word-to-markdown 1.1.1 → 1.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8826b727f290781e7713325662d056482018d730
-  data.tar.gz: 8692363359366aac70359bf251ccba409f80bba7
+  metadata.gz: 08754da1501d6e4918d753a0727a6fc28fe17962
+  data.tar.gz: 4947e109b790a2c61575ce8349b0f11f51598320
 SHA512:
-  metadata.gz: 8db1e766ad6bfc341de71a4fc82d14f8a3d109005f2bda9d779af2bd7b0f722d160cf873bff98cf56f9fa7929ab9282e945d249fc220fa56beafe46bd962cf9c
-  data.tar.gz: fd84315c249e983a6bdf073a8573d2fbca82886ed05da15b8325ceca4f655b3181cee6ee20cf888c933a4b10794a5c5145ad86a8f9ebf8f9550163de9ce284da
+  metadata.gz: b70ac3cf257afc4eea9e591923bb43835d6f1a31b45bf0d6a39728acbbd55bc759e2d88f9f3d9456740d683552f4379aa046b321121cf5721f7114ab634d788c
+  data.tar.gz: f1e16e97e23ff20229f187474872496e1201409a5f606d25f5f62dba039ea2e8c66c20ead82278037861fe8d9a9256113f4064c894cf37015261d9b8635a83ca

data/bin/w2m

@@ -2,10 +2,15 @@
 
 require 'word-to-markdown'
 
-if ARGV.size != 1
+if ARGV.size != 1 || ARGV[0] == "--help"
   puts "Usage: bundle exec w2m path/to/document.docx"
   exit 1
 end
 
-doc = WordToMarkdown.new ARGV[0]
-puts doc.to_s
+if ARGV[0] == "--version"
+  puts "WordToMarkdown v#{WordToMarkdown::VERSION}"
+  puts "LibreOffice #{WordToMarkdown.soffice_version}"
+else
+  doc = WordToMarkdown.new ARGV[0]
+  puts doc.to_s
+end

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

@@ -14,7 +14,6 @@ class WordToMarkdown
     end
 
     def convert!
-
       # Fonts and headings
       semanticize_font_styles!
       semanticize_headings!
@@ -95,18 +94,18 @@ class WordToMarkdown
 
     def remove_unicode_bullets_from_list_items!
       @document.tree.search("li span").each do |span|
-        span.content = span.content.gsub /^([#{UNICODE_BULLETS.join("")}]+)/, ""
+        span.inner_html = span.inner_html.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, ""
+        span.inner_html = span.inner_html.gsub /^[a-zA-Z0-9]+\./m, ""
       end
     end
 
     def remove_whitespace_from_list_items!
-      @document.tree.search("li span").each { |span| span.content.strip! }
+      @document.tree.search("li span").each { |span| span.inner_html.strip! }
     end
 
     def semanticize_table_headers!

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

@@ -17,7 +17,7 @@ class WordToMarkdown
 
     def tree
       @tree ||= begin
-        tree = Nokogiri::HTML(normalize(raw_html))
+        tree = Nokogiri::HTML(normalized_html)
         tree.css("title").remove
         tree
       end
@@ -38,8 +38,8 @@ class WordToMarkdown
     # 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=([^\"]+)/)
+    def encoding
+      match = raw_html.encode("UTF-8", :invalid => :replace, :replace => "").match(/charset=([^\"]+)/)
       if match
         match[1].sub("macintosh", "MacRoman")
       else
@@ -54,9 +54,9 @@ class WordToMarkdown
     # 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 => "")
+    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
@@ -71,9 +71,11 @@ class WordToMarkdown
     #
     # 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!(" ", " ")                     # 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
     end

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

@@ -1,3 +1,3 @@
 class WordToMarkdown
-  VERSION = "1.1.1"
+  VERSION = "1.1.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.1.2
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-01-10 00:00:00.000000000 Z
+date: 2015-03-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: reverse_markdown