metanorma-standoc 1.5.1 → 1.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2b4ec9dd5050345506b6b416eaad6b57865cb3c0b9e57e00e3b52f625fe87a48
-  data.tar.gz: 4e53f6a44684a9694104f74c7560040893a47c70c5c8292810e9349a32c1e151
+  metadata.gz: 910ada4e6d4f62c6106391e3ec0de46a7ba4a9d5362bb103cd80ee0b2acef9dc
+  data.tar.gz: de8546c035da0236faa4a6ca5df9b0f54f16806d09386793f359e55b69884212
 SHA512:
-  metadata.gz: 8d437d0619e0da4931009f2f92db0778bdd0eccb9bd15f81a7e38edc66a89474cecaa4099bd55bf8178a13a9551d533378068730231e2ed13d2ead794da7cb3a
-  data.tar.gz: c5a606e3c94a341a6ce19bf5e77df8bf49eeae5d68cf6143d7050190a29f7213a34d74ab7743b87f54d7766fd17606cfb05f05b51a63f7a85ae113b9a23e98fd
+  metadata.gz: 422e64b66f95fa4c49727687c446bd3f79bc09aa0609b352bd68cc659ff06bf57243ed410e4baa8f0cb501f101212d305a756b41548fcee7e877135aea22e1f3
+  data.tar.gz: 97d6e164975997ecc396376abdaf2edad43c1f4fbfa601dbbc5f2f4d465747164350f500aaadc05f9fd6ed1e499925df7d74626fcde21a0578feeb50d607b84e

data/lib/asciidoctor/standoc/base.rb

@@ -170,7 +170,7 @@ module Asciidoctor
       end
 
       def doctype(node)
-        node.attr("doctype")
+        node.attr("doctype")&.gsub(/\s+/, "-")&.downcase
       end
 
       def front(node, xml)

data/lib/asciidoctor/standoc/cleanup.rb

@@ -71,6 +71,7 @@ module Asciidoctor
         para_cleanup(xmldoc)
         empty_element_cleanup(xmldoc)
         img_cleanup(xmldoc)
+        anchor_cleanup(xmldoc)
         xmldoc
       end
 

data/lib/asciidoctor/standoc/cleanup_inline.rb

@@ -117,7 +117,8 @@ 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 +130,61 @@ 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)
+        ret = ret1 + s[1..-1].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

@@ -203,7 +203,9 @@ 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

data/lib/asciidoctor/standoc/cleanup_section.rb

@@ -141,12 +141,29 @@ module Asciidoctor
       end
 
       def clausebefore_cleanup(xmldoc)
+        preface_clausebefore_cleanup(xmldoc)
+        sections_clausebefore_cleanup(xmldoc)
+      end
+
+       def preface_clausebefore_cleanup(xmldoc)
+        return unless xmldoc.at("//preface")
+        unless ins = xmldoc.at("//preface").children.first
+          xmldoc.at("//preface") << " "
+          ins = xmldoc.at("//preface").children.first
+        end
+        xmldoc.xpath("//preface//*[@beforeclauses = 'true']").each do |x|
+          x.delete("beforeclauses")
+          ins.previous = x.remove
+        end
+      end
+
+      def sections_clausebefore_cleanup(xmldoc)
         return unless xmldoc.at("//sections")
         unless ins = xmldoc.at("//sections").children.first
           xmldoc.at("//sections") << " "
           ins = xmldoc.at("//sections").children.first
         end
-        xmldoc.xpath("//*[@beforeclauses = 'true']").each do |x|
+        xmldoc.xpath("//sections//*[@beforeclauses = 'true']").each do |x|
           x.delete("beforeclauses")
           ins.previous = x.remove
         end

data/lib/asciidoctor/standoc/cleanup_terms.rb

@@ -110,8 +110,8 @@ module Asciidoctor
         end
         ret = Nokogiri::XML(key.to_xml)
         HTMLEntities.new.decode(ret.text).
-          gsub(/[\[\]\{\}<>\(\)]/, "").strip.
-          gsub(/[[:punct]]|[_^]/, ":\\0").gsub(/`/, "").
+          gsub(/[\[\]\{\}<>\(\)]/, "").gsub(/\s/m, "").
+          gsub(/[[:punct:]]|[_^]/, ":\\0").gsub(/`/, "").
           gsub(/[0-9]+/, "þ\\0")
       end
         

data/lib/asciidoctor/standoc/isodoc.rng

@@ -42,8 +42,11 @@
     </define>
     <define name="xref">
       <element name="xref">
+        <!-- attribute target { xsd:IDREF }, -->
         <attribute name="target">
-          <data type="IDREF"/>
+          <data type="string">
+            <param name="pattern">\i\c*|\c+#\c+</param>
+          </data>
         </attribute>
         <optional>
           <attribute name="type">

data/lib/asciidoctor/standoc/log.rb

@@ -8,7 +8,8 @@ module Asciidoctor
       def add(category, loc, msg)
         return if @novalid
         @log[category] = [] unless @log[category]
-        @log[category] << { location: current_location(loc), message: msg }
+        @log[category] << { location: current_location(loc), message: msg,
+                            context: context(loc) }
         loc = loc.nil? ? "" : "(#{current_location(loc)}): "
         warn "#{category}: #{loc}#{msg}" 
       end
@@ -31,6 +32,13 @@ module Asciidoctor
         "??"
       end
 
+      def context(n)
+        return nil if n.is_a? String
+        n.respond_to?(:to_xml) and return n.to_xml
+        n.respond_to?(:to_s) and return n.to_s
+        nil
+      end
+
       def write(file)
         File.open(file, "w:UTF-8") do |f|
           f.puts "#{file} errors"
@@ -41,6 +49,7 @@ module Asciidoctor
             end.each do |n|
               loc = n[:location] ? "(#{n[:location]}): " : ""
               f.puts "#{loc}#{n[:message]}" 
+              n[:context]&.split(/\n/)&.first(5)&.each { |l| f.puts "\t#{l}" }
             end
           end
         end

data/lib/asciidoctor/standoc/utils.rb

@@ -128,7 +128,8 @@ module Asciidoctor
         ::Nokogiri::XML::Builder.with fragment, &block
         fragment.to_xml(encoding: "US-ASCII", indent: 0).lines.map do |l|
           l.gsub(/>\n$/, ">").gsub(/\s*\n$/m, " ").gsub("–", "\u0096").
-            gsub("—", "\u0097")
+            gsub("—", "\u0097").gsub("–", "\u0096").
+            gsub("—", "\u0097")
         end
       end
 

data/lib/asciidoctor/standoc/validate.rb

@@ -8,7 +8,8 @@ module Asciidoctor
   module Standoc
     module Validate
 
-      SOURCELOCALITY = "./termsource/origin//locality[@type = 'clause']/referenceFrom".freeze
+      SOURCELOCALITY = "./termsource/origin//locality[@type = 'clause']/"\
+        "referenceFrom".freeze
 
       def init_iev
         return nil if @no_isobib
@@ -19,13 +20,16 @@ module Asciidoctor
 
       def iev_validate(xmldoc)
         xmldoc.xpath("//term").each do |t|
-          /^IEC 60050-/.match(t&.at("./termsource/origin/@citeas")&.text) or next
-          pref = t.xpath("./preferred").inject([]) { |m, x| m << x&.text&.downcase }
-          locality = t.xpath(SOURCELOCALITY)&.text or next
+          /^IEC 60050-/.match(t&.at("./termsource/origin/@citeas")&.text) &&
+            loc = t.xpath(SOURCELOCALITY)&.text or next
           @iev = init_iev or return
-          iev = @iev.fetch(locality, xmldoc&.at("//language")&.text || "en") or next
+          iev = @iev.fetch(loc, xmldoc&.at("//language")&.text || "en") or next
+          pref = t.xpath("./preferred").inject([]) do |m, x|
+            m << x&.text&.downcase
+          end
           pref.include?(iev.downcase) or
-          @log.add("Bibliography", t, %(Term "#{pref[0]}" does not match IEV #{locality} "#{iev}"))
+            @log.add("Bibliography", t, %(Term "#{pref[0]}" does not match ) +
+                     %(IEV #{loc} "#{iev}"))
         end
       end
 
@@ -35,20 +39,26 @@ module Asciidoctor
         iev_validate(doc.root)
       end
 
+      def repeat_id_validate1(ids, x)
+        if ids[x["id"]]
+          @log.add("Anchors", x, "Anchor #{x['id']} has already been used "\
+                   "at line #{ids[x['id']]}")
+          raise StandardError.new "Error: multiple instances of same ID"
+        else
+          ids[x["id"]] = x.line
+        end
+        ids
+      end
+
       def repeat_id_validate(doc)
         ids = {}
-        crash = false
-        doc.xpath("//*[@id]").each do |x|
-          if ids[x["id"]]
-            @log.add("Anchors", x, "Anchor #{x['id']} has already been used at line #{ids[x['id']]}")
-            crash = true
-          else
-            ids[x["id"]] = x.line
+        begin
+          doc.xpath("//*[@id]").each do |x|
+            ids = repeat_id_validate1(ids, x)
           end
-        end
-        if crash
+        rescue StandardError => e
           clean_exit
-          abort("Cannot deal with multiple instances of same ID")
+          abort(e.message)
         end
       end
 
@@ -59,8 +69,10 @@ module Asciidoctor
             f.close
             errors = Jing.new(schema).validate(f.path)
             warn "Syntax Valid!" if errors.none?
-            errors.each do |error|
-              @log.add("Syntax", "XML Line #{"%06d" % error[:line]}:#{error[:column]}", error[:message])
+            errors.each do |e|
+              @log.add("Metanorma XML Syntax",
+                       "XML Line #{"%06d" % e[:line]}:#{e[:column]}",
+                       e[:message])
             end
           rescue Jing::Error => e
             clean_exit

data/lib/asciidoctor/standoc/validate_section.rb

@@ -22,7 +22,7 @@ module Asciidoctor
       def style_warning(node, msg, text = nil)
         w = msg
         w += ": #{text}" if text
-        @log.add("Style Warning", node, w)
+        @log.add("Metanorma XML Style Warning", node, w)
       end
 
       def asset_title_style(root)

data/lib/metanorma/standoc/version.rb

@@ -1,5 +1,5 @@
 module Metanorma
   module Standoc
-   VERSION = "1.5.1".freeze
+   VERSION = "1.5.2".freeze
   end
 end

data/metanorma-standoc.gemspec

@@ -30,7 +30,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "ruby-jing"
   spec.add_dependency "isodoc", "~> 1.2.0"
   spec.add_dependency "iev", "~> 0.2.1"
-  spec.add_dependency "relaton", "~> 1.2.0"
+  spec.add_dependency "relaton", "~> 1.3.0"
   spec.add_dependency "relaton-iev", "~> 1.0.0"
   spec.add_dependency "sterile", "~> 1.0.14"
   spec.add_dependency "concurrent-ruby"

data/spec/asciidoctor-standoc/base_spec.rb

@@ -327,6 +327,7 @@ RSpec.describe Asciidoctor::Standoc do
       :doc-uri: E
       :relaton-uri: F
       :title-eo: Dokumenttitolo
+      :doctype: This is a DocType
 
       [abstract]
       == Abstract
@@ -422,7 +423,7 @@ RSpec.describe Asciidoctor::Standoc do
            </owner>
          </copyright>
          <ext>
-         <doctype>article</doctype>
+         <doctype>this-is-a-doctype</doctype>
          </ext>
        </bibdata>
          <preface>

data/spec/asciidoctor-standoc/blocks_spec.rb

@@ -1255,7 +1255,14 @@ RSpec.describe Asciidoctor::Standoc do
         <description><p id="_">I recommend <em>this</em>.</p>
        </description><specification exclude="false" type="tabular" keep-with-next="true" keep-lines-together="true"><p id="_">This is the object of the recommendation:</p><table id="_">  <tbody>    <tr>      <td align="left">Object</td>      <td align="left">Value</td>    </tr>    <tr>      <td align="left">Mission</td>      <td align="left">Accomplished</td>    </tr>  </tbody></table></specification><description>
        <p id="_">As for the measurement targets,</p>
-       </description><measurement-target exclude="false"><p id="_">The measurement target shall be measured as:</p><formula id="_">  <stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><mfrac><mi>r</mi><mn>1</mn></mfrac><mo>=</mo><mn>0</mn></math></stem></formula></measurement-target>
+       </description><measurement-target exclude="false"><p id="_">The measurement target shall be measured as:</p><formula id="_">  <stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><mfrac>
+       <mrow>
+  <mi>r</mi>
+</mrow>
+<mrow>
+  <mn>1</mn>
+</mrow>
+</mfrac><mo>=</mo><mn>0</mn></math></stem></formula></measurement-target>
        <verification exclude="false"><p id="_">The following code will be run for verification:</p><sourcecode  lang="CoreRoot" id="_">CoreRoot(success): HttpResponse
 if (success)
   recommendation(label: success-response)

data/spec/asciidoctor-standoc/cleanup_spec.rb

@@ -158,7 +158,21 @@ RSpec.describe Asciidoctor::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="_"><preferred><stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub><mi>t</mi><mn>90</mn></msub></math></stem></preferred><admitted><stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub><mi>t</mi><mn>91</mn></msub></math></stem></admitted>
+         <term id="_"><preferred><stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub>
+         <mrow>
+  <mi>t</mi>
+</mrow>
+<mrow>
+  <mn>90</mn>
+</mrow>
+</msub></math></stem></preferred><admitted><stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub>
+<mrow>
+  <mi>t</mi>
+</mrow>
+<mrow>
+  <mn>91</mn>
+</mrow>
+</msub></math></stem></admitted>
        <definition><p id="_">Time</p></definition></term>
        </terms>
        </sections>
@@ -229,8 +243,22 @@ RSpec.describe Asciidoctor::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="_"><preferred><stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub><mi>t</mi><mn>90</mn></msub></math></stem></preferred><definition><formula id="_"> 
-         <stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub><mi>t</mi><mi>A</mi></msub></math></stem> 
+         <term id="_"><preferred><stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub>
+          <mrow>
+   <mi>t</mi>
+ </mrow>
+ <mrow>
+   <mn>90</mn>
+ </mrow>
+</msub></math></stem></preferred><definition><formula id="_"> 
+         <stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><msub>
+         <mrow>
+  <mi>t</mi>
+</mrow>
+<mrow>
+  <mi>A</mi>
+</mrow>
+</msub></math></stem> 
        </formula>
        <p id="_">This paragraph is extraneous</p></definition>
        </term>
@@ -1359,7 +1387,14 @@ end
        #{BLANK_HDR}
        <sections>
          <p id="_">
-         <stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><mfrac><mn>1</mn><mi>r</mi></mfrac></math></stem>
+         <stem type="MathML"><math xmlns="http://www.w3.org/1998/Math/MathML"><mfrac>
+<mrow>
+  <mn>1</mn>
+</mrow>
+<mrow>
+  <mi>r</mi>
+</mrow>
+</mfrac></math></stem>
        </p>
        </sections>
        </standard-document>
@@ -1669,12 +1704,28 @@ it "sorts symbols lists" do
   x_1_:: Definition 3
   x_m_:: Definition 4
   x:: Definition 5
+  stem:[n]:: Definition 6
+  m:: Definition 7
   INPUT
   #{BLANK_HDR}
   <sections>
     <definitions id='L' obligation="normative">
       <title>Symbols and abbreviated terms</title>
       <dl id='_'>
+      <dt>m</dt>
+<dd>
+  <p id='_'>Definition 7</p>
+</dd>
+<dt>
+  <stem type='MathML'>
+    <math xmlns='http://www.w3.org/1998/Math/MathML'>
+      <mi>n</mi>
+    </math>
+  </stem>
+</dt>
+<dd>
+  <p id='_'>Definition 6</p>
+</dd>
         <dt>x</dt>
         <dd>
           <p id='_'>Definition 5</p>
@@ -1727,8 +1778,12 @@ it "sorts symbols lists" do
         <dt><stem type='MathML'>
         <math xmlns='http://www.w3.org/1998/Math/MathML'>
   <msub>
-    <mi>x</mi>
-    <mi>m</mi>
+    <mrow>
+  <mi>x</mi>
+</mrow>
+<mrow>
+  <mi>m</mi>
+</mrow>
   </msub>
 </math>
         </stem></dt>
@@ -1738,8 +1793,12 @@ it "sorts symbols lists" do
         <dt><stem type='MathML'>
          <math xmlns='http://www.w3.org/1998/Math/MathML'>
    <msub>
-     <mi>x</mi>
-     <mn>1</mn>
+     <mrow>
+  <mi>x</mi>
+</mrow>
+<mrow>
+  <mn>1</mn>
+</mrow>
    </msub>
  </math>
         </stem></dt>
@@ -1872,6 +1931,9 @@ it "moves %beforeclause admonitions to right position" do
 INPUT
   #{BLANK_HDR}
   <preface>
+    <note id='_'>
+      <p id='_'>Note which is very important</p>
+    </note>
     <foreword id='_' obligation='informative'>
       <title>Foreword</title>
       <p id='_'>Foreword</p>
@@ -1882,9 +1944,6 @@ INPUT
     </introduction>
   </preface>
   <sections>
-    <note id='_'>
-      <p id='_'>Note which is very important</p>
-    </note>
     <admonition id='_' type='important'>
       <p id='_'>Notice which is very important</p>
     </admonition>
@@ -3102,6 +3161,57 @@ INPUT
 OUTPUT
 end
 
+it "fixes illegal anchors" do
+input = <<~INPUT
+#{ASCIIDOC_BLANK_HDR}
+
+[[a:b]]
+== A
+<</:ab>>
+<<:>>
+<<1>>
+<<1:>>
+<<1#b>>
+<<:a#b:>>
+
+INPUT
+expect(xmlpp(Asciidoctor.convert(input, backend: :standoc, header_footer: true).gsub(/<p id="_[^"]+">/, "").gsub('</p>', ""))).to be_equivalent_to (<<~"OUTPUT")
+<standard-document xmlns='https://www.metanorma.org/ns/standoc'>
+  <bibdata type='standard'>
+    <title language='en' format='text/plain'>Document title</title>
+    <language>en</language>
+    <script>Latn</script>
+    <status>
+      <stage>published</stage>
+    </status>
+    <copyright>
+      <from>2020</from>
+    </copyright>
+    <ext>
+      <doctype>article</doctype>
+    </ext>
+  </bibdata>
+  <sections>
+  <clause id='a_b' inline-header='false' obligation='normative'>
+             <title>A</title>
+             <xref target='__ab'/>
+             <xref target='_'/>
+             <xref target='_1'/>
+             <xref target='_1_'/>
+             <xref target='1#b'/>
+             <xref target='_a#b_'/>
+           </clause>
+  </sections>
+</standard-document>
+OUTPUT
+expect{Asciidoctor.convert(input, backend: :standoc, header_footer: true)}.to output(%r{normalised identifier in <clause id="a_b" inline-header="false" obligation="normative"/> from a:b}).to_stderr
+expect{Asciidoctor.convert(input, backend: :standoc, header_footer: true)}.to output(%r{normalised identifier in <xref target="__ab"/> from /:ab}).to_stderr
+expect{Asciidoctor.convert(input, backend: :standoc, header_footer: true)}.to output(%r{normalised identifier in <xref target="_"/> from :}).to_stderr
+expect{Asciidoctor.convert(input, backend: :standoc, header_footer: true)}.to output(%r{normalised identifier in <xref target="_1"/> from 1}).to_stderr
+expect{Asciidoctor.convert(input, backend: :standoc, header_footer: true)}.to output(%r{normalised identifier in <xref target="_1_"/> from 1:}).to_stderr
+expect{Asciidoctor.convert(input, backend: :standoc, header_footer: true)}.to output(%r{normalised identifier in <xref target="_a#b_"/> from :a#b:}).to_stderr
+end
+
 
   private