html2doc 0.9.3 → 1.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 34f2ebe1b5fb0faf57bcb2b73c63ca4d4f4916f0f5daa47d5ec50ca69238ca3e
-  data.tar.gz: 16479f56aba64e5c2839546720fe6f2d998d24db42009b3849c788d111ca09d2
+  metadata.gz: 8aa0a8504ff535fa43595e3839d7de18fbb8a7cbb3b2ed303d1965656814dfe3
+  data.tar.gz: a56eb2333cd28420e7f8001f37edc9db5dc9b07f21eed192b02c35184e45c7af
 SHA512:
-  metadata.gz: '09cb8b389a2d70dced3d4660b344b7cbc64409017404482c105a2f6f25daa528e27627f4c52b69a74a959b535d87f5d14822ad177156a01232af5466f55d8eeb'
-  data.tar.gz: 66b314e12b36f509bcdfade0e24bae06ed5333af57f956c22840a2a1c3b8c8172a891ef30d91072a8e8b18a2e2e34c45146473bcc3e235cb7614a47d8c92a1dd
+  metadata.gz: '01291816da883daad14800ad3cdb41bc611c5698c9bec518c52fd0a67f133f8fd367d1b129ceb8827f214834fb970a5bbaa2f4e7d4af404bd221aca2dec61e78'
+  data.tar.gz: fd8119ee883d255d10e9882f3541adae2f57c9631dcec451dde230d252e101096afe0b3dd090ebe8cf31cc45f2339e452c3d55f08ac13110c1b41f11faac8ba5

data/.github/workflows/macos.yml

@@ -1,17 +1,28 @@
-# Auto-generated !!! Do not edit it manually
-# use ci-master https://github.com/metanorma/metanorma-build-scripts
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: macos
 
-on: [push, pull_request]
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths-ignore:
+      - .github/workflows/ubuntu.yml
+      - .github/workflows/windows.yml
 
 jobs:
   test-macos:
     name: Test on Ruby ${{ matrix.ruby }} macOS
     runs-on: macos-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
       fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
+        experimental: [false]
+        include:
+          - ruby: '2.7'
+            experimental: true
     steps:
       - uses: actions/checkout@master
       - name: Use Ruby

data/.github/workflows/ubuntu.yml

@@ -1,17 +1,30 @@
-# Auto-generated !!! Do not edit it manually
-# use ci-master https://github.com/metanorma/metanorma-build-scripts
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: ubuntu
 
-on: [push, pull_request]
+on:
+  push:
+    branches: [ master ]
+    tags:
+      - '*'
+  pull_request:
+    paths-ignore:
+      - .github/workflows/macos.yml
+      - .github/workflows/windows.yml
 
 jobs:
   test-linux:
     name: Test on Ruby ${{ matrix.ruby }} Ubuntu
     runs-on: ubuntu-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
       fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
+        experimental: [false]
+        include:
+          - ruby: '2.7'
+            experimental: true
     steps:
       - uses: actions/checkout@master
       - name: Use Ruby
@@ -21,8 +34,20 @@ jobs:
           architecture: 'x64'
       - name: Update gems
         run: |
-          gem install bundler 
+          gem install bundler
           bundle install --jobs 4 --retry 3
       - name: Run specs
         run: |
           bundle exec rake
+      - name: Trigger dependent repositories
+        if: github.ref == 'refs/heads/master' && matrix.ruby == '2.6'
+        env:
+          GH_USERNAME: ${{ secrets.PAT_USERNAME }}
+          GH_ACCESS_TOKEN: ${{ secrets.PAT_TOKEN }}
+        run: |
+          curl -LO --retry 3 https://raw.githubusercontent.com/metanorma/metanorma-build-scripts/master/trigger-gh-actions.sh
+          [[ -f ".github/workflows/dependent_repos.env" ]] && source .github/workflows/dependent_repos.env
+          for repo in $DEPENDENT_REPOS
+          do
+            sh trigger-gh-actions.sh $ORGANISATION $repo $GH_USERNAME $GH_ACCESS_TOKEN $GITHUB_REPOSITORY "{ \"ref\": \"${GITHUB_REF}\" }"
+          done

data/.github/workflows/windows.yml

@@ -1,17 +1,28 @@
-# Auto-generated !!! Do not edit it manually
-# use ci-master https://github.com/metanorma/metanorma-build-scripts
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 name: windows
 
-on: [push, pull_request]
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths-ignore:
+      - .github/workflows/macos.yml
+      - .github/workflows/ubuntu.yml
 
 jobs:
   test-windows:
     name: Test on Ruby ${{ matrix.ruby }} Windows
     runs-on: windows-latest
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
       fail-fast: false
       matrix:
         ruby: [ '2.6', '2.5', '2.4' ]
+        experimental: [false]
+        include:
+          - ruby: '2.7'
+            experimental: true
     steps:
       - uses: actions/checkout@master
       - name: Use Ruby
@@ -22,9 +33,8 @@ jobs:
       - name: Update gems
         shell: pwsh
         run: |
-          gem install bundler 
+          gem install bundler
           bundle config --local path vendor/bundle
-          bundle update
           bundle install --jobs 4 --retry 3
       - name: Run specs
         run: |

data/README.adoc

@@ -3,8 +3,9 @@
 https://github.com/metanorma/html2doc/workflows/main/badge.svg
 
 image:https://img.shields.io/gem/v/html2doc.svg["Gem Version", link="https://rubygems.org/gems/html2doc"]
-image:https://travis-ci.com/metanorma/html2doc.svg["Build Status", link="https://travis-ci.com/metanorma/html2doc"]
-image:https://ci.appveyor.com/api/projects/status/aspj42o70q3dnkf1?svg=true["Appveyor Build Status", link="https://ci.appveyor.com/project/metanorma/html2doc"]
+image:https://github.com/metanorma/html2doc/workflows/ubuntu/badge.svg["Ubuntu Build Status", link="https://github.com/metanorma/html2doc/actions?query=workflow%3Aubuntu"]
+image:https://github.com/metanorma/html2doc/workflows/macos/badge.svg["OSX Build Status", link="https://github.com/metanorma/html2doc/actions?query=workflow%3Amacos"]
+image:https://github.com/metanorma/html2doc/workflows/windows/badge.svg["Windows Build Status", link="https://github.com/metanorma/html2doc/actions?query=workflow%3Awindows"]
 image:https://codeclimate.com/github/metanorma/html2doc/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/metanorma/html2doc"]
 image:https://img.shields.io/github/issues-pr-raw/metanorma/html2doc.svg["Pull Requests", link="https://github.com/metanorma/html2doc/pulls"]
 image:https://img.shields.io/github/commits-since/metanorma/html2doc/latest.svg["Commits since latest",link="https://github.com/metanorma/html2doc/releases"]
@@ -23,9 +24,12 @@ This work is driven by the Word document generation procedure documented in http
 
 The gem currently does the following:
 
-* Convert any AsciiMath and MathML to Word's native mathematical formatting language, OOXML. Word supports copy-pasting MathML into Word and converting it into OOXML; however the conversion is not infallible (we have found problems with `\sum`: Word claims parameters were missing, and inserting dotted squares to indicate as much), and you may need to post-edit the OOXML.
+* Convert any AsciiMath and MathML to Word's native mathematical formatting language, OOXML. Word supports copy-pasting MathML into Word and converting it into OOXML; however the conversion is not infallible (we have in the past found problems with `\sum`: Word claims parameters were missing, and inserting dotted squares to indicate as much), and you may need to post-edit the OOXML.
 ** The gem does attempt to repair the MathML input, to bring it in line with Word's OOXML's expectations. If you find any issues with AsciiMath or MathML input, please raise an issue.
-* Identify any footnotes in the document (defined as hyperlinks with attributes `class = "Footnote"` or `epub:type = "footnote"`), and render them as Microsoft Word footnotes.
+* Identify any footnotes in the document (defined as hyperlinks with attributes `class = "Footnote"` or `epub:type = "footnote"`), and render them as Microsoft Word footnotes. 
+** The corresponding footnote content is any `div` or `aside` element with the same `@id` attribute as the footnote points to; e.g. `<a href="#ftn1" epub:type="footnote"><sup>3</sup></a></span>`, pointing to `<aside id="ftn3">`.
+** By default, the footnote hyperlink contents are overwritten with the autonumbering element: `<a href="#ftn1" epub:type="footnote"><sup>1</sup></a>` is replaced with `<a style='mso-footnote-id:ftn1' href='#_ftn1' name='_ftnref1' title='' id='_ftnref1'><span class='MsoFootnoteReference'><span style='mso-special-character:footnote'/></span>`
+** If the footnote hyperlink already contains (as a child) an element marked up as `<span class='MsoFootnoteReference'>`, only that span is replaced by the Microsoft autonumber element; any text surrounding it is preserved in both the footnote reference and the footnote target. For example, `<a href="#ftn1" epub:type="footnote"><span class='MsoFootnoteReference'>1</span>)</a>` will render as the footnote _1)_, both in the link and the target.
 * Resize any local images in the HTML file to fit within the maximum page size. (Word will otherwise crash on reading the document.)
 * Optionally apply list styles with predefined bullet and numbering from a Word CSS to the unordered and ordered lists in the document, restarting numbering for each ordered list.
 * Convert all lists to native Word HTML rendering (using paragraphs with `MsoListParagraphCxSpFirst, MsoListParagraphCxSpMiddle, MsoListParagraphCxSpLast` styles)
@@ -113,7 +117,7 @@ The bad news is that Word's understanding of HTML is HTML 4. In order for bookma
 
 The good news with generating a Word document via HTML is that Word understands CSS, and you can determine much of what the Word document looks like by manipulating that CSS. That extends to features that are not part of HTML CSS: if you want to work out how to get Word to do something in CSS, save a Word document that already does what you want as HTML, and inspect the HTML and CSS you get.
 
-The bad news is that Word's implementation of CSS is poorly documented -- even if Office HTML is documented in a 1300 page document (online at https://stigmortenmyre.no/mso/, https://www.rodriguezcommaj.com/assets/resources/microsoft-office-html-and-xml-reference.pdf), and the CSS selectors are only partially and selectively implemented. For list styles, for example, `mso-level-text` governs how the list label is displayed; but it is only recognised in a `@list` style: it is ignored in a CSS rule like `ol li`, or in a `style` attribute on a node. Working out the right CSS for what you want will take some trial and error, and you are better placed to try to do things Word's way than the right way.
+The bad news is that Word's implementation of CSS is poorly documented -- even if Office HTML is documented in a 1300 page document (online at https://stigmortenmyre.no/mso/, https://www.rodriguezcommaj.com/assets/resources/microsoft-office-html-and-xml-reference.pdf), and the CSS selectors are only partially and selectively implemented. For list styles, for example, `mso-level-text` governs how the list label is displayed; but it is only recognised in a `@list` style: it is ignored in a CSS rule like `ol li`, or in a `style` attribute on a node. CSS selectors only support classes, in ancestor relations: `p.class1 ol.class2` is supported, but `#id1` is not, and neither is `p > ol`. Working out the right CSS for what you want will take some trial and error, and you are better placed to try to do things Word's way than the right way.
 
 === XSLT
 

data/html2doc.gemspec

@@ -31,7 +31,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "nokogiri", ">= 1.10.4"
   spec.add_dependency "thread_safe"
   spec.add_dependency "uuidtools"
-  spec.add_dependency "asciimath", "~> 1.0.9"
+  spec.add_dependency "asciimath", "~> 2.0.0"
 
   spec.add_development_dependency "byebug", "~> 9.1"
   spec.add_development_dependency "equivalent-xml", "~> 0.6"

data/lib/html2doc/lists.rb

@@ -2,7 +2,7 @@ require "uuidtools"
 require "asciimath"
 require "htmlentities"
 require "nokogiri"
-require "pp"
+require "uuidtools"
 
 module Html2Doc
   def self.style_list(li, level, liststyle, listnumber)
@@ -15,13 +15,8 @@ module Html2Doc
     li["style"] += "mso-list:#{liststyle} level#{level} lfo#{listnumber};"
   end
 
-  def self.list_add(xpath, liststyles, listtype, level)
-    xpath.each_with_index do |list, i|
-      @listnumber += 1 if level == 1
-      list["seen"] = true if level == 1
-      (list.xpath(".//li") - list.xpath(".//ol//li | .//ul//li")).each do |li|
-        style_list(li, level, liststyles[listtype], @listnumber)
-        if [:ul, :ol].include? listtype
+  def self.list_add1(li, liststyles, listtype, level)
+    if [:ul, :ol].include? listtype
           list_add(li.xpath(".//ul") - li.xpath(".//ul//ul | .//ol//ul"),
                    liststyles, :ul, level + 1)
           list_add(li.xpath(".//ol") - li.xpath(".//ul//ol | .//ol//ol"),
@@ -32,6 +27,20 @@ module Html2Doc
           list_add(li.xpath(".//ol") - li.xpath(".//ul//ol | .//ol//ol"),
                    liststyles, listtype, level + 1)
         end
+  end
+
+  def self.list_add(xpath, liststyles, listtype, level)
+    xpath.each_with_index do |list, i|
+      @listnumber += 1 if level == 1
+      list["seen"] = true if level == 1
+      list["id"] ||= UUIDTools::UUID.random_create
+      (list.xpath(".//li") - list.xpath(".//ol//li | .//ul//li")).each do |li|
+        style_list(li, level, liststyles[listtype], @listnumber)
+        list_add1(li, liststyles, listtype, level)
+      end
+      list.xpath(".//ul[not(ancestor::li/ancestor::*/@id = '#{list['id']}')] | "\
+                 ".//ol[not(ancestor::li/ancestor::*/@id = '#{list['id']}')]").each do |li|
+        list_add1(li.parent, liststyles, listtype, level-1)
       end
     end
   end

data/lib/html2doc/mime.rb

@@ -68,6 +68,7 @@ module Html2Doc
     realSize = ImageSize.path(path).size
     s = [i["width"].to_i, i["height"].to_i]
     s = realSize if s[0].zero? && s[1].zero?
+    return [nil, nil] if realSize[0].nil? || realSize[1].nil?
     s[1] = s[0] * realSize[1] / realSize[0] if s[1].zero? && !s[0].zero?
     s[0] = s[1] * realSize[0] / realSize[1] if s[0].zero? && !s[1].zero?
     s = [(s[0] * maxheight / s[1]).ceil, maxheight] if s[1] > maxheight
@@ -87,10 +88,9 @@ module Html2Doc
 
   # only processes locally stored images
   def self.image_cleanup(docxml, dir, localdir)
-    #docxml.xpath(IMAGE_PATH).each do |i|
     docxml.traverse do |i|
       next unless i.element? && %w(img v:imagedata).include?(i.name)
-      warnsvg(i["src"])
+      #warnsvg(i["src"])
       next if /^http/.match i["src"]
       next if %r{^data:image/[^;]+;base64}.match i["src"]
       local_filename = %r{^([A-Z]:)?/}.match(i["src"]) ? i["src"] :
@@ -115,12 +115,12 @@ module Html2Doc
     if a.size == 2 && !(/ src="https?:/.match a[1]) &&
         !(%r{ src="data:image/[^;]+;base64}.match a[1])
       m = / src=['"](?<src>[^"']+)['"]/.match a[1]
-      warnsvg(m[:src])
+      #warnsvg(m[:src])
       m2 = /\.(?<suffix>[a-zA-Z_0-9]+)$/.match m[:src]
-      new_filename = "file:///C:/Doc/#{filename}_files/#{mkuuid}.#{m2[:suffix]}"
+      new_filename = "#{mkuuid}.#{m2[:suffix]}"
       old_filename = %r{^([A-Z]:)?/}.match(m[:src]) ? m[:src] : File.join(localdir, m[:src])
-      FileUtils.cp old_filename, File.join(dir, "#{mkuuid}.#{m2[:suffix]}")
-      a[1].sub!(%r{ src=['"](?<src>[^"']+)['"]}, " src='#{new_filename}'")
+      FileUtils.cp old_filename, File.join(dir, new_filename)
+      a[1].sub!(%r{ src=['"](?<src>[^"']+)['"]}, " src='file:///C:/Doc/#{filename}_files/#{new_filename}'")
     end
     a.join
   end

data/lib/html2doc/notes.rb

@@ -15,7 +15,7 @@ module Html2Doc
     body = docxml.at("//body")
     list = body.add_child("<div style='mso-element:footnote-list'/>")
     footnotes.each_with_index do |f, i|
-      fn = list.first.add_child(footnote_container(i + 1))
+      fn = list.first.add_child(footnote_container(docxml, i + 1))
       f.parent = fn.first
       footnote_div_to_p(f)
     end
@@ -33,13 +33,16 @@ module Html2Doc
     end
   end
 
-  def self.footnote_container(i)
+  FN = "<span class='MsoFootnoteReference'>"\
+    "<span style='mso-special-character:footnote'/></span>".freeze
+
+  def self.footnote_container(docxml, i)
+    ref = docxml&.at("//a[@href='#_ftn#{i}']")&.children&.to_xml(indent: 0).
+      gsub(/>\n</, "><") || FN
     <<~DIV
       <div style='mso-element:footnote' id='ftn#{i}'>
         <a style='mso-footnote-id:ftn#{i}' href='#_ftn#{i}'
-           name='_ftnref#{i}' title='' id='_ftnref#{i}'><span
-           class='MsoFootnoteReference'><span
-           style='mso-special-character:footnote'></span></span></div>
+           name='_ftnref#{i}' title='' id='_ftnref#{i}'>#{ref.strip}</a></div>
     DIV
   end
 
@@ -49,8 +52,17 @@ module Html2Doc
     note = docxml.at("//*[@name = '#{href}' or @id = '#{href}']")
     return false if note.nil?
     set_footnote_link_attrs(a, i)
-    a.children = "<span class='MsoFootnoteReference'>"\
-      "<span style='mso-special-character:footnote'/></span>"
+    if a.at("./span[@class = 'MsoFootnoteReference']")
+      a.children.each do |c|
+        if c.name == "span" and c["class"] == "MsoFootnoteReference"
+          c.replace(FN)
+        else
+          c.wrap("<span class='MsoFootnoteReference'></span>")
+        end
+      end
+    else
+      a.children = FN
+    end
     fn << transform_footnote_text(note)
   end
 

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 module Html2Doc
-  VERSION = "0.9.3".freeze
+  VERSION = "1.0.3".freeze
 end

data/spec/html2doc_spec.rb

@@ -372,11 +372,11 @@ RSpec.describe Html2Doc do
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
       to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
-    #{word_body("
+    #{word_body(%{
        <div><m:oMath>
-       #{ASCII_MATH}<m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>\"integer\"</m:t></m:r>
+       <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><m:r><m:t>=</m:t></m:r><m:sSup><m:e><m:r><m:t>(</m:t></m:r><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:r><m:t>(</m:t></m:r><m:r><m:t>n+1</m:t></m:r><m:r><m:t>)</m:t></m:r></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f><m:r><m:t>)</m:t></m:r></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>"integer"</m:t></m:r><m:r><m:t>)</m:t></m:r>
        </m:oMath>
-       </div>", '<div style="mso-element:footnote-list"/>')}
+       </div>}, '<div style="mso-element:footnote-list"/>')}
     #{WORD_FTR1}
     OUTPUT
   end
@@ -388,7 +388,7 @@ RSpec.describe Html2Doc do
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
     #{word_body("
        <div><m:oMath>
-       <m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>integer</m:t></m:r>
+       <m:r><m:t>text</m:t></m:r><m:r><m:rPr><m:nor></m:nor></m:rPr><m:t>integer</m:t></m:r><m:r><m:t>)</m:t></m:r>
        </m:oMath>
        </div>", '<div style="mso-element:footnote-list"/>')}
     #{WORD_FTR1}
@@ -400,11 +400,11 @@ RSpec.describe Html2Doc do
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
       to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
-    #{word_body("
-       <div style=\"text-align:left;\"><m:oMathPara><m:oMathParaPr><m:jc m:val=\"left\"/></m:oMathParaPr><m:oMath>
-       #{ASCII_MATH}
+    #{word_body(%{
+       <div style="text-align:left;"><m:oMathPara><m:oMathParaPr><m:jc m:val="left"/></m:oMathParaPr><m:oMath>
+       <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><m:r><m:t>=</m:t></m:r><m:sSup><m:e><m:r><m:t>(</m:t></m:r><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:r><m:t>(</m:t></m:r><m:r><m:t>n+1</m:t></m:r><m:r><m:t>)</m:t></m:r></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f><m:r><m:t>)</m:t></m:r></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
        </m:oMath>
-       </m:oMathPara></div>", '<div style="mso-element:footnote-list"/>')}
+       </m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
     #{WORD_FTR1}
     OUTPUT
   end
@@ -414,11 +414,11 @@ RSpec.describe Html2Doc do
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
       to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
-    #{word_body("
-       <div style=\"text-align:right;\"><m:oMathPara><m:oMathParaPr><m:jc m:val=\"right\"/></m:oMathParaPr><m:oMath>
-       #{ASCII_MATH}
+    #{word_body(%{
+       <div style="text-align:right;"><m:oMathPara><m:oMathParaPr><m:jc m:val="right"/></m:oMathParaPr><m:oMath>
+       <m:nary><m:naryPr><m:chr m:val="&#x2211;"></m:chr><m:limLoc m:val="undOvr"></m:limLoc><m:grow m:val="on"></m:grow><m:subHide m:val="off"></m:subHide><m:supHide m:val="off"></m:supHide></m:naryPr><m:sub><m:r><m:t>i=1</m:t></m:r></m:sub><m:sup><m:r><m:t>n</m:t></m:r></m:sup><m:e><m:sSup><m:e><m:r><m:t>i</m:t></m:r></m:e><m:sup><m:r><m:t>3</m:t></m:r></m:sup></m:sSup></m:e></m:nary><m:r><m:t>=</m:t></m:r><m:sSup><m:e><m:r><m:t>(</m:t></m:r><m:f><m:fPr><m:type m:val="bar"></m:type></m:fPr><m:num><m:r><m:t>n</m:t></m:r><m:r><m:t>(</m:t></m:r><m:r><m:t>n+1</m:t></m:r><m:r><m:t>)</m:t></m:r></m:num><m:den><m:r><m:t>2</m:t></m:r></m:den></m:f><m:r><m:t>)</m:t></m:r></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup>
        </m:oMath>
-       </m:oMathPara></div>", '<div style="mso-element:footnote-list"/>')}
+       </m:oMathPara></div>}, '<div style="mso-element:footnote-list"/>')}
     #{WORD_FTR1}
     OUTPUT
   end
@@ -566,10 +566,12 @@ RSpec.describe Html2Doc do
     OUTPUT
   end
 
+=begin
   it "warns about SVG" do
     simple_body = '<img src="https://example.com/19160-6.svg">'
     expect{ Html2Doc.process(html_input(simple_body), filename: "test") }.to output("https://example.com/19160-6.svg: SVG not supported\n").to_stderr
   end
+=end
 
   it "processes epub:type footnotes" do
     simple_body = '<div>This is a very simple 
@@ -611,6 +613,26 @@ RSpec.describe Html2Doc do
     OUTPUT
   end
 
+  it "processes footnotes with text wrapping the footnote reference" do
+        simple_body = '<div>This is a very simple
+     document<a class="footnote" href="#a1">(<span class="MsoFootnoteReference">1</span>)</a> allegedly<a class="footnote" href="#a2">2</a></div>
+     <aside id="a1">Footnote</aside>
+     <aside id="a2">Other Footnote</aside>'
+    Html2Doc.process(html_input(simple_body), filename: "test")
+    expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
+      to match_fuzzy(<<~OUTPUT)
+    #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
+    #{word_body('<div>This is a very simple
+    document<a class="footnote" href="#_ftn1" style="mso-footnote-id:ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference">(</span><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span><span class="MsoFootnoteReference">)</span></a> allegedly<a class="footnote" href="#_ftn2" style="mso-footnote-id:ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a></div>',
+    '<div style="mso-element:footnote-list"><div style="mso-element:footnote" id="ftn1">
+<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn1" href="#_ftn1" name="_ftnref1" title="" id="_ftnref1"><span class="MsoFootnoteReference">(</span><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span><span class="MsoFootnoteReference">)</span></a>Footnote</p></div>
+<div style="mso-element:footnote" id="ftn2">
+<p id="" class="MsoFootnoteText"><a style="mso-footnote-id:ftn2" href="#_ftn2" name="_ftnref2" title="" id="_ftnref2"><span class="MsoFootnoteReference"><span style="mso-special-character:footnote"></span></span></a>Other Footnote</p></div>
+</div>')}
+    #{WORD_FTR1}
+    OUTPUT
+  end
+
   it "extracts paragraphs from footnotes" do
     simple_body = '<div>This is a very simple
      document<a class="footnote" href="#a1">1</a> allegedly<a class="footnote" href="#a2">2</a></div>
@@ -633,15 +655,16 @@ RSpec.describe Html2Doc do
 
   it "labels lists with list styles" do
     simple_body = <<~BODY
-      <div><ul>
-      <li><div><p><ol><li><ul><li><p><ol><li><ol><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
+      <div><ul id="0">
+      <li><div><p><ol id="1"><li><ul id="2"><li><p><ol id="3"><li><ol id="4"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li><div><ul id="5"><li>C</li></ul></div>
     BODY
     Html2Doc.process(html_input(simple_body), filename: "test", liststyles: {ul: "l1", ol: "l2"})
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
       to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
     #{word_body('<div>
-    <p style="mso-list:l1 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p></div>',
+    <p style="mso-list:l1 level1 lfo1;" class="MsoListParagraphCxSpFirst"><div><p class="MsoNormal"><p style="mso-list:l2 level2 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level4 lfo1;" class="MsoListParagraphCxSpFirst"><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpFirst">A</p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpMiddle">B<p class="MsoListParagraphCxSpMiddle">B2</p></p><p style="mso-list:l2 level5 lfo1;" class="MsoListParagraphCxSpLast">C</p></p></p></p></div></p><div><p style="mso-list:l1 level1 lfo2;" class="MsoListParagraphCxSpFirst">C</p></div>
+    </div>',
     '<div style="mso-element:footnote-list"/>')}
     #{WORD_FTR1}
     OUTPUT
@@ -651,8 +674,8 @@ RSpec.describe Html2Doc do
   it "restarts numbering of lists with list styles" do
     simple_body = <<~BODY
       <div>
-      <ol><li><div><p><ol><li><ul><li><p><ol><li><ol><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol>
-      <ol><li><div><p><ol><li><ul><li><p><ol><li><ol><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol></div>
+      <ol id="1"><li><div><p><ol id="2"><li><ul id="3"><li><p><ol id="4"><li><ol id="5"><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol>
+      <ol id="6"><li><div><p><ol id="7"><li><ul id="8"><li><p><ol id="9"><li><ol id="10"><li>A</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ol></div>
     BODY
     Html2Doc.process(html_input(simple_body), filename: "test", liststyles: {ul: "l1", ol: "l2"})
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).
@@ -668,12 +691,12 @@ RSpec.describe Html2Doc do
 
     it "labels lists with multiple list styles" do
     simple_body = <<~BODY
-      <div><ul class="steps">
-      <li><div><p><ol><li><ul><li><p><ol><li><ol><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
-      <div><ul>
-      <li><div><p><ol><li><ul><li><p><ol><li><ol><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
-      <div><ul class="other">
-      <li><div><p><ol><li><ul><li><p><ol><li><ol><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
+      <div><ul class="steps" id="0">
+      <li><div><p><ol id="1"><li><ul id="2"><li><p><ol id="3"><li><ol id="4"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
+      <div><ul id="5">
+      <li><div><p><ol id="6"><li><ul id="7"><li><p><ol id="8"><li><ol id="9"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
+      <div><ul class="other" id="10">
+      <li><div><p><ol id="11"><li><ul id="12"><li><p><ol id="13"><li><ol id="14"><li>A</li><li><p>B</p><p>B2</p></li><li>C</li></ol></li></ol></p></li></ul></li></ol></p></div></li></ul></div>
     BODY
     Html2Doc.process(html_input(simple_body), filename: "test", liststyles: {ul: "l1", ol: "l2", steps: "l3"})
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 0.9.3
+  version: 1.0.3
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-12-24 00:00:00.000000000 Z
+date: 2020-06-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -100,14 +100,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.9
+        version: 2.0.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.9
+        version: 2.0.0
 - !ruby/object:Gem::Dependency
   name: byebug
   requirement: !ruby/object:Gem::Requirement