+      TERM_CLAUSE =
+        "//sections//terms | "\
+        "//sections//clause[descendant::terms][not(descendant::definitions)]"
+          .freeze
+
+      PUBLISHER = "./contributor[role/@type = 'publisher']/organization".freeze
+
+      OTHERIDS = "@type = 'DOI' or @type = 'metanorma' or @type = 'ISSN' or "\
+                 "@type = 'ISBN'".freeze
+
+      def pub_class(bib)
+        return 1 if bib.at("#{PUBLISHER}[abbreviation = 'ISO']")
+        return 1 if bib.at("#{PUBLISHER}[name = 'International Organization "\
+                           "for Standardization']")
+        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})]")
+
+        4
+      end
+
+      def sort_biblio(bib)
+        bib.sort do |a, b|
+          sort_biblio_key(a) <=> sort_biblio_key(b)
+        end
+      end
+
+      # TODO sort by authors
+      # sort by: doc class (ISO, IEC, other standard (not DOI &c), other
+      # then standard class (docid class other than DOI &c)
+      # then docnumber if present, numeric sort
+      #      else alphanumeric metanorma id (abbreviation)
+      # then doc part number if present, numeric sort
+      # then doc id (not DOI &c)
+      # then title
+      def sort_biblio_key(bib)
+        pubclass = pub_class(bib)
+        num = bib&.at("./docnumber")&.text
+        id = bib&.at("./docidentifier[not(#{OTHERIDS})]")
+        metaid = bib&.at("./docidentifier[@type = 'metanorma']")&.text
+        abbrid = metaid unless /^\[\d+\]$/.match?(metaid)
+        /\d-(?<partid>\d+)/ =~ id&.text
+        type = id["type"] if id
+        title = bib&.at("./title[@type = 'main']")&.text ||
+          bib&.at("./title")&.text || bib&.at("./formattedref")&.text
+        "#{pubclass} :: #{type} :: "\
+          "#{num.nil? ? abbrid : sprintf('%09d', num.to_i)} :: "\
+          "#{sprintf('%09d', partid.to_i)} :: #{id&.text} :: #{title}"
+      end
+
+      def sections_cleanup(xml)
+        super
+        return unless @amd
+
+        xml.xpath("//*[@inline-header]").each do |h|
+          h.delete("inline-header")
+        end
+      end
+
+      def boilerplate_file(_xmldoc)
+        file = @lang == "fr" ? "boilerplate-fr.xml" : "boilerplate.xml"
+        File.join(@libdir, file)
+      end
+
+      def footnote_cleanup(xmldoc)
+        unpub_footnotes(xmldoc)
+        super
+      end
+
+      def unpub_footnotes(xmldoc)
+        xmldoc.xpath("//bibitem/note[@type = 'Unpublished-Status']").each do |n|
+          id = n.parent["id"]
+          e = xmldoc.at("//eref[@bibitemid = '#{id}']") or next
+          fn = n.children.to_xml
+          n&.elements&.first&.name == "p" or fn = "<p>#{fn}</p>"
+          e.next = "<fn>#{fn}</fn>"
+        end
+      end
+
+      def bibitem_cleanup(xmldoc)
+        super
+        unpublished_note(xmldoc)
+      end
+
+      def unpublished_note(xmldoc)
+        xmldoc.xpath("//bibitem[not(note[@type = 'Unpublished-Status'])]")
+          .each do |b|
+          next if pub_class(b) > 2
+          next unless (s = b.at("./status/stage")) && (s.text.to_i < 60)
+
+          id = b.at("docidentifier").text
+          b.at("./language | ./script | ./abstract | ./status")
+            .previous = %(<note type="Unpublished-Status">
+                          <p>#{@i18n.under_preparation.sub(/%/, id)}</p></note>)
+        end
+      end
+
+      def termdef_boilerplate_insert(xmldoc, isodoc, once = false)
+        once = true
+        super
+      end
+
+      def term_defs_boilerplate_cont(src, term, isodoc)
+        @vocab and src.empty? and return
+        super
+      end
+    end
+  end
+end

data/lib/metanorma/iso/converter.rb

@@ -0,0 +1,18 @@
+require "asciidoctor"
+require "metanorma-standoc"
+require "metanorma/iso/version"
+require "metanorma/iso/base"
+require "metanorma/iso/front"
+require "metanorma/iso/section"
+require "metanorma/iso/validate"
+require "metanorma/iso/cleanup"
+
+module Metanorma
+  module ISO
+    # A {Converter} implementation that generates ISO output, and a document
+    # schema encapsulation of the document for validation
+    class Converter < ::Metanorma::Standoc::Converter
+      register_for "iso"
+    end
+  end
+end

data/lib/metanorma/iso/front.rb

@@ -0,0 +1,170 @@
+require "date"
+require "nokogiri"
+require "htmlentities"
+require "json"
+require "pathname"
+require "open-uri"
+require_relative "front_id"
+
+module Metanorma
+  module ISO
+    class Converter < Standoc::Converter
+      def metadata_ext(node, xml)
+        super
+        structured_id(node, xml)
+        xml.stagename stage_name(get_stage(node), get_substage(node),
+                                 doctype(node), node.attr("iteration"))
+        @amd && a = node.attr("updates-document-type") and
+          xml.updates_document_type a
+      end
+
+      def metadata_subdoctype(node, xml)
+        super
+        a = node.attr("horizontal") and xml.horizontal a
+      end
+
+      def org_abbrev
+        { "International Organization for Standardization" => "ISO",
+          "International Electrotechnical Commission" => "IEC" }
+      end
+
+      def metadata_author(node, xml)
+        publishers = node.attr("publisher") || "ISO"
+        csv_split(publishers).each do |p|
+          xml.contributor do |c|
+            c.role **{ type: "author" }
+            c.organization do |a|
+              organization(a, p, false, node, !node.attr("publisher"))
+            end
+          end
+        end
+      end
+
+      def metadata_publisher(node, xml)
+        publishers = node.attr("publisher") || "ISO"
+        csv_split(publishers).each do |p|
+          xml.contributor do |c|
+            c.role **{ type: "publisher" }
+            c.organization do |a|
+              organization(a, p, true, node, !node.attr("publisher"))
+            end
+          end
+        end
+      end
+
+      def metadata_copyright(node, xml)
+        publishers = node.attr("copyright-holder") || node.attr("publisher") ||
+          "ISO"
+        csv_split(publishers).each do |p|
+          xml.copyright do |c|
+            c.from (node.attr("copyright-year") || Date.today.year)
+            c.owner do |owner|
+              owner.organization do |o|
+                organization(
+                  o, p, true, node,
+                  !(node.attr("copyright-holder") || node.attr("publisher"))
+                )
+              end
+            end
+          end
+        end
+      end
+
+      def metadata_status(node, xml)
+        stage = get_stage(node)
+        substage = get_substage(node)
+        xml.status do |s|
+          s.stage stage, **attr_code(abbreviation: cover_stage_abbr(node))
+          s.substage substage
+          node.attr("iteration") && (s.iteration node.attr("iteration"))
+        end
+      end
+
+      def metadata_committee(node, xml)
+        xml.editorialgroup do |a|
+          committee_component("technical-committee", node, a)
+          committee_component("subcommittee", node, a)
+          committee_component("workgroup", node, a)
+          node.attr("secretariat") && a.secretariat(node.attr("secretariat"))
+        end
+      end
+
+      def title_intro(node, xml, lang, at)
+        return unless node.attr("title-intro-#{lang}")
+
+        xml.title(**attr_code(at.merge(type: "title-intro"))) do |t1|
+          t1 << Metanorma::Utils::asciidoc_sub(node.attr("title-intro-#{lang}"))
+        end
+      end
+
+      def title_main(node, xml, lang, at)
+        xml.title **attr_code(at.merge(type: "title-main")) do |t1|
+          t1 << Metanorma::Utils::asciidoc_sub(node.attr("title-main-#{lang}"))
+        end
+      end
+
+      def title_part(node, xml, lang, at)
+        return unless node.attr("title-part-#{lang}")
+
+        xml.title(**attr_code(at.merge(type: "title-part"))) do |t1|
+          t1 << Metanorma::Utils::asciidoc_sub(node.attr("title-part-#{lang}"))
+        end
+      end
+
+      def title_amd(node, xml, lang, at)
+        return unless node.attr("title-amendment-#{lang}")
+
+        xml.title(**attr_code(at.merge(type: "title-amd"))) do |t1|
+          t1 << Metanorma::Utils::asciidoc_sub(
+            node.attr("title-amendment-#{lang}"),
+          )
+        end
+      end
+
+      def title_full(node, xml, lang, at)
+        title = node.attr("title-main-#{lang}")
+        intro = node.attr("title-intro-#{lang}")
+        part = node.attr("title-part-#{lang}")
+        amd = node.attr("title-amendment-#{lang}")
+        title = "#{intro} -- #{title}" if intro
+        title = "#{title} -- #{part}" if part
+        title = "#{title} -- #{amd}" if amd && @amd
+        xml.title **attr_code(at.merge(type: "main")) do |t1|
+          t1 << Metanorma::Utils::asciidoc_sub(title)
+        end
+      end
+
+      def title(node, xml)
+        ["en", "fr"].each do |lang|
+          at = { language: lang, format: "text/plain" }
+          title_full(node, xml, lang, at)
+          title_intro(node, xml, lang, at)
+          title_main(node, xml, lang, at)
+          title_part(node, xml, lang, at)
+          title_amd(node, xml, lang, at) if @amd
+        end
+      end
+
+      def relaton_relations
+        super + %w(obsoletes successor-of manifestation-of related annotation-of)
+      end
+
+      def relaton_relation_descriptions
+        super.merge(
+          "amends" => "updates", "revises" => "updates",
+          "replaces" => "obsoletes",
+          "supersedes" => "obsoletes",
+          "corrects" => "updates",
+          "informatively-cited-in" => "isCitedIn",
+          "informatively-cites" => "cites",
+          "normatively-cited in" => "isCitedIn",
+          "normatively-cites" => "cites",
+          "identical-adopted-from" => "adoptedFrom",
+          "modified-adopted-from" => "adoptedFrom",
+          "related-directive" => "related",
+          "related-mandate" => "related",
+        )
+      end
+    end
+  end
+end