Merge pull request #4 from flavorjones/3-head-includes-body

Modify pluck behavior when seeing a `head` tag to include the `body`
flavorjones · Apr 26, 2024 · 60ff491 · 60ff491
2 parents d345d9d + 04ba3eb
commit 60ff491
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 3 deletions.
diff --git a/lib/nokogiri/html5/inference.rb b/lib/nokogiri/html5/inference.rb
@@ -93,7 +93,7 @@ module PluckRegexp # :nodoc:
  TBODY = /\A\s*<(#{PluckTags::TBODY.join("|")})\b/i
  TBODY_TR = /\A\s*<(#{PluckTags::TBODY_TR.join("|")})\b/i
  COLGROUP = /\A\s*<(#{PluckTags::COLGROUP.join("|")})\b/i
- HEAD_OUTER = /\A\s*<(head)\b/i
+ HTML_INNER = /\A\s*<(head)\b/i
  BODY_OUTER = /\A\s*<(body)\b/i
  end
 
@@ -184,7 +184,7 @@ def pluck_path(input) # :nodoc:
  when PluckRegexp::TBODY then "tbody/*"
  when PluckRegexp::TBODY_TR then "tbody/tr/*"
  when PluckRegexp::COLGROUP then "colgroup/*"
- when PluckRegexp::HEAD_OUTER then "head"
+ when PluckRegexp::HTML_INNER then "./*"
  when PluckRegexp::BODY_OUTER then "body"
  end
  end

diff --git a/test/nokogiri/html5/test_inference.rb b/test/nokogiri/html5/test_inference.rb
@@ -26,7 +26,7 @@
  ],
  "html" => [
  "<body><div>hello</div></body>",
- "<head><meta charset=\"UTF-8\"><title>hello</title></head>"
+ "<head><meta charset=\"UTF-8\"><title>hello</title></head><body><div>hello</div></body>"
  ]
  }
 
@@ -99,6 +99,25 @@
  end
  end
 
+ describe "passed a Fragment containing head and body" do
+ it "returns a Fragment containing both head and body" do
+ fragment = "<head></head><body></body>"
+ actual = Nokogiri::HTML5::Inference.parse(fragment).to_html
+
+ assert_equal(fragment, actual)
+ end
+ end
+
+ describe "passed a Fragment containing head and p" do
+ it "returns a Fragment containing both head and body" do
+ fragment = "<head><p>"
+ expected = "<head></head><body><p></p></body>"
+ actual = Nokogiri::HTML5::Inference.parse(fragment).to_html
+
+ assert_equal(expected, actual)
+ end
+ end
+
  describe "multiple children that need plucking" do
  it "parses correctly" do
  fragment = "<tr><td>hello</td></tr><tr><td>world</td></tr>"