RubyGems - html2doc - Versions diffs - 1.5.4 → 1.6.0 - Mend

html2doc 1.5.4 → 1.6.0

Files changed (8) hide show

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 74b05f46f1fd365f9ff0766e95d884bd2959c01b92c70d4a080651adfc2e8d3c
-  data.tar.gz: f70eb009e705ff767b34922fc0444740be8dde80da8b78c503784e02be0e4560
+  metadata.gz: 47535bf46876ee49a732b6c136f78b58a9ac009f880b95c5a73c8770293f3735
+  data.tar.gz: a052e0c3ba3ee27ca208b2624d7a832cba67bcc959f1ec5da36f9a7049c26c35
 SHA512:
-  metadata.gz: e3d93501d63bd27ed6e5245cb18dbc49013fcecd83bc57acf3a5d3c797636b928b91e148e33e8326f10f77f9b94a7175d85294eb86a1b4b2261aafb7dfe9d7a4
-  data.tar.gz: 4cbb8887089e622b9d9d1fd82dc4e5fd4e8e81a28a59dcf02ccce22cb3c9e6e7c4c7802177259557c268d697ced17ec09e4181e82c0dc851a613553e7f5b58c1
+  metadata.gz: '096dc5a7fe4b35e5afdec632f37b28f9980fcbcba4222e1ec1eb81fe4653a62cc00c5d9b90ed38ae54d4320ea8bf7e0fd0698625045504d371bcb90fb6247a54'
+  data.tar.gz: 7aeebef3892dc2273bc4ab9899624fc113b1989c3af097204b4f73eb250a7d52e8b3cfe62439e84fb179c1e9bbc96563af669d87f56b15dd82b4fc99953a2227

data/lib/html2doc/base.rb CHANGED Viewed

@@ -30,8 +30,7 @@ class Html2Doc
   end
   def process_header(headerfile)
-    return if headerfile.nil?
+    headerfile.nil? and return
     doc = File.read(headerfile, encoding: "utf-8")
     doc = header_image_cleanup(doc, @dir1, @filename,
                                File.dirname(@filename))
@@ -54,7 +53,7 @@ class Html2Doc
   end
   def process_html(result)
-    docxml = to_xhtml(asciimath_to_mathml(result, @asciimathdelims))
+    docxml = to_xhtml(result)
     define_head(cleanup(docxml))
     msword_fix(from_xhtml(docxml))
   end
@@ -66,6 +65,7 @@ class Html2Doc
   end
   def cleanup(docxml)
+    locate_landscape(docxml)
     namespace(docxml.root)
     image_cleanup(docxml, @dir1, @imagedir)
     mathml_to_ooml(docxml)
@@ -76,76 +76,11 @@ class Html2Doc
     docxml
   end
-  NOKOHEAD = <<~HERE.freeze
-    <!DOCTYPE html SYSTEM
-    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-    <html xmlns="http://www.w3.org/1999/xhtml">
-    <head> <title></title> <meta charset="UTF-8" /> </head>
-    <body> </body> </html>
-  HERE
-  def to_xhtml(xml)
-    xml.gsub!(/<\?xml[^>]*>/, "")
-    unless /<!DOCTYPE /.match? xml
-      xml = '<!DOCTYPE html SYSTEM
-          "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' + xml
-    end
-    xml = xml.gsub(/<!--\s*\[([^\]]+)\]>/, "<!-- MSWORD-COMMENT \\1 -->")
-      .gsub(/<!\s*\[endif\]\s*-->/, "<!-- MSWORD-COMMENT-END -->")
-    Nokogiri::XML.parse(xml)
-  end
-  DOCTYPE = <<~"DOCTYPE".freeze
-    <!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
-  DOCTYPE
-  def from_xhtml(xml)
-    xml.to_xml.sub(%{ xmlns="http://www.w3.org/1999/xhtml"}, "")
-      .sub(DOCTYPE, "").gsub(%{ />}, "/>")
-      .gsub(/<!-- MSWORD-COMMENT (.+?) -->/, "<!--[\\1]>")
-      .gsub(/<!-- MSWORD-COMMENT-END -->/, "<![endif]-->")
-      .gsub("\n--&gt;\n", "\n-->\n")
-  end
-  def msword_fix(doc)
-    # brain damage in MSWord parser
-    doc.gsub!(%r{<w:DoNotOptimizeForBrowser></w:DoNotOptimizeForBrowser>},
-              "<w:DoNotOptimizeForBrowser/>")
-    doc.gsub!(%r{<span style="mso-special-character:footnote"/>},
-              '<span style="mso-special-character:footnote"></span>')
-    doc.gsub!(%r{<div style="mso-element:footnote-list"></div>},
-              '<div style="mso-element:footnote-list"/>')
-    doc.gsub!(%r{(<a style="mso-comment-reference:[^>/]+)/>}, "\\1></a>")
-    doc.gsub!(%r{<link rel="File-List"}, "<link rel=File-List")
-    doc.gsub!(%r{<meta http-equiv="Content-Type"},
-              "<meta http-equiv=Content-Type")
-    doc.gsub!(%r{></m:jc>}, "/>")
-    doc.gsub!(%r{></v:stroke>}, "/>")
-    doc.gsub!(%r{></v:f>}, "/>")
-    doc.gsub!(%r{></v:path>}, "/>")
-    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|
-      a.size > 2 and a[2] = a[2].gsub(/>\s+</, "><")
-      a
-    end.join
-  end
-  PRINT_VIEW = <<~XML.freeze
-    <xml>
-    <w:WordDocument>
-    <w:View>Print</w:View>
-    <w:Zoom>100</w:Zoom>
-    <w:DoNotOptimizeForBrowser/>
-    </w:WordDocument>
-    </xml>
-    <meta http-equiv='Content-Type' content="text/html; charset=utf-8"/>
-  XML
+  def locate_landscape(_docxml)
+    css = read_stylesheet(@stylesheet)
+    @landscape = css.scan(/div\.\S+\s+\{\s*page:\s*[^;]+L;\s*\}/m)
+      .map { |e| e.sub(/^div\.(\S+).*$/m, "\\1") }
+  end
   def define_head1(docxml, _dir)
     docxml.xpath("//*[local-name() = 'head']").each do |h|
@@ -174,7 +109,6 @@ class Html2Doc
     # xml.children.first << Nokogiri::XML::Comment.new(xml, s)
     xml.children.first << Nokogiri::XML::CDATA
       .new(xml, "\n<!--\n#{stylesheet}\n-->\n")
     xml.root.to_s
   end
@@ -199,30 +133,15 @@ class Html2Doc
       head.add_child css
     elsif title.nil?
       head.children.first.add_previous_sibling css
-    else
-      title.add_next_sibling css
+    else title.add_next_sibling css
     end
   end
-  def namespace(root)
-    {
-      o: "urn:schemas-microsoft-com:office:office",
-      w: "urn:schemas-microsoft-com:office:word",
-      v: "urn:schemas-microsoft-com:vml",
-      m: "http://schemas.microsoft.com/office/2004/12/omml",
-    }.each { |k, v| root.add_namespace_definition(k.to_s, v) }
-  end
-  def rootnamespace(root)
-    root.add_namespace(nil, "http://www.w3.org/TR/REC-html40")
-  end
   def bookmarks(docxml)
     docxml.xpath("//*[@id][not(@name)][not(@style = 'mso-element:footnote')]")
       .each do |x|
-      next if x["id"].empty? ||
-        %w(shapetype v:shapetype shape v:shape).include?(x.name)
+      (x["id"].empty? ||
+        %w(shapetype v:shapetype shape v:shape).include?(x.name)) and next
       if x.children.empty? then x.add_child("<a name='#{x['id']}'></a>")
       else x.children.first.previous = "<a name='#{x['id']}'></a>"
       end

data/lib/html2doc/math.rb CHANGED Viewed

@@ -5,29 +5,6 @@ require "nokogiri"
 require "plane1converter"
 class Html2Doc
-  def asciimath_to_mathml1(expr, retain_asciimath)
-    ret = Plurimath::Math.parse(HTMLEntities.new.decode(expr), "asciimath").to_mathml
-      .gsub(/<math>/, "<math xmlns='http://www.w3.org/1998/Math/MathML'>").strip
-    retain_asciimath and
-      ret += "<asciimath>#{@c.encode(@c.decode(expr), :basic)}</asciimath>"
-    ret
-  rescue StandardError => e
-    puts "parsing: #{expr}"
-    puts e.message
-    raise e
-  end
-  def asciimath_to_mathml(doc, delims, retain_asciimath: false)
-    return doc if delims.nil? || delims.size < 2
-    m = doc.split(/(#{Regexp.escape(delims[0])}|#{Regexp.escape(delims[1])})/)
-    m.each_slice(4).map.with_index do |(*a), i|
-      progress_conv(i, 500, (m.size / 4).floor, 1000, "AsciiMath")
-      a[2].nil? or a[2] = asciimath_to_mathml1(a[2], retain_asciimath)
-      a.size > 1 ? a[0] + a[2] : a[0]
-    end.join
-  end
   def progress_conv(idx, step, total, threshold, msg)
     return unless (idx % step).zero? && total > threshold && idx.positive?

data/lib/html2doc/mime.rb CHANGED Viewed

@@ -78,8 +78,7 @@ class Html2Doc
   def image_resize(img, path, maxheight, maxwidth)
     s, realsize = get_image_size(img, path)
-    return s if s[0] == nil && s[1] == nil
+    s[0] == nil && s[1] == nil and return s
     if img.name == "svg" && !img["viewBox"]
       img["viewBox"] = "0 0 #{s[0]} #{s[1]}"
     end
@@ -118,12 +117,24 @@ class Html2Doc
     docxml.traverse do |i|
       skip_image_cleanup?(i) and next
       local_filename = rename_image(i, dir, localdir)
-      i["width"], i["height"] = image_resize(i, local_filename, maxheight,
-                                             maxwidth)
+      i["width"], i["height"] =
+        if landscape?(i)
+          image_resize(i, local_filename, maxwidth, maxheight)
+        else
+          image_resize(i, local_filename, maxheight, maxwidth)
+        end
     end
     docxml
   end
+  def landscape?(img)
+    img.ancestors.each do |a|
+      a.name == "div" or next
+      @landscape.include?(a["class"]) and return true
+    end
+    false
+  end
   def rename_image(img, dir, localdir)
     local_filename = localname(img["src"], localdir)
     new_filename = "#{mkuuid}#{File.extname(img['src'])}"
@@ -134,10 +145,9 @@ class Html2Doc
   def skip_image_cleanup?(img)
     src = img["src"]
-    return true unless img.element? && %w(img v:imagedata).include?(img.name)
-    return true if src.nil? || src.empty? || /^http/.match?(src) ||
-      %r{^data:(image|application)/[^;]+;base64}.match?(src)
+    (img.element? && %w(img v:imagedata).include?(img.name)) or return true
+    (src.nil? || src.empty? || /^http/.match?(src) ||
+      %r{^data:(image|application)/[^;]+;base64}.match?(src)) and return true
     false
   end
@@ -222,8 +232,7 @@ class Html2Doc
       f.write %{<xml xmlns:o="urn:schemas-microsoft-com:office:office">
         <o:MainFile HRef="../#{filename}.htm"/>}
       Dir.entries(dir).sort.each do |item|
-        next if item == "." || item == ".." || /^\./.match(item)
+        (item == "." || item == ".." || /^\./.match(item)) and next
         f.write %{  <o:File HRef="#{item}"/>\n}
       end
       f.write("</xml>\n")

data/lib/html2doc/version.rb CHANGED Viewed

@@ -1,3 +1,3 @@
 class Html2Doc
-  VERSION = "1.5.4".freeze
+  VERSION = "1.6.0".freeze
 end

data/lib/html2doc/xml.rb ADDED Viewed

@@ -0,0 +1,83 @@
+class Html2Doc
+  NOKOHEAD = <<~HERE.freeze
+    <!DOCTYPE html SYSTEM
+    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+    <html xmlns="http://www.w3.org/1999/xhtml">
+    <head> <title></title> <meta charset="UTF-8" /> </head>
+    <body> </body> </html>
+  HERE
+  def to_xhtml(xml)
+    xml.gsub!(/<\?xml[^>]*>/, "")
+    unless /<!DOCTYPE /.match? xml
+      xml = '<!DOCTYPE html SYSTEM
+          "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">' + xml
+    end
+    xml = xml.gsub(/<!--\s*\[([^\]]+)\]>/, "<!-- MSWORD-COMMENT \\1 -->")
+      .gsub(/<!\s*\[endif\]\s*-->/, "<!-- MSWORD-COMMENT-END -->")
+    Nokogiri::XML.parse(xml)
+  end
+  DOCTYPE = <<~DOCTYPE.freeze
+    <!DOCTYPE html SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+  DOCTYPE
+  def from_xhtml(xml)
+    xml.to_xml.sub(%{ xmlns="http://www.w3.org/1999/xhtml"}, "")
+      .sub(DOCTYPE, "").gsub(%{ />}, "/>")
+      .gsub(/<!-- MSWORD-COMMENT (.+?) -->/, "<!--[\\1]>")
+      .gsub(/<!-- MSWORD-COMMENT-END -->/, "<![endif]-->")
+      .gsub("\n--&gt;\n", "\n-->\n")
+  end
+  def msword_fix(doc)
+    # brain damage in MSWord parser
+    doc.gsub!(%r{<w:DoNotOptimizeForBrowser></w:DoNotOptimizeForBrowser>},
+              "<w:DoNotOptimizeForBrowser/>")
+    doc.gsub!(%r{<span style="mso-special-character:footnote"/>},
+              '<span style="mso-special-character:footnote"></span>')
+    doc.gsub!(%r{<div style="mso-element:footnote-list"></div>},
+              '<div style="mso-element:footnote-list"/>')
+    doc.gsub!(%r{(<a style="mso-comment-reference:[^>/]+)/>}, "\\1></a>")
+    doc.gsub!(%r{<link rel="File-List"}, "<link rel=File-List")
+    doc.gsub!(%r{<meta http-equiv="Content-Type"},
+              "<meta http-equiv=Content-Type")
+    doc.gsub!(%r{></m:jc>}, "/>")
+    doc.gsub!(%r{></v:stroke>}, "/>")
+    doc.gsub!(%r{></v:f>}, "/>")
+    doc.gsub!(%r{></v:path>}, "/>")
+    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|
+      a.size > 2 and a[2] = a[2].gsub(/>\s+</, "><")
+      a
+    end.join
+  end
+  PRINT_VIEW = <<~XML.freeze
+    <xml>
+    <w:WordDocument>
+    <w:View>Print</w:View>
+    <w:Zoom>100</w:Zoom>
+    <w:DoNotOptimizeForBrowser/>
+    </w:WordDocument>
+    </xml>
+    <meta http-equiv='Content-Type' content="text/html; charset=utf-8"/>
+  XML
+  def namespace(root)
+    { o: "urn:schemas-microsoft-com:office:office",
+      w: "urn:schemas-microsoft-com:office:word",
+      v: "urn:schemas-microsoft-com:vml",
+      m: "http://schemas.microsoft.com/office/2004/12/omml" }.each { |k, v| root.add_namespace_definition(k.to_s, v) }
+  end
+  def rootnamespace(root)
+    root.add_namespace(nil, "http://www.w3.org/TR/REC-html40")
+  end
+end

data/lib/html2doc.rb CHANGED Viewed

@@ -4,3 +4,4 @@ require_relative "html2doc/mime"
 require_relative "html2doc/notes"
 require_relative "html2doc/math"
 require_relative "html2doc/lists"
+require_relative "html2doc/xml"

metadata CHANGED Viewed

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 1.5.4
+  version: 1.6.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-05-19 00:00:00.000000000 Z
+date: 2023-08-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -293,6 +293,7 @@ files:
 - lib/html2doc/notes.rb
 - lib/html2doc/version.rb
 - lib/html2doc/wordstyle.css
+- lib/html2doc/xml.rb
 homepage: https://github.com/metanorma/html2doc
 licenses:
 - CC-BY-SA-3.0