metanorma-standoc 1.5.3 → 1.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7503bfc7dd68c2d6a6b2ded8f08611e92067a15aa4088c02f1e5408ff8e027e6
-  data.tar.gz: 65cd5d4d3648788113fd30437fe8d649c6e498b9ebdab8d5b41d2fadb7439056
+  metadata.gz: 0a619338025bf24d56d382fde0bfcd3d7c5f2e5ecf5520d995d8c7d4986cb67d
+  data.tar.gz: 1f8c10a80a5ada1b94c6216568eb11851fd081c9ae63bae2d8b9e3e080673b17
 SHA512:
-  metadata.gz: 73510f7d926c6acf395377794a753cef6bb0f0658fb66c606df07e23548c17f010c7120b77765b388fb363a4309051fcf03a601d6ea95cf20aca6e4645b1c674
-  data.tar.gz: bae732755cc47dcae17e0d8ef01bcd35173c8941807b2d5844cf45f008f57c199977756d4fd15b0e3c8c558e73432dd9ba88be2b01f61b32cff180308adcd83d
+  metadata.gz: 5d9fea4687d265c36099b30faa69893c10ec011e7d1a8b7e32b4e0df4ef9d892e5efe90bb8bd0767f51f3ec74f91b05dc3613532eeff247f1a2039b6094f15dc
+  data.tar.gz: 2ccb181da62a4ca659c2f3915ffdbebbc88b501c97938244d65d780b241e05bd2f61870ac32cc8a3cef739ac7a36b8c714f2cc5027d9269e78c7e6f6bcabb12c

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

@@ -33,10 +33,6 @@ 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:

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}>"

data/lib/asciidoctor/standoc/basicdoc.rng

@@ -158,17 +158,7 @@
         <data type="ID"/>
       </attribute>
       <oneOrMore>
-        <choice>
-          <ref name="formula"/>
-          <ref name="ul"/>
-          <ref name="ol"/>
-          <ref name="dl"/>
-          <ref name="quote"/>
-          <ref name="sourcecode"/>
-          <ref name="paragraph"/>
-          <ref name="table"/>
-          <ref name="figure"/>
-        </choice>
+        <ref name="paragraph"/>
       </oneOrMore>
     </element>
   </define>
@@ -1028,6 +1018,9 @@
           <value>alphabet_upper</value>
         </choice>
       </attribute>
+      <optional>
+        <attribute name="start"/>
+      </optional>
       <oneOrMore>
         <ref name="li"/>
       </oneOrMore>

data/lib/asciidoctor/standoc/cleanup.rb

@@ -81,12 +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
@@ -146,16 +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_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)

data/lib/asciidoctor/standoc/front_contributor.rb

@@ -22,14 +22,18 @@ module Asciidoctor
       end
 
       def organization(org, orgname)
+        abbrevs = org_abbrev
+        n = abbrevs.invert[orgname] and orgname = n
         org.name orgname
+        a = org_abbrev[orgname] and org.abbreviation a
       end
 
       # , " => ," : CSV definition does not deal with space followed by quote
       # at start of field
       def csv_split(s, delim = ",")
-        CSV.parse_line(s&.gsub(/, "(?!")/, ',"'), liberal_parsing: true,
-                       col_sep: delim)&.map { |x| x.strip }
+        CSV.parse_line(s&.gsub(/, "(?!")/, ',"'),
+                       liberal_parsing: true,
+                       col_sep: delim)&.compact&.map { |x| x.strip }
       end
 
       def metadata_author(node, xml)
@@ -105,6 +109,10 @@ module Asciidoctor
         nil
       end
 
+      def org_abbrev
+        { }
+      end
+
       def metadata_publisher(node, xml)
         publishers = node.attr("publisher") || default_publisher || return
         csv_split(publishers)&.each do |p|

data/lib/asciidoctor/standoc/inline.rb

@@ -33,18 +33,28 @@ module Asciidoctor
       end
 
       def inline_anchor_xref(node)
-        m = /^(?<case>capital%|lowercase%)?(?<fn>fn(:\s*(?<text>.*))?)?$/.match node.text
-        casing = m.nil? ? nil : m[:case]&.sub(/%$/, "")
-        f = (m.nil? || m[:fn].nil?) ? "inline" : "footnote"
-        c = (!m.nil? && (!m[:fn].nil? || !m[:case].nil?)) ? m[:text] : node.text
-        t = node.target.gsub(/^#/, "").gsub(%r{(\.xml|\.adoc)(#.*$)}, "\\2")
         noko do |xml|
-          xml.xref **attr_code(target: t, type: f, case: casing) do |x|
+          attrs = inline_anchor_xref_attrs(node)
+          c = attrs[:text]
+          attrs.delete(:text) unless c.nil?
+          xml.xref **attr_code(attrs) do |x|
             x << c
           end
         end.join
       end
 
+      def inline_anchor_xref_attrs(node)
+        m = /^(?<drop>droploc%)?(?<case>capital%|lowercase%)?(?<drop2>droploc%)?
+          (?<fn>fn(:\s*(?<text>.*))?)?$/x.match node.text
+        casing = m.nil? ? nil : m[:case]&.sub(/%$/, "")
+        droploc = m.nil? ? nil : ((m[:drop].nil? && m[:drop2].nil?) ? nil: true)
+        f = (m.nil? || m[:fn].nil?) ? "inline" : "footnote"
+        c = (!m.nil? && (%i[case fn drop drop2].any? { |x| !m[x].nil? })) ?
+          m[:text] : node.text
+        t = node.target.gsub(/^#/, "").gsub(%r{(\.xml|\.adoc)(#.*$)}, "\\2")
+        { target: t, type: f, case: casing, droploc: droploc, text: c }
+      end
+
       def inline_anchor_link(node)
         contents = node.text
         contents = "" if node.target.gsub(%r{^mailto:}, "") == node.text
@@ -106,40 +116,8 @@ module Asciidoctor
         HTMLEntities.new.encode(text, :basic, :hexadecimal).
           gsub(/&amp;gt;/, ">").gsub(/\&amp;lt;/, "<").gsub(/&amp;amp;/, "&").
           gsub(/&gt;/, ">").gsub(/&lt;/, "<").gsub(/&amp;/, "&").
-          gsub(/&quot;/, '"').gsub(/&#xa;/, "\n")
-      end
-
-=begin
-      def latex_run1(lxm_input, cmd)
-        IO.popen(cmd, "r+", external_encoding: "UTF-8") do |io|
-          io.write(lxm_input)
-          io.close_write
-          io.read
-        end
-      end
-
-      def latex_run(lxm_input)
-        results = nil
-        Metanorma::Standoc::Requirements[:latexml].cmd.each_with_index do |cmd, i|
-          warn "Retrying with #{cmd}" if i > 0
-          results = latex_run1(lxm_input, cmd)
-          if $CHILD_STATUS.to_i.zero?
-            warn "Success!" if i > 0
-            break
-          end
-        end
-        $CHILD_STATUS.to_i.zero? ? results : nil
-      end
-
-      def latex_parse(text)
-        lxm_input = Unicode2LaTeX.unicode2latex(HTMLEntities.new.decode(text))
-        results = latex_run(lxm_input)
-        results.nil? and
-          @log.add('Math', nil,
-                   "latexmlmath failed to process equation:\n#{lxm_input}")
-        results&.sub(%r{<math ([^>]+ )?display="block"}, "<math \\1")
+          gsub(/&quot;/, '"').gsub(/&#xa;/, "\n").gsub(/&amp;#/, "&#")
       end
-=end
 
       def latex_parse(text)
         lxm_input = Unicode2LaTeX.unicode2latex(HTMLEntities.new.decode(text))
@@ -163,7 +141,7 @@ module Asciidoctor
             s.parent.children = math
           end
         else
-          xml.stem text, **{ type: "AsciiMath" }
+          xml.stem text&.gsub(/\&amp;#/, "&#"), **{ type: "AsciiMath" }
         end
       end
 

data/lib/asciidoctor/standoc/isodoc.rng

@@ -64,6 +64,11 @@
             </choice>
           </attribute>
         </optional>
+        <optional>
+          <attribute name="droploc">
+            <data type="boolean"/>
+          </attribute>
+        </optional>
         <text/>
       </element>
     </define>
@@ -859,6 +864,13 @@
   </define>
   <define name="standard-document">
     <element name="standard-document">
+      <attribute name="version"/>
+      <attribute name="type">
+        <choice>
+          <value>semantic</value>
+          <value>presentation</value>
+        </choice>
+      </attribute>
       <ref name="bibdata"/>
       <optional>
         <ref name="boilerplate"/>
@@ -880,7 +892,7 @@
       <oneOrMore>
         <choice>
           <ref name="content"/>
-          <ref name="preface_abstract"/>
+          <ref name="abstract"/>
           <ref name="foreword"/>
           <ref name="introduction"/>
           <ref name="acknowledgements"/>
@@ -1481,11 +1493,6 @@
       </optional>
     </element>
   </define>
-  <define name="preface_abstract">
-    <element name="abstract">
-      <ref name="Basic-Section"/>
-    </element>
-  </define>
   <define name="term-clause">
     <element name="clause">
       <optional>

data/lib/asciidoctor/standoc/json2_text_preprocessor.rb

@@ -36,7 +36,8 @@ module Asciidoctor
       protected
 
       def content_from_file(document, file_path)
-        JSON.parse(File.read(relative_file_path(document, file_path)))
+        JSON.parse(File.read(relative_file_path(document, file_path),
+          encoding: "UTF-8"))
       end
     end
   end

data/lib/asciidoctor/standoc/ref.rb

@@ -42,8 +42,7 @@ module Asciidoctor
 
       def docid(t, code)
         type, code1 = /^\[\d+\]$|^\([^)]+\).*$/.match(code) ?
-          ["metanorma", mn_code(code)] :
-          @bibdb&.docid_type(code) || [nil, code]
+          ["metanorma", mn_code(code)] : @bibdb&.docid_type(code) || [nil, code]
         code1.sub!(/^nofetch\((.+)\)$/, "\\1")
         t.docidentifier **attr_code(type: type) do |d|
           d << code1
@@ -84,6 +83,10 @@ module Asciidoctor
         ref = fetch_ref xml, m[:code], nil, no_year: true, note: m[:fn],
           title: m[:text], usrlbl: m[:usrlbl]
         return use_my_anchor(ref, m[:anchor]) if ref
+        isorefmatches2_1(xml, m)
+      end
+
+      def isorefmatches2_1(xml, m)
         xml.bibitem **attr_code(ref_attributes(m)) do |t|
           isorefrender1(t, m, "--")
           t.date **{ type: "published" } do |d|
@@ -106,13 +109,14 @@ module Asciidoctor
 
       def isorefmatches3(xml, m)
         yr = norm_year(m[:year])
-        #hasyr =  m.names.include?("year") && yr != "--"
         hasyr = !yr.nil? && yr != "--"
-        #noyr =  m.names.include?("year") && yr == "--"
         ref = fetch_ref xml, m[:code], hasyr ? yr : nil, all_parts: true, 
           no_year: yr == "--", text: m[:text], usrlbl: m[:usrlbl]
         return use_my_anchor(ref, m[:anchor]) if ref
+        isorefmatches3_1(xml, m, yr, hasyr, ref)
+      end
 
+      def isorefmatches3_1(xml, m, yr, hasyr, ref)
         xml.bibitem(**attr_code(ref_attributes(m))) do |t|
           isorefrender1(t, m, yr, " (all parts)")
           conditional_date(t, m, yr == "--")
@@ -147,30 +151,24 @@ module Asciidoctor
       end
 
       MALFORMED_REF = "no anchor on reference, markup may be malformed: see "\
-        "https://www.metanorma.com/author/topics/document-format/bibliography/ , "\
-        "https://www.metanorma.com/author/iso/topics/markup/#bibliographies".freeze
+        "https://www.metanorma.com/author/topics/document-format/"\
+        "bibliography/ , https://www.metanorma.com/author/iso/topics/markup/"\
+        "#bibliographies".freeze
 
       def analyse_ref_nofetch(ret)
         return ret unless m = /^nofetch\((?<id>.+)\)$/.match(ret[:id])
-        ret[:id] = m[:id]
-        ret[:nofetch] = true
-        ret
+        ret.merge(id: m[:id], nofetch: true)
       end
 
       def analyse_ref_repo_path(ret)
         return ret unless m =
           /^(?<type>repo|path):\((?<key>[^,]+),(?<id>.+)\)$/.match(ret[:id])
-        ret[:id] = m[:id]
-        ret[:type] = m[:type]
-        ret[:key] = m[:key]
-        ret[:nofetch] = true
-        ret
+        ret.merge(id: m[:id], type: m[:type], key: m[:key], nofetch: true)
       end
 
       def analyse_ref_numeric(ret)
         return ret unless /^\d+$/.match(ret[:id])
-        ret[:numeric] = true
-        ret
+        ret.merge(numeric: true)
       end
 
       # ref id = (usrlbl)code[:-]year
@@ -178,10 +176,7 @@ module Asciidoctor
       def analyse_ref_code(code)
         ret = {id: code}
         return ret if code.nil? || code.empty?
-        ret = analyse_ref_nofetch(ret)
-        ret = analyse_ref_repo_path(ret)
-        ret = analyse_ref_numeric(ret)
-        ret
+        analyse_ref_nofetch(analyse_ref_repo_path(analyse_ref_numeric(ret)))
       end
 
       # TODO: alternative where only title is available
@@ -190,6 +185,10 @@ module Asciidoctor
           @log.add("AsciiDoc Input", node, "#{MALFORMED_REF}: #{item}")
           return
         end
+        refitem1(xml, item, m)
+      end
+
+      def refitem1(xml, item, m)
         code = analyse_ref_code(m[:code])
         unless code[:id] && code[:numeric] || code[:nofetch]
           ref = fetch_ref xml, code[:id],
@@ -214,23 +213,25 @@ module Asciidoctor
         (?<text>.*)$}xm
 
         ISO_REF_NO_YEAR = %r{^<ref\sid="(?<anchor>[^"]+)">
-      \[(?<usrlbl>\([^)]+\))?(?<code>(ISO|IEC)[^0-9]*\s[0-9-]+):(--|\&\#821[12]\;)\]</ref>,?\s*
+      \[(?<usrlbl>\([^)]+\))?(?<code>(ISO|IEC)[^0-9]*\s[0-9-]+):
+      (--|\&\#821[12]\;)\]</ref>,?\s*
         (<fn[^>]*>\s*<p>(?<fn>[^\]]+)</p>\s*</fn>)?,?\s?(?<text>.*)$}xm
 
         ISO_REF_ALL_PARTS = %r{^<ref\sid="(?<anchor>[^"]+)">
-        \[(?<usrlbl>\([^)]+\))?(?<code>(ISO|IEC)[^0-9]*\s[0-9]+)(:(?<year>--|\&\#821[12]\;|[0-9][0-9-]+))?\s
+        \[(?<usrlbl>\([^)]+\))?(?<code>(ISO|IEC)[^0-9]*\s[0-9]+)
+        (:(?<year>--|\&\#821[12]\;|[0-9][0-9-]+))?\s
         \(all\sparts\)\]</ref>,?\s*
           (<fn[^>]*>\s*<p>(?<fn>[^\]]+)</p>\s*</fn>,?\s?)?(?<text>.*)$}xm
 
           NON_ISO_REF = %r{^<ref\sid="(?<anchor>[^"]+)">
-        \[(?<usrlbl>\([^)]+\))?(?<code>[^\]]+?)([:-](?<year>(19|20)[0-9][0-9]))?\]</ref>,?\s*
-          (?<text>.*)$}xm
-
-          def reference1_matches(item)
-            matched = ISO_REF.match item
-            matched2 = ISO_REF_NO_YEAR.match item
-            matched3 = ISO_REF_ALL_PARTS.match item
-            [matched, matched2, matched3]
+        \[(?<usrlbl>\([^)]+\))?(?<code>[^\]]+?)
+        ([:-](?<year>(19|20)[0-9][0-9]))?\]</ref>,?\s*(?<text>.*)$}xm
+
+        def reference1_matches(item)
+          matched = ISO_REF.match item
+          matched2 = ISO_REF_NO_YEAR.match item
+          matched3 = ISO_REF_ALL_PARTS.match item
+          [matched, matched2, matched3]
         end
 
         def reference1(node, item, xml)