word-to-markdown 1.1.7 → 1.1.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 9d852a4ac53478b17c5336883ec861ea52bfac83
-  data.tar.gz: 4505d3165e6e167a5908cf277d9c28d42b8b66e5
+SHA256:
+  metadata.gz: 3febb4398acdc4eacedcc62e09f4beeaee625858043a27e6df7e597fee1e0d17
+  data.tar.gz: 7a76057aeca2db8f321282bc309a835f282ea921343b28c8bce6d83cd0fc4582
 SHA512:
-  metadata.gz: b14cf7b9341a1f779b0943c050822bd8c2c358851e99c0e712722f6090f8d7d8ca3f2e1c79ded4663b51fca3706c8f490e1bcdda99d77d85e7aa0c0895615597
-  data.tar.gz: d3ea8bb028083f5e9752f5989700c98de481e654e2a8188efc7d9741049605036c36b26fd17df6ef3d9aca2ef7ef358c736e589af980dea98b12be8f08025868
+  metadata.gz: ee2340688c2d5f3f21c7e47f85220bebc88201e28200a682146041fa7f5a47e89c56d687b4f6565a95d7d3e7f4c70fb1551894ad297620e7bd49cef520975e18
+  data.tar.gz: 44d405387990ee9a09cb33572a1d7843461c0817789c92a08df6d3542082ffc837bbd39d544a2e6a734a0772c67da3afed77049dc96b0ace0d562473515816e1

data/LICENSE.md

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2014, Ben Balter
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,78 @@
+# Word to Markdown converter
+
+A Ruby gem to liberate content from [the jail that is Word documents](http://ben.balter.com/2012/10/19/we-ve-been-trained-to-make-paper/#jailbreaking-content)
+
+[![Build Status](https://travis-ci.org/benbalter/word-to-markdown.svg?branch=master)](https://travis-ci.org/benbalter/word-to-markdown) [![Gem Version](https://badge.fury.io/rb/word-to-markdown.png)](http://badge.fury.io/rb/word-to-markdown) [![Inline docs](http://inch-ci.org/github/benbalter/word-to-markdown.png)](http://inch-ci.org/github/benbalter/word-to-markdown) [![Build status](https://ci.appveyor.com/api/projects/status/x2gnsfvli3q47a2e/branch/master?svg=true)](https://ci.appveyor.com/project/benbalter/word-to-markdown/branch/master)
+
+## The problem
+
+> Our default content publishing workflow is terribly broken. [We've all been trained to make paper](http://ben.balter.com/2012/10/19/we-ve-been-trained-to-make-paper/), yet today, content authored once is more commonly consumed in multiple formats, and rarely, if ever, does it embody physical form. Put another way, our go-to content authoring workflow remains relatively unchanged since it was conceived in the early 80s.
+>
+> I'm asked regularly by government employees — knowledge workers who fire up a desktop word processor as the first step to any project — for an automated pipeline to convert Microsoft Word documents to [Markdown](http://guides.github.com/overviews/mastering-markdown/), the *lingua franca* of the internet, but as my recent foray into building [just such a converter](http://word-to-markdown.herokuapp.com/) proves, it's not that simple.
+>
+> Markdown isn't just an alternative format. Markdown forces you to write for the web.
+
+**[Read more](http://ben.balter.com/2014/03/31/word-versus-markdown-more-than-mere-semantics/)**
+
+**[Demo](http://word-to-markdown.herokuapp.com/)**
+
+## Install
+
+You'll need to install [LibreOffice](http://www.libreoffice.org/). Then:
+
+```bash
+gem install word-to-markdown
+```
+
+## Usage
+
+```ruby
+file = WordToMarkdown.new("/path/to/document.docx")
+=> <WordToMarkdown path="/path/to/document.docx">
+
+file.to_s
+=> "# Test\n\n This is a test"
+
+file.document.tree
+=> <Nokogiri Document>
+```
+
+### Command line usage
+
+Once you've installed the gem, it's just:
+
+```
+$ w2m path/to/document.docx
+```
+
+*Outputs the resulting markdown to stdout*
+
+## Supports
+
+* Paragraphs
+* Numbered lists
+* Unnumbered lists
+* Nested lists
+* Italic
+* Bold
+* Explicit headings (e.g., selected as "Heading 1" or "Heading 2")
+* Implicit headings (e.g., text with a larger font size relative to paragraph text)
+* Images
+* Tables
+* Hyperlinks
+
+## Requirements and configuration
+
+Word-to-markdown requires `soffice` a command line interface to LibreOffice that works on Linux, Mac, and Windows. To install soffice, see [the LibreOffice documentation](https://www.libreoffice.org/get-help/install-howto/).
+
+## Testing
+
+```
+script/cibuild
+```
+
+## Server
+
+[Word-to-markdown-demo](https://github.com/benbalter/word-to-markdown-demo) contains a lightweight server for converting Word Documents as a service.
+
+A live version runs at [word-to-markdown.herokuapp.com](http://word-to-markdown.herokuapp.com).

data/bin/w2m

@@ -1,13 +1,14 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
 require 'word-to-markdown'
 
-if ARGV.size != 1 || ARGV[0] == "--help"
-  puts "Usage: bundle exec w2m path/to/document.docx"
+if ARGV.size != 1 || ARGV[0] == '--help'
+  puts 'Usage: bundle exec w2m path/to/document.docx'
   exit 1
 end
 
-if ARGV[0] == "--version"
+if ARGV[0] == '--version'
   puts "WordToMarkdown v#{WordToMarkdown::VERSION}"
   puts "LibreOffice v#{WordToMarkdown.soffice.version}" unless Gem.win_platform?
 else

data/lib/cliver/dependency_ext.rb

@@ -1,16 +1,18 @@
+# frozen_string_literal: true
+
 require 'sys/proctable'
 
 module Cliver
   class Dependency
-
     include Sys
 
     # Memoized shortcut for detect
     # Returns the path to the detected dependency
     # Raises an error if the dependency was not satisfied
-    def path
+    def detected_path
       @detected_path ||= detect!
     end
+    alias path detected_path
 
     # Is the detected dependency currently open?
     def open?
@@ -24,12 +26,12 @@ module Cliver
     def version
       return @detected_version if defined? @detected_version
       return if Gem.win_platform?
-      version = installed_versions.find { |p, v| p == path }
+      version = installed_versions.find { |p, _v| p == path }
       @detected_version = version.nil? ? nil : version[1]
     end
 
     def major_version
-      version.split(".").first if version
+      version.split('.').first if version
     end
   end
 end

data/lib/nokogiri/xml/element.rb

@@ -1,7 +1,8 @@
+# frozen_string_literal: true
+
 module Nokogiri
   module XML
     class Element
-
       DEFAULT_FONT_SIZE = 12.to_f
 
       # The node's font size
@@ -13,11 +14,11 @@ module Nokogiri
       end
 
       def bold?
-        styles['font-weight'] && styles['font-weight'] == "bold"
+        styles['font-weight'] && styles['font-weight'] == 'bold'
       end
 
       def italic?
-        styles['font-style'] && styles['font-style'] == "italic"
+        styles['font-style'] && styles['font-style'] == 'italic'
       end
     end
   end

data/lib/word-to-markdown.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'descriptive_statistics'
 require 'reverse_markdown'
 require 'nokogiri-styles'
@@ -16,86 +18,93 @@ require_relative 'nokogiri/xml/element'
 require_relative 'cliver/dependency_ext'
 
 class WordToMarkdown
-
   attr_reader :document, :converter
 
+  # Options to be passed to Reverse Markdown
   REVERSE_MARKDOWN_OPTIONS = {
-    unknown_tags: :bypass,
+    unknown_tags:    :bypass,
     github_flavored: true
-  }
+  }.freeze
 
-  SOFFICE_VERSION_REQUIREMENT = '> 4.0'
+  # Minimum version of LibreOffice Required
+  SOFFICE_VERSION_REQUIREMENT = '> 4.0'.freeze
 
+  # Paths to look for LibreOffice, in order of preference
   PATHS = [
-    "*", # Sub'd for ENV["PATH"]
-    "~/Applications/LibreOffice.app/Contents/MacOS",
-    "/Applications/LibreOffice.app/Contents/MacOS",
-    "/Program Files/LibreOffice 5/program",
-    "/Program Files (x86)/LibreOffice 4/program"
-  ]
+    '*', # Sub'd for ENV["PATH"]
+    '~/Applications/LibreOffice.app/Contents/MacOS',
+    '/Applications/LibreOffice.app/Contents/MacOS',
+    '/Program Files/LibreOffice 5/program',
+    '/Program Files (x86)/LibreOffice 4/program'
+  ].freeze
 
   # Create a new WordToMarkdown object
   #
-  # input - a HTML string or path to an HTML file
-  #
-  # Returns the WordToMarkdown object
+  # @param path [string] Path to the Word document
+  # @param tmpdir [string] Path to a working directory to use
+  # @return [WordToMarkdown] WordToMarkdown object with the converted document
   def initialize(path, tmpdir = nil)
     @document = WordToMarkdown::Document.new path, tmpdir
     @converter = WordToMarkdown::Converter.new @document
     converter.convert!
   end
 
-  def self.run_command(*args)
-    raise "LibreOffice already running" if soffice.open?
-
-    output, status = Open3.capture2e(soffice.path, *args)
-    logger.debug output
-    raise "Command `#{soffice.path} #{args.join(" ")}` failed: #{output}" if status.exitstatus != 0
-    output
+  # Helper method to return the document body, as markdown
+  # @return [string] the document body, as markdown
+  def to_s
+    document.to_s
   end
 
-  # Returns a Cliver::Dependency object representing our soffice dependency
-  #
-  # Attempts to resolve by looking at PATH followed by paths in the PATHS constant
-  #
-  # Methods used internally:
-  #   path    - returns the resolved path. Raises an error if not satisfied
-  #   version - returns the resolved version
-  #   open    - is the dependency currently open/running?
-  def self.soffice
-    @@soffice_dependency ||= Cliver::Dependency.new("soffice", *soffice_dependency_args)
-  end
+  class << self
+    # Run an soffice command
+    #
+    # @param args [string] one or more arguments to pass to the sofice command
+    # @return [string] the command output
+    def run_command(*args)
+      raise 'LibreOffice already running' if soffice.open?
 
-  def self.logger
-    @@logger ||= begin
-      logger = Logger.new(STDOUT)
-      logger.level = Logger::ERROR unless ENV["DEBUG"]
-      logger
+      output, status = Open3.capture2e(soffice.path, *args)
+      logger.debug output
+      raise "Command `#{soffice.path} #{args.join(' ')}` failed: #{output}" if status.exitstatus != 0
+      output
     end
-  end
 
-  # Pretty print the class in console
-  def inspect
-    "<WordToMarkdown path=\"#{@document.path}\">"
-  end
+    # Returns a Cliver::Dependency object representing our soffice dependency
+    #
+    # Attempts to resolve by looking at PATH followed by paths in the PATHS constant
+    #
+    # Methods used internally:
+    #   path    - returns the resolved path. Raises an error if not satisfied
+    #   version - returns the resolved version
+    #   open    - is the dependency currently open/running?
+    # @return Cliver::Dependency instance
+    def soffice
+      @soffice ||= Cliver::Dependency.new('soffice', *soffice_dependency_args)
+    end
 
-  def to_s
-    document.to_s
-  end
+    # @return Logger instance
+    def logger
+      @logger ||= begin
+        logger = Logger.new(STDOUT)
+        logger.level = Logger::ERROR unless ENV['DEBUG']
+        logger
+      end
+    end
 
-  private
+    private
 
-  # Workaround for two upstream bugs:
-  # 1. `soffice.exe --version` on windows opens a popup and retuns a null string when manually closed
-  # 2. Even if the second argument to Cliver is nil, Cliver thinks there's a requirement
-  #    and will shell out to `soffice.exe --version`
-  # In order to support Windows, don't pass *any* version requirement to Cliver
-  def self.soffice_dependency_args
-    args = [:path => PATHS.join(File::PATH_SEPARATOR)]
-    if Gem.win_platform?
-      args
-    else
-      args.unshift SOFFICE_VERSION_REQUIREMENT
+    # Workaround for two upstream bugs:
+    # 1. `soffice.exe --version` on windows opens a popup and retuns a null string when manually closed
+    # 2. Even if the second argument to Cliver is nil, Cliver thinks there's a requirement
+    #    and will shell out to `soffice.exe --version`
+    # In order to support Windows, don't pass *any* version requirement to Cliver
+    def soffice_dependency_args
+      args = [path: PATHS.join(File::PATH_SEPARATOR)]
+      if Gem.win_platform?
+        args
+      else
+        args.unshift SOFFICE_VERSION_REQUIREMENT
+      end
     end
   end
 end

data/lib/word-to-markdown/converter.rb

@@ -1,18 +1,29 @@
-# encoding: utf-8
+# frozen_string_literal: true
+
 class WordToMarkdown
   class Converter
-
     attr_reader :document
 
-    HEADING_DEPTH = 6 # Number of headings to guess, e.g., h6
-    HEADING_STEP = 100/HEADING_DEPTH
+    # Number of headings to guess, e.g., h6
+    HEADING_DEPTH = 6
+
+    # Percentile step for eaceh eheading
+    HEADING_STEP = 100 / HEADING_DEPTH
+
+    # Minimum heading size
     MIN_HEADING_SIZE = 20
-    UNICODE_BULLETS = ["○", "o", "●", "\u2022", "\\p{C}"]
 
+    # Unicode bullets to strip when processing
+    UNICODE_BULLETS = ['○', 'o', '●', "\u2022", '\\p{C}'].freeze
+
+    # @param document [WordToMarkdown::Document] The document to convert
     def initialize(document)
       @document = document
     end
 
+    # Convert the document
+    #
+    # Note: this action is destructive!
     def convert!
       # Fonts and headings
       semanticize_font_styles!
@@ -29,22 +40,22 @@ class WordToMarkdown
       remove_numbering_from_list_items!
     end
 
-    # Returns an array of Nokogiri nodes that are implicit headings
+    # @return [Array<Nokogiri::Node>] Return an array of Nokogiri Nodes that are implicit headings
     def implicit_headings
       @implicit_headings ||= begin
         headings = []
-        @document.tree.css("[style]").each do |element|
+        @document.tree.css('[style]').each do |element|
           headings.push element unless element.font_size.nil? || element.font_size < MIN_HEADING_SIZE
         end
         headings
       end
     end
 
-    # Returns an array of font-sizes for implicit headings in the document
+    # @return [Array<Integer>] An array of font-sizes for implicit headings in the document
     def font_sizes
       @font_sizes ||= begin
         sizes = []
-        @document.tree.css("[style]").each do |element|
+        @document.tree.css('[style]').each do |element|
           sizes.push element.font_size.round(-1) unless element.font_size.nil?
         end
         sizes.uniq.sort
@@ -53,11 +64,10 @@ class WordToMarkdown
 
     # Given a Nokogiri node, guess what heading it represents, if any
     #
-    # node - the nokigiri node
-    #
-    # retuns the heading tag (e.g., H1), or nil
+    # @param node [Nokigiri::Node] the nokigiri node
+    # @return [String, nil] the heading tag (e.g., H1), or nil
     def guess_heading(node)
-      return nil if node.font_size == nil
+      return nil if node.font_size.nil?
       [*1...HEADING_DEPTH].each do |heading|
         return "h#{heading}" if node.font_size >= h(heading)
       end
@@ -67,51 +77,58 @@ class WordToMarkdown
     # Minimum font size required for a given heading
     # e.g., H(2) would represent the minimum font size of an implicit h2
     #
-    # n - the heading number, e.g., 1, 2
+    # @param num [Integer] the heading number, e.g., 1, 2
     #
-    # returns the minimum font size as an integer
-    def h(n)
-      font_sizes.percentile ((HEADING_DEPTH-1)-n) * HEADING_STEP
+    # @return [Integer] the minimum font size
+    def h(num)
+      font_sizes.percentile(((HEADING_DEPTH - 1) - num) * HEADING_STEP)
     end
 
+    # Convert span-based font styles to `strong`s and `em`s
     def semanticize_font_styles!
-      @document.tree.css("span").each do |node|
+      @document.tree.css('span').each do |node|
         if node.bold?
-          node.node_name = "strong"
+          node.node_name = 'strong'
         elsif node.italic?
-          node.node_name = "em"
+          node.node_name = 'em'
         end
       end
     end
 
+    # Remove top-level paragraphs from table cells
     def remove_paragraphs_from_tables!
-      @document.tree.search("td p").each { |node| node.node_name = "span" }
+      @document.tree.search('td p').each { |node| node.node_name = 'span' }
     end
 
+    # Remove top-level paragraphs from list items
     def remove_paragraphs_from_list_items!
-      @document.tree.search("li p").each { |node| node.node_name = "span" }
+      @document.tree.search('li p').each { |node| node.node_name = 'span' }
     end
 
+    # Remove prepended unicode bullets from list items
     def remove_unicode_bullets_from_list_items!
-      path = WordToMarkdown.soffice.major_version == "5" ? "li span span" : "li span"
+      path = WordToMarkdown.soffice.major_version == '5' ? 'li span span' : 'li span'
       @document.tree.search(path).each do |span|
-        span.inner_html = span.inner_html.gsub /^([#{UNICODE_BULLETS.join("")}]+)/, ""
+        span.inner_html = span.inner_html.gsub(/^([#{UNICODE_BULLETS.join("")}]+)/, '')
       end
     end
 
+    # Remove prepended numbers from list items
     def remove_numbering_from_list_items!
-      path = WordToMarkdown.soffice.major_version == "5" ? "li span span" : "li span"
+      path = WordToMarkdown.soffice.major_version == '5' ? 'li span span' : 'li span'
       @document.tree.search(path).each do |span|
-        span.inner_html = span.inner_html.gsub /^[a-zA-Z0-9]+\./m, ""
+        span.inner_html = span.inner_html.gsub(/^[a-zA-Z0-9]+\./m, '')
       end
     end
 
+    # Remvoe whitespace from list items
     def remove_whitespace_from_list_items!
-      @document.tree.search("li span").each { |span| span.inner_html.strip! }
+      @document.tree.search('li span').each { |span| span.inner_html.strip! }
     end
 
+    # Convert table headers to `th`s2
     def semanticize_table_headers!
-      @document.tree.search("table tr:first td").each { |node| node.node_name = "th" }
+      @document.tree.search('table tr:first td').each { |node| node.node_name = 'th' }
     end
 
     # Try to guess heading where implicit bassed on font size
@@ -121,6 +138,5 @@ class WordToMarkdown
         element.node_name = heading unless heading.nil?
       end
     end
-
   end
 end

data/lib/word-to-markdown/document.rb

@@ -1,50 +1,54 @@
-# encoding: utf-8
+# frozen_string_literal: true
+
 class WordToMarkdown
   class Document
     class NotFoundError < StandardError; end
-    class ConverstionError < StandardError; end
+    class ConversionError < StandardError; end
 
-    attr_reader :path, :raw_html, :tmpdir
+    attr_reader :path, :tmpdir
 
+    # @param path [string] Path to the Word document
+    # @param tmpdir [string] Path to a working directory to use
     def initialize(path, tmpdir = nil)
       @path = File.expand_path path, Dir.pwd
       @tmpdir = tmpdir || Dir.mktmpdir
       raise NotFoundError, "File #{@path} does not exist" unless File.exist?(@path)
     end
 
+    # @return [String] the document's extension
     def extension
       File.extname path
     end
 
+    # @return [Nokigiri::Document]
     def tree
       @tree ||= begin
         tree = Nokogiri::HTML(normalized_html)
-        tree.css("title").remove
+        tree.css('title').remove
         tree
       end
     end
 
-    # Returns the html representation of the document
+    # @return [String] the html representation of the document
     def html
-      tree.to_html.gsub("</li>\n", "</li>")
+      tree.to_html.gsub("</li>\n", '</li>')
     end
 
-    # Returns the markdown representation of the document
-    def to_s
+    # @return [String] the markdown representation of the document
+    def markdown
       @markdown ||= scrub_whitespace(ReverseMarkdown.convert(html, WordToMarkdown::REVERSE_MARKDOWN_OPTIONS))
     end
+    alias to_s markdown
 
     # Determine the document encoding
     #
-    # html - the raw html export
-    #
-    # Returns the encoding, defaulting to "UTF-8"
+    # @return [String] the encoding, defaulting to "UTF-8"
     def encoding
-      match = raw_html.encode("UTF-8", :invalid => :replace, :replace => "").match(/charset=([^\"]+)/)
+      match = raw_html.encode('UTF-8', invalid: :replace, replace: '').match(/charset=([^\"]+)/)
       if match
-        match[1].sub("macintosh", "MacRoman")
+        match[1].sub('macintosh', 'MacRoman')
       else
-        "UTF-8"
+        'UTF-8'
       end
     end
 
@@ -52,55 +56,57 @@ class WordToMarkdown
 
     # Perform pre-processing normalization
     #
-    # html - the raw html input from the export
-    #
-    # Returns the normalized html
+    # @return [String] the normalized html
     def normalized_html
-      html = raw_html.force_encoding(encoding)
-      html = html.encode("UTF-8", :invalid => :replace, :replace => "")
-      html = Premailer.new(html, :with_html_string => true, :input_encoding => "UTF-8").to_inline_css
-      html.gsub! /\n|\r/," "         # Remove linebreaks
-      html.gsub! /“|”/, '"'          # Straighten curly double quotes
-      html.gsub! /‘|’/, "'"          # Straighten curly single quotes
-      html.gsub! />\s+</, "><"       # Remove extra whitespace between tags
+      html = raw_html.dup.force_encoding(encoding)
+      html = html.encode('UTF-8', invalid: :replace, replace: '')
+      html = Premailer.new(html, with_html_string: true, input_encoding: 'UTF-8').to_inline_css
+      html.gsub!(/\n|\r/, ' ')  # Remove linebreaks
+      html.gsub!(/“|”/, '"')    # Straighten curly double quotes
+      html.gsub!(/‘|’/, "'")    # Straighten curly single quotes
+      html.gsub!(/>\s+</, '><') # Remove extra whitespace between tags
       html
     end
 
     # Perform post-processing normalization of certain Word quirks
     #
-    # string - the markdown representation of the document
+    # @param string [String] the markdown representation of the document
     #
-    # Returns the normalized markdown
+    # @return [String] the normalized markdown
     def scrub_whitespace(string)
-      string.gsub!("&nbsp;", " ")                     # HTML encoded spaces
-      string.sub!(/\A[[:space:]]+/,'')                # document leading whitespace
-      string.sub!(/[[:space:]]+\z/,'')                # document trailing whitespace
-      string.gsub!(/([ ]+)$/, '')                     # line trailing whitespace
-      string.gsub!(/\n\n\n\n/,"\n\n")                 # Quadruple line breaks
-      string.gsub!(/\u00A0/, "")                      # Unicode non-breaking spaces, injected as tabs
+      string = string.dup
+      string.gsub!('&nbsp;', ' ')       # HTML encoded spaces
+      string.sub!(/\A[[:space:]]+/, '') # document leading whitespace
+      string.sub!(/[[:space:]]+\z/, '') # document trailing whitespace
+      string.gsub!(/([ ]+)$/, '')       # line trailing whitespace
+      string.gsub!(/\n\n\n\n/, "\n\n")  # Quadruple line breaks
+      string.delete!(' ')               # Unicode non-breaking spaces, injected as tabs
       string
     end
 
+    # @return [String] the path to the intermediary HTML document
     def dest_path
-      dest_filename = File.basename(path).gsub(/#{Regexp.escape(extension)}$/, ".html")
+      dest_filename = File.basename(path).gsub(/#{Regexp.escape(extension)}$/, '.html')
       File.expand_path(dest_filename, tmpdir)
     end
 
+    # @return [String] the unnormalized HTML representation
     def raw_html
       @raw_html ||= begin
-        WordToMarkdown::run_command '--headless', '--convert-to', filter, path, '--outdir', tmpdir
-        raise ConverstionError, "Failed to convert #{path}" unless File.exists?(dest_path)
+        WordToMarkdown.run_command '--headless', '--convert-to', filter, path, '--outdir', tmpdir
+        raise ConversionError, "Failed to convert #{path}" unless File.exist?(dest_path)
         html = File.read dest_path
         File.delete dest_path
         html
       end
     end
 
+    # @return [String] the LibreOffice filter to use for conversion
     def filter
-      if WordToMarkdown.soffice.major_version == "5"
-        "html:XHTML Writer File:UTF8"
+      if WordToMarkdown.soffice.major_version == '5'
+        'html:XHTML Writer File:UTF8'
       else
-        "html"
+        'html'
       end
     end
   end

data/lib/word-to-markdown/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 class WordToMarkdown
-  VERSION = "1.1.7"
+  VERSION = '1.1.8'.freeze
 end

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 1.1.7
+  version: 1.1.8
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-01-04 00:00:00.000000000 Z
+date: 2018-08-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: reverse_markdown
+  name: cliver
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.6'
+        version: '0.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.6'
+        version: '0.3'
 - !ruby/object:Gem::Dependency
   name: descriptive_statistics
   requirement: !ruby/object:Gem::Requirement
@@ -39,103 +39,103 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.5'
 - !ruby/object:Gem::Dependency
-  name: premailer
+  name: nokogiri-styles
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '0.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.8'
+        version: '0.1'
 - !ruby/object:Gem::Dependency
-  name: nokogiri-styles
+  name: premailer
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: '1.8'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: '1.8'
 - !ruby/object:Gem::Dependency
-  name: sys-proctable
+  name: reverse_markdown
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.9'
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.9'
+        version: '1.0'
 - !ruby/object:Gem::Dependency
-  name: cliver
+  name: sys-proctable
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '1.0'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.4'
+        version: '1.6'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.4'
+        version: '1.6'
 - !ruby/object:Gem::Dependency
-  name: shoulda
+  name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '5.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.5'
+        version: '5.0'
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: mocha
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.6'
+        version: '1.1'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
@@ -151,33 +151,47 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.10'
 - !ruby/object:Gem::Dependency
-  name: mocha
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.1'
+        version: '10.4'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.1'
+        version: '10.4'
 - !ruby/object:Gem::Dependency
-  name: minitest
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '0.49'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.0'
+        version: '0.49'
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.5'
 description: Ruby Gem to convert Word documents to markdown.
 email: ben.balter@github.com
 executables:
@@ -185,6 +199,8 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- LICENSE.md
+- README.md
 - bin/w2m
 - lib/cliver/dependency_ext.rb
 - lib/nokogiri/xml/element.rb
@@ -212,7 +228,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: Ruby Gem to convert Word documents to markdown