From f6539202c52a051a4e6946a318a1d9cd29002990 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20D=C3=BCrst?= Date: Thu, 1 Jul 2021 17:33:43 +0900 Subject: =?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(+) (limited to 'test/ruby') diff --git a/test/ruby/test_transcode.rb b/test/ruby/test_transcode.rb index 17384fd0c7..c8b0034e06 100644 --- a/test/ruby/test_transcode.rb +++ b/test/ruby/test_transcode.rb @@ -143,6 +143,9 @@ class TestTranscode < Test::Unit::TestCase assert_equal('"<">"', escaped.encode('UTF-8'), "failed encoding #{src_enc} to #{dst_enc} with xml: :attr") end end + # regression test; U+6E7F (湿) uses the same bytes in ISO-2022-JP as "<>" + assert_equal( "<>\u6E7F", "<>\u6E7F".encode("ISO-2022-JP").encode("ISO-2022-JP", :xml=>:text).encode("UTF-8")) + assert_equal("\"<>\u6E7F\"", "<>\u6E7F".encode("ISO-2022-JP").encode("ISO-2022-JP", :xml=>:attr).encode("UTF-8")) end def test_ascii_range -- cgit v1.2.3