llvm-project/llvm/lib/AsmParser/Lexer.l

246 lines
8.2 KiB
Plaintext
Raw Normal View History

2001-06-07 04:29:01 +08:00
/*===-- Lexer.l - Scanner for llvm assembly files ----------------*- C++ -*--=//
//
// This file implements the flex scanner for LLVM assembly languages files.
//
//===------------------------------------------------------------------------=*/
%option prefix="llvmAsm"
%option yylineno
%option nostdinit
%option never-interactive
%option batch
%option noyywrap
%option nodefault
%option 8bit
%option outfile="Lexer.cpp"
%option ecs
%option noreject
%option noyymore
%{
#include "ParserInternals.h"
#include "llvm/BasicBlock.h"
#include "llvm/Method.h"
#include "llvm/Module.h"
#include <list>
#include "llvmAsmParser.h"
#include <ctype.h>
#include <stdlib.h>
2001-06-07 04:29:01 +08:00
#define RET_TOK(type, Enum, sym) \
llvmAsmlval.type = Instruction::Enum; return sym
// TODO: All of the static identifiers are figured out by the lexer,
// these should be hashed to reduce the lexer size
2001-06-07 04:29:01 +08:00
// atoull - Convert an ascii string of decimal digits into the unsigned long
// long representation... this does not have to do input error checking,
// because we know that the input will be matched by a suitable regex...
//
uint64_t atoull(const char *Buffer) {
uint64_t Result = 0;
for (; *Buffer; Buffer++) {
uint64_t OldRes = Result;
Result *= 10;
Result += *Buffer-'0';
if (Result < OldRes) { // Uh, oh, overflow detected!!!
ThrowException("constant bigger than 64 bits detected!");
}
}
return Result;
}
// UnEscapeLexed - Run through the specified buffer and change \xx codes to the
// appropriate character. If AllowNull is set to false, a \00 value will cause
// an exception to be thrown.
//
// If AllowNull is set to true, the return value of the function points to the
// last character of the string in memory.
//
char *UnEscapeLexed(char *Buffer, bool AllowNull = false) {
char *BOut = Buffer;
for (char *BIn = Buffer; *BIn; ) {
if (BIn[0] == '\\' && isxdigit(BIn[1]) && isxdigit(BIn[2])) {
char Tmp = BIn[3]; BIn[3] = 0; // Terminate string
*BOut = strtol(BIn+1, 0, 16); // Convert to number
if (!AllowNull && !*BOut)
ThrowException("String literal cannot accept \\00 escape!");
BIn[3] = Tmp; // Restore character
BIn += 3; // Skip over handled chars
++BOut;
} else {
*BOut++ = *BIn++;
}
}
return BOut;
}
2001-06-07 04:29:01 +08:00
#define YY_NEVER_INTERACTIVE 1
%}
/* Comments start with a ; and go till end of line */
Comment ;.*
/* Variable(Value) identifiers start with a % sign */
VarID %[-a-zA-Z$._][-a-zA-Z$._0-9]*
2001-06-07 04:29:01 +08:00
/* Label identifiers end with a colon */
Label [-a-zA-Z$._0-9]+:
2001-06-07 04:29:01 +08:00
/* Quoted names can contain any character except " and \ */
StringConstant \"[^\"]+\"
/* [PN]Integer: match positive and negative literal integer values that
* are preceeded by a '%' character. These represent unnamed variable slots.
*/
EPInteger %[0-9]+
ENInteger %-[0-9]+
/* E[PN]Integer: match positive and negative literal integer values */
PInteger [0-9]+
NInteger -[0-9]+
/* FPConstant - A Floating point constant.
TODO: Expand lexer to support 10e50 FP constant notation */
FPConstant [-+]?[0-9]+[.][0-9]*([eE][-+]?[0-9]+)?
2001-06-07 04:29:01 +08:00
%%
{Comment} { /* Ignore comments for now */ }
begin { return BEGINTOK; }
end { return END; }
true { return TRUE; }
false { return FALSE; }
declare { return DECLARE; }
global { return GLOBAL; }
constant { return CONSTANT; }
const { return CONST; }
internal { return INTERNAL; }
uninitialized { return UNINIT; }
2001-06-07 04:29:01 +08:00
implementation { return IMPLEMENTATION; }
\.\.\. { return DOTDOTDOT; }
string { return STRING; }
null { return NULL_TOK; }
to { return TO; }
except { return EXCEPT; }
2001-06-07 04:29:01 +08:00
void { llvmAsmlval.PrimType = Type::VoidTy ; return VOID; }
bool { llvmAsmlval.PrimType = Type::BoolTy ; return BOOL; }
sbyte { llvmAsmlval.PrimType = Type::SByteTy ; return SBYTE; }
ubyte { llvmAsmlval.PrimType = Type::UByteTy ; return UBYTE; }
short { llvmAsmlval.PrimType = Type::ShortTy ; return SHORT; }
ushort { llvmAsmlval.PrimType = Type::UShortTy; return USHORT; }
int { llvmAsmlval.PrimType = Type::IntTy ; return INT; }
uint { llvmAsmlval.PrimType = Type::UIntTy ; return UINT; }
long { llvmAsmlval.PrimType = Type::LongTy ; return LONG; }
ulong { llvmAsmlval.PrimType = Type::ULongTy ; return ULONG; }
float { llvmAsmlval.PrimType = Type::FloatTy ; return FLOAT; }
double { llvmAsmlval.PrimType = Type::DoubleTy; return DOUBLE; }
type { llvmAsmlval.PrimType = Type::TypeTy ; return TYPE; }
label { llvmAsmlval.PrimType = Type::LabelTy ; return LABEL; }
opaque { llvmAsmlval.TypeVal =
new PATypeHolder<Type>(OpaqueType::get());
return OPAQUE;
}
2001-06-07 04:29:01 +08:00
2001-06-07 04:29:01 +08:00
not { RET_TOK(UnaryOpVal, Not, NOT); }
add { RET_TOK(BinaryOpVal, Add, ADD); }
sub { RET_TOK(BinaryOpVal, Sub, SUB); }
mul { RET_TOK(BinaryOpVal, Mul, MUL); }
div { RET_TOK(BinaryOpVal, Div, DIV); }
rem { RET_TOK(BinaryOpVal, Rem, REM); }
and { RET_TOK(BinaryOpVal, And, AND); }
or { RET_TOK(BinaryOpVal, Or , OR ); }
xor { RET_TOK(BinaryOpVal, Xor, XOR); }
2001-06-07 04:29:01 +08:00
setne { RET_TOK(BinaryOpVal, SetNE, SETNE); }
seteq { RET_TOK(BinaryOpVal, SetEQ, SETEQ); }
setlt { RET_TOK(BinaryOpVal, SetLT, SETLT); }
setgt { RET_TOK(BinaryOpVal, SetGT, SETGT); }
setle { RET_TOK(BinaryOpVal, SetLE, SETLE); }
setge { RET_TOK(BinaryOpVal, SetGE, SETGE); }
phi { RET_TOK(OtherOpVal, PHINode, PHI); }
call { RET_TOK(OtherOpVal, Call, CALL); }
cast { RET_TOK(OtherOpVal, Cast, CAST); }
shl { RET_TOK(OtherOpVal, Shl, SHL); }
shr { RET_TOK(OtherOpVal, Shr, SHR); }
2001-06-07 04:29:01 +08:00
ret { RET_TOK(TermOpVal, Ret, RET); }
br { RET_TOK(TermOpVal, Br, BR); }
switch { RET_TOK(TermOpVal, Switch, SWITCH); }
invoke { RET_TOK(TermOpVal, Invoke, INVOKE); }
2001-06-07 04:29:01 +08:00
malloc { RET_TOK(MemOpVal, Malloc, MALLOC); }
alloca { RET_TOK(MemOpVal, Alloca, ALLOCA); }
free { RET_TOK(MemOpVal, Free, FREE); }
load { RET_TOK(MemOpVal, Load, LOAD); }
store { RET_TOK(MemOpVal, Store, STORE); }
getelementptr { RET_TOK(MemOpVal, GetElementPtr, GETELEMENTPTR); }
2001-06-07 04:29:01 +08:00
{VarID} {
UnEscapeLexed(yytext+1);
llvmAsmlval.StrVal = strdup(yytext+1); // Skip %
return VAR_ID;
}
{Label} {
2001-06-07 04:29:01 +08:00
yytext[strlen(yytext)-1] = 0; // nuke colon
UnEscapeLexed(yytext);
llvmAsmlval.StrVal = strdup(yytext);
2001-06-07 04:29:01 +08:00
return LABELSTR;
}
{StringConstant} { // Note that we cannot unescape a string constant here! The
// string constant might contain a \00 which would not be
// understood by the string stuff. It is valid to make a
// [sbyte] c"Hello World\00" constant, for example.
//
2001-06-07 04:29:01 +08:00
yytext[strlen(yytext)-1] = 0; // nuke end quote
llvmAsmlval.StrVal = strdup(yytext+1); // Nuke start quote
2001-06-07 04:29:01 +08:00
return STRINGCONSTANT;
}
2001-06-07 04:29:01 +08:00
{PInteger} { llvmAsmlval.UInt64Val = atoull(yytext); return EUINT64VAL; }
{NInteger} {
uint64_t Val = atoull(yytext+1);
// +1: we have bigger negative range
if (Val > (uint64_t)INT64_MAX+1)
ThrowException("Constant too large for signed 64 bits!");
llvmAsmlval.SInt64Val = -Val;
return ESINT64VAL;
}
{EPInteger} { llvmAsmlval.UIntVal = atoull(yytext+1); return UINTVAL; }
{ENInteger} {
uint64_t Val = atoull(yytext+2);
// +1: we have bigger negative range
if (Val > (uint64_t)INT32_MAX+1)
ThrowException("Constant too large for signed 32 bits!");
llvmAsmlval.SIntVal = -Val;
return SINTVAL;
}
{FPConstant} { llvmAsmlval.FPVal = atof(yytext); return FPVAL; }
2001-06-07 04:29:01 +08:00
[ \t\n] { /* Ignore whitespace */ }
. { return yytext[0]; }
2001-06-07 04:29:01 +08:00
%%