word-to-markdown 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 81c1f8bce02e417b5338908ad224b5eede8170f1
-  data.tar.gz: 48ddedc28faa4f8de21b0038e8f758585fa376e5
+  metadata.gz: 0b8d7208877325f1e568f7f91255a7cfbc2df815
+  data.tar.gz: 4864e21eb71649017c61f677b24e611650a5aed0
 SHA512:
-  metadata.gz: 28a0c7229327a22874ee65dd7bf748c853deb9aafe83ad05ca7d228d701847f9707e7655dd354ddda4aa5b5400ca151ec0a67590aaf7bcc1fe83ade50bc4befc
-  data.tar.gz: 6f1e0ae2c3cca7ee0c9bce22439b6f21c79ad572851fa6056593f1fb0c1d26bee289bb586cdfab11102314cb7261e3ae0c7e515c04185fcb6d52bbc5e036c3b6
+  metadata.gz: 63bea7811559b150d55388090f1fd79df3a4f2a562cfe767bb3675a6c2af5e398cad2c00383ffb00c4536e66aebbbdc470a378eea4e3deec9de686cfd314082f
+  data.tar.gz: cd2c2593502aedef4fa2baddd245d671312b4521877401d1a07e60693d66d1fd15c3e7b14d5746bb7661a479daee7e00cc1c27e2a385ed73ee2846e01151a7f3

data/lib/word-to-markdown.rb

@@ -11,10 +11,11 @@ class WordToMarkdown
   MIN_HEADING_SIZE = 20
 
   LI_SELECTORS = %w[
-    MsoListParagraphCxSpFirst
-    MsoListParagraphCxSpMiddle
-    MsoListParagraphCxSpLast
-    MsoListParagraph
+    .MsoListParagraphCxSpFirst
+    .MsoListParagraphCxSpMiddle
+    .MsoListParagraphCxSpLast
+    .MsoListParagraph
+    li
   ]
 
   attr_reader :path, :doc
@@ -143,7 +144,21 @@ class WordToMarkdown
 
   # CSS selector to select non-symantic lists
   def li_selectors
-    ".#{LI_SELECTORS.join(",.")}"
+    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
@@ -160,25 +175,24 @@ class WordToMarkdown
         list_type = "ul"
       end
 
+      # calculate indent level
+      current_indent = indent(node.indent)
+
       # Determine parent node for this li, creating it if necessary
-      if node.indent > indent_level
+      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#{node.indent}"]
-        if node.indent == 1
-          list.parent = node.parent
-        else
-          list.parent = node.parent.css(".indent#{node.indent-1} li").last
-        end
+        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#{node.indent}").last
+        list = node.parent.css(".indent#{current_indent}").last
       end
 
       # Note our current nesting depth
-      indent_level = node.indent
+      indent_level = current_indent
 
       # Convert list paragraphs to actual numbered and unnumbered lists
       node.node_name = "li"
-      node.parent = list
+      node.parent = list if list
 
       # Scrub unicode bullets
       span = node.css("span:first")[1]

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: word-to-markdown
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-27 00:00:00.000000000 Z
+date: 2014-03-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: reverse_markdown