word-to-markdown 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 858e79fff023fe2b3150484359c1bccc480182bf
+  data.tar.gz: a6c2ac95b8be35efa54bd1938c31d08dc8bb0df0
+SHA512:
+  metadata.gz: daa684a5bd4bda7eb465bc4c58c75dea0080d095943ead5d6e0696cd4c941cd80f268b3b9f638fc1e02f7875c50de757e3c85331054ee89bd173228cc650922f
+  data.tar.gz: 73466db83836034919b906dee2b549ced6077f8b6a343e9f19bb2488942056e618027873a3b43fa6bbaddcdb0a54acb9f010d6115cc1ad413269c5645ac775c8

data/lib/word-to-markdown.rb

@@ -0,0 +1,102 @@
+require 'reverse_markdown'
+require 'descriptive_statistics'
+
+class WordToMarkdown
+
+  HEADING_DEPTH = 6 # Number of headings to guess, e.g., h6
+  HEADING_STEP = 100/HEADING_DEPTH
+  LI_SELECTORS = %w[
+    MsoListParagraphCxSpFirst
+    MsoListParagraphCxSpMiddle
+    MsoListParagraphCxSpLast
+  ]
+
+  attr_reader :path, :doc, :html
+
+  def initialize(path)
+    @path = path
+    @html = File.open(@path).read.encode("UTF-8", :invalid => :replace, :replace => "")
+    @doc = Nokogiri::HTML @html
+    semanticize!
+  end
+
+  def inspect
+    "<WordToMarkdown path=\"#{@path}\">"
+  end
+
+  def to_s
+    @markdown ||= scrub_whitespace(ReverseMarkdown.parse(@doc.to_html))
+  end
+
+  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!(/^([0-9]+)\.[[:space:]]*/,"\\1. ") # Numbered lists
+    string.gsub!(/^-[[:space:]]*/,"- ")             # Unnumbered lists
+    string
+  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?
+      end
+      headings
+    end
+  end
+
+  # Returns an array of font-sizes for implicit headings in the document
+  def font_sizes
+    @font_sizes ||= begin
+      sizes = []
+      implicit_headings.each { |element| sizes.push element.font_size }
+      sizes
+    end
+  end
+
+  # Given a Nokogiri node, guess what heading it represents, if any
+  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
+  def h(n)
+    font_sizes.percentile ((HEADING_DEPTH-1)-n) * HEADING_STEP
+  end
+
+  # Try to make semantic markup explicit where implied by the export
+  def semanticize!
+    # Convert unnumbered list paragraphs to actual unnumbered lists
+    @doc.css(".#{LI_SELECTORS.join(",.")}").each { |node| node.node_name = "li" }
+
+    # 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
+  end
+end
+
+module Nokogiri
+  module XML
+    class Element
+
+      FONT_SIZE_REGEX = /\bfont-size:\s?([0-9\.]+)pt;?\b/
+
+      def font_size
+        @font_size ||= begin
+          match = FONT_SIZE_REGEX.match attr("style")
+          match[1].to_i unless match.nil?
+        end
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,142 @@
+--- !ruby/object:Gem::Specification
+name: word-to-markdown
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Ben Balter
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-03-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: reverse_markdown
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.4.7
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.4.7
+- !ruby/object:Gem::Dependency
+  name: descriptive_statistics
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.1.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.1.3
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Ruby Gem to convert Word documents to markdown.
+email: ben.balter@github.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/word-to-markdown.rb
+homepage: https://github.com/benbalter/word-to-markdown
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.0
+signing_key: 
+specification_version: 4
+summary: Ruby Gem to convert Word documents to markdown
+test_files: []