html2doc 1.1.1 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b92a72c9d0ee6005e38ab8de1f0cbc48455819955d34eb349fef1244504a9971
-  data.tar.gz: 52b07e9c1720bc2bf7a7196e0f650c62b81bf534535795bb2a136f2e79829416
+  metadata.gz: 64cb262d3176610f0887cc69bab66fa2a3a7ca8445f8ad493d9d65c455a091d6
+  data.tar.gz: 468dc7a8fb687cdbf6db1497cf9d9b5e164687b7d460a5eac1fb983b4673672b
 SHA512:
-  metadata.gz: af4b84183859fd83ac500c6c1ac28e76d49ec7fb48c8a4cf49bc3543909b913e78c8293918b34e21e9e68f2dc78a500824337677ae1aea54bcf7cbecebd9363d
-  data.tar.gz: 9e0bd48390458ec57dcc9650643a9332a549148a1297b37962e37399453d95132e39c69cb94ea13fcc70f9d6bc273fccf742da61e6f4a3025710182df1d65144
+  metadata.gz: 2a47bbe5df7ae0767ad2f4ccf52c1f96b8e27fc32d08b3b7b25e5051a3d229b29b9852a51c052a701990f9be6dbf0efc97795ea0c0ff4b3745b63f5a0c7adb4f
+  data.tar.gz: c4c10a84141889d820fd8d2afc273122b28372794edd9fdb3e60aee28773350d3e545f2a3efb75c4d28eff350d367b020d01d6e5cc2874a957ca612124e78fd4

data/.github/workflows/rake.yml

@@ -16,19 +16,9 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        ruby: [ '2.7', '2.6', '2.5', '2.4' ]
+        ruby: [ '3.0', '2.7', '2.6', '2.5' ]
         os: [ ubuntu-latest, windows-latest, macos-latest ]
         experimental: [ false ]
-        include:
-          - ruby: '3.0'
-            os: 'ubuntu-latest'
-            experimental: true
-          - ruby: '3.0'
-            os: 'windows-latest'
-            experimental: true
-          - ruby: '3.0'
-            os: 'macos-latest'
-            experimental: true
     steps:
       - uses: actions/checkout@v2
         with:

data/.hound.yml

@@ -1,3 +1,5 @@
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 ruby:
-  Enabled: true
+  enabled: true
   config_file: .rubocop.yml

data/.rubocop.yml

@@ -1,12 +1,10 @@
-# This project follows the Ribose OSS style guide.
-# https://github.com/riboseinc/oss-guides
-# All project-specific additions and overrides should be specified in this file.
+# Auto-generated by Cimas: Do not edit it manually!
+# See https://github.com/metanorma/cimas
 inherit_from:
   - https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
 
 # local repo-specific modifications
+# ...
 
 AllCops:
-  DisplayCopNames: false
-  StyleGuideCopsOnly: false
-  TargetRubyVersion: 2.4
+  TargetRubyVersion: 2.5

data/README.adoc

@@ -58,11 +58,12 @@ There there are two other Microsoft Word vendors in the Ruby ecosystem.
 --
 require "html2doc"
 
-Html2Doc.process(result, filename: filename, stylesheet: stylesheet, header_filename: header_filename, dir: dir, asciimathdelims: asciimathdelims, liststyles: liststyles)
+Html2Doc.process(result, filename: filename, imagedir: imagedir, stylesheet: stylesheet, header_filename: header_filename, dir: dir, asciimathdelims: asciimathdelims, liststyles: liststyles)
 --
 
 result:: is the Html document to be converted into Word, as a string.
 filename:: is the name the document is to be saved as, without a file suffix
+imagedir:: base directory for local image file names in source XML
 stylesheet:: is the full path filename of the CSS stylesheet for Microsoft Word-specific styles. If this is not provided, the program will used the default stylesheet included in the gem, `lib/html2doc/wordstyle.css`. The stylsheet provided must match this stylesheet; you can obtain one by saving a Word document with your desired styles to HTML, and extracting the style definitions from the HTML document header.
 header_filename:: is the filename of the HTML document containing header and footer for the document, as well as footnote/endnote separators; if there is none, use nil. To generate your own such document, save a Word document with headers/footers and/or footnote/endnote separators as an HTML document; the `header.html` will be in the `{filename}.fld` folder generated along with the HTML. A sample file is available at https://github.com/metanorma/metanorma-iso/blob/master/lib/asciidoctor/iso/word/header.html
 dir:: is the folder that any ancillary files (images, headers, filelist) are to be saved to. If not provided, it will be created as `{filename}_files`. Anything in the directory will be attached to the Word document; so this folder should only contain the images that accompany the document. (If the images are elsewhere on the local drive, the gem will move them into the folder. External URL images are left alone, and are not downloaded.)

data/bin/html2doc

@@ -24,5 +24,5 @@ Html2Doc.process(
   File.read(ARGV[0], encoding: "utf-8"),
   filename: ARGV[0].gsub(/\.html?$/, ""),
   stylesheet: options[:stylesheet],
-  header: options[:header]
+  header: options[:header],
 )

data/bin/rspec

@@ -1,5 +1,5 @@
 #!/usr/bin/env ruby
-  
+
 # This file was generated by Bundler.
 #
 # The application 'rspec' is installed as part of a gem, and

data/html2doc.gemspec

@@ -1,5 +1,4 @@
-
-lib = File.expand_path("../lib", __FILE__)
+lib = File.expand_path("lib", __dir__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "html2doc/version"
 
@@ -16,23 +15,23 @@ Gem::Specification.new do |spec|
     This gem is in active development.
   DESCRIPTION
 
-  spec.homepage      = "https://github.com/metanorma/html2doc"
-  spec.licenses       = ["CC-BY-SA-3.0", "BSD-2-Clause"]
+  spec.homepage = "https://github.com/metanorma/html2doc"
+  spec.licenses = ["CC-BY-SA-3.0", "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.required_ruby_version = Gem::Requirement.new(">= 2.5.0")
 
+  spec.add_dependency "asciimath", "~> 2.0.2"
   spec.add_dependency "htmlentities", "~> 4.3.4"
   spec.add_dependency "image_size"
   spec.add_dependency "mime-types"
-  spec.add_dependency "nokogiri", "~> 1.10.4"
+  spec.add_dependency "nokogiri", "~> 1.12"
+  spec.add_dependency "plane1converter", "~> 0.0.1"
   spec.add_dependency "thread_safe"
   spec.add_dependency "uuidtools"
-  spec.add_dependency "asciimath", "~> 2.0.2"
-  spec.add_dependency "plane1converter", "~> 0.0.1"
 
   spec.add_development_dependency "byebug", "~> 9.1"
   spec.add_development_dependency "equivalent-xml", "~> 0.6"
@@ -40,8 +39,8 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "guard-rspec", "~> 4.7"
   spec.add_development_dependency "rake", "~> 12.0"
   spec.add_development_dependency "rspec", "~> 3.6"
+  spec.add_development_dependency "rspec-match_fuzzy", "~> 0.1.3"
   spec.add_development_dependency "rubocop", "~> 1.5.2"
   spec.add_development_dependency "simplecov", "~> 0.15"
   spec.add_development_dependency "timecop", "~> 0.9"
-  spec.add_development_dependency "rspec-match_fuzzy", "~> 0.1.3"
 end

data/lib/html2doc/base.rb

@@ -53,7 +53,7 @@ module Html2Doc
 
   def self.cleanup(docxml, hash)
     namespace(docxml.root)
-    image_cleanup(docxml, hash[:dir1], File.dirname(hash[:filename]))
+    image_cleanup(docxml, hash[:dir1], hash[:imagedir])
     mathml_to_ooml(docxml)
     lists(docxml, hash[:liststyles])
     footnotes(docxml)
@@ -106,6 +106,7 @@ module Html2Doc
     doc.gsub!(%r{></o:lock>}, "/>")
     doc.gsub!(%r{></v:imagedata>}, "/>")
     doc.gsub!(%r{></w:wrap>}, "/>")
+    doc.gsub!(%r{<(/)?m:(span|em)\b}, "<\\1\\2")
     doc.gsub!(%r{&tab;|&amp;tab;},
               '<span style="mso-tab-count:1">&#xA0; </span>')
     doc.split(%r{(<m:oMath>|</m:oMath>)}).each_slice(4).map do |a|
@@ -127,7 +128,7 @@ module Html2Doc
     <meta http-equiv=Content-Type content="text/html; charset=utf-8"/>
   XML
 
-  def self.define_head1(docxml, dir)
+  def self.define_head1(docxml, _dir)
     docxml.xpath("//*[local-name() = 'head']").each do |h|
       h.children.first.add_previous_sibling <<~XML
         #{PRINT_VIEW}
@@ -147,7 +148,7 @@ module Html2Doc
     end
   end
 
-  def self.stylesheet(filename, header_filename, fn)
+  def self.stylesheet(_filename, _header_filename, fn)
     (fn.nil? || fn.empty?) and
       fn = File.join(File.dirname(__FILE__), "wordstyle.css")
     stylesheet = File.read(fn, encoding: "UTF-8")

data/lib/html2doc/lists.rb

@@ -2,30 +2,29 @@ require "uuidtools"
 require "asciimath"
 require "htmlentities"
 require "nokogiri"
-require "uuidtools"
 
 module Html2Doc
-  def self.style_list(li, level, liststyle, listnumber)
+  def self.style_list(elem, level, liststyle, listnumber)
     return unless liststyle
 
-    if li["style"]
-      li["style"] += ";"
+    if elem["style"]
+      elem["style"] += ";"
     else
-      li["style"] = ""
+      elem["style"] = ""
     end
-    li["style"] += "mso-list:#{liststyle} level#{level} lfo#{listnumber};"
+    elem["style"] += "mso-list:#{liststyle} level#{level} lfo#{listnumber};"
   end
 
-  def self.list_add1(li, liststyles, listtype, level)
+  def self.list_add1(elem, liststyles, listtype, level)
     if %i[ul ol].include? listtype
-      list_add(li.xpath(".//ul") - li.xpath(".//ul//ul | .//ol//ul"),
+      list_add(elem.xpath(".//ul") - elem.xpath(".//ul//ul | .//ol//ul"),
                liststyles, :ul, level + 1)
-      list_add(li.xpath(".//ol") - li.xpath(".//ul//ol | .//ol//ol"),
+      list_add(elem.xpath(".//ol") - elem.xpath(".//ul//ol | .//ol//ol"),
                liststyles, :ol, level + 1)
     else
-      list_add(li.xpath(".//ul") - li.xpath(".//ul//ul | .//ol//ul"),
+      list_add(elem.xpath(".//ul") - elem.xpath(".//ul//ul | .//ol//ul"),
                liststyles, listtype, level + 1)
-      list_add(li.xpath(".//ol") - li.xpath(".//ul//ol | .//ol//ol"),
+      list_add(elem.xpath(".//ol") - elem.xpath(".//ul//ol | .//ol//ol"),
                liststyles, listtype, level + 1)
     end
   end
@@ -47,45 +46,43 @@ module Html2Doc
     end
   end
 
-  def self.list2para(u)
-    return if u.xpath("./li").empty?
+  def self.list2para(list)
+    return if list.xpath("./li").empty?
 
-    u.xpath("./li").first["class"] ||= "MsoListParagraphCxSpFirst"
-    u.xpath("./li").last["class"] ||= "MsoListParagraphCxSpLast"
-    u.xpath("./li/p").each { |p| p["class"] ||= "MsoListParagraphCxSpMiddle" }
-    u.xpath("./li").each do |l|
+    list.xpath("./li").first["class"] ||= "MsoListParagraphCxSpFirst"
+    list.xpath("./li").last["class"] ||= "MsoListParagraphCxSpLast"
+    list.xpath("./li/p").each { |p| p["class"] ||= "MsoListParagraphCxSpMiddle" }
+    list.xpath("./li").each do |l|
       l.name = "p"
       l["class"] ||= "MsoListParagraphCxSpMiddle"
       l&.first_element_child&.name == "p" and
         l.first_element_child.replace(l.first_element_child.children)
     end
-    u.replace(u.children)
+    list.replace(list.children)
   end
 
   TOPLIST = "[not(ancestor::ul) and not(ancestor::ol)]".freeze
 
-  def self.lists1(docxml, liststyles, k)
-    case k
+  def self.lists1(docxml, liststyles, style)
+    case style
     when :ul then list_add(docxml.xpath("//ul[not(@class)]#{TOPLIST}"),
                            liststyles, :ul, 1)
     when :ol then list_add(docxml.xpath("//ol[not(@class)]#{TOPLIST}"),
                            liststyles, :ol, 1)
     else
-      list_add(docxml.xpath("//ol[@class = '#{k}']#{TOPLIST} | "\
-                            "//ul[@class = '#{k}']#{TOPLIST}"),
-      liststyles, k, 1)
+      list_add(docxml.xpath("//ol[@class = '#{style}']#{TOPLIST} | "\
+                            "//ul[@class = '#{style}']#{TOPLIST}"),
+      liststyles, style, 1)
     end
   end
 
   def self.lists_unstyled(docxml, liststyles)
-    if liststyles.has_key?(:ul)
+    liststyles.has_key?(:ul) and
       list_add(docxml.xpath("//ul#{TOPLIST}[not(@seen)]"),
                liststyles, :ul, 1)
-    end
-    if liststyles.has_key?(:ol)
+    liststyles.has_key?(:ol) and
       list_add(docxml.xpath("//ol#{TOPLIST}[not(@seen)]"),
                liststyles, :ul, 1)
-    end
     docxml.xpath("//ul[@seen] | //ol[@seen]").each do |l|
       l.delete("seen")
     end

data/lib/html2doc/math.rb

@@ -25,13 +25,18 @@ module Html2Doc
 
     m = doc.split(/(#{Regexp.escape(delims[0])}|#{Regexp.escape(delims[1])})/)
     m.each_slice(4).map.with_index do |(*a), i|
-      i % 500 == 0 && m.size > 1000 && i > 0 and
-        warn "MathML #{i} of #{(m.size / 4).floor}"
+      progress_conv(i, 500, (m.size / 4).floor, 1000, "AsciiMath")
       a[2].nil? || a[2] = asciimath_to_mathml1(a[2])
       a.size > 1 ? a[0] + a[2] : a[0]
     end.join
   end
 
+  def self.progress_conv(idx, step, total, threshold, msg)
+    return unless (idx % step).zero? && total > threshold && idx.positive?
+
+    warn "#{msg} #{idx} of #{total}"
+  end
+
   def self.unwrap_accents(doc)
     doc.xpath("//*[@accent = 'true']").each do |x|
       x.elements.length > 1 or next
@@ -69,18 +74,20 @@ module Html2Doc
     math
   end
 
+  HTML_NS = 'xmlns="http://www.w3.org/1999/xhtml"'.freeze
+
   def self.unitalic(math)
     math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'p']]").each do |x|
-      x.wrap("<span style='font-style:normal;'></span>")
+      x.wrap("<span #{HTML_NS} style='font-style:normal;'></span>")
     end
     math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'bi']]").each do |x|
-      x.wrap("<span class='nostem' style='font-weight:bold;'><em></em></span>")
+      x.wrap("<span #{HTML_NS} class='nostem' style='font-weight:bold;'><em></em></span>")
     end
     math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'i']]").each do |x|
-      x.wrap("<span class='nostem'><em></em></span>")
+      x.wrap("<span #{HTML_NS} class='nostem'><em></em></span>")
     end
     math.xpath(".//xmlns:r[xmlns:rPr[not(xmlns:scr)]/xmlns:sty[@m:val = 'b']]").each do |x|
-      x.wrap("<span style='font-style:normal;font-weight:bold;'></span>")
+      x.wrap("<span #{HTML_NS} style='font-style:normal;font-weight:bold;'></span>")
     end
     math.xpath(".//xmlns:r[xmlns:rPr/xmlns:scr[@m:val = 'monospace']]").each do |x|
       to_plane1(x, :monospace)
@@ -128,20 +135,30 @@ module Html2Doc
     docnamespaces = docxml.collect_namespaces
     m = docxml.xpath("//*[local-name() = 'math']")
     m.each_with_index do |x, i|
-      i % 100 == 0 && m.size > 500 && i > 0 and
-        warn "Math OOXML #{i} of #{m.size}"
-      element = ooxml_cleanup(x, docnamespaces)
-      doc = Nokogiri::XML::Document::new
-      doc.root = element
-      ooxml = unitalic(esc_space(@xsltemplate.transform(doc))).to_s
-        .gsub(/<\?[^>]+>\s*/, "")
-        .gsub(/ xmlns(:[^=]+)?="[^"]+"/, "")
-        .gsub(%r{<(/)?(?!span)(?!em)([a-z])}, "<\\1m:\\2")
-      ooxml = uncenter(x, ooxml)
-      x.swap(ooxml)
+      progress_conv(i, 100, m.size, 500, "Math OOXML")
+      mathml_to_ooml1(x, docnamespaces)
     end
   end
 
+  # We need span and em not to be namespaced. Word can't deal with explicit 
+  # namespaces.
+  # We will end up stripping them out again under Nokogiri 1.11, which correctly
+  # insists on inheriting namespace from parent.
+  def self.ooml_clean(xml)
+    xml.to_s
+      .gsub(/<\?[^>]+>\s*/, "")
+      .gsub(/ xmlns(:[^=]+)?="[^"]+"/, "")
+      .gsub(%r{<(/)?(?!span)(?!em)([a-z])}, "<\\1m:\\2")
+  end
+
+  def self.mathml_to_ooml1(xml, docnamespaces)
+    doc = Nokogiri::XML::Document::new
+    doc.root = ooxml_cleanup(xml, docnamespaces)
+      ooxml = ooml_clean(unitalic(esc_space(@xsltemplate.transform(doc))))
+    ooxml = uncenter(xml, ooxml)
+    xml.swap(ooxml)
+  end
+
   # escape space as &#x32;; we are removing any spaces generated by
   # XML indentation
   def self.esc_space(xml)
@@ -157,7 +174,7 @@ module Html2Doc
   # left/right if parent is so tagged
   def self.uncenter(math, ooxml)
     alignnode = math.at(".//ancestor::*[@style][local-name() = 'p' or "\
-                     "local-name() = 'div' or local-name() = 'td']/@style")
+                        "local-name() = 'div' or local-name() = 'td']/@style")
     return ooxml unless alignnode && (math.next == nil && math.previous == nil)
 
     %w(left right).each do |dir|

data/lib/html2doc/mime.rb

@@ -43,7 +43,7 @@ module Html2Doc
   def self.mime_type(item)
     types = MIME::Types.type_for(item)
     type = types ? types.first.to_s : 'text/plain; charset="utf-8"'
-    type = type + ' charset="utf-8"' if /^text/.match(type) && types
+    type = %(#{type} charset="utf-8") if /^text/.match(type) && types
     type
   end
 
@@ -77,14 +77,14 @@ module Html2Doc
   end
 
   # max width for Word document is 400, max height is 680
-  def self.image_resize(i, path, maxheight, maxwidth)
-    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.nil? || 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?
+  def self.image_resize(img, path, maxheight, maxwidth)
+    realsize = ImageSize.path(path).size
+    s = [img["width"].to_i, img["height"].to_i]
+    s = realsize if s[0].zero? && s[1].zero?
+    return [nil, nil] if realsize.nil? || 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
     s = [maxwidth, (s[1] * maxwidth / s[0]).ceil] if s[0] > maxwidth
     s
@@ -100,16 +100,18 @@ module Html2Doc
     warn "#{src}: SVG not supported" if /\.svg$/i.match?(src)
   end
 
+  def self.localname(src, localdir)
+    %r{^([A-Z]:)?/}.match?(src) ? src : File.join(localdir, src)
+  end
+
   # only processes locally stored images
   def self.image_cleanup(docxml, dir, localdir)
     docxml.traverse do |i|
       next unless i.element? && %w(img v:imagedata).include?(i.name)
-      #warnsvg(i["src"])
-      next if /^http/.match i["src"]
+      next if /^http/.match? i["src"]
       next if %r{^data:(image|application)/[^;]+;base64}.match? i["src"]
 
-      local_filename = %r{^([A-Z]:)?/}.match(i["src"]) ? i["src"] :
-        File.join(localdir, i["src"])
+      local_filename = localname(i["src"], localdir)
       new_filename = "#{mkuuid}#{File.extname(i['src'])}"
       FileUtils.cp local_filename, File.join(dir, new_filename)
       i["width"], i["height"] = image_resize(i, local_filename, 680, 400)
@@ -130,12 +132,9 @@ module Html2Doc
     if a.size == 2 && !(/ src="https?:/.match a[1]) &&
         !(%r{ src="data:(image|application)/[^;]+;base64}.match a[1])
       m = / src=['"](?<src>[^"']+)['"]/.match a[1]
-      #warnsvg(m[:src])
       m2 = /\.(?<suffix>[a-zA-Z_0-9]+)$/.match m[:src]
       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, new_filename)
+      FileUtils.cp localname(m[:src], localdir), File.join(dir, new_filename)
       a[1].sub!(%r{ src=['"](?<src>[^"']+)['"]}, " src='cid:#{new_filename}'")
     end
     a.join

data/lib/html2doc/notes.rb

@@ -56,19 +56,22 @@ module Html2Doc
 
     set_footnote_link_attrs(elem, idx)
     if elem.at("./span[@class = 'MsoFootnoteReference']")
-      elem.children.each do |c|
-        if c.name == "span" && c["class"] == "MsoFootnoteReference"
-          c.replace(FN)
-        else
-          c.wrap("<span class='MsoFootnoteReference'></span>")
-        end
-      end
-    else
-      elem.children = FN
+      process_footnote_link1(elem)
+    else elem.children = FN
     end
     footnote << transform_footnote_text(note)
   end
 
+  def self.process_footnote_link1(elem)
+    elem.children.each do |c|
+      if c.name == "span" && c["class"] == "MsoFootnoteReference"
+        c.replace(FN)
+      else
+        c.wrap("<span class='MsoFootnoteReference'></span>")
+      end
+    end
+  end
+
   def self.transform_footnote_text(note)
     note["id"] = ""
     note.xpath(".//div").each { |div| div.replace(div.children) }

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 module Html2Doc
-  VERSION = "1.1.1".freeze
+  VERSION = "1.2.0".freeze
 end

data/lib/html2doc.rb

@@ -4,6 +4,3 @@ require_relative "html2doc/mime"
 require_relative "html2doc/notes"
 require_relative "html2doc/math"
 require_relative "html2doc/lists"
-#require_relative "asciimath/parser"
-#require_relative "asciimath/mathml"
-#require_relative "asciimath/html"