path: root/lib/Sema/SemaChecking.cpp

//===--- SemaChecking.cpp - Extra Semantic Checking -----------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
//  This file implements extra semantic analysis beyond what is enforced 
//  by the C type system.
//
//===----------------------------------------------------------------------===//

#include "Sema.h"
#include "clang/AST/ASTContext.h"
#include "clang/AST/DeclObjC.h"
#include "clang/AST/ExprCXX.h"
#include "clang/AST/ExprObjC.h"
#include "clang/Lex/LiteralSupport.h"
#include "clang/Lex/Preprocessor.h"
using namespace clang;

/// getLocationOfStringLiteralByte - Return a source location that points to the
/// specified byte of the specified string literal.
///
/// Strings are amazingly complex.  They can be formed from multiple tokens and
/// can have escape sequences in them in addition to the usual trigraph and
/// escaped newline business.  This routine handles this complexity.
///
SourceLocation Sema::getLocationOfStringLiteralByte(const StringLiteral *SL,
                                                    unsigned ByteNo) const {
  assert(!SL->isWide() && "This doesn't work for wide strings yet");
  
  llvm::SmallString<16> SpellingBuffer;
  
  // Loop over all of the tokens in this string until we find the one that
  // contains the byte we're looking for.
  unsigned TokNo = 0;
  while (1) {
    assert(TokNo < SL->getNumConcatenated() && "Invalid byte number!");
    SourceLocation StrTokLoc = SL->getStrTokenLoc(TokNo);
   
    // Get the spelling of the string so that we can get the data that makes up
    // the string literal, not the identifier for the macro it is potentially
    // expanded through.
    SourceLocation StrTokSpellingLoc = SourceMgr.getSpellingLoc(StrTokLoc);

    // Re-lex the token to get its length and original spelling.
    std::pair<FileID, unsigned> LocInfo =
      SourceMgr.getDecomposedLoc(StrTokSpellingLoc);
    std::pair<const char *,const char *> Buffer =
      SourceMgr.getBufferData(LocInfo.first);
    const char *StrData = Buffer.first+LocInfo.second;
    
    // Create a langops struct and enable trigraphs.  This is sufficient for
    // relexing tokens.
    LangOptions LangOpts;
    LangOpts.Trigraphs = true;
    
    // Create a lexer starting at the beginning of this token.
    Lexer TheLexer(StrTokSpellingLoc, LangOpts, Buffer.first, StrData,
                   Buffer.second);
    Token TheTok;
    TheLexer.LexFromRawLexer(TheTok);
    
    // We generally care about the length of the token, which is known by the 
    // lexer as long as we don't need to clean it (trigraphs/newlines).
    unsigned TokNumBytes;
    if (!TheTok.needsCleaning()) {
      TokNumBytes = TheTok.getLength();
    } else {
      // Get the spelling of the token to remove trigraphs and escaped newlines.
      SpellingBuffer.resize(TheTok.getLength());
      const char *SpellingPtr = &SpellingBuffer[0];
      TokNumBytes = PP.getSpelling(TheTok, SpellingPtr);
    }
    
    // The length of the string is the token length minus the two quotes.
    TokNumBytes -= 2;

    // If the byte is in this token, return the location of the byte.
    if (ByteNo < TokNumBytes ||
        (ByteNo == TokNumBytes && TokNo == SL->getNumConcatenated())) {
      unsigned Offset = 
        StringLiteralParser::getOffsetOfStringByte(TheTok, ByteNo, PP);
     
      // Now that we know the offset of the token in the spelling, use the
      // preprocessor to get the offset in the original source.
      return PP.AdvanceToTokenCharacter(StrTokLoc, Offset);
    }
    
    // Move to the next string token.
    ++TokNo;
    ByteNo -= TokNumBytes;
  }
}


/// CheckFunctionCall - Check a direct function call for various correctness
/// and safety properties not strictly enforced by the C type system.
Action::OwningExprResult
Sema::CheckFunctionCall(FunctionDecl *FDecl, CallExpr *TheCall) {
  OwningExprResult TheCallResult(Owned(TheCall));
  // Get the IdentifierInfo* for the called function.
  IdentifierInfo *FnInfo = FDecl->getIdentifier();

  // None of the checks below are needed for functions that don't have
  // simple names (e.g., C++ conversion functions).
  if (!FnInfo)
    return move(TheCallResult);

  switch (FDecl->getBuiltinID(Context)) {
  case Builtin::BI__builtin___CFStringMakeConstantString:
    assert(TheCall->getNumArgs() == 1 &&
           "Wrong # arguments to builtin CFStringMakeConstantString");
    if (CheckObjCString(TheCall->getArg(0)))
      return ExprError();
    return move(TheCallResult);
  case Builtin::BI__builtin_stdarg_start:
  case Builtin::BI__builtin_va_start:
    if (SemaBuiltinVAStart(TheCall))
      return ExprErro