word-to-markdown 0.0.3 → 0.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 438abfb05468da472c652d87e12b80d40f714572
-  data.tar.gz: b43be781c4a35c7d5968bb97b8620af3cfd10bb8
+  metadata.gz: 2f7734f2a7a7b2ca0f3ac11ea9350cb5b34afdb3
+  data.tar.gz: f8b438412256bad44a7ca1ef5c094ef045a202be
 SHA512:
-  metadata.gz: 0fe70f87fdb8524e85316fccf6784f23e43e60f614e6037e7289583804b9a0f0fb4930eb79c60c23b67e11c3e2c57c87aa16a36a67d07e3c1aba375938b50614
-  data.tar.gz: e0ae583d9d9e343b9b722e236018a108e27ea454aec521607dd807a2dc63a4f96ca2a8392eec0024af1c1f723aa30c83621456c75726559df7180cacb5c3f310
+  metadata.gz: de20ce24839bc2e32f2405bc7b2acb37c1b0a78ca5a7bab06d16a3467639f6e00cccc8193a370b1fc695277857c9d69e8be87eb8ae82953cede2fc6b13732c91
+  data.tar.gz: 335420b487bd2bb17a11d8ec80321053e615502ab0dcb7217068ca5bd0a61a62a20a49ed437244bde7ae8494b099a6699b4c8cd823b8e6d14296985466ce7d78

data/lib/word-to-markdown.rb

@@ -1,5 +1,6 @@
 require 'reverse_markdown'
 require 'descriptive_statistics'
+require 'premailer'
 
 class WordToMarkdown
 
@@ -34,9 +35,14 @@ class WordToMarkdown
   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! /\n|\r/," "         # Remove linebreaks
     html.gsub! /“|”/, '"'          # Straighten curly double quotes
@@ -44,18 +50,26 @@ class WordToMarkdown
     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))
   end
 
+  # Returns the html representation of the document
   def html
     doc.to_html
   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
@@ -65,6 +79,11 @@ class WordToMarkdown
     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
@@ -73,6 +92,7 @@ class WordToMarkdown
     string.gsub!(/^-[[:space:]·]*/,"- ")            # Unnumbered lists
     string.gsub!(/\u00A0/, "")                      # Unicode non-breaking spaces, injected as tabs
     string.gsub!(/^ /, "")                          # Leading spaces
+    string.gsub!(/^- (\d+)\./, "\\1.")              # OL's wrapped in UL's see http://bit.ly/1ivqxy8
     string
   end
 
@@ -91,12 +111,18 @@ class WordToMarkdown
   def font_sizes
     @font_sizes ||= begin
       sizes = []
-      implicit_headings.each { |element| sizes.push element.font_size }
-      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|
@@ -107,6 +133,10 @@ 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
+  #
+  # returns the minimum font size as an integer
   def h(n)
     font_sizes.percentile ((HEADING_DEPTH-1)-n) * HEADING_STEP
   end
@@ -133,6 +163,7 @@ module Nokogiri
 
       FONT_SIZE_REGEX = /\bfont-size:\s?([0-9\.]+)pt;?\b/
 
+      # Extend nokogiri nodes to guess their font size where defined
       def font_size
         @font_size ||= begin
           match = FONT_SIZE_REGEX.match attr("style")

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-24 00:00:00.000000000 Z
+date: 2014-03-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: reverse_markdown
@@ -38,6 +38,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: 1.1.3
+- !ruby/object:Gem::Dependency
+  name: premailer
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement