metanorma-standoc 1.8.6 → 1.9.2

data/lib/asciidoctor/standoc/section.rb

@@ -10,7 +10,9 @@ module Asciidoctor
       @norm_ref = false
 
       def sectiontype1(node)
-        node&.attr("heading")&.downcase || node.title.gsub(/<[^>]+>/, "").downcase
+        node&.attr("heading")&.downcase ||
+          node.title.gsub(%r{<index>.*?</index>}m, "").gsub(/<[^>]+>/, "")
+          .strip.downcase
       end
 
       def sectiontype(node, level = true)

data/lib/asciidoctor/standoc/terms.rb

@@ -12,12 +12,13 @@ module Asciidoctor
         @definitions = defs
       end
 
-      def symbols_attrs(node, a)
+      def symbols_attrs(node, attr)
         case sectiontype1(node)
-        when "symbols" then a.merge(type: "symbols")
-        when "abbreviated terms", "abbreviations" then a.merge(type: "abbreviated_terms")
+        when "symbols" then attr.merge(type: "symbols")
+        when "abbreviated terms", "abbreviations"
+          attr.merge(type: "abbreviated_terms")
         else
-          a
+          attr
         end
       end
 
@@ -51,13 +52,17 @@ module Asciidoctor
 
       # subclause contains subclauses
       def term_def_subclause_parse(attrs, xml, node)
-        node.role == "nonterm"  and return nonterm_term_def_subclause_parse(attrs, xml, node)
-        node.role == "boilerplate"  and return terms_boilerplate_parse(attrs, xml, node)
+        node.role == "nonterm" and
+          return nonterm_term_def_subclause_parse(attrs, xml, node)
+        node.role == "boilerplate" and
+          return terms_boilerplate_parse(attrs, xml, node)
         st = sectiontype(node, false)
         return symbols_parse(attrs, xml, node) if @definitions
+
         sub = node.find_by(context: :section) { |s| s.level == node.level + 1 }
         sub.empty? || (return term_def_parse(attrs, xml, node, false))
-        st == "symbols and abbreviated terms" and (return symbols_parse(attrs, xml, node))
+        st == "symbols and abbreviated terms" and
+          return symbols_parse(attrs, xml, node)
         st == "terms and definitions" and return clause_parse(attrs, xml, node)
         term_def_subclause_parse1(attrs, xml, node)
       end
@@ -69,7 +74,7 @@ module Asciidoctor
         end
       end
 
-      def term_def_parse(attrs, xml, node, toplevel)
+      def term_def_parse(attrs, xml, node, _toplevel)
         xml.terms **attr_code(attrs) do |section|
           section.title { |t| t << node.title }
           (s = node.attr("source")) && s.split(/,/).each do |s1|
@@ -79,19 +84,23 @@ module Asciidoctor
         end
       end
 
-      def term_source_attrs(seen_xref)
-        { bibitemid: seen_xref.children[0]["target"],
+      def term_source_attrs(_node, seen_xref)
+        { case: seen_xref.children[0]["case"],
+          droploc: seen_xref.children[0]["droploc"],
+          bibitemid: seen_xref.children[0]["target"],
           format: seen_xref.children[0]["format"], type: "inline" }
       end
 
-      def add_term_source(xml_t, seen_xref, m)
+      def add_term_source(node, xml_t, seen_xref, match)
         if seen_xref.children[0].name == "concept"
           xml_t.origin { |o| o << seen_xref.children[0].to_xml }
         else
-          xml_t.origin seen_xref.children[0].content, **attr_code(term_source_attrs(seen_xref))
+          attrs = term_source_attrs(node, seen_xref)
+          attrs.delete(:text)
+          xml_t.origin seen_xref.children[0].content, **attr_code(attrs)
         end
-        m[:text] && xml_t.modification do |mod|
-          mod.p { |p| p << m[:text].sub(/^\s+/, "") }
+        match[:text] && xml_t.modification do |mod|
+          mod.p { |p| p << match[:text].sub(/^\s+/, "") }
         end
       end
 
@@ -106,7 +115,9 @@ module Asciidoctor
 
       def extract_termsource_refs(text, node)
         matched = TERM_REFERENCE_RE.match text
-        matched.nil? and @log.add("AsciiDoc Input", node, "term reference not in expected format: #{text}")
+        matched.nil? and @log.add("AsciiDoc Input", node,
+                                  "term reference not in expected format:"\
+                                  "#{text}")
         matched
       end
 
@@ -116,7 +127,7 @@ module Asciidoctor
           attrs = { status: matched[:text] ? "modified" : "identical" }
           xml.termsource **attrs do |xml_t|
             seen_xref = Nokogiri::XML.fragment(matched[:xref])
-            add_term_source(xml_t, seen_xref, matched)
+            add_term_source(node, xml_t, seen_xref, matched)
           end
         end.join("\n")
       end

data/lib/asciidoctor/standoc/utils.rb

@@ -19,11 +19,11 @@ module Asciidoctor
       end
 
       NOKOHEAD = <<~HERE.freeze
-          <!DOCTYPE html SYSTEM
-          "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-          <html xmlns="http://www.w3.org/1999/xhtml">
-          <head> <title></title> <meta charset="UTF-8" /> </head>
-          <body> </body> </html>
+        <!DOCTYPE html SYSTEM
+        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+        <html xmlns="http://www.w3.org/1999/xhtml">
+        <head> <title></title> <meta charset="UTF-8" /> </head>
+        <body> </body> </html>
       HERE
 
       # block for processing XML document fragments as XHTML,
@@ -34,9 +34,9 @@ module Asciidoctor
         fragment = doc.fragment("")
         ::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("&#150;", "\u0096").
-            gsub("&#151;", "\u0097").gsub("&#x96;", "\u0096").
-            gsub("&#x97;", "\u0097")
+          l.gsub(/>\n$/, ">").gsub(/\s*\n$/m, " ").gsub("&#150;", "\u0096")
+            .gsub("&#151;", "\u0097").gsub("&#x96;", "\u0096")
+            .gsub("&#x97;", "\u0097")
         end
       end
 
@@ -66,10 +66,36 @@ module Asciidoctor
         conv
       end
 
+      def default_script(lang)
+        case lang
+        when "ar", "fa"
+          "Arab"
+        when "ur"
+          "Aran"
+        when "ru", "bg"
+          "Cyrl"
+        when "hi"
+          "Deva"
+        when "el"
+          "Grek"
+        when "zh"
+          "Hans"
+        when "ko"
+          "Kore"
+        when "he"
+          "Hebr"
+        when "ja"
+          "Jpan"
+        else
+          "Latn"
+        end
+      end
+
       class EmptyAttr
-        def attr(_x)
+        def attr(_any_attribute)
           nil
         end
+
         def attributes
           {}
         end

data/lib/asciidoctor/standoc/validate.rb

@@ -1,5 +1,5 @@
 require "asciidoctor/standoc/utils"
-require_relative "./validate_section.rb"
+require_relative "./validate_section"
 require "nokogiri"
 require "jing"
 require "iev"
@@ -7,13 +7,13 @@ require "iev"
 module Asciidoctor
   module Standoc
     module Validate
-
       SOURCELOCALITY = "./termsource/origin//locality[@type = 'clause']/"\
         "referenceFrom".freeze
 
       def init_iev
         return nil if @no_isobib
         return @iev if @iev
+
         @iev = Iev::Db.new(@iev_globalname, @iev_localname) unless @no_isobib
         @iev
       end
@@ -44,23 +44,23 @@ module Asciidoctor
         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")
+          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
+        found and
+          clean_abort("Numeric reference in normative references", doc.to_xml)
       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']]}")
+      def repeat_id_validate1(ids, elem)
+        if ids[elem["id"]]
+          @log.add("Anchors", elem, "Anchor #{elem['id']} has already been "\
+                   "used at line #{ids[elem['id']]}")
           raise StandardError.new "Error: multiple instances of same ID"
         else
-          ids[x["id"]] = x.line
+          ids[elem["id"]] = elem.line
         end
         ids
       end
@@ -72,39 +72,41 @@ module Asciidoctor
             ids = repeat_id_validate1(ids, x)
           end
         rescue StandardError => e
-          clean_exit
-          abort(e.message)
+          clean_abort(e.message, doc.to_xml)
         end
       end
 
       def schema_validate(doc, schema)
-        Tempfile.open(["tmp", ".xml"], :encoding => 'UTF-8') do |f|
+        Tempfile.open(["tmp", ".xml"], encoding: "UTF-8") do |f|
           begin
-            f.write(doc.to_xml) 
-            f.close
-            errors = Jing.new(schema).validate(f.path)
-            warn "Syntax Valid!" if errors.none?
-            errors.each do |e|
-              @log.add("Metanorma XML Syntax",
-                       "XML Line #{"%06d" % e[:line]}:#{e[:column]}",
-                       e[:message])
-            end
+            schema_validate1(f, doc, schema)
           rescue Jing::Error => e
-            clean_exit
-            abort "Jing failed with error: #{e}"
+            clean_abort("Jing failed with error: #{e}", doc.to_xml)
           ensure
             f.close!
           end
         end
       end
 
+      def schema_validate1(file, doc, schema)
+        file.write(doc.to_xml)
+        file.close
+        errors = Jing.new(schema).validate(file.path)
+        warn "Syntax Valid!" if errors.none?
+        errors.each do |e|
+          @log.add("Metanorma XML Syntax",
+                   "XML Line #{'%06d' % e[:line]}:#{e[:column]}", e[:message])
+        end
+      end
+
       # 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")
+          .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.rb

@@ -1,5 +1,4 @@
 require "asciidoctor" unless defined? Asciidoctor::Converter
-#require_relative "asciidoctor/standoc"
 require_relative "asciidoctor/standoc/converter"
 require_relative "metanorma/standoc/version"
 require "asciidoctor/extensions"

data/lib/metanorma/standoc/version.rb

@@ -8,17 +8,17 @@ module Metanorma
 
     def all_modules(mod)
       [mod] + mod.constants.map { |c| mod.const_get(c) }
-        .select {|c| c.is_a?(Module) && parent_of(c) == mod }
-        .flat_map {|m| all_modules(m) }
+        .select { |c| c.is_a?(Module) && parent_of(c) == mod }
+        .flat_map { |m| all_modules(m) }
     end
 
     def versioned(mod, flavour)
-      all_modules(mod).select {|c| defined? c::VERSION}.
-        select {|c| c.name =~ /::#{flavour}$/ }
+      all_modules(mod).select { |c| defined? c::VERSION }
+        .select { |c| c.name =~ /::#{flavour}$/ }
     end
   end
 
   module Standoc
-    VERSION= "1.8.6".freeze
+    VERSION = "1.9.2".freeze
   end
 end

data/metanorma-standoc.gemspec

@@ -1,6 +1,6 @@
 # coding: utf-8
 
-lib = File.expand_path("../lib", __FILE__)
+lib = File.expand_path("lib", __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "metanorma/standoc/version"
 
@@ -27,29 +27,29 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
 
   spec.add_dependency "asciidoctor", "~> 2.0.0"
-  spec.add_dependency "ruby-jing"
-  spec.add_dependency "isodoc", "~> 1.5.0"
   spec.add_dependency "iev", "~> 0.2.1"
+  spec.add_dependency "isodoc", "~> 1.6.2"
   spec.add_dependency "metanorma-plugin-datastruct"
-  spec.add_dependency "metanorma-plugin-lutaml", "~> 0.3.0"
+  spec.add_dependency "metanorma-plugin-lutaml"
+  spec.add_dependency "ruby-jing"
   # relaton-cli not just relaton, to avoid circular reference in metanorma
+  spec.add_dependency "asciimath2unitsml", "~> 0.3.0"
+  spec.add_dependency "concurrent-ruby"
+  spec.add_dependency "latexmath"
+  spec.add_dependency "mathml2asciimath"
+  spec.add_dependency "metanorma-utils", "~> 1.2.0"
   spec.add_dependency "relaton-cli", "~> 1.7.0"
   spec.add_dependency "relaton-iev", "~> 1.1.0"
-  spec.add_dependency "concurrent-ruby"
   spec.add_dependency "unicode2latex", "~> 0.0.1"
-  spec.add_dependency "metanorma-utils", "~> 1.0.2"
-  spec.add_dependency "mathml2asciimath"
-  spec.add_dependency "latexmath"
-  spec.add_dependency "asciimath2unitsml", "~> 0.2.0"
 
   spec.add_development_dependency "byebug"
-  spec.add_development_dependency "sassc", "2.4.0"
   spec.add_development_dependency "equivalent-xml", "~> 0.6"
   spec.add_development_dependency "guard", "~> 2.14"
   spec.add_development_dependency "guard-rspec", "~> 4.7"
   spec.add_development_dependency "rake", "~> 13.0"
   spec.add_development_dependency "rspec", "~> 3.6"
-  spec.add_development_dependency "rubocop", "= 0.54.0"
+  spec.add_development_dependency "rubocop", "~> 1.5.2"
+  spec.add_development_dependency "sassc", "2.4.0"
   spec.add_development_dependency "simplecov", "~> 0.15"
   spec.add_development_dependency "timecop", "~> 0.9"
   spec.add_development_dependency "vcr", "~> 5.0.0"

data/spec/asciidoctor/base_spec.rb

@@ -240,6 +240,7 @@ OUTPUT
       :pub-uri: http://www.example.com
       :isbn: ISBN-13
       :isbn10: ISBN-10
+      :classification: a:b, c
     INPUT
     <?xml version="1.0" encoding="UTF-8"?>
 <standard-document xmlns="https://www.metanorma.org/ns/standoc" type="semantic" version="#{Metanorma::Standoc::VERSION}">
@@ -361,18 +362,51 @@ OUTPUT
   <role type="publisher"/>
   <organization>
     <name>Hanna Barbera</name>
+    <address>
+  <formattedAddress>
+    1 Infinity Loop
+    <br/>
+    California
+  </formattedAddress>
+</address>
+<phone>3333333</phone>
+<phone type='fax'>4444444</phone>
+<email>x@example.com</email>
+<uri>http://www.example.com</uri>
   </organization>
 </contributor>
 <contributor>
   <role type="publisher"/>
   <organization>
     <name>Cartoon Network</name>
+    <address>
+  <formattedAddress>
+    1 Infinity Loop
+    <br/>
+    California
+  </formattedAddress>
+</address>
+<phone>3333333</phone>
+<phone type='fax'>4444444</phone>
+<email>x@example.com</email>
+<uri>http://www.example.com</uri>
   </organization>
 </contributor>
 <contributor>
   <role type="publisher"/>
   <organization>
     <name>Ribose, Inc.</name>
+    <address>
+  <formattedAddress>
+    1 Infinity Loop
+    <br/>
+    California
+  </formattedAddress>
+</address>
+<phone>3333333</phone>
+<phone type='fax'>4444444</phone>
+<email>x@example.com</email>
+<uri>http://www.example.com</uri>
   </organization>
 </contributor>
 <edition>2</edition>
@@ -392,6 +426,17 @@ OUTPUT
        <owner>
      <organization>
        <name>Ribose, Inc.</name>
+        <address>
+   <formattedAddress>
+     1 Infinity Loop
+     <br/>
+     California
+   </formattedAddress>
+ </address>
+ <phone>3333333</phone>
+ <phone type='fax'>4444444</phone>
+ <email>x@example.com</email>
+ <uri>http://www.example.com</uri>
      </organization>
    </owner>
  </copyright>
@@ -400,6 +445,17 @@ OUTPUT
    <owner>
      <organization>
        <name>Hanna Barbera</name>
+        <address>
+   <formattedAddress>
+     1 Infinity Loop
+     <br/>
+     California
+   </formattedAddress>
+ </address>
+ <phone>3333333</phone>
+ <phone type='fax'>4444444</phone>
+ <email>x@example.com</email>
+ <uri>http://www.example.com</uri>
      </organization>
    </owner>
   </copyright>
@@ -421,6 +477,8 @@ OUTPUT
              <docidentifier>JKL MNO</docidentifier>
            </bibitem>
          </relation>
+         <classification type='a'>b</classification>
+         <classification type='default'>c</classification>
 <keyword>a</keyword>
 <keyword>b</keyword>
 <keyword>c</keyword>
@@ -469,6 +527,7 @@ OUTPUT
       :relaton-uri: F
       :title-eo: Dokumenttitolo
       :doctype: This is a DocType
+      :docsubtype: This is a DocSubType
       :subdivision: Subdivision
       :subdivision-abbr: SD
 
@@ -567,6 +626,7 @@ OUTPUT
          </copyright>
          <ext>
          <doctype>this-is-a-doctype</doctype>
+         <subdoctype>This is a DocSubType</subdoctype>
          </ext>
        </bibdata>
          <preface>
@@ -625,13 +685,6 @@ OUTPUT
         <name>International Standards Organization</name>
         <subdivision>Subdivision</subdivision>
         <abbreviation>SD</abbreviation>
-        <address>
-  <formattedAddress>1 Infinity Loop <br/>California</formattedAddress>
-</address>
-<phone>3333333</phone>
-<phone type='fax'>4444444</phone>
-<email>x@example.com</email>
-<uri>http://www.example.com</uri>
       </organization>
     </contributor>
     <contributor>
@@ -709,6 +762,7 @@ OUTPUT
       :header-font: Comic Sans
       :monospace-font: Andale Mono
       :htmlstylesheet: spec/assets/html.scss
+      :htmlstylesheet-override: spec/assets/html-override.css
       :htmlcoverpage: spec/assets/htmlcover.html
       :htmlintropage: spec/assets/htmlintro.html
       :scripts: spec/assets/scripts.html
@@ -727,6 +781,7 @@ OUTPUT
     expect(html).to match(%r[an empty html cover page])
     expect(html).to match(%r[an empty html intro page])
     expect(html).to match(%r[This is > a script])
+    expect(html).to match(%r[html-override])
   end
 
   it "uses specified fonts and assets in Word" do
@@ -741,6 +796,7 @@ OUTPUT
       :header-font: Comic Sans
       :monospace-font: Andale Mono
       :wordstylesheet: spec/assets/word.scss
+      :wordstylesheet-override: spec/assets/word-override.css
       :wordcoverpage: spec/assets/wordcover.html
       :wordintropage: spec/assets/wordintro.html
       :header: spec/assets/header.html
@@ -758,8 +814,10 @@ OUTPUT
     expect(html).to match(%r[h1[^{]+\{[^{]+font-family: Comic Sans;]m)
     expect(html).to match(%r[an empty word cover page])
     expect(html).to match(%r[an empty word intro page])
+    expect(html).to match(%r[word-override])
     expect(html).to include('\o "1-3"')
-    expect(html).to include(%[Content-Location: file:///C:/Doc/test_files/header.html
+    expect(html).to include(%[Content-ID: <header.html>
+Content-Disposition: inline; filename="header.html"
 Content-Transfer-Encoding: base64
 Content-Type: text/html charset="utf-8"
 
@@ -783,6 +841,18 @@ QU1FOiB0ZXN0Cgo=
     expect(File.exist?("test.doc")).to be true
   end
 
+  it "process mn2pdf attributes" do
+    node = Nokogiri::XML("<fake/>").at("fake")
+    node["mn2pdf-font-manifest-file"] = "passed/as/font/manifest/to/mn2pdf.jar"
+
+    options = Asciidoctor::Standoc::Converter
+      .new(:standoc, header_footer: true)
+      .doc_extract_attributes(node)
+
+    expect(options.dig(:mn2pdf, :font_manifest_file))
+      .to eq(node["mn2pdf-font-manifest-file"])
+  end
+
   private
 
   def mock_org_abbrevs