From ce372be903e5f3597f1dc83cb558f165850b3bee Mon Sep 17 00:00:00 2001 From: "NARUSE, Yui" Date: Wed, 20 Mar 2024 22:40:46 +0900 Subject: merge revision(s) ade56737e2273847426214035c0ff2340b43799a: [Backport #20190] (#10300) Fix coderange of invalid_encoding_string.<<(ord) Appending valid encoding character can change coderange from invalid to valid. Example: "\x95".force_encoding('sjis')<<0x5C will be a valid string "\x{955C}" --- string.c | 6 +++++- test/ruby/test_string.rb | 3 +++ version.h | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/string.c b/string.c index dfeba64a68..04162ef4d0 100644 --- a/string.c +++ b/string.c @@ -3522,8 +3522,12 @@ rb_str_concat(VALUE str1, VALUE str2) } rb_str_resize(str1, pos+len); memcpy(RSTRING_PTR(str1) + pos, buf, len); - if (cr == ENC_CODERANGE_7BIT && code > 127) + if (cr == ENC_CODERANGE_7BIT && code > 127) { cr = ENC_CODERANGE_VALID; + } + else if (cr == ENC_CODERANGE_BROKEN) { + cr = ENC_CODERANGE_UNKNOWN; + } ENC_CODERANGE_SET(str1, cr); } return str1; diff --git a/test/ruby/test_string.rb b/test/ruby/test_string.rb index 4aa119f8fd..42f2544b5a 100644 --- a/test/ruby/test_string.rb +++ b/test/ruby/test_string.rb @@ -301,6 +301,9 @@ CODE assert_raise(RangeError, bug) {S("a".force_encoding(Encoding::UTF_8)) << -1} assert_raise(RangeError, bug) {S("a".force_encoding(Encoding::UTF_8)) << 0x81308130} assert_nothing_raised {S("a".force_encoding(Encoding::GB18030)) << 0x81308130} + + s = "\x95".force_encoding(Encoding::SJIS).tap(&:valid_encoding?) + assert_predicate(s << 0x5c, :valid_encoding?) end def test_MATCH # '=~' diff --git a/version.h b/version.h index 7fc8d20892..6e24079fb6 100644 --- a/version.h +++ b/version.h @@ -11,7 +11,7 @@ # define RUBY_VERSION_MINOR RUBY_API_VERSION_MINOR #define RUBY_VERSION_TEENY 0 #define RUBY_RELEASE_DATE RUBY_RELEASE_YEAR_STR"-"RUBY_RELEASE_MONTH_STR"-"RUBY_RELEASE_DAY_STR -#define RUBY_PATCHLEVEL 15 +#define RUBY_PATCHLEVEL 16 #include "ruby/version.h" #include "ruby/internal/abi.h" -- cgit v1.2.3