metanorma-iso 1.8.3 → 1.9.0

data/lib/isodoc/iso/isosts_convert.rb

@@ -1,31 +1,30 @@
 require "isodoc"
-require "mn2sts"
+require "mnconvert"
 
 module IsoDoc
   module Iso
-
     # A {Converter} implementation that generates HTML output, and a document
     # schema encapsulation of the document for validation
     #
     class IsoStsConvert < IsoDoc::XslfoPdfConvert
-      def initialize(options)
+      def initialize(_options)
         @libdir = File.dirname(__FILE__)
         @format = :isosts
         @suffix = "isosts.xml"
       end
 
-      def convert(input_filename, file = nil, debug = false, output_filename = nil)
-        file = File.read(input_filename, encoding: "utf-8") if file.nil?
-        docxml, filename, dir = convert_init(file, input_filename, debug)
-        /\.xml$/.match(input_filename) or
-          input_filename = Tempfile.open([filename, ".xml"], encoding: "utf-8") do |f|
-          f.write file
-          f.path
-        end
+      def convert(input_fname, file = nil, debug = false, output_fname = nil)
+        file = File.read(input_fname, encoding: "utf-8") if file.nil?
+        _, fname, dir = convert_init(file, input_fname, debug)
+        /\.xml$/.match(input_fname) or
+          input_fname = Tempfile.open([fname, ".xml"], encoding: "utf-8") do |f|
+            f.write file
+            f.path
+          end
         FileUtils.rm_rf dir
-        Mn2sts.convert(input_filename, output_filename || "#{filename}.#{@suffix}", iso: true)
+        MnConvert.convert(input_fname, output_fname || "#{fname}.#{@suffix}",
+                          MnConvert::InputFormat::MN, { output_format: :iso })
       end
     end
   end
 end
-

data/lib/isodoc/iso/metadata.rb

@@ -38,12 +38,12 @@ module IsoDoc
           set(:statusabbr, status_abbrev(docstatus["abbreviation"] || "??",
                                          isoxml&.at(ns("//bibdata/status/substage"))&.text,
                                          isoxml&.at(ns("//bibdata/status/iteration"))&.text,
-                                         isoxml&.at(ns("//version/draft"))&.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           unpublished(docstatus.text) and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("//version/revision-date"))
+        revdate = isoxml.at(ns("//bibdata/version/revision-date"))
         set(:revdate, revdate&.text)
       end
 

data/lib/isodoc/iso/presentation_xml_convert.rb

@@ -45,7 +45,7 @@ module IsoDoc
         prefix_name(node, " — ", lbl, "name")
       end
 
-      def eref_localities1_zh(target, type, from, to, n, delim)
+      def eref_localities1_zh(target, type, from, upto, node, delim)
         subsection = from&.text&.match(/\./)
         ret = if delim == ";"
                 ";"
@@ -53,32 +53,31 @@ module IsoDoc
                 type == "list" ? "" : delim
               end
         ret += " 第#{from.text}" if from
-        ret += "–#{to.text}" if to
+        ret += "–#{upto.text}" if upto
         loc = (@i18n.locality[type] || type.sub(/^locality:/, "").capitalize)
         ret += " #{loc}" unless subsection && type == "clause" ||
           type == "list" || target.match(/^IEV$|^IEC 60050-/) ||
-          n["droploc"] == "true"
+          node["droploc"] == "true"
         ret += ")" if type == "list"
         ret
       end
 
-      def eref_localities1(target, type, from, to, delim, n, lang = "en")
+      def eref_localities1(target, type, from, upto, delim, node, lang = "en")
         return "" if type == "anchor"
 
         subsection = from&.text&.match(/\./)
         type = type.downcase
         lang == "zh" and
-          return l10n(eref_localities1_zh(target, type, from, to, n, delim))
-        ret = if delim == ";"
-                ";"
+          return l10n(eref_localities1_zh(target, type, from, upto, node, delim))
+        ret = if delim == ";" then ";"
               else
                 type == "list" ? "" : delim
               end
-        ret += eref_locality_populate(type, n) unless subsection &&
+        ret += eref_locality_populate(type, node) unless subsection &&
           type == "clause" || type == "list" ||
           target.match(/^IEV$|^IEC 60050-/)
         ret += " #{from.text}" if from
-        ret += "–#{to.text}" if to
+        ret += "–#{upto.text}" if upto
         ret += ")" if type == "list"
         l10n(ret)
       end
@@ -113,6 +112,60 @@ module IsoDoc
         end
       end
 
+      def concept(docxml)
+        docxml.xpath(ns("//terms//concept")).each_with_object({}) do |f, m|
+          concept_term(f, m)
+        end
+        docxml.xpath(ns("//concept")).each do |node|
+          concept_render(node, node["ital"] || "false", node["ref"] || "false")
+        end
+      end
+
+      def concept_term(node, seen)
+        term = node&.at(ns("./refterm"))&.to_xml
+        if term && seen[term]
+          concept_render(node, node["ital"] || "false", node["ref"] || "false")
+        else concept_render(node, node["ital"] || "true", node["ref"] || "true")
+        end
+        seen[term] = true if term
+        seen
+      end
+
+      def concept1_ref(node, ref)
+        if r = node.at(ns("./xref | ./eref | ./termref"))
+          return r.remove if ref == "false"
+
+          r.name == "termref" and
+            r.replace(@i18n.term_defined_in.sub(/%/, r.to_xml)) or
+            r.replace("(#{r.to_xml})")
+        end
+      end
+
+      def concept1(node)
+        node.replace(node&.at(ns("./renderterm"))&.children ||
+                     node&.at(ns("./refterm"))&.children ||
+                     node.children)
+      end
+
+      # we're assuming terms and clauses in the right place for display,
+      # to cope with multiple terms sections
+
+      def display_order(docxml)
+        i = 0
+        i = display_order_xpath(docxml, "//preface/*", i)
+        i = display_order_at(docxml, "//clause[@type = 'scope']", i)
+        i = display_order_at(docxml, @xrefs.klass.norm_ref_xpath, i)
+        # i = display_order_at(docxml, "//sections/terms | "\
+        # "//sections/clause[descendant::terms]", i)
+        # i = display_order_at(docxml, "//sections/definitions", i)
+        # i = display_order_xpath(docxml, @xrefs.klass.middle_clause(docxml), i)
+        i = display_order_xpath(docxml, "//sections/clause[not(@type = 'scope')] | "\
+                                "//sections/terms | //sections/definitions", i)
+        i = display_order_xpath(docxml, "//annex", i)
+        i = display_order_xpath(docxml, @xrefs.klass.bibliography_xpath, i)
+        display_order_xpath(docxml, "//indexsect", i)
+      end
+
       include Init
     end
   end

data/lib/isodoc/iso/sts_convert.rb

@@ -1,9 +1,8 @@
 require "isodoc"
-require "mn2sts"
+require "mnconvert"
 
 module IsoDoc
   module Iso
-
     class StsConvert < IsoDoc::XslfoPdfConvert
       def initialize(_options) # rubocop:disable Lint/MissingSuper
         @libdir = File.dirname(__FILE__)
@@ -14,14 +13,14 @@ module IsoDoc
       def convert(in_fname, file = nil, debug = false, out_fname = nil)
         file = File.read(in_fname, encoding: "utf-8") if file.nil?
         _docxml, filename, dir = convert_init(file, in_fname, debug)
-        unless /\.xml$/.match?(in_fname)
+        /\.xml$/.match?(in_fname) or
           in_fname = Tempfile.open([filename, ".xml"], encoding: "utf-8") do |f|
             f.write file
             f.path
           end
-        end
         FileUtils.rm_rf dir
-        Mn2sts.convert(in_fname, out_fname || "#{filename}.#{@suffix}")
+        Mnconvert.convert(in_fname, out_fname || "#{filename}.#{@suffix}",
+                          MnConvert::InputFormat::MN)
       end
     end
   end

data/lib/isodoc/iso/word_convert.rb

@@ -14,34 +14,34 @@ module IsoDoc
         @htmlToClevels = 3 if @htmlToClevels.zero?
       end
 
+      def font_choice(options)
+        if options[:script] == "Hans" then '"Source Han Sans",serif'
+        else '"Cambria",serif'
+        end
+      end
+
       def default_fonts(options)
-        {
-          bodyfont: (options[:script] == "Hans" ? '"Source Han Sans",serif' :
-                     '"Cambria",serif'),
-                     headerfont: (options[:script] == "Hans" ? '"Source Han Sans",sans-serif' :
-                                  '"Cambria",serif'),
-                                  monospacefont: '"Courier New",monospace',
-                                  normalfontsize: "11.0pt",
-                                  monospacefontsize: "9.0pt",
-                                  smallerfontsize: "10.0pt",
-                                  footnotefontsize: "10.0pt",
-        }
+        { bodyfont: font_choice(options),
+          headerfont: font_choice(options),
+          monospacefont: '"Courier New",monospace',
+          normalfontsize: "11.0pt",
+          monospacefontsize: "9.0pt",
+          smallerfontsize: "10.0pt",
+          footnotefontsize: "10.0pt" }
       end
 
       def default_file_locations(options)
-        {
-          htmlstylesheet: (options[:alt] ? html_doc_path("style-human.scss") :
-                           html_doc_path("style-iso.scss")),
-        htmlcoverpage: html_doc_path("html_iso_titlepage.html"),
-        htmlintropage: html_doc_path("html_iso_intro.html"),
-        wordstylesheet: html_doc_path("wordstyle.scss"),
-        standardstylesheet: html_doc_path("isodoc.scss"),
-        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",
-        }
+        a = options[:alt] ? "style-human.scss" : "style-iso.scss"
+        { htmlstylesheet: html_doc_path(a),
+          htmlcoverpage: html_doc_path("html_iso_titlepage.html"),
+          htmlintropage: html_doc_path("html_iso_intro.html"),
+          wordstylesheet: html_doc_path("wordstyle.scss"),
+          standardstylesheet: html_doc_path("isodoc.scss"),
+          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
 
       def make_body(xml, docxml)
@@ -54,9 +54,10 @@ module IsoDoc
         end
       end
 
-      def colophon(body, docxml)
-        stage =  @meta.get[:stage_int]
+      def colophon(body, _docxml)
+        stage = @meta.get[:stage_int]
         return if !stage.nil? && stage < 60
+
         body.br **{ clear: "all", style: "page-break-before:left;"\
                     "mso-break-type:section-break" }
         body.div **{ class: "colophon" } do |div|
@@ -67,35 +68,55 @@ module IsoDoc
         super
         xml.xpath("//div[@class = 'figure']//table[@class = 'dl']").each do |t|
           t["class"] = "figdl"
-          d = t.add_previous_sibling("<div class='figdl'/>")
+          d = t.add_previous_sibling("<div class='figdl' "\
+                                     "style='page-break-after:avoid;'/>")
           t.parent = d.first
         end
       end
 
       # force Annex h2 down to be p.h2Annex, so it is not picked up by ToC
-      def word_annex_cleanup1(docxml, i)
-        docxml.xpath("//h#{i}[ancestor::*[@class = 'Section3']]").each do |h2|
+      def word_annex_cleanup1(docxml, lvl)
+        docxml.xpath("//h#{lvl}[ancestor::*[@class = 'Section3']]").each do |h2|
           h2.name = "p"
-          h2["class"] = "h#{i}Annex"
+          h2["class"] = "h#{lvl}Annex"
         end
       end
 
       def word_annex_cleanup(docxml)
-        word_annex_cleanup1(docxml, 2)
-        word_annex_cleanup1(docxml, 3)
-        word_annex_cleanup1(docxml, 4)
-        word_annex_cleanup1(docxml, 5)
-        word_annex_cleanup1(docxml, 6)
+        (2..6).each { |i| word_annex_cleanup1(docxml, i) }
+      end
+
+      def word_annex_cleanup_h1(docxml)
+        docxml.xpath("//h1[@class = 'Annex']").each do |h|
+          h.name = "p"
+          h["class"] = "ANNEX"
+        end
+        %w(BiblioTitle ForewordTitle IntroTitle).each do |s|
+          docxml.xpath("//*[@class = '#{s}']").each do |h|
+            h.name = "p"
+          end
+        end
+      end
+
+      def style_cleanup(docxml)
+        word_annex_cleanup_h1(docxml)
+        style_cleanup1(docxml)
+      end
+
+      def style_cleanup1(docxml)
+        docxml.xpath("//*[@class = 'example']").each do |p|
+          p["class"] = "Example"
+        end
       end
 
       def authority_hdr_cleanup(docxml)
-        docxml&.xpath("//div[@class = 'boilerplate-license']").each do |d|
+        docxml&.xpath("//div[@class = 'boilerplate-license']")&.each do |d|
           d.xpath(".//h1").each do |p|
             p.name = "p"
             p["class"] = "zzWarningHdr"
           end
         end
-        docxml&.xpath("//div[@class = 'boilerplate-copyright']").each do |d|
+        docxml&.xpath("//div[@class = 'boilerplate-copyright']")&.each do |d|
           d.xpath(".//h1").each do |p|
             p.name = "p"
             p["class"] = "zzCopyrightHdr"
@@ -120,11 +141,104 @@ module IsoDoc
       def word_cleanup(docxml)
         authority_hdr_cleanup(docxml)
         super
+        style_cleanup(docxml)
         docxml
       end
 
-      def footnote_reference_format(a)
-        a.children = "<span class='MsoFootnoteReference'>#{a.children.to_xml}</span>)"
+      def word_toc_preface(level)
+        <<~TOC.freeze
+          <span lang="EN-GB"><span
+            style='mso-element:field-begin'></span><span
+            style='mso-spacerun:yes'>&#xA0;</span>TOC
+            \\o &quot;1-#{level}&quot; \\h \\z \\t &quot;Heading
+            1;1;ANNEX;1;Biblio Title;1;Foreword Title;1;Intro Title;1&quot; <span
+            style='mso-element:field-separator'></span></span>
+        TOC
+      end
+
+      def footnote_reference_format(link)
+        link.children =
+          "<span class='MsoFootnoteReference'>#{link.children.to_xml}</span>)"
+      end
+
+      def bibliography_attrs
+        { class: "BiblioTitle" }
+      end
+
+      def bibliography(xml, out)
+        f = xml.at(ns(bibliography_xpath)) and f["hidden"] != "true" or return
+        page_break(out)
+        out.div do |div|
+          div.h1 **bibliography_attrs do |h1|
+            f&.at(ns("./title"))&.children&.each { |c2| parse(c2, h1) }
+          end
+          biblio_list(f, div, true)
+        end
+      end
+
+      def bibliography_parse(node, out)
+        node["hidden"] != true or return
+        out.div do |div|
+          clause_parse_title(node, div, node.at(ns("./title")), out,
+                             bibliography_attrs)
+          biblio_list(node, div, true)
+        end
+      end
+
+      def para_class(node)
+        if !node.ancestors("definition").empty? && !@in_footnote
+          "Definition"
+        elsif !node.ancestors("foreword").empty? && !@in_footnote
+          "ForewordText"
+        else
+          super
+        end
+      end
+
+      def termref_attrs
+        { class: "Source" }
+      end
+
+      def termref_parse(node, out)
+        out.p **termref_attrs do |p|
+          p << "[TERMREF]"
+          node.children.each { |n| parse(n, p) }
+          p << "[/TERMREF]"
+        end
+      end
+
+      def figure_name_attrs(node)
+        s = node.ancestors("annex").empty? ? "FigureTitle" : "AnnexFigureTitle"
+        { class: s, style: "text-align:center;" }
+      end
+
+      def figure_name_parse(node, div, name)
+        return if name.nil?
+
+        div.p **figure_name_attrs(node) do |p|
+          name.children.each { |n| parse(n, p) }
+        end
+      end
+
+      def table_title_attrs(node)
+        s = node.ancestors("annex").empty? ? "Tabletitle" : "AnnexTableTitle"
+        { class: s, style: "text-align:center;" }
+      end
+
+      def table_title_parse(node, out)
+        name = node.at(ns("./name")) or return
+        out.p **table_title_attrs(node) do |p|
+          name&.children&.each { |n| parse(n, p) }
+        end
+      end
+
+      def annex_name(_annex, 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) }
+        end
       end
 
       include BaseConvert

data/lib/isodoc/iso/xref.rb

@@ -8,7 +8,7 @@ module IsoDoc
         if @klass.amd(doc)
           initial_anchor_names_amd(doc)
         else
-          super
+          initial_anchor_names1(doc)
         end
         introduction_names(doc.at(ns("//introduction")))
       end
@@ -26,6 +26,22 @@ module IsoDoc
         termexample_anchor_names(doc)
       end
 
+      def initial_anchor_names1(doc)
+        doc.xpath(ns("//preface/*")).each { |c| c.element? and preface_names(c) }
+        # potentially overridden in middle_section_asset_names()
+        sequential_asset_names(doc.xpath(ns("//preface/*")))
+        n = Counter.new
+        n = section_names(doc.at(ns("//clause[@type = 'scope']")), n, 1)
+        n = section_names(doc.at(ns(@klass.norm_ref_xpath)), n, 1)
+        doc.xpath(ns("//sections/clause[not(@type = 'scope')] | "\
+                     "//sections/terms | //sections/definitions")).each do |c|
+          n = section_names(c, n, 1)
+        end
+        middle_section_asset_names(doc)
+        termnote_anchor_names(doc)
+        termexample_anchor_names(doc)
+      end
+
       # we can reference 0-number clauses in introduction
       def introduction_names(clause)
         return if clause.nil?
@@ -99,20 +115,21 @@ module IsoDoc
         clause.xpath(ns(".//formula")).each do |t|
           next if t["id"].nil? || t["id"].empty?
 
-          @anchors[t["id"]] =
-            anchor_struct("#{num}#{hiersep}#{c.increment(t).print}", t,
-                          t["inequality"] ? @labels["inequality"] : @labels["formula"],
-                          "formula", t["unnumbered"])
+          @anchors[t["id"]] = anchor_struct(
+            "#{num}#{hiersep}#{c.increment(t).print}", t,
+            t["inequality"] ? @labels["inequality"] : @labels["formula"],
+            "formula", t["unnumbered"]
+          )
         end
       end
 
-      def figure_anchor(t, sublabel, label)
-        @anchors[t["id"]] = anchor_struct(
+      def figure_anchor(elem, sublabel, label)
+        @anchors[elem["id"]] = anchor_struct(
           (sublabel ? "#{label} #{sublabel}" : label),
-          nil, @labels["figure"], "figure", t["unnumbered"]
+          nil, @labels["figure"], "figure", elem["unnumbered"]
         )
-        sublabel && t["unnumbered"] != "true" and
-          @anchors[t["id"]][:label] = sublabel
+        sublabel && elem["unnumbered"] != "true" and
+          @anchors[elem["id"]][:label] = sublabel
       end
 
       def sequential_figure_names(clause)