id	summary	reporter	owner	description	type	status	milestone	component	version	severity	resolution	keywords	cc
4340	property_tree xml parser failed to handle wstream with i18n char	zhuo.qiang@…	Sebastian Redl	"boost::property_tree::read_xml(wistream&, wptree&) throw exception if tag/value/attribute has a unicode with '\0' inside, 

for example, for chinese character L'\u4E00', an exception will be throwed because the parser treat L'\u4E00' as '\0'.

for example, the following test case won't pass:

BOOST_AUTO_TEST_CASE(test_i18n_xml_tag_name)
{
    wistringstream in(L""<\u4E00>abc</\u4E00>"");
    property_tree::wptree pt;
    BOOST_REQUIRE_NO_THROW(property_tree::read_xml(in, pt));
    BOOST_CHECK(L""abc"" == pt.get<wstring>(L""\u4E00""));
}

BOOST_AUTO_TEST_CASE(test_i18n_xml_attribute_name)
{
    wistringstream in(L""<tag \u4E00=\""abc\"">def</tag>"");
    property_tree::wptree pt;
    BOOST_REQUIRE_NO_THROW(property_tree::read_xml(in, pt));
    BOOST_CHECK(L""abc"" == pt.get<wstring>(L""tag.<xmlattr>.\u4E00""));
}

BOOST_AUTO_TEST_CASE(test_i18n_xml_attribute_value)
{
    wistringstream in(L""<tag attribute=\""\u4E00\"">def</tag>"");
    property_tree::wptree pt;
    BOOST_REQUIRE_NO_THROW(property_tree::read_xml(in, pt));
    BOOST_CHECK(L""\u4E00"" == pt.get<wstring>(L""tag.<xmlattr>.attribute""));
}

BOOST_AUTO_TEST_CASE(test_i18n_xml_tag_value)
{
    wistringstream in(L""<tag>\u4E00</tag>"");
    property_tree::wptree pt;
    BOOST_REQUIRE_NO_THROW(property_tree::read_xml(in, pt));
    BOOST_CHECK(L""\u4E00"" == pt.get<wstring>(L""tag""));
}


The fix is treat the all char whose value above 255 same as 'z' when doing semantic action.



"	Patches	closed	Boost 1.45.0	property_tree	Boost 1.44.0	Showstopper	fixed	property_tree i18n unicode