llvm/examples/Kaleidoscope/Chapter8/toy.cpp

#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Triple.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/ExecutionEngine/ExecutionEngine.h"
#include "llvm/ExecutionEngine/MCJIT.h"
#include "llvm/ExecutionEngine/SectionMemoryManager.h"
#include "llvm/IR/DIBuilder.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Verifier.h"
#include "llvm/Support/Host.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Transforms/Scalar.h"
#include <cctype>
#include <cstdio>
#include <iostream>
#include <map>
#include <string>
#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,

  // var definition
  tok_var = -13
};

std::string getTokName(int Tok) {
  switch (Tok) {
  case tok_eof:
    return "eof";
  case tok_def:
    return "def";
  case tok_extern:
    return "extern";
  case tok_identifier:
    return "identifier";
  case tok_number:
    return "number";
  case tok_if:
    return "if";
  case tok_then:
    return "then";
  case tok_else:
    return "else";
  case tok_for:
    return "for";
  case tok_in:
    return "in";
  case tok_binary:
    return "binary";
  case tok_unary:
    return "unary";
  case tok_var:
    return "var";
  }
  return std::string(1, (char)Tok);
}

namespace {
class PrototypeAST;
class ExprAST;
}
static IRBuilder<> Builder(getGlobalContext());
struct DebugInfo {
  DICompileUnit *TheCU;
  DIType *DblTy;
  std::vector<DIScope *> LexicalBlocks;
  std::map<const PrototypeAST *, DIScope *> FnScopeMap;

  void emitLocation(ExprAST *AST);
  DIType *getDoubleTy();
} KSDbgInfo;

static std::string IdentifierStr; // Filled in if tok_identifier
static double NumVal;             // Filled in if tok_number
struct SourceLocation {
  int Line;
  int Col;
};
static SourceLocation CurLoc;
static SourceLocation LexLoc = { 1, 0 };

static int advance() {
  int LastChar = getchar();

  if (LastChar == '\n' || LastChar == '\r') {
    LexLoc.Line++;
    LexLoc.Col = 0;
  } else
    LexLoc.Col++;
  return LastChar;
}

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

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

  CurLoc = LexLoc;

  if (isalpha(LastChar)) { // identifier: [a-zA-Z][a-zA-Z0-9]*
    IdentifierStr = LastChar;
    while (isalnum((LastChar = advance())))
      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;
    if (IdentifierStr == "var")
      return tok_var;
    return tok_identifier;
  }

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

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

  if (LastChar == '#') {
    // Comment until end of line.
    do
      LastChar = advance();
    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 = advance();
  return ThisChar;
}

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

std::ostream &indent(std::ostream &O, int size) {
  return O << std::string(size, ' ');
}

/// ExprAST - Base class for all expression nodes.
class ExprAST {
  SourceLocation Loc;
public:
  int getLine() const { return Loc.Line; }
  int getCol() const { return Loc.Col; }
  ExprAST(SourceLocation Loc = CurLoc) : Loc(Loc) {}
  virtual std::ostream &dump(std::ostream &out, int ind) {
    return out << ':' << getLine() << ':' << getCol() << '\n';
  }
  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) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    return ExprAST::dump(out << Val, ind);
  }
  Value *Codegen() override;
};

/// VariableExprAST - Expression class for referencing a variable, like "a".
class VariableExprAST : public ExprAST {
  std::string Name;
public:
  VariableExprAST(SourceLocation Loc, const std::string &Name)
      : ExprAST(Loc), Name(Name) {}
  const std::string &getName() const { return Name; }
  std::ostream &dump(std::ostream &out, int ind) override {
    return ExprAST::dump(out << Name, ind);
  }
  Value *Codegen() override;
};

/// UnaryExprAST - Expression class for a unary operator.
class UnaryExprAST : public ExprAST {
  char Opcode;
  std::unique_ptr<ExprAST> Operand;
public:
  UnaryExprAST(char Opcode, std::unique_ptr<ExprAST> Operand)
      : Opcode(Opcode), Operand(std::move(Operand)) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    ExprAST::dump(out << "unary" << Opcode, ind);
    Operand->dump(out, ind + 1);
    return out;
  }
  Value *Codegen() override;
};

/// BinaryExprAST - Expression class for a binary operator.
class BinaryExprAST : public ExprAST {
  char Op;
  std::unique_ptr<ExprAST> LHS, RHS;
public:
  BinaryExprAST(SourceLocation Loc, char Op, std::unique_ptr<ExprAST> LHS,
                std::unique_ptr<ExprAST> RHS)
      : ExprAST(Loc), Op(Op), LHS(std::move(LHS)), RHS(std::move(RHS)) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    ExprAST::dump(out << "binary" << Op, ind);
    LHS->dump(indent(out, ind) << "LHS:", ind + 1);
    RHS->dump(indent(out, ind) << "RHS:", ind + 1);
    return out;
  }
  Value *Codegen() override;
};

/// CallExprAST - Expression class for function calls.
class CallExprAST : public ExprAST {
  std::string Callee;
  std::vector<std::unique_ptr<ExprAST>> Args;
public:
  CallExprAST(SourceLocation Loc, const std::string &Callee,
              std::vector<std::unique_ptr<ExprAST>> Args)
      : ExprAST(Loc), Callee(Callee), Args(std::move(Args)) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    ExprAST::dump(out << "call " << Callee, ind);
    for (const auto &Arg : Args)
      Arg->dump(indent(out, ind + 1), ind + 1);
    return out;
  }
  Value *Codegen() override;
};

/// IfExprAST - Expression class for if/then/else.
class IfExprAST : public ExprAST {
  std::unique_ptr<ExprAST> Cond, Then, Else;
public:
  IfExprAST(SourceLocation Loc, std::unique_ptr<ExprAST> Cond,
            std::unique_ptr<ExprAST> Then, std::unique_ptr<ExprAST> Else)
    : ExprAST(Loc), Cond(std::move(Cond)), Then(std::move(Then)), Else(std::move(Else)) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    ExprAST::dump(out << "if", ind);
    Cond->dump(indent(out, ind) << "Cond:", ind + 1);
    Then->dump(indent(out, ind) << "Then:", ind + 1);
    Else->dump(indent(out, ind) << "Else:", ind + 1);
    return out;
  }
  Value *Codegen() override;
};

/// ForExprAST - Expression class for for/in.
class ForExprAST : public ExprAST {
  std::string VarName;
  std::unique_ptr<ExprAST> Start, End, Step, Body;
public:
  ForExprAST(const std::string &VarName, std::unique_ptr<ExprAST> Start,
             std::unique_ptr<ExprAST> End, std::unique_ptr<ExprAST> Step,
             std::unique_ptr<ExprAST> Body)
      : VarName(VarName), Start(std::move(Start)), End(std::move(End)),
        Step(std::move(Step)), Body(std::move(Body)) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    ExprAST::dump(out << "for", ind);
    Start->dump(indent(out, ind) << "Cond:", ind + 1);
    End->dump(indent(out, ind) << "End:", ind + 1);
    Step->dump(indent(out, ind) << "Step:", ind + 1);
    Body->dump(indent(out, ind) << "Body:", ind + 1);
    return out;
  }
  Value *Codegen() override;
};

/// VarExprAST - Expression class for var/in
class VarExprAST : public ExprAST {
  std::vector<std::pair<std::string, std::unique_ptr<ExprAST>>> VarNames;
  std::unique_ptr<ExprAST> Body;
public:
  VarExprAST(std::vector<std::pair<std::string, std::unique_ptr<ExprAST>>> VarNames,
             std::unique_ptr<ExprAST> Body)
      : VarNames(std::move(VarNames)), Body(std::move(Body)) {}
  std::ostream &dump(std::ostream &out, int ind) override {
    ExprAST::dump(out << "var", ind);
    for (const auto &NamedVar : VarNames)
      NamedVar.second->dump(indent(out, ind) << NamedVar.first << ':', ind + 1);
    Body->dump(indent(out, ind) << "Body:", ind + 1);
    return out;
  }
  Value *Codegen() override;
};

/// PrototypeAST - This class represents the "prototype" for a function,
/// which captures its argument names as well as if it is an operator.
class PrototypeAST {
  std::string Name;
  std::vector<std::string> Args;
  bool IsOperator;
  unsigned Precedence; // Precedence if a binary op.
  int Line;
public:
  PrototypeAST(SourceLocation Loc, const std::string &Name,
               std::vector<std::string> Args, bool IsOperator = false,
               unsigned Prec = 0)
    : Name(Name), Args(std::move(Args)), IsOperator(IsOperator),
      Precedence(Prec), Line(Loc.Line) {}

  bool isUnaryOp() const { return IsOperator && Args.size() == 1; }
  bool isBinaryOp() const { return IsOperator && Args.size() == 2; }

  char getOperatorName() const {
    assert(isUnaryOp() || isBinaryOp());
    return Name[Name.size() - 1];
  }

  unsigned getBinaryPrecedence() const { return Precedence; }

  Function *Codegen();

  void CreateArgumentAllocas(Function *F);
  const std::vector<std::string> &getArgs() const { return Args; }
};

/// FunctionAST - This class represents a function definition itself.
class FunctionAST {
  std::unique_ptr<PrototypeAST> Proto;
  std::unique_ptr<ExprAST> Body;
public:
  FunctionAST(std::unique_ptr<PrototypeAST> Proto,
              std::unique_ptr<ExprAST> Body)
      : Proto(std::move(Proto)), Body(std::move(Body)) {}

  std::ostream &dump(std::ostream &out, int ind) {
    indent(out, ind) << "FunctionAST\n";
    ++ind;
    indent(out, ind) << "Body:";
    return Body ? Body->dump(out, ind) : out << "null\n";
  }

  Function *Codegen();
};
} // end anonymous namespace

//===----------------------------------------------------------------------===//
// Parser
//===----------------------------------------------------------------------===//

/// CurTok/getNextToken - Provide a simple token buffer.  CurTok is the current
/// token the parser is looking at.  getNextToken reads another token from the
/// lexer and updates CurTok with its results.
static int CurTok;
static int getNextToken() { return CurTok = gettok(); }

/// BinopPrecedence - This holds the precedence for each binary operator that is
/// defined.
static std::map<char, int> BinopPrecedence;

/// GetTokPrecedence - Get the precedence of the pending binary operator token.
static int GetTokPrecedence() {
  if (!isascii(CurTok))
    return -1;

  // Make sure it's a declared binop.
  int TokPrec = BinopPrecedence[CurTok];
  if (TokPrec <= 0)
    return -1;
  return TokPrec;
}

/// Error* - These are little helper functions for error handling.
std::unique_ptr<ExprAST> Error(const char *Str) {
  fprintf(stderr, "Error: %s\n", Str);
  return nullptr;
}
std::unique_ptr<PrototypeAST> ErrorP(const char *Str) {
  Error(Str);
  return nullptr;
}
std::unique_ptr<FunctionAST> ErrorF(const char *Str) {
  Error(Str);
  return nullptr;
}

static std::unique_ptr<ExprAST> ParseExpression();

/// identifierexpr
///   ::= identifier
///   ::= identifier '(' expression* ')'
  static std::unique_ptr<ExprAST> ParseIdentifierExpr() {
  std::string IdName = IdentifierStr;

  SourceLocation LitLoc = CurLoc;

  getNextToken(); // eat identifier.

  if (CurTok != '(') // Simple variable ref.
    return llvm::make_unique<VariableExprAST>(LitLoc, IdName);

  // Call.
  getNextToken(); // eat (
  std::vector<std::unique_ptr<ExprAST>> Args;
  if (CurTok != ')') {
    while (1) {
      auto Arg = ParseExpression();
      if (!Arg)
        return nullptr;
      Args.push_back(std::move(Arg));

      if (CurTok == ')')
        break;

      if (CurTok != ',')
        return Error("Expected ')' or ',' in argument list");
      getNextToken();
    }
  }

  // Eat the ')'.
  getNextToken();

  return llvm::make_unique<CallExprAST>(LitLoc, IdName, std::move(Args));
}

/// numberexpr ::= number
static std::unique_ptr<ExprAST> ParseNumberExpr() {
  auto Result = llvm::make_unique<NumberExprAST>(NumVal);
  getNextToken(); // consume the number
  return std::move(Result);
}

/// parenexpr ::= '(' expression ')'
static std::unique_ptr<ExprAST> ParseParenExpr() {
  getNextToken(); // eat (.
  auto V = ParseExpression();
  if (!V)
    return nullptr;

  if (CurTok != ')')
    return Error("expected ')'");
  getNextToken(); // eat ).
  return V;
}

/// ifexpr ::= 'if' expression 'then' expression 'else' expression
static std::unique_ptr<ExprAST> ParseIfExpr() {
  SourceLocation IfLoc = CurLoc;

  getNextToken(); // eat the if.

  // condition.
  auto Cond = ParseExpression();
  if (!Cond)
    return nullptr;

  if (CurTok != tok_then)
    return Error("expected then");
  getNextToken(); // eat the then

  auto Then = ParseExpression();
  if (!Then)
    return nullptr;

  if (CurTok != tok_else)
    return Error("expected else");

  getNextToken();

  auto Else = ParseExpression();
  if (!Else)
    return nullptr;

  return llvm::make_unique<IfExprAST>(IfLoc, std::move(Cond), std::move(Then),
                                      std::move(Else));
}

/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression
static std::unique_ptr<ExprAST> ParseForExpr() {
  getNextToken(); // eat the for.

  if (CurTok != tok_identifier)
    return Error("expected identifier after for");

  std::string IdName = IdentifierStr;
  getNextToken(); // eat identifier.

  if (CurTok != '=')
    return Error("expected '=' after for");
  getNextToken(); // eat '='.

  auto Start = ParseExpression();
  if (!Start)
    return nullptr;
  if (CurTok != ',')
    return Error("expected ',' after for start value");
  getNextToken();

  auto End = ParseExpression();
  if (!End)
    return nullptr;

  // The step value is optional.
  std::unique_ptr<ExprAST> Step;
  if (CurTok == ',') {
    getNextToken();
    Step = ParseExpression();
    if (!Step)
      return nullptr;
  }

  if (CurTok != tok_in)
    return Error("expected 'in' after for");
  getNextToken(); // eat 'in'.

  auto Body = ParseExpression();
  if (!Body)
    return nullptr;

  return llvm::make_unique<ForExprAST>(IdName, std::move(Start), std::move(End),
                                       std::move(Step), std::move(Body));
}

/// varexpr ::= 'var' identifier ('=' expression)?
//                    (',' identifier ('=' expression)?)* 'in' expression
static std::unique_ptr<ExprAST> ParseVarExpr() {
  getNextToken(); // eat the var.

  std::vector<std::pair<std::string, std::unique_ptr<ExprAST>>> VarNames;

  // At least one variable name is required.
  if (CurTok != tok_identifier)
    return Error("expected identifier after var");

  while (1) {
    std::string Name = IdentifierStr;
    getNextToken(); // eat identifier.

    // Read the optional initializer.
    std::unique_ptr<ExprAST> Init = nullptr;
    if (CurTok == '=') {
      getNextToken(); // eat the '='.

      Init = ParseExpression();
      if (!Init)
        return nullptr;
    }

    VarNames.push_back(std::make_pair(Name, std::move(Init)));

    // End of var list, exit loop.
    if (CurTok != ',')
      break;
    getNextToken(); // eat the ','.

    if (CurTok != tok_identifier)
      return Error("expected identifier list after var");
  }

  // At this point, we have to have 'in'.
  if (CurTok != tok_in)
    return Error("expected 'in' keyword after 'var'");
  getNextToken(); // eat 'in'.

  auto Body = ParseExpression();
  if (!Body)
    return nullptr;

  return llvm::make_unique<VarExprAST>(std::move(VarNames), std::move(Body));
}

/// primary
///   ::= identifierexpr
///   ::= numberexpr
///   ::= parenexpr
///   ::= ifexpr
///   ::= forexpr
///   ::= varexpr
static std::unique_ptr<ExprAST> ParsePrimary() {
  switch (CurTok) {
  default:
    return Error("unknown token when expecting an expression");
  case tok_identifier:
    return ParseIdentifierExpr();
  case tok_number:
    return ParseNumberExpr();
  case '(':
    return ParseParenExpr();
  case tok_if:
    return ParseIfExpr();
  case tok_for:
    return ParseForExpr();
  case tok_var:
    return ParseVarExpr();
  }
}

/// unary
///   ::= primary
///   ::= '!' unary
static std::unique_ptr<ExprAST> ParseUnary() {
  // If the current token is not an operator, it must be a primary expr.
  if (!isascii(CurTok) || CurTok == '(' || CurTok == ',')
    return ParsePrimary();

  // If this is a unary operator, read it.
  int Opc = CurTok;
  getNextToken();
  if (auto Operand = ParseUnary())
    return llvm::make_unique<UnaryExprAST>(Opc, std::move(Operand));
  return nullptr;
}

/// binoprhs
///   ::= ('+' unary)*
static std::unique_ptr<ExprAST> ParseBinOpRHS(int ExprPrec, std::unique_ptr<ExprAST> LHS) {
  // If this is a binop, find its precedence.
  while (1) {
    int TokPrec = GetTokPrecedence();

    // If this is a binop that binds at least as tightly as the current binop,
    // consume it, otherwise we are done.
    if (TokPrec < ExprPrec)
      return LHS;

    // Okay, we know this is a binop.
    int BinOp = CurTok;
    SourceLocation BinLoc = CurLoc;
    getNextToken(); // eat binop

    // Parse the unary expression after the binary operator.
    auto RHS = ParseUnary();
    if (!RHS)
      return nullptr;

    // If BinOp binds less tightly with RHS than the operator after RHS, let
    // the pending operator take RHS as its LHS.
    int NextPrec = GetTokPrecedence();
    if (TokPrec < NextPrec) {
      RHS = ParseBinOpRHS(TokPrec + 1, std::move(RHS));
      if (!RHS)
        return nullptr;
    }

    // Merge LHS/RHS.
    LHS = llvm::make_unique<BinaryExprAST>(BinLoc, BinOp, std::move(LHS),
                                           std::move(RHS));
  }
}

/// expression
///   ::= unary binoprhs
///
static std::unique_ptr<ExprAST> ParseExpression() {
  auto LHS = ParseUnary();
  if (!LHS)
    return nullptr;

  return ParseBinOpRHS(0, std::move(LHS));
}

/// prototype
///   ::= id '(' id* ')'
///   ::= binary LETTER number? (id, id)
///   ::= unary LETTER (id)
static std::unique_ptr<PrototypeAST> ParsePrototype() {
  std::string FnName;

  SourceLocation FnLoc = CurLoc;

  unsigned Kind = 0; // 0 = identifier, 1 = unary, 2 = binary.
  unsigned BinaryPrecedence = 30;

  switch (CurTok) {
  default:
    return ErrorP("Expected function name in prototype");
  case tok_identifier:
    FnName = IdentifierStr;
    Kind = 0;
    getNextToken();
    break;
  case tok_unary:
    getNextToken();
    if (!isascii(CurTok))
      return ErrorP("Expected unary operator");
    FnName = "unary";
    FnName += (char)CurTok;
    Kind = 1;
    getNextToken();
    break;
  case tok_binary:
    getNextToken();
    if (!isascii(CurTok))
      return ErrorP("Expected binary operator");
    FnName = "binary";
    FnName += (char)CurTok;
    Kind = 2;
    getNextToken();

    // Read the precedence if present.
    if (CurTok == tok_number) {
      if (NumVal < 1 || NumVal > 100)
        return ErrorP("Invalid precedecnce: must be 1..100");
      BinaryPrecedence = (unsigned)NumVal;
      getNextToken();
    }
    break;
  }

  if (CurTok != '(')
    return ErrorP("Expected '(' in prototype");

  std::vector<std::string> ArgNames;
  while (getNextToken() == tok_identifier)
    ArgNames.push_back(IdentifierStr);
  if (CurTok != ')')
    return ErrorP("Expected ')' in prototype");

  // success.
  getNextToken(); // eat ')'.

  // Verify right number of names for operator.
  if (Kind && ArgNames.size() != Kind)
    return ErrorP("Invalid number of operands for operator");

  return llvm::make_unique<PrototypeAST>(FnLoc, FnName, ArgNames, Kind != 0,
                                         BinaryPrecedence);
}

/// definition ::= 'def' prototype expression
static std::unique_ptr<FunctionAST> ParseDefinition() {
  getNextToken(); // eat def.
  auto Proto = ParsePrototype();
  if (!Proto)
    return nullptr;

  if (auto E = ParseExpression())
    return llvm::make_unique<FunctionAST>(std::move(Proto), std::move(E));
  return nullptr;
}

/// toplevelexpr ::= expression
static std::unique_ptr<FunctionAST> ParseTopLevelExpr() {
  SourceLocation FnLoc = CurLoc;
  if (auto E = ParseExpression()) {
    // Make an anonymous proto.
    auto Proto =
      llvm::make_unique<PrototypeAST>(FnLoc, "main", std::vector<std::string>());
    return llvm::make_unique<FunctionAST>(std::move(Proto), std::move(E));
  }
  return nullptr;
}

/// external ::= 'extern' prototype
static std::unique_ptr<PrototypeAST> ParseExtern() {
  getNextToken(); // eat extern.
  return ParsePrototype();
}

//===----------------------------------------------------------------------===//
// Debug Info Support
//===----------------------------------------------------------------------===//

static DIBuilder *DBuilder;

DIType *DebugInfo::getDoubleTy() {
  if (DblTy)
    return DblTy;

  DblTy = DBuilder->createBasicType("double", 64, 64, dwarf::DW_ATE_float);
  return DblTy;
}

void DebugInfo::emitLocation(ExprAST *AST) {
  if (!AST)
    return Builder.SetCurrentDebugLocation(DebugLoc());
  DIScope *Scope;
  if (LexicalBlocks.empty())
    Scope = TheCU;
  else
    Scope = LexicalBlocks.back();
  Builder.SetCurrentDebugLocation(
      DebugLoc::get(AST->getLine(), AST->getCol(), Scope));
}

static DISubroutineType *CreateFunctionType(unsigned NumArgs, DIFile *Unit) {
  SmallVector<Metadata *, 8> EltTys;
  DIType *DblTy = KSDbgInfo.getDoubleTy();

  // Add the result type.
  EltTys.push_back(DblTy);

  for (unsigned i = 0, e = NumArgs; i != e; ++i)
    EltTys.push_back(DblTy);

  return DBuilder->createSubroutineType(Unit,
                                        DBuilder->getOrCreateTypeArray(EltTys));
}

//===----------------------------------------------------------------------===//
// Code Generation
//===----------------------------------------------------------------------===//

static Module *TheModule;
static std::map<std::string, AllocaInst *> NamedValues;
static legacy::FunctionPassManager *TheFPM;

Value *ErrorV(const char *Str) {
  Error(Str);
  return nullptr;
}

/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of
/// the function.  This is used for mutable variables etc.
static AllocaInst *CreateEntryBlockAlloca(Function *TheFunction,
                                          const std::string &VarName) {
  IRBuilder<> TmpB(&TheFunction->getEntryBlock(),
                   TheFunction->getEntryBlock().begin());
  return TmpB.CreateAlloca(Type::getDoubleTy(getGlobalContext()), 0,
                           VarName.c_str());
}

Value *NumberExprAST::Codegen() {
  KSDbgInfo.emitLocation(this);
  return ConstantFP::get(getGlobalContext(), APFloat(Val));
}

Value *VariableExprAST::Codegen() {
  // Look this variable up in the function.
  Value *V = NamedValues[Name];
  if (!V)
    return ErrorV("Unknown variable name");

  KSDbgInfo.emitLocation(this);
  // Load the value.
  return Builder.CreateLoad(V, Name.c_str());
}

Value *UnaryExprAST::Codegen() {
  Value *OperandV = Operand->Codegen();
  if (!OperandV)
    return nullptr;

  Function *F = TheModule->getFunction(std::string("unary") + Opcode);
  if (!F)
    return ErrorV("Unknown unary operator");

  KSDbgInfo.emitLocation(this);
  return Builder.CreateCall(F, OperandV, "unop");
}

Value *BinaryExprAST::Codegen() {
  KSDbgInfo.emitLocation(this);

  // Special case '=' because we don't want to emit the LHS as an expression.
  if (Op == '=') {
    // Assignment requires the LHS to be an identifier.
    // This assume we're building without RTTI because LLVM builds that way by
    // default.  If you build LLVM with RTTI this can be changed to a
    // dynamic_cast for automatic error checking.
    VariableExprAST *LHSE = static_cast<VariableExprAST*>(LHS.get());
    if (!LHSE)
      return ErrorV("destination of '=' must be a variable");
    // Codegen the RHS.
    Value *Val = RHS->Codegen();
    if (!Val)
      return nullptr;

    // Look up the name.
    Value *Variable = NamedValues[LHSE->getName()];
    if (!Variable)
      return ErrorV("Unknown variable name");

    Builder.CreateStore(Val, Variable);
    return Val;
  }

  Value *L = LHS->Codegen();
  Value *R = RHS->Codegen();
  if (!L || !R)
    return nullptr;

  switch (Op) {
  case '+':
    return Builder.CreateFAdd(L, R, "addtmp");
  case '-':
    return Builder.CreateFSub(L, R, "subtmp");
  case '*':
    return Builder.CreateFMul(L, R, "multmp");
  case '<':
    L = Builder.CreateFCmpULT(L, R, "cmptmp");
    // Convert bool 0/1 to double 0.0 or 1.0
    return Builder.CreateUIToFP(L, Type::getDoubleTy(getGlobalContext()),
                                "booltmp");
  default:
    break;
  }

  // If it wasn't a builtin binary operator, it must be a user defined one. Emit
  // a call to it.
  Function *F = TheModule->getFunction(std::string("binary") + Op);
  assert(F && "binary operator not found!");

  Value *Ops[] = { L, R };
  return Builder.CreateCall(F, Ops, "binop");
}

Value *CallExprAST::Codegen() {
  KSDbgInfo.emitLocation(this);

  // Look up the name in the global module table.
  Function *CalleeF = TheModule->getFunction(Callee);
  if (!CalleeF)
    return ErrorV("Unknown function referenced");

  // If argument mismatch error.
  if (CalleeF->arg_size() != Args.size())
    return ErrorV("Incorrect # arguments passed");

  std::vector<Value *> ArgsV;
  for (unsigned i = 0, e = Args.size(); i != e; ++i) {
    ArgsV.push_back(Args[i]->Codegen());
    if (!ArgsV.back())
      return nullptr;
  }

  return Builder.CreateCall(CalleeF, ArgsV, "calltmp");
}

Value *IfExprAST::Codegen() {
  KSDbgInfo.emitLocation(this);

  Value *CondV = Cond->Codegen();
  if (!CondV)
    return nullptr;

  // Convert condition to a bool by comparing equal to 0.0.
  CondV = Builder.CreateFCmpONE(
      CondV, ConstantFP::get(getGlobalContext(), APFloat(0.0)), "ifcond");

  Function *TheFunction = Builder.GetInsertBlock()->getParent();

  // Create blocks for the then and else cases.  Insert the 'then' block at the
  // end of the function.
  BasicBlock *ThenBB =
      BasicBlock::Create(getGlobalContext(), "then", TheFunction);
  BasicBlock *ElseBB = BasicBlock::Create(getGlobalContext(), "else");
  BasicBlock *MergeBB = BasicBlock::Create(getGlobalContext(), "ifcont");

  Builder.CreateCondBr(CondV, ThenBB, ElseBB);

  // Emit then value.
  Builder.SetInsertPoint(ThenBB);

  Value *ThenV = Then->Codegen();
  if (!ThenV)
    return nullptr;

  Builder.CreateBr(MergeBB);
  // Codegen of 'Then' can change the current block, update ThenBB for the PHI.
  ThenBB = Builder.GetInsertBlock();

  // Emit else block.
  TheFunction->getBasicBlockList().push_back(ElseBB);
  Builder.SetInsertPoint(ElseBB);

  Value *ElseV = Else->Codegen();
  if (!ElseV)
    return nullptr;

  Builder.CreateBr(MergeBB);
  // Codegen of 'Else' can change the current block, update ElseBB for the PHI.
  ElseBB = Builder.GetInsertBlock();

  // Emit merge block.
  TheFunction->getBasicBlockList().push_back(MergeBB);
  Builder.SetInsertPoint(MergeBB);
  PHINode *PN =
      Builder.CreatePHI(Type::getDoubleTy(getGlobalContext()), 2, "iftmp");

  PN->addIncoming(ThenV, ThenBB);
  PN->addIncoming(ElseV, ElseBB);
  return PN;
}

Value *ForExprAST::Codegen() {
  // Output this as:
  //   var = alloca double
  //   ...
  //   start = startexpr
  //   store start -> var
  //   goto loop
  // loop:
  //   ...
  //   bodyexpr
  //   ...
  // loopend:
  //   step = stepexpr
  //   endcond = endexpr
  //
  //   curvar = load var
  //   nextvar = curvar + step
  //   store nextvar -> var
  //   br endcond, loop, endloop
  // outloop:

  Function *TheFunction = Builder.GetInsertBlock()->getParent();

  // Create an alloca for the variable in the entry block.
  AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);

  KSDbgInfo.emitLocation(this);

  // Emit the start code first, without 'variable' in scope.
  Value *StartVal = Start->Codegen();
  if (!StartVal)
    return nullptr;

  // Store the value into the alloca.
  Builder.CreateStore(StartVal, Alloca);

  // Make the new basic block for the loop header, inserting after current
  // block.
  BasicBlock *LoopBB =
      BasicBlock::Create(getGlobalContext(), "loop", TheFunction);

  // Insert an explicit fall through from the current block to the LoopBB.
  Builder.CreateBr(LoopBB);

  // Start insertion in LoopBB.
  Builder.SetInsertPoint(LoopBB);

  // Within the loop, the variable is defined equal to the PHI node.  If it
  // shadows an existing variable, we have to restore it, so save it now.
  AllocaInst *OldVal = NamedValues[VarName];
  NamedValues[VarName] = Alloca;

  // Emit the body of the loop.  This, like any other expr, can change the
  // current BB.  Note that we ignore the value computed by the body, but don't
  // allow an error.
  if (!Body->Codegen())
    return nullptr;

  // Emit the step value.
  Value *StepVal;
  if (Step) {
    StepVal = Step->Codegen();
    if (!StepVal)
      return nullptr;
  } else {
    // If not specified, use 1.0.
    StepVal = ConstantFP::get(getGlobalContext(), APFloat(1.0));
  }

  // Compute the end condition.
  Value *EndCond = End->Codegen();
  if (!EndCond)
    return EndCond;

  // Reload, increment, and restore the alloca.  This handles the case where
  // the body of the loop mutates the variable.
  Value *CurVar = Builder.CreateLoad(Alloca, VarName.c_str());
  Value *NextVar = Builder.CreateFAdd(CurVar, StepVal, "nextvar");
  Builder.CreateStore(NextVar, Alloca);

  // Convert condition to a bool by comparing equal to 0.0.
  EndCond = Builder.CreateFCmpONE(
      EndCond, ConstantFP::get(getGlobalContext(), APFloat(0.0)), "loopcond");

  // Create the "after loop" block and insert it.
  BasicBlock *AfterBB =
      BasicBlock::Create(getGlobalContext(), "afterloop", TheFunction);

  // Insert the conditional branch into the end of LoopEndBB.
  Builder.CreateCondBr(EndCond, LoopBB, AfterBB);

  // Any new code will be inserted in AfterBB.
  Builder.SetInsertPoint(AfterBB);

  // Restore the unshadowed variable.
  if (OldVal)
    NamedValues[VarName] = OldVal;
  else
    NamedValues.erase(VarName);

  // for expr always returns 0.0.
  return Constant::getNullValue(Type::getDoubleTy(getGlobalContext()));
}

Value *VarExprAST::Codegen() {
  std::vector<AllocaInst *> OldBindings;

  Function *TheFunction = Builder.GetInsertBlock()->getParent();

  // Register all variables and emit their initializer.
  for (unsigned i = 0, e = VarNames.size(); i != e; ++i) {
    const std::string &VarName = VarNames[i].first;
    ExprAST *Init = VarNames[i].second.get();

    // Emit the initializer before adding the variable to scope, this prevents
    // the initializer from referencing the variable itself, and permits stuff
    // like this:
    //  var a = 1 in
    //    var a = a in ...   # refers to outer 'a'.
    Value *InitVal;
    if (Init) {
      InitVal = Init->Codegen();
      if (!InitVal)
        return nullptr;
    } else { // If not specified, use 0.0.
      InitVal = ConstantFP::get(getGlobalContext(), APFloat(0.0));
    }

    AllocaInst *Alloca = CreateEntryBlockAlloca(TheFunction, VarName);
    Builder.CreateStore(InitVal, Alloca);

    // Remember the old variable binding so that we can restore the binding when
    // we unrecurse.
    OldBindings.push_back(NamedValues[VarName]);

    // Remember this binding.
    NamedValues[VarName] = Alloca;
  }

  KSDbgInfo.emitLocation(this);

  // Codegen the body, now that all vars are in scope.
  Value *BodyVal = Body->Codegen();
  if (!BodyVal)
    return nullptr;

  // Pop all our variables from scope.
  for (unsigned i = 0, e = VarNames.size(); i != e; ++i)
    NamedValues[VarNames[i].first] = OldBindings[i];

  // Return the body computation.
  return BodyVal;
}

Function *PrototypeAST::Codegen() {
  // Make the function type:  double(double,double) etc.
  std::vector<Type *> Doubles(Args.size(),
                              Type::getDoubleTy(getGlobalContext()));
  FunctionType *FT =
      FunctionType::get(Type::getDoubleTy(getGlobalContext()), Doubles, false);

  Function *F =
      Function::Create(FT, Function::ExternalLinkage, Name, TheModule);

  // If F conflicted, there was already something named 'Name'.  If it has a
  // body, don't allow redefinition or reextern.
  if (F->getName() != Name) {
    // Delete the one we just made and get the existing one.
    F->eraseFromParent();
    F = TheModule->getFunction(Name);

    // If F already has a body, reject this.
    if (!F->empty()) {
      ErrorF("redefinition of function");
      return nullptr;
    }

    // If F took a different number of args, reject.
    if (F->arg_size() != Args.size()) {
      ErrorF("redefinition of function with different # args");
      return nullptr;
    }
  }

  // Set names for all arguments.
  unsigned Idx = 0;
  for (Function::arg_iterator AI = F->arg_begin(); Idx != Args.size();
       ++AI, ++Idx)
    AI->setName(Args[Idx]);

  // Create a subprogram DIE for this function.
  DIFile *Unit = DBuilder->createFile(KSDbgInfo.TheCU->getFilename(),
                                      KSDbgInfo.TheCU->getDirectory());
  DIScope *FContext = Unit;
  unsigned LineNo = Line;
  unsigned ScopeLine = Line;
  DISubprogram *SP = DBuilder->createFunction(
      FContext, Name, StringRef(), Unit, LineNo,
      CreateFunctionType(Args.size(), Unit), false /* internal linkage */,
      true /* definition */, ScopeLine, DINode::FlagPrototyped, false, F);

  KSDbgInfo.FnScopeMap[this] = SP;
  return F;
}

/// CreateArgumentAllocas - Create an alloca for each argument and register the
/// argument in the symbol table so that references to it will succeed.
void PrototypeAST::CreateArgumentAllocas(Function *F) {
  Function::arg_iterator AI = F->arg_begin();
  for (unsigned Idx = 0, e = Args.size(); Idx != e; ++Idx, ++AI) {
    // Create an alloca for this variable.
    AllocaInst *Alloca = CreateEntryBlockAlloca(F, Args[Idx]);

    // Create a debug descriptor for the variable.
    DIScope *Scope = KSDbgInfo.LexicalBlocks.back();
    DIFile *Unit = DBuilder->createFile(KSDbgInfo.TheCU->getFilename(),
                                        KSDbgInfo.TheCU->getDirectory());
    DILocalVariable *D = DBuilder->createParameterVariable(
        Scope, Args[Idx], Idx + 1, Unit, Line, KSDbgInfo.getDoubleTy(), true);

    DBuilder->insertDeclare(Alloca, D, DBuilder->createExpression(),
                            DebugLoc::get(Line, 0, Scope),
                            Builder.GetInsertBlock());

    // Store the initial value into the alloca.
    Builder.CreateStore(AI, Alloca);

    // Add arguments to variable symbol table.
    NamedValues[Args[Idx]] = Alloca;
  }
}

Function *FunctionAST::Codegen() {
  NamedValues.clear();

  Function *TheFunction = Proto->Codegen();
  if (!TheFunction)
    return nullptr;

  // Push the current scope.
  KSDbgInfo.LexicalBlocks.push_back(KSDbgInfo.FnScopeMap[Proto.get()]);

  // Unset the location for the prologue emission (leading instructions with no
  // location in a function are considered part of the prologue and the debugger
  // will run past them when breaking on a function)
  KSDbgInfo.emitLocation(nullptr);

  // If this is an operator, install it.
  if (Proto->isBinaryOp())
    BinopPrecedence[Proto->getOperatorName()] = Proto->getBinaryPrecedence();

  // Create a new basic block to start insertion into.
  BasicBlock *BB = BasicBlock::Create(getGlobalContext(), "entry", TheFunction);
  Builder.SetInsertPoint(BB);

  // Add all arguments to the symbol table and create their allocas.
  Proto->CreateArgumentAllocas(TheFunction);

  KSDbgInfo.emitLocation(Body.get());

  if (Value *RetVal = Body->Codegen()) {
    // Finish off the function.
    Builder.CreateRet(RetVal);

    // Pop off the lexical block for the function.
    KSDbgInfo.LexicalBlocks.pop_back();

    // Validate the generated code, checking for consistency.
    verifyFunction(*TheFunction);

    // Optimize the function.
    TheFPM->run(*TheFunction);

    return TheFunction;
  }

  // Error reading body, remove function.
  TheFunction->eraseFromParent();

  if (Proto->isBinaryOp())
    BinopPrecedence.erase(Proto->getOperatorName());

  // Pop off the lexical block for the function since we added it
  // unconditionally.
  KSDbgInfo.LexicalBlocks.pop_back();

  return nullptr;
}

//===----------------------------------------------------------------------===//
// Top-Level parsing and JIT Driver
//===----------------------------------------------------------------------===//

static ExecutionEngine *TheExecutionEngine;

static void HandleDefinition() {
  if (auto FnAST = ParseDefinition()) {
    if (!FnAST->Codegen()) {
      fprintf(stderr, "Error reading function definition:");
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleExtern() {
  if (auto ProtoAST = ParseExtern()) {
    if (!ProtoAST->Codegen()) {
      fprintf(stderr, "Error reading extern");
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleTopLevelExpression() {
  // Evaluate a top-level expression into an anonymous function.
  if (auto FnAST = ParseTopLevelExpr()) {
    if (!FnAST->Codegen()) {
      fprintf(stderr, "Error generating code for top level expr");
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

/// top ::= definition | external | expression | ';'
static void MainLoop() {
  while (1) {
    switch (CurTok) {
    case tok_eof:
      return;
    case ';':
      getNextToken();
      break; // ignore top-level semicolons.
    case tok_def:
      HandleDefinition();
      break;
    case tok_extern:
      HandleExtern();
      break;
    default:
      HandleTopLevelExpression();
      break;
    }
  }
}

//===----------------------------------------------------------------------===//
// "Library" functions that can be "extern'd" from user code.
//===----------------------------------------------------------------------===//

/// putchard - putchar that takes a double and returns 0.
extern "C" double putchard(double X) {
  putchar((char)X);
  return 0;
}

/// printd - printf that takes a double prints it as "%f\n", returning 0.
extern "C" double printd(double X) {
  printf("%f\n", X);
  return 0;
}

//===----------------------------------------------------------------------===//
// Main driver code.
//===----------------------------------------------------------------------===//

int main() {
  InitializeNativeTarget();
  InitializeNativeTargetAsmPrinter();
  InitializeNativeTargetAsmParser();
  LLVMContext &Context = getGlobalContext();

  // Install standard binary operators.
  // 1 is lowest precedence.
  BinopPrecedence['='] = 2;
  BinopPrecedence['<'] = 10;
  BinopPrecedence['+'] = 20;
  BinopPrecedence['-'] = 20;
  BinopPrecedence['*'] = 40; // highest.

  // Prime the first token.
  getNextToken();

  // Make the module, which holds all the code.
  std::unique_ptr<Module> Owner = make_unique<Module>("my cool jit", Context);
  TheModule = Owner.get();

  // Add the current debug info version into the module.
  TheModule->addModuleFlag(Module::Warning, "Debug Info Version",
                           DEBUG_METADATA_VERSION);

  // Darwin only supports dwarf2.
  if (Triple(sys::getProcessTriple()).isOSDarwin())
    TheModule->addModuleFlag(llvm::Module::Warning, "Dwarf Version", 2);

  // Construct the DIBuilder, we do this here because we need the module.
  DBuilder = new DIBuilder(*TheModule);

  // Create the compile unit for the module.
  // Currently down as "fib.ks" as a filename since we're redirecting stdin
  // but we'd like actual source locations.
  KSDbgInfo.TheCU = DBuilder->createCompileUnit(
      dwarf::DW_LANG_C, "fib.ks", ".", "Kaleidoscope Compiler", 0, "", 0);

  // Create the JIT.  This takes ownership of the module.
  std::string ErrStr;
  TheExecutionEngine =
      EngineBuilder(std::move(Owner))
          .setErrorStr(&ErrStr)
          .setMCJITMemoryManager(llvm::make_unique<SectionMemoryManager>())
          .create();
  if (!TheExecutionEngine) {
    fprintf(stderr, "Could not create ExecutionEngine: %s\n", ErrStr.c_str());
    exit(1);
  }

  legacy::FunctionPassManager OurFPM(TheModule);

  // Set up the optimizer pipeline.  Start with registering info about how the
  // target lays out data structures.
  TheModule->setDataLayout(TheExecutionEngine->getDataLayout());
#if 0
  // Provide basic AliasAnalysis support for GVN.
  OurFPM.add(createBasicAliasAnalysisPass());
  // Promote allocas to registers.
  OurFPM.add(createPromoteMemoryToRegisterPass());
  // Do simple "peephole" optimizations and bit-twiddling optzns.
  OurFPM.add(createInstructionCombiningPass());
  // Reassociate expressions.
  OurFPM.add(createReassociatePass());
  // Eliminate Common SubExpressions.
  OurFPM.add(createGVNPass());
  // Simplify the control flow graph (deleting unreachable blocks, etc).
  OurFPM.add(createCFGSimplificationPass());
  #endif
  OurFPM.doInitialization();

  // Set the global so the code gen can use this.
  TheFPM = &OurFPM;

  // Run the main "interpreter loop" now.
  MainLoop();

  TheFPM = 0;

  // Finalize the debug info.
  DBuilder->finalize();

  // Print out all of the generated code.
  TheModule->dump();

  return 0;
}