html2doc 0.8.2 → 0.8.3

data/lib/html2doc/mime.rb

@@ -2,6 +2,7 @@ require "uuidtools"
 require "base64"
 require "mime/types"
 require "image_size"
+require "fileutils"
 
 module Html2Doc
   def self.mime_preamble(boundary, filename, result)
@@ -20,7 +21,7 @@ module Html2Doc
 
   def self.mime_attachment(boundary, filename, item, dir)
     encoded_file = Base64.strict_encode64(
-      File.read("#{dir}/#{item}"),
+      File.read("#{dir}/#{item}", encoding: "utf-8"),
     ).gsub(/(.{76})/, "\\1\n")
     <<~"FILE"
     --#{boundary}
@@ -55,7 +56,7 @@ module Html2Doc
       mhtml += mime_attachment(boundary, filename, item, dir)
     end
     mhtml += "--#{boundary}--"
-    File.open("#{filename}.doc", "w") { |f| f.write mhtml }
+    File.open("#{filename}.doc", "w:UTF-8") { |f| f.write mhtml }
   end
 
   # max height for Word document is 400, max width is 680
@@ -72,13 +73,14 @@ module Html2Doc
 
   IMAGE_PATH = "//*[local-name() = 'img' or local-name() = 'imagedata']".freeze
 
+  # only processes locally stored images
   def self.image_cleanup(docxml, dir)
     docxml.xpath(IMAGE_PATH).each do |i|
+      next if /^http/.match i["src"]
       matched = /\.(?<suffix>\S+)$/.match i["src"]
       uuid = UUIDTools::UUID.random_create.to_s
       new_full_filename = File.join(dir, "#{uuid}.#{matched[:suffix]}")
-      # presupposes that the image source is local
-      system "cp #{i['src']} #{new_full_filename}"
+      FileUtils.cp i["src"], new_full_filename
       i["width"], i["height"] = image_resize(i, 400, 680)
       i["src"] = new_full_filename
     end
@@ -100,7 +102,8 @@ module Html2Doc
       uuid = UUIDTools::UUID.random_create.to_s
       new_full_filename = "file:///C:/Doc/#{filename}_files/#{uuid}.#{matched2[:suffix]}"
       dest_filename = File.join(dir, "#{uuid}.#{matched2[:suffix]}")
-      system "cp #{matched[:src]} #{dest_filename}"
+      #system "cp #{matched[:src]} #{dest_filename}"
+      FileUtils.cp matched[:src], dest_filename
       a[1].sub!(%r{ src=['"](?<src>[^"']+)['"]}, " src='#{new_full_filename}'")
     end
     a.join

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 module Html2Doc
-  VERSION = "0.8.2".freeze
+  VERSION = "0.8.3".freeze
 end

data/spec/html2doc_spec.rb

@@ -364,7 +364,7 @@ RSpec.describe Html2Doc do
     OUTPUT
   end
 
-      it "processes a header with an image" do
+  it "processes a header with an image" do
     Html2Doc.process(html_input(""), filename: "test", header_file: "spec/header_img.html")
     expect(guid_clean(File.read("test.doc", encoding: "utf-8"))).to match(%r{Content-Type: image/png})
   end
@@ -517,7 +517,7 @@ RSpec.describe Html2Doc do
     expect(testdoc).to match(%r{Content-Type: image/png})
     expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
-    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.png" width="400" height="387"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.png" width="412" height="400"></img>', '<div style="mso-element:footnote-list"/>'))}
     #{image_clean(WORD_FTR3)}
     OUTPUT
   end
@@ -529,7 +529,7 @@ RSpec.describe Html2Doc do
     expect(testdoc).to match(%r{Content-Type: image/gif})
     expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
-    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.gif" width="400" height="118"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.gif" width="680" height="202"></img>', '<div style="mso-element:footnote-list"/>'))}
     #{image_clean(WORD_FTR3).gsub(/image\.png/, "image.gif")}
     OUTPUT
   end
@@ -541,7 +541,7 @@ RSpec.describe Html2Doc do
     expect(testdoc).to match(%r{Content-Type: image/jpeg})
     expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
     #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
-    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.jpg" width="208" height="680"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.jpg" width="122" height="400"></img>', '<div style="mso-element:footnote-list"/>'))}
     #{image_clean(WORD_FTR3).gsub(/image\.png/, "image.jpg")}
     OUTPUT
   end
@@ -577,6 +577,16 @@ RSpec.describe Html2Doc do
     expect(Html2Doc.image_resize(image, 100, 100)).to eq [30, 100]
   end
 
+  it "does not move images if they are external URLs" do
+    simple_body = '<img src="https://example.com/19160-6.png">'
+    Html2Doc.process(html_input(simple_body), filename: "test")
+    testdoc = File.read("test.doc", encoding: "utf-8")
+    expect(image_clean(guid_clean(testdoc))).to match_fuzzy(<<~OUTPUT)
+    #{WORD_HDR} #{DEFAULT_STYLESHEET} #{WORD_HDR_END}
+    #{image_clean(word_body('<img src="https://example.com/19160-6.png"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{image_clean(WORD_FTR1)}
+    OUTPUT
+  end
 
   it "processes epub:type footnotes" do
     simple_body = '<div>This is a very simple 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 0.8.2
+  version: 0.8.3
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-07-14 00:00:00.000000000 Z
+date: 2018-08-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -310,6 +310,7 @@ files:
 - lib/html2doc/base.rb
 - lib/html2doc/lists.rb
 - lib/html2doc/math.rb
+- lib/html2doc/mathml2omml.xsl
 - lib/html2doc/mime.rb
 - lib/html2doc/mml2omml.xsl
 - lib/html2doc/notes.rb