From 3819f9fe80279f40639f4808bf257340548797fa Mon Sep 17 00:00:00 2001
From: Watson <watson1978@gmail.com>
Date: Thu, 11 Jul 2024 14:54:06 +0900
Subject: [PATCH] Fix ReDoS by using repeated space characters inside
 `<!DOCTYPE name [<!ATTLIST>]>`

Fix performance by removing unnecessary spaces.
---
 lib/rexml/parsers/baseparser.rb |  2 +-
 test/parse/test_attlist.rb      | 17 +++++++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)
 create mode 100644 test/parse/test_attlist.rb

diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
index e8f1a069..260b04d3 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -349,7 +349,7 @@ def pull_event
               contents = md[0]
 
               pairs = {}
-              values = md[0].scan( ATTDEF_RE )
+              values = md[0].strip.scan( ATTDEF_RE )
               values.each do |attdef|
                 unless attdef[3] == "#IMPLIED"
                   attdef.compact!
diff --git a/test/parse/test_attlist.rb b/test/parse/test_attlist.rb
new file mode 100644
index 00000000..e50545f0
--- /dev/null
+++ b/test/parse/test_attlist.rb
@@ -0,0 +1,17 @@
+require "test/unit"
+require "core_assertions"
+
+require "rexml/document"
+
+module REXMLTests
+  class TestParseAttlist < Test::Unit::TestCase
+    include Test::Unit::CoreAssertions
+
+    def test_gt_linear_performance_attlist
+      seq = [10000, 50000, 100000, 150000, 200000]
+      assert_linear_performance(seq, rehearsal: 10) do |n|
+        REXML::Document.new('<!DOCTYPE schema SYSTEM "foo.dtd" [<!ATTLIST ' + " " * n + ' root v CDATA #FIXED "test">]>')
+      end
+    end
+  end
+end