diff options
author | Jeremy Evans <[email protected]> | 2021-06-26 12:32:39 -0700 |
---|---|---|
committer | GitHub <[email protected]> | 2021-06-26 12:32:39 -0700 |
commit | e86c1f6fc53433ef5c82ed2b7a4cc9a12c153e4c (patch) | |
tree | c72cf93eaf31977d2cd80ecda12683c4017e3b55 | |
parent | 391abc543cea118a9cd7d6310acadbfa352668ef (diff) |
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 <[email protected]>
Notes
Notes:
Merged: https://github.com/ruby/ruby/pull/4605
Merged-By: jeremyevans <[email protected]>
-rw-r--r-- | test/ruby/test_transcode.rb | 19 | ||||
-rw-r--r-- | transcode.c | 6 |
2 files changed, 25 insertions, 0 deletions
diff --git a/test/ruby/test_transcode.rb b/test/ruby/test_transcode.rb index 04c8248697..17384fd0c7 100644 --- a/test/ruby/test_transcode.rb +++ b/test/ruby/test_transcode.rb @@ -126,6 +126,25 @@ class TestTranscode < Test::Unit::TestCase assert_equal("D\xFCrst".force_encoding('iso-8859-2'), "D\xFCrst".encode('iso-8859-2', 'iso-8859-1')) end + def test_encode_xml_multibyte + encodings = %w'UTF-8 UTF-16LE UTF-16BE UTF-32LE UTF-32BE' + encodings.each do |src_enc| + encodings.each do |dst_enc| + escaped = "<>".encode(src_enc).encode(dst_enc, :xml=>:text) + assert_equal("<>", escaped.encode('UTF-8'), "failed encoding #{src_enc} to #{dst_enc} with xml: :text") + + escaped = '<">'.encode(src_enc).encode(dst_enc, :xml=>:attr) + assert_equal('"<">"', escaped.encode('UTF-8'), "failed encoding #{src_enc} to #{dst_enc} with xml: :attr") + + escaped = "<>".encode(src_enc).force_encoding("UTF-8").encode(dst_enc, src_enc, :xml=>:text) + assert_equal("<>", escaped.encode('UTF-8'), "failed encoding #{src_enc} to #{dst_enc} with xml: :text") + + escaped = '<">'.encode(src_enc).force_encoding("UTF-8").encode(dst_enc, src_enc, :xml=>:attr) + assert_equal('"<">"', escaped.encode('UTF-8'), "failed encoding #{src_enc} to #{dst_enc} with xml: :attr") + end + end + end + def test_ascii_range encodings = [ 'US-ASCII', 'ASCII-8BIT', diff --git a/transcode.c b/transcode.c index 505c8177fb..a452448d99 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 = ""; |