From b4f8623441a8be53b643fed826ba44e933cafd7e Mon Sep 17 00:00:00 2001
From: nagachika <nagachika@ruby-lang.org>
Date: Thu, 18 Jan 2024 11:50:31 +0900
Subject: merge revision(s) b3d612804946e841e47d14e09b6839224a79c1a4: [Backport
 #20150]

	Fix memory leak in grapheme clusters

	[Bug #20150]

	String#grapheme_cluters and String#each_grapheme_cluster leaks memory
	because if the string is not UTF-8, then the created regex will not
	be freed.

	For example:

	    str = "hello world".encode(Encoding::UTF_32LE)

	    10.times do
	      1_000.times do
	        str.grapheme_clusters
	      end

	      puts `ps -o rss= -p #{$$}`
	    end

	Before:

	    26000
	    42256
	    59008
	    75792
	    92528
	    109232
	    125936
	    142672
	    159392
	    176160

	After:

	    9264
	    9504
	    9808
	    10000
	    10128
	    10224
	    10352
	    10544
	    10704
	    10896
	---
	 string.c                 | 98 +++++++++++++++++++++++++++++++-----------------
	 test/ruby/test_string.rb | 11 ++++++
	 2 files changed, 75 insertions(+), 34 deletions(-)
---
 test/ruby/test_string.rb | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'test/ruby')

diff --git a/test/ruby/test_string.rb b/test/ruby/test_string.rb
index 7c685407d6..069813e681 100644
--- a/test/ruby/test_string.rb
+++ b/test/ruby/test_string.rb
@@ -1074,6 +1074,17 @@ CODE
     assert_equal("C", res[2])
   end
 
+  def test_grapheme_clusters_memory_leak
+    assert_no_memory_leak([], "", "#{<<~"begin;"}\n#{<<~'end;'}", "[Bug #todo]", rss: true)
+    begin;
+      str = "hello world".encode(Encoding::UTF_32LE)
+
+      10_000.times do
+        str.grapheme_clusters
+      end
+    end;
+  end
+
   def test_each_line
     verbose, $VERBOSE = $VERBOSE, nil
 
-- 
cgit v1.2.3