diff options
author | usa <usa@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2013-04-02 04:13:32 +0000 |
---|---|---|
committer | usa <usa@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> | 2013-04-02 04:13:32 +0000 |
commit | be36df7f55a073e7fcb677497dfaf3c0bab12278 (patch) | |
tree | 2a5d4f95b73877fe4b36e53c119bf23095b1d662 | |
parent | b6a72bcf2f868bf075d334d05c7522c426db080f (diff) |
merge revision(s) 35112,35121: [Backport #6190]
* transcode.c (str_encode_bang, encoded_dup): if nothing was
transcoded, just set encoding but leave coderange unchanged as
forcee_encoding. [ruby-core:43557][Bug #6190]
* transcode.c (documentation for str_encode): Explain
that transcoding to the same encoding is a no-op
(i.e. no exceptions, no replacements,...).
[ruby-core:43557][Bug #6190]
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_1_9_3@40056 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
-rw-r--r-- | ChangeLog | 13 | ||||
-rw-r--r-- | test/ruby/test_m17n.rb | 8 | ||||
-rw-r--r-- | transcode.c | 10 | ||||
-rw-r--r-- | version.h | 2 |
4 files changed, 32 insertions, 1 deletions
@@ -1,3 +1,16 @@ +Tue Apr 2 13:13:19 2013 Martin Duerst <duerst@it.aoyama.ac.jp> + + * transcode.c (documentation for str_encode): Explain + that transcoding to the same encoding is a no-op + (i.e. no exceptions, no replacements,...). + [ruby-core:43557][Bug #6190] + +Tue Apr 2 13:13:19 2013 Nobuyoshi Nakada <nobu@ruby-lang.org> + + * transcode.c (str_encode_bang, encoded_dup): if nothing was + transcoded, just set encoding but leave coderange unchanged as + forcee_encoding. [ruby-core:43557][Bug #6190] + Tue Apr 2 13:07:29 2013 Tanaka Akira <akr@fsij.org> * time.c (num_exact): use to_r method only if to_int method is diff --git a/test/ruby/test_m17n.rb b/test/ruby/test_m17n.rb index 3553f3a0a4..699c8151dd 100644 --- a/test/ruby/test_m17n.rb +++ b/test/ruby/test_m17n.rb @@ -1369,6 +1369,14 @@ class TestM17N < Test::Unit::TestCase assert_equal(true, s.valid_encoding?) s << "\xff".force_encoding("utf-16be") assert_equal(false, s.valid_encoding?, bug4018) + + bug6190 = '[ruby-core:43557]' + s = "\xe9" + s = s.encode("utf-8", "utf-8") + assert_equal(false, s.valid_encoding?, bug6190) + s = "\xe9" + s.encode!("utf-8", "utf-8") + assert_equal(false, s.valid_encoding?, bug6190) end def test_getbyte diff --git a/transcode.c b/transcode.c index 4c3a273e7a..045ce2e118 100644 --- a/transcode.c +++ b/transcode.c @@ -2805,6 +2805,10 @@ str_encode_bang(int argc, VALUE *argv, VALUE str) encidx = str_transcode(argc, argv, &newstr); if (encidx < 0) return str; + if (newstr == str) { + rb_enc_associate_index(str, encidx); + return str; + } rb_str_shared_replace(str, newstr); return str_encode_associate(str, encidx); } @@ -2831,6 +2835,10 @@ static VALUE encoded_dup(VALUE newstr, VALUE str, int encidx); * in the source encoding. The last form by default does not raise * exceptions but uses replacement strings. * + * Please note that conversion from an encoding +enc+ to the + * same encoding +enc+ is a no-op, i.e. the receiver is returned without + * any changes, and no exceptions are raised, even if there are invalid bytes. + * * The +options+ Hash gives details for conversion and can have the following * keys: * @@ -2891,6 +2899,8 @@ encoded_dup(VALUE newstr, VALUE str, int encidx) if (encidx < 0) return rb_str_dup(str); if (newstr == str) { newstr = rb_str_dup(str); + rb_enc_associate_index(newstr, encidx); + return newstr; } else { RBASIC(newstr)->klass = rb_obj_class(str); @@ -1,5 +1,5 @@ #define RUBY_VERSION "1.9.3" -#define RUBY_PATCHLEVEL 407 +#define RUBY_PATCHLEVEL 408 #define RUBY_RELEASE_DATE "2013-04-02" #define RUBY_RELEASE_YEAR 2013 |