зеркало из https://github.com/microsoft/clang-1.git
Properly validate UCNs for C99 and C++03 (both more restrictive than C(++)11).
Add warnings under -Wc++11-compat, -Wc++98-compat, and -Wc99-compat when a particular UCN is incompatible with a different standard, and -Wunicode when a UCN refers to a surrogate character in C++03. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@174788 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Jordan Rose
Родитель
d523df6a14
Коммит
ed9c59f2ae
|
|
@ -40,6 +40,7 @@ def ImplicitConversionFloatingPointToBool :
|
|||
DiagGroup<"implicit-conversion-floating-point-to-bool">;
|
||||
def BadArrayNewLength : DiagGroup<"bad-array-new-length">;
|
||||
def BuiltinRequiresHeader : DiagGroup<"builtin-requires-header">;
|
||||
def C99Compat : DiagGroup<"c99-compat">;
|
||||
def CXXCompat: DiagGroup<"c++-compat">;
|
||||
def CastAlign : DiagGroup<"cast-align">;
|
||||
def : DiagGroup<"cast-qual">;
|
||||
|
|
|
|||
|
|
@ -121,6 +121,18 @@ def err_ucn_escape_basic_scs : Error<
|
|||
def err_ucn_control_character : Error<
|
||||
"universal character name refers to a control character">;
|
||||
def err_ucn_escape_invalid : Error<"invalid universal character">;
|
||||
def warn_ucn_escape_surrogate : Warning<
|
||||
"universal character name refers to a surrogate character">,
|
||||
InGroup<Unicode>;
|
||||
|
||||
def warn_c99_compat_unicode_id : Warning<
|
||||
"%select{using this character in an identifier|starting an identifier with "
|
||||
"this character}0 is incompatible with C99">,
|
||||
InGroup<C99Compat>, DefaultIgnore;
|
||||
def warn_cxx98_compat_unicode_id : Warning<
|
||||
"using this character in an identifier is incompatible with C++98">,
|
||||
InGroup<CXX98Compat>, DefaultIgnore;
|
||||
|
||||
def warn_cxx98_compat_literal_ucn_escape_basic_scs : Warning<
|
||||
"specifying character '%0' with a universal character name "
|
||||
"is incompatible with C++98">, InGroup<CXX98Compat>, DefaultIgnore;
|
||||
|
|
|
|||
|
|
@ -36,6 +36,7 @@
|
|||
#include "llvm/Support/Compiler.h"
|
||||
#include "llvm/Support/ConvertUTF.h"
|
||||
#include "llvm/Support/MemoryBuffer.h"
|
||||
#include "UnicodeCharSets.h"
|
||||
#include <cstring>
|
||||
using namespace clang;
|
||||
|
||||
|
|
@ -1351,72 +1352,61 @@ void Lexer::SkipBytes(unsigned Bytes, bool StartOfLine) {
|
|||
IsAtStartOfLine = StartOfLine;
|
||||
}
|
||||
|
||||
namespace {
|
||||
struct UCNCharRange {
|
||||
uint32_t Lower;
|
||||
uint32_t Upper;
|
||||
};
|
||||
|
||||
// C11 D.1, C++11 [charname.allowed]
|
||||
// FIXME: C99 and C++03 each have a different set of allowed UCNs.
|
||||
const UCNCharRange UCNAllowedCharRanges[] = {
|
||||
// 1
|
||||
{ 0x00A8, 0x00A8 }, { 0x00AA, 0x00AA }, { 0x00AD, 0x00AD },
|
||||
{ 0x00AF, 0x00AF }, { 0x00B2, 0x00B5 }, { 0x00B7, 0x00BA },
|
||||
{ 0x00BC, 0x00BE }, { 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 },
|
||||
{ 0x00F8, 0x00FF },
|
||||
// 2
|
||||
{ 0x0100, 0x167F }, { 0x1681, 0x180D }, { 0x180F, 0x1FFF },
|
||||
// 3
|
||||
{ 0x200B, 0x200D }, { 0x202A, 0x202E }, { 0x203F, 0x2040 },
|
||||
{ 0x2054, 0x2054 }, { 0x2060, 0x206F },
|
||||
// 4
|
||||
{ 0x2070, 0x218F }, { 0x2460, 0x24FF }, { 0x2776, 0x2793 },
|
||||
{ 0x2C00, 0x2DFF }, { 0x2E80, 0x2FFF },
|
||||
// 5
|
||||
{ 0x3004, 0x3007 }, { 0x3021, 0x302F }, { 0x3031, 0x303F },
|
||||
// 6
|
||||
{ 0x3040, 0xD7FF },
|
||||
// 7
|
||||
{ 0xF900, 0xFD3D }, { 0xFD40, 0xFDCF }, { 0xFDF0, 0xFE44 },
|
||||
{ 0xFE47, 0xFFFD },
|
||||
// 8
|
||||
{ 0x10000, 0x1FFFD }, { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD },
|
||||
{ 0x40000, 0x4FFFD }, { 0x50000, 0x5FFFD }, { 0x60000, 0x6FFFD },
|
||||
{ 0x70000, 0x7FFFD }, { 0x80000, 0x8FFFD }, { 0x90000, 0x9FFFD },
|
||||
{ 0xA0000, 0xAFFFD }, { 0xB0000, 0xBFFFD }, { 0xC0000, 0xCFFFD },
|
||||
{ 0xD0000, 0xDFFFD }, { 0xE0000, 0xEFFFD }
|
||||
};
|
||||
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);
|
||||
}
|
||||
|
||||
static bool isAllowedIDChar(uint32_t c) {
|
||||
unsigned LowPoint = 0;
|
||||
unsigned HighPoint = llvm::array_lengthof(UCNAllowedCharRanges);
|
||||
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)
|
||||
return true;
|
||||
else
|
||||
return !isCharInSet(C, C99DisallowedInitialIDChars);
|
||||
}
|
||||
|
||||
// Binary search the UCNAllowedCharRanges set.
|
||||
while (HighPoint != LowPoint) {
|
||||
unsigned MidPoint = (HighPoint + LowPoint) / 2;
|
||||
if (c < UCNAllowedCharRanges[MidPoint].Lower)
|
||||
HighPoint = MidPoint;
|
||||
else if (c > UCNAllowedCharRanges[MidPoint].Upper)
|
||||
LowPoint = MidPoint + 1;
|
||||
else
|
||||
return true;
|
||||
static inline CharSourceRange makeCharRange(Lexer &L, const char *Begin,
|
||||
const char *End) {
|
||||
return CharSourceRange::getCharRange(L.getSourceLocation(Begin),
|
||||
L.getSourceLocation(End));
|
||||
}
|
||||
|
||||
static void maybeDiagnoseIDCharCompat(DiagnosticsEngine &Diags, uint32_t C,
|
||||
CharSourceRange Range, bool IsFirst) {
|
||||
// Check C99 compatibility.
|
||||
if (Diags.getDiagnosticLevel(diag::warn_c99_compat_unicode_id,
|
||||
Range.getBegin()) > DiagnosticsEngine::Ignored) {
|
||||
enum {
|
||||
CannotAppearInIdentifier = 0,
|
||||
CannotStartIdentifier
|
||||
};
|
||||
|
||||
if (!isCharInSet(C, C99AllowedIDChars)) {
|
||||
Diags.Report(Range.getBegin(), diag::warn_c99_compat_unicode_id)
|
||||
<< Range
|
||||
<< CannotAppearInIdentifier;
|
||||
} else if (IsFirst && isCharInSet(C, C99DisallowedInitialIDChars)) {
|
||||
Diags.Report(Range.getBegin(), diag::warn_c99_compat_unicode_id)
|
||||
<< Range
|
||||
<< CannotStartIdentifier;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
static bool isAllowedInitiallyIDChar(uint32_t c) {
|
||||
// C11 D.2, C++11 [charname.disallowed]
|
||||
// FIXME: C99 only forbids "digits", presumably as described in C99 Annex D.
|
||||
// FIXME: C++03 does not forbid any initial characters.
|
||||
return !(0x0300 <= c && c <= 0x036F) &&
|
||||
!(0x1DC0 <= c && c <= 0x1DFF) &&
|
||||
!(0x20D0 <= c && c <= 0x20FF) &&
|
||||
!(0xFE20 <= c && c <= 0xFE2F);
|
||||
}
|
||||
|
||||
// Check C++98 compatibility.
|
||||
if (Diags.getDiagnosticLevel(diag::warn_cxx98_compat_unicode_id,
|
||||
Range.getBegin()) > DiagnosticsEngine::Ignored) {
|
||||
if (!isCharInSet(C, CXX03AllowedIDChars)) {
|
||||
Diags.Report(Range.getBegin(), diag::warn_cxx98_compat_unicode_id)
|
||||
<< Range;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void Lexer::LexIdentifier(Token &Result, const char *CurPtr) {
|
||||
// Match [_A-Za-z0-9]*, we have already matched [_A-Za-z$]
|
||||
|
|
@ -1474,9 +1464,15 @@ FinishIdentifier:
|
|||
} else if (C == '\\') {
|
||||
const char *UCNPtr = CurPtr + Size;
|
||||
uint32_t CodePoint = tryReadUCN(UCNPtr, CurPtr, /*Token=*/0);
|
||||
if (CodePoint == 0 || !isAllowedIDChar(CodePoint))
|
||||
if (CodePoint == 0 || !isAllowedIDChar(CodePoint, LangOpts))
|
||||
goto FinishIdentifier;
|
||||
|
||||
if (!isLexingRawMode()) {
|
||||
maybeDiagnoseIDCharCompat(PP->getDiagnostics(), CodePoint,
|
||||
makeCharRange(*this, CurPtr, UCNPtr),
|
||||
/*IsFirst=*/false);
|
||||
}
|
||||
|
||||
Result.setFlag(Token::HasUCN);
|
||||
if ((UCNPtr - CurPtr == 6 && CurPtr[1] == 'u') ||
|
||||
(UCNPtr - CurPtr == 10 && CurPtr[1] == 'U'))
|
||||
|
|
@ -1496,9 +1492,15 @@ FinishIdentifier:
|
|||
&CodePoint,
|
||||
strictConversion);
|
||||
if (Result != conversionOK ||
|
||||
!isAllowedIDChar(static_cast<uint32_t>(CodePoint)))
|
||||
!isAllowedIDChar(static_cast<uint32_t>(CodePoint), LangOpts))
|
||||
goto FinishIdentifier;
|
||||
|
||||
if (!isLexingRawMode()) {
|
||||
maybeDiagnoseIDCharCompat(PP->getDiagnostics(), CodePoint,
|
||||
makeCharRange(*this, CurPtr, UnicodePtr),
|
||||
/*IsFirst=*/false);
|
||||
}
|
||||
|
||||
CurPtr = UnicodePtr;
|
||||
C = getCharAndSize(CurPtr, Size);
|
||||
continue;
|
||||
|
|
@ -2569,9 +2571,7 @@ uint32_t Lexer::tryReadUCN(const char *&StartPtr, const char *SlashLoc,
|
|||
|
||||
// If the user wrote \U1234, suggest a fixit to \u.
|
||||
if (i == 4 && NumHexDigits == 8) {
|
||||
CharSourceRange URange =
|
||||
CharSourceRange::getCharRange(getSourceLocation(KindLoc),
|
||||
getSourceLocation(KindLoc + 1));
|
||||
CharSourceRange URange = makeCharRange(*this, KindLoc, KindLoc + 1);
|
||||
Diag(KindLoc, diag::note_ucn_four_not_eight)
|
||||
<< FixItHint::CreateReplacement(URange, "u");
|
||||
}
|
||||
|
|
@ -2625,35 +2625,28 @@ uint32_t Lexer::tryReadUCN(const char *&StartPtr, const char *SlashLoc,
|
|||
}
|
||||
|
||||
return 0;
|
||||
|
||||
} else if ((!LangOpts.CPlusPlus || LangOpts.CPlusPlus11) &&
|
||||
(CodePoint >= 0xD800 && CodePoint <= 0xDFFF)) {
|
||||
|
||||
} else if (CodePoint >= 0xD800 && CodePoint <= 0xDFFF) {
|
||||
// C++03 allows UCNs representing surrogate characters. C99 and C++11 don't.
|
||||
// We don't use isLexingRawMode() here because we need to warn about bad
|
||||
// We don't use isLexingRawMode() here because we need to diagnose bad
|
||||
// UCNs even when skipping preprocessing tokens in a #if block.
|
||||
if (Result && PP)
|
||||
Diag(BufferPtr, diag::err_ucn_escape_invalid);
|
||||
if (Result && PP) {
|
||||
if (LangOpts.CPlusPlus && !LangOpts.CPlusPlus11)
|
||||
Diag(BufferPtr, diag::warn_ucn_escape_surrogate);
|
||||
else
|
||||
Diag(BufferPtr, diag::err_ucn_escape_invalid);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
return CodePoint;
|
||||
}
|
||||
|
||||
static bool isUnicodeWhitespace(uint32_t C) {
|
||||
return (C == 0x0085 || C == 0x00A0 || C == 0x1680 ||
|
||||
C == 0x180E || (C >= 0x2000 && C <= 0x200A) ||
|
||||
C == 0x2028 || C == 0x2029 || C == 0x202F ||
|
||||
C == 0x205F || C == 0x3000);
|
||||
}
|
||||
|
||||
void Lexer::LexUnicode(Token &Result, uint32_t C, const char *CurPtr) {
|
||||
if (!isLexingRawMode() && !PP->isPreprocessedOutput() &&
|
||||
isUnicodeWhitespace(C)) {
|
||||
CharSourceRange CharRange =
|
||||
CharSourceRange::getCharRange(getSourceLocation(),
|
||||
getSourceLocation(CurPtr));
|
||||
isCharInSet(C, UnicodeWhitespaceChars)) {
|
||||
Diag(BufferPtr, diag::ext_unicode_whitespace)
|
||||
<< CharRange;
|
||||
<< makeCharRange(*this, BufferPtr, CurPtr);
|
||||
|
||||
Result.setFlag(Token::LeadingSpace);
|
||||
if (SkipWhitespace(Result, CurPtr))
|
||||
|
|
@ -2662,14 +2655,21 @@ void Lexer::LexUnicode(Token &Result, uint32_t C, const char *CurPtr) {
|
|||
return LexTokenInternal(Result);
|
||||
}
|
||||
|
||||
if (isAllowedIDChar(C) && isAllowedInitiallyIDChar(C)) {
|
||||
if (isAllowedIDChar(C, LangOpts) && isAllowedInitiallyIDChar(C, LangOpts)) {
|
||||
if (!isLexingRawMode() && !ParsingPreprocessorDirective &&
|
||||
!PP->isPreprocessedOutput()) {
|
||||
maybeDiagnoseIDCharCompat(PP->getDiagnostics(), C,
|
||||
makeCharRange(*this, BufferPtr, CurPtr),
|
||||
/*IsFirst=*/true);
|
||||
}
|
||||
|
||||
MIOpt.ReadToken();
|
||||
return LexIdentifier(Result, CurPtr);
|
||||
}
|
||||
|
||||
if (!isLexingRawMode() && !ParsingPreprocessorDirective &&
|
||||
!PP->isPreprocessedOutput() &&
|
||||
!isASCII(*BufferPtr) && !isAllowedIDChar(C)) {
|
||||
!isASCII(*BufferPtr) && !isAllowedIDChar(C, LangOpts)) {
|
||||
// Non-ASCII characters tend to creep into source code unintentionally.
|
||||
// Instead of letting the parser complain about the unknown token,
|
||||
// just drop the character.
|
||||
|
|
@ -2679,11 +2679,8 @@ void Lexer::LexUnicode(Token &Result, uint32_t C, const char *CurPtr) {
|
|||
// loophole in the mapping of Unicode characters to basic character set
|
||||
// characters that allows us to map these particular characters to, say,
|
||||
// whitespace.
|
||||
CharSourceRange CharRange =
|
||||
CharSourceRange::getCharRange(getSourceLocation(),
|
||||
getSourceLocation(CurPtr));
|
||||
Diag(BufferPtr, diag::err_non_ascii)
|
||||
<< FixItHint::CreateRemoval(CharRange);
|
||||
<< FixItHint::CreateRemoval(makeCharRange(*this, BufferPtr, CurPtr));
|
||||
|
||||
BufferPtr = CurPtr;
|
||||
return LexTokenInternal(Result);
|
||||
|
|
|
|||
|
|
@ -0,0 +1,496 @@
|
|||
//===--- UnicodeCharSets.h - Contains important sets of characters --------===//
|
||||
//
|
||||
// The LLVM Compiler Infrastructure
|
||||
//
|
||||
// This file is distributed under the University of Illinois Open Source
|
||||
// License. See LICENSE.TXT for details.
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
#ifndef CLANG_LEX_UNICODECHARSETS_H
|
||||
#define CLANG_LEX_UNICODECHARSETS_H
|
||||
|
||||
#include "llvm/ADT/ArrayRef.h"
|
||||
#include "llvm/ADT/SmallPtrSet.h"
|
||||
#include "llvm/Support/Compiler.h"
|
||||
#include "llvm/Support/Debug.h"
|
||||
#include "llvm/Support/Mutex.h"
|
||||
#include "llvm/Support/MutexGuard.h"
|
||||
#include "llvm/Support/raw_ostream.h"
|
||||
|
||||
namespace {
|
||||
struct UnicodeCharRange {
|
||||
uint32_t Lower;
|
||||
uint32_t Upper;
|
||||
};
|
||||
typedef llvm::ArrayRef<UnicodeCharRange> UnicodeCharSet;
|
||||
|
||||
typedef llvm::SmallPtrSet<const UnicodeCharRange *, 16> ValidatedCharSetsTy;
|
||||
}
|
||||
|
||||
static inline ValidatedCharSetsTy &getValidatedCharSets() {
|
||||
static ValidatedCharSetsTy Validated;
|
||||
return Validated;
|
||||
}
|
||||
|
||||
/// Returns true if each of the ranges in \p CharSet is a proper closed range
|
||||
/// [min, max], and if the ranges themselves are ordered and non-overlapping.
|
||||
static inline bool isValidCharSet(UnicodeCharSet CharSet) {
|
||||
#ifndef NDEBUG
|
||||
static llvm::sys::Mutex ValidationMutex;
|
||||
|
||||
// Check the validation cache.
|
||||
{
|
||||
llvm::MutexGuard Guard(ValidationMutex);
|
||||
if (getValidatedCharSets().count(CharSet.data()))
|
||||
return true;
|
||||
}
|
||||
|
||||
// Walk through the ranges.
|
||||
uint32_t Prev = 0;
|
||||
for (UnicodeCharSet::iterator I = CharSet.begin(), E = CharSet.end();
|
||||
I != E; ++I) {
|
||||
if (Prev >= I->Lower) {
|
||||
DEBUG(llvm::dbgs() << "Upper bound 0x");
|
||||
DEBUG(llvm::dbgs().write_hex(Prev));
|
||||
DEBUG(llvm::dbgs() << " should be less than succeeding lower bound 0x");
|
||||
DEBUG(llvm::dbgs().write_hex(I->Lower) << "\n");
|
||||
return false;
|
||||
}
|
||||
if (I->Upper < I->Lower) {
|
||||
DEBUG(llvm::dbgs() << "Upper bound 0x");
|
||||
DEBUG(llvm::dbgs().write_hex(I->Lower));
|
||||
DEBUG(llvm::dbgs() << " should not be less than lower bound 0x");
|
||||
DEBUG(llvm::dbgs().write_hex(I->Upper) << "\n");
|
||||
return false;
|
||||
}
|
||||
Prev = I->Upper;
|
||||
}
|
||||
|
||||
// Update the validation cache.
|
||||
{
|
||||
llvm::MutexGuard Guard(ValidationMutex);
|
||||
getValidatedCharSets().insert(CharSet.data());
|
||||
}
|
||||
#endif
|
||||
return true;
|
||||
}
|
||||
|
||||
/// Returns true if the Unicode code point \p C is within the set of
|
||||
/// characters specified by \p CharSet.
|
||||
LLVM_READONLY static inline bool isCharInSet(uint32_t C,
|
||||
UnicodeCharSet CharSet) {
|
||||
assert(isValidCharSet(CharSet));
|
||||
|
||||
size_t LowPoint = 0;
|
||||
size_t HighPoint = CharSet.size();
|
||||
|
||||
// Binary search the set of char ranges.
|
||||
while (HighPoint != LowPoint) {
|
||||
size_t MidPoint = (HighPoint + LowPoint) / 2;
|
||||
if (C < CharSet[MidPoint].Lower)
|
||||
HighPoint = MidPoint;
|
||||
else if (C > CharSet[MidPoint].Upper)
|
||||
LowPoint = MidPoint + 1;
|
||||
else
|
||||
return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
// C11 D.1, C++11 [charname.allowed]
|
||||
static const UnicodeCharRange C11AllowedIDChars[] = {
|
||||
// 1
|
||||
{ 0x00A8, 0x00A8 }, { 0x00AA, 0x00AA }, { 0x00AD, 0x00AD },
|
||||
{ 0x00AF, 0x00AF }, { 0x00B2, 0x00B5 }, { 0x00B7, 0x00BA },
|
||||
{ 0x00BC, 0x00BE }, { 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 },
|
||||
{ 0x00F8, 0x00FF },
|
||||
// 2
|
||||
{ 0x0100, 0x167F }, { 0x1681, 0x180D }, { 0x180F, 0x1FFF },
|
||||
// 3
|
||||
{ 0x200B, 0x200D }, { 0x202A, 0x202E }, { 0x203F, 0x2040 },
|
||||
{ 0x2054, 0x2054 }, { 0x2060, 0x206F },
|
||||
// 4
|
||||
{ 0x2070, 0x218F }, { 0x2460, 0x24FF }, { 0x2776, 0x2793 },
|
||||
{ 0x2C00, 0x2DFF }, { 0x2E80, 0x2FFF },
|
||||
// 5
|
||||
{ 0x3004, 0x3007 }, { 0x3021, 0x302F }, { 0x3031, 0x303F },
|
||||
// 6
|
||||
{ 0x3040, 0xD7FF },
|
||||
// 7
|
||||
{ 0xF900, 0xFD3D }, { 0xFD40, 0xFDCF }, { 0xFDF0, 0xFE44 },
|
||||
{ 0xFE47, 0xFFFD },
|
||||
// 8
|
||||
{ 0x10000, 0x1FFFD }, { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD },
|
||||
{ 0x40000, 0x4FFFD }, { 0x50000, 0x5FFFD }, { 0x60000, 0x6FFFD },
|
||||
{ 0x70000, 0x7FFFD }, { 0x80000, 0x8FFFD }, { 0x90000, 0x9FFFD },
|
||||
{ 0xA0000, 0xAFFFD }, { 0xB0000, 0xBFFFD }, { 0xC0000, 0xCFFFD },
|
||||
{ 0xD0000, 0xDFFFD }, { 0xE0000, 0xEFFFD }
|
||||
};
|
||||
|
||||
// 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[] = {
|
||||
// Latin
|
||||
{ 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 }, { 0x00F8, 0x01F5 },
|
||||
{ 0x01FA, 0x0217 }, { 0x0250, 0x02A8 },
|
||||
|
||||
// Greek
|
||||
{ 0x0384, 0x0384 }, { 0x0388, 0x038A }, { 0x038C, 0x038C },
|
||||
{ 0x038E, 0x03A1 }, { 0x03A3, 0x03CE }, { 0x03D0, 0x03D6 },
|
||||
{ 0x03DA, 0x03DA }, { 0x03DC, 0x03DC }, { 0x03DE, 0x03DE },
|
||||
{ 0x03E0, 0x03E0 }, { 0x03E2, 0x03F3 },
|
||||
|
||||
// Cyrillic
|
||||
{ 0x0401, 0x040D }, { 0x040F, 0x044F }, { 0x0451, 0x045C },
|
||||
{ 0x045E, 0x0481 }, { 0x0490, 0x04C4 }, { 0x04C7, 0x04C8 },
|
||||
{ 0x04CB, 0x04CC }, { 0x04D0, 0x04EB }, { 0x04EE, 0x04F5 },
|
||||
{ 0x04F8, 0x04F9 },
|
||||
|
||||
// Armenian
|
||||
{ 0x0531, 0x0556 }, { 0x0561, 0x0587 },
|
||||
|
||||
// Hebrew
|
||||
{ 0x05D0, 0x05EA }, { 0x05F0, 0x05F4 },
|
||||
|
||||
// Arabic
|
||||
{ 0x0621, 0x063A }, { 0x0640, 0x0652 }, { 0x0670, 0x06B7 },
|
||||
{ 0x06BA, 0x06BE }, { 0x06C0, 0x06CE }, { 0x06E5, 0x06E7 },
|
||||
|
||||
// Devanagari
|
||||
{ 0x0905, 0x0939 }, { 0x0958, 0x0962 },
|
||||
|
||||
// Bengali
|
||||
{ 0x0985, 0x098C }, { 0x098F, 0x0990 }, { 0x0993, 0x09A8 },
|
||||
{ 0x09AA, 0x09B0 }, { 0x09B2, 0x09B2 }, { 0x09B6, 0x09B9 },
|
||||
{ 0x09DC, 0x09DD }, { 0x09DF, 0x09E1 }, { 0x09F0, 0x09F1 },
|
||||
|
||||
// Gurmukhi
|
||||
{ 0x0A05, 0x0A0A }, { 0x0A0F, 0x0A10 }, { 0x0A13, 0x0A28 },
|
||||
{ 0x0A2A, 0x0A30 }, { 0x0A32, 0x0A33 }, { 0x0A35, 0x0A36 },
|
||||
{ 0x0A38, 0x0A39 }, { 0x0A59, 0x0A5C }, { 0x0A5E, 0x0A5E },
|
||||
|
||||
// Gujarti
|
||||
{ 0x0A85, 0x0A8B }, { 0x0A8D, 0x0A8D }, { 0x0A8F, 0x0A91 },
|
||||
{ 0x0A93, 0x0AA8 }, { 0x0AAA, 0x0AB0 }, { 0x0AB2, 0x0AB3 },
|
||||
{ 0x0AB5, 0x0AB9 }, { 0x0AE0, 0x0AE0 },
|
||||
|
||||
// Oriya
|
||||
{ 0x0B05, 0x0B0C }, { 0x0B0F, 0x0B10 }, { 0x0B13, 0x0B28 },
|
||||
{ 0x0B2A, 0x0B30 }, { 0x0B32, 0x0B33 }, { 0x0B36, 0x0B39 },
|
||||
{ 0x0B5C, 0x0B5D }, { 0x0B5F, 0x0B61 },
|
||||
|
||||
// Tamil
|
||||
{ 0x0B85, 0x0B8A }, { 0x0B8E, 0x0B90 }, { 0x0B92, 0x0B95 },
|
||||
{ 0x0B99, 0x0B9A }, { 0x0B9C, 0x0B9C }, { 0x0B9E, 0x0B9F },
|
||||
{ 0x0BA3, 0x0BA4 }, { 0x0BA8, 0x0BAA }, { 0x0BAE, 0x0BB5 },
|
||||
{ 0x0BB7, 0x0BB9 },
|
||||
|
||||
// Telugu
|
||||
{ 0x0C05, 0x0C0C }, { 0x0C0E, 0x0C10 }, { 0x0C12, 0x0C28 },
|
||||
{ 0x0C2A, 0x0C33 }, { 0x0C35, 0x0C39 }, { 0x0C60, 0x0C61 },
|
||||
|
||||
// Kannada
|
||||
{ 0x0C85, 0x0C8C }, { 0x0C8E, 0x0C90 }, { 0x0C92, 0x0CA8 },
|
||||
{ 0x0CAA, 0x0CB3 }, { 0x0CB5, 0x0CB9 }, { 0x0CE0, 0x0CE1 },
|
||||
|
||||
// Malayam
|
||||
{ 0x0D05, 0x0D0C }, { 0x0D0E, 0x0D10 }, { 0x0D12, 0x0D28 },
|
||||
{ 0x0D2A, 0x0D39 }, { 0x0D60, 0x0D61 },
|
||||
|
||||
// Thai
|
||||
{ 0x0E01, 0x0E30 }, { 0x0E32, 0x0E33 }, { 0x0E40, 0x0E46 },
|
||||
{ 0x0E4F, 0x0E5B },
|
||||
|
||||
// Lao
|
||||
{ 0x0E81, 0x0E82 }, { 0x0E84, 0x0E84 }, { 0x0E87, 0x0E87 },
|
||||
{ 0x0E88, 0x0E88 }, { 0x0E8A, 0x0E8A }, { 0x0E8D, 0x0E8D },
|
||||
{ 0x0E94, 0x0E97 }, { 0x0E99, 0x0E9F }, { 0x0EA1, 0x0EA3 },
|
||||
{ 0x0EA5, 0x0EA5 }, { 0x0EA7, 0x0EA7 }, { 0x0EAA, 0x0EAA },
|
||||
{ 0x0EAB, 0x0EAB }, { 0x0EAD, 0x0EB0 }, { 0x0EB2, 0x0EB2 },
|
||||
{ 0x0EB3, 0x0EB3 }, { 0x0EBD, 0x0EBD }, { 0x0EC0, 0x0EC4 },
|
||||
{ 0x0EC6, 0x0EC6 },
|
||||
|
||||
// Georgian
|
||||
{ 0x10A0, 0x10C5 }, { 0x10D0, 0x10F6 },
|
||||
|
||||
// Hangul
|
||||
{ 0x1100, 0x1159 }, { 0x1161, 0x11A2 }, { 0x11A8, 0x11F9 },
|
||||
|
||||
// Latin (2)
|
||||
{ 0x1E00, 0x1E9A }, { 0x1EA0, 0x1EF9 },
|
||||
|
||||
// Greek (2)
|
||||
{ 0x1F00, 0x1F15 }, { 0x1F18, 0x1F1D }, { 0x1F20, 0x1F45 },
|
||||
{ 0x1F48, 0x1F4D }, { 0x1F50, 0x1F57 }, { 0x1F59, 0x1F59 },
|
||||
{ 0x1F5B, 0x1F5B }, { 0x1F5D, 0x1F5D }, { 0x1F5F, 0x1F7D },
|
||||
{ 0x1F80, 0x1FB4 }, { 0x1FB6, 0x1FBC }, { 0x1FC2, 0x1FC4 },
|
||||
{ 0x1FC6, 0x1FCC }, { 0x1FD0, 0x1FD3 }, { 0x1FD6, 0x1FDB },
|
||||
{ 0x1FE0, 0x1FEC }, { 0x1FF2, 0x1FF4 }, { 0x1FF6, 0x1FFC },
|
||||
|
||||
// Hiragana
|
||||
{ 0x3041, 0x3094 }, { 0x309B, 0x309E },
|
||||
|
||||
// Katakana
|
||||
{ 0x30A1, 0x30FE },
|
||||
|
||||
// Bopmofo [sic]
|
||||
{ 0x3105, 0x312C },
|
||||
|
||||
// CJK Unified Ideographs
|
||||
{ 0x4E00, 0x9FA5 }, { 0xF900, 0xFA2D }, { 0xFB1F, 0xFB36 },
|
||||
{ 0xFB38, 0xFB3C }, { 0xFB3E, 0xFB3E }, { 0xFB40, 0xFB41 },
|
||||
{ 0xFB42, 0xFB44 }, { 0xFB46, 0xFBB1 }, { 0xFBD3, 0xFD3F },
|
||||
{ 0xFD50, 0xFD8F }, { 0xFD92, 0xFDC7 }, { 0xFDF0, 0xFDFB },
|
||||
{ 0xFE70, 0xFE72 }, { 0xFE74, 0xFE74 }, { 0xFE76, 0xFEFC },
|
||||
{ 0xFF21, 0xFF3A }, { 0xFF41, 0xFF5A }, { 0xFF66, 0xFFBE },
|
||||
{ 0xFFC2, 0xFFC7 }, { 0xFFCA, 0xFFCF }, { 0xFFD2, 0xFFD7 },
|
||||
{ 0xFFDA, 0xFFDC }
|
||||
};
|
||||
|
||||
// C99 Annex D
|
||||
static const UnicodeCharRange C99AllowedIDChars[] = {
|
||||
// Latin (1)
|
||||
{ 0x00AA, 0x00AA },
|
||||
|
||||
// Special characters (1)
|
||||
{ 0x00B5, 0x00B5 }, { 0x00B7, 0x00B7 },
|
||||
|
||||
// Latin (2)
|
||||
{ 0x00BA, 0x00BA }, { 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 },
|
||||
{ 0x00F8, 0x01F5 }, { 0x01FA, 0x0217 }, { 0x0250, 0x02A8 },
|
||||
|
||||
// Special characters (2)
|
||||
{ 0x02B0, 0x02B8 }, { 0x02BB, 0x02BB }, { 0x02BD, 0x02C1 },
|
||||
{ 0x02D0, 0x02D1 }, { 0x02E0, 0x02E4 }, { 0x037A, 0x037A },
|
||||
|
||||
// Greek (1)
|
||||
{ 0x0386, 0x0386 }, { 0x0388, 0x038A }, { 0x038C, 0x038C },
|
||||
{ 0x038E, 0x03A1 }, { 0x03A3, 0x03CE }, { 0x03D0, 0x03D6 },
|
||||
{ 0x03DA, 0x03DA }, { 0x03DC, 0x03DC }, { 0x03DE, 0x03DE },
|
||||
{ 0x03E0, 0x03E0 }, { 0x03E2, 0x03F3 },
|
||||
|
||||
// Cyrillic
|
||||
{ 0x0401, 0x040C }, { 0x040E, 0x044F }, { 0x0451, 0x045C },
|
||||
{ 0x045E, 0x0481 }, { 0x0490, 0x04C4 }, { 0x04C7, 0x04C8 },
|
||||
{ 0x04CB, 0x04CC }, { 0x04D0, 0x04EB }, { 0x04EE, 0x04F5 },
|
||||
{ 0x04F8, 0x04F9 },
|
||||
|
||||
// Armenian (1)
|
||||
{ 0x0531, 0x0556 },
|
||||
|
||||
// Special characters (3)
|
||||
{ 0x0559, 0x0559 },
|
||||
|
||||
// Armenian (2)
|
||||
{ 0x0561, 0x0587 },
|
||||
|
||||
// Hebrew
|
||||
{ 0x05B0, 0x05B9 }, { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF },
|
||||
{ 0x05C1, 0x05C2 }, { 0x05D0, 0x05EA }, { 0x05F0, 0x05F2 },
|
||||
|
||||
// Arabic (1)
|
||||
{ 0x0621, 0x063A }, { 0x0640, 0x0652 },
|
||||
|
||||
// Digits (1)
|
||||
{ 0x0660, 0x0669 },
|
||||
|
||||
// Arabic (2)
|
||||
{ 0x0670, 0x06B7 }, { 0x06BA, 0x06BE }, { 0x06C0, 0x06CE },
|
||||
{ 0x06D0, 0x06DC }, { 0x06E5, 0x06E8 }, { 0x06EA, 0x06ED },
|
||||
|
||||
// Digits (2)
|
||||
{ 0x06F0, 0x06F9 },
|
||||
|
||||
// Devanagari and Special characeter 0x093D.
|
||||
{ 0x0901, 0x0903 }, { 0x0905, 0x0939 }, { 0x093D, 0x094D },
|
||||
{ 0x0950, 0x0952 }, { 0x0958, 0x0963 },
|
||||
|
||||
// Digits (3)
|
||||
{ 0x0966, 0x096F },
|
||||
|
||||
// Bengali (1)
|
||||
{ 0x0981, 0x0983 }, { 0x0985, 0x098C }, { 0x098F, 0x0990 },
|
||||
{ 0x0993, 0x09A8 }, { 0x09AA, 0x09B0 }, { 0x09B2, 0x09B2 },
|
||||
{ 0x09B6, 0x09B9 }, { 0x09BE, 0x09C4 }, { 0x09C7, 0x09C8 },
|
||||
{ 0x09CB, 0x09CD }, { 0x09DC, 0x09DD }, { 0x09DF, 0x09E3 },
|
||||
|
||||
// Digits (4)
|
||||
{ 0x09E6, 0x09EF },
|
||||
|
||||
// Bengali (2)
|
||||
{ 0x09F0, 0x09F1 },
|
||||
|
||||
// Gurmukhi (1)
|
||||
{ 0x0A02, 0x0A02 }, { 0x0A05, 0x0A0A }, { 0x0A0F, 0x0A10 },
|
||||
{ 0x0A13, 0x0A28 }, { 0x0A2A, 0x0A30 }, { 0x0A32, 0x0A33 },
|
||||
{ 0x0A35, 0x0A36 }, { 0x0A38, 0x0A39 }, { 0x0A3E, 0x0A42 },
|
||||
{ 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A59, 0x0A5C },
|
||||
{ 0x0A5E, 0x0A5E },
|
||||
|
||||
// Digits (5)
|
||||
{ 0x0A66, 0x0A6F },
|
||||
|
||||
// Gurmukhi (2)
|
||||
{ 0x0A74, 0x0A74 },
|
||||
|
||||
// Gujarti
|
||||
{ 0x0A81, 0x0A83 }, { 0x0A85, 0x0A8B }, { 0x0A8D, 0x0A8D },
|
||||
{ 0x0A8F, 0x0A91 }, { 0x0A93, 0x0AA8 }, { 0x0AAA, 0x0AB0 },
|
||||
{ 0x0AB2, 0x0AB3 }, { 0x0AB5, 0x0AB9 }, { 0x0ABD, 0x0AC5 },
|
||||
{ 0x0AC7, 0x0AC9 }, { 0x0ACB, 0x0ACD }, { 0x0AD0, 0x0AD0 },
|
||||
{ 0x0AE0, 0x0AE0 },
|
||||
|
||||
// Digits (6)
|
||||
{ 0x0AE6, 0x0AEF },
|
||||
|
||||
// Oriya and Special character 0x0B3D
|
||||
{ 0x0B01, 0x0B03 }, { 0x0B05, 0x0B0C }, { 0x0B0F, 0x0B10 },
|
||||
{ 0x0B13, 0x0B28 }, { 0x0B2A, 0x0B30 }, { 0x0B32, 0x0B33 },
|
||||
{ 0x0B36, 0x0B39 }, { 0x0B3D, 0x0B43 }, { 0x0B47, 0x0B48 },
|
||||
{ 0x0B4B, 0x0B4D }, { 0x0B5C, 0x0B5D }, { 0x0B5F, 0x0B61 },
|
||||
|
||||
// Digits (7)
|
||||
{ 0x0B66, 0x0B6F },
|
||||
|
||||
// Tamil
|
||||
{ 0x0B82, 0x0B83 }, { 0x0B85, 0x0B8A }, { 0x0B8E, 0x0B90 },
|
||||
{ 0x0B92, 0x0B95 }, { 0x0B99, 0x0B9A }, { 0x0B9C, 0x0B9C },
|
||||
{ 0x0B9E, 0x0B9F }, { 0x0BA3, 0x0BA4 }, { 0x0BA8, 0x0BAA },
|
||||
{ 0x0BAE, 0x0BB5 }, { 0x0BB7, 0x0BB9 }, { 0x0BBE, 0x0BC2 },
|
||||
{ 0x0BC6, 0x0BC8 }, { 0x0BCA, 0x0BCD },
|
||||
|
||||
// Digits (8)
|
||||
{ 0x0BE7, 0x0BEF },
|
||||
|
||||
// Telugu
|
||||
{ 0x0C01, 0x0C03 }, { 0x0C05, 0x0C0C }, { 0x0C0E, 0x0C10 },
|
||||
{ 0x0C12, 0x0C28 }, { 0x0C2A, 0x0C33 }, { 0x0C35, 0x0C39 },
|
||||
{ 0x0C3E, 0x0C44 }, { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D },
|
||||
{ 0x0C60, 0x0C61 },
|
||||
|
||||
// Digits (9)
|
||||
{ 0x0C66, 0x0C6F },
|
||||
|
||||
// Kannada
|
||||
{ 0x0C82, 0x0C83 }, { 0x0C85, 0x0C8C }, { 0x0C8E, 0x0C90 },
|
||||
{ 0x0C92, 0x0CA8 }, { 0x0CAA, 0x0CB3 }, { 0x0CB5, 0x0CB9 },
|
||||
{ 0x0CBE, 0x0CC4 }, { 0x0CC6, 0x0CC8 }, { 0x0CCA, 0x0CCD },
|
||||
{ 0x0CDE, 0x0CDE }, { 0x0CE0, 0x0CE1 },
|
||||
|
||||
// Digits (10)
|
||||
{ 0x0CE6, 0x0CEF },
|
||||
|
||||
// Malayam
|
||||
{ 0x0D02, 0x0D03 }, { 0x0D05, 0x0D0C }, { 0x0D0E, 0x0D10 },
|
||||
{ 0x0D12, 0x0D28 }, { 0x0D2A, 0x0D39 }, { 0x0D3E, 0x0D43 },
|
||||
{ 0x0D46, 0x0D48 }, { 0x0D4A, 0x0D4D }, { 0x0D60, 0x0D60 },
|
||||
|
||||
// Digits (11)
|
||||
{ 0x0D66, 0x0D6F },
|
||||
|
||||
// Thai...including Digits { 0x0E50, 0x0E59 }
|
||||
{ 0x0E01, 0x0E3A }, { 0x0E40, 0x0E5B },
|
||||
|
||||
// Lao (1)
|
||||
{ 0x0E81, 0x0E82 }, { 0x0E84, 0x0E84 }, { 0x0E87, 0x0E88 },
|
||||
{ 0x0E8A, 0x0E8A }, { 0x0E8D, 0x0E8D }, { 0x0E94, 0x0E97 },
|
||||
{ 0x0E99, 0x0E9F }, { 0x0EA1, 0x0EA3 }, { 0x0EA5, 0x0EA5 },
|
||||
{ 0x0EA7, 0x0EA7 }, { 0x0EAA, 0x0EAB }, { 0x0EAD, 0x0EAE },
|
||||
{ 0x0EB0, 0x0EB9 }, { 0x0EBB, 0x0EBD }, { 0x0EC0, 0x0EC4 },
|
||||
{ 0x0EC6, 0x0EC6 }, { 0x0EC8, 0x0ECD },
|
||||
|
||||
// Digits (12)
|
||||
{ 0x0ED0, 0x0ED9 },
|
||||
|
||||
// Lao (2)
|
||||
{ 0x0EDC, 0x0EDD },
|
||||
|
||||
// Tibetan (1)
|
||||
{ 0x0F00, 0x0F00 }, { 0x0F18, 0x0F19 },
|
||||
|
||||
// Digits (13)
|
||||
{ 0x0F20, 0x0F33 },
|
||||
|
||||
// Tibetan (2)
|
||||
{ 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 },
|
||||
{ 0x0F3E, 0x0F47 }, { 0x0F49, 0x0F69 }, { 0x0F71, 0x0F84 },
|
||||
{ 0x0F86, 0x0F8B }, { 0x0F90, 0x0F95 }, { 0x0F97, 0x0F97 },
|
||||
{ 0x0F99, 0x0FAD }, { 0x0FB1, 0x0FB7 }, { 0x0FB9, 0x0FB9 },
|
||||
|
||||
// Georgian
|
||||
{ 0x10A0, 0x10C5 }, { 0x10D0, 0x10F6 },
|
||||
|
||||
// Latin (3)
|
||||
{ 0x1E00, 0x1E9B }, { 0x1EA0, 0x1EF9 },
|
||||
|
||||
// Greek (2)
|
||||
{ 0x1F00, 0x1F15 }, { 0x1F18, 0x1F1D }, { 0x1F20, 0x1F45 },
|
||||
{ 0x1F48, 0x1F4D }, { 0x1F50, 0x1F57 }, { 0x1F59, 0x1F59 },
|
||||
{ 0x1F5B, 0x1F5B }, { 0x1F5D, 0x1F5D }, { 0x1F5F, 0x1F7D },
|
||||
{ 0x1F80, 0x1FB4 }, { 0x1FB6, 0x1FBC },
|
||||
|
||||
// Special characters (4)
|
||||
{ 0x1FBE, 0x1FBE },
|
||||
|
||||
// Greek (3)
|
||||
{ 0x1FC2, 0x1FC4 }, { 0x1FC6, 0x1FCC }, { 0x1FD0, 0x1FD3 },
|
||||
{ 0x1FD6, 0x1FDB }, { 0x1FE0, 0x1FEC }, { 0x1FF2, 0x1FF4 },
|
||||
{ 0x1FF6, 0x1FFC },
|
||||
|
||||
// Special characters (5)
|
||||
{ 0x203F, 0x2040 },
|
||||
|
||||
// Latin (4)
|
||||
{ 0x207F, 0x207F },
|
||||
|
||||
// Special characters (6)
|
||||
{ 0x2102, 0x2102 }, { 0x2107, 0x2107 }, { 0x210A, 0x2113 },
|
||||
{ 0x2115, 0x2115 }, { 0x2118, 0x211D }, { 0x2124, 0x2124 },
|
||||
{ 0x2126, 0x2126 }, { 0x2128, 0x2128 }, { 0x212A, 0x2131 },
|
||||
{ 0x2133, 0x2138 }, { 0x2160, 0x2182 }, { 0x3005, 0x3007 },
|
||||
{ 0x3021, 0x3029 },
|
||||
|
||||
// Hiragana
|
||||
{ 0x3041, 0x3093 }, { 0x309B, 0x309C },
|
||||
|
||||
// Katakana
|
||||
{ 0x30A1, 0x30F6 }, { 0x30FB, 0x30FC },
|
||||
|
||||
// Bopmofo [sic]
|
||||
{ 0x3105, 0x312C },
|
||||
|
||||
// CJK Unified Ideographs
|
||||
{ 0x4E00, 0x9FA5 },
|
||||
|
||||
// Hangul,
|
||||
{ 0xAC00, 0xD7A3 }
|
||||
};
|
||||
|
||||
// C11 D.2, C++11 [charname.disallowed]
|
||||
static const UnicodeCharRange C11DisallowedInitialIDChars[] = {
|
||||
{ 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[] = {
|
||||
{ 0x0660, 0x0669 }, { 0x06F0, 0x06F9 }, { 0x0966, 0x096F },
|
||||
{ 0x09E6, 0x09EF }, { 0x0A66, 0x0A6F }, { 0x0AE6, 0x0AEF },
|
||||
{ 0x0B66, 0x0B6F }, { 0x0BE7, 0x0BEF }, { 0x0C66, 0x0C6F },
|
||||
{ 0x0CE6, 0x0CEF }, { 0x0D66, 0x0D6F }, { 0x0E50, 0x0E59 },
|
||||
{ 0x0ED0, 0x0ED9 }, { 0x0F20, 0x0F33 }
|
||||
};
|
||||
|
||||
// Unicode v6.2, chapter 6.2, table 6-2.
|
||||
static const UnicodeCharRange UnicodeWhitespaceChars[] = {
|
||||
{ 0x0085, 0x0085 }, { 0x00A0, 0x00A0 }, { 0x1680, 0x1680 },
|
||||
{ 0x180E, 0x180E }, { 0x2000, 0x200A }, { 0x2028, 0x2029 },
|
||||
{ 0x202F, 0x202F }, { 0x205F, 0x205F }, { 0x3000, 0x3000 }
|
||||
};
|
||||
|
||||
#endif
|
||||
|
|
@ -0,0 +1,78 @@
|
|||
// RUN: %clang_cc1 %s -fsyntax-only -std=c99 -verify
|
||||
// RUN: %clang_cc1 %s -fsyntax-only -std=c11 -Wc99-compat -verify
|
||||
// RUN: %clang_cc1 %s -fsyntax-only -x c++ -std=c++03 -Wc++11-compat -verify
|
||||
// RUN: %clang_cc1 %s -fsyntax-only -x c++ -std=c++11 -Wc++98-compat -verify
|
||||
|
||||
// Identifier characters
|
||||
extern char a\u01F6; // C11, C++11
|
||||
extern char a\u00AA; // C99, C11, C++11
|
||||
extern char a\u0384; // C++03, C11, C++11
|
||||
extern char a\u0E50; // C99, C++03, C11, C++11
|
||||
extern char a\uFFFF; // none
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
// Identifier initial characters
|
||||
extern char \u0E50; // C++03, C11, C++11
|
||||
extern char \u0300; // disallowed initially in C11/C++11, always in C99/C++03
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
// Disallowed everywhere
|
||||
#define A \u0000 // expected-error{{control character}}
|
||||
#define B \u001F // expected-error{{control character}}
|
||||
#define C \u007F // expected-error{{control character}}
|
||||
#define D \u009F // expected-error{{control character}}
|
||||
#define E \uD800 // C++03 allows UCNs representing surrogate characters!
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#if __cplusplus
|
||||
# if __cplusplus >= 201103L
|
||||
// C++11
|
||||
// expected-warning@7 {{using this character in an identifier is incompatible with C++98}}
|
||||
// expected-warning@8 {{using this character in an identifier is incompatible with C++98}}
|
||||
// expected-error@11 {{expected ';'}}
|
||||
// expected-error@19 {{expected unqualified-id}}
|
||||
// expected-error@33 {{invalid universal character}}
|
||||
|
||||
# else
|
||||
// C++03
|
||||
// expected-error@7 {{expected ';'}}
|
||||
// expected-error@8 {{expected ';'}}
|
||||
// expected-error@11 {{expected ';'}}
|
||||
// expected-error@19 {{expected unqualified-id}}
|
||||
// expected-warning@33 {{universal character name refers to a surrogate character}}
|
||||
|
||||
# endif
|
||||
#else
|
||||
# if __STDC_VERSION__ >= 201112L
|
||||
// C11
|
||||
// expected-warning@7 {{using this character in an identifier is incompatible with C99}}
|
||||
// expected-warning@9 {{using this character in an identifier is incompatible with C99}}
|
||||
// expected-error@11 {{expected ';'}}
|
||||
// expected-warning@18 {{starting an identifier with this character is incompatible with C99}}
|
||||
// expected-error@19 {{expected identifier}}
|
||||
// expected-error@33 {{invalid universal character}}
|
||||
|
||||
# else
|
||||
// C99
|
||||
// expected-error@7 {{expected ';'}}
|
||||
// expected-error@9 {{expected ';'}}
|
||||
// expected-error@11 {{expected ';'}}
|
||||
// expected-error@18 {{expected identifier}}
|
||||
// expected-error@19 {{expected identifier}}
|
||||
// expected-error@33 {{invalid universal character}}
|
||||
|
||||
# endif
|
||||
#endif
|
||||
|
|
@ -0,0 +1,68 @@
|
|||
// RUN: %clang_cc1 %s -fsyntax-only -std=c99 -verify
|
||||
// RUN: %clang_cc1 %s -fsyntax-only -std=c11 -Wc99-compat -verify
|
||||
// RUN: %clang_cc1 %s -fsyntax-only -x c++ -std=c++03 -Wc++11-compat -verify
|
||||
// RUN: %clang_cc1 %s -fsyntax-only -x c++ -std=c++11 -Wc++98-compat -verify
|
||||
|
||||
// Note: This file contains Unicode characters; please do not remove them!
|
||||
|
||||
// Identifier characters
|
||||
extern char aǶ; // C11, C++11
|
||||
extern char aª; // C99, C11, C++11
|
||||
extern char a΄; // C++03, C11, C++11
|
||||
extern char a๐; // C99, C++03, C11, C++11
|
||||
extern char a﹅; // none
|
||||
extern char x̀; // C11, C++11. Note that this does not have a composed form.
|
||||
|
||||
|
||||
|
||||
|
||||
// Identifier initial characters
|
||||
extern char ๐; // C++03, C11, C++11
|
||||
extern char ̀; // disallowed initially in C11/C++11, always in C99/C++03
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#if __cplusplus
|
||||
# if __cplusplus >= 201103L
|
||||
// C++11
|
||||
// expected-warning@9 {{using this character in an identifier is incompatible with C++98}}
|
||||
// expected-warning@10 {{using this character in an identifier is incompatible with C++98}}
|
||||
// expected-error@13 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-warning@14 {{using this character in an identifier is incompatible with C++98}}
|
||||
// expected-error@21 {{expected unqualified-id}}
|
||||
|
||||
# else
|
||||
// C++03
|
||||
// expected-error@9 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@10 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@13 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@14 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@21 {{non-ASCII characters are not allowed outside of literals and identifiers}} expected-warning@21 {{declaration does not declare anything}}
|
||||
|
||||
# endif
|
||||
#else
|
||||
# if __STDC_VERSION__ >= 201112L
|
||||
// C11
|
||||
// expected-warning@9 {{using this character in an identifier is incompatible with C99}}
|
||||
// expected-warning@11 {{using this character in an identifier is incompatible with C99}}
|
||||
// expected-error@13 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-warning@14 {{using this character in an identifier is incompatible with C99}}
|
||||
// expected-warning@20 {{starting an identifier with this character is incompatible with C99}}
|
||||
// expected-error@21 {{expected identifier}}
|
||||
|
||||
# else
|
||||
// C99
|
||||
// expected-error@9 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@11 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@13 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@14 {{non-ASCII characters are not allowed outside of literals and identifiers}}
|
||||
// expected-error@20 {{expected identifier}}
|
||||
// expected-error@21 {{non-ASCII characters are not allowed outside of literals and identifiers}} expected-warning@21 {{declaration does not declare anything}}
|
||||
|
||||
# endif
|
||||
#endif
|
||||
Загрузка…
Ссылка в новой задаче