word-to-markdown 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 858e79fff023fe2b3150484359c1bccc480182bf
-  data.tar.gz: a6c2ac95b8be35efa54bd1938c31d08dc8bb0df0
+  metadata.gz: 64e2eeda272f608f1d1bfd5690abdeebdd1f31d8
+  data.tar.gz: ad2cd8d38fe5893463097ddb41fd973e001642df
 SHA512:
-  metadata.gz: daa684a5bd4bda7eb465bc4c58c75dea0080d095943ead5d6e0696cd4c941cd80f268b3b9f638fc1e02f7875c50de757e3c85331054ee89bd173228cc650922f
-  data.tar.gz: 73466db83836034919b906dee2b549ced6077f8b6a343e9f19bb2488942056e618027873a3b43fa6bbaddcdb0a54acb9f010d6115cc1ad413269c5645ac775c8
+  metadata.gz: 37da10c45c34e29bd671c2d6833e81f754eaea14e07fbca693eb8b5d813db9a5a508d2bb483a0045f0d5df8de3d704db0ec8bfe25f2345c6358dd8d83eaea003
+  data.tar.gz: cff63c72bbc8fba7e994454875c01b56d9d239fa822762e30d317519d28e3ae7821f9414be923733f4a1cb48c888dcd7fd15c0c346c07d510687f11782507f55

data/lib/word-to-markdown.rb

@@ -5,27 +5,62 @@ class WordToMarkdown
 
   HEADING_DEPTH = 6 # Number of headings to guess, e.g., h6
   HEADING_STEP = 100/HEADING_DEPTH
+  MIN_HEADING_SIZE = 20
+  
   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
+  attr_reader :path, :doc
+
+  # 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
+    end
+    @doc = Nokogiri::HTML normalize(html)
     semanticize!
   end
 
+  # Perform pre-processing normalization
+  def normalize(html)
+    encoding = encoding(html)
+    html = html.force_encoding(encoding).encode("UTF-8", :invalid => :replace, :replace => "")
+    html.gsub! /\<\/?o:[^>]+>/, "" # Strip everything in the office namespace
+    html.gsub! /\n|\r/," "         # remove linebreaks
+    html
+  end
+
   def inspect
     "<WordToMarkdown path=\"#{@path}\">"
   end
 
   def to_s
-    @markdown ||= scrub_whitespace(ReverseMarkdown.parse(@doc.to_html))
+    @markdown ||= scrub_whitespace(ReverseMarkdown.parse(html))
+  end
+
+  def html
+    @doc.to_html
+  end
+
+  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
 
   def scrub_whitespace(string)
@@ -33,7 +68,9 @@ class WordToMarkdown
     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.gsub!(/^-[[:space:]·]*/,"- ")            # Unnumbered lists
+    string.gsub!(/\u00A0/, "")                      # Unicode non-breaking spaces, injected as tabs
+    string.gsub!(/^ /, "")                          # Leading spaces
     string
   end
 
@@ -42,7 +79,7 @@ class WordToMarkdown
     @implicit_headings ||= begin
       headings = []
       @doc.css("[style]").each do |element|
-        headings.push element unless element.font_size.nil?
+        headings.push element unless element.font_size.nil? || element.font_size < MIN_HEADING_SIZE
       end
       headings
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-22 00:00:00.000000000 Z
+date: 2014-03-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: reverse_markdown