path: root/examples/Kaleidoscope/Chapter6/toy.cpp

#include "llvm/DerivedTypes.h"
#include "llvm/ExecutionEngine/ExecutionEngine.h"
#include "llvm/ExecutionEngine/JIT.h"
#include "llvm/LLVMContext.h"
#include "llvm/Module.h"
#include "llvm/PassManager.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Target/TargetData.h"
#include "llvm/Target/TargetSelect.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Support/IRBuilder.h"
#include <cstdio>
#include <string>
#include <map>
#include <vector>
using namespace llvm;

//===----------------------------------------------------------------------===//
// Lexer
//===----------------------------------------------------------------------===//

// The lexer returns tokens [0-255] if it is an unknown character, otherwise one
// of these for known things.
enum Token {
  tok_eof = -1,

  // commands
  tok_def = -2, tok_extern = -3,

  // primary
  tok_identifier = -4, tok_number = -5,
  
  // control
  tok_if = -6, tok_then = -7, tok_else = -8,
  tok_for = -9, tok_in = -10,
  
  // operators
  tok_binary = -11, tok_unary = -12
};

static std::string IdentifierStr;  // Filled in if tok_identifier
static double NumVal;              // Filled in if tok_number

/// gettok - Return the next token from standard input.
static int gettok() {
  static int LastChar = ' ';

  // Skip any whitespace.
  while (isspace(LastChar))
    LastChar = getchar();

  if (isalpha(LastChar)) { // identifier: [a-zA-Z][a-zA-Z0-9]*
    IdentifierStr = LastChar;
    while (isalnum((LastChar = getchar())))
      IdentifierStr += LastChar;

    if (IdentifierStr == "def") return tok_def;
    if (IdentifierStr == "extern") return tok_extern;
    if (IdentifierStr == "if") return tok_if;
    if (IdentifierStr == "then") return tok_then;
    if (IdentifierStr == "else") return tok_else;
    if (IdentifierStr == "for") return tok_for;
    if (IdentifierStr == "in") return tok_in;
    if (IdentifierStr == "binary") return tok_binary;
    if (IdentifierStr == "unary") return tok_unary;
    return tok_identifier;
  }

  if (isdigit(LastChar) || LastChar == '.') {   // Number: [0-9.]+
    std::string NumStr;
    do {
      NumStr += LastChar;
      LastChar = getchar();
    } while (isdigit(LastChar) || LastChar == '.');

    NumVal = strtod(NumStr.c_str(), 0);
    return tok_number;
  }

  if (LastChar == '#') {
    // Comment until end of line.
    do LastChar = getchar();
    while (LastChar != EOF && LastChar != '\n' && LastChar != '\r');
    
    if (LastChar != EOF)
      return gettok();
  }
  
  // Check for end of file.  Don't eat the EOF.
  if (LastChar == EOF)
    return tok_eof;

  // Otherwise, just return the character as its ascii value.
  int ThisChar = LastChar;
  LastChar = getchar();
  return ThisChar;
}

//===----------------------------------------------------------------------===//
// Abstract Syntax Tree (aka Parse Tree)
//===----------------------------------------------------------------------===//

/// ExprAST - Base class for all expression nodes.
class ExprAST {
public:
  virtual ~ExprAST() {}
  virtual Value *Codegen() = 0;
};

/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
  double Val;
public:
  NumberExprAST(double val) : Val(val) {}
  virtual Value *Codegen();
};

/// VariableExprAST - Expression class for referencing a variable, like "a".
class VariableExprAST : public ExprAST {
  std::string Name;
public:
  VariableExprAST(const std::string &name) : Name(name) {}
  virtual Value *Codegen();
};

/// UnaryExprAST - Expression class for a unary operator.
class UnaryExprAST : public ExprAST {
  char Opcode;
  ExprAST *Operand;
public:
  UnaryExprAST(char opcode, ExprAST *operand) 
    : Opcode(opcode), Operand(operand) {}
  virtual Value *Codegen();
};

/// BinaryExprAST - Expression class for a binary operator.
class BinaryExprAST : public ExprAST {
  char Op;
  ExprAST *LHS, *RHS;
public:
  BinaryExprAST(char op, ExprAST *lhs, ExprAST *rhs) 
    : Op(op), LHS(lhs),