Skip to content

[S390X] fix utf8->utf16 conversion test case failures #129789

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
saitama951 wants to merge 2 commits into
base: main
Choose a base branch
from
+44 −9
Open

[S390X] fix utf8->utf16 conversion test case failures #129789

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
61002ed
fix utf8 encoding test case failures
saitama951 Jun 24, 2026
48ade3e
Add > U+00FF test case
am11 May 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions src/coreclr/pal/tests/palsuite/locale_info/MultiByteToWideChar/test4/test4.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -224,6 +224,23 @@ PALTEST(locale_info_MultiByteToWideChar_test4_paltest_multibytetowidechar_test4,
free(wideBuffer);
}

{
// U+6F22 — code unit > U+00FF catches long-code-path bugs that move
// only the low byte instead of performing a full 16-bit byte swap.
const char utf8[] = "\xE6\xBC\xA2";
WCHAR wide[1] = { 0 };
size_t n = minipal_convert_utf8_to_utf16(utf8, sizeof(utf8) - 1, (CHAR16_T*)wide, 1, 0);
if (n != 1 || wide[0] != 0x6F22)
Fail("utf8->utf16 produced 0x%04x (n=%zu)\n", wide[0], n);

#if BIGENDIAN
wide[0] = 0;
n = minipal_convert_utf8_to_utf16(utf8, sizeof(utf8) - 1, (CHAR16_T*)wide, 1, MINIPAL_TREAT_AS_LITTLE_ENDIAN);
if (n != 1 || wide[0] != 0x226F)
Fail("treat-as-LE utf8->utf16 produced 0x%04x (n=%zu)\n", wide[0], n);
#endif
}

#if BIGENDIAN
{
const char* ascii = "ABCDEFGHIJKLMNOPQRSTUVWXYZ123456";
Expand Down
21 changes: 21 additions & 0 deletions src/coreclr/pal/tests/palsuite/locale_info/WideCharToMultiByte/test5/test5.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,6 +148,27 @@ PALTEST(locale_info_WideCharToMultiByte_test5_paltest_widechartomultibyte_test5,
free(utf8Buffer);
}

{
// U+6F22 — code unit > U+00FF catches long-code-path bugs that move
// only the low byte instead of performing a full 16-bit byte swap.
const WCHAR srcNative[1] = { 0x6F22 };
CHAR utf8[4] = { 0 };
size_t n = minipal_convert_utf16_to_utf8((const CHAR16_T*)srcNative, 1, utf8, sizeof(utf8), 0);
if (n != 3 || memcmp(utf8, "\xE6\xBC\xA2", 3) != 0)
Fail("utf16->utf8 produced %02x %02x %02x (n=%zu)\n",
(unsigned char)utf8[0], (unsigned char)utf8[1], (unsigned char)utf8[2], n);

#if BIGENDIAN
// Stored little-endian (22 6F) reads as BE word 0x226F.
const WCHAR srcLE[1] = { 0x226F };
memset(utf8, 0, sizeof(utf8));
n = minipal_convert_utf16_to_utf8((const CHAR16_T*)srcLE, 1, utf8, sizeof(utf8), MINIPAL_TREAT_AS_LITTLE_ENDIAN);
if (n != 3 || memcmp(utf8, "\xE6\xBC\xA2", 3) != 0)
Fail("treat-as-LE utf16->utf8 produced %02x %02x %02x (n=%zu)\n",
(unsigned char)utf8[0], (unsigned char)utf8[1], (unsigned char)utf8[2], n);
#endif
}

#if BIGENDIAN
{
const char* expected = "ABCDEFGHIJKLMNOPQRSTUVWXYZ123456";
Expand Down
15 changes: 6 additions & 9 deletions src/native/minipal/utf8.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -983,7 +983,7 @@ static size_t GetChars(UTF8Encoding* self, unsigned char* bytes, size_t byteCoun
}
#if BIGENDIAN
if (self->treatAsLE)
*pTarget = ((CHAR16_T)ch)<<8;
*pTarget = (((CHAR16_T)ch) << 8 | ((CHAR16_T)ch) >> 8);
else
#endif
*pTarget = (CHAR16_T)ch;
Expand Down Expand Up @@ -1438,7 +1438,7 @@ static size_t GetBytes(UTF8Encoding* self, CHAR16_T* chars, size_t charCount, un
// compiling "ch = *pSrc++;", so rather use "ch = *pSrc; pSrc++;" instead
#if BIGENDIAN
if (self->treatAsLE)
ch = (*pSrc) >> 8;
ch = (CHAR16_T)(((*pSrc) >> 8) | ((*pSrc) << 8));
else
#endif
ch = *pSrc;
Expand Down Expand Up @@ -1581,7 +1581,7 @@ static size_t GetBytes(UTF8Encoding* self, CHAR16_T* chars, size_t charCount, un
{
#if BIGENDIAN
if (self->treatAsLE)
ch = (*pSrc) >> 8;
ch = (CHAR16_T)(((*pSrc) >> 8) | ((*pSrc) << 8));
else
#endif
ch = *pSrc;
Expand Down Expand Up @@ -1619,7 +1619,7 @@ static size_t GetBytes(UTF8Encoding* self, CHAR16_T* chars, size_t charCount, un
{
#if BIGENDIAN
if (self->treatAsLE)
ch = (*pSrc) >> 8;
ch = (CHAR16_T)(((*pSrc) >> 8) | ((*pSrc) << 8));
else
#endif
ch = *pSrc;
Expand All @@ -1635,7 +1635,7 @@ static size_t GetBytes(UTF8Encoding* self, CHAR16_T* chars, size_t charCount, un
{
#if BIGENDIAN
if (self->treatAsLE)
ch = (*pSrc) >> 8;
ch = (CHAR16_T)(((*pSrc) >> 8) | ((*pSrc) << 8));
else
#endif
ch = *pSrc;
Expand All @@ -1652,10 +1652,7 @@ static size_t GetBytes(UTF8Encoding* self, CHAR16_T* chars, size_t charCount, un
ch = *(int*)pSrc;
int chc = *(int*)(pSrc + 2);
#if BIGENDIAN
if (self->treatAsLE){
if (((ch | chc) & (int)0x80FF80FF) != 0) goto LongCodeWithMask;
}
else
if (((ch | chc) & (int)0x80FF80FF) != 0) goto LongCodeWithMask;
#else
if (((ch | chc) & (int)0xFF80FF80) != 0) goto LongCodeWithMask;
#endif
Expand Down
Loading