metanorma-standoc 1.8.3 → 1.8.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a5a0e8bdc48a2fa268df4c2d2342787a3c1312eb349c0a8a37306c2674c4440e
-  data.tar.gz: e063188d68034654d5edf0d45b51b22b7018371dfeef1b252576b6d3d8fe57b9
+  metadata.gz: d069ef191d60dfccff15d8a39e2c961c343f1e19928e06645c78833be951f052
+  data.tar.gz: 61dff9a129459b4f2b0c4cb426dabd84a822285c8cce41cd88ce20cc4706d3a5
 SHA512:
-  metadata.gz: fd3fe9734d21153f7955dbd3b3eeade50bee97403a6bc53c18ef97cb72345970c7951f9d96b51916f4ce7a89ff56d6c8e6d9cf5b6d67482ed598c2c6ae8090e8
-  data.tar.gz: dbc628d7b0df786191086a908b0f849bb9f75dc23881030748313ed78350d9722675371483232bc52ebd38404ec1da79ee1e985484ae648212479a0b66ac346d
+  metadata.gz: 9a5991f1f7b0262f7b2e3069572d4221f0f944be86a869e9a6bb5bdabe26441305882898788840ef373dfb1671d7c2a8d9d59e1d5942e8d2df6ccc17eee1c114
+  data.tar.gz: 7e9c4dbf9f8d28970756ed8d516df46d5a4c2710754065818c2966de478ed32e1d189d0eec12de1ca5b0b23de5e077f9c4254e738442a7d4a1005e62d6a304d1

data/.rubocop.yml

@@ -5,6 +5,6 @@
 inherit_from:
   - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
 AllCops:
-  TargetRubyVersion: 2.6
+  TargetRubyVersion: 2.4
 Rails:
   Enabled: true

data/lib/asciidoctor/standoc/base.rb

@@ -139,7 +139,7 @@ module Asciidoctor
 
       def document(node)
         init(node)
-        ret = makexml(node).to_xml(indent: 2)
+        ret = makexml(node).to_xml(encoding: "US-ASCII", indent: 2)
         outputs(node, ret) unless node.attr("nodoc") || !node.attr("docfile")
         clean_exit
         ret

data/lib/asciidoctor/standoc/cleanup.rb

@@ -45,7 +45,6 @@ module Asciidoctor
         xref_cleanup(xmldoc)
         concept_cleanup(xmldoc)
         origin_cleanup(xmldoc)
-        svgmap_cleanup(xmldoc)
         termdef_cleanup(xmldoc)
         RelatonIev::iev_cleanup(xmldoc, @bibdb)
         element_name_cleanup(xmldoc)
@@ -59,6 +58,7 @@ module Asciidoctor
         bookmark_cleanup(xmldoc)
         requirement_cleanup(xmldoc)
         bibdata_cleanup(xmldoc)
+        svgmap_cleanup(xmldoc)
         boilerplate_cleanup(xmldoc)
         smartquotes_cleanup(xmldoc)
         variant_cleanup(xmldoc)
@@ -172,7 +172,7 @@ module Asciidoctor
 
       def img_cleanup(xmldoc)
         return xmldoc unless @datauriimage
-        xmldoc.xpath("//image").each { |i| i["src"] = datauri(i["src"]) }
+        xmldoc.xpath("//image").each { |i| i["src"] = Metanorma::Utils::datauri(i["src"], @localdir) }
       end
 
       def variant_cleanup(xmldoc)

data/lib/asciidoctor/standoc/cleanup_boilerplate.rb

@@ -106,7 +106,7 @@ module Asciidoctor
       def bibdata_cleanup(xmldoc)
         bibdata_anchor_cleanup(xmldoc)
         bibdata_docidentifier_cleanup(xmldoc)
-                biblio_indirect_erefs(xmldoc, @internal_eref_namespaces&.uniq)
+        biblio_indirect_erefs(xmldoc, @internal_eref_namespaces&.uniq)
       end
 
       def bibdata_anchor_cleanup(xmldoc)
@@ -124,7 +124,7 @@ module Asciidoctor
         end
       end
 
-       def gather_indirect_erefs(xmldoc, prefix)
+      def gather_indirect_erefs(xmldoc, prefix)
         xmldoc.xpath("//eref[@type = '#{prefix}']").each_with_object({}) do |e, m|
           e.delete("type")
           m[e["bibitemid"]] = true

data/lib/asciidoctor/standoc/cleanup_maths.rb

@@ -2,6 +2,7 @@ require "nokogiri"
 require "pathname"
 require "open-uri"
 require "html2doc"
+require "asciimath2unitsml"
 require_relative "./cleanup_block.rb"
 require_relative "./cleanup_footnotes.rb"
 require_relative "./cleanup_ref.rb"
@@ -73,13 +74,49 @@ module Asciidoctor
         end
       end
 
+      UNITSML_NS = "http://unitsml.nist.gov/2005".freeze
+
+      def add_misc_container(xmldoc)
+        unless ins = xmldoc.at("//misc-container")
+          a = xmldoc.at("//termdocsource") || xmldoc.at("//bibdata")
+          a.next = "<misc-container/>"
+          ins = xmldoc.at("//misc-container")
+        end
+        ins
+      end
+
+      def mathml_unitsML(xmldoc)
+        return unless xmldoc.at(".//m:*", "m" => UNITSML_NS)
+        misc = add_misc_container(xmldoc)
+        unitsml = misc.add_child("<UnitsML xmlns='#{UNITSML_NS}'/>").first
+        %w(Unit CountedItem Quantity Dimension Prefix).each do |t|
+          gather_unitsml(unitsml, xmldoc, t)
+        end
+      end
+
+      def gather_unitsml(unitsml, xmldoc, t)
+        tags = xmldoc.xpath(".//m:#{t}", "m" => UNITSML_NS).each_with_object({}) do |x, m|
+          m[x["id"]] = x.remove
+        end
+        return if tags.empty?
+        set = unitsml.add_child("<#{t}Set/>").first
+        tags.values.each { |v| set << v }
+      end
+
+      def asciimath2unitsml_options
+        { multiplier: :space }
+      end
+
       def mathml_cleanup(xmldoc)
+        unitsml = Asciimath2UnitsML::Conv.new(asciimath2unitsml_options)
         xmldoc.xpath("//stem[@type = 'MathML']").each do |x|
           xml_unescape_mathml(x)
           mathml_namespace(x)
           mathml_preserve_space(x)
           mathml_italicise(x)
+          unitsml.MathML2UnitsML(x)
         end
+        mathml_unitsML(xmldoc)
       end
     end
   end

data/lib/asciidoctor/standoc/cleanup_ref.rb

@@ -50,6 +50,7 @@ module Asciidoctor
       def biblio_renumber(xmldoc)
         i = 0
         xmldoc.xpath("//bibliography//references | //clause//references | //annex//references").each do |r|
+          next if r["normative"] == "true"
           r.xpath("./bibitem").each do |b|
             i += 1
             next unless docid = b.at("./docidentifier[@type = 'metanorma']")
@@ -88,18 +89,8 @@ module Asciidoctor
         end
       end
 
-      def docid_prefix(prefix, docid)
-        docid = "#{prefix} #{docid}" unless omit_docid_prefix(prefix)
-        docid
-      end
-
-      def omit_docid_prefix(prefix)
-        return true if prefix.nil? || prefix.empty?
-        %(ISO IEC IEV ITU metanorma).include? prefix
-      end
-
-      def format_ref(ref, type, isopub)
-        return docid_prefix(type, ref) if isopub
+      def format_ref(ref, type)
+        return @isodoc.docid_prefix(type, ref) if type != "metanorma"
         return "[#{ref}]" if /^\d+$/.match(ref) && !/^\[.*\]$/.match(ref)
         ref
       end
@@ -115,7 +106,7 @@ module Asciidoctor
           isopub = ref.at(ISO_PUBLISHER_XPATH)
           docid = ref.at("./docidentifier[@type = 'metanorma']") ||
             ref.at("./docidentifier[not(@type = 'DOI')]") or next
-          reference = format_ref(docid.text, docid["type"], isopub)
+          reference = format_ref(docid.text, docid["type"])
           @anchors[ref["id"]] = { xref: reference }
         end
       end

data/lib/asciidoctor/standoc/cleanup_section.rb

@@ -62,10 +62,15 @@ module Asciidoctor
         end
       end
 
+      def make_indexsect(x, s)
+        x.xpath("//sections/indexsect").reverse_each { |r| s.next = r.remove }
+      end
+
       def sections_order_cleanup(x)
         s = x.at("//sections")
         make_preface(x, s)
         make_annexes(x)
+        make_indexsect(x, s)
         make_bibliography(x, s)
         x.xpath("//sections/annex").reverse_each { |r| s.next = r.remove }
       end

data/lib/asciidoctor/standoc/inline.rb

@@ -175,25 +175,12 @@ module Asciidoctor
         end.join
       end
 
-      def datauri(uri)
-        return uri if /^data:/.match(uri)
-        types = MIME::Types.type_for(@localdir + uri)
-        type = types ? types.first.to_s : 'text/plain; charset="utf-8"'
-        # FIXME: nested uri path error(
-        #   sources/plantuml/plantuml20200524-90467-1iqek5i.png ->
-        #   sources/sources/plantuml/plantuml20200524-90467-1iqek5i.png)
-        path = File.file?(uri) ? uri : @localdir + uri
-        bin = File.open(path, 'rb', &:read)
-        data = Base64.strict_encode64(bin)
-        "data:#{type};base64,#{data}"
-      end
-
       def image_attributes(node)
         uri = node.image_uri (node.attr("target") || node.target)
-        types = /^data:/.match(uri) ? datauri2mime(uri) : MIME::Types.type_for(uri)
+        types = /^data:/.match(uri) ? Metanorma::Utils::datauri2mime(uri) : MIME::Types.type_for(uri)
         type = types.first.to_s
         uri = uri.sub(%r{^data:image/\*;}, "data:#{type};")
-        attr_code(src: uri, #@datauriimage ? datauri(uri) : uri,
+        attr_code(src: uri, 
                   id: Metanorma::Utils::anchor_or_uuid,
                   mimetype: type,
                   height: node.attr("height") || "auto",

data/lib/asciidoctor/standoc/isodoc.rng

@@ -919,6 +919,9 @@
         </choice>
       </attribute>
       <ref name="bibdata"/>
+      <optional>
+        <ref name="misccontainer"/>
+      </optional>
       <optional>
         <ref name="boilerplate"/>
       </optional>
@@ -929,11 +932,21 @@
       <zeroOrMore>
         <ref name="annex"/>
       </zeroOrMore>
+      <optional>
+        <ref name="bibliography"/>
+      </optional>
       <zeroOrMore>
-        <ref name="references"/>
+        <ref name="indexsect"/>
       </zeroOrMore>
     </element>
   </define>
+  <define name="misccontainer">
+    <element name="misc-container">
+      <oneOrMore>
+        <ref name="AnyElement"/>
+      </oneOrMore>
+    </element>
+  </define>
   <define name="preface">
     <element name="preface">
       <oneOrMore>
@@ -957,6 +970,11 @@
       <ref name="Content-Section"/>
     </element>
   </define>
+  <define name="indexsect">
+    <element name="indexsect">
+      <ref name="Content-Section"/>
+    </element>
+  </define>
   <define name="boilerplate">
     <element name="boilerplate">
       <optional>

data/lib/asciidoctor/standoc/section.rb

@@ -88,6 +88,8 @@ module Asciidoctor
               bibliography_parse(a, xml, node)
             elsif node.attr("style") == "abstract" 
               abstract_parse(a, xml, node)
+            elsif node.attr("style") == "index" 
+              indexsect_parse(a, xml, node)
             elsif node.attr("style") == "appendix" && node.level == 1
               annex_parse(a, xml, node)
             else
@@ -114,6 +116,13 @@ module Asciidoctor
         end.join("\n")
       end
 
+      def indexsect_parse(attrs, xml, node)
+        xml.indexsect **attr_code(attrs) do |xml_section|
+          xml_section.title { |name| name << node.title }
+          xml_section << node.content
+        end
+      end
+
       def abstract_parse(attrs, xml, node)
         xml.abstract **attr_code(attrs) do |xml_section|
           xml_section << node.content

data/lib/asciidoctor/standoc/utils.rb

@@ -5,7 +5,6 @@ require "json"
 require "pathname"
 require "open-uri"
 require "uuidtools"
-require "mimemagic"
 
 module Asciidoctor
   module Standoc
@@ -57,29 +56,6 @@ module Asciidoctor
         end
       end
 
-      def datauri2mime(uri)
-        %r{^data:image/(?<imgtype>[^;]+);base64,(?<imgdata>.+)$} =~ uri
-        type = nil
-        imgtype = "png" unless /^[a-z0-9]+$/.match imgtype
-        Tempfile.open(["imageuri", ".#{imgtype}"]) do |file|
-          type = datauri2mime1(file, imgdata)
-        end
-        [type]
-      end
-
-      def datauri2mime1(file, imgdata)
-        type = nil
-        begin
-          file.binmode
-          file.write(Base64.strict_decode64(imgdata))
-          file.rewind
-          type = MimeMagic.by_magic(file)
-        ensure
-          file.close!
-        end
-        type
-      end
-
       SUBCLAUSE_XPATH = "//clause[not(parent::sections)]"\
         "[not(ancestor::boilerplate)]".freeze
 

data/lib/asciidoctor/standoc/validate.rb

@@ -35,10 +35,25 @@ module Asciidoctor
 
       def content_validate(doc)
         section_validate(doc)
+        norm_ref_validate(doc)
         repeat_id_validate(doc.root)
         iev_validate(doc.root)
       end
 
+      def norm_ref_validate(doc)
+        found = false
+        doc.xpath("//references[@normative = 'true']/bibitem").each do |b|
+          next unless docid = b.at("./docidentifier[@type = 'metanorma']")
+          next unless  /^\[\d+\]$/.match(docid.text)
+          @log.add("Bibliography", b, "Numeric reference in normative references")
+          found = true
+        end
+        if found
+          clean_exit
+          abort("Numeric reference in normative references")
+        end
+      end
+
       def repeat_id_validate1(ids, x)
         if ids[x["id"]]
           @log.add("Anchors", x, "Anchor #{x['id']} has already been used "\
@@ -89,7 +104,7 @@ module Asciidoctor
       def formattedstr_strip(doc)
         doc.xpath("//*[@format] | //stem | //bibdata//description | "\
                   "//formattedref | //bibdata//note | //bibdata/abstract | "\
-                  "//bibitem/abstract | //bibitem/note").each do |n|
+                  "//bibitem/abstract | //bibitem/note | //misc-container").each do |n|
           n.elements.each do |e|
             e.traverse do |e1|
               e1.element? and e1.each { |k, _v| e1.delete(k) }

data/lib/metanorma/standoc/version.rb

@@ -19,6 +19,6 @@ module Metanorma
   end
 
   module Standoc
-    VERSION= "1.8.3".freeze
+    VERSION= "1.8.4".freeze
   end
 end

data/metanorma-standoc.gemspec

@@ -38,9 +38,9 @@ Gem::Specification.new do |spec|
   spec.add_dependency "concurrent-ruby"
   spec.add_dependency "unicode2latex", "~> 0.0.1"
   spec.add_dependency "metanorma-utils", "~> 1.0.2"
-  spec.add_dependency "mimemagic"
   spec.add_dependency "mathml2asciimath"
   spec.add_dependency "latexmath"
+  spec.add_dependency "asciimath2unitsml", "~> 0.1.1"
 
   spec.add_development_dependency "byebug"
   spec.add_development_dependency "sassc", "2.4.0"

data/spec/asciidoctor/cleanup_spec.rb

@@ -2118,6 +2118,120 @@ expect(xmlpp(Asciidoctor.convert(input, backend: :standoc, header_footer: true))
 OUTPUT
 
 end
+
+it "converts UnitsML to MathML" do
+  expect(xmlpp(strip_guid(Asciidoctor.convert(<<~INPUT, backend: :standoc, header_footer: true)))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+= Document title
+Author
+:stem:
+
+[stem]
+++++
+<math xmlns='http://www.w3.org/1998/Math/MathML'>
+  <mrow>
+  <mn>7</mn>
+  <mtext>unitsml(m*kg^-2)</mtext>
+  <mo>+</mo>
+  <mn>8</mn>
+  <mtext>unitsml(m*kg^-2)</mtext>
+  </mrow>
+</math>
+++++
+INPUT
+#{BLANK_HDR}
+<misc-container>
+           <UnitsML xmlns='http://unitsml.nist.gov/2005'>
+             <UnitSet>
+               <Unit xml:id='U_m.kg-2' dimensionURL='#D_LM-2'>
+                 <UnitSystem name='SI' type='SI_derived' xml:lang='en-US'/>
+                 <UnitName xml:lang='en'>m*kg^-2</UnitName>
+                 <UnitSymbol type='HTML'>
+                   m&#160;kg
+                   <sup>&#8722;2</sup>
+                 </UnitSymbol>
+                 <UnitSymbol type='MathML'>
+                   <math xmlns='http://www.w3.org/1998/Math/MathML'>
+                     <mrow>
+                       <mi mathvariant='normal'>m</mi>
+                       <mo rspace='thickmathspace'>&#8290;</mo>
+                       <msup>
+                         <mrow>
+                           <mi mathvariant='normal'>kg</mi>
+                         </mrow>
+                         <mrow>
+                           <mo>&#8722;</mo>
+                           <mn>2</mn>
+                         </mrow>
+                       </msup>
+                     </mrow>
+                   </math>
+                 </UnitSymbol>
+                 <RootUnits>
+                   <EnumeratedRootUnit unit='meter'/>
+                   <EnumeratedRootUnit unit='gram' prefix='k' powerNumerator='-2'/>
+                 </RootUnits>
+               </Unit>
+             </UnitSet>
+             <DimensionSet>
+               <Dimension xml:id='D_LM-2'>
+                 <Length symbol='L' powerNumerator='1'/>
+                 <Mass symbol='M' powerNumerator='-2'/>
+               </Dimension>
+             </DimensionSet>
+             <PrefixSet>
+               <Prefix prefixBase='10' prefixPower='3' xml:id='NISTp10_3'>
+                 <PrefixName xml:lang='en'>kilo</PrefixName>
+                 <PrefixSymbol type='ASCII'>k</PrefixSymbol>
+               </Prefix>
+             </PrefixSet>
+           </UnitsML>
+         </misc-container>
+         <sections>
+           <formula id='_'>
+             <stem type='MathML'>
+               <math xmlns='http://www.w3.org/1998/Math/MathML'>
+                 <mrow>
+                   <mn>7</mn>
+                   <mo rspace='thickmathspace'>&#8290;</mo>
+                   <mrow xref='U_m.kg-2'>
+                     <mi mathvariant='normal'>m</mi>
+                     <mo rspace='thickmathspace'>&#8290;</mo>
+                     <msup>
+                       <mrow>
+                         <mi mathvariant='normal'>kg</mi>
+                       </mrow>
+                       <mrow>
+                         <mo>&#8722;</mo>
+                         <mn>2</mn>
+                       </mrow>
+                     </msup>
+                   </mrow>
+                   <mo>+</mo>
+                   <mn>8</mn>
+                   <mo rspace='thickmathspace'>&#8290;</mo>
+                   <mrow xref='U_m.kg-2'>
+                     <mi mathvariant='normal'>m</mi>
+                     <mo rspace='thickmathspace'>&#8290;</mo>
+                     <msup>
+                       <mrow>
+                         <mi mathvariant='normal'>kg</mi>
+                       </mrow>
+                       <mrow>
+                         <mo>&#8722;</mo>
+                         <mn>2</mn>
+                       </mrow>
+                     </msup>
+                   </mrow>
+                 </mrow>
+               </math>
+             </stem>
+           </formula>
+         </sections>
+       </standard-document>
+OUTPUT
+
+end
+
 it "customises italicisation of MathML" do
 input = <<~INPUT
 = Document title
@@ -2350,14 +2464,17 @@ end
   it "process express_ref macro with no existing bibliography" do
     expect(xmlpp(strip_guid(Asciidoctor.convert(<<~"INPUT", backend: :standoc, header_footer: true, agree_to_terms: true)))).to be_equivalent_to xmlpp(<<~"OUTPUT")
       #{ASCIIDOC_BLANK_HDR}
+      [[B]]
+      [type="express-schema"]
       == Clause
 
       <<express-schema:A:A.B.C,C>>
       <<express-schema:A>>
+      <<express-schema:B>>
     INPUT
        #{BLANK_HDR}
        <sections>
-           <clause id='_' inline-header='false' obligation='normative'>
+           <clause id='B' inline-header='false' obligation='normative' type="express-schema">
              <title>Clause</title>
              <p id='_'>
                <eref bibitemid='express-schema_A' citeas="">
@@ -2367,6 +2484,7 @@ end
                  C
                </eref>
                <eref bibitemid='express-schema_A' citeas=""/>
+               <xref target='B'/>
              </p>
            </clause>
          </sections>