Skip to content

[clang][bytecode] Implement __builtin_{wcscmp,wcsncmp} #132723

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.

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

Merged
merged 1 commit into from
Mar 24, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
28 changes: 26 additions & 2 deletions clang/lib/AST/ByteCode/InterpBuiltin.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -212,11 +212,13 @@ static bool interp__builtin_strcmp(InterpState &S, CodePtr OpPC,
const Pointer &A = getParam<Pointer>(Frame, 0);
const Pointer &B = getParam<Pointer>(Frame, 1);

if (ID == Builtin::BIstrcmp || ID == Builtin::BIstrncmp)
if (ID == Builtin::BIstrcmp || ID == Builtin::BIstrncmp ||
ID == Builtin::BIwcscmp || ID == Builtin::BIwcsncmp)
diagnoseNonConstexprBuiltin(S, OpPC, ID);

uint64_t Limit = ~static_cast<uint64_t>(0);
if (ID == Builtin::BIstrncmp || ID == Builtin::BI__builtin_strncmp)
if (ID == Builtin::BIstrncmp || ID == Builtin::BI__builtin_strncmp ||
ID == Builtin::BIwcsncmp || ID == Builtin::BI__builtin_wcsncmp)
Limit = peekToAPSInt(S.Stk, *S.getContext().classify(Call->getArg(2)))
.getZExtValue();

Expand All @@ -231,6 +233,9 @@ static bool interp__builtin_strcmp(InterpState &S, CodePtr OpPC,
if (A.isDummy() || B.isDummy())
return false;

bool IsWide = ID == Builtin::BIwcscmp || ID == Builtin::BIwcsncmp ||
ID == Builtin::BI__builtin_wcscmp ||
ID == Builtin::BI__builtin_wcsncmp;
assert(A.getFieldDesc()->isPrimitiveArray());
assert(B.getFieldDesc()->isPrimitiveArray());

Expand All @@ -248,6 +253,21 @@ static bool interp__builtin_strcmp(InterpState &S, CodePtr OpPC,
!CheckRange(S, OpPC, PB, AK_Read)) {
return false;
}

if (IsWide)
INT_TYPE_SWITCH(
*S.getContext().classify(S.getASTContext().getWCharType()), {
T A = PA.deref<T>();
T B = PB.deref<T>();
if (A < B) {
pushInteger(S, -1, Call->getType());
return true;
} else if (A > B) {
pushInteger(S, 1, Call->getType());
return true;
}
});

uint8_t CA = PA.deref<uint8_t>();
uint8_t CB = PB.deref<uint8_t>();

Expand Down Expand Up @@ -2120,6 +2140,10 @@ bool InterpretBuiltin(InterpState &S, CodePtr OpPC, const Function *F,
case Builtin::BIstrcmp:
case Builtin::BI__builtin_strncmp:
case Builtin::BIstrncmp:
case Builtin::BI__builtin_wcsncmp:
case Builtin::BIwcsncmp:
case Builtin::BI__builtin_wcscmp:
case Builtin::BIwcscmp:
if (!interp__builtin_strcmp(S, OpPC, Frame, F, Call))
return false;
break;
Expand Down
46 changes: 46 additions & 0 deletions clang/test/AST/ByteCode/builtin-functions.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@ extern "C" {
extern char *strchr(const char *s, int c);
extern wchar_t *wmemchr(const wchar_t *s, wchar_t c, size_t n);
extern wchar_t *wcschr(const wchar_t *s, wchar_t c);
extern int wcscmp(const wchar_t *s1, const wchar_t *s2);
extern int wcsncmp(const wchar_t *s1, const wchar_t *s2, size_t n);
}

namespace strcmp {
Expand Down Expand Up @@ -66,6 +68,50 @@ namespace strcmp {
static_assert(__builtin_strncmp("abab\0banana", "abab\0canada", 100) == 0);
}

namespace WcsCmp {
constexpr wchar_t kFoobar[6] = {L'f',L'o',L'o',L'b',L'a',L'r'};
constexpr wchar_t kFoobazfoobar[12] = {L'f',L'o',L'o',L'b',L'a',L'z',L'f',L'o',L'o',L'b',L'a',L'r'};

static_assert(__builtin_wcscmp(L"abab", L"abab") == 0);
static_assert(__builtin_wcscmp(L"abab", L"abba") == -1);
static_assert(__builtin_wcscmp(L"abab", L"abaa") == 1);
static_assert(__builtin_wcscmp(L"ababa", L"abab") == 1);
static_assert(__builtin_wcscmp(L"abab", L"ababa") == -1);
static_assert(__builtin_wcscmp(L"abab\0banana", L"abab") == 0);
static_assert(__builtin_wcscmp(L"abab", L"abab\0banana") == 0);
static_assert(__builtin_wcscmp(L"abab\0banana", L"abab\0canada") == 0);
#if __WCHAR_WIDTH__ == 32
static_assert(__builtin_wcscmp(L"a\x83838383", L"a") == (wchar_t)-1U >> 31);
#endif
static_assert(__builtin_wcscmp(0, L"abab") == 0); // both-error {{not an integral constant}} \
// both-note {{dereferenced null}}
static_assert(__builtin_wcscmp(L"abab", 0) == 0); // both-error {{not an integral constant}} \
// both-note {{dereferenced null}}

static_assert(__builtin_wcscmp(kFoobar, kFoobazfoobar) == -1);
static_assert(__builtin_wcscmp(kFoobar, kFoobazfoobar + 6) == 0); // both-error {{not an integral constant}} \
// both-note {{dereferenced one-past-the-end}}

static_assert(__builtin_wcsncmp(L"abaa", L"abba", 5) == -1);
static_assert(__builtin_wcsncmp(L"abaa", L"abba", 4) == -1);
static_assert(__builtin_wcsncmp(L"abaa", L"abba", 3) == -1);
static_assert(__builtin_wcsncmp(L"abaa", L"abba", 2) == 0);
static_assert(__builtin_wcsncmp(L"abaa", L"abba", 1) == 0);
static_assert(__builtin_wcsncmp(L"abaa", L"abba", 0) == 0);
static_assert(__builtin_wcsncmp(0, 0, 0) == 0);
static_assert(__builtin_wcsncmp(L"abab\0banana", L"abab\0canada", 100) == 0);
#if __WCHAR_WIDTH__ == 32
static_assert(__builtin_wcsncmp(L"a\x83838383", L"aa", 2) ==
(wchar_t)-1U >> 31);
#endif

static_assert(__builtin_wcsncmp(kFoobar, kFoobazfoobar, 6) == -1);
static_assert(__builtin_wcsncmp(kFoobar, kFoobazfoobar, 7) == -1);
static_assert(__builtin_wcsncmp(kFoobar, kFoobazfoobar + 6, 6) == 0);
static_assert(__builtin_wcsncmp(kFoobar, kFoobazfoobar + 6, 7) == 0); // both-error {{not an integral constant}} \
// both-note {{dereferenced one-past-the-end}}
}

/// Copied from constant-expression-cxx11.cpp
namespace strlen {
constexpr const char *a = "foo\0quux";
Expand Down