metanorma-standoc 1.5.0 → 1.6.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 76c3b117ea592275339f9ee8103f17645d9675f45635abfbc8e5333fc512af1c
-  data.tar.gz: a345b19a2657f356225f2087e17a7dba7bd4720389cf44487892d3f1e1bc5345
+  metadata.gz: 11adce8b2fe42f3e2b4db51088b5818f5cff207a62cc19e33b27cf5a53160c47
+  data.tar.gz: 17967efeb1bc5c518a9498ec8329d7ae0fb6c77cb19bb911527aa15efd2f0881
 SHA512:
-  metadata.gz: 630d1159cc78920d3bab3e73a2577b54d00bb966b0faa15166ff1af832656ab985e55f8fa830d40a2fbec96a8cf8555880f89f0e73d749dc73540e6cd8303469
-  data.tar.gz: f3c46604bb69f1e34eb8b2af182e198e99a6f2cae3bce808a9547e096b1852b4868c00a8522370a52c92ad5f263ab2f7e5ee348196fffbe1084ef1c666900080
+  metadata.gz: 6bef6b7fb5db91fd23d039a2e01d69685ba049b3ef34ebb2c4eaafa2e144b54c6c948b1c0a91796b700c2c18494c048d79d71b21fe58e1437f994a296d950785
+  data.tar.gz: 6c4d35c69f213280a58dd8b5e53da18c4947cc5de3210397f35f19726dbcceb2a3ea4f26066f86ee2fca2e0d0a37d9941e6cb092a7625d557dfba25eb4367812

data/.github/workflows/macos.yml

@@ -29,18 +29,13 @@ jobs:
         uses: actions/setup-ruby@v1
         with:
           ruby-version: ${{ matrix.ruby }}
-      - name: Install LaTeXML
-        run: |
-          brew install libxml2 cpanminus
-          env PATH=$(brew --prefix libxml2)/bin:$PATH \
-            cpanm --notest XML::LibXSLT@1.96 git://github.com/brucemiller/LaTeXML.git@9a0e7dc5
-      - name: Install PlantUML
-        run: |
-          brew install plantuml
       - name: Update gems
         run: |
           sudo gem install bundler --force
           bundle install --jobs 4 --retry 3
+      - name: Install PlantUML
+        run: |
+          brew install plantuml
       - name: Run specs
         run: |
-          env PATH=$(brew --prefix perl)/bin:$PATH bundle exec rake
+          bundle exec rake

data/.github/workflows/ubuntu.yml

@@ -33,17 +33,13 @@ jobs:
         run: |
           gem install bundler
           bundle install --jobs 4 --retry 3
-      - name: Install LaTeXML
-        run: |
-          sudo snap install latexml --edge
-          echo "::add-path::/snap/bin"
       - name: Install PlantUML
         uses: nick-invision/retry@v1
         with:
           polling_interval_seconds: 5
           timeout_minutes: 5
           max_attempts: 3
-          command: sudo bash -c "curl -L https://github.com/metanorma/plantuml-install/raw/master/ubuntu.sh | bash"
+          command: sudo apt-get update -y && sudo bash -c "curl -L https://github.com/metanorma/plantuml-install/raw/master/ubuntu.sh | bash"
       - name: Run specs
         run: |
           bundle exec rake

data/.github/workflows/windows.yml

@@ -29,25 +29,15 @@ jobs:
         uses: actions/setup-ruby@v1
         with:
           ruby-version: ${{ matrix.ruby }}
-      - name: Install MN Windows dependencies
-        shell: pwsh
-        run: |
-          choco install --no-progress plantuml make sed gnuwin32-coreutils.install grep
       - name: Update gems
         shell: pwsh
         run: |
           gem install bundler
           bundle config --local path vendor/bundle
           bundle install --jobs 4 --retry 3
-      - name: Install LaTeXML
-        shell: cmd
+      - name: Install PlantUML
         run: |
-          cinst -y latexml
-          refreshenv
-          set PATH=C:\Strawberry\c\bin;C:\Strawberry\perl\site\bin;C:\Strawberry\perl\bin;%PATH%
-          where latexmlmath
+          cinst -y plantuml
       - name: Run specs
-        shell: pwsh
         run: |
-          $env:Path = "C:\Strawberry\c\bin;C:\Strawberry\perl\site\bin;C:\Strawberry\perl\bin;$env:Path"
           bundle exec rake

data/lib/asciidoctor/standoc/base.rb

@@ -143,6 +143,11 @@ module Asciidoctor
         ret
       end
 
+      def version
+        flavour = self.class.name.sub(/::Converter$/, "").sub(/^.+::/, "")
+        Metanorma.versioned(Metanorma, flavour)[-1]::VERSION
+      end
+
       def clean_exit
         @log.write(@output_dir + @filename + ".err") unless @novalid
         @files_to_delete.each { |f| FileUtils.rm f }
@@ -150,7 +155,7 @@ module Asciidoctor
 
       def makexml1(node)
         result = ["<?xml version='1.0' encoding='UTF-8'?>",
-                  "<#{xml_root_tag}>"]
+                  "<#{xml_root_tag} type='semantic' version='#{version}'>"]
         result << noko { |ixml| front node, ixml }
         result << noko { |ixml| middle node, ixml }
         result << "</#{xml_root_tag}>"
@@ -170,7 +175,7 @@ module Asciidoctor
       end
 
       def doctype(node)
-        node.attr("doctype")
+        node.attr("doctype")&.gsub(/\s+/, "-")&.downcase
       end
 
       def front(node, xml)

data/lib/asciidoctor/standoc/basicdoc.rng

@@ -402,6 +402,16 @@
           </choice>
         </attribute>
       </optional>
+      <optional>
+        <attribute name="valign">
+          <choice>
+            <value>top</value>
+            <value>middle</value>
+            <value>bottom</value>
+            <value>baseline</value>
+          </choice>
+        </attribute>
+      </optional>
       <choice>
         <zeroOrMore>
           <ref name="TextElement"/>
@@ -429,6 +439,16 @@
           </choice>
         </attribute>
       </optional>
+      <optional>
+        <attribute name="valign">
+          <choice>
+            <value>top</value>
+            <value>middle</value>
+            <value>bottom</value>
+            <value>baseline</value>
+          </choice>
+        </attribute>
+      </optional>
       <choice>
         <zeroOrMore>
           <ref name="TextElement"/>
@@ -998,6 +1018,9 @@
           <value>alphabet_upper</value>
         </choice>
       </attribute>
+      <optional>
+        <attribute name="start"/>
+      </optional>
       <oneOrMore>
         <ref name="li"/>
       </oneOrMore>

data/lib/asciidoctor/standoc/cleanup.rb

@@ -9,6 +9,7 @@ require_relative "./cleanup_boilerplate.rb"
 require_relative "./cleanup_section.rb"
 require_relative "./cleanup_terms.rb"
 require_relative "./cleanup_inline.rb"
+require_relative "./cleanup_amend.rb"
 require "relaton_iev"
 
 module Asciidoctor
@@ -71,6 +72,7 @@ module Asciidoctor
         para_cleanup(xmldoc)
         empty_element_cleanup(xmldoc)
         img_cleanup(xmldoc)
+        anchor_cleanup(xmldoc)
         xmldoc
       end
 
@@ -79,12 +81,13 @@ module Asciidoctor
         xmldoc.traverse do |n|
           next unless n.text?
           if @smartquotes
-            next unless /[-'"(<>]|\.\.|\dx/.match(n)
-            next unless n.ancestors("pre, tt, sourcecode, bibdata, on, "\
-                                    "stem, figure[@class = 'pseudocode']").empty?
+            /[-'"(<>]|\.\.|\dx/.match(n) or next
+            n.ancestors("pre, tt, sourcecode, bibdata, on, "\
+                        "stem, figure[@class = 'pseudocode']").empty? or next
             n.replace(Utils::smartformat(n.text))
           else
-            n.replace(n.text.gsub(/(?<=\p{Alnum})\u2019(?=\p{Alpha})/, "'"))
+            n.replace(n.text.gsub(/(?<=\p{Alnum})\u2019(?=\p{Alpha})/, "'"))#.
+            #gsub(/</, "&lt;").gsub(/>/, "&gt;"))
           end
         end
       end
@@ -144,16 +147,33 @@ module Asciidoctor
         align_callouts_to_annotations(xmldoc)
       end
 
+      def xml_unescape_mathml(x)
+        return if x.children.any? { |y| y.element? }
+        math = x.text.gsub(/&lt;/, "<").gsub(/&gt;/, ">").gsub(/&quot;/, '"').
+          gsub(/&apos;/, "'").gsub(/&amp;/, "&").
+          gsub(/<[^: \r\n\t\/]+:/, "<").gsub(/<\/[^ \r\n\t:]+:/, "</")
+        x.children = math
+      end
+
+      def mathml_preserve_space(m)
+        m.xpath(".//m:mtext",
+                "m" => "http://www.w3.org/1998/Math/MathML").each do |x|
+          x.children = x.children.to_xml.gsub(/^\s/, "&#xA0;").
+            gsub(/\s$/, "&#xA0;")
+        end
+      end
+
+      def mathml_namespace(stem)
+        stem.xpath("./math", ).each do |x|
+          x.default_namespace = "http://www.w3.org/1998/Math/MathML"
+        end
+      end
+
       def mathml_cleanup(xmldoc)
         xmldoc.xpath("//stem[@type = 'MathML']").each do |x|
-          next if x.children.any? { |y| y.element? }
-          math = x.text.gsub(/&lt;/, "<").gsub(/&gt;/, ">").gsub(/&quot;/, '"').
-            gsub(/&apos;/, "'").gsub(/&amp;/, "&").
-            gsub(/<[^: \r\n\t\/]+:/, "<").gsub(/<\/[^ \r\n\t:]+:/, "</").
-            gsub(/ xmlns[^>"']+/, "").
-            gsub(/<math /, '<math xmlns="http://www.w3.org/1998/Math/MathML" ').
-            gsub(/<math>/, '<math xmlns="http://www.w3.org/1998/Math/MathML">')
-          x.children = math
+          xml_unescape_mathml(x)
+          mathml_namespace(x)
+          mathml_preserve_space(x)
         end
       end
 

data/lib/asciidoctor/standoc/cleanup_amend.rb

@@ -0,0 +1,54 @@
+module Asciidoctor
+  module Standoc
+    module Cleanup
+      def change_clauses(x)
+        x.xpath("//clause[@change]").each do |c|
+          a = create_amend(c)
+        end
+      end
+
+      def create_amend(c)
+        a = c.add_child("<amend id='_#{UUIDTools::UUID.random_create}'/>").first
+        c.elements.each do |e|
+          e.parent = a unless %w(amend title).include? e.name
+        end
+        create_amend1(c, a)
+      end
+
+      def create_amend1(c, a)
+        create_amend2(c, a)
+        d = a.at("./description")
+        d.xpath(".//autonumber").each { |e| d.previous = e }
+        d.xpath(".//p[normalize-space(.)='']").each { |e| e.remove }
+        move_attrs_to_amend(c, a)
+        a
+      end
+
+      def create_amend2(c, a)
+        q = a.at("./quote") and q.name = "newcontent"
+        if q.nil?
+          a.children = "<description>#{a.children.to_xml}</description>"
+        else
+          pre = q&.xpath("./preceding-sibling::*")&.remove
+          post = q&.xpath("./following-sibling::*")&.remove
+          pre.empty? or a << "<description>#{pre.to_xml}</description>"
+          a << q.remove
+          post.empty? or a << "<description>#{post.to_xml}</description>"
+        end
+      end
+
+      def move_attrs_to_amend(c, a)
+        %w(change path path_end title).each do |e|
+          next unless c[e]
+          a[e] = c[e]
+          c.delete(e)
+        end
+        return unless a["locality"]
+        loc = a.children.add_previous_sibling("<location/>")
+        extract_localities1(loc, a["locality"])
+        loc1 = loc.at("./localityStack") and loc.replace(loc1.elements)
+        a.delete("locality")
+      end
+    end
+  end
+end

data/lib/asciidoctor/standoc/cleanup_block.rb

@@ -1,8 +1,6 @@
 require "date"
-require "nokogiri"
 require "htmlentities"
 require "json"
-require "pathname"
 require "open-uri"
 
 module Asciidoctor

data/lib/asciidoctor/standoc/cleanup_footnotes.rb

@@ -1,10 +1,7 @@
 require "date"
-require "nokogiri"
 require "htmlentities"
 require "json"
-require "pathname"
 require "open-uri"
-require "pp"
 
 module Asciidoctor
   module Standoc
@@ -75,7 +72,18 @@ module Asciidoctor
         end
       end
 
+      def title_footnote_move(xmldoc)
+        ins = xmldoc.at("//bibdata/language")
+        xmldoc.xpath("//bibdata/title//fn").each do |f|
+          f.name = "note"
+          f["type"] = "title-footnote"
+          f.delete("reference")
+          ins.previous = f.remove
+        end
+      end
+
       def footnote_cleanup(xmldoc)
+        title_footnote_move(xmldoc)
         table_footnote_renumber(xmldoc)
         other_footnote_renumber(xmldoc)
         xmldoc.xpath("//fn").each do |fn|

data/lib/asciidoctor/standoc/cleanup_inline.rb

@@ -50,6 +50,10 @@ module Asciidoctor
 
       def extract_localities(x)
         text = x&.children&.first&.remove&.text
+        extract_localities1(x, text)
+      end
+
+      def extract_localities1(x, text)
         b = x.add_child("<localityStack/>").first if LOCALITY_RE.match text
         while (m = LOCALITY_RE.match text)
           ref = m[:ref] ? "<referenceFrom>#{tq m[:ref]}</referenceFrom>" : ""
@@ -117,7 +121,8 @@ module Asciidoctor
       def concept_termbase_cleanup(x)
         text = x&.children&.first&.remove&.text
         termbase, key = x["key"].split(/:/, 2)
-        x.add_child(%(<termref base="#{termbase}" target="#{key}">#{text}</termref>))
+        x.add_child(%(<termref base="#{termbase}" target="#{key}">) + 
+                    "#{text}</termref>")
       end
 
       def concept_xref_cleanup(x)
@@ -129,6 +134,62 @@ module Asciidoctor
         x.children = "<eref>#{x.children.to_xml}</eref>"
         extract_localities(x.first_element_child)
       end
+
+      NAMECHAR = "\u0000-\u0022\u0024\u002c\u002f\u003a-\u0040\\u005b-\u005e"\
+        "\u0060\u007b-\u00b6\u00b8-\u00bf\u00d7\u00f7\u037e\u2000-\u200b"\
+        "\u200e-\u203e\u2041-\u206f\u2190-\u2bff\u2ff0-\u3000".freeze
+      #"\ud800-\uf8ff\ufdd0-\ufdef\ufffe-\uffff".freeze
+      NAMESTARTCHAR = "\\u002d\u002e\u0030-\u0039\u00b7\u0300-\u036f"\
+        "\u203f-\u2040".freeze
+
+      def to_ncname(s)
+        start = s[0]
+        ret1 = %r([#{NAMECHAR}#]).match(start) ? "_" :
+          (%r([#{NAMESTARTCHAR}#]).match(start) ? "_#{start}" : start)
+        ret2 = s[1..-1] || ""
+        ret = (ret1 || "") + ret2.gsub(%r([#{NAMECHAR}#]), "_")
+        ret
+      end
+
+      def to_xreftarget(s)
+        return to_ncname(s) unless /^[^#]+#.+$/.match(s)
+          /^(?<pref>[^#]+)#(?<suff>.+)$/ =~ s
+        pref = pref.gsub(%r([#{NAMECHAR}]), "_")
+        suff = suff.gsub(%r([#{NAMECHAR}]), "_")
+        "#{pref}##{suff}"
+      end
+
+      IDREF = "//*/@id | //review/@from | //review/@to | "\
+        "//callout/@target | //citation/@bibitemid | //eref/@bibitemid".freeze
+
+      def anchor_cleanup(x)
+        anchor_cleanup1(x)
+        xreftarget_cleanup(x)
+      end
+
+      def anchor_cleanup1(x)
+        x.xpath(IDREF).each do |s|
+          if (ret = to_ncname(s.value)) != (orig = s.value)
+            s.value = ret
+            output = s.parent.dup
+            output.children.remove
+            @log.add("Anchors", s.parent, "normalised identifier in #{output} "\
+                     "from #{orig}")
+          end
+        end
+      end
+
+      def xreftarget_cleanup(x)
+        x.xpath("//xref/@target").each do |s|
+          if (ret = to_xreftarget(s.value)) != (orig = s.value)
+            s.value = ret
+            output = s.parent.dup
+            output.children.remove
+            @log.add("Anchors", s.parent, "normalised identifier in #{output} "\
+                     "from #{orig}")
+          end
+        end
+      end
     end
   end
 end

data/lib/asciidoctor/standoc/cleanup_ref.rb

@@ -49,9 +49,8 @@ module Asciidoctor
       # consecutively, but that standards codes are preserved as is:
       # only numeric references are renumbered
       def biblio_renumber(xmldoc)
-        r = xmldoc.at("//references[@normative = 'false'] | "\
-                      "//clause[.//references[@normative = 'false']] | "\
-                      "//annex[.//references[@normative = 'false']]") or return
+        r = xmldoc.at("//references | //clause[.//references] | "\
+                      "//annex[.//references]") or return
         r.xpath(".//bibitem[not(ancestor::bibitem)]").each_with_index do |b, i|
           next unless docid = b.at("./docidentifier[@type = 'metanorma']")
           next unless  /^\[\d+\]$/.match(docid.text)
@@ -127,20 +126,22 @@ module Asciidoctor
           bibitemxml = RelatonBib::BibliographicItem.new(
             RelatonBib::HashConverter::hash_to_bib(bib)).to_xml or next
           bibitem = Nokogiri::XML(bibitemxml)
-          bibitem["id"] = c["id"] if c["id"]
+          bibitem.root["id"] = c["id"] if c["id"] && !/^_/.match(c["id"])
           c.replace(bibitem.root)
         end
       end
 
       def validate_ref_dl(bib, c)
-        unless bib["id"]
+        id = bib["id"]
+        id ||= c["id"] unless /^_/.match(c["id"]) # do not accept implicit id
+        unless id
           @log.add("Anchors", c, "The following reference is missing "\
                    "an anchor:\n" + c.to_xml)
           return
         end
-        bib["title"] or @log.add("Bibliography", c, "Reference #{bib['id']} "\
+        bib["title"] or @log.add("Bibliography", c, "Reference #{id} "\
                                  "is missing a title")
-        bib["docid"] or @log.add("Bibliography", c, "Reference #{bib['id']} "\
+        bib["docid"] or @log.add("Bibliography", c, "Reference #{id} "\
                                  "is missing a document identifier (docid)")
       end
 
@@ -201,7 +202,9 @@ module Asciidoctor
         end
         if !nested and c.at("./title")
           title = c.at("./title").remove.children.to_xml
-          bib["title"] = bib["title"] ? Array(bib["title"]) : []
+          bib["title"] = [bib["title"]] if bib["title"].is_a? Hash
+          bib["title"] = [bib["title"]] if bib["title"].is_a? String
+          bib["title"] = [] unless bib["title"]
           bib["title"] << title if !title.empty?
         end
         bib