/// FindBufferContainingLoc - Return the ID of the buffer containing the
/// specified location, returning -1 if not found.
int SourceMgr::FindBufferContainingLoc(SMLoc Loc) const {
for (unsigned i = 0, e = Buffers.size(); i != e; ++i)
if (Loc.getPointer() >= Buffers[i].Buffer->getBufferStart() &&
// Use <= here so that a pointer to the null at the end of the buffer
// is included as part of the buffer.
Loc.getPointer() <= Buffers[i].Buffer->getBufferEnd())
return i;
return -1;
}
/// GetMessage - Return an SMDiagnostic at the specified location with the
/// specified string.
///
/// @param Type - If non-null, the kind of message (e.g., "error") which is
/// prefixed to the message.
SMDiagnostic SourceMgr::GetMessage(SMLoc Loc, SourceMgr::DiagKind Kind,
const Twine &Msg,
ArrayRef<SMRange> Ranges) const {
// First thing to do: find the current buffer containing the specified
// location.
int CurBuf = FindBufferContainingLoc(Loc);
assert(CurBuf != -1 && "Invalid or unspecified location!");
MemoryBuffer *CurMB = getBufferInfo(CurBuf).Buffer;
// Scan backward to find the start of the line.
const char *LineStart = Loc.getPointer();
while (LineStart != CurMB->getBufferStart() &&
LineStart[-1] != '\n' && LineStart[-1] != '\r')
--LineStart;
// Get the end of the line.
const char *LineEnd = Loc.getPointer();
while (LineEnd != CurMB->getBufferEnd() &&
LineEnd[0] != '\n' && LineEnd[0] != '\r')
++LineEnd;
std::string LineStr(LineStart, LineEnd);
// Convert any ranges to column ranges that only intersect the line of the
// location.
SmallVector<std::pair<unsigned, unsigned>, 4> ColRanges;
for (unsigned i = 0, e = Ranges.size(); i != e; ++i) {
SMRange R = Ranges[i];
if (!R.isValid()) continue;
// If the line doesn't contain any part of the range, then ignore it.
if (R.Start.getPointer() > LineEnd || R.End.getPointer() < LineStart)
continue;
// Ignore pieces of the range that go onto other lines.
if (R.Start.getPointer() < LineStart)
R.Start = SMLoc::getFromPointer(LineStart);
if (R.End.getPointer() > LineEnd)
R.End = SMLoc::getFromPointer(LineEnd);
// Translate from SMLoc ranges to column ranges.
ColRanges.push_back(std::make_pair(R.Start.getPointer()-LineStart,
R.End.getPointer()-LineStart));
}
return SMDiagnostic(*this, Loc,
CurMB->getBufferIdentifier(), FindLineNumber(Loc, CurBuf),
Loc.getPointer()-LineStart, Kind, Msg.str(),
LineStr, ColRanges);
}
SMDiagnostic MIRParserImpl::diagFromMIStringDiag(const SMDiagnostic &Error,
SMRange SourceRange) {
assert(SourceRange.isValid() && "Invalid source range");
SMLoc Loc = SourceRange.Start;
bool HasQuote = Loc.getPointer() < SourceRange.End.getPointer() &&
*Loc.getPointer() == '\'';
// Translate the location of the error from the location in the MI string to
// the corresponding location in the MIR file.
Loc = Loc.getFromPointer(Loc.getPointer() + Error.getColumnNo() +
(HasQuote ? 1 : 0));
// TODO: Translate any source ranges as well.
return SM.GetMessage(Loc, Error.getKind(), Error.getMessage(), None,
Error.getFixIts());
}
std::pair<unsigned, unsigned>
SourceMgr::getLineAndColumn(SMLoc Loc, unsigned BufferID) const {
if (!BufferID)
BufferID = FindBufferContainingLoc(Loc);
assert(BufferID && "Invalid Location!");
auto &SB = getBufferInfo(BufferID);
const char *Ptr = Loc.getPointer();
size_t Sz = SB.Buffer->getBufferSize();
assert(Sz <= std::numeric_limits<uint64_t>::max());
unsigned LineNo;
if (Sz <= std::numeric_limits<uint8_t>::max())
LineNo = SB.getLineNumber<uint8_t>(Ptr);
else if (Sz <= std::numeric_limits<uint16_t>::max())
LineNo = SB.getLineNumber<uint16_t>(Ptr);
else if (Sz <= std::numeric_limits<uint32_t>::max())
LineNo = SB.getLineNumber<uint32_t>(Ptr);
else
LineNo = SB.getLineNumber<uint64_t>(Ptr);
const char *BufStart = SB.Buffer->getBufferStart();
size_t NewlineOffs = StringRef(BufStart, Ptr-BufStart).find_last_of("\n\r");
if (NewlineOffs == StringRef::npos) NewlineOffs = ~(size_t)0;
return std::make_pair(LineNo, Ptr-BufStart-NewlineOffs);
}
/// Parse an instruction mnemonic followed by its operands.
bool PPCAsmParser::
ParseInstruction(ParseInstructionInfo &Info, StringRef Name, SMLoc NameLoc,
SmallVectorImpl<MCParsedAsmOperand*> &Operands) {
// The first operand is the token for the instruction name.
// If the instruction ends in a '.', we need to create a separate
// token for it, to match what TableGen is doing.
size_t Dot = Name.find('.');
StringRef Mnemonic = Name.slice(0, Dot);
Operands.push_back(PPCOperand::CreateToken(Mnemonic, NameLoc, isPPC64()));
if (Dot != StringRef::npos) {
SMLoc DotLoc = SMLoc::getFromPointer(NameLoc.getPointer() + Dot);
StringRef DotStr = Name.slice(Dot, StringRef::npos);
Operands.push_back(PPCOperand::CreateToken(DotStr, DotLoc, isPPC64()));
}
// If there are no more operands then finish
if (getLexer().is(AsmToken::EndOfStatement))
return false;
// Parse the first operand
if (ParseOperand(Operands))
return true;
while (getLexer().isNot(AsmToken::EndOfStatement) &&
getLexer().is(AsmToken::Comma)) {
// Consume the comma token
getLexer().Lex();
// Parse the next operand
if (ParseOperand(Operands))
return true;
}
return false;
}
OperandMatchResultTy BPFAsmParser::parseRegister(OperandVector &Operands) {
SMLoc S = getLoc();
SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1);
switch (getLexer().getKind()) {
default:
return MatchOperand_NoMatch;
case AsmToken::Identifier:
StringRef Name = getLexer().getTok().getIdentifier();
unsigned RegNo = MatchRegisterName(Name);
if (RegNo == 0)
return MatchOperand_NoMatch;
getLexer().Lex();
Operands.push_back(BPFOperand::createReg(RegNo, S, E));
}
return MatchOperand_Success;
}
bool ELFAsmParser::ParseSectionName(StringRef &SectionName) {
// A section name can contain -, so we cannot just use
// ParseIdentifier.
SMLoc FirstLoc = getLexer().getLoc();
unsigned Size = 0;
if (getLexer().is(AsmToken::String)) {
SectionName = getTok().getIdentifier();
Lex();
return false;
}
for (;;) {
StringRef Tmp;
unsigned CurSize;
SMLoc PrevLoc = getLexer().getLoc();
if (getLexer().is(AsmToken::Minus)) {
CurSize = 1;
Lex(); // Consume the "-".
} else if (getLexer().is(AsmToken::String)) {
CurSize = getTok().getIdentifier().size() + 2;
Lex();
} else if (getLexer().is(AsmToken::Identifier)) {
CurSize = getTok().getIdentifier().size();
Lex();
} else {
break;
}
Size += CurSize;
SectionName = StringRef(FirstLoc.getPointer(), Size);
// Make sure the following token is adjacent.
if (PrevLoc.getPointer() + CurSize != getTok().getLoc().getPointer())
break;
}
if (Size == 0)
return true;
return false;
}
bool ELFAsmParser::ParseSectionName(StringRef &SectionName) {
// A section name can contain -, so we cannot just use
// parseIdentifier.
SMLoc FirstLoc = getLexer().getLoc();
unsigned Size = 0;
if (getLexer().is(AsmToken::String)) {
SectionName = getTok().getIdentifier();
Lex();
return false;
}
while (!getParser().hasPendingError()) {
SMLoc PrevLoc = getLexer().getLoc();
if (getLexer().is(AsmToken::Comma) ||
getLexer().is(AsmToken::EndOfStatement))
break;
unsigned CurSize;
if (getLexer().is(AsmToken::String)) {
CurSize = getTok().getIdentifier().size() + 2;
Lex();
} else if (getLexer().is(AsmToken::Identifier)) {
CurSize = getTok().getIdentifier().size();
Lex();
} else {
CurSize = getTok().getString().size();
Lex();
}
Size += CurSize;
SectionName = StringRef(FirstLoc.getPointer(), Size);
// Make sure the following token is adjacent.
if (PrevLoc.getPointer() + CurSize != getTok().getLoc().getPointer())
break;
}
if (Size == 0)
return true;
return false;
}
/// GetMessage - Return an SMDiagnostic at the specified location with the
/// specified string.
///
/// @param Type - If non-null, the kind of message (e.g., "error") which is
/// prefixed to the message.
SMDiagnostic SourceMgr::GetMessage(SMLoc Loc, const Twine &Msg,
const char *Type, bool ShowLine) const {
// First thing to do: find the current buffer containing the specified
// location.
int CurBuf = FindBufferContainingLoc(Loc);
assert(CurBuf != -1 && "Invalid or unspecified location!");
MemoryBuffer *CurMB = getBufferInfo(CurBuf).Buffer;
// Scan backward to find the start of the line.
const char *LineStart = Loc.getPointer();
while (LineStart != CurMB->getBufferStart() &&
LineStart[-1] != '\n' && LineStart[-1] != '\r')
--LineStart;
std::string LineStr;
if (ShowLine) {
// Get the end of the line.
const char *LineEnd = Loc.getPointer();
while (LineEnd != CurMB->getBufferEnd() &&
LineEnd[0] != '\n' && LineEnd[0] != '\r')
++LineEnd;
LineStr = std::string(LineStart, LineEnd);
}
std::string PrintedMsg;
raw_string_ostream OS(PrintedMsg);
if (Type)
OS << Type << ": ";
OS << Msg;
return SMDiagnostic(*this, Loc,
CurMB->getBufferIdentifier(), FindLineNumber(Loc, CurBuf),
Loc.getPointer()-LineStart, OS.str(),
LineStr, ShowLine);
}
int TGLexer::getNextChar() {
char CurChar = *CurPtr++;
switch (CurChar) {
default:
return (unsigned char)CurChar;
case 0: {
// A nul character in the stream is either the end of the current buffer or
// a random nul in the file. Disambiguate that here.
if (CurPtr-1 != CurBuf->getBufferEnd())
return 0; // Just whitespace.
// If this is the end of an included file, pop the parent file off the
// include stack.
SMLoc ParentIncludeLoc = SrcMgr.getParentIncludeLoc(CurBuffer);
if (ParentIncludeLoc != SMLoc()) {
CurBuffer = SrcMgr.FindBufferContainingLoc(ParentIncludeLoc);
CurBuf = SrcMgr.getMemoryBuffer(CurBuffer);
CurPtr = ParentIncludeLoc.getPointer();
return getNextChar();
}
// Otherwise, return end of file.
--CurPtr; // Another call to lex will return EOF again.
return EOF;
}
case '\n':
case '\r':
// Handle the newline character by ignoring it and incrementing the line
// count. However, be careful about 'dos style' files with \n\r in them.
// Only treat a \n\r or \r\n as a single line.
if ((*CurPtr == '\n' || (*CurPtr == '\r')) &&
*CurPtr != CurChar)
++CurPtr; // Eat the two char newline sequence.
return '\n';
}
}
OperandMatchResultTy BPFAsmParser::parseImmediate(OperandVector &Operands) {
switch (getLexer().getKind()) {
default:
return MatchOperand_NoMatch;
case AsmToken::LParen:
case AsmToken::Minus:
case AsmToken::Plus:
case AsmToken::Integer:
case AsmToken::String:
case AsmToken::Identifier:
break;
}
const MCExpr *IdVal;
SMLoc S = getLoc();
if (getParser().parseExpression(IdVal))
return MatchOperand_ParseFail;
SMLoc E = SMLoc::getFromPointer(S.getPointer() - 1);
Operands.push_back(BPFOperand::createImm(IdVal, S, E));
return MatchOperand_Success;
}
std::pair<unsigned, unsigned>
SourceMgr::getLineAndColumn(SMLoc Loc, unsigned BufferID) const {
if (!BufferID)
BufferID = FindBufferContainingLoc(Loc);
assert(BufferID && "Invalid Location!");
const MemoryBuffer *Buff = getMemoryBuffer(BufferID);
// Count the number of \n's between the start of the file and the specified
// location.
unsigned LineNo = 1;
const char *BufStart = Buff->getBufferStart();
const char *Ptr = BufStart;
// If we have a line number cache, and if the query is to a later point in the
// same file, start searching from the last query location. This optimizes
// for the case when multiple diagnostics come out of one file in order.
if (LineNoCacheTy *Cache = getCache(LineNoCache))
if (Cache->LastQueryBufferID == BufferID &&
Cache->LastQuery <= Loc.getPointer()) {
Ptr = Cache->LastQuery;
LineNo = Cache->LineNoOfQuery;
}
// Scan for the location being queried, keeping track of the number of lines
// we see.
for (; SMLoc::getFromPointer(Ptr) != Loc; ++Ptr)
if (*Ptr == '\n') ++LineNo;
// Allocate the line number cache if it doesn't exist.
if (!LineNoCache)
LineNoCache = new LineNoCacheTy();
// Update the line # cache.
LineNoCacheTy &Cache = *getCache(LineNoCache);
Cache.LastQueryBufferID = BufferID;
Cache.LastQuery = Ptr;
Cache.LineNoOfQuery = LineNo;
size_t NewlineOffs = StringRef(BufStart, Ptr-BufStart).find_last_of("\n\r");
if (NewlineOffs == StringRef::npos) NewlineOffs = ~(size_t)0;
return std::make_pair(LineNo, Ptr-BufStart-NewlineOffs);
}
/// ParseInstruction - Parse an BPF instruction which is in BPF verifier
/// format.
bool BPFAsmParser::ParseInstruction(ParseInstructionInfo &Info, StringRef Name,
SMLoc NameLoc, OperandVector &Operands) {
// The first operand could be either register or actually an operator.
unsigned RegNo = MatchRegisterName(Name);
if (RegNo != 0) {
SMLoc E = SMLoc::getFromPointer(NameLoc.getPointer() - 1);
Operands.push_back(BPFOperand::createReg(RegNo, NameLoc, E));
} else if (BPFOperand::isValidIdAtStart (Name))
Operands.push_back(BPFOperand::createToken(Name, NameLoc));
else
return Error(NameLoc, "invalid register/token name");
while (!getLexer().is(AsmToken::EndOfStatement)) {
// Attempt to parse token as operator
if (parseOperandAsOperator(Operands) == MatchOperand_Success)
continue;
// Attempt to parse token as register
if (parseRegister(Operands) == MatchOperand_Success)
continue;
// Attempt to parse token as an immediate
if (parseImmediate(Operands) != MatchOperand_Success) {
SMLoc Loc = getLexer().getLoc();
return Error(Loc, "unexpected token");
}
}
if (getLexer().isNot(AsmToken::EndOfStatement)) {
SMLoc Loc = getLexer().getLoc();
getParser().eatToEndOfStatement();
return Error(Loc, "unexpected token");
}
// Consume the EndOfStatement.
getParser().Lex();
return false;
}
/// FindLineNumber - Find the line number for the specified location in the
/// specified file. This is not a fast method.
unsigned SourceMgr::FindLineNumber(SMLoc Loc, int BufferID) const {
if (BufferID == -1) BufferID = FindBufferContainingLoc(Loc);
assert(BufferID != -1 && "Invalid Location!");
MemoryBuffer *Buff = getBufferInfo(BufferID).Buffer;
// Count the number of \n's between the start of the file and the specified
// location.
unsigned LineNo = 1;
const char *Ptr = Buff->getBufferStart();
// If we have a line number cache, and if the query is to a later point in the
// same file, start searching from the last query location. This optimizes
// for the case when multiple diagnostics come out of one file in order.
if (LineNoCacheTy *Cache = getCache(LineNoCache))
if (Cache->LastQueryBufferID == BufferID &&
Cache->LastQuery <= Loc.getPointer()) {
Ptr = Cache->LastQuery;
LineNo = Cache->LineNoOfQuery;
}
// Scan for the location being queried, keeping track of the number of lines
// we see.
for (; SMLoc::getFromPointer(Ptr) != Loc; ++Ptr)
if (*Ptr == '\n') ++LineNo;
// Allocate the line number cache if it doesn't exist.
if (LineNoCache == 0)
LineNoCache = new LineNoCacheTy();
// Update the line # cache.
LineNoCacheTy &Cache = *getCache(LineNoCache);
Cache.LastQueryBufferID = BufferID;
Cache.LastQuery = Ptr;
Cache.LineNoOfQuery = LineNo;
return LineNo;
}
SMDiagnostic SourceMgr::GetMessage(SMLoc Loc, SourceMgr::DiagKind Kind,
const Twine &Msg,
ArrayRef<SMRange> Ranges,
ArrayRef<SMFixIt> FixIts) const {
// First thing to do: find the current buffer containing the specified
// location to pull out the source line.
SmallVector<std::pair<unsigned, unsigned>, 4> ColRanges;
std::pair<unsigned, unsigned> LineAndCol;
const char *BufferID = "<unknown>";
std::string LineStr;
if (Loc.isValid()) {
unsigned CurBuf = FindBufferContainingLoc(Loc);
assert(CurBuf && "Invalid or unspecified location!");
const MemoryBuffer *CurMB = getMemoryBuffer(CurBuf);
BufferID = CurMB->getBufferIdentifier();
// Scan backward to find the start of the line.
const char *LineStart = Loc.getPointer();
const char *BufStart = CurMB->getBufferStart();
while (LineStart != BufStart && LineStart[-1] != '\n' &&
LineStart[-1] != '\r')
--LineStart;
// Get the end of the line.
const char *LineEnd = Loc.getPointer();
const char *BufEnd = CurMB->getBufferEnd();
while (LineEnd != BufEnd && LineEnd[0] != '\n' && LineEnd[0] != '\r')
++LineEnd;
LineStr = std::string(LineStart, LineEnd);
// Convert any ranges to column ranges that only intersect the line of the
// location.
for (unsigned i = 0, e = Ranges.size(); i != e; ++i) {
SMRange R = Ranges[i];
if (!R.isValid()) continue;
// If the line doesn't contain any part of the range, then ignore it.
if (R.Start.getPointer() > LineEnd || R.End.getPointer() < LineStart)
continue;
// Ignore pieces of the range that go onto other lines.
if (R.Start.getPointer() < LineStart)
R.Start = SMLoc::getFromPointer(LineStart);
if (R.End.getPointer() > LineEnd)
R.End = SMLoc::getFromPointer(LineEnd);
// Translate from SMLoc ranges to column ranges.
// FIXME: Handle multibyte characters.
ColRanges.push_back(std::make_pair(R.Start.getPointer()-LineStart,
R.End.getPointer()-LineStart));
}
LineAndCol = getLineAndColumn(Loc, CurBuf);
}
return SMDiagnostic(*this, Loc, BufferID, LineAndCol.first,
LineAndCol.second-1, Kind, Msg.str(),
LineStr, ColRanges, FixIts);
}
/// parseDirectiveSection:
/// ::= .section identifier (',' identifier)*
bool DarwinAsmParser::parseDirectiveSection(StringRef, SMLoc) {
SMLoc Loc = getLexer().getLoc();
StringRef SectionName;
if (getParser().parseIdentifier(SectionName))
return Error(Loc, "expected identifier after '.section' directive");
// Verify there is a following comma.
if (!getLexer().is(AsmToken::Comma))
return TokError("unexpected token in '.section' directive");
std::string SectionSpec = SectionName;
SectionSpec += ",";
// Add all the tokens until the end of the line, ParseSectionSpecifier will
// handle this.
StringRef EOL = getLexer().LexUntilEndOfStatement();
SectionSpec.append(EOL.begin(), EOL.end());
Lex();
if (getLexer().isNot(AsmToken::EndOfStatement))
return TokError("unexpected token in '.section' directive");
Lex();
StringRef Segment, Section;
unsigned StubSize;
unsigned TAA;
bool TAAParsed;
std::string ErrorStr =
MCSectionMachO::ParseSectionSpecifier(SectionSpec, Segment, Section,
TAA, TAAParsed, StubSize);
if (!ErrorStr.empty())
return Error(Loc, ErrorStr.c_str());
// Issue a warning if the target is not powerpc and Section is a *coal* section.
Triple TT = getParser().getContext().getObjectFileInfo()->getTargetTriple();
Triple::ArchType ArchTy = TT.getArch();
if (ArchTy != Triple::ppc && ArchTy != Triple::ppc64) {
StringRef NonCoalSection = StringSwitch<StringRef>(Section)
.Case("__textcoal_nt", "__text")
.Case("__const_coal", "__const")
.Case("__datacoal_nt", "__data")
.Default(Section);
if (!Section.equals(NonCoalSection)) {
StringRef SectionVal(Loc.getPointer());
size_t B = SectionVal.find(',') + 1, E = SectionVal.find(',', B);
SMLoc BLoc = SMLoc::getFromPointer(SectionVal.data() + B);
SMLoc ELoc = SMLoc::getFromPointer(SectionVal.data() + E);
getParser().Warning(Loc, "section \"" + Section + "\" is deprecated",
SMRange(BLoc, ELoc));
getParser().Note(Loc, "change section name to \"" + NonCoalSection +
"\"", SMRange(BLoc, ELoc));
}
}
// FIXME: Arch specific.
bool isText = Segment == "__TEXT"; // FIXME: Hack.
getStreamer().SwitchSection(getContext().getMachOSection(
Segment, Section, TAA, StubSize,
isText ? SectionKind::getText()
: SectionKind::getDataRel()));
return false;
}
