llvm-tutorial/source/LexerParser.cpp

#include "llvm/ADT/STLExtras.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Verifier.h"
#include <cctype>
#include <cstdio>
#include <map>
#include <string>
#include <vector>
#include "Ast.h"

using namespace llvm;
using namespace ast;


namespace helper {
// Cloning make_unique here until it's standard in C++14.
// Using a namespace to avoid conflicting with MSVC's std::make_unique (which
// ADL can sometimes find in unqualified calls).
template <class T, class... Args>
static
    typename std::enable_if<!std::is_array<T>::value, std::unique_ptr<T>>::type
    make_unique(Args &&... args) {
  return std::unique_ptr<T>(new T(std::forward<Args>(args)...));
}
}

//===----------------------------------------------------------------------===//
// 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
};

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;
    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(), nullptr);
    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;
}

//===----------------------------------------------------------------------===//
// 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;
}

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

/// numberexpr ::= number
static std::unique_ptr<ExprAST> ParseNumberExpr() {
  auto Result = helper::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;
}

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

  getNextToken(); // eat identifier.

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

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

      if (CurTok == ')')
        break;

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

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

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

/// primary
///   ::= identifierexpr
///   ::= numberexpr
///   ::= parenexpr
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();
  }
}

/// binoprhs
///   ::= ('+' primary)*
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;
    getNextToken(); // eat binop

    // Parse the primary expression after the binary operator.
    auto RHS = ParsePrimary();
    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 = helper::make_unique<BinaryExprAST>(BinOp, std::move(LHS),
                                             std::move(RHS));
  }
}

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

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

/// prototype
///   ::= id '(' id* ')'
static std::unique_ptr<PrototypeAST> ParsePrototype() {
  if (CurTok != tok_identifier)
    return ErrorP("Expected function name in prototype");

  std::string FnName = IdentifierStr;
  getNextToken();

  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 ')'.

  return helper::make_unique<PrototypeAST>(FnName, std::move(ArgNames));
}

/// 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 helper::make_unique<FunctionAST>(std::move(Proto), std::move(E));
  return nullptr;
}

/// toplevelexpr ::= expression
static std::unique_ptr<FunctionAST> ParseTopLevelExpr() {
  if (auto E = ParseExpression()) {
    // Make an anonymous proto.
    auto Proto = helper::make_unique<PrototypeAST>("__anon_expr",
                                                   std::vector<std::string>());
    return helper::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();
}

//===----------------------------------------------------------------------===//
// Top-Level parsing
//===----------------------------------------------------------------------===//

static void HandleDefinition() {
  if (auto FnAST = ParseDefinition()) {
    if (auto *FnIR = FnAST->codegen()) {
      fprintf(stderr, "Read function definition:");
      FnIR->dump();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleExtern() {
  if (auto ProtoAST = ParseExtern()) {
    if (auto *FnIR = ProtoAST->codegen()) {
      fprintf(stderr, "Read extern: ");
      FnIR->dump();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

static void HandleTopLevelExpression() {
  // Evaluate a top-level expression into an anonymous function.
  if (auto FnAST = ParseTopLevelExpr()) {
    if (auto *FnIR = FnAST->codegen()) {
      fprintf(stderr, "Read top-level expression:");
      FnIR->dump();
    }
  } else {
    // Skip token for error recovery.
    getNextToken();
  }
}

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

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

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

  // Prime the first token.
  fprintf(stderr, "ready> ");
  getNextToken();

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

  AstTree::TheModule->dump();

  return 0;
}