diff options
author | nagachika <nagachika@ruby-lang.org> | 2021-07-18 11:19:13 +0900 |
---|---|---|
committer | nagachika <nagachika@ruby-lang.org> | 2021-07-18 11:19:13 +0900 |
commit | b93a2d9d2cac5d3efe72537debedb089d447d33a (patch) | |
tree | 232278aa0df215b592e05053d1081413a46590f5 /ext | |
parent | ca6ebde821991cb558003c3a1d680eaa8df3169d (diff) |
merge revision(s) 391abc543cea118a9cd7d6310acadbfa352668ef,e86c1f6fc53433ef5c82ed2b7a4cc9a12c153e4c,f6539202c52a051a4e6946a318a1d9cd29002990: [Backport #12052]
Scan the coderange in the given encoding
---
ext/-test-/string/enc_str_buf_cat.c | 14 ++++++++++++++
string.c | 32 ++++++++++++++++++++++---------
test/-ext-/string/test_enc_str_buf_cat.rb | 9 +++++++++
3 files changed, 46 insertions(+), 9 deletions(-)
Work around issue transcoding issue with non-ASCII compatible
encodings and xml escaping
When using a non-ASCII compatible source and destination encoding
and xml escaping (the :xml option to String#encode), the resulting
string was broken, as it used the correct non-ASCII compatible
encoding, but contained data that was ASCII-compatible instead of
compatible with the string's encoding.
Work around this issue by detecting the case where both the
source and destination encoding are non-ASCII compatible, and
transcoding the source string from the non-ASCII compatible
encoding to UTF-8. The xml escaping code will correctly handle
the UTF-8 source string and the return the correctly encoded
and escaped value.
Fixes [Bug #12052]
Co-authored-by: Nobuyoshi Nakada <nobu@ruby-lang.org>
---
test/ruby/test_transcode.rb | 19 +++++++++++++++++++
transcode.c | 6 ++++++
2 files changed, 25 insertions(+)
=?UTF-8?q?-=20add=20regression=20tests=20for=20U+6E7F=20(?=
=?UTF-8?q?=E6=B9=BF)=20in=20ISO-2022-JP?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
In ISO-2022-JP, the bytes use to code are the same as those for "<>".
This adds regression tests to make sure that these bytes, when representing
湿, are NOT escaped with encode("ISO-2022-JP, xml: :text) or similar.
These are additional regression tests for #12052.
---
test/ruby/test_transcode.rb | 3 +++
1 file changed, 3 insertions(+)
Diffstat (limited to 'ext')
-rw-r--r-- | ext/-test-/string/enc_str_buf_cat.c | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/ext/-test-/string/enc_str_buf_cat.c b/ext/-test-/string/enc_str_buf_cat.c index 9ac4a298be..4c1b262e1e 100644 --- a/ext/-test-/string/enc_str_buf_cat.c +++ b/ext/-test-/string/enc_str_buf_cat.c @@ -7,8 +7,22 @@ enc_str_buf_cat(VALUE str, VALUE str2) return rb_enc_str_buf_cat(str, RSTRING_PTR(str2), RSTRING_LEN(str2), rb_enc_get(str2)); } +static VALUE +str_conv_enc_opts(VALUE str, VALUE from, VALUE to, VALUE ecflags, VALUE ecopts) +{ + rb_encoding *from_enc = NIL_P(from) ? NULL : rb_to_encoding(from); + rb_encoding *to_enc = NIL_P(to) ? NULL : rb_to_encoding(to); + int flags = NUM2INT(ecflags); + if (!NIL_P(ecopts)) { + Check_Type(ecopts, T_HASH); + OBJ_FREEZE(ecopts); + } + return rb_str_conv_enc_opts(str, from_enc, to_enc, flags, ecopts); +} + void Init_string_enc_str_buf_cat(VALUE klass) { rb_define_method(klass, "enc_str_buf_cat", enc_str_buf_cat, 1); + rb_define_method(klass, "str_conv_enc_opts", str_conv_enc_opts, 4); } |