From b8a5f4cd5c8fe29c65d7a00e67170223d9d2b50e Mon Sep 17 00:00:00 2001
From: Watson <watson1978@gmail.com>
Date: Tue, 16 Jul 2024 10:48:53 +0900
Subject: [PATCH] Fix performance issue caused by using repeated `>` characters
 inside `<?xml` (#170)

A `<` is treated as a string delimiter.
In certain cases, if `<` is used in succession, read and match are
repeated, which slows down the process. Therefore, the following is used
to read ahead to a specific part of the string in advance.
---
 lib/rexml/parsers/baseparser.rb           |  3 ++-
 lib/rexml/source.rb                       |  6 +++---
 test/parse/test_processing_instruction.rb | 11 +++++++++++
 3 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
index 5cf1af21..b117e654 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -125,6 +125,7 @@ class BaseParser
 
       module Private
         INSTRUCTION_END = /#{NAME}(\s+.*?)?\?>/um
+        INSTRUCTION_TERM = "?>"
         TAG_PATTERN = /((?>#{QNAME_STR}))\s*/um
         CLOSE_PATTERN = /(#{QNAME_STR})\s*>/um
         ATTLISTDECL_END = /\s+#{NAME}(?:#{ATTDEF})*\s*>/um
@@ -639,7 +640,7 @@ def parse_id_invalid_details(accept_external_id:,
       end
 
       def process_instruction(start_position)
-        match_data = @source.match(Private::INSTRUCTION_END, true)
+        match_data = @source.match(Private::INSTRUCTION_END, true, term: Private::INSTRUCTION_TERM)
         unless match_data
           message = "Invalid processing instruction node"
           @source.position = start_position
diff --git a/lib/rexml/source.rb b/lib/rexml/source.rb
index 5715c352..4c30532a 100644
--- a/lib/rexml/source.rb
+++ b/lib/rexml/source.rb
@@ -117,7 +117,7 @@ def read_until(term)
     def ensure_buffer
     end
 
-    def match(pattern, cons=false)
+    def match(pattern, cons=false, term: nil)
       if cons
         @scanner.scan(pattern).nil? ? nil : @scanner
       else
@@ -240,7 +240,7 @@ def ensure_buffer
     # Note: When specifying a string for 'pattern', it must not include '>' except in the following formats:
     # - ">"
     # - "XXX>" (X is any string excluding '>')
-    def match( pattern, cons=false )
+    def match( pattern, cons=false, term: nil )
       while true
         if cons
           md = @scanner.scan(pattern)
@@ -250,7 +250,7 @@ def match( pattern, cons=false )
         break if md
         return nil if pattern.is_a?(String)
         return nil if @source.nil?
-        return nil unless read
+        return nil unless read(term)
       end
 
       md.nil? ? nil : @scanner
diff --git a/test/parse/test_processing_instruction.rb b/test/parse/test_processing_instruction.rb
index 13384935..ac4c2ff0 100644
--- a/test/parse/test_processing_instruction.rb
+++ b/test/parse/test_processing_instruction.rb
@@ -1,8 +1,12 @@
 require "test/unit"
+require "core_assertions"
+
 require "rexml/document"
 
 module REXMLTests
   class TestParseProcessinInstruction < Test::Unit::TestCase
+    include Test::Unit::CoreAssertions
+
     def parse(xml)
       REXML::Document.new(xml)
     end
@@ -69,5 +73,12 @@ def test_after_root
 
       assert_equal("abc", events[:processing_instruction])
     end
+
+    def test_gt_linear_performance
+      seq = [10000, 50000, 100000, 150000, 200000]
+      assert_linear_performance(seq, rehearsal: 10) do |n|
+        REXML::Document.new('<?xml version="1.0" ' + ">" * n + ' ?>')
+      end
+    end
   end
 end