html2doc 0.9.4 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dcc9db6cc57352a2e100bf1c1ff4127518d79fb67b958f52cd36580a4ab0b716
-  data.tar.gz: 93979a73373bad8d3405ce8dd621455b54514d3e2e0017d9d91096b038405edb
+  metadata.gz: 6dacc967f64994c36c4566869a97848278dce24d5318417dc0e9a901bb4fa9ae
+  data.tar.gz: d96f332a360c7aa04b8c8d5931274737b7c31349ab28cc7e04e34785e0675169
 SHA512:
-  metadata.gz: d5d29322e87a5ec048dfacd91fe3bb3ecc27478348062cae38cff7dfa3c30fb8fdca06a20cd248e87d50d48a483fa1e24e60bb3d195ab900fb80a65289090df4
-  data.tar.gz: 2803cb07d404a133fd7debee942c79e95154e7eb703527c96a00b8f10a03219d36f99b414c0ef964bd3beec01aed178524b2068b8b6ce45771e5246556a769ee
+  metadata.gz: 6e059a12f8d8bb192b31e4d573f6a661e9091a474a6da3c2c60e81e9ee99cf45251da0f5a5badf23ebd9cd913e0ce47e35fe3b7a3ac4e0610626af6c0eba27c6
+  data.tar.gz: dce3f36d0006eebc92e01a12e62dc826329487ebfd6186d425561991175cf6c7057f569bb1dc49ff14a9d471dedf64c236ae60da5cc265374329a2ec1f9dc302

data/README.adoc

@@ -25,7 +25,10 @@ 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.
 ** 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)

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 = "0.9.4".freeze
+  VERSION = "1.0.0".freeze
 end

data/spec/html2doc_spec.rb

@@ -613,6 +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>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 0.9.4
+  version: 1.0.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-01-30 00:00:00.000000000 Z
+date: 2020-03-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities