diff options
Diffstat (limited to 'lib/Lex/LiteralSupport.cpp')
| -rw-r--r-- | lib/Lex/LiteralSupport.cpp | 52 |
1 files changed, 36 insertions, 16 deletions
diff --git a/lib/Lex/LiteralSupport.cpp b/lib/Lex/LiteralSupport.cpp index e68b82fb499a..fbfd3fe5cce0 100644 --- a/lib/Lex/LiteralSupport.cpp +++ b/lib/Lex/LiteralSupport.cpp @@ -14,12 +14,25 @@ #include "clang/Lex/LiteralSupport.h" #include "clang/Basic/CharInfo.h" +#include "clang/Basic/LangOptions.h" +#include "clang/Basic/SourceLocation.h" #include "clang/Basic/TargetInfo.h" #include "clang/Lex/LexDiagnostic.h" +#include "clang/Lex/Lexer.h" #include "clang/Lex/Preprocessor.h" +#include "clang/Lex/Token.h" +#include "llvm/ADT/APInt.h" +#include "llvm/ADT/SmallVector.h" #include "llvm/ADT/StringExtras.h" +#include "llvm/ADT/StringSwitch.h" #include "llvm/Support/ConvertUTF.h" #include "llvm/Support/ErrorHandling.h" +#include <algorithm> +#include <cassert> +#include <cstddef> +#include <cstdint> +#include <cstring> +#include <string> using namespace clang; @@ -134,7 +147,7 @@ static unsigned ProcessCharEscape(const char *ThisTokBegin, if (Diags) Diag(Diags, Features, Loc, ThisTokBegin, EscapeBegin, ThisTokBuf, diag::err_hex_escape_no_digits) << "x"; - HadError = 1; + HadError = true; break; } @@ -389,7 +402,7 @@ static void EncodeUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf, if (CharByteWidth == 4) { // FIXME: Make the type of the result buffer correct instead of // using reinterpret_cast. - UTF32 *ResultPtr = reinterpret_cast<UTF32*>(ResultBuf); + llvm::UTF32 *ResultPtr = reinterpret_cast<llvm::UTF32*>(ResultBuf); *ResultPtr = UcnVal; ResultBuf += 4; return; @@ -398,7 +411,7 @@ static void EncodeUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf, if (CharByteWidth == 2) { // FIXME: Make the type of the result buffer correct instead of // using reinterpret_cast. - UTF16 *ResultPtr = reinterpret_cast<UTF16*>(ResultBuf); + llvm::UTF16 *ResultPtr = reinterpret_cast<llvm::UTF16*>(ResultBuf); if (UcnVal <= (UTF32)0xFFFF) { *ResultPtr = UcnVal; @@ -452,7 +465,6 @@ static void EncodeUCNEscape(const char *ThisTokBegin, const char *&ThisTokBuf, ResultBuf += bytesToWrite; } - /// integer-constant: [C99 6.4.4.1] /// decimal-constant integer-suffix /// octal-constant integer-suffix @@ -985,7 +997,6 @@ NumericLiteralParser::GetFloatValue(llvm::APFloat &Result) { return Result.convertFromString(Str, APFloat::rmNearestTiesToEven); } - /// \verbatim /// user-defined-character-literal: [C++11 lex.ext] /// character-literal ud-suffix @@ -1103,11 +1114,11 @@ CharLiteralParser::CharLiteralParser(const char *begin, const char *end, char const *tmp_in_start = start; uint32_t *tmp_out_start = buffer_begin; - ConversionResult res = - ConvertUTF8toUTF32(reinterpret_cast<UTF8 const **>(&start), - reinterpret_cast<UTF8 const *>(begin), - &buffer_begin, buffer_end, strictConversion); - if (res != conversionOK) { + llvm::ConversionResult res = + llvm::ConvertUTF8toUTF32(reinterpret_cast<llvm::UTF8 const **>(&start), + reinterpret_cast<llvm::UTF8 const *>(begin), + &buffer_begin, buffer_end, llvm::strictConversion); + if (res != llvm::conversionOK) { // If we see bad encoding for unprefixed character literals, warn and // simply copy the byte values, for compatibility with gcc and // older versions of clang. @@ -1499,13 +1510,13 @@ void StringLiteralParser::init(ArrayRef<Token> StringToks){ if (CharByteWidth == 4) { // FIXME: Make the type of the result buffer correct instead of // using reinterpret_cast. - UTF32 *ResultWidePtr = reinterpret_cast<UTF32*>(ResultPtr); + llvm::UTF32 *ResultWidePtr = reinterpret_cast<llvm::UTF32*>(ResultPtr); *ResultWidePtr = ResultChar; ResultPtr += 4; } else if (CharByteWidth == 2) { // FIXME: Make the type of the result buffer correct instead of // using reinterpret_cast. - UTF16 *ResultWidePtr = reinterpret_cast<UTF16*>(ResultPtr); + llvm::UTF16 *ResultWidePtr = reinterpret_cast<llvm::UTF16*>(ResultPtr); *ResultWidePtr = ResultChar & 0xFFFF; ResultPtr += 2; } else { @@ -1520,12 +1531,12 @@ void StringLiteralParser::init(ArrayRef<Token> StringToks){ if (CharByteWidth == 4) { // FIXME: Make the type of the result buffer correct instead of // using reinterpret_cast. - UTF32 *ResultWidePtr = reinterpret_cast<UTF32*>(ResultBuf.data()); + llvm::UTF32 *ResultWidePtr = reinterpret_cast<llvm::UTF32*>(ResultBuf.data()); ResultWidePtr[0] = GetNumStringChars() - 1; } else if (CharByteWidth == 2) { // FIXME: Make the type of the result buffer correct instead of // using reinterpret_cast. - UTF16 *ResultWidePtr = reinterpret_cast<UTF16*>(ResultBuf.data()); + llvm::UTF16 *ResultWidePtr = reinterpret_cast<llvm::UTF16*>(ResultBuf.data()); ResultWidePtr[0] = GetNumStringChars() - 1; } else { assert(CharByteWidth == 1 && "Unexpected char width"); @@ -1559,7 +1570,7 @@ void StringLiteralParser::init(ArrayRef<Token> StringToks){ static const char *resyncUTF8(const char *Err, const char *End) { if (Err == End) return End; - End = Err + std::min<unsigned>(getNumBytesForUTF8(*Err), End-Err); + End = Err + std::min<unsigned>(llvm::getNumBytesForUTF8(*Err), End-Err); while (++Err != End && (*Err & 0xC0) == 0x80) ; return Err; @@ -1571,7 +1582,7 @@ static const char *resyncUTF8(const char *Err, const char *End) { bool StringLiteralParser::CopyStringFragment(const Token &Tok, const char *TokBegin, StringRef Fragment) { - const UTF8 *ErrorPtrTmp; + const llvm::UTF8 *ErrorPtrTmp; if (ConvertUTF8toWide(CharByteWidth, Fragment, ResultPtr, ErrorPtrTmp)) return false; @@ -1697,3 +1708,12 @@ unsigned StringLiteralParser::getOffsetOfStringByte(const Token &Tok, return SpellingPtr-SpellingStart; } + +/// Determine whether a suffix is a valid ud-suffix. We avoid treating reserved +/// suffixes as ud-suffixes, because the diagnostic experience is better if we +/// treat it as an invalid suffix. +bool StringLiteralParser::isValidUDSuffix(const LangOptions &LangOpts, + StringRef Suffix) { + return NumericLiteralParser::isValidUDSuffix(LangOpts, Suffix) || + Suffix == "sv"; +} |