From c6a0d03649c686a537c1f513a1e32205ac6a6512 Mon Sep 17 00:00:00 2001 From: Peter Zhu Date: Wed, 26 Jun 2024 16:12:53 -0400 Subject: [PATCH] Fix corruption of encoding name string [Bug #20595] enc_set_default_encoding will free the C string if the encoding is nil, but the C string can be used by the encoding name string. This will cause the encoding name string to be corrupted. Consider the following code: Encoding.default_internal = Encoding::ASCII_8BIT names = Encoding.default_internal.names p names Encoding.default_internal = nil p names It outputs: ["ASCII-8BIT", "BINARY", "internal"] ["ASCII-8BIT", "BINARY", "\x00\x00\x00\x00\x00\x00\x00\x00"] Co-authored-by: Matthew Valentine-House --- encoding.c | 2 +- test/ruby/test_m17n.rb | 11 +++++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/encoding.c b/encoding.c index 480cc8bdc6..a09d84b757 100644 --- a/encoding.c +++ b/encoding.c @@ -1301,7 +1301,7 @@ enc_names_i(st_data_t name, st_data_t idx, st_data_t args) VALUE *arg = (VALUE *)args; if ((int)idx == (int)arg[0]) { - VALUE str = rb_fstring_cstr((char *)name); + VALUE str = rb_interned_str_cstr((char *)name); rb_ary_push(arg[1], str); } return ST_CONTINUE; diff --git a/test/ruby/test_m17n.rb b/test/ruby/test_m17n.rb index a6493374b5..3c7bb4b870 100644 --- a/test/ruby/test_m17n.rb +++ b/test/ruby/test_m17n.rb @@ -1721,6 +1721,17 @@ class TestM17N < Test::Unit::TestCase assert_equal(e("[\"\xB4\xC1\xBB\xFA\"]"), s, bug11787) end + def test_encoding_names_of_default_internal + # [Bug #20595] + assert_separately(%w(-W0), "#{<<~"begin;"}\n#{<<~"end;"}") + begin; + Encoding.default_internal = Encoding::ASCII_8BIT + names = Encoding.default_internal.names + Encoding.default_internal = nil + assert_include names, "int" + "ernal", "[Bug #20595]" + end; + end + def test_greek_capital_gap bug12204 = '[ruby-core:74478] [Bug #12204] GREEK CAPITAL RHO and SIGMA' assert_equal("\u03A3", "\u03A1".succ, bug12204)