1berry/ruby
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix corruption of encoding name string

Browse Source 
[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 <matt@eightbitraptor.com>
This commit is contained in:
Peter Zhu 2024-06-26 16:12:53 -04:00
parent 815b345b41
commit c6a0d03649
2 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
encoding.c
View File

@ -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;

11
test/ruby/test_m17n.rb
View File

@ -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)