diff options
Diffstat (limited to 'lib/MC/MCParser/AsmLexer.cpp')
-rw-r--r-- | lib/MC/MCParser/AsmLexer.cpp | 54 |
1 files changed, 47 insertions, 7 deletions
diff --git a/lib/MC/MCParser/AsmLexer.cpp b/lib/MC/MCParser/AsmLexer.cpp index 549bd47..5c1ae2f 100644 --- a/lib/MC/MCParser/AsmLexer.cpp +++ b/lib/MC/MCParser/AsmLexer.cpp @@ -65,10 +65,46 @@ int AsmLexer::getNextChar() { } } +/// LexFloatLiteral: [0-9]*[.][0-9]*([eE][+-]?[0-9]*)? +/// +/// The leading integral digit sequence and dot should have already been +/// consumed, some or all of the fractional digit sequence *can* have been +/// consumed. +AsmToken AsmLexer::LexFloatLiteral() { + // Skip the fractional digit sequence. + while (isdigit(*CurPtr)) + ++CurPtr; + + // Check for exponent; we intentionally accept a slighlty wider set of + // literals here and rely on the upstream client to reject invalid ones (e.g., + // "1e+"). + if (*CurPtr == 'e' || *CurPtr == 'E') { + ++CurPtr; + if (*CurPtr == '-' || *CurPtr == '+') + ++CurPtr; + while (isdigit(*CurPtr)) + ++CurPtr; + } + + return AsmToken(AsmToken::Real, + StringRef(TokStart, CurPtr - TokStart)); +} + /// LexIdentifier: [a-zA-Z_.][a-zA-Z0-9_$.@]* +static bool IsIdentifierChar(char c) { + return isalnum(c) || c == '_' || c == '$' || c == '.' || c == '@'; +} AsmToken AsmLexer::LexIdentifier() { - while (isalnum(*CurPtr) || *CurPtr == '_' || *CurPtr == '$' || - *CurPtr == '.' || *CurPtr == '@') + // Check for floating point literals. + if (CurPtr[-1] == '.' && isdigit(*CurPtr)) { + // Disambiguate a .1243foo identifier from a floating literal. + while (isdigit(*CurPtr)) + ++CurPtr; + if (*CurPtr == 'e' || *CurPtr == 'E' || !IsIdentifierChar(*CurPtr)) + return LexFloatLiteral(); + } + + while (IsIdentifierChar(*CurPtr)) ++CurPtr; // Handle . as a special case. @@ -84,7 +120,7 @@ AsmToken AsmLexer::LexSlash() { switch (*CurPtr) { case '*': break; // C style comment. case '/': return ++CurPtr, LexLineComment(); - default: return AsmToken(AsmToken::Slash, StringRef(CurPtr, 1)); + default: return AsmToken(AsmToken::Slash, StringRef(CurPtr-1, 1)); } // C Style comment. @@ -125,7 +161,6 @@ static void SkipIgnoredIntegerSuffix(const char *&CurPtr) { CurPtr += 3; } - /// LexDigit: First character is [0-9]. /// Local Label: [0-9][:] /// Forward/Backward Label: [0-9][fb] @@ -133,13 +168,18 @@ static void SkipIgnoredIntegerSuffix(const char *&CurPtr) { /// Octal integer: 0[0-7]+ /// Hex integer: 0x[0-9a-fA-F]+ /// Decimal integer: [1-9][0-9]* -/// TODO: FP literal. AsmToken AsmLexer::LexDigit() { // Decimal integer: [1-9][0-9]* - if (CurPtr[-1] != '0') { + if (CurPtr[-1] != '0' || CurPtr[0] == '.') { while (isdigit(*CurPtr)) ++CurPtr; - + + // Check for floating point literals. + if (*CurPtr == '.' || *CurPtr == 'e') { + ++CurPtr; + return LexFloatLiteral(); + } + StringRef Result(TokStart, CurPtr - TokStart); long long Value; |