tequilaOS/platform_bionic
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge "Fix 5-byte mbrtoc16 test for glibc/musl." into main am: d0b8d3c901 am: 38ef6b78c2 am: b8e9947119

Browse source 
Original change: https://android-review.googlesource.com/c/platform/bionic/+/2658959

Change-Id: I00fccba333323f70a8cd6e9f2d263c0706b0d724
Signed-off-by: Automerger Merge Worker <android-build-automerger-merge-worker@system.gserviceaccount.com>
This commit is contained in:
Dan Albert 2023-07-19 00:31:31 +00:00 committed by Automerger Merge Worker
commit 1d9a47178c
1 changed files with 33 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
tests/uchar_test.cpp
View file

@ -24,6 +24,22 @@
#include <locale.h> #include <locale.h>
#include <stdint.h> #include <stdint.h>
// Modern versions of UTF-8 (https://datatracker.ietf.org/doc/html/rfc3629 and
// newer) explicitly disallow code points beyond U+10FFFF, which exclude all 5-
// and 6-byte sequences. Earlier versions of UTF-8 allowed the wider range:
// https://datatracker.ietf.org/doc/html/rfc2279.
//
// Bionic's unicode implementation was written after the high values were
// excluded, so it has never supported them. Other implementations (at least
// as of glibc 2.36), do support those sequences.
#if defined(__ANDROID__) || defined(ANDROID_HOST_MUSL)
constexpr bool kLibcSupportsLongUtf8Sequences = 0;
#elif defined(__GLIBC__)
constexpr bool kLibcSupportsLongUtf8Sequences = 1;
#else
#error kLibcSupportsLongUtf8Sequences must be configured for this platform
#endif
TEST(uchar, sizeof_uchar_t) { TEST(uchar, sizeof_uchar_t) {
EXPECT_EQ(2U, sizeof(char16_t)); EXPECT_EQ(2U, sizeof(char16_t));
EXPECT_EQ(4U, sizeof(char32_t)); EXPECT_EQ(4U, sizeof(char32_t));
@ -146,10 +162,24 @@ TEST(uchar, mbrtoc16) {
ASSERT_EQ(static_cast<char16_t>(0xdbea), out); ASSERT_EQ(static_cast<char16_t>(0xdbea), out);
ASSERT_EQ(4U, mbrtoc16(&out, "\xf4\x8a\xaf\x8d" "ef", 6, nullptr)); ASSERT_EQ(4U, mbrtoc16(&out, "\xf4\x8a\xaf\x8d" "ef", 6, nullptr));
ASSERT_EQ(static_cast<char16_t>(0xdfcd), out); ASSERT_EQ(static_cast<char16_t>(0xdfcd), out);
// Illegal 5-byte UTF-8. }
TEST(uchar, mbrtoc16_long_sequences) {
ASSERT_STREQ("C.UTF-8", setlocale(LC_CTYPE, "C.UTF-8"));
uselocale(LC_GLOBAL_LOCALE);
char16_t out = u'\0';
errno = 0; errno = 0;
ASSERT_EQ(static_cast<size_t>(-1), mbrtoc16(&out, "\xf8\xa1\xa2\xa3\xa4", 5, nullptr)); auto result = mbrtoc16(&out, "\xf8\xa1\xa2\xa3\xa4", 5, nullptr);
ASSERT_EQ(EILSEQ, errno); if (kLibcSupportsLongUtf8Sequences) {
EXPECT_EQ(5U, result);
EXPECT_EQ(0, errno);
EXPECT_EQ(u'\uf94a', out);
} else {
EXPECT_EQ(static_cast<size_t>(-1), result);
EXPECT_EQ(EILSEQ, errno);
EXPECT_EQ(u'\0', out);
}
} }
TEST(uchar, mbrtoc16_reserved_range) { TEST(uchar, mbrtoc16_reserved_range) {