word-to-markdown 0.2.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0b8d7208877325f1e568f7f91255a7cfbc2df815
-  data.tar.gz: 4864e21eb71649017c61f677b24e611650a5aed0
+  metadata.gz: 65c40ca66cec250fa58be0b50f9691c49e80ba6c
+  data.tar.gz: 0bb6276f14bfbcbb6ff11b47f2b0fd0fbff94c10
 SHA512:
-  metadata.gz: 63bea7811559b150d55388090f1fd79df3a4f2a562cfe767bb3675a6c2af5e398cad2c00383ffb00c4536e66aebbbdc470a378eea4e3deec9de686cfd314082f
-  data.tar.gz: cd2c2593502aedef4fa2baddd245d671312b4521877401d1a07e60693d66d1fd15c3e7b14d5746bb7661a479daee7e00cc1c27e2a385ed73ee2846e01151a7f3
+  metadata.gz: f20b0252fab914e0a412fdab1b76005d5ce2daa10392bcce0daafd6fae9a7744f66cd26259fb65f1272a7ba3845b460ca0c772bb924a72a09303240bf4586dce
+  data.tar.gz: 84c8ab75b71bc19933cbe6860e8511c31d5dbb370898229b9d67e933aa8f754cfe8dd85a1f3220a4454199011691d2185422076a65bda7d86257a9abd6a7cf8e

data/bin/w2m

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+require 'word-to-markdown'
+
+if ARGV.size != 1
+  puts "Usage: bundle exec w2m path/to/document.docx"
+  exit 1
+end
+
+doc = WordToMarkdown.new ARGV[0]
+puts doc.to_s

data/lib/nokogiri/xml/element.rb

@@ -0,0 +1,22 @@
+module Nokogiri
+  module XML
+    class Element
+
+      # The node's font size
+      # Used for guessing heading sizes
+      #
+      # Returns a float with the font-size
+      def font_size
+        styles['font-size'].to_f if styles['font-size']
+      end
+
+      def bold?
+        styles['font-weight'] && styles['font-weight'] == "bold"
+      end
+
+      def italic?
+        styles['font-style'] && styles['font-style'] == "italic"
+      end
+    end
+  end
+end

data/lib/word-to-markdown.rb

@@ -3,253 +3,70 @@ require 'descriptive_statistics'
 require 'premailer'
 require 'nokogiri'
 require 'nokogiri-styles'
+require 'tmpdir'
+require_relative 'word-to-markdown/version'
+require_relative 'word-to-markdown/document'
+require_relative 'word-to-markdown/converter'
+require_relative 'nokogiri/xml/element'
 
 class WordToMarkdown
 
-  HEADING_DEPTH = 6 # Number of headings to guess, e.g., h6
-  HEADING_STEP = 100/HEADING_DEPTH
-  MIN_HEADING_SIZE = 20
+  attr_reader :document, :converter
 
-  LI_SELECTORS = %w[
-    .MsoListParagraphCxSpFirst
-    .MsoListParagraphCxSpMiddle
-    .MsoListParagraphCxSpLast
-    .MsoListParagraph
-    li
-  ]
-
-  attr_reader :path, :doc
+  REVERSE_MARKDOWN_OPTIONS = {
+    unknown_tags: :bypass,
+    github_flavored: true
+  }
 
   # Create a new WordToMarkdown object
   #
   # input - a HTML string or path to an HTML file
   #
   # Returns the WordToMarkdown object
-  def initialize(input)
-    path = File.expand_path input, Dir.pwd
-    if File.exist?(path)
-      html = File.open(path).read
-      @path = path
-    else
-      @path = String
-      html = input.to_s
+  def initialize(path)
+    @document = WordToMarkdown::Document.new path
+    @converter = WordToMarkdown::Converter.new @document
+    converter.convert!
+  end
+
+  # source: https://github.com/ricn/libreconv/blob/master/lib/libreconv.rb#L48
+  def self.which(cmd)
+    exts = ENV['PATHEXT'] ? ENV['PATHEXT'].split(';') : ['']
+    ENV['PATH'].split(File::PATH_SEPARATOR).each do |path|
+      exts.each do |ext|
+        exe = File.join(path, "#{cmd}#{ext}")
+        return exe if File.executable? exe
+      end
     end
-    @doc = Nokogiri::HTML normalize(html)
-    semanticize!
-  end
-
-  # Perform pre-processing normalization
-  #
-  # html - the raw html input from the export
-  #
-  # Returns the normalized html
-  def normalize(html)
-    encoding = encoding(html)
-    html = html.force_encoding(encoding).encode("UTF-8", :invalid => :replace, :replace => "")
-    html = Premailer.new(html, :with_html_string => true, :input_encoding => "UTF-8").to_inline_css
-    html.gsub! /\<\/?o:[^>]+>/, "" # Strip everything in the office namespace
-    html.gsub! /\<\/?w:[^>]+>/, "" # Strip everything in the word namespace
-    html.gsub! /\n|\r/," "         # Remove linebreaks
-    html.gsub! /“|”/, '"'          # Straighten curly double quotes
-    html.gsub! /‘|’/, "'"          # Straighten curly single quotes
-    html
-  end
-
-  # Pretty print the class in console
-  def inspect
-    "<WordToMarkdown path=\"#{@path}\">"
-  end
 
-  # Returns the markdown representation of the document
-  def to_s
-    @markdown ||= scrub_whitespace(ReverseMarkdown.parse(html))
+    return nil
   end
 
-  # Returns the html representation of the document
-  def html
-    doc.to_html.gsub("</li>\n", "</li>")
-  end
-
-  # Determine the document encoding
-  #
-  # html - the raw html export
-  #
-  # Returns the encoding, defaulting to "UTF-8"
-  def encoding(html)
-    match = html.encode("UTF-8", :invalid => :replace, :replace => "").match(/charset=([^\"]+)/)
-    if match
-      match[1].sub("macintosh", "MacRoman")
+  def self.soffice_path
+    if RUBY_PLATFORM.include?("darwin")
+      "/Applications/LibreOffice.app/Contents/MacOS/soffice"
     else
-      "UTF-8"
+      soffice_path ||= which("soffice")
+      soffice_path ||= which("soffice.bin")
+      soffice_path ||= "soffice"
     end
   end
 
-  # Perform post-processing normalization of certain Word quirks
-  #
-  # string - the markdown representation of the document
-  #
-  # Returns the normalized markdown
-  def scrub_whitespace(string)
-    string.sub!(/\A[[:space:]]+/,'')                # leading whitespace
-    string.sub!(/[[:space:]]+\z/,'')                # trailing whitespace
-    string.gsub!(/\n\n \n\n/,"\n\n")                # Quadruple line breaks
-    string.gsub!(/\u00A0/, "")                      # Unicode non-breaking spaces, injected as tabs
-    string
+  # Ideally this would be done via open3, but Travis CI can't seen to find soffice when we do
+  def self.run_command(*args)
+    `#{soffice_path} #{args.join(' ')}`
   end
 
-  # Returns an array of Nokogiri nodes that are implicit headings
-  def implicit_headings
-    @implicit_headings ||= begin
-      headings = []
-      doc.css("[style]").each do |element|
-        headings.push element unless element.font_size.nil? || element.font_size < MIN_HEADING_SIZE
-      end
-      headings
-    end
+  def self.soffice_version
+    run_command('--version').strip.sub "LibreOffice ", ""
   end
 
-  # Returns an array of font-sizes for implicit headings in the document
-  def font_sizes
-    @font_sizes ||= begin
-      sizes = []
-      doc.css("[style]").each do |element|
-        sizes.push element.font_size.round(-1) unless element.font_size.nil?
-      end
-      sizes.uniq.sort
-    end
-  end
-
-  # Given a Nokogiri node, guess what heading it represents, if any
-  #
-  # node - the nokigiri node
-  #
-  # retuns the heading tag (e.g., H1), or nil
-  def guess_heading(node)
-    return nil if node.font_size == nil
-    [*1...HEADING_DEPTH].each do |heading|
-      return "h#{heading}" if node.font_size >= h(heading)
-    end
-    nil
-  end
-
-  # 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
-  #
-  # returns the minimum font size as an integer
-  def h(n)
-    font_sizes.percentile ((HEADING_DEPTH-1)-n) * HEADING_STEP
-  end
-
-  # CSS selector to select non-symantic lists
-  def li_selectors
-    LI_SELECTORS.join(",")
-  end
-
-  # Returns an array of all indented values
-  def indents
-    @indents ||= doc.css(li_selectors).map{ |el| el.indent }.uniq.sort
-  end
-
-  # Determine the indent level given an indent value
-  #
-  # level - the true indent, e.g., 2.5 (from 2.5em)
-  #
-  # Returns an integer representing the indent level
-  def indent(level)
-    indents.find_index level
-  end
-
-  # Try to make semantic markup explicit where implied by the export
-  def semanticize!
-
-    # Semanticize lists
-    indent_level = 0
-    doc.css(li_selectors).each do |node|
-
-      # Determine if this is an implicit UL or an implicit OL list item
-      if node.classes.include?("MsoListParagraph") || node.content.match(/^[a-zA-Z0-9]+\./)
-        list_type = "ol"
-      else
-        list_type = "ul"
-      end
-
-      # calculate indent level
-      current_indent = indent(node.indent)
-
-      # Determine parent node for this li, creating it if necessary
-      if current_indent > indent_level || indent_level == 0 && node.parent.css(".indent#{current_indent}").empty?
-        list = Nokogiri::XML::Node.new list_type, @doc
-        list.classes = ["list", "indent#{current_indent}"]
-        list.parent = node.parent.css(".indent#{current_indent-1} li").last || node.parent
-      else
-        list = node.parent.css(".indent#{current_indent}").last
-      end
-
-      # Note our current nesting depth
-      indent_level = current_indent
-
-      # Convert list paragraphs to actual numbered and unnumbered lists
-      node.node_name = "li"
-      node.parent = list if list
-
-      # Scrub unicode bullets
-      span = node.css("span:first")[1]
-      if span && span.styles["mso-list"] && span.styles["mso-list"] == "Ignore"
-        span.content = span.content[1..-1] unless span.content.match /^\d+\./
-      end
-
-      # Convert all pseudo-numbered list items into numbered list items, e.g., ii. => 2.
-      node.content = node.content.gsub /^[[:space:] ]+/, ""
-      node.content = node.content.gsub /^[a-zA-Z0-9]+\.[[:space:]]+/, ""
-
-    end
-
-    # Try to guess heading where implicit bassed on font size
-    implicit_headings.each do |element|
-      heading = guess_heading element
-      element.node_name = heading unless heading.nil?
-    end
-
-    # Removes paragraphs from tables
-    doc.search("td p").each { |node| node.node_name = "span" }
+  # Pretty print the class in console
+  def inspect
+    "<WordToMarkdown path=\"#{@document.path}\">"
   end
-end
 
-module Nokogiri
-  module XML
-    class Element
-
-      def indent
-        if styles['mso-list']
-          styles['mso-list'].split(" ")[1].sub("level","").to_i
-        else
-          (left_margin / 0.5).to_i
-        end
-      end
-
-      # The node's left-margin
-      # Used for parsing nested Lis
-      #
-      # Returns a float with the left margin
-      def left_margin
-        if styles['margin-left']
-          styles['margin-left'].to_f
-        elsif styles['margin']
-          styles['margin'].split(" ").last.to_f
-        else
-          0
-        end
-      end
-
-      # The node's font size
-      # Used for guessing heading sizes
-      #
-      # Returns a float with the font-size
-      def font_size
-        styles['font-size'].to_f if styles['font-size']
-      end
-    end
+  def to_s
+    document.to_s
   end
 end

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

@@ -0,0 +1,124 @@
+class WordToMarkdown
+  class Converter
+
+    attr_reader :document
+
+    HEADING_DEPTH = 6 # Number of headings to guess, e.g., h6
+    HEADING_STEP = 100/HEADING_DEPTH
+    MIN_HEADING_SIZE = 20
+    UNICODE_BULLETS = ["○", "o", "●", "\uF0B7", "\u2022", "\uF0A7"]
+
+    def initialize(document)
+      @document = document
+    end
+
+    def convert!
+
+      # Fonts and headings
+      semanticize_font_styles!
+      semanticize_headings!
+
+      # Tables
+      remove_paragraphs_from_tables!
+      semanticize_table_headers!
+
+      # list items
+      remove_paragraphs_from_list_items!
+      remove_unicode_bullets_from_list_items!
+      remove_whitespace_from_list_items!
+      remove_numbering_from_list_items!
+    end
+
+    # Returns an array of Nokogiri nodes that are implicit headings
+    def implicit_headings
+      @implicit_headings ||= begin
+        headings = []
+        @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
+    def font_sizes
+      @font_sizes ||= begin
+        sizes = []
+        @document.tree.css("[style]").each do |element|
+          sizes.push element.font_size.round(-1) unless element.font_size.nil?
+        end
+        sizes.uniq.sort
+      end
+    end
+
+    # Given a Nokogiri node, guess what heading it represents, if any
+    #
+    # node - the nokigiri node
+    #
+    # retuns the heading tag (e.g., H1), or nil
+    def guess_heading(node)
+      return nil if node.font_size == nil
+      [*1...HEADING_DEPTH].each do |heading|
+        return "h#{heading}" if node.font_size >= h(heading)
+      end
+      nil
+    end
+
+    # 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
+    #
+    # returns the minimum font size as an integer
+    def h(n)
+      font_sizes.percentile ((HEADING_DEPTH-1)-n) * HEADING_STEP
+    end
+
+    def semanticize_font_styles!
+      @document.tree.css("span").each do |node|
+        if node.bold?
+          node.node_name = "strong"
+        elsif node.italic?
+          node.node_name = "em"
+        end
+      end
+    end
+
+    def remove_paragraphs_from_tables!
+      @document.tree.search("td p").each { |node| node.node_name = "span" }
+    end
+
+    def remove_paragraphs_from_list_items!
+      @document.tree.search("li p").each { |node| node.node_name = "span" }
+    end
+
+    def remove_unicode_bullets_from_list_items!
+      @document.tree.search("li span").each do |span|
+        span.content = span.content.gsub /^([#{UNICODE_BULLETS.join("")}]+)/, ""
+      end
+    end
+
+    def remove_numbering_from_list_items!
+      @document.tree.search("li span").each do |span|
+        span.content = span.content.gsub /^[a-zA-Z0-9]+\./m, ""
+      end
+    end
+
+    def remove_whitespace_from_list_items!
+      @document.tree.search("li span").each { |span| span.content.strip! }
+    end
+
+    def semanticize_table_headers!
+      @document.tree.search("table tr:first td").each { |node| node.node_name = "th" }
+    end
+
+    # Try to guess heading where implicit bassed on font size
+    def semanticize_headings!
+      implicit_headings.each do |element|
+        heading = guess_heading element
+        element.node_name = heading unless heading.nil?
+      end
+    end
+
+  end
+end

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

@@ -0,0 +1,97 @@
+class WordToMarkdown
+  class Document
+    class NotFoundError < StandardError; end
+
+    attr_reader :path, :raw_html
+
+    def initialize(path)
+      @path = File.expand_path path, Dir.pwd
+      raise NotFoundError, "File #{@path} does not exist" unless File.exist?(@path)
+    end
+
+    def extension
+      File.extname path
+    end
+
+    def tree
+      @tree ||= begin
+        tree = Nokogiri::HTML(normalize(raw_html))
+        tree.css("title").remove
+        tree
+      end
+    end
+
+    # Returns the html representation of the document
+    def html
+      tree.to_html.gsub("</li>\n", "</li>")
+    end
+
+    # Returns the markdown representation of the document
+    def to_s
+      @markdown ||= scrub_whitespace(ReverseMarkdown.convert(html, WordToMarkdown::REVERSE_MARKDOWN_OPTIONS))
+    end
+
+    # Determine the document encoding
+    #
+    # html - the raw html export
+    #
+    # Returns the encoding, defaulting to "UTF-8"
+    def encoding(html)
+      match = html.encode("UTF-8", :invalid => :replace, :replace => "").match(/charset=([^\"]+)/)
+      if match
+        match[1].sub("macintosh", "MacRoman")
+      else
+        "UTF-8"
+      end
+    end
+
+    private
+
+    # Perform pre-processing normalization
+    #
+    # html - the raw html input from the export
+    #
+    # Returns the normalized html
+    def normalize(html)
+      encoding = encoding(html)
+      html = html.force_encoding(encoding).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
+    #
+    # Returns the normalized markdown
+    def scrub_whitespace(string)
+      string.sub!(/\A[[:space:]]+/,'')                # leading whitespace
+      string.sub!(/[[:space:]]+\z/,'')                # trailing whitespace
+      string.gsub!(/\n\n \n\n/,"\n\n")                # Quadruple line breaks
+      string.gsub!(/\u00A0/, "")                      # Unicode non-breaking spaces, injected as tabs
+      string
+    end
+
+    def tmpdir
+      @tmpdir ||= Dir.mktmpdir
+    end
+
+    def dest_path
+      dest_filename = File.basename(path).gsub(/#{Regexp.escape(extension)}$/, ".html")
+      File.expand_path(dest_filename, tmpdir)
+    end
+
+    def raw_html
+      @raw_html ||= begin
+        WordToMarkdown::run_command '--headless', '--convert-to', 'html', path, '--outdir', tmpdir
+        html = File.read dest_path
+        File.delete dest_path
+        html
+      end
+    end
+  end
+end

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

@@ -0,0 +1,3 @@
+class WordToMarkdown
+  VERSION = "1.0.0"
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-30 00:00:00.000000000 Z
+date: 2014-05-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: reverse_markdown
@@ -16,147 +16,167 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.7
+        version: '0.5'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.4.7
+        version: '0.5'
 - !ruby/object:Gem::Dependency
   name: descriptive_statistics
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.3
+        version: '1.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.3
+        version: '1.1'
 - !ruby/object:Gem::Dependency
   name: premailer
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.8'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.8'
 - !ruby/object:Gem::Dependency
   name: nokogiri-styles
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.1'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '10.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '10.3'
 - !ruby/object:Gem::Dependency
   name: shoulda
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.5'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '4.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '4.1'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.6'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.6'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.9'
 - !ruby/object:Gem::Dependency
-  name: rerun
+  name: mocha
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '4.7'
 description: Ruby Gem to convert Word documents to markdown.
 email: ben.balter@github.com
-executables: []
+executables:
+- w2m
 extensions: []
 extra_rdoc_files: []
 files:
+- bin/w2m
+- lib/nokogiri/xml/element.rb
 - lib/word-to-markdown.rb
+- lib/word-to-markdown/converter.rb
+- lib/word-to-markdown/document.rb
+- lib/word-to-markdown/version.rb
 homepage: https://github.com/benbalter/word-to-markdown
 licenses:
 - MIT