}
static bool isAllowedIDChar(uint32_t C, const LangOptions &LangOpts) {
- if (LangOpts.CPlusPlus11 || LangOpts.C11)
- return isCharInSet(C, C11AllowedIDChars);
- else if (LangOpts.CPlusPlus)
- return isCharInSet(C, CXX03AllowedIDChars);
- else
- return isCharInSet(C, C99AllowedIDChars);
+ if (LangOpts.CPlusPlus11 || LangOpts.C11) {
+ static const llvm::sys::UnicodeCharSet C11AllowedIDChars(
+ C11AllowedIDCharRanges);
+ return C11AllowedIDChars.contains(C);
+ } else if (LangOpts.CPlusPlus) {
+ static const llvm::sys::UnicodeCharSet CXX03AllowedIDChars(
+ CXX03AllowedIDCharRanges);
+ return CXX03AllowedIDChars.contains(C);
+ } else {
+ static const llvm::sys::UnicodeCharSet C99AllowedIDChars(
+ C99AllowedIDCharRanges);
+ return C99AllowedIDChars.contains(C);
+ }
}
static bool isAllowedInitiallyIDChar(uint32_t C, const LangOptions &LangOpts) {
assert(isAllowedIDChar(C, LangOpts));
- if (LangOpts.CPlusPlus11 || LangOpts.C11)
- return !isCharInSet(C, C11DisallowedInitialIDChars);
- else if (LangOpts.CPlusPlus)
+ if (LangOpts.CPlusPlus11 || LangOpts.C11) {
+ static const llvm::sys::UnicodeCharSet C11DisallowedInitialIDChars(
+ C11DisallowedInitialIDCharRanges);
+ return !C11DisallowedInitialIDChars.contains(C);
+ } else if (LangOpts.CPlusPlus) {
return true;
- else
- return !isCharInSet(C, C99DisallowedInitialIDChars);
+ } else {
+ static const llvm::sys::UnicodeCharSet C99DisallowedInitialIDChars(
+ C99DisallowedInitialIDCharRanges);
+ return !C99DisallowedInitialIDChars.contains(C);
+ }
}
static inline CharSourceRange makeCharRange(Lexer &L, const char *Begin,
CannotStartIdentifier
};
- if (!isCharInSet(C, C99AllowedIDChars)) {
+ static const llvm::sys::UnicodeCharSet C99AllowedIDChars(
+ C99AllowedIDCharRanges);
+ static const llvm::sys::UnicodeCharSet C99DisallowedInitialIDChars(
+ C99DisallowedInitialIDCharRanges);
+ if (!C99AllowedIDChars.contains(C)) {
Diags.Report(Range.getBegin(), diag::warn_c99_compat_unicode_id)
<< Range
<< CannotAppearInIdentifier;
- } else if (IsFirst && isCharInSet(C, C99DisallowedInitialIDChars)) {
+ } else if (IsFirst && C99DisallowedInitialIDChars.contains(C)) {
Diags.Report(Range.getBegin(), diag::warn_c99_compat_unicode_id)
<< Range
<< CannotStartIdentifier;
// Check C++98 compatibility.
if (Diags.getDiagnosticLevel(diag::warn_cxx98_compat_unicode_id,
Range.getBegin()) > DiagnosticsEngine::Ignored) {
- if (!isCharInSet(C, CXX03AllowedIDChars)) {
+ static const llvm::sys::UnicodeCharSet CXX03AllowedIDChars(
+ CXX03AllowedIDCharRanges);
+ if (!CXX03AllowedIDChars.contains(C)) {
Diags.Report(Range.getBegin(), diag::warn_cxx98_compat_unicode_id)
<< Range;
}
}
void Lexer::LexUnicode(Token &Result, uint32_t C, const char *CurPtr) {
+ static const llvm::sys::UnicodeCharSet UnicodeWhitespaceChars(
+ UnicodeWhitespaceCharRanges);
if (!isLexingRawMode() && !PP->isPreprocessedOutput() &&
- isCharInSet(C, UnicodeWhitespaceChars)) {
+ UnicodeWhitespaceChars.contains(C)) {
Diag(BufferPtr, diag::ext_unicode_whitespace)
<< makeCharRange(*this, BufferPtr, CurPtr);
#include "llvm/Support/UnicodeCharRanges.h"
// C11 D.1, C++11 [charname.allowed]
-static const UnicodeCharRange C11AllowedIDChars[] = {
+static const llvm::sys::UnicodeCharRange C11AllowedIDCharRanges[] = {
// 1
{ 0x00A8, 0x00A8 }, { 0x00AA, 0x00AA }, { 0x00AD, 0x00AD },
{ 0x00AF, 0x00AF }, { 0x00B2, 0x00B5 }, { 0x00B7, 0x00BA },
// C++03 [extendid]
// Note that this is not the same as C++98, but we don't distinguish C++98
// and C++03 in Clang.
-static const UnicodeCharRange CXX03AllowedIDChars[] = {
+static const llvm::sys::UnicodeCharRange CXX03AllowedIDCharRanges[] = {
// Latin
{ 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 }, { 0x00F8, 0x01F5 },
{ 0x01FA, 0x0217 }, { 0x0250, 0x02A8 },
};
// C99 Annex D
-static const UnicodeCharRange C99AllowedIDChars[] = {
+static const llvm::sys::UnicodeCharRange C99AllowedIDCharRanges[] = {
// Latin (1)
{ 0x00AA, 0x00AA },
};
// C11 D.2, C++11 [charname.disallowed]
-static const UnicodeCharRange C11DisallowedInitialIDChars[] = {
+static const llvm::sys::UnicodeCharRange C11DisallowedInitialIDCharRanges[] = {
{ 0x0300, 0x036F }, { 0x1DC0, 0x1DFF }, { 0x20D0, 0x20FF },
{ 0xFE20, 0xFE2F }
};
// C99 6.4.2.1p3: The initial character [of an identifier] shall not be a
// universal character name designating a digit.
// C99 Annex D defines these characters as "Digits".
-static const UnicodeCharRange C99DisallowedInitialIDChars[] = {
+static const llvm::sys::UnicodeCharRange C99DisallowedInitialIDCharRanges[] = {
{ 0x0660, 0x0669 }, { 0x06F0, 0x06F9 }, { 0x0966, 0x096F },
{ 0x09E6, 0x09EF }, { 0x0A66, 0x0A6F }, { 0x0AE6, 0x0AEF },
{ 0x0B66, 0x0B6F }, { 0x0BE7, 0x0BEF }, { 0x0C66, 0x0C6F },
};
// Unicode v6.2, chapter 6.2, table 6-2.
-static const UnicodeCharRange UnicodeWhitespaceChars[] = {
+static const llvm::sys::UnicodeCharRange UnicodeWhitespaceCharRanges[] = {
{ 0x0085, 0x0085 }, { 0x00A0, 0x00A0 }, { 0x1680, 0x1680 },
{ 0x180E, 0x180E }, { 0x2000, 0x200A }, { 0x2028, 0x2029 },
{ 0x202F, 0x202F }, { 0x205F, 0x205F }, { 0x3000, 0x3000 }