html2doc 1.3.0.1 → 1.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6f471eed9c61de156ee7aa0dd279d21335fd193dda721727197c2dc508a7bf56
-  data.tar.gz: 79365ba28433486f8d6442aa939729af2456c570baccbb88b9ddb835d1f94172
+  metadata.gz: 56d8c42bd609845f35a5a994fed43d12ebc9fb0d8d303fd60f9a064f4da26a7b
+  data.tar.gz: e9310883dbc5991640e66a1c085d6bcb2ca87155449326b7076489e78d64d187
 SHA512:
-  metadata.gz: ccdfd5dc149461e651cf9a0ca22504052e76f3980c75498b05f1720451694acc41c8a91c16f92a2611e553a9d93b9caa482c93b47cdbd95288767588895a22ac
-  data.tar.gz: 14b4833c7d5fd9f179b9101b240acca1f2f2e8e40ef6521f0bd244d6a5f526255a2a34928960403b28575685e1d6e29d84156577a54fa13bedea1048eb9eeafb
+  metadata.gz: 8d7076b196634dc81a3942a59155c7c80da21b9eb68721dab437170c54876f970b80448fa31f520648145eca9ace1fea0c7751be04021f9c1f95fe0bf3fa64ce
+  data.tar.gz: 532b022bda9cc4fb88eafeb467c7d6d26ba8dc5ea21f5553ba251e8b92469de6e906f5947a3fdb3bbee241cbaea8805f3477978bbe78af359a6bb7140399a971

data/lib/html2doc/math.rb

@@ -140,7 +140,7 @@ module Html2Doc
     end
   end
 
-  # We need span and em not to be namespaced. Word can't deal with explicit 
+  # 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.
@@ -154,11 +154,28 @@ module Html2Doc
   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 = ooml_clean(unitalic(esc_space(accent_tr(@xsltemplate.transform(doc)))))
     ooxml = uncenter(xml, ooxml)
     xml.swap(ooxml)
   end
 
+  def self.accent_tr(xml)
+    xml.xpath(".//*[local-name()='accPr']/*[local-name()='chr']").each do |x|
+      x["m:val"] &&= accent_tr1(x["m:val"])
+      x["val"] &&= accent_tr1(x["val"])
+    end
+    xml
+  end
+
+  def self.accent_tr1(accent)
+    case accent
+    when "\u2192" then "\u20D7"
+    when "^" then "\u0302"
+    when "~" then "\u0303"
+    else accent
+    end
+  end
+
   # escape space as 2; we are removing any spaces generated by
   # XML indentation
   def self.esc_space(xml)
@@ -180,7 +197,7 @@ module Html2Doc
     %w(left right).each do |dir|
       if alignnode.text.include? ("text-align:#{dir}")
         ooxml = "<m:oMathPara><m:oMathParaPr><m:jc "\
-          "m:val='#{dir}'/></m:oMathParaPr>#{ooxml}</m:oMathPara>"
+                "m:val='#{dir}'/></m:oMathParaPr>#{ooxml}</m:oMathPara>"
       end
     end
     ooxml

data/lib/html2doc/mime.rb

@@ -107,12 +107,13 @@ module Html2Doc
   # only processes locally stored images
   def self.image_cleanup(docxml, dir, localdir)
     docxml.traverse do |i|
+      src = i["src"]
       next unless i.element? && %w(img v:imagedata).include?(i.name)
-      next if /^http/.match? i["src"]
-      next if %r{^data:(image|application)/[^;]+;base64}.match? i["src"]
+      next if src.nil? || src.empty? || /^http/.match?(src)
+      next if %r{^data:(image|application)/[^;]+;base64}.match? src
 
-      local_filename = localname(i["src"], localdir)
-      new_filename = "#{mkuuid}#{File.extname(i['src'])}"
+      local_filename = localname(src, localdir)
+      new_filename = "#{mkuuid}#{File.extname(src)}"
       FileUtils.cp local_filename, File.join(dir, new_filename)
       i["width"], i["height"] = image_resize(i, local_filename, 680, 400)
       i["src"] = File.join(File.basename(dir), new_filename)

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 module Html2Doc
-  VERSION = "1.3.0.1".freeze
+  VERSION = "1.3.1".freeze
 end

data/spec/html2doc_spec.rb

@@ -461,7 +461,7 @@ RSpec.describe Html2Doc do
       OUTPUT
   end
 
-  it "unwraps accent in MathML" do
+  it "unwraps and converts accent in MathML" do
     Html2Doc.process(html_input("<div><math xmlns='http://www.w3.org/1998/Math/MathML'>
                                 <mover accent='true'><mrow><mi>p</mi></mrow><mrow><mo>^</mo></mrow></mover>
 </math></div>"), filename: "test", asciimathdelims: ["{{", "}}"])
@@ -469,7 +469,7 @@ RSpec.describe Html2Doc do
       .to match_fuzzy(<<~OUTPUT)
         #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
         #{word_body('<div><m:oMath>
-                <m:acc><m:accPr><m:chr m:val="^"></m:chr></m:accPr><m:e><m:r><m:t>p</m:t></m:r></m:e></m:acc>
+                <m:acc><m:accPr><m:chr m:val="&#x302;"></m:chr></m:accPr><m:e><m:r><m:t>p</m:t></m:r></m:e></m:acc>
                 </m:oMath>
                 </div>', '<div style="mso-element:footnote-list"/>')}
         #{WORD_FTR1}

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 1.3.0.1
+  version: 1.3.1
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-01-22 00:00:00.000000000 Z
+date: 2022-02-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: asciimath