diff options
author | nagachika <nagachika@ruby-lang.org> | 2021-07-03 13:49:46 +0900 |
---|---|---|
committer | nagachika <nagachika@ruby-lang.org> | 2021-07-03 13:49:46 +0900 |
commit | e62cccaeb0986d43480bccbd365cb20056bda4d7 (patch) | |
tree | 7b70b94213b5b5758e9e1292fc3022011d2c914a /transcode.c | |
parent | 2aad080396f5b79a33502f1d812fb237968cb931 (diff) |
merge revision(s) e86c1f6fc53433ef5c82ed2b7a4cc9a12c153e4c,f6539202c52a051a4e6946a318a1d9cd29002990: [Backport #1205]
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 'transcode.c')
-rw-r--r-- | transcode.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/transcode.c b/transcode.c index a72afdc44b..d2abd9e0e5 100644 --- a/transcode.c +++ b/transcode.c @@ -2719,6 +2719,12 @@ str_transcode0(int argc, VALUE *argv, VALUE *self, int ecflags, VALUE ecopts) } } else { + if (senc && denc && !rb_enc_asciicompat(senc) && !rb_enc_asciicompat(denc)) { + rb_encoding *utf8 = rb_utf8_encoding(); + str = rb_str_conv_enc(str, senc, utf8); + senc = utf8; + sname = "UTF-8"; + } if (encoding_equal(sname, dname)) { sname = ""; dname = ""; |