metanorma-standoc 2.0.1 → 2.0.4

data/lib/metanorma/standoc/terms.rb

@@ -92,7 +92,7 @@ module Metanorma
         end
       end
 
-      def term_source_attrs(_node, seen_xref)
+      def termsource_origin_attrs(_node, seen_xref)
         { case: seen_xref.children[0]["case"],
           droploc: seen_xref.children[0]["droploc"],
           bibitemid: seen_xref.children[0]["target"],
@@ -103,7 +103,7 @@ module Metanorma
         if seen_xref.children[0].name == "concept"
           xml_t.origin { |o| o << seen_xref.children[0].to_xml }
         else
-          attrs = term_source_attrs(node, seen_xref)
+          attrs = termsource_origin_attrs(node, seen_xref)
           attrs.delete(:text)
           xml_t.origin **attr_code(attrs) do |o|
             o << seen_xref.children[0].children.to_xml
@@ -135,13 +135,16 @@ module Metanorma
         matched
       end
 
+      def termsource_attrs(node, matched)
+        status = node.attr("status") ||
+          (matched[:text] ? "modified" : "identical")
+        { status: status, type: node.attr("type") || "authoritative" }
+      end
+
       def termsource(node)
-        matched = extract_termsource_refs(node.content, node) || return
+        matched = extract_termsource_refs(node.content, node) or return
         noko do |xml|
-          status = node.attr("status") ||
-            (matched[:text] ? "modified" : "identical")
-          attrs = { status: status, type: node.attr("type") || "authoritative" }
-          xml.termsource **attrs do |xml_t|
+          xml.termsource **termsource_attrs(node, matched) do |xml_t|
             seen_xref = Nokogiri::XML.fragment(matched[:xref])
             add_term_source(node, xml_t, seen_xref, matched)
           end

data/lib/metanorma/standoc/utils.rb

@@ -32,7 +32,9 @@ module Metanorma
         doc = ::Nokogiri::XML.parse(NOKOHEAD)
         fragment = doc.fragment("")
         ::Nokogiri::XML::Builder.with fragment, &block
-        fragment.to_xml(encoding: "US-ASCII", indent: 0).lines.map do |l|
+        fragment.to_xml(encoding: "US-ASCII", indent: 0,
+                        save_with: Nokogiri::XML::Node::SaveOptions::AS_XML)
+          .lines.map do |l|
           l.gsub(/>\n$/, ">").gsub(/\s*\n$/m, " ").gsub("–", "\u0096")
             .gsub("—", "\u0097").gsub("–", "\u0096")
             .gsub("—", "\u0097")

data/lib/metanorma/standoc/validate.rb

@@ -120,20 +120,25 @@ module Metanorma
         end
       end
 
+      SVG_NS = "http://www.w3.org/2000/svg".freeze
+
       # RelaxNG cannot cope well with wildcard attributes. So we strip
       # any attributes from FormattedString instances (which can contain
       # xs:any markup, and are signalled with @format) before validation.
       def formattedstr_strip(doc)
         doc.xpath("//*[@format] | //stem | //bibdata//description | "\
                   "//formattedref | //bibdata//note | //bibdata/abstract | "\
-                  "//bibitem/abstract | //bibitem/note | //misc-container")
-          .each do |n|
+                  "//bibitem/abstract | //bibitem/note | //misc-container",
+                  "m" => SVG_NS).each do |n|
           n.elements.each do |e|
             e.traverse do |e1|
               e1.element? and e1.each { |k, _v| e1.delete(k) }
             end
           end
         end
+        doc.xpath("//m:svg", "m" => SVG_NS).each do |n|
+          n.replace("<svg/>")
+        end
         doc
       end
 

data/lib/metanorma/standoc/version.rb

@@ -19,6 +19,6 @@ module Metanorma
   end
 
   module Standoc
-    VERSION = "2.0.1".freeze
+    VERSION = "2.0.4".freeze
   end
 end

data/spec/assets/a1.adoc

@@ -0,0 +1,8 @@
+= X
+A
+
+== Clause 1
+
+X
+
+embed::spec/assets/a2.adoc[]

data/spec/assets/a2.adoc

@@ -0,0 +1,8 @@
+= X
+A
+
+== Clause 2
+
+X
+
+embed::spec/assets/a3.adoc[]

data/spec/assets/a3.adoc

@@ -0,0 +1,9 @@
+= X
+A
+
+== Clause 3
+
+X
+
+include::spec/assets/a4.adoc[]
+

data/spec/assets/a4.adoc

@@ -0,0 +1,4 @@
+== Clause 4
+
+X
+

data/spec/metanorma/base_spec.rb

@@ -1051,7 +1051,7 @@ QU1FOiB0ZXN0Cgo=
       .new(:standoc, header_footer: true)
       .doc_extract_attributes(node)
 
-    expect(options.dig(:mn2pdf, :font_manifest))
+    expect(options[:font_manifest])
       .to eq(node[Metanorma::Standoc::Base::FONTS_MANIFEST])
   end
 

data/spec/metanorma/cleanup_blocks_spec.rb

@@ -1039,4 +1039,140 @@ RSpec.describe Metanorma::Standoc do
     annotation_id = output.at("//xmlns:annotation/@id").text
     expect(callout_id).to eq(annotation_id)
   end
+  it "deduplicates identifiers in inline SVGs" do
+    input = <<~INPUT
+      #{BLANK_HDR}
+        <sections>
+        <svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 256 256">
+         <defs>
+           <linearGradient id="gradient1">
+             <stop class="stop1" offset="0%" xlink:href="#gradient1"/>
+             <stop class="stop2" offset="100%"/>
+             <style>url(#gradient1)</style>
+           </linearGradient>
+         </defs>
+         <circle fill="url(#gradient1)" cx="128" cy="128" r="100" />
+       </svg>
+               <svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 256 256">
+         <defs>
+           <linearGradient id="gradient2">
+             <stop class="stop1" offset="0%" xlink:href="#gradient2"/>
+             <stop class="stop2" offset="100%"/>
+             <style>url(#gradient2)</style>
+           </linearGradient>
+         </defs>
+         <circle fill="url(#gradient2)" cx="128" cy="128" r="100" />
+       </svg>
+             <svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0 0 256 256">
+         <defs>
+           <linearGradient id="gradient1">
+             <stop class="stop1" offset="0%" xlink:href="#gradient1"/>
+             <stop class="stop2" offset="100%"/>
+             <style>url(#gradient1)</style>
+           </linearGradient>
+         </defs>
+         <circle fill="url(#gradient1)" cx="128" cy="128" r="100" />
+       </svg>
+             </sections>
+      </standard-document>
+    INPUT
+    output = <<~OUTPUT
+      #{BLANK_HDR}
+                 <sections>
+                   <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" viewBox="0 0 256 256">
+         <defs>
+           <linearGradient id="gradient1_inject_0">
+             <stop class="stop1" offset="0%" xlink:href="#gradient1_inject_0"/>
+             <stop class="stop2" offset="100%"/>
+             <style>url(#gradient1_inject_0)</style>
+           </linearGradient>
+         </defs>
+         <circle fill="url(#gradient1_inject_0)" cx="128" cy="128" r="100"/>
+       </svg>
+               <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" viewBox="0 0 256 256">
+         <defs>
+           <linearGradient id="gradient2">
+             <stop class="stop1" offset="0%" xlink:href="#gradient2"/>
+             <stop class="stop2" offset="100%"/>
+             <style>url(#gradient2)</style>
+           </linearGradient>
+         </defs>
+         <circle fill="url(#gradient2)" cx="128" cy="128" r="100"/>
+       </svg>
+             <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" viewBox="0 0 256 256">
+         <defs>
+           <linearGradient id="gradient1_inject_2">
+             <stop class="stop1" offset="0%" xlink:href="#gradient1_inject_2"/>
+             <stop class="stop2" offset="100%"/>
+             <style>url(#gradient1_inject_2)</style>
+           </linearGradient>
+         </defs>
+         <circle fill="url(#gradient1_inject_2)" cx="128" cy="128" r="100"/>
+       </svg>
+             </sections>
+      </standard-document>
+    OUTPUT
+    expect(Metanorma::Standoc::Converter.new(nil, *OPTIONS)
+      .cleanup(Nokogiri::XML(input)).to_xml)
+      .to be_equivalent_to xmlpp(output)
+  end
+
+  it "deduplicates identifiers in embedded SVGs" do
+    input = <<~INPUT
+      #{ASCIIDOC_BLANK_HDR.sub(/:data-uri-image: false/, ':data-uri-image: true')}
+
+      image::spec/fixtures/action_schemaexpg1.svg[]
+
+      image::spec/examples/rice_images/rice_image1.png[]
+
+      image::spec/fixtures/action_schemaexpg1.svg[]
+    INPUT
+
+    output = <<~OUTPUT
+       #{BLANK_HDR}
+                <sections>
+          <figure id='_'>
+            <svg xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' version='1.1' id='Layer_1' x='0px' y='0px' viewBox='0 0 595.28 841.89' style='enable-background:new 0 0 595.28 841.89;' xml:space='preserve'>
+              <style/>
+              <image/>
+              <a xlink:href='mn://action_schema'>
+                <rect x='123.28' y='273.93' class='st0' width='88.05' height='41.84'/>
+              </a>
+              <a xlink:href='mn://basic_attribute_schema'>
+                <rect x='324.69' y='450.52' class='st0' width='132.62' height='40.75'/>
+              </a>
+              <a xlink:href='mn://support_resource_schema'>
+                <rect x='324.69' y='528.36' class='st0' width='148.16' height='40.75'/>
+              </a>
+            </svg>
+          </figure>
+          <figure id='_'>
+              <image/>
+          </figure>
+          <figure id='_'>
+            <svg xmlns='http://www.w3.org/2000/svg' xmlns:xlink='http://www.w3.org/1999/xlink' version='1.1' id='Layer_1_inject_1' x='0px' y='0px' viewBox='0 0 595.28 841.89' style='enable-background:new 0 0 595.28 841.89;' xml:space='preserve'>
+              <style/>
+              <image/>
+              <a xlink:href='mn://action_schema'>
+                <rect x='123.28' y='273.93' class='st0' width='88.05' height='41.84'/>
+              </a>
+              <a xlink:href='mn://basic_attribute_schema'>
+                <rect x='324.69' y='450.52' class='st0' width='132.62' height='40.75'/>
+              </a>
+              <a xlink:href='mn://support_resource_schema'>
+                <rect x='324.69' y='528.36' class='st0' width='148.16' height='40.75'/>
+              </a>
+            </svg>
+          </figure>
+        </sections>
+      </standard-document>
+    OUTPUT
+    xml = Nokogiri::XML(Asciidoctor.convert(input, *OPTIONS))
+    xml.xpath("//*[local-name() = 'image']").each do |x|
+      x.replace("<image/>")
+    end
+    expect(xmlpp(strip_guid(xml.to_xml)
+      .gsub(%r{<style.*?</style>}m, "<style/>")))
+      .to be_equivalent_to xmlpp(output)
+  end
 end

data/spec/metanorma/cleanup_spec.rb

@@ -282,7 +282,7 @@ RSpec.describe Metanorma::Standoc do
               </localityStack>
               the reference,xyz</eref>
        <eref type='inline' bibitemid='iso216' citeas='ISO 216'>
-         <localityStack>
+         <localityStack connective="and">
            <locality type='whole'/>
            <locality type='clause'>
              <referenceFrom>3</referenceFrom>
@@ -298,7 +298,7 @@ RSpec.describe Metanorma::Standoc do
            <referenceFrom>the reference</referenceFrom>
            </locality>
          </localityStack>
-         <localityStack>
+         <localityStack connective="and">
            <locality type='whole'/>
            <locality type='clause'>
              <referenceFrom>3</referenceFrom>
@@ -585,7 +585,7 @@ RSpec.describe Metanorma::Standoc do
           <title type='main' format='text/plain' language='en' script='Latn'>International Electrotechnical Vocabulary (IEV) — Part 102: Mathematics — General concepts and linear algebra</title>
           <uri type="src">https://webstore.iec.ch/publication/160</uri>
           <uri type="obp">/preview/info_iec60050-102%7Bed1.0%7Db.pdf</uri>
-          <docidentifier type="IEC">IEC 60050-102:2007</docidentifier>
+          <docidentifier type="IEC" primary="true">IEC 60050-102:2007</docidentifier>
           <docidentifier type='URN'>urn:iec:std:iec:60050-102:2007:::en</docidentifier>
           <date type="published">
             <on>2007-08-27</on>
@@ -624,7 +624,7 @@ RSpec.describe Metanorma::Standoc do
           <title type="main" format="text/plain" language="en" script="Latn">International Electrotechnical Vocabulary (IEV) — Part 103: Mathematics — Functions</title>
           <uri type="src">https://webstore.iec.ch/publication/161</uri>
           <uri type="obp">/preview/info_iec60050-103%7Bed1.0%7Db.pdf</uri>
-          <docidentifier type="IEC">IEC 60050-103:2009</docidentifier>
+          <docidentifier type="IEC" primary="true">IEC 60050-103:2009</docidentifier>
           <docidentifier type='URN'>urn:iec:std:iec:60050-103:2009:::en</docidentifier>
           <date type="published">
             <on>2009-12-14</on>
@@ -1116,7 +1116,7 @@ RSpec.describe Metanorma::Standoc do
       <dd>
         <p id='_'>Definition 7</p>
       </dd>
-      <dt id="symbol-_-n-">
+      <dt id="symbol-n">
         <stem type='MathML'>
           <math xmlns='http://www.w3.org/1998/Math/MathML'>
             <mi>n</mi>
@@ -1178,7 +1178,7 @@ RSpec.describe Metanorma::Standoc do
               <dd>
                 <p id='_'>Definition 5</p>
               </dd>
-              <dt  id='symbol-_-xm-'><stem type='MathML'>
+              <dt  id='symbol-x-m'><stem type='MathML'>
               <math xmlns='http://www.w3.org/1998/Math/MathML'>
         <msub>
           <mrow>
@@ -1193,7 +1193,7 @@ RSpec.describe Metanorma::Standoc do
               <dd>
                 <p id='_'>Definition 4</p>
               </dd>
-              <dt  id='symbol-_-x1-'><stem type='MathML'>
+              <dt  id='symbol-x-1'><stem type='MathML'>
                <math xmlns='http://www.w3.org/1998/Math/MathML'>
          <msub>
            <mrow>
@@ -1212,7 +1212,7 @@ RSpec.describe Metanorma::Standoc do
               <dd>
                 <p id='_'>Definition 2</p>
               </dd>
-              <dt  id='symbol-_-__x3b1_-'>
+              <dt  id='symbol-__x3b1_'>
               <stem type='MathML'>
         <math xmlns='http://www.w3.org/1998/Math/MathML'>
           <mi>α</mi>
@@ -1288,7 +1288,7 @@ RSpec.describe Metanorma::Standoc do
              <sourcecode id='L__xf6_we'>
                <name>
                  See
-                 <eref type='inline' bibitemid='L__xf6_wner2016' citeas='L&#246;wner et al. 2016'/>
+                 <eref type='inline' bibitemid='L__xf6_wner2016' citeas='L&amp;#xf6;wner et al. 2016'/>
                </name>
                ABC
              </sourcecode>
@@ -1829,13 +1829,13 @@ RSpec.describe Metanorma::Standoc do
            </ext>
          </bibdata>
          <preface>
-           <note id='_f91b621e-d8cb-30bf-eef6-7d0150204829'>
+           <note id='_2cfe95f6-7ad6-aa57-8207-6f7d7928aa8e'>
              <p id='_76d95913-a379-c60f-5144-1f09655cafa6'>
                Note which is very important
                <xref target='_76d95913-a379-c60f-5144-1f09655cafa6'/>
              </p>
            </note>
-           <foreword id='_0826616f-13a4-0634-baee-5003c5534175' obligation='informative'>
+           <foreword id='_96b556cb-657c-985b-351b-ed70d8bd6fdd' obligation='informative'>
              <title>Foreword</title>
              <p id='_d2f825bf-3e18-6143-8777-34e59928d48c'>Foreword</p>
            </foreword>
@@ -1845,7 +1845,7 @@ RSpec.describe Metanorma::Standoc do
            </introduction>
          </preface>
          <sections>
-           <admonition id='_068def71-3ec8-0395-8853-0e2d3ef5b841' type='important'>
+           <admonition id='_6abb9105-854c-e79c-c351-73a56d6ca81f' type='important'>
              <p id='_69ec375e-c992-5be3-76dd-a2311f9bb6cc'>Notice which is very important</p>
            </admonition>
            <clause id='_scope' type='scope' inline-header='false' obligation='normative'>
@@ -1858,7 +1858,7 @@ RSpec.describe Metanorma::Standoc do
     input1 = xmlpp(Asciidoctor.convert(input, *OPTIONS))
       .sub(/<p id='([^']+)'>(\s+)Note which is very important(\s+)<xref target='a'/,
            "<p id='\\1'>\\2Note which is very important\\3<xref target='\\1'")
-    expect(input1)
+    expect(xmlpp(input1))
       .to be_equivalent_to xmlpp(output)
   end
 

data/spec/metanorma/cleanup_terms_spec.rb

@@ -728,7 +728,7 @@ RSpec.describe Metanorma::Standoc do
           <terms id='_' obligation='normative'>
             <title>Terms and definitions</title>
             <p id='_'>For the purposes of this document, the following terms and definitions apply.</p>
-            <term id='term-_-t90-'>
+            <term id='term-t90'>
               <preferred>
                 <letter-symbol>
                   <name>

data/spec/metanorma/inline_spec.rb

@@ -444,6 +444,37 @@ RSpec.describe Metanorma::Standoc do
       .to be_equivalent_to(output)
   end
 
+  it "processes combinations of crossreferences" do
+    input = <<~INPUT
+      #{ASCIIDOC_BLANK_HDR}
+      == Section
+
+      <<ref1;to!ref2>>
+      <<from!ref1;to!ref2,text>>
+      <<ref1;ref2>>
+      <<ref1;and!ref2>>
+      <<ref1;or!ref2,text>>
+      <<from!ref1;to!ref2;and!ref3;to!ref4>>
+    INPUT
+    output = <<~OUTPUT
+      #{BLANK_HDR}
+       <sections>
+       <clause id="_" inline-header="false" obligation="normative">
+       <title>Section</title>
+       <p id="_"><xref target="ref1"><location target="ref1" connective="from"/><location target="ref2" connective="to"/></xref>
+       <xref target="ref1"><location target="ref1" connective="from"/><location target="ref2" connective="to"/>text</xref>
+       <xref target="ref1"><location target="ref1" connective="and"/><location target="ref2" connective="and"/></xref>
+       <xref target="ref1"><location target="ref1" connective="and"/><location target="ref2" connective="and"/></xref>
+       <xref target="ref1"><location target="ref1" connective="and"/><location target="ref2" connective="or"/>text</xref>
+       <xref target="ref1"><location target="ref1" connective="from"/><location target="ref2" connective="to"/><location target="ref3" connective="and"/><location target="ref4" connective="to"/></xref></p>
+       </clause>
+       </sections>
+       </standard-document>
+    OUTPUT
+    expect((strip_guid(Asciidoctor.convert(input, *OPTIONS))))
+      .to be_equivalent_to(output)
+  end
+
   it "processes bibliographic anchors" do
     input = <<~INPUT
       #{ASCIIDOC_BLANK_HDR}

data/spec/metanorma/isobib_cache_spec.rb

@@ -49,7 +49,7 @@ ISO_124_DATED = <<~XML.freeze
          <uri type="src">https://www.iso.org/standard/61884.html</uri>
          <uri type="obp">https://www.iso.org/obp/ui/#!iso:std:61884:en</uri>
          <uri type="rss">https://www.iso.org/contents/data/standard/06/18/61884.detail.rss</uri>
-         <docidentifier type="ISO">ISO 124:2014</docidentifier>
+         <docidentifier type="ISO" primary="true">ISO 124:2014</docidentifier>
          <docidentifier type='URN'>urn:iso:std:iso:124:stage-90.93:ed-7:en</docidentifier>
          <docnumber>124</docnumber>
          <date type="published">
@@ -208,7 +208,7 @@ ISO_123_DATED = <<~XML.freeze
            <uri type="src">https://www.iso.org/standard/23281.html</uri>
            <uri type="obp">https://www.iso.org/obp/ui/#!iso:std:23281:en</uri>
            <uri type="rss">https://www.iso.org/contents/data/standard/02/32/23281.detail.rss</uri>
-           <docidentifier type="ISO">ISO 123:2001</docidentifier>
+           <docidentifier type="ISO" primary="true">ISO 123:2001</docidentifier>
            <docidentifier type='URN'>urn:iso:std:iso:123:stage-90.93:ed-3:en</docidentifier>
            <docnumber>123</docnumber>
            <date type="published">

data/spec/metanorma/macros_plantuml_spec.rb

@@ -129,51 +129,50 @@ RSpec.describe Metanorma::Standoc do
       expect(
         xmlpp(
           strip_guid(Asciidoctor.convert(input, *OPTIONS))
-                      .gsub(%r{".+spec/assets/lutaml/[^./]+\.},
-                            '"spec/assets/_.'),
+                      .gsub(%r{"[^".]+spec/assets/lutaml/[^./"]+\.png},
+                            '"spec/assets/_.png'),
         ),
-      )
-        .to(be_equivalent_to(xmlpp(output)))
+      ).to(be_equivalent_to(xmlpp(output)))
     end
+  end
 
-    context "when inline macro, path supplied as the second arg" do
-      let(:example_file) { fixtures_path("diagram_definitions.lutaml") }
-      let(:input) do
-        <<~TEXT
-          = Document title
-          Author
-          :docfile: test.adoc
-          :nodoc:
-          :novalid:
-          :no-isobib:
-          :imagesdir: spec/assets
-          :data-uri-image: false
-
-          lutaml_diagram::#{example_file}[]
-
-        TEXT
-      end
-      let(:output) do
-        <<~TEXT
-          #{BLANK_HDR}
-          <sections>
-          <figure id="_">
-          <image src="spec/assets/_.png" id="_" mimetype="image/png" height="auto" width="auto"/>
-          </figure>
-          </sections>
-          </standard-document>
-        TEXT
-      end
-
-      it "correctly renders input" do
-        expect(
-          xmlpp(
-            strip_guid(Asciidoctor.convert(input, *OPTIONS))
-                        .gsub(%r{".+spec/assets/lutaml/[^./]+\.},
-                              '"spec/assets/_.'),
-          ),
-        ).to(be_equivalent_to(xmlpp(output)))
-      end
+  context "when inline macro, path supplied as the second arg" do
+    let(:example_file) { fixtures_path("diagram_definitions.lutaml") }
+    let(:input) do
+      <<~TEXT
+        = Document title
+        Author
+        :docfile: test.adoc
+        :nodoc:
+        :novalid:
+        :no-isobib:
+        :imagesdir: spec/assets
+        :data-uri-image: false
+
+        lutaml_diagram::#{example_file}[]
+
+      TEXT
+    end
+    let(:output) do
+      <<~TEXT
+        #{BLANK_HDR}
+        <sections>
+        <figure id="_">
+        <image src="spec/assets/_.png" id="_" mimetype="image/png" height="auto" width="auto"/>
+        </figure>
+        </sections>
+        </standard-document>
+      TEXT
+    end
+
+    it "correctly renders input" do
+      expect(
+        xmlpp(
+          strip_guid(Asciidoctor.convert(input, *OPTIONS))
+                      .gsub(%r{"[^".]+spec/assets/lutaml/[^./"]+\.png},
+                            '"spec/assets/_.png'),
+        ),
+      ).to(be_equivalent_to(xmlpp(output)))
     end
   end