metanorma-iso 1.0.0

data/spec/isodoc/iso_spec.rb

@@ -0,0 +1,168 @@
+require "spec_helper"
+
+RSpec.describe IsoDoc::Iso do
+  system "rm -f test.html"
+  it "processes isodoc as ISO: HTML output" do
+    IsoDoc::Iso::HtmlConvert.new({}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html).to match(%r[\.Sourcecode[^{]+\{[^{]+font-family: "Courier New", monospace;]m)
+    expect(html).to match(%r[blockquote[^{]+\{[^{]+font-family: "Cambria", serif;]m)
+    expect(html).to match(%r[\.h2Annex[^{]+\{[^{]+font-family: "Cambria", serif;]m)
+  end
+
+  it "processes isodoc as ISO: alt HTML output" do
+  system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({alt: true}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html).to match(%r[\.Sourcecode[^{]+\{[^{]+font-family: "Space Mono", monospace;]m)
+    expect(html).to match(%r[blockquote[^{]+\{[^{]+font-family: "Lato", sans-serif;]m)
+    expect(html).to match(%r[\.h2Annex[^{]+\{[^{]+font-family: "Lato", sans-serif;]m)
+  end
+
+  it "processes isodoc as ISO: Chinese HTML output" do
+  system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({script: "Hans"}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html).to match(%r[\.Sourcecode[^{]+\{[^{]+font-family: "Courier New", monospace;]m)
+    expect(html).to match(%r[blockquote[^{]+\{[^{]+font-family: "SimSun", serif;]m)
+    expect(html).to match(%r[\.h2Annex[^{]+\{[^{]+font-family: "SimHei", sans-serif;]m)
+  end
+
+  it "processes isodoc as ISO: user nominated fonts" do
+  system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({bodyfont: "Zapf Chancery", headerfont: "Comic Sans", monospacefont: "Andale Mono"}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    html = File.read("test.html", encoding: "utf-8")
+    expect(html).to match(%r[\.Sourcecode[^{]+\{[^{]+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 "processes isodoc as ISO: Word output" do
+  system "rm -f test.doc"
+    IsoDoc::Iso::WordConvert.new({}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    html = File.read("test.doc", encoding: "utf-8")
+    expect(html).to match(%r[\.Sourcecode[^{]+\{[^{]+font-family: "Courier New", monospace;]m)
+    expect(html).to match(%r[Quote[^{]+\{[^{]+font-family: "Cambria", serif;]m)
+    expect(html).to match(%r[\.h2Annex[^{]+\{[^{]+font-family: "Cambria", serif;]m)
+  end
+
+  it "does not include IEV in references" do
+    expect(IsoDoc::Iso::HtmlConvert.new({}).convert("test", <<~"INPUT", true)).to be_equivalent_to <<~"OUTPUT"
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">
+  <eref bibitemid="IEV"/>
+  <eref bibitemid="ISO20483"/>
+  </p>
+    </foreword></preface>
+    <bibliography><references id="_normative_references" obligation="informative"><title>Normative References</title>
+          <bibitem type="international-standard" id="IEV">
+  <title format="text/plain" language="en" script="Latn">Electropedia: 
+  The World's Online Electrotechnical Vocabulary</title>
+  <source type="src">http://www.electropedia.org</source>
+  <docidentifier>IEV</docidentifier>
+  <date type="published"> <on>2018</on> </date>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <name>International Electrotechnical Commission</name>
+      <abbreviation>IEC</abbreviation>
+      <uri>www.iec.ch</uri>
+    </organization>
+  </contributor>
+  <language>en</language> <language>fr</language>
+  <script>Latn</script>
+  <copyright>
+    <from>2018</from>
+    <owner>
+      <organization>
+      <name>International Electrotechnical Commission</name>
+      <abbreviation>IEC</abbreviation>
+      <uri>www.iec.ch</uri>
+      </organization>
+    </owner>
+  </copyright>
+  <relation type="updates">
+    <bibitem>
+      <formattedref>IEC 60050</formattedref>
+    </bibitem>
+  </relation>
+</bibitem>
+<bibitem id="ISO20483" type="standard">
+  <title format="text/plain">Cereals and pulses</title>
+  <docidentifier>ISO 20483</docidentifier>
+  <date type="published"><from>2013</from><to>2014</to></date>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <name>International Organization for Standardization</name>
+    </organization>
+  </contributor>
+</bibitem>
+</references>
+</bibliography>
+    </iso-standard>
+    INPUT
+    #{HTML_HDR}
+                 <br/>
+             <div>
+               <h1 class="ForewordTitle">Foreword</h1>
+               <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">
+         <a href="#IEV">IEV:2018</a>
+         <a href="#ISO20483">ISO 20483:2013&#8211;2014</a>
+         </p>
+             </div>
+             <p class="zzSTDTitle1"/>
+             <div>
+               <h1>1.&#160; Normative references</h1>
+               <p>The following documents are referred to in the text in such a way that some or all of their content constitutes requirements of this document. For dated references, only the edition cited applies. For undated references, the latest edition of the referenced document (including any amendments) applies.</p>
+               <p id="ISO20483" class="NormRef">ISO 20483:2013&#8211;2014, <i> Cereals and pulses</i></p>
+             </div>
+           </div>
+         </body>
+       </html>
+
+    OUTPUT
+end
+
+end

data/spec/isodoc/metadata_spec.rb

@@ -0,0 +1,152 @@
+require "spec_helper"
+require "nokogiri"
+
+RSpec.describe IsoDoc::Iso::Metadata do
+  it "processes IsoXML metadata" do
+    c = IsoDoc::Iso::HtmlConvert.new({})
+    arr = c.convert_init(<<~"INPUT", "test", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    INPUT
+  expect(Hash[c.info(Nokogiri::XML(<<~"INPUT"), nil).sort]).to be_equivalent_to <<~"OUTPUT"
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <bibdata type="international-standard">
+  <title>
+    <title-intro language="en" format="text/plain">Cereals and pulses</title-intro>
+    <title-main language="en" format="text/plain">Specifications and test methods</title-main>
+    <title-part language="en" format="text/plain">Rice</title-part>
+  </title>
+  <title>
+    <title-intro language="fr" format="text/plain">Céréales et légumineuses</title-intro>
+    <title-main language="fr" format="text/plain">Spécification et méthodes d'essai</title-main>
+    <title-part language="fr" format="text/plain">Riz</title-part>
+  </title>
+  <docidentifier>
+    <project-number part="1">17301</project-number>
+    <tc-document-number>17301</tc-document-number>
+  </docidentifier>
+  <date type="published"><on>2011</on></date>
+  <date type="accessed"><on>2012</on></date>
+  <date type="created"><from>2010</from><to>2011</to></date>
+  <date type="activated"><on>2013</on></date>
+  <date type="obsoleted"><on>2014</on></date>
+  <contributor>
+    <role type="author"/>
+    <organization>
+      <abbreviation>ISO</abbreviation>
+    </organization>
+  </contributor>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <abbreviation>ISO</abbreviation>
+    </organization>
+  </contributor>
+  <language>en</language>
+  <script>Latn</script>
+  <status>
+    <stage>30</stage>
+    <substage>92</substage>
+    <iteration>3</iteration>
+  </status>
+  <copyright>
+    <from>2016</from>
+    <owner>
+      <organization>
+        <abbreviation>ISO</abbreviation>
+      </organization>
+    </owner>
+  </copyright>
+  <editorialgroup>
+    <technical-committee number="34">Food products</technical-committee>
+    <subcommittee number="4">Cereals and pulses</subcommittee>
+    <workgroup number="3">Rice Group</workgroup>
+    <secretariat>GB</secretariat>
+  </editorialgroup>
+</bibdata><version>
+  <edition>2</edition>
+  <revision-date>2016-05-01</revision-date>
+  <draft>0.4</draft>
+</version>
+</iso-standard>
+INPUT
+       {:accesseddate=>"2012", :activateddate=>"2013", :agency=>"ISO", :confirmeddate=>"XXX", :createddate=>"2010&ndash;2011", :docnumber=>"PreCD3 17301-1", :docsubtitle=>"C&#xe9;r&#xe9;ales et l&#xe9;gumineuses&nbsp;&mdash; Sp&#xe9;cification et m&#xe9;thodes d&#x27;essai&nbsp;&mdash; Partie&nbsp;1: Riz", :docsubtitleintro=>"C&#xe9;r&#xe9;ales et l&#xe9;gumineuses", :docsubtitlemain=>"Sp&#xe9;cification et m&#xe9;thodes d&#x27;essai", :docsubtitlepart=>"Partie&nbsp;1: Riz", :doctitle=>"Cereals and pulses&nbsp;&mdash; Specifications and test methods&nbsp;&mdash; Part&nbsp;1: Rice", :doctitleintro=>"Cereals and pulses", :doctitlemain=>"Specifications and test methods", :doctitlepart=>"Part&nbsp;1: Rice", :doctype=>"International Standard", :docyear=>"2016", :draft=>"0.4", :draftinfo=>" (draft 0.4, 2016-05-01)", :editorialgroup=>["TC 34", "SC 4", "WG 3"], :ics=>"XXX", :implementeddate=>"XXX", :issueddate=>"XXX", :obsoleteddate=>"2014", :obsoletes=>nil, :obsoletes_part=>nil, :publisheddate=>"2011", :revdate=>"2016-05-01", :sc=>"SC 4", :secretariat=>"GB", :stage=>"30", :stage_int=>30, :stageabbr=>"PreCD3", :tc=>"TC 34", :updateddate=>"XXX", :wg=>"WG 3"}
+OUTPUT
+  end
+
+  it "processes IsoXML metadata" do
+    c = IsoDoc::Iso::HtmlConvert.new({})
+    arr = c.convert_init(<<~"INPUT", "test", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    INPUT
+  expect(Hash[c.info(Nokogiri::XML(<<~"INPUT"), nil).sort]).to be_equivalent_to <<~"OUTPUT"
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <bibdata type="international-standard">
+  <title>
+    <title-intro language="en" format="text/plain">Cereals and pulses</title-intro>
+    <title-main language="en" format="text/plain">Specifications and test methods</title-main>
+    <title-part language="en" format="text/plain">Rice</title-part>
+  </title>
+  <title>
+    <title-intro language="fr" format="text/plain">Céréales et légumineuses</title-intro>
+    <title-main language="fr" format="text/plain">Spécification et méthodes d'essai</title-main>
+    <title-part language="fr" format="text/plain">Riz</title-part>
+  </title>
+  <docidentifier>
+    <project-number part="1" subpart="3">17301</project-number>
+    <tc-document-number>17301</tc-document-number>
+  </docidentifier>
+  <contributor>
+    <role type="author"/>
+    <organization>
+      <name>ISO</name>
+    </organization>
+  </contributor>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <abbreviation>ISO</abbreviation>
+     </organization>
+  </contributor>
+  <contributor>
+    <role type="publisher"/>
+    <organization>
+      <abbreviation>IEC</abbreviation>
+    </organization>
+  </contributor>
+  <language>en</language>
+  <script>Latn</script>
+  <status>
+    <stage>30</stage>
+    <substage>92</substage>
+  </status>
+  <copyright>
+    <from>2016</from>
+    <owner>
+      <organization>
+        <name>International Organization for Standardization</name>
+      </organization>
+    </owner>
+  </copyright>
+  <relation type="obsoletes">
+    <locality type="clause"><referenceFrom>3.1</referenceFrom></locality>
+    <docidentifier>IEC 8121</docidentifier>
+  </relation>
+  <editorialgroup>
+    <technical-committee number="34" type="ABC">Food products</technical-committee>
+    <subcommittee number="4" type="DEF">Cereals and pulses</subcommittee>
+    <workgroup number="3" type="GHI">Rice Group</workgroup>
+  </editorialgroup>
+  <ics><code>1.2.3</code></ics>
+  <ics><code>1.2.3</code></ics>
+</bibdata><version>
+  <edition>2</edition>
+  <revision-date>2016-05-01</revision-date>
+  <draft>12</draft>
+</version>
+</iso-standard>
+INPUT
+{:accesseddate=>"XXX", :agency=>"ISO/IEC", :confirmeddate=>"XXX", :createddate=>"XXX", :docnumber=>"CD 17301-1-3", :docsubtitle=>"C&#xe9;r&#xe9;ales et l&#xe9;gumineuses&nbsp;&mdash; Sp&#xe9;cification et m&#xe9;thodes d&#x27;essai&nbsp;&mdash; Partie&nbsp;1&ndash;3: Riz", :docsubtitleintro=>"C&#xe9;r&#xe9;ales et l&#xe9;gumineuses", :docsubtitlemain=>"Sp&#xe9;cification et m&#xe9;thodes d&#x27;essai", :docsubtitlepart=>"Partie&nbsp;1&ndash;3: Riz", :doctitle=>"Cereals and pulses&nbsp;&mdash; Specifications and test methods&nbsp;&mdash; Part&nbsp;1&ndash;3: Rice", :doctitleintro=>"Cereals and pulses", :doctitlemain=>"Specifications and test methods", :doctitlepart=>"Part&nbsp;1&ndash;3: Rice", :doctype=>"International Standard", :docyear=>"2016", :draft=>"12", :draftinfo=>" (draft 12, 2016-05-01)", :editorialgroup=>["ABC 34", "DEF 4", "GHI 3"], :ics=>"1.2.3, 1.2.3", :implementeddate=>"XXX", :issueddate=>"XXX", :obsoleteddate=>"XXX", :obsoletes=>"IEC 8121", :obsoletes_part=>"3.1", :publisheddate=>"XXX", :revdate=>"2016-05-01", :sc=>"DEF 4", :secretariat=>"XXXX", :stage=>"30", :stage_int=>30, :stageabbr=>"CD", :tc=>"ABC 34", :updateddate=>"XXX", :wg=>"GHI 3"}
+OUTPUT
+  end
+
+end

data/spec/isodoc/postproc_spec.rb

@@ -0,0 +1,405 @@
+require "spec_helper"
+
+RSpec.describe IsoDoc do
+  it "generates file based on string input" do
+    system "rm -f test.doc"
+    system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css", filename: "test"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    expect(File.exist?("test.html")).to be true
+    html = File.read("test.html")
+    expect(html).to match(%r{<title>test</title><style>})
+    expect(html).to match(%r{cdnjs\.cloudflare\.com/ajax/libs/mathjax/2\.7\.1/MathJax\.js})
+    expect(html).to match(/delimiters: \[\['\(#\(', '\)#\)'\]\]/)
+  end
+
+  it "generates HTML output docs with null configuration" do
+    system "rm -f test.doc"
+    system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    expect(File.exist?("test.html")).to be true
+    html = File.read("test.html")
+    expect(html).to match(%r{<title>test</title><style>})
+    expect(html).to match(%r{cdnjs\.cloudflare\.com/ajax/libs/mathjax/2\.7\.1/MathJax\.js})
+    expect(html).to match(/delimiters: \[\['\(#\(', '\)#\)'\]\]/)
+  end
+
+  it "generates Word output docs with null configuration" do
+    system "rm -f test.doc"
+    system "rm -f test.html"
+    IsoDoc::Iso::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <preface><foreword>
+    <note>
+  <p id="_f06fd0d1-a203-4f3d-a515-0bdba0f8d83f">These results are based on a study carried out on three different types of kernel.</p>
+</note>
+    </foreword></preface>
+    </iso-standard>
+    INPUT
+    expect(File.exist?("test.doc")).to be true
+    word = File.read("test.doc")
+    expect(word).to match(/<style>/)
+  end
+
+  it "generates HTML output docs with null configuration from file" do
+    system "rm -f spec/assets/iso.doc"
+    system "rm -f spec/assets/iso.html"
+    IsoDoc::Iso::HtmlConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("spec/assets/iso.xml", nil, false)
+    expect(File.exist?("spec/assets/iso.html")).to be true
+    html = File.read("spec/assets/iso.html")
+    expect(html).to match(/<style>/)
+    expect(html).to match(%r{https://use.fontawesome.com})
+    expect(html).to match(%r{libs/jquery})
+  end
+
+  it "generates Word output docs with null configuration from file" do
+    system "rm -f spec/assets/iso.doc"
+    IsoDoc::Iso::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("spec/assets/iso.xml", nil, false)
+    expect(File.exist?("spec/assets/iso.doc")).to be true
+    word = File.read("spec/assets/iso.doc")
+    expect(word).to match(/<w:WordDocument>/)
+    expect(word).to match(/<style>/)
+  end
+
+  it "converts annex subheadings to h2Annex class for Word" do
+    system "rm -f test.doc"
+    system "rm -f test.html"
+    IsoDoc::Iso::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <annex id="P" inline-header="false" obligation="normative">
+         <title>Annex</title>
+         <clause id="Q" inline-header="false" obligation="normative">
+         <title>Annex A.1</title>
+         </clause>
+                <appendix id="Q2" inline-header="false" obligation="normative">
+         <title>An Appendix</title>
+       </appendix>
+    </annex>
+    </iso-standard>
+    INPUT
+    word = File.read("test.doc").sub(/^.*<div class="WordSection3">/m, '<div class="WordSection3">').
+      sub(%r{<div style="mso-element:footnote-list"/>.*$}m, "")
+    expect(word).to be_equivalent_to <<~"OUTPUT"
+           <div class="WordSection3">
+               <p class="zzSTDTitle1"></p>
+               <br clear="all" style="mso-special-character:line-break;page-break-before:always"/>
+               <div class="Section3"><a name="P" id="P"></a>
+                 <h1 class="Annex"><b>Annex A</b><br/>(normative)<br/><br/><b>Annex</b></h1>
+                 <div><a name="Q" id="Q"></a>
+            <p class="h2Annex">A.1. Annex A.1</p>
+       </div>
+              <div><a name="Q2" id="Q2"></a>
+                <p class="h2Annex">Appendix 1. An Appendix</p>
+                </div>
+               </div>
+             </div>
+             <br clear="all" style="page-break-before:left;mso-break-type:section-break"/>
+        <div class="colophon"></div>
+    OUTPUT
+  end
+
+  it "populates Word template with terms reference labels" do
+    system "rm -f test.doc"
+    system "rm -f test.html"
+    IsoDoc::Iso::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <sections>
+    <terms id="_terms_and_definitions" obligation="normative"><title>Terms and Definitions</title>
+
+<term id="paddy1"><preferred>paddy</preferred>
+<definition><p id="_eb29b35e-123e-4d1c-b50b-2714d41e747f">rice retaining its husk after threshing</p></definition>
+<termsource status="modified">
+  <origin bibitemid="ISO7301" type="inline" citeas="ISO 7301:2011"><locality type="clause"><referenceFrom>3.1</referenceFrom></locality></origin>
+    <modification>
+    <p id="_e73a417d-ad39-417d-a4c8-20e4e2529489">The term "cargo rice" is shown as deprecated, and Note 1 to entry is not included here</p>
+  </modification>
+</termsource></term>
+
+</terms>
+</sections>
+</iso-standard>
+
+    INPUT
+    word = File.read("test.doc").sub(/^.*<div class="WordSection3">/m, '<div class="WordSection3">').
+      sub(%r{<div style="mso-element:footnote-list"/>.*$}m, "")
+    expect(word).to be_equivalent_to <<~"OUTPUT"
+           <div class="WordSection3">
+               <p class="zzSTDTitle1"></p>
+               <div><a name="_terms_and_definitions" id="_terms_and_definitions"></a><h1>1.<span style="mso-tab-count:1">&#xA0; </span>Terms and definitions</h1><p class="MsoNormal">For the purposes of this document,
+           the following terms and definitions apply.</p>
+       <p class="MsoNormal">ISO and IEC maintain terminological databases for use in
+       standardization at the following addresses:</p>
+
+       <ul>
+       <li style="mso-list:l3 level1 lfo1;" class="MsoNormal"> <p class="MsoNormal">ISO Online browsing platform: available at
+         <a href="http://www.iso.org/obp">http://www.iso.org/obp</a></p> </li>
+       <li style="mso-list:l3 level1 lfo1;" class="MsoNormal"> <p class="MsoNormal">IEC Electropedia: available at
+         <a href="http://www.electropedia.org">http://www.electropedia.org</a>
+       </p> </li> </ul>
+       <p class="TermNum"><a name="paddy1" id="paddy1"></a>1.1</p><p class="Terms" style="text-align:left;">paddy</p>
+       <p class="MsoNormal"><a name="_eb29b35e-123e-4d1c-b50b-2714d41e747f" id="_eb29b35e-123e-4d1c-b50b-2714d41e747f"></a>rice retaining its husk after threshing</p>
+       <p class="MsoNormal">[SOURCE: <a href="#ISO7301">ISO 7301:2011, 3.1</a>, modified &mdash; The term "cargo rice" is shown as deprecated, and Note 1 to entry is not included here]</p></div>
+             </div>
+             <br clear="all" style="page-break-before:left;mso-break-type:section-break"/>
+        <div class="colophon"></div>
+    OUTPUT
+  end
+
+  it "populates Word header" do
+    system "rm -f test.doc"
+    IsoDoc::Iso::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css", header: "spec/assets/header.html"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+               <bibdata type="article">
+                        <docidentifier>
+           <project-number part="1">1000</project-number>
+         </docidentifier>
+        </bibdata>
+</iso-standard>
+
+    INPUT
+    word = File.read("test.doc").sub(%r{^.*Content-Location: file:///C:/Doc/test_files/header.html}m, "Content-Location: file:///C:/Doc/test_files/header.html").
+      sub(/------=_NextPart.*$/m, "")
+    #expect(word).to include(%{Content-Location: file:///C:/Doc/test_files/header.html\nContent-Transfer-Encoding: base64\nContent-Type: text/html charset="utf-8" })
+    expect(word).to include(%{Content-Location: file:///C:/Doc/test_files/header.html})
+  end
+
+  it "populates Word ToC" do
+    system "rm -f test.doc"
+    IsoDoc::Iso::WordConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css", wordintropage: "spec/assets/wordintro.html"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+        <sections>
+               <clause inline-header="false" obligation="normative"><title>Clause 4</title><clause id="N" inline-header="false" obligation="normative">
+
+         <title>Introduction<bookmark id="Q"/> to this<fn reference="1">
+  <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6">Formerly denoted as 15 % (m/m).</p>
+</fn></title>
+       </clause>
+       <clause id="O" inline-header="false" obligation="normative">
+         <title>Clause 4.2</title>
+         <p>A<fn reference="1">
+  <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6">Formerly denoted as 15 % (m/m).</p>
+</fn></p>
+       </clause></clause>
+        </sections>
+        </iso-standard>
+
+    INPUT
+    word = File.read("test.doc").sub(/^.*An empty word intro page\./m, '').
+      sub(%r{<br clear="all" class="section"/>\s*<div class="WordSection3">.*$}m, "")
+    expect(word.gsub(/_Toc\d\d+/, "_Toc")).to be_equivalent_to <<~'OUTPUT'
+       <p class="MsoToc1"><span lang="EN-GB" xml:lang="EN-GB"><span style="mso-element:field-begin"></span><span style="mso-spacerun:yes">&#xA0;</span>TOC
+         \o "1-2" \h \z \u <span style="mso-element:field-separator"></span></span>
+       <span class="MsoHyperlink"><span lang="EN-GB" style="mso-no-proof:yes" xml:lang="EN-GB">
+       <a href="#_Toc">1.<span style="mso-tab-count:1">&#xA0; </span>Clause 4<span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">
+       <span style="mso-tab-count:1 dotted">. </span>
+       </span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">
+       <span style="mso-element:field-begin"></span></span>
+       <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"> PAGEREF _Toc \h </span>
+         <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"><span style="mso-element:field-separator"></span></span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">1</span>
+         <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"></span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"><span style="mso-element:field-end"></span></span></a></span></span></p>
+
+       <p class="MsoToc2">
+         <span class="MsoHyperlink">
+           <span lang="EN-GB" style="mso-no-proof:yes" xml:lang="EN-GB">
+       <a href="#_Toc">1.1. Introduction to this<span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">
+       <span style="mso-tab-count:1 dotted">. </span>
+       </span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">
+       <span style="mso-element:field-begin"></span></span>
+       <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"> PAGEREF _Toc \h </span>
+         <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"><span style="mso-element:field-separator"></span></span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">1</span>
+         <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"></span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"><span style="mso-element:field-end"></span></span></a></span>
+         </span>
+       </p>
+
+       <p class="MsoToc2">
+         <span class="MsoHyperlink">
+           <span lang="EN-GB" style="mso-no-proof:yes" xml:lang="EN-GB">
+       <a href="#_Toc">1.2. Clause 4.2<span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">
+       <span style="mso-tab-count:1 dotted">. </span>
+       </span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">
+       <span style="mso-element:field-begin"></span></span>
+       <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"> PAGEREF _Toc \h </span>
+         <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"><span style="mso-element:field-separator"></span></span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB">1</span>
+         <span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"></span><span lang="EN-GB" class="MsoTocTextSpan" xml:lang="EN-GB"><span style="mso-element:field-end"></span></span></a></span>
+         </span>
+       </p>
+
+       <p class="MsoToc1">
+         <span lang="EN-GB" xml:lang="EN-GB">
+           <span style="mso-element:field-end"></span>
+         </span>
+         <span lang="EN-GB" xml:lang="EN-GB">
+           <p class="MsoNormal">&#xA0;</p>
+         </span>
+       </p>
+
+
+               <p class="MsoNormal">&#xA0;</p>
+             </div>
+    OUTPUT
+  end
+
+  it "reorders footnote numbers in HTML" do
+    system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css", wordintropage: "spec/assets/wordintro.html"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+        <sections>
+               <clause inline-header="false" obligation="normative"><title>Clause 4</title><fn reference="3">
+  <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6">This is a footnote.</p>
+</fn><clause id="N" inline-header="false" obligation="normative">
+
+         <title>Introduction to this<fn reference="2">
+  <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6">Formerly denoted as 15 % (m/m).</p>
+</fn></title>
+       </clause>
+       <clause id="O" inline-header="false" obligation="normative">
+         <title>Clause 4.2</title>
+         <p>A<fn reference="1">
+  <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6">Formerly denoted as 15 % (m/m).</p>
+</fn></p>
+       </clause></clause>
+        </sections>
+        </iso-standard>
+    INPUT
+    html = File.read("test.html").sub(/^.*<main class="main-section">/m, '<main class="main-section">').
+      sub(%r{</main>.*$}m, "</main>")
+    expect(html).to be_equivalent_to <<~"OUTPUT"
+           <main class="main-section"><button onclick="topFunction()" id="myBtn" title="Go to top">Top</button>
+             <p class="zzSTDTitle1"></p>
+             <div>
+               <h1>1.&#xA0; Clause 4</h1>
+               <a rel="footnote" href="#fn:3" epub:type="footnote" id="fnref:1">
+                 <sup>1</sup>
+               </a>
+               <div id="N">
+
+                <h2>1.1. Introduction to this<a rel="footnote" href="#fn:2" epub:type="footnote" id="fnref:2"><sup>2</sup></a></h2>
+              </div>
+               <div id="O">
+                <h2>1.2. Clause 4.2</h2>
+                <p>A<a rel="footnote" href="#fn:2" epub:type="footnote"><sup>2</sup></a></p>
+              </div>
+             </div>
+             <aside id="fn:3" class="footnote">
+         <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6"><a rel="footnote" href="#fn:3" epub:type="footnote" id="fnref:1">
+                 <sup>1</sup>
+               </a>This is a footnote.</p>
+       <a href="#fnref:1">&#x21A9;</a></aside>
+             <aside id="fn:2" class="footnote">
+         <p id="_ff27c067-2785-4551-96cf-0a73530ff1e6"><a rel="footnote" href="#fn:2" epub:type="footnote" id="fnref:2"><sup>2</sup></a>Formerly denoted as 15 % (m/m).</p>
+       <a href="#fnref:2">&#x21A9;</a></aside>
+
+           </main>
+    OUTPUT
+  end
+
+  it "moves images in HTML" do
+    system "rm -f test.html"
+    system "rm -rf _images"
+    IsoDoc::Iso::HtmlConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("test", <<~"INPUT", false)
+        <iso-standard xmlns="http://riboseinc.com/isoxml">
+        <preface><foreword>
+         <figure id="_">
+         <name>Split-it-right sample divider</name>
+                  <image src="spec/assets/rice_image1.png" id="_" imagetype="PNG"/>
+                  <image src="spec/assets/rice_image1.png" id="_" width="20000" height="300000" imagetype="PNG"/>
+                  <image src="spec/assets/rice_image1.png" id="_" width="99" height="auto" imagetype="PNG"/>
+       </figure>
+       </foreword></preface>
+        </iso-standard>
+    INPUT
+    html = File.read("test.html").sub(/^.*<main class="main-section">/m, '<main class="main-section">').
+      sub(%r{</main>.*$}m, "</main>")
+    expect(`ls _images`).to match(/\.png$/)
+    expect(html.gsub(/\/[0-9a-f-]+\.png/, "/_.png")).to be_equivalent_to <<~"OUTPUT"
+           <main class="main-section"><button onclick="topFunction()" id="myBtn" title="Go to top">Top</button>
+             <br />
+             <div>
+               <h1 class="ForewordTitle">Foreword</h1>
+               <div id="_" class="figure">
+               <img src="_images/_.png" height="776" width="922" />
+<img src="_images/_.png" height="800" width="53" />
+<img src="_images/_.png" height="83" width="99" />
+       <p class="FigureTitle" align="center">Figure 1&#xA0;&#x2014; Split-it-right sample divider</p></div>
+             </div>
+             <p class="zzSTDTitle1"></p>
+           </main>
+    OUTPUT
+
+  end
+
+  it "processes IsoXML terms for HTML" do
+    system "rm -f test.doc"
+    system "rm -f test.html"
+    IsoDoc::Iso::HtmlConvert.new({wordstylesheet: "spec/assets/word.css", htmlstylesheet: "spec/assets/html.css"}).convert("test", <<~"INPUT", false)
+    <iso-standard xmlns="http://riboseinc.com/isoxml">
+    <sections>
+    <terms id="_terms_and_definitions" obligation="normative"><title>Terms and Definitions</title>
+
+<term id="paddy1"><preferred>paddy</preferred>
+<domain>rice</domain>
+<definition><p id="_eb29b35e-123e-4d1c-b50b-2714d41e747f">rice retaining its husk after threshing</p></definition>
+<termexample id="_bd57bbf1-f948-4bae-b0ce-73c00431f892">
+  <p id="_65c9a509-9a89-4b54-a890-274126aeb55c">Foreign seeds, husks, bran, sand, dust.</p>
+  <ul>
+  <li>A</li>
+  </ul>
+</termexample>
+<termexample id="_bd57bbf1-f948-4bae-b0ce-73c00431f894">
+  <ul>
+  <li>A</li>
+  </ul>
+</termexample>
+
+<termsource status="modified">
+  <origin bibitemid="ISO7301" type="inline" citeas="ISO 7301:2011"><locality type="clause"><referenceFrom>3.1</referenceFrom></locality></origin>
+    <modification>
+    <p id="_e73a417d-ad39-417d-a4c8-20e4e2529489">The term "cargo rice" is shown as deprecated, and Note 1 to entry is not included here</p>
+  </modification>
+</termsource></term>
+
+<term id="paddy"><preferred>paddy</preferred><admitted>paddy rice</admitted>
+<admitted>rough rice</admitted>
+<deprecates>cargo rice</deprecates>
+<definition><p id="_eb29b35e-123e-4d1c-b50b-2714d41e747f">rice retaining its husk after threshing</p></definition>
+<termexample id="_bd57bbf1-f948-4bae-b0ce-73c00431f893">
+  <ul>
+  <li>A</li>
+  </ul>
+</termexample>
+<termnote id="_671a1994-4783-40d0-bc81-987d06ffb74e">
+  <p id="_19830f33-e46c-42cc-94ca-a5ef101132d5">The starch of waxy rice consists almost entirely of amylopectin. The kernels have a tendency to stick together after cooking.</p>
+</termnote>
+<termnote id="_671a1994-4783-40d0-bc81-987d06ffb74f">
+<ul><li>A</li></ul>
+  <p id="_19830f33-e46c-42cc-94ca-a5ef101132d5">The starch of waxy rice consists almost entirely of amylopectin. The kernels have a tendency to stick together after cooking.</p>
+</termnote>
+<termsource status="identical">
+  <origin bibitemid="ISO7301" type="inline" citeas="ISO 7301:2011"><locality type="clause"><referenceFrom>3.1</referenceFrom></locality></origin>
+</termsource></term>
+</terms>
+</sections>
+</iso-standard>
+    INPUT
+    expect(File.exist?("test.html")).to be true
+    html = File.read("test.html")
+    expect(html).to match(%r{<h2 class="TermNum" id="paddy1">1\.1</h2>})
+    expect(html).to match(%r{<h2 class="TermNum" id="paddy">1\.2</h2>})
+  end
+
+end