kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

string.c: fix false coderange

Browse source 
* string.c (rb_enc_str_scrub): enc can differ from the actual
  encoding of the string, the cached coderange is useless then.
  [ruby-core:82674] [Bug #13874]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@59763 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2017-09-06 13:11:44 +00:00
parent faa26f5570
commit bd10ce165c
2 changed files with 36 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
string.c
View file

@ -9553,6 +9553,8 @@ str_compat_and_valid(VALUE str, rb_encoding *enc)
return str; return str;
} }
static VALUE enc_str_scrub(rb_encoding *enc, VALUE str, VALUE repl, int cr);
/** /**
* @param str the string to be scrubbed * @param str the string to be scrubbed
* @param repl the replacement character * @param repl the replacement character
@ -9561,13 +9563,25 @@ str_compat_and_valid(VALUE str, rb_encoding *enc)
VALUE VALUE
rb_str_scrub(VALUE str, VALUE repl) rb_str_scrub(VALUE str, VALUE repl)
{ {
return rb_enc_str_scrub(STR_ENC_GET(str), str, repl); rb_encoding *enc = STR_ENC_GET(str);
return enc_str_scrub(enc, str, repl, ENC_CODERANGE(str));
} }
VALUE VALUE
rb_enc_str_scrub(rb_encoding *enc, VALUE str, VALUE repl) rb_enc_str_scrub(rb_encoding *enc, VALUE str, VALUE repl)
{ {
int cr = ENC_CODERANGE(str); int cr = ENC_CODERANGE_UNKNOWN;
if (enc == STR_ENC_GET(str)) {
/* cached coderange makes sense only when enc equals the
* actual encoding of str */
cr = ENC_CODERANGE(str);
}
return enc_str_scrub(enc, str, repl, cr);
}
static VALUE
enc_str_scrub(rb_encoding *enc, VALUE str, VALUE repl, int cr)
{
int encidx; int encidx;
VALUE buf = Qnil; VALUE buf = Qnil;
const char *rep; const char *rep;

27
test/ruby/test_transcode.rb
View file

@ -2180,17 +2180,19 @@ class TestTranscode < Test::Unit::TestCase
def test_valid_dummy_encoding def test_valid_dummy_encoding
bug9314 = '[ruby-core:59354] [Bug #9314]' bug9314 = '[ruby-core:59354] [Bug #9314]'
assert_separately(%W[- -- #{bug9314}], <<-'end;') assert_separately(%W[- -- #{bug9314}], "#{<<~"begin;"}\n#{<<~'end;'}")
bug = ARGV.shift begin;
result = assert_nothing_raised(TypeError, bug) {break "test".encode(Encoding::UTF_16)} bug = ARGV.shift
assert_equal("\xFE\xFF\x00t\x00e\x00s\x00t", result.b, bug) result = assert_nothing_raised(TypeError, bug) {break "test".encode(Encoding::UTF_16)}
result = assert_nothing_raised(TypeError, bug) {break "test".encode(Encoding::UTF_32)} assert_equal("\xFE\xFF\x00t\x00e\x00s\x00t", result.b, bug)
assert_equal("\x00\x00\xFE\xFF\x00\x00\x00t\x00\x00\x00e\x00\x00\x00s\x00\x00\x00t", result.b, bug) result = assert_nothing_raised(TypeError, bug) {break "test".encode(Encoding::UTF_32)}
assert_equal("\x00\x00\xFE\xFF\x00\x00\x00t\x00\x00\x00e\x00\x00\x00s\x00\x00\x00t", result.b, bug)
end; end;
end end
def test_loading_race def test_loading_race
assert_separately([], <<-'end;') #do assert_separately([], "#{<<~"begin;"}\n#{<<~'end;'}")
begin;
bug11277 = '[ruby-dev:49106] [Bug #11277]' bug11277 = '[ruby-dev:49106] [Bug #11277]'
num = 2 num = 2
th = (0...num).map do |i| th = (0...num).map do |i|
@ -2207,6 +2209,17 @@ class TestTranscode < Test::Unit::TestCase
end; end;
end end
def test_scrub_encode_with_coderange
bug = '[ruby-core:82674] [Bug #13874]'
s = "\xe5".b
u = Encoding::UTF_8
assert_equal("?", s.encode(u, u, invalid: :replace, replace: "?"),
"should replace invalid byte")
assert_predicate(s, :valid_encoding?, "any char is valid in binary")
assert_equal("?", s.encode(u, u, invalid: :replace, replace: "?"),
"#{bug} coderange should not have side effects")
end
def test_universal_newline def test_universal_newline
bug11324 = '[ruby-core:69841] [Bug #11324]' bug11324 = '[ruby-core:69841] [Bug #11324]'
usascii = Encoding::US_ASCII usascii = Encoding::US_ASCII