//===----------------------------------------------------------------------===//
#include "llvm/MC/MCParser/AsmLexer.h"
-#include "llvm/Support/SMLoc.h"
-#include "llvm/Support/MemoryBuffer.h"
#include "llvm/MC/MCAsmInfo.h"
+#include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/SMLoc.h"
#include <cctype>
#include <cerrno>
#include <cstdio>
AsmLexer::AsmLexer(const MCAsmInfo &_MAI) : MAI(_MAI) {
CurBuf = NULL;
CurPtr = NULL;
+ isAtStartOfLine = true;
}
AsmLexer::~AsmLexer() {
void AsmLexer::setBuffer(const MemoryBuffer *buf, const char *ptr) {
CurBuf = buf;
-
+
if (ptr)
CurPtr = ptr;
else
CurPtr = CurBuf->getBufferStart();
-
+
TokStart = 0;
}
/// location. This is defined to always return AsmToken::Error.
AsmToken AsmLexer::ReturnError(const char *Loc, const std::string &Msg) {
SetError(SMLoc::getFromPointer(Loc), Msg);
-
+
return AsmToken(AsmToken::Error, StringRef(Loc, 0));
}
// a random nul in the file. Disambiguate that here.
if (CurPtr-1 != CurBuf->getBufferEnd())
return 0; // Just whitespace.
-
+
// Otherwise, return end of file.
- --CurPtr; // Another call to lex will return EOF again.
+ --CurPtr; // Another call to lex will return EOF again.
return EOF;
}
}
while (IsIdentifierChar(*CurPtr))
++CurPtr;
-
+
// Handle . as a special case.
if (CurPtr == TokStart+1 && TokStart[0] == '.')
return AsmToken(AsmToken::Dot, StringRef(TokStart, 1));
-
+
return AsmToken(AsmToken::Identifier, StringRef(TokStart, CurPtr - TokStart));
}
case '*':
// End of the comment?
if (CurPtr[0] != '/') break;
-
+
++CurPtr; // End the */.
return LexToken();
}
// FIXME: This is broken if we happen to a comment at the end of a file, which
// was .included, and which doesn't end with a newline.
int CurChar = getNextChar();
- while (CurChar != '\n' && CurChar != '\n' && CurChar != EOF)
+ while (CurChar != '\n' && CurChar != '\r' && CurChar != EOF)
CurChar = getNextChar();
-
+
if (CurChar == EOF)
return AsmToken(AsmToken::Eof, StringRef(CurPtr, 0));
return AsmToken(AsmToken::EndOfStatement, StringRef(CurPtr, 0));
return ReturnError(TokStart, "invalid decimal number");
Value = (long long)UValue;
}
-
+
// The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
// suffixes on integer literals.
SkipIgnoredIntegerSuffix(CurPtr);
-
+
return AsmToken(AsmToken::Integer, Result, Value);
}
-
+
if (*CurPtr == 'b') {
++CurPtr;
// See if we actually have "0b" as part of something like "jmp 0b\n"
const char *NumStart = CurPtr;
while (CurPtr[0] == '0' || CurPtr[0] == '1')
++CurPtr;
-
+
// Requires at least one binary digit.
if (CurPtr == NumStart)
- return ReturnError(TokStart, "Invalid binary number");
-
+ return ReturnError(TokStart, "invalid binary number");
+
StringRef Result(TokStart, CurPtr - TokStart);
-
+
long long Value;
if (Result.substr(2).getAsInteger(2, Value))
- return ReturnError(TokStart, "Invalid binary number");
-
+ return ReturnError(TokStart, "invalid binary number");
+
// The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
// suffixes on integer literals.
SkipIgnoredIntegerSuffix(CurPtr);
-
+
return AsmToken(AsmToken::Integer, Result, Value);
}
-
+
if (*CurPtr == 'x') {
++CurPtr;
const char *NumStart = CurPtr;
while (isxdigit(CurPtr[0]))
++CurPtr;
-
+
// Requires at least one hex digit.
if (CurPtr == NumStart)
- return ReturnError(CurPtr-2, "Invalid hexadecimal number");
+ return ReturnError(CurPtr-2, "invalid hexadecimal number");
unsigned long long Result;
if (StringRef(TokStart, CurPtr - TokStart).getAsInteger(0, Result))
- return ReturnError(TokStart, "Invalid hexadecimal number");
-
+ return ReturnError(TokStart, "invalid hexadecimal number");
+
// The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
// suffixes on integer literals.
SkipIgnoredIntegerSuffix(CurPtr);
-
+
return AsmToken(AsmToken::Integer, StringRef(TokStart, CurPtr - TokStart),
(int64_t)Result);
}
-
+
// Must be an octal number, it starts with 0.
- while (*CurPtr >= '0' && *CurPtr <= '7')
+ while (*CurPtr >= '0' && *CurPtr <= '9')
++CurPtr;
-
+
StringRef Result(TokStart, CurPtr - TokStart);
long long Value;
if (Result.getAsInteger(8, Value))
- return ReturnError(TokStart, "Invalid octal number");
-
+ return ReturnError(TokStart, "invalid octal number");
+
// The darwin/x86 (and x86-64) assembler accepts and ignores ULL and LL
// suffixes on integer literals.
SkipIgnoredIntegerSuffix(CurPtr);
-
+
return AsmToken(AsmToken::Integer, Result, Value);
}
} else
Value = TokStart[1];
- return AsmToken(AsmToken::Integer, Res, Value);
+ return AsmToken(AsmToken::Integer, Res, Value);
}
// Allow \", etc.
CurChar = getNextChar();
}
-
+
if (CurChar == EOF)
return ReturnError(TokStart, "unterminated string constant");
CurChar = getNextChar();
}
-
+
return AsmToken(AsmToken::String, StringRef(TokStart, CurPtr - TokStart));
}
StringRef AsmLexer::LexUntilEndOfStatement() {
TokStart = CurPtr;
- while (!isAtStartOfComment(*CurPtr) && // Start of line comment.
- *CurPtr != ';' && // End of statement marker.
+ while (!isAtStartOfComment(*CurPtr) && // Start of line comment.
+ !isAtStatementSeparator(CurPtr) && // End of statement marker.
*CurPtr != '\n' &&
*CurPtr != '\r' &&
(*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) {
return StringRef(TokStart, CurPtr-TokStart);
}
+StringRef AsmLexer::LexUntilEndOfLine() {
+ TokStart = CurPtr;
+
+ while (*CurPtr != '\n' &&
+ *CurPtr != '\r' &&
+ (*CurPtr != 0 || CurPtr != CurBuf->getBufferEnd())) {
+ ++CurPtr;
+ }
+ return StringRef(TokStart, CurPtr-TokStart);
+}
+
bool AsmLexer::isAtStartOfComment(char Char) {
// FIXME: This won't work for multi-character comment indicators like "//".
return Char == *MAI.getCommentString();
}
+bool AsmLexer::isAtStatementSeparator(const char *Ptr) {
+ return strncmp(Ptr, MAI.getSeparatorString(),
+ strlen(MAI.getSeparatorString())) == 0;
+}
+
AsmToken AsmLexer::LexToken() {
TokStart = CurPtr;
// This always consumes at least one character.
int CurChar = getNextChar();
-
- if (isAtStartOfComment(CurChar))
+
+ if (isAtStartOfComment(CurChar)) {
+ // If this comment starts with a '#', then return the Hash token and let
+ // the assembler parser see if it can be parsed as a cpp line filename
+ // comment. We do this only if we are at the start of a line.
+ if (CurChar == '#' && isAtStartOfLine)
+ return AsmToken(AsmToken::Hash, StringRef(TokStart, 1));
+ isAtStartOfLine = true;
return LexLineComment();
+ }
+ if (isAtStatementSeparator(TokStart)) {
+ CurPtr += strlen(MAI.getSeparatorString()) - 1;
+ return AsmToken(AsmToken::EndOfStatement,
+ StringRef(TokStart, strlen(MAI.getSeparatorString())));
+ }
+ // If we're missing a newline at EOF, make sure we still get an
+ // EndOfStatement token before the Eof token.
+ if (CurChar == EOF && !isAtStartOfLine) {
+ isAtStartOfLine = true;
+ return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
+ }
+
+ isAtStartOfLine = false;
switch (CurChar) {
default:
// Handle identifier: [a-zA-Z_.][a-zA-Z0-9_$.@]*
if (isalpha(CurChar) || CurChar == '_' || CurChar == '.')
return LexIdentifier();
-
+
// Unknown character, emit an error.
return ReturnError(TokStart, "invalid character in input");
case EOF: return AsmToken(AsmToken::Eof, StringRef(TokStart, 0));
case 0:
case ' ':
case '\t':
- // Ignore whitespace.
- return LexToken();
+ if (SkipSpace) {
+ // Ignore whitespace.
+ return LexToken();
+ } else {
+ int len = 1;
+ while (*CurPtr==' ' || *CurPtr=='\t') {
+ CurPtr++;
+ len++;
+ }
+ return AsmToken(AsmToken::Space, StringRef(TokStart, len));
+ }
case '\n': // FALL THROUGH.
- case '\r': // FALL THROUGH.
- case ';': return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
+ case '\r':
+ isAtStartOfLine = true;
+ return AsmToken(AsmToken::EndOfStatement, StringRef(TokStart, 1));
case ':': return AsmToken(AsmToken::Colon, StringRef(TokStart, 1));
case '+': return AsmToken(AsmToken::Plus, StringRef(TokStart, 1));
case '-': return AsmToken(AsmToken::Minus, StringRef(TokStart, 1));
case ',': return AsmToken(AsmToken::Comma, StringRef(TokStart, 1));
case '$': return AsmToken(AsmToken::Dollar, StringRef(TokStart, 1));
case '@': return AsmToken(AsmToken::At, StringRef(TokStart, 1));
- case '=':
+ case '\\': return AsmToken(AsmToken::BackSlash, StringRef(TokStart, 1));
+ case '=':
if (*CurPtr == '=')
return ++CurPtr, AsmToken(AsmToken::EqualEqual, StringRef(TokStart, 2));
return AsmToken(AsmToken::Equal, StringRef(TokStart, 1));
- case '|':
+ case '|':
if (*CurPtr == '|')
return ++CurPtr, AsmToken(AsmToken::PipePipe, StringRef(TokStart, 2));
return AsmToken(AsmToken::Pipe, StringRef(TokStart, 1));
case '^': return AsmToken(AsmToken::Caret, StringRef(TokStart, 1));
- case '&':
+ case '&':
if (*CurPtr == '&')
return ++CurPtr, AsmToken(AsmToken::AmpAmp, StringRef(TokStart, 2));
return AsmToken(AsmToken::Amp, StringRef(TokStart, 1));
- case '!':
+ case '!':
if (*CurPtr == '=')
return ++CurPtr, AsmToken(AsmToken::ExclaimEqual, StringRef(TokStart, 2));
return AsmToken(AsmToken::Exclaim, StringRef(TokStart, 1));
return LexDigit();
case '<':
switch (*CurPtr) {
- case '<': return ++CurPtr, AsmToken(AsmToken::LessLess,
+ case '<': return ++CurPtr, AsmToken(AsmToken::LessLess,
StringRef(TokStart, 2));
- case '=': return ++CurPtr, AsmToken(AsmToken::LessEqual,
+ case '=': return ++CurPtr, AsmToken(AsmToken::LessEqual,
StringRef(TokStart, 2));
- case '>': return ++CurPtr, AsmToken(AsmToken::LessGreater,
+ case '>': return ++CurPtr, AsmToken(AsmToken::LessGreater,
StringRef(TokStart, 2));
default: return AsmToken(AsmToken::Less, StringRef(TokStart, 1));
}
case '>':
switch (*CurPtr) {
- case '>': return ++CurPtr, AsmToken(AsmToken::GreaterGreater,
+ case '>': return ++CurPtr, AsmToken(AsmToken::GreaterGreater,
StringRef(TokStart, 2));
- case '=': return ++CurPtr, AsmToken(AsmToken::GreaterEqual,
+ case '=': return ++CurPtr, AsmToken(AsmToken::GreaterEqual,
StringRef(TokStart, 2));
default: return AsmToken(AsmToken::Greater, StringRef(TokStart, 1));
}
-
+
// TODO: Quoted identifiers (objc methods etc)
// local labels: [0-9][:]
// Forward/backward labels: [0-9][fb]
projects / oota-llvm.git / blobdiff