metanorma-bsi 0.0.1

data/lib/metanorma-bsi.rb

@@ -0,0 +1,15 @@
+require "asciidoctor" unless defined? Asciidoctor::Converter
+require_relative "asciidoctor/bsi/converter"
+require_relative "metanorma/bsi/version"
+require "isodoc/bsi/html_convert"
+require "isodoc/bsi/sts_convert"
+require "isodoc/bsi/pdf_convert"
+require "isodoc/bsi/presentation_xml_convert"
+require "isodoc/bsi/metadata"
+require "isodoc/bsi/xref"
+
+if defined? Metanorma
+  require_relative "metanorma/bsi"
+  Metanorma::Registry.instance.register(Metanorma::BSI::Processor)
+end
+

data/lib/metanorma/bsi.rb

@@ -0,0 +1,6 @@
+require_relative "./bsi/processor"
+
+module Metanorma
+  module BSI
+  end
+end

data/lib/metanorma/bsi/processor.rb

@@ -0,0 +1,51 @@
+require "metanorma/processor"
+
+module Metanorma
+  module BSI
+    class Processor < Metanorma::Processor
+
+      def initialize
+        @short = :bsi
+        @input_format = :asciidoc
+        @asciidoctor_backend = :bsi
+      end
+
+      def output_formats
+        super.merge(
+          html: "html",
+          pdf: "pdf",
+          sts: "sts.xml"
+        )
+      end
+
+      def fonts_manifest
+        {
+          "Tahoma" => nil,
+          "STIX Two Math" => nil,
+          "Source Han Sans" => nil,
+          "Courier" => nil,
+          "Courier New" => nil,
+        }
+      end
+
+      def version
+        "Metanorma::BSI #{Metanorma::BSI::VERSION}"
+      end
+
+      def output(xml, inname, outname, format, options = {})
+        case format
+        when :html
+          IsoDoc::BSI::HtmlConvert.new(options).convert(inname, xml, nil, outname)
+        when :pdf
+          IsoDoc::BSI::PdfConvert.new(options).convert(inname, xml, nil, outname)
+        when :sts
+          IsoDoc::BSI::StsConvert.new(options).convert(inname, isodoc_node, nil, outname)
+        when :presentation
+          IsoDoc::BSI::PresentationXMLConvert.new(options).convert(inname, xml, nil, outname)
+        else
+          super
+        end
+      end
+    end
+  end
+end

data/lib/metanorma/bsi/version.rb

@@ -0,0 +1,6 @@
+module Metanorma
+  module BSI
+    VERSION = "0.0.1".freeze
+  end
+end
+

data/metanorma-bsi.gemspec

@@ -0,0 +1,47 @@
+# coding: utf-8
+
+lib = File.expand_path("lib", __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "metanorma/bsi/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "metanorma-bsi"
+  spec.version       = Metanorma::BSI::VERSION
+  spec.authors       = ["Ribose Inc."]
+  spec.email         = ["open.source@ribose.com"]
+
+  spec.summary       = "metanorma-bsi lets you write BSI standards "\
+    "in AsciiDoc."
+  spec.description   = <<~DESCRIPTION
+    metanorma-bsi lets you write BSI standards in AsciiDoc syntax.
+
+    This gem is in active development.
+  DESCRIPTION
+
+  spec.homepage      = "https://github.com/metanorma/metanorma-bsi"
+  spec.license       = "BSD-2-Clause"
+
+  spec.bindir        = "bin"
+  spec.require_paths = ["lib"]
+  spec.files         = `git ls-files`.split("\n")
+  spec.test_files    = `git ls-files -- {spec}/*`.split("\n")
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
+
+  spec.add_dependency "metanorma-iso", "~> 1.8.0"
+  spec.add_dependency "mn2sts", "~> 1.5.0"
+  spec.add_dependency "ruby-jing"
+
+  spec.add_development_dependency "byebug"
+  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 "iev", "~> 0.2.0"
+  spec.add_development_dependency "rake", "~> 13.0"
+  spec.add_development_dependency "rspec", "~> 3.6"
+  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"
+  spec.add_development_dependency "webmock"
+end

data/spec/asciidoctor/base_spec.rb

@@ -0,0 +1,778 @@
+require "spec_helper"
+require "fileutils"
+
+RSpec.describe Asciidoctor::BSI do
+  before(:all) do
+    @blank_hdr = blank_hdr_gen
+  end
+
+  it "has a version number" do
+    expect(Metanorma::BSI::VERSION).not_to be nil
+  end
+
+  it "processes a blank document" do
+    expect(xmlpp(strip_guid(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+    #{ASCIIDOC_BLANK_HDR}
+    INPUT
+    #{@blank_hdr}
+<sections/>
+</bsi-standard>
+    OUTPUT
+  end
+
+  it "converts a blank document" do
+    FileUtils.rm_f "test.doc"
+    FileUtils.rm_f "test.html"
+    FileUtils.rm_f "test.pdf"
+    expect(xmlpp(strip_guid(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :novalid:
+      :no-isobib:
+    INPUT
+      #{@blank_hdr}
+      <sections/>
+      </bsi-standard>
+    OUTPUT
+    expect(File.exist?("test.pdf")).to be true
+    expect(File.exist?("test.html")).to be true
+    expect(File.exist?("test.doc")).to be true
+    expect(File.exist?("htmlstyle.css")).to be false
+  end
+
+  it "processes default metadata" do
+    expect(xmlpp(strip_guid(Nokogiri::XML(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)).at("//xmlns:bibdata").to_xml))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :nodoc:
+      :novalid:
+      :no-isobib:
+      :docnumber: 1000
+      :partnumber: 1
+      :edition: 2
+      :revdate: 2000-01-01
+      :draft: 0.3.4
+      :technical-committee: TC
+      :technical-committee-number: 1
+      :technical-committee-type: A
+      :subcommittee: SC
+      :subcommittee-number: 2
+      :subcommittee-type: B
+      :workgroup: WG
+      :workgroup-number: 3
+      :workgroup-type: C
+      :technical-committee_2: TC1
+      :technical-committee-number_2: 11
+      :technical-committee-type_2: A1
+      :subcommittee_2: SC1
+      :subcommittee-number_2: 21
+      :subcommittee-type_2: B1
+      :workgroup_2: WG1
+      :workgroup-number_2: 31
+      :workgroup-type_2: C1
+      :secretariat: SECRETARIAT
+      :docstage: 10
+      :docsubstage: 20
+      :iteration: 3
+      :language: en
+      :title-intro-en: Introduction
+      :title-main-en: Main Title -- Title
+      :title-part-en: Title Part
+      :title-intro-fr: Introduction Française
+      :title-main-fr: Titre Principal
+      :title-part-fr: Part du Titre
+      :library-ics: 1,2,3
+      :accessibility-color-inside: true
+      :price-code: XC
+      :cen-processing: true
+      :secretary: Fred Nerk
+      :interest-to-committees: TC 6121, SC 12
+      :obsoletes: ABC; DEF
+    INPUT
+       <bibdata type="standard">
+   <title language="en" format="text/plain" type="main">Introduction — Main Title — Title — Title Part</title>
+   <title language="en" format="text/plain" type="title-intro">Introduction</title>
+   <title language="en" format="text/plain" type="title-main">Main Title — Title</title>
+   <title language="en" format="text/plain" type="title-part">Title Part</title>
+   <title language="fr" format="text/plain" type="main">Introduction Française — Titre Principal — Part du Titre</title>
+   <title language="fr" format="text/plain" type="title-intro">Introduction Française</title>
+   <title language="fr" format="text/plain" type="title-main">Titre Principal</title>
+   <title language="fr" format="text/plain" type="title-part">Part du Titre</title>
+         <docidentifier type="BS">BS/PreNP 1000-1</docidentifier>
+<docnumber>1000</docnumber>
+         <contributor>
+           <role type="author"/>
+           <organization>
+             <name>British Standards Institute</name>
+             <abbreviation>BSI</abbreviation>
+           </organization>
+         </contributor>
+         <contributor>
+           <role type="publisher"/>
+           <organization>
+             <name>British Standards Institute</name>
+             <abbreviation>BSI</abbreviation>
+           </organization>
+         </contributor>
+         <edition>2</edition>
+<version>
+         <revision-date>2000-01-01</revision-date>
+         <draft>0.3.4</draft>
+       </version>
+         <language>en</language>
+         <script>Latn</script>
+         <status>
+           <stage abbreviation="NP">10</stage>
+           <substage>20</substage>
+           <iteration>3</iteration>
+         </status>
+         <copyright>
+           <from>#{Date.today.year}</from>
+           <owner>
+             <organization>
+             <name>British Standards Institute</name>
+             <abbreviation>BSI</abbreviation>
+             </organization>
+           </owner>
+         </copyright>
+         <relation type='obsoletes'>
+  <bibitem>
+    <title>--</title>
+    <docidentifier>ABC</docidentifier>
+  </bibitem>
+</relation>
+<relation type='obsoletes'>
+  <bibitem>
+    <title>--</title>
+    <docidentifier>DEF</docidentifier>
+  </bibitem>
+</relation>
+         <ext>
+         <doctype>article</doctype>
+         <editorialgroup>
+           <technical-committee number="1" type="A">TC</technical-committee>
+           <technical-committee number="11" type="A1">TC1</technical-committee>
+           <subcommittee number="2" type="B">SC</subcommittee>
+           <subcommittee number="21" type="B1">SC1</subcommittee>
+           <workgroup number="3" type="C">WG</workgroup>
+           <workgroup number="31" type="C1">WG1</workgroup>
+           <secretariat>SECRETARIAT</secretariat>
+         </editorialgroup>
+         <ics>
+  <code>1</code>
+</ics>
+<ics>
+  <code>2</code>
+</ics>
+<ics>
+  <code>3</code>
+</ics>
+<structuredidentifier>
+  <project-number part="1">BS 1000</project-number>
+</structuredidentifier>
+<stagename>New work item proposal</stagename>
+       </ext>
+       </bibdata>
+    OUTPUT
+  end
+
+
+  it "processes complex metadata" do
+    expect(xmlpp(strip_guid(Nokogiri::XML(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)).at("//xmlns:bibdata").to_xml))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :nodoc:
+      :novalid:
+      :no-isobib:
+      :docnumber: 1000
+      :partnumber: 1-1
+      :tc-docnumber: 2000
+      :language: el
+      :script: Grek
+      :publisher: BSI;IETF;ISO
+      :copyright-year: 2001
+      :docstage: 50
+      :doctype: technical-specification
+      :function: emc
+      :horizontal: true
+    INPUT
+       <bibdata type="standard">
+         <docidentifier type="BS">BS/IETF/ISO/FDTS TS 1000-1-1</docidentifier>
+         <docidentifier type="iso-tc">2000</docidentifier>
+         <docnumber>1000</docnumber>
+         <contributor>
+           <role type="author"/>
+           <organization>
+             <name>British Standards Institute</name>
+             <abbreviation>BSI</abbreviation>
+           </organization>
+         </contributor>
+         <contributor>
+           <role type="author"/>
+           <organization>
+             <name>IETF</name>
+           </organization>
+         </contributor>
+         <contributor>
+           <role type="author"/>
+           <organization>
+             <name>International Organization for Standardization</name>
+             <abbreviation>ISO</abbreviation>
+           </organization>
+         </contributor>
+         <contributor>
+           <role type="publisher"/>
+           <organization>
+             <name>British Standards Institute</name>
+             <abbreviation>BSI</abbreviation>
+           </organization>
+         </contributor>
+         <contributor>
+           <role type="publisher"/>
+           <organization>
+             <name>IETF</name>
+           </organization>
+         </contributor>
+         <contributor>
+           <role type="publisher"/>
+           <organization>
+             <name>International Organization for Standardization</name>
+             <abbreviation>ISO</abbreviation>
+           </organization>
+         </contributor>
+         <language>el</language>
+         <script>Grek</script>
+         <status>
+           <stage abbreviation="FDTS TS">50</stage>
+           <substage>00</substage>
+         </status>
+         <copyright>
+           <from>2001</from>
+           <owner>
+             <organization>
+               <name>British Standards Institute</name>
+               <abbreviation>BSI</abbreviation>
+             </organization>
+           </owner>
+         </copyright>
+         <copyright>
+           <from>2001</from>
+           <owner>
+             <organization>
+               <name>IETF</name>
+             </organization>
+           </owner>
+         </copyright>
+         <copyright>
+           <from>2001</from>
+           <owner>
+             <organization>
+               <name>International Organization for Standardization</name>
+               <abbreviation>ISO</abbreviation>
+             </organization>
+           </owner>
+         </copyright>
+         <ext>
+         <doctype>technical-specification</doctype>
+         <editorialgroup>
+           <technical-committee/>
+           <subcommittee/>
+           <workgroup/>
+         </editorialgroup>
+         <structuredidentifier>
+           <project-number part="1" subpart="1">BS/IETF/ISO 1000</project-number>
+         </structuredidentifier>
+         <stagename>Final draft</stagename>
+         </ext>
+       </bibdata>
+    OUTPUT
+  end
+
+  it "processes adoption of ISO standards" do
+    VCR.use_cassette "iso-639" do
+    expect(xmlpp(strip_guid(Nokogiri::XML(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)).at("//xmlns:bibdata").to_xml))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :docnumber: ISO 639
+      :partnumber: 2
+      :nodoc:
+      :novalid:
+      :adopted-from: ISO 639-2
+      :copyright-year: 2001
+    INPUT
+    <bibdata type='standard'>
+  <docidentifier type='BS'>BS ISO 639-2:2001</docidentifier>
+  <docnumber>ISO 639</docnumber>
+  <contributor>
+    <role type='author'/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+  <contributor>
+    <role type='publisher'/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+  <language>en</language>
+  <script>Latn</script>
+  <status>
+    <stage abbreviation='IS'>60</stage>
+    <substage>60</substage>
+  </status>
+  <copyright>
+    <from>2001</from>
+    <owner>
+      <organization>
+        <name>British Standards Institute</name>
+        <abbreviation>BSI</abbreviation>
+      </organization>
+    </owner>
+  </copyright>
+  <relation type='adoptedFrom'>
+    <bibitem type='standard'>
+      <fetched>2021-04-25</fetched>
+      <title type='title-main' format='text/plain' language='en' script='Latn'>Codes for the representation of names of languages</title>
+      <title type='title-part' format='text/plain' language='en' script='Latn'>Part 2: Alpha-3 code</title>
+      <title type='main' format='text/plain' language='en' script='Latn'>
+        Codes for the representation of names of
+        languages&#8201;&#8212;&#8201;Part 2: Alpha-3 code
+      </title>
+      <title type='title-main' format='text/plain' language='fr' script='Latn'>Codes pour la repr&#233;sentation des noms de langue</title>
+      <title type='title-part' format='text/plain' language='fr' script='Latn'>Partie 2: Code alpha-3</title>
+      <title type='main' format='text/plain' language='fr' script='Latn'>
+        Codes pour la repr&#233;sentation des noms de
+        langue&#8201;&#8212;&#8201;Partie 2: Code alpha-3
+      </title>
+      <uri type='src'>https://www.iso.org/standard/4767.html</uri>
+      <uri type='obp'>https://www.iso.org/obp/ui/#!iso:std:4767:en</uri>
+      <uri type='rss'>https://www.iso.org/contents/data/standard/00/47/4767.detail.rss</uri>
+      <docidentifier type='ISO'>ISO 639-2</docidentifier>
+      <docidentifier type='URN'>urn:iso:std:iso:639:-2:stage-90.20:ed-1:en,fr</docidentifier>
+      <docnumber>639</docnumber>
+      <contributor>
+        <role type='publisher'/>
+        <organization>
+          <name>International Organization for Standardization</name>
+          <abbreviation>ISO</abbreviation>
+          <uri>www.iso.org</uri>
+        </organization>
+      </contributor>
+      <edition>1</edition>
+      <language>en</language>
+      <language>fr</language>
+      <script>Latn</script>
+      <status>
+        <stage>90</stage>
+        <substage>20</substage>
+      </status>
+      <copyright>
+        <from>1998</from>
+        <owner>
+          <organization>
+            <name>ISO</name>
+          </organization>
+        </owner>
+      </copyright>
+      <relation type='instance'>
+        <bibitem type='standard'>
+          <fetched>2021-04-25</fetched>
+          <title type='title-main' format='text/plain' language='en' script='Latn'>Codes for the representation of names of languages</title>
+          <title type='title-part' format='text/plain' language='en' script='Latn'>Part 2: Alpha-3 code</title>
+          <title type='main' format='text/plain' language='en' script='Latn'>
+            Codes for the representation of names of
+            languages&#8201;&#8212;&#8201;Part 2: Alpha-3 code
+          </title>
+          <title type='title-main' format='text/plain' language='fr' script='Latn'>Codes pour la repr&#233;sentation des noms de langue</title>
+          <title type='title-part' format='text/plain' language='fr' script='Latn'>Partie 2: Code alpha-3</title>
+          <title type='main' format='text/plain' language='fr' script='Latn'>
+            Codes pour la repr&#233;sentation des noms de
+            langue&#8201;&#8212;&#8201;Partie 2: Code alpha-3
+          </title>
+          <uri type='src'>https://www.iso.org/standard/4767.html</uri>
+          <uri type='obp'>https://www.iso.org/obp/ui/#!iso:std:4767:en</uri>
+          <uri type='rss'>https://www.iso.org/contents/data/standard/00/47/4767.detail.rss</uri>
+          <docidentifier type='ISO'>ISO 639-2:1998</docidentifier>
+          <docidentifier type='URN'>urn:iso:std:iso:639:-2:stage-90.20:ed-1:en,fr</docidentifier>
+          <docnumber>639</docnumber>
+          <date type='published'>
+            <on>1998-11</on>
+          </date>
+          <contributor>
+            <role type='publisher'/>
+            <organization>
+              <name>International Organization for Standardization</name>
+              <abbreviation>ISO</abbreviation>
+              <uri>www.iso.org</uri>
+            </organization>
+          </contributor>
+          <edition>1</edition>
+          <language>en</language>
+          <language>fr</language>
+          <script>Latn</script>
+          <abstract format='text/plain' language='fr' script='Latn'>
+             La pr&#233;sente partie de l&#8217;ISO 639 fournit deux jeux de
+            codets &#224; trois caract&#232;res pour la repr&#233;sentation des
+            noms de langue, l&#8217;un destin&#233; &#224; des applications en
+            terminologie, l&#8217;autre destin&#233; &#224; des applications
+            bibliographiques. Les deux jeux de codets sont les m&#234;mes,
+            except&#233; pour vingt-cinq langues qui ont des codets
+            diff&#233;rents &#224; cause du crit&#232;re utilis&#233; pour les
+            former . &#192; l&#8217;origine, des codets de langues ont
+            &#233;t&#233; cr&#233;&#233;s &#224; l&#8217;usage des
+            biblioth&#232;ques, des services documentaires et des &#233;diteurs,
+            pour indiquer la langue dans l&#8217;&#233;change
+            d&#8217;information, particuli&#232;rement entre des syst&#232;mes
+            informatis&#233;s. Ces codets ont &#233;t&#233; utilis&#233;s
+            largement &#224; l&#8217;int&#233;rieur de la communaut&#233; des
+            biblioth&#232;ques, et ils peuvent &#234;tre adopt&#233;s pour toute
+            application qui requiert l&#8217;expression de la langue sous forme
+            cod&#233;e, en terminologie ou en lexicographie. Le code alpha-2 a
+            &#233;t&#233; cr&#233;&#233; pour un usage pratique pour la plupart
+            des grandes langues du monde, langues qui sont les plus souvent
+            repr&#233;sent&#233;es dans le corpus de la litt&#233;rature
+            mondiale. De nouveaux codets sont cr&#233;&#233;s quand il devient
+            &#233;vident qu&#8217;il existe un corpus significatif de
+            litt&#233;rature dans une langue particuli&#232;re. Les langages
+            cr&#233;&#233;s pour &#234;tre utilis&#233;s exclusivement par des
+            machines, comme les langages de programmation, ne sont pas inclus
+            dans le pr&#233;sent code.
+          </abstract>
+          <status>
+            <stage>90</stage>
+            <substage>20</substage>
+          </status>
+          <copyright>
+            <from>1998</from>
+            <owner>
+              <organization>
+                <name>ISO</name>
+              </organization>
+            </owner>
+          </copyright>
+          <place>Geneva</place>
+        </bibitem>
+      </relation>
+      <place>Geneva</place>
+    </bibitem>
+  </relation>
+  <ext>
+    <doctype>article</doctype>
+    <editorialgroup>
+      <technical-committee/>
+      <subcommittee/>
+      <workgroup/>
+    </editorialgroup>
+    <structuredidentifier>
+      <project-number part='2'>BS ISO 639</project-number>
+    </structuredidentifier>
+    <stagename>International standard</stagename>
+  </ext>
+</bibdata>
+   OUTPUT
+   end
+  end
+
+  it "processes boilerplate in English" do
+    doc = (strip_guid(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)))
+      = Document title
+      Author
+      :docfile: test.adoc
+      :nodoc:
+      :novalid:
+      :no-isobib:
+      :docnumber: 1000
+      :partnumber: 1-1
+      :tc-docnumber: 2000
+      :language: en
+      :script: Latn
+      :publisher: IEC,IETF,ISO
+      :copyright-year: 2001
+    INPUT
+    expect(doc).to include "Unless otherwise specified"
+    end
+
+    it "defaults substage" do
+    expect(xmlpp(strip_guid(Nokogiri::XML(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)).at("//xmlns:bibdata").to_xml))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :nodoc:
+      :novalid:
+      :no-isobib:
+      :docnumber: 1000
+      :docstage: 50
+    INPUT
+<bibdata type="standard">
+  <docidentifier type="BS">BS/FDIS 1000</docidentifier>
+  <docnumber>1000</docnumber>
+  <contributor>
+    <role type="author"/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+
+  <language>en</language>
+  <script>Latn</script>
+  <status>
+    <stage abbreviation="FDIS">50</stage>
+    <substage>00</substage>
+  </status>
+  <copyright>
+    <from>#{Date.today.year}</from>
+    <owner>
+      <organization>
+        <name>British Standards Institute</name>
+        <abbreviation>BSI</abbreviation>
+      </organization>
+    </owner>
+  </copyright>
+  <ext>
+    <doctype>article</doctype>
+    <editorialgroup>
+      <technical-committee/>
+      <subcommittee/>
+      <workgroup/>
+    </editorialgroup>
+    <structuredidentifier>
+      <project-number>BS 1000</project-number>
+    </structuredidentifier>
+    <stagename>Final draft</stagename>
+  </ext>
+</bibdata>
+OUTPUT
+    end
+
+        it "defaults substage for stage 60" do
+    expect(xmlpp(strip_guid(Nokogiri::XML(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)).at("//xmlns:bibdata").to_xml))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :nodoc:
+      :novalid:
+      :no-isobib:
+      :docnumber: 1000
+      :docstage: 60
+    INPUT
+<bibdata type="standard">
+  <docidentifier type="BS">BS 1000</docidentifier>
+  <docnumber>1000</docnumber>
+  <contributor>
+    <role type="author"/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+
+  <language>en</language>
+  <script>Latn</script>
+  <status>
+  <stage abbreviation='IS'>60</stage>
+<substage>60</substage>
+  </status>
+  <copyright>
+    <from>#{Date.today.year}</from>
+    <owner>
+      <organization>
+        <name>British Standards Institute</name>
+        <abbreviation>BSI</abbreviation>
+      </organization>
+    </owner>
+  </copyright>
+  <ext>
+    <doctype>article</doctype>
+    <editorialgroup>
+      <technical-committee/>
+      <subcommittee/>
+      <workgroup/>
+    </editorialgroup>
+    <structuredidentifier>
+      <project-number>BS 1000</project-number>
+    </structuredidentifier>
+    <stagename>International standard</stagename>
+  </ext>
+</bibdata>
+OUTPUT
+    end
+
+  it "populates metadata for PRF" do
+    expect(xmlpp(strip_guid(Nokogiri::XML(Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)).at("//xmlns:bibdata").to_xml))).to be_equivalent_to xmlpp(<<~"OUTPUT")
+      = Document title
+      Author
+      :docfile: test.adoc
+      :nodoc:
+      :novalid:
+      :no-isobib:
+      :docnumber: 1000
+      :docstage: 60
+      :docsubstage: 00
+    INPUT
+<bibdata type="standard">
+  <docidentifier type="BS">BS 1000</docidentifier>
+  <docnumber>1000</docnumber>
+  <contributor>
+    <role type="author"/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <name>British Standards Institute</name>
+      <abbreviation>BSI</abbreviation>
+    </organization>
+  </contributor>
+
+  <language>en</language>
+  <script>Latn</script>
+  <status>
+  <stage abbreviation='PRF'>60</stage>
+<substage>00</substage>
+  </status>
+  <copyright>
+    <from>#{Date.today.year}</from>
+    <owner>
+      <organization>
+        <name>British Standards Institute</name>
+        <abbreviation>BSI</abbreviation>
+      </organization>
+    </owner>
+  </copyright>
+  <ext>
+    <doctype>article</doctype>
+    <editorialgroup>
+      <technical-committee/>
+      <subcommittee/>
+      <workgroup/>
+    </editorialgroup>
+    <structuredidentifier>
+      <project-number>BS 1000</project-number>
+    </structuredidentifier>
+    <stagename>Proof</stagename>
+  </ext>
+</bibdata>
+OUTPUT
+    end
+
+
+  it "reads scripts into blank HTML document" do
+    FileUtils.rm_f "test.html"
+    Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)
+      = Document title
+      Author
+      :docfile: test.adoc
+      :novalid:
+      :no-isobib:
+      :no-pdf:
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html).to match(%r{<script>})
+  end
+
+  it "uses default fonts" do
+    FileUtils.rm_f "test.html"
+    Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)
+      = Document title
+      Author
+      :docfile: test.adoc
+      :novalid:
+      :no-isobib:
+      :no-pdf:
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html)
+      .to match(%r[\bpre[^{]+\{[^{]+font-family: "Courier New", monospace;]m)
+    expect(html)
+      .to match(%r[blockquote[^{]+\{[^{]+font-family: "Tahoma", sans-serif;]m)
+    expect(html)
+      .to match(%r[\.h2Annex[^{]+\{[^{]+font-family: "Tahoma", sans-serif;]m)
+  end
+
+  it "uses Chinese fonts" do
+    FileUtils.rm_f "test.html"
+    Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)
+      = Document title
+      Author
+      :docfile: test.adoc
+      :novalid:
+      :no-isobib:
+      :script: Hans
+      :no-pdf:
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html)
+      .to match(%r[\bpre[^{]+\{[^{]+font-family: "Courier New", monospace;]m)
+    expect(html)
+      .to match(%r[blockquote[^{]+\{[^{]+font-family: "Source Han Sans", serif;]m)
+    expect(html)
+      .to match(%r[\.h2Annex[^{]+\{[^{]+font-family: "Source Han Sans", sans-serif;]m)
+  end
+
+  it "uses specified fonts" do
+    FileUtils.rm_f "test.html"
+    Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)
+      = Document title
+      Author
+      :docfile: test.adoc
+      :novalid:
+      :no-isobib:
+      :script: Hans
+      :body-font: Zapf Chancery
+      :header-font: Comic Sans
+      :monospace-font: Andale Mono
+      :no-pdf:
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html)
+      .to match(%r[\bpre[^{]+\{[^{]+font-family: Andale Mono;]m)
+    expect(html)
+      .to match(%r[blockquote[^{]+\{[^{]+font-family: Zapf Chancery;]m)
+    expect(html)
+      .to match(%r[\.h2Annex[^{]+\{[^{]+font-family: Comic Sans;]m)
+  end
+
+  it "strips MS-specific CSS" do
+    FileUtils.rm_f "test.html"
+    FileUtils.rm_f "test.doc"
+    Asciidoctor.convert(<<~"INPUT", backend: :bsi, header_footer: true)
+      = Document title
+      Author
+      :docfile: test.adoc
+      :novalid:
+      :no-isobib:
+      :no-pdf:
+    INPUT
+    word = File.read("test.doc", encoding: "utf-8")
+    html = File.read("test.html", encoding: "utf-8")
+    expect(word).to match(%r[mso-style-name: "Intro Title";]m)
+    expect(html).not_to match(%r[mso-style-name: "Intro Title";]m)
+  end
+
+
+end