metanorma-iso 2.1.1 → 2.1.2

data/lib/isodoc/iso/metadata.rb

@@ -5,11 +5,8 @@ module IsoDoc
     class Metadata < IsoDoc::Metadata
       def initialize(lang, script, i18n)
         super
-        set(:tc, "XXXX")
-        set(:sc, "XXXX")
-        set(:wg, "XXXX")
+        DATETYPES.each { |w| @metadata["#{w.gsub(/-/, '_')}date".to_sym] = nil }
         set(:editorialgroup, [])
-        set(:secretariat, "XXX")
         set(:obsoletes, nil)
         set(:obsoletes_part, nil)
       end
@@ -37,13 +34,14 @@ module IsoDoc
       def docstatus1(isoxml, docstatus)
         set(:stage, docstatus.text)
         set(:stage_int, docstatus.text.to_i)
+        set(:substage_int, isoxml.at(ns("//bibdata/status/substage"))&.text)
         set(:unpublished, unpublished(docstatus.text))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))
+                          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         unpublished(docstatus.text) and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
@@ -65,28 +63,11 @@ module IsoDoc
 
       # 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 "Partie"
-        when "ru" then "Часть"
-        end
-      end
-
-      def amd_label(lang)
-        case lang
-        when "en", "fr" then "AMENDMENT"
-        when "ru" then "ПОПРАВКА"
-        end
-      end
-
-      def corr_label(lang)
-        case lang
-        when "en" then "TECHNICAL CORRIGENDUM"
-        when "fr" then "RECTIFICATIF TECHNIQUE"
-        when "ru" then "ТЕХНИЧЕСКОЕ ИСПРАВЛЕНИЕ"
-        end
-      end
+      PART_LABEL = { en: "Part", fr: "Partie", ru: "Часть" }.freeze
+      AMD_LABEL = { en: "AMENDMENT", fr: "AMENDMENT", ru: "ПОПРАВКА" }.freeze
+      CORR_LABEL = { en: "TECHNICAL CORRIGENDUM",
+                     fr: "RECTIFICATIF TECHNIQUE",
+                     ru: "ТЕХНИЧЕСКОЕ ИСПРАВЛЕНИЕ" }.freeze
 
       def part_title(part, titlenums, lang)
         return "" unless part
@@ -96,7 +77,7 @@ module IsoDoc
         titlenums[:part] && titlenums[:subpart] and
           p = "#{titlenums[:part]}&#x2013;#{titlenums[:subpart]}"
         titlenums[:part] and
-          suffix = "#{part_label(lang)}&#xa0;#{p}: " + suffix
+          suffix = "#{PART_LABEL[lang.to_sym]}&#xa0;#{p}: " + suffix
         suffix
       end
 
@@ -104,15 +85,15 @@ module IsoDoc
         p = titlenums[:part]
         titlenums[:part] && titlenums[:subpart] and
           p = "#{titlenums[:part]}&#x2013;#{titlenums[:subpart]}"
-        "#{part_label(lang)}&#xa0;#{p}"
+        "#{PART_LABEL[lang.to_sym]}&#xa0;#{p}"
       end
 
       def amd_prefix(titlenums, lang)
-        "#{amd_label(lang)}&#xa0;#{titlenums[:amd]}"
+        "#{AMD_LABEL[lang.to_sym]}&#xa0;#{titlenums[:amd]}"
       end
 
       def corr_prefix(titlenums, lang)
-        "#{corr_label(lang)}&#xa0;#{titlenums[:corr]}"
+        "#{CORR_LABEL[lang.to_sym]}&#xa0;#{titlenums[:corr]}"
       end
 
       def compose_title(tparts, tnums, lang)
@@ -130,20 +111,21 @@ module IsoDoc
       end
 
       def title_nums(isoxml)
-        { part: isoxml.at(ns("//bibdata//project-number/@part")),
-          subpart: isoxml.at(ns("//bibdata//project-number/@subpart")),
-          amd: isoxml.at(ns("//bibdata//project-number/@amendment")),
-          corr: isoxml.at(ns("//bibdata//project-number/@corrigendum")) }
+        prefix = "//bibdata/ext/structuredidentifier/project-number"
+        { part: isoxml.at(ns("#{prefix}/@part")),
+          subpart: isoxml.at(ns("#{prefix}/@subpart")),
+          amd: isoxml.at(ns("#{prefix}/@amendment")),
+          corr: isoxml.at(ns("#{prefix}/@corrigendum")) }
       end
 
       def title_parts(isoxml, lang)
-        { intro: isoxml.at(ns("//bibdata//title[@type='title-intro' and "\
+        { intro: isoxml.at(ns("//bibdata/title[@type='title-intro' and "\
                               "@language='#{lang}']")),
-          main: isoxml.at(ns("//bibdata//title[@type='title-main' and "\
+          main: isoxml.at(ns("//bibdata/title[@type='title-main' and "\
                              "@language='#{lang}']")),
-          part: isoxml.at(ns("//bibdata//title[@type='title-part' and "\
+          part: isoxml.at(ns("//bibdata/title[@type='title-part' and "\
                              "@language='#{lang}']")),
-          amd: isoxml.at(ns("//bibdata//title[@type='title-amd' and "\
+          amd: isoxml.at(ns("//bibdata/title[@type='title-amd' and "\
                             "@language='#{lang}']")) }
       end
 
@@ -197,40 +179,58 @@ module IsoDoc
         tc(xml)
         sc(xml)
         wg(xml)
+        approvalgroup(xml)
         secretariat(xml)
       end
 
       def tc(xml)
-        tc_type = xml.at(ns("//bibdata/ext/editorialgroup/technical-committee/"\
+        tcid = tc_base(xml, "editorialgroup") or return
+        set(:tc, tcid)
+        set(:editorialgroup, get[:editorialgroup] << tcid)
+      end
+
+      def tc_base(xml, grouptype)
+        tc_num = xml.at(ns("//bibdata/ext/#{grouptype}/"\
+                           "technical-committee/@number")) or return nil
+        tc_type = xml.at(ns("//bibdata/ext/#{grouptype}/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)
-        end
+        "#{tc_type} #{tc_num.text}"
       end
 
       def sc(xml)
-        sc_num = xml.at(ns("//bibdata/ext/editorialgroup/subcommittee/@number"))
-        sc_type = xml.at(ns("//bibdata/ext/editorialgroup/subcommittee/"\
+        scid = sc_base(xml, "editorialgroup") or return
+        set(:sc, scid)
+        set(:editorialgroup, get[:editorialgroup] << scid)
+      end
+
+      def sc_base(xml, grouptype)
+        sc_num = xml.at(ns("//bibdata/ext/#{grouptype}/subcommittee/"\
+                           "@number")) or return nil
+        sc_type = xml.at(ns("//bibdata/ext/#{grouptype}/subcommittee/"\
                             "@type"))&.text || "SC"
-        if sc_num
-          scid = "#{sc_type} #{sc_num.text}"
-          set(:sc, scid)
-          set(:editorialgroup, get[:editorialgroup] << scid)
-        end
+        "#{sc_type} #{sc_num.text}"
       end
 
       def wg(xml)
-        wg_num = xml.at(ns("//bibdata/ext/editorialgroup/workgroup/@number"))
-        wg_type = xml.at(ns("//bibdata/ext/editorialgroup/workgroup/"\
+        wgid = wg_base(xml, "editorialgroup") or return
+        set(:wg, wgid)
+        set(:editorialgroup, get[:editorialgroup] << wgid)
+      end
+
+      def wg_base(xml, grouptype)
+        wg_num = xml.at(ns("//bibdata/ext/#{grouptype}/workgroup/"\
+                           "@number")) or return
+        wg_type = xml.at(ns("//bibdata/ext/#{grouptype}/workgroup/"\
                             "@type"))&.text || "WG"
-        if wg_num
-          wgid = "#{wg_type} #{wg_num.text}"
-          set(:wg, wgid)
-          set(:editorialgroup, get[:editorialgroup] << wgid)
-        end
+        "#{wg_type} #{wg_num.text}"
+      end
+
+      def approvalgroup(xml)
+        ag = tc_base(xml, "approvalgroup") or return
+        ret = [ag]
+        ret << sc_base(xml, "approvalgroup")
+        ret << wg_base(xml, "approvalgroup")
+        set(:approvalgroup, ret)
       end
 
       def secretariat(xml)

data/lib/isodoc/iso/presentation_bibdata.rb

@@ -0,0 +1,74 @@
+module IsoDoc
+  module Iso
+    class PresentationXMLConvert < IsoDoc::PresentationXMLConvert
+      def bibdata(docxml)
+        super
+        editorialgroup_identifier(docxml)
+        warning_for_missing_metadata(docxml)
+      end
+
+      def warning_for_missing_metadata(docxml)
+        return unless @meta.get[:unpublished]
+
+        ret = ""
+        docxml.at(ns("//bibdata/ext//secretariat")) or
+          ret += "<p>Secretariat is missing.</p>"
+        docxml.at(ns("//bibdata/ext//editorialgroup")) or
+          ret += "<p>Editorial groups are missing.</p>"
+        docxml.at(ns("//bibdata/date[@type = 'published' or @type = 'issued' "\
+                     "or @type = 'created']")) ||
+          docxml.at(ns("//bibdata/version/revision-date")) or
+          ret += "<p>Document date is missing.</p>"
+        return if ret.empty?
+
+        warning_for_missing_metadata1(docxml, ret)
+      end
+
+      def warning_for_missing_metadata1(docxml, ret)
+        id = UUIDTools::UUID.random_create
+        ret = "<review date='#{Date.today}' reviewer='Metanorma' id='_#{id}'>"\
+              "<p><strong>Metadata warnings:<strong></p> #{ret}</review>"
+        ins = docxml.at(ns("//sections//title")) or return
+        ins.children.first.previous = ret
+      end
+
+      def editorialgroup_identifier(docxml)
+        %w(editorialgroup approvalgroup).each do |v|
+          docxml.xpath(ns("//bibdata/ext/#{v}")).each do |a|
+            editorialgroup_identifier1(a)
+          end
+        end
+      end
+
+      def editorialgroup_identifier1(group)
+        agency = group.xpath(ns("./agency"))&.map(&:text)
+        ret = %w(technical-committee subcommittee workgroup)
+          .each_with_object([]) do |v, m|
+          a = group.at(ns("./#{v}")) or next
+          m << "#{a['type']} #{a['number']}"
+        end
+        group["identifier"] = (agency + ret).join("/")
+      end
+
+      def bibdata_i18n(bib)
+        hash_translate(bib, @i18n.get["doctype_dict"], "./ext/doctype")
+        bibdata_i18n_stage(bib, bib.at(ns("./status/stage")),
+                           bib.at(ns("./ext/doctype")))
+        hash_translate(bib, @i18n.get["substage_dict"],
+                       "./status/substage")
+        edition_translate(bib)
+      end
+
+      def bibdata_i18n_stage(bib, stage, type, lang: @lang, i18n: @i18n)
+        return unless stage
+
+        i18n.get["stage_dict"][stage.text].is_a?(Hash) or
+          return hash_translate(bib, i18n.get["stage_dict"],
+                                "./status/stage", lang)
+        i18n.get["stage_dict"][stage.text][type&.text] and
+          tag_translate(stage, lang,
+                        i18n.get["stage_dict"][stage.text][type&.text])
+      end
+    end
+  end
+end

data/lib/isodoc/iso/presentation_xml_convert.rb

@@ -1,8 +1,8 @@
 require_relative "init"
 require "isodoc"
 require_relative "index"
-require_relative "presentation_inline"
 require_relative "presentation_xref"
+require_relative "presentation_bibdata"
 require_relative "../../relaton/render/general"
 
 module IsoDoc
@@ -172,9 +172,10 @@ module IsoDoc
       def admonition_name(xml)
         "#{xml} — "
       end
-    
+
       def bibrenderer
-        ::Relaton::Render::Iso::General.new(language: @lang, i18nhash: @i18n.get)
+        ::Relaton::Render::Iso::General.new(language: @lang,
+                                            i18nhash: @i18n.get)
       end
 
       def bibrender(xml)
@@ -185,6 +186,16 @@ module IsoDoc
         end
       end
 
+      def ol_depth(node)
+        depth = node.ancestors(@iso_class ? "ol" : "ul, ol").size + 1
+        type = :alphabet
+        type = :arabic if [2, 7].include? depth
+        type = :roman if [3, 8].include? depth
+        type = :alphabet_upper if [4, 9].include? depth
+        type = :roman_upper if [5, 10].include? depth
+        type
+      end
+
       include Init
     end
   end

data/lib/isodoc/iso/presentation_xref.rb

@@ -104,8 +104,14 @@ module IsoDoc
       end
 
       def prefix_container(container, linkend, target)
-        delim = @xrefs.anchor(target, :type) == "listitem" ? " " : ", "
-        l10n(@xrefs.anchor(container, :xref) + delim + linkend)
+        delim = ", "
+        type = :xref
+        if @xrefs.anchor(target, :type) == "listitem" &&
+            !@xrefs.anchor(target, :refer_list)
+          delim = " "
+          type = :label # 7 a) not Clause 7 a), but Clause 7 List 1 a)
+        end
+        l10n(@xrefs.anchor(container, type) + delim + linkend)
       end
 
       def expand_citeas(text)

data/lib/isodoc/iso/sections.rb

@@ -1,7 +1,7 @@
 module IsoDoc
   module Iso
     module BaseConvert
-      def middle_title(isoxml, out)
+      def middle_title(_isoxml, out)
         middle_title_main(out)
         middle_title_amd(out)
       end

data/lib/isodoc/iso/word_cleanup.rb

@@ -44,6 +44,9 @@ module IsoDoc
         docxml.xpath("//*[@class = 'example']").each do |p|
           p["class"] = "Example"
         end
+        docxml.xpath("//*[@class = 'zzHelp']/p[not(@class)]").each do |p|
+          p["class"] = "zzHelp"
+        end
       end
 
       def authority_hdr_cleanup(docxml)

data/lib/isodoc/iso/word_convert.rb

@@ -14,10 +14,11 @@ module IsoDoc
         @wordToClevels = 3 if @wordToClevels.zero?
         @htmlToClevels = options[:htmltoclevels].to_i
         @htmlToClevels = 3 if @htmlToClevels.zero?
-        init_dis
+        init_dis(options)
       end
 
-      def init_dis
+      def init_dis(options)
+        @wordtemplate = options[:isowordtemplate]
         @dis = ::IsoDoc::Iso::WordDISConvert.new(options)
       end
 
@@ -55,8 +56,10 @@ module IsoDoc
                 output_filename = nil)
         file = File.read(input_filename, encoding: "utf-8") if file.nil?
         docxml = Nokogiri::XML(file) { |config| config.huge }
+        stage = docxml&.at(ns("//bibdata/status/stage"))&.text
         if @dis &&
-            /^[45].$/.match?(docxml&.at(ns("//bibdata/status/stage"))&.text)
+            ((/^[4569].$/.match?(stage) && @wordtemplate != "simple") ||
+            (/^[0-3].$/.match?(stage) && @wordtemplate == "dis"))
           @dis.convert(input_filename, file, debug, output_filename)
         else
           super

data/lib/isodoc/iso/word_dis_cleanup.rb

@@ -0,0 +1,235 @@
+module IsoDoc
+  module Iso
+    class WordDISConvert < WordConvert
+      def style_cleanup(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",
+        Sourcecode: "Code",
+        zzSTDTitle1: "zzSTDTitle",
+        zzSTDTitle2: "zzSTDTitle",
+        zzCopyright1: "zzCopyright",
+      }.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)
+        amd_style(docxml)
+        code_style(docxml)
+        figure_style(docxml)
+        note_style(docxml)
+        example_style(docxml)
+        quote_style(docxml)
+        dis_style_interactions(docxml)
+      end
+
+      def dis_style_interactions(docxml)
+        docxml.xpath("//p[@class = 'Code' or @class = 'Code-' or "\
+                     "@class = 'Code--']"\
+                     "[following::p[@class = 'Examplecontinued']]").each do |p|
+          p["style"] ||= ""
+          p["style"] = "margin-bottom:12pt;#{p['style']}"
+        end
+      end
+
+      def amd_style(docxml)
+        return unless @meta.get[:doctype] == "Amendment"
+
+        docxml.xpath("//div[@class = 'WordSection3']//h1").each do |h|
+          h.name = "p"
+          h["style"] = "font-style:italic;page-break-after:avoid;"
+        end
+      end
+
+      def quote_style(docxml)
+        docxml.xpath("//div[@class = 'Quote' or @class = 'Note' or "\
+                     "@class = 'Example' or @class = 'Admonition']").each do |d|
+                       quote_style1(d)
+                     end
+      end
+
+      def para_style_change(div, class1, class2)
+        s = class1 ? "@class = '#{class1}'" : "not(@class)"
+        div.xpath(".//p[#{s}]").each do |p|
+          p["class"] = class2
+        end
+      end
+
+      def quote_style1(div)
+        para_style_change(div, nil, "BodyTextindent1")
+        para_style_change(div, "Code-", "Code--")
+        para_style_change(div, "Code", "Code-")
+        if div["class"] != "Example"
+          para_style_change(div, "Example", "Exampleindent")
+          para_style_change(div, "Examplecontinued", "Exampleindentcontinued")
+        end
+        if div["class"] != "Note"
+          para_style_change(div, "Note", "Noteindent")
+          para_style_change(div, "Notecontinued", "Noteindentcontinued")
+        end
+        div.xpath(".//table[@class = 'dl']").each do |t|
+          t["style"] = "margin-left: 1cm;"
+        end
+      end
+
+      def remove_note_label(doc)
+        doc.xpath("//span[@class = 'note_label' or @class = 'example_label']")
+          .each do |s|
+          s.replace(s.children)
+        end
+      end
+
+      def note_style(docxml)
+        remove_note_label(docxml)
+        note_continued_style(docxml)
+      end
+
+      def example_style(docxml)
+        example_continued_style(docxml)
+      end
+
+      def example_continued_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
+        end
+      end
+
+      def note_continued_style(docxml)
+        docxml.xpath("//div[@class = 'Note']").each do |d|
+          d.xpath("./p").each_with_index do |p, i|
+            next if p["class"] && p["class"] != "Note"
+
+            p["class"] = (i.zero? ? "Note" : "Notecontinued")
+          end
+        end
+      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 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 word_cleanup(docxml)
+        word_table_cell_para(docxml)
+        super
+        word_section_end_empty_para(docxml)
+        docxml
+      end
+
+      def authority_cleanup(docxml)
+        super
+        if @meta.get[:stage_int].to_s[0] == "9" ||
+            @meta.get[:stage_int].to_s[0] == "6"
+          copyright_prf(docxml)
+        else
+          copyright_dis(docxml)
+        end
+      end
+
+      def copyright_prf(docxml)
+        docxml.xpath("//p[@id = 'boilerplate-address']")&.each do |p|
+          p["class"] = "zzCopyright"
+          p["style"] = "text-indent:20.15pt;"
+          p.replace(p.to_xml.gsub(%r{<br/>}, "</p>\n<p class='zzCopyright' "\
+                                             "style='text-indent:20.15pt;'>"))
+        end
+        docxml.xpath("//p[@class = 'zzCopyrightHdr']")&.each do |p|
+          # p["class"] = "zzCopyright"
+          p.remove
+        end
+      end
+
+      def copyright_dis(docxml)
+        docxml.xpath("//p[@id = 'boilerplate-address']")&.each do |p|
+          p["class"] = "zzCopyright"
+          p.replace(p.to_xml.gsub(%r{<br/>}, "</p>\n<p class='zzCopyright'>"))
+        end
+        docxml.xpath("//p[@class = 'zzCopyrightHdr']")&.each do |p|
+          p.remove
+        end
+      end
+
+      def word_section_end_empty_para(docxml)
+        docxml.at("//div[@class='WordSection1']/p[last()]").remove
+      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
+    end
+  end
+end