From ce565cd4b851977bf37a470bee54e441bb60486d Mon Sep 17 00:00:00 2001
From: Peter Zhu <peter@peterzhu.ca>
Date: Mon, 29 Jul 2024 20:45:26 -0400
Subject: [Bug #20653] Fix memory leak in String#start_with? when regexp times
 out (#11255)

Fix memory leak in String#start_with? when regexp times out

[Bug #20653]

This commit refactors how Onigmo handles timeout. Instead of raising a
timeout error, onig_search will return a ONIGERR_TIMEOUT which the
caller can free memory, and then raise a timeout error.

This fixes a memory leak in String#start_with when the regexp times out.
For example:

    regex = Regexp.new("^#{"(a*)" * 10_000}x$", timeout: 0.000001)
    str = "a" * 1000000 + "x"

    10.times do
      100.times do
        str.start_with?(regex)
      rescue
      end

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

Before:

    33216
    51936
    71152
    81728
    97152
    103248
    120384
    133392
    133520
    133616

After:

    14912
    15376
    15824
    15824
    16128
    16128
    16144
    16144
    16160
    16160
---
 test/ruby/test_string.rb | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'test')

diff --git a/test/ruby/test_string.rb b/test/ruby/test_string.rb
index 149c128ed4..dcb81cfc6d 100644
--- a/test/ruby/test_string.rb
+++ b/test/ruby/test_string.rb
@@ -2010,6 +2010,22 @@ CODE
     assert_nil($&)
   end
 
+  def test_start_with_timeout_memory_leak
+    assert_no_memory_leak([], "#{<<~"begin;"}", "#{<<~'end;'}", "[Bug #20653]", rss: true)
+      regex = Regexp.new("^#{"(a*)" * 10_000}x$", timeout: 0.000001)
+      str = "a" * 1_000_000 + "x"
+
+      code = proc do
+        str.start_with?(regex)
+      rescue
+      end
+
+      10.times(&code)
+    begin;
+      1_000.times(&code)
+    end;
+  end
+
   def test_strip
     assert_equal(S("x"), S("      x        ").strip)
     assert_equal(S("x"), S(" \n\r\t     x  \t\r\n\n      ").strip)
-- 
cgit v1.2.3