html2doc 0.8.3 → 0.8.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c7d587c237cbfcaa7fbc1565fedfb3ef586ea7ce1105e79207130a3c6bffdbdf
-  data.tar.gz: 0f4c63e1ee7c47e4327d813fb524351914db8fb5e27dedf76a8082b0f7cd1246
+  metadata.gz: ebe0e5db8814308a2e3d8ade848d2a7a0323d2caf2e87f471d333edcf271ab8b
+  data.tar.gz: 6a0b6944d46e3a05aece3a52f445d00425ac78fa6d4e66a08adc9697618a7df4
 SHA512:
-  metadata.gz: bb584350898d40679e2e0eb5eb42d993b6407a2a52588e2e54bf59291b6987c4517689b5ec83b5c1620f6e09c5a7698ea51bf924b75de4e769b9f2789e253451
-  data.tar.gz: 25caa1a0e9aa35d5c776f21328cadb3d0efa9f9950efd7a14caed976e3f1bfe6b31cfbaf3ae541dac143c25fb2fd70ac5ec59d4d8c94eb86cd42b17301e8d657
+  metadata.gz: 78b8a0b62a7420145b032a40004dd97cb05851d700c182ca9fc6bc94884c1ae4f5eb917fae3e0084ef189db3d41d1338afe6a6dc6415e8445848e72db7642b85
+  data.tar.gz: 5245dc6ae3dbb947f47b1fb21f775b6021385bba13449014fd5dde1d55cd572e52abc2019b7430ad42ead2f55c5ccb165c495d359ed6d9bb8010875b14988322

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    html2doc (0.8.2)
+    html2doc (0.8.4)
       asciimath
       htmlentities (~> 4.3.4)
       image_size
@@ -14,7 +14,7 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    asciimath (1.0.4)
+    asciimath (1.0.6)
     ast (2.4.0)
     byebug (9.1.0)
     coderay (1.1.2)
@@ -48,18 +48,18 @@ GEM
       ruby_dep (~> 1.2)
     lumberjack (1.0.13)
     method_source (0.9.0)
-    mime-types (3.1)
+    mime-types (3.2.2)
       mime-types-data (~> 3.2015)
-    mime-types-data (3.2016.0521)
+    mime-types-data (3.2018.0812)
     mini_portile2 (2.3.0)
     nenv (0.3.0)
-    nokogiri (1.8.4)
+    nokogiri (1.8.5)
       mini_portile2 (~> 2.3.0)
     notiffany (0.1.1)
       nenv (~> 0.1)
       shellany (~> 0.0)
     parallel (1.12.1)
-    parser (2.5.1.0)
+    parser (2.5.1.2)
       ast (~> 2.4.0)
     powerpack (0.1.2)
     pry (0.11.3)
@@ -70,30 +70,30 @@ GEM
     rb-fsevent (0.10.3)
     rb-inotify (0.9.10)
       ffi (>= 0.5.0, < 2)
-    rspec (3.7.0)
-      rspec-core (~> 3.7.0)
-      rspec-expectations (~> 3.7.0)
-      rspec-mocks (~> 3.7.0)
-    rspec-core (3.7.1)
-      rspec-support (~> 3.7.0)
-    rspec-expectations (3.7.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.0)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.7.0)
+      rspec-support (~> 3.8.0)
     rspec-match_fuzzy (0.1.3)
       rspec (>= 3.2)
-    rspec-mocks (3.7.0)
+    rspec-mocks (3.8.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.7.0)
-    rspec-support (3.7.1)
-    rubocop (0.58.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.0)
+    rubocop (0.59.2)
       jaro_winkler (~> 1.5.1)
       parallel (~> 1.10)
-      parser (>= 2.5)
+      parser (>= 2.5, != 2.5.1.1)
       powerpack (~> 0.1)
       rainbow (>= 2.2.2, < 4.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (~> 1.0, >= 1.0.1)
-    ruby-progressbar (1.9.0)
+    ruby-progressbar (1.10.0)
     ruby-xslt (0.9.10)
     ruby_dep (1.5.0)
     shellany (0.0.1)

data/README.adoc

@@ -21,13 +21,13 @@ 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.
-* Resize any images in the HTML file to fit within the maximum page size. (Word will otherwise crash on reading the document.)
+* 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 any internal `@id` anchors to `a@name` anchors; Word only hyperlinks to the latter.
 * Generate a filelist.xml listing of all files to be bundled into the Word document.
 * Assign the class `MsoNormal` to any paragraphs that do not have a class, so that they can be treated as Normal Style when editing the Word document.
 * Inject Microsoft Word-specific CSS into the HTML document. If a CSS file is not supplied, the CSS file used is at `lib/html2doc/wordstyle.css` is used by default. Microsoft Word HTML has particular requirements from its CSS, and you should review the sample CSS before replacing it with your own. (This generic CSS can be overridden by CSS already in the HTML document, since the generic CSS is injected at the top of the document.)
-* Bundle up the images, the HTML file of the document proper, and the `header.html` file representing header/footer information, into a MIME file, and save that file to disk (so that Microsoft Word can deal with it as a Word file.)
+* Bundle up the local images, the HTML file of the document proper, and the `header.html` file representing header/footer information, into a MIME file, and save that file to disk (so that Microsoft Word can deal with it as a Word file.)
 
 For a representative generator of HTML that uses this gem in postprocessing, see https://github.com/riboseinc/asciidoctor-iso
 
@@ -55,7 +55,7 @@ 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
 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/riboseinc/asciidoctor-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.)
+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.)
 asciimathdelims:: are the AsciiMath delimiters used in the text (an array of an opening and a closing delimiter). If none are provided, no AsciiMath conversion is attempted.
 liststyles:: a hash of list style labels in Word CSS, which are used to define the behaviour of list item labels (e.g. _i)_ vs _i._). The gem recognises the hash keys `ul`, `ol`. So if the appearance of an ordered list's item labels in the supplied stylesheet is governed by style `@list l1` (e.g. `@list l1:level1 {mso-level-text:"%1\)";}` appears in the stylesheet), call the method with `liststyles:{ol: "l1"}`.
 

data/lib/html2doc/base.rb

@@ -4,6 +4,7 @@ require "htmlentities"
 require "nokogiri"
 require "xml/xslt"
 require "pp"
+require "fileutils"
 
 module Html2Doc
   def self.process(result, hash)
@@ -37,9 +38,9 @@ module Html2Doc
   end
 
   def self.rm_temp_files(filename, dir, dir1)
-    system "rm #{filename}.htm"
-    system "rm -r #{dir1}/header.html"
-    system "rm -r #{dir1}" unless dir
+    FileUtils.rm "#{filename}.htm"
+    FileUtils.rm_f "#{dir1}/header.html"
+    FileUtils.rm_r dir1 unless dir
   end
 
   def self.cleanup(docxml, hash)

data/lib/html2doc/mime.rb

@@ -59,7 +59,7 @@ module Html2Doc
     File.open("#{filename}.doc", "w:UTF-8") { |f| f.write mhtml }
   end
 
-  # max height for Word document is 400, max width is 680
+  # max width for Word document is 400, max height is 680
   def self.image_resize(i, maxheight, maxwidth)
     realSize = ImageSize.path(i["src"]).size
     s = [i["width"].to_i, i["height"].to_i]
@@ -81,7 +81,7 @@ module Html2Doc
       uuid = UUIDTools::UUID.random_create.to_s
       new_full_filename = File.join(dir, "#{uuid}.#{matched[:suffix]}")
       FileUtils.cp i["src"], new_full_filename
-      i["width"], i["height"] = image_resize(i, 400, 680)
+      i["width"], i["height"] = image_resize(i, 680, 400)
       i["src"] = new_full_filename
     end
     docxml

data/lib/html2doc/version.rb

@@ -1,3 +1,3 @@
 module Html2Doc
-  VERSION = "0.8.3".freeze
+  VERSION = "0.8.4".freeze
 end

data/spec/html2doc_spec.rb

@@ -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="412" height="400"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{image_clean(word_body('<img src="test_files/cb7b0d19-891e-4634-815a-570d019d454c.png" width="400" height="388"></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="680" height="202"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{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_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="122" height="400"></img>', '<div style="mso-element:footnote-list"/>'))}
+    #{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_FTR3).gsub(/image\.png/, "image.jpg")}
     OUTPUT
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html2doc
 version: !ruby/object:Gem::Version
-  version: 0.8.3
+  version: 0.8.4
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-26 00:00:00.000000000 Z
+date: 2018-10-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities