Merge pull request #14 from benbalter/gdoc-support

Gdoc support
benbalter · Mar 30, 2014 · 9ee1895 · 9ee1895
2 parents db0c515 + ae4b60d
commit 9ee1895
Show file tree

Hide file tree

Showing 3 changed files with 243 additions and 10 deletions.
diff --git a/lib/word-to-markdown.rb b/lib/word-to-markdown.rb
@@ -15,6 +15,7 @@ class WordToMarkdown
     .MsoListParagraphCxSpMiddle
     .MsoListParagraphCxSpLast
     .MsoListParagraph
+    li
   ]
 
   attr_reader :path, :doc
@@ -146,6 +147,20 @@ def li_selectors
     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
   def semanticize!
 
@@ -160,25 +175,24 @@ def semanticize!
         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]

diff --git a/test/fixtures/gdoc.htm b/test/fixtures/gdoc.htm
@@ -0,0 +1,215 @@
+<html>
+
+<head>
+  <meta content="text/html; charset=UTF-8" http-equiv="content-type">
+  <style type="text/css">
+    .lst-kix_id6kp4jljtnx-2>li: before {
+      content: "\0025a0  "
+    }
+    .lst-kix_id6kp4jljtnx-4>li: before {
+      content: "\0025cb  "
+    }
+    .lst-kix_id6kp4jljtnx-3>li: before {
+      content: "\0025cf  "
+    }
+    ul.lst-kix_id6kp4jljtnx-0 {
+      list-style-type: none
+    }
+    ul.lst-kix_id6kp4jljtnx-1 {
+      list-style-type: none
+    }
+    .lst-kix_id6kp4jljtnx-7>li: before {
+      content: "\0025cb  "
+    }
+    ul.lst-kix_id6kp4jljtnx-2 {
+      list-style-type: none
+    }
+    ul.lst-kix_id6kp4jljtnx-3 {
+      list-style-type: none
+    }
+    .lst-kix_id6kp4jljtnx-6>li: before {
+      content: "\0025cf  "
+    }
+    ul.lst-kix_id6kp4jljtnx-4 {
+      list-style-type: none
+    }
+    ul.lst-kix_id6kp4jljtnx-5 {
+      list-style-type: none
+    }
+    ul.lst-kix_id6kp4jljtnx-6 {
+      list-style-type: none
+    }
+    ul.lst-kix_id6kp4jljtnx-8 {
+      list-style-type: none
+    }
+    ul.lst-kix_id6kp4jljtnx-7 {
+      list-style-type: none
+    }
+    .lst-kix_id6kp4jljtnx-1>li: before {
+      content: "\0025cb  "
+    }
+    .lst-kix_id6kp4jljtnx-8>li: before {
+      content: "\0025a0  "
+    }
+    .lst-kix_id6kp4jljtnx-0>li: before {
+      content: "\0025cf  "
+    }
+    .lst-kix_id6kp4jljtnx-5>li: before {
+      content: "\0025a0  "
+    }
+    ol {
+      margin: 0;
+      padding: 0
+    }
+    .c1 {
+      widows: 2;
+      orphans: 2;
+      direction: ltr
+    }
+    .c4 {
+      max-width: 468pt;
+      background-color: #ffffff;
+      padding: 72pt 72pt 72pt 72pt
+    }
+    .c5 {
+      padding-left: 0pt;
+      margin-left: 72pt
+    }
+    .c0 {
+      margin: 0;
+      padding: 0
+    }
+    .c3 {
+      padding-left: 0pt;
+      margin-left: 36pt
+    }
+    .c2 {
+      height: 11pt
+    }
+    .title {
+      widows: 2;
+      padding-top: 0pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #000000;
+      font-size: 21pt;
+      font-family: "Trebuchet MS";
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+    .subtitle {
+      widows: 2;
+      padding-top: 0pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #666666;
+      font-style: italic;
+      font-size: 13pt;
+      font-family: "Trebuchet MS";
+      padding-bottom: 10pt;
+      page-break-after: avoid
+    }
+    li {
+      color: #000000;
+      font-size: 11pt;
+      font-family: "Arial"
+    }
+    p {
+      color: #000000;
+      font-size: 11pt;
+      margin: 0;
+      font-family: "Arial"
+    }
+    h1 {
+      widows: 2;
+      padding-top: 10pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #000000;
+      font-size: 16pt;
+      font-family: "Trebuchet MS";
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+    h2 {
+      widows: 2;
+      padding-top: 10pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #000000;
+      font-size: 13pt;
+      font-family: "Trebuchet MS";
+      font-weight: bold;
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+    h3 {
+      widows: 2;
+      padding-top: 8pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #666666;
+      font-size: 12pt;
+      font-family: "Trebuchet MS";
+      font-weight: bold;
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+    h4 {
+      widows: 2;
+      padding-top: 8pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #666666;
+      font-size: 11pt;
+      text-decoration: underline;
+      font-family: "Trebuchet MS";
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+    h5 {
+      widows: 2;
+      padding-top: 8pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #666666;
+      font-size: 11pt;
+      font-family: "Trebuchet MS";
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+    h6 {
+      widows: 2;
+      padding-top: 8pt;
+      line-height: 1.15;
+      orphans: 2;
+      text-align: left;
+      color: #666666;
+      font-style: italic;
+      font-size: 11pt;
+      font-family: "Trebuchet MS";
+      padding-bottom: 0pt;
+      page-break-after: avoid
+    }
+  </style>
+</head>
+
+<body class="c4">
+  <ul class="c0 lst-kix_id6kp4jljtnx-0 start">
+    <li class="c1 c3"><span>Bullet point</span>
+    </li>
+  </ul>
+  <ul class="c0 lst-kix_id6kp4jljtnx-1 start">
+    <li class="c1 c5"><span>Indented bullet point</span>
+    </li>
+  </ul>
+</body>
+
+</html>
diff --git a/test/test_word_to_markdown_lists.rb b/test/test_word_to_markdown_lists.rb
@@ -22,6 +22,10 @@ class TestWordToMarkdownLists < Test::Unit::TestCase
     validate_fixture "nested-ul", "- One\n  - Sub one\n    - Sub sub one\n    - Sub sub two\n\n  - Sub two\n\n- Two"
   end
 
+  should "parse gdoc nested uls" do
+    validate_fixture "gdoc", "- Bullet point\n\n  - Indented bullet point"
+  end
+
   should "parse left margin" do
     doc = WordToMarkdown.new "<p style='margin-left: 25px'>foo</p>"
     assert_equal 25, doc.doc.css("p").first.left_margin