Merge branch 'pr136-block-level'

flavorjones · Feb 7, 2018 · 9b13194 · 9b13194
2 parents 6ca00aa + e5d0c7b
commit 9b13194
Show file tree

Hide file tree

Showing 3 changed files with 94 additions and 8 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,7 @@
 Features:
 
 * Support HTML5 `<main>` tag. #133 (Thanks, @MothOnMars!)
+* Recognize HTML5 block elements. #136 (Thanks, @MothOnMars!)
 * Support SVG `<symbol>` tag. #131 (Thanks, @baopham!)
 * Support for whitelisting CSS functions, initially just `calc`. #122/#123 (Thanks, @NikoRoberts!)
 

diff --git a/lib/loofah/elements.rb b/lib/loofah/elements.rb
@@ -2,13 +2,88 @@
 
 module Loofah
   module Elements
-    # Block elements in HTML4
-    STRICT_BLOCK_LEVEL = Set.new %w[address blockquote center dir div dl
-      fieldset form h1 h2 h3 h4 h5 h6 hr isindex menu noframes
-      noscript ol p pre table ul]
+    STRICT_BLOCK_LEVEL_HTML4 = Set.new %w[
+      address
+      blockquote
+      center
+      dir
+      div
+      dl
+      fieldset
+      form
+      h1
+      h2
+      h3
+      h4
+      h5
+      h6
+      hr
+      isindex
+      menu
+      noframes
+      noscript
+      ol
+      p
+      pre
+      table
+      ul
+    ]
 
-    # The following elements may also be considered block-level elements since they may contain block-level elements
-    LOOSE_BLOCK_LEVEL = Set.new %w[dd dt frameset li tbody td tfoot th thead tr]
+    # https://developer.mozilla.org/en-US/docs/Web/HTML/Block-level_elements
+    STRICT_BLOCK_LEVEL_HTML5 = Set.new %w[
+      address
+      article
+      aside
+      blockquote
+      canvas
+      dd
+      div
+      dl
+      dt
+      fieldset
+      figcaption
+      figure
+      footer
+      form
+      h1
+      h2
+      h3
+      h4
+      h5
+      h6
+      header
+      hgroup
+      hr
+      li
+      main
+      nav
+      noscript
+      ol
+      output
+      p
+      pre
+      section
+      table
+      tfoot
+      ul
+      video
+    ]
+
+    STRICT_BLOCK_LEVEL = STRICT_BLOCK_LEVEL_HTML4 + STRICT_BLOCK_LEVEL_HTML5
+
+    # The following elements may also be considered block-level
+    # elements since they may contain block-level elements
+    LOOSE_BLOCK_LEVEL = Set.new %w[dd
+      dt
+      frameset
+      li
+      tbody
+      td
+      tfoot
+      th
+      thead
+      tr
+    ]
 
     BLOCK_LEVEL = STRICT_BLOCK_LEVEL + LOOSE_BLOCK_LEVEL
   end

diff --git a/test/integration/test_html.rb b/test/integration/test_html.rb
@@ -19,11 +19,16 @@ class IntegrationTestHtml < Loofah::TestCase
     end
 
     context "#to_text" do
-      it "add newlines before and after block elements" do
+      it "add newlines before and after html4 block elements" do
         html = Loofah.fragment "<div>tweedle<h1>beetle</h1>bottle<span>puddle</span>paddle<div>battle</div>muddle</div>"
         assert_equal "\ntweedle\nbeetle\nbottlepuddlepaddle\nbattle\nmuddle\n", html.to_text
       end
 
+      it "add newlines before and after html5 block elements" do
+        html = Loofah.fragment "<div>tweedle<section>beetle</section>bottle<span>puddle</span>paddle<div>battle</div>muddle</div>"
+        assert_equal "\ntweedle\nbeetle\nbottlepuddlepaddle\nbattle\nmuddle\n", html.to_text
+      end
+
       it "remove extraneous whitespace" do
         html = Loofah.fragment "<div>tweedle\n\n\t\n\s\nbeetle</div>"
         assert_equal "\ntweedle\n\nbeetle\n", html.to_text
@@ -47,11 +52,16 @@ class IntegrationTestHtml < Loofah::TestCase
     end
 
     context "#to_text" do
-      it "add newlines before and after block elements" do
+      it "add newlines before and after html4 block elements" do
         html = Loofah.document "<div>tweedle<h1>beetle</h1>bottle<span>puddle</span>paddle<div>battle</div>muddle</div>"
         assert_equal "\ntweedle\nbeetle\nbottlepuddlepaddle\nbattle\nmuddle\n", html.to_text
       end
 
+      it "add newlines before and after html5 block elements" do
+        html = Loofah.document "<div>tweedle<section>beetle</section>bottle<span>puddle</span>paddle<div>battle</div>muddle</div>"
+        assert_equal "\ntweedle\nbeetle\nbottlepuddlepaddle\nbattle\nmuddle\n", html.to_text
+      end
+
       it "remove extraneous whitespace" do
         html = Loofah.document "<div>tweedle\n\n\t\n\s\nbeetle</div>"
         assert_equal "\ntweedle\n\nbeetle\n", html.to_text