diff --git a/lib/markbridge/parsers/html/parser.rb b/lib/markbridge/parsers/html/parser.rb
index 61a718c..ad43622 100644
--- a/lib/markbridge/parsers/html/parser.rb
+++ b/lib/markbridge/parsers/html/parser.rb
@@ -5,6 +5,11 @@ module Parsers
module HTML
# Parses HTML into an AST using Nokogiri
class Parser
+ # Tags whose contents should be dropped entirely (not emitted as text).
+ # These are raw-text/metadata elements whose children are either CSS,
+ # JavaScript, or document metadata that shouldn't appear in output.
+ IGNORED_TAGS = %w[style script head title noscript template].freeze
+
attr_reader :unknown_tags
# Create a new parser with optional custom handlers
@@ -72,6 +77,8 @@ def process_text_node(node, parent)
# @param parent [AST::Element]
def process_element_node(node, parent)
tag_name = node.name.downcase
+ return if IGNORED_TAGS.include?(tag_name)
+
handler = @handlers[tag_name]
if handler
diff --git a/spec/unit/markbridge/parsers/html/parser_spec.rb b/spec/unit/markbridge/parsers/html/parser_spec.rb
index b3d7e13..2624229 100644
--- a/spec/unit/markbridge/parsers/html/parser_spec.rb
+++ b/spec/unit/markbridge/parsers/html/parser_spec.rb
@@ -132,6 +132,39 @@
expect(doc.children[1].children[0].text).to eq("Two")
end
+ it "drops style tag contents entirely" do
+ doc = parser.parse("hello")
+
+ expect(doc.children.size).to eq(1)
+ expect(doc.children[0]).to be_a(Markbridge::AST::Text)
+ expect(doc.children[0].text).to eq("hello")
+ end
+
+ it "drops script tag contents entirely" do
+ doc = parser.parse("hello")
+
+ expect(doc.children.size).to eq(1)
+ expect(doc.children[0]).to be_a(Markbridge::AST::Text)
+ expect(doc.children[0].text).to eq("hello")
+ end
+
+ it "drops head subtree including nested style/title/meta" do
+ html =
+ "T" \
+ "body text"
+ doc = parser.parse(html)
+
+ expect(doc.children.size).to eq(1)
+ expect(doc.children[0]).to be_a(Markbridge::AST::Text)
+ expect(doc.children[0].text).to eq("body text")
+ end
+
+ it "does not count ignored tags as unknown" do
+ parser.parse("")
+
+ expect(parser.unknown_tags).to be_empty
+ end
+
it "tracks unknown tags" do
parser.parse("text")