When iterating over a range of char16_t in reverse the _Utf_view was
incorrectly treating U+DC00 as a valid high surrogate that can precede
the low surrogate. But U+DC00 is a low surrogate, and so should not be
allowed before another low surrogate. The check should be u2 >= 0xDC00
rather than u2 > 0xDC00.
libstdc++-v3/ChangeLog:
* include/bits/unicode.h (_Utf_view::_M_read_reverse_utf16):
Fix check for high surrogate preceding low surrogate.
* testsuite/ext/unicode/view.cc: Check unpaired low surrogates.
---
Tested x86_64-linux.
libstdc++-v3/include/bits/unicode.h | 2 +-
libstdc++-v3/testsuite/ext/unicode/view.cc | 5 +++++
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/libstdc++-v3/include/bits/unicode.h
b/libstdc++-v3/include/bits/unicode.h
index 00efbe89ca8e..44872db4ed68 100644
--- a/libstdc++-v3/include/bits/unicode.h
+++ b/libstdc++-v3/include/bits/unicode.h
@@ -527,7 +527,7 @@ namespace __unicode
{
// read a low surrogate, expect a high surrogate before it.
uint16_t __u2 = *--_M_curr();
- if (__u2 < 0xD800 || __u2 > 0xDC00) [[unlikely]]
+ if (__u2 < 0xD800 || __u2 >= 0xDC00) [[unlikely]]
__c = _S_error(); // unpaired low surrogate
else
{
diff --git a/libstdc++-v3/testsuite/ext/unicode/view.cc
b/libstdc++-v3/testsuite/ext/unicode/view.cc
index 4ccf646e0945..40c8fcf34fb7 100644
--- a/libstdc++-v3/testsuite/ext/unicode/view.cc
+++ b/libstdc++-v3/testsuite/ext/unicode/view.cc
@@ -94,6 +94,11 @@ test_illformed_utf16()
compare(uc::_Utf16_view(s4), u"\uFFFD\uFFFD"sv);
std::array s5{ s[1], s[0], s[1] };
compare(uc::_Utf16_view(s5), u"\uFFFD\N{CLOWN FACE}"sv);
+
+ std::array<char16_t, 2> s6{ 0xDC00, 0xDC01 };
+ compare(uc::_Utf16_view(s6), u"\uFFFD\uFFFD"sv);
+ std::array<char16_t, 2> s7{ 0xD7FF, 0xDC00 };
+ compare(uc::_Utf16_view(s7), u"\uD7FF\uFFFD"sv);
}
constexpr void
--
2.51.0
