.. contents::
:local:
-Written by `Chris Lattner <mailto:sabre@nondot.org>`_
-
Chapter 2 Introduction
======================
/// NumberExprAST - Expression class for numeric literals like "1.0".
class NumberExprAST : public ExprAST {
double Val;
+
public:
- NumberExprAST(double val) : Val(val) {}
+ NumberExprAST(double Val) : Val(Val) {}
};
The code above shows the definition of the base ExprAST class and one
/// VariableExprAST - Expression class for referencing a variable, like "a".
class VariableExprAST : public ExprAST {
std::string Name;
+
public:
- VariableExprAST(const std::string &name) : Name(name) {}
+ VariableExprAST(const std::string &Name) : Name(Name) {}
};
/// BinaryExprAST - Expression class for a binary operator.
class BinaryExprAST : public ExprAST {
char Op;
- ExprAST *LHS, *RHS;
+ std::unique_ptr<ExprAST> LHS, RHS;
+
public:
- BinaryExprAST(char op, ExprAST *lhs, ExprAST *rhs)
- : Op(op), LHS(lhs), RHS(rhs) {}
+ BinaryExprAST(char op, std::unique_ptr<ExprAST> LHS,
+ std::unique_ptr<ExprAST> RHS)
+ : Op(op), LHS(std::move(LHS)), RHS(std::move(RHS)) {}
};
/// CallExprAST - Expression class for function calls.
class CallExprAST : public ExprAST {
std::string Callee;
- std::vector<ExprAST*> Args;
+ std::vector<std::unique_ptr<ExprAST>> Args;
+
public:
- CallExprAST(const std::string &callee, std::vector<ExprAST*> &args)
- : Callee(callee), Args(args) {}
+ CallExprAST(const std::string &Callee,
+ std::vector<std::unique_ptr<ExprAST>> Args)
+ : Callee(Callee), Args(std::move(Args)) {}
};
This is all (intentionally) rather straight-forward: variables capture
class PrototypeAST {
std::string Name;
std::vector<std::string> Args;
+
public:
- PrototypeAST(const std::string &name, const std::vector<std::string> &args)
- : Name(name), Args(args) {}
+ PrototypeAST(const std::string &name, std::vector<std::string> Args)
+ : Name(name), Args(std::move(Args)) {}
};
/// FunctionAST - This class represents a function definition itself.
class FunctionAST {
- PrototypeAST *Proto;
- ExprAST *Body;
+ std::unique_ptr<PrototypeAST> Proto;
+ std::unique_ptr<ExprAST> Body;
+
public:
- FunctionAST(PrototypeAST *proto, ExprAST *body)
- : Proto(proto), Body(body) {}
+ FunctionAST(std::unique_ptr<PrototypeAST> Proto,
+ std::unique_ptr<ExprAST> Body)
+ : Proto(std::move(Proto)), Body(std::move(Body)) {}
};
In Kaleidoscope, functions are typed with just a count of their
.. code-block:: c++
- ExprAST *X = new VariableExprAST("x");
- ExprAST *Y = new VariableExprAST("y");
- ExprAST *Result = new BinaryExprAST('+', X, Y);
+ auto LHS = llvm::make_unique<VariableExprAST>("x");
+ auto RHS = llvm::make_unique<VariableExprAST>("y");
+ auto Result = std::make_unique<BinaryExprAST>('+', std::move(LHS),
+ std::move(RHS));
In order to do this, we'll start by defining some basic helper routines:
/// Error* - These are little helper functions for error handling.
- ExprAST *Error(const char *Str) { fprintf(stderr, "Error: %s\n", Str);return 0;}
- PrototypeAST *ErrorP(const char *Str) { Error(Str); return 0; }
- FunctionAST *ErrorF(const char *Str) { Error(Str); return 0; }
+ 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;
+ }
The ``Error`` routines are simple helper routines that our parser will
use to handle errors. The error recovery in our parser will not be the
.. code-block:: c++
/// numberexpr ::= number
- static ExprAST *ParseNumberExpr() {
- ExprAST *Result = new NumberExprAST(NumVal);
+ static std::unique_ptr<ExprAST> ParseNumberExpr() {
+ auto Result = llvm::make_unique<NumberExprAST>(NumVal);
getNextToken(); // consume the number
- return Result;
+ return std::move(Result);
}
This routine is very simple: it expects to be called when the current
.. code-block:: c++
/// parenexpr ::= '(' expression ')'
- static ExprAST *ParseParenExpr() {
- getNextToken(); // eat (.
- ExprAST *V = ParseExpression();
- if (!V) return 0;
+ static std::unique_ptr<ExprAST> ParseParenExpr() {
+ getNextToken(); // eat (.
+ auto V = ParseExpression();
+ if (!V)
+ return nullptr;
if (CurTok != ')')
return Error("expected ')'");
- getNextToken(); // eat ).
+ getNextToken(); // eat ).
return V;
}
/// identifierexpr
/// ::= identifier
/// ::= identifier '(' expression* ')'
- static ExprAST *ParseIdentifierExpr() {
+ static std::unique_ptr<ExprAST> ParseIdentifierExpr() {
std::string IdName = IdentifierStr;
getNextToken(); // eat identifier.
if (CurTok != '(') // Simple variable ref.
- return new VariableExprAST(IdName);
+ return llvm::make_unique<VariableExprAST>(IdName);
// Call.
getNextToken(); // eat (
- std::vector<ExprAST*> Args;
+ std::vector<std::unique_ptr<ExprAST>> Args;
if (CurTok != ')') {
while (1) {
- ExprAST *Arg = ParseExpression();
- if (!Arg) return 0;
- Args.push_back(Arg);
+ if (auto Arg = ParseExpression())
+ Args.push_back(std::move(Arg));
+ else
+ return nullptr;
- if (CurTok == ')') break;
+ if (CurTok == ')')
+ break;
if (CurTok != ',')
return Error("Expected ')' or ',' in argument list");
// Eat the ')'.
getNextToken();
- return new CallExprAST(IdName, Args);
+ return llvm::make_unique<CallExprAST>(IdName, std::move(Args));
}
This routine follows the same style as the other routines. (It expects
/// ::= identifierexpr
/// ::= numberexpr
/// ::= parenexpr
- static ExprAST *ParsePrimary() {
+ 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();
+ default:
+ return Error("unknown token when expecting an expression");
+ case tok_identifier:
+ return ParseIdentifierExpr();
+ case tok_number:
+ return ParseNumberExpr();
+ case '(':
+ return ParseParenExpr();
}
}
/// expression
/// ::= primary binoprhs
///
- static ExprAST *ParseExpression() {
- ExprAST *LHS = ParsePrimary();
- if (!LHS) return 0;
+ static std::unique_ptr<ExprAST> ParseExpression() {
+ auto LHS = ParsePrimary();
+ if (!LHS)
+ return nullptr;
- return ParseBinOpRHS(0, LHS);
+ return ParseBinOpRHS(0, std::move(LHS));
}
``ParseBinOpRHS`` is the function that parses the sequence of pairs for
/// binoprhs
/// ::= ('+' primary)*
- static ExprAST *ParseBinOpRHS(int ExprPrec, ExprAST *LHS) {
+ 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();
getNextToken(); // eat binop
// Parse the primary expression after the binary operator.
- ExprAST *RHS = ParsePrimary();
- if (!RHS) return 0;
+ auto RHS = ParsePrimary();
+ if (!RHS)
+ return nullptr;
As such, this code eats (and remembers) the binary operator and then
parses the primary expression that follows. This builds up the whole
}
// Merge LHS/RHS.
- LHS = new BinaryExprAST(BinOp, LHS, RHS);
+ LHS = llvm::make_unique<BinaryExprAST>(BinOp, std::move(LHS),
+ std::move(RHS));
} // loop around to the top of the while loop.
}
// the pending operator take RHS as its LHS.
int NextPrec = GetTokPrecedence();
if (TokPrec < NextPrec) {
- RHS = ParseBinOpRHS(TokPrec+1, RHS);
- if (RHS == 0) return 0;
+ RHS = ParseBinOpRHS(TokPrec+1, std::move(RHS));
+ if (!RHS)
+ return nullptr;
}
// Merge LHS/RHS.
- LHS = new BinaryExprAST(BinOp, LHS, RHS);
+ LHS = llvm::make_unique<BinaryExprAST>(BinOp, std::move(LHS),
+ std::move(RHS));
} // loop around to the top of the while loop.
}
/// prototype
/// ::= id '(' id* ')'
- static PrototypeAST *ParsePrototype() {
+ static std::unique_ptr<PrototypeAST> ParsePrototype() {
if (CurTok != tok_identifier)
return ErrorP("Expected function name in prototype");
// success.
getNextToken(); // eat ')'.
- return new PrototypeAST(FnName, ArgNames);
+ return llvm::make_unique<PrototypeAST>(FnName, std::move(ArgNames));
}
Given this, a function definition is very simple, just a prototype plus
.. code-block:: c++
/// definition ::= 'def' prototype expression
- static FunctionAST *ParseDefinition() {
+ static std::unique_ptr<FunctionAST> ParseDefinition() {
getNextToken(); // eat def.
- PrototypeAST *Proto = ParsePrototype();
- if (Proto == 0) return 0;
+ auto Proto = ParsePrototype();
+ if (!Proto) return nullptr;
- if (ExprAST *E = ParseExpression())
- return new FunctionAST(Proto, E);
- return 0;
+ if (auto E = ParseExpression())
+ return llvm::make_unique<FunctionAST>(std::move(Proto), std::move(E));
+ return nullptr;
}
In addition, we support 'extern' to declare functions like 'sin' and
.. code-block:: c++
/// external ::= 'extern' prototype
- static PrototypeAST *ParseExtern() {
+ static std::unique_ptr<PrototypeAST> ParseExtern() {
getNextToken(); // eat extern.
return ParsePrototype();
}
.. code-block:: c++
/// toplevelexpr ::= expression
- static FunctionAST *ParseTopLevelExpr() {
- if (ExprAST *E = ParseExpression()) {
+ static std::unique_ptr<FunctionAST> ParseTopLevelExpr() {
+ if (auto E = ParseExpression()) {
// Make an anonymous proto.
- PrototypeAST *Proto = new PrototypeAST("", std::vector<std::string>());
- return new FunctionAST(Proto, E);
+ auto Proto = llvm::make_unique<PrototypeAST>("", std::vector<std::string>());
+ return llvm::make_unique<FunctionAST>(std::move(Proto), std::move(E));
}
- return 0;
+ return nullptr;
}
Now that we have all the pieces, let's build a little driver that will
while (1) {
fprintf(stderr, "ready> ");
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;
+ case tok_eof:
+ return;
+ case ';': // ignore top-level semicolons.
+ getNextToken();
+ break;
+ case tok_def:
+ HandleDefinition();
+ break;
+ case tok_extern:
+ HandleExtern();
+ break;
+ default:
+ HandleTopLevelExpression();
+ break;
}
}
}
Here is the code:
-.. code-block:: c++
-
- #include <cstdio>
- #include <cstdlib>
- #include <string>
- #include <map>
- #include <vector>
-
- //===----------------------------------------------------------------------===//
- // 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(), 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() {}
- };
-
- /// NumberExprAST - Expression class for numeric literals like "1.0".
- class NumberExprAST : public ExprAST {
- double Val;
- public:
- NumberExprAST(double val) : Val(val) {}
- };
-
- /// VariableExprAST - Expression class for referencing a variable, like "a".
- class VariableExprAST : public ExprAST {
- std::string Name;
- public:
- VariableExprAST(const std::string &name) : Name(name) {}
- };
-
- /// 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), RHS(rhs) {}
- };
-
- /// CallExprAST - Expression class for function calls.
- class CallExprAST : public ExprAST {
- std::string Callee;
- std::vector<ExprAST*> Args;
- public:
- CallExprAST(const std::string &callee, std::vector<ExprAST*> &args)
- : Callee(callee), Args(args) {}
- };
-
- /// PrototypeAST - This class represents the "prototype" for a function,
- /// which captures its name, and its argument names (thus implicitly the number
- /// of arguments the function takes).
- class PrototypeAST {
- std::string Name;
- std::vector<std::string> Args;
- public:
- PrototypeAST(const std::string &name, const std::vector<std::string> &args)
- : Name(name), Args(args) {}
-
- };
-
- /// FunctionAST - This class represents a function definition itself.
- class FunctionAST {
- PrototypeAST *Proto;
- ExprAST *Body;
- public:
- FunctionAST(PrototypeAST *proto, ExprAST *body)
- : Proto(proto), Body(body) {}
-
- };
-
- //===----------------------------------------------------------------------===//
- // 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.
- ExprAST *Error(const char *Str) { fprintf(stderr, "Error: %s\n", Str);return 0;}
- PrototypeAST *ErrorP(const char *Str) { Error(Str); return 0; }
- FunctionAST *ErrorF(const char *Str) { Error(Str); return 0; }
-
- static ExprAST *ParseExpression();
-
- /// identifierexpr
- /// ::= identifier
- /// ::= identifier '(' expression* ')'
- static ExprAST *ParseIdentifierExpr() {
- std::string IdName = IdentifierStr;
-
- getNextToken(); // eat identifier.
-
- if (CurTok != '(') // Simple variable ref.
- return new VariableExprAST(IdName);
-
- // Call.
- getNextToken(); // eat (
- std::vector<ExprAST*> Args;
- if (CurTok != ')') {
- while (1) {
- ExprAST *Arg = ParseExpression();
- if (!Arg) return 0;
- Args.push_back(Arg);
-
- if (CurTok == ')') break;
-
- if (CurTok != ',')
- return Error("Expected ')' or ',' in argument list");
- getNextToken();
- }
- }
-
- // Eat the ')'.
- getNextToken();
-
- return new CallExprAST(IdName, Args);
- }
-
- /// numberexpr ::= number
- static ExprAST *ParseNumberExpr() {
- ExprAST *Result = new NumberExprAST(NumVal);
- getNextToken(); // consume the number
- return Result;
- }
-
- /// parenexpr ::= '(' expression ')'
- static ExprAST *ParseParenExpr() {
- getNextToken(); // eat (.
- ExprAST *V = ParseExpression();
- if (!V) return 0;
-
- if (CurTok != ')')
- return Error("expected ')'");
- getNextToken(); // eat ).
- return V;
- }
-
- /// primary
- /// ::= identifierexpr
- /// ::= numberexpr
- /// ::= parenexpr
- static 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 ExprAST *ParseBinOpRHS(int ExprPrec, 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.
- ExprAST *RHS = ParsePrimary();
- if (!RHS) return 0;
-
- // 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, RHS);
- if (RHS == 0) return 0;
- }
-
- // Merge LHS/RHS.
- LHS = new BinaryExprAST(BinOp, LHS, RHS);
- }
- }
-
- /// expression
- /// ::= primary binoprhs
- ///
- static ExprAST *ParseExpression() {
- ExprAST *LHS = ParsePrimary();
- if (!LHS) return 0;
-
- return ParseBinOpRHS(0, LHS);
- }
-
- /// prototype
- /// ::= id '(' id* ')'
- static 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 new PrototypeAST(FnName, ArgNames);
- }
-
- /// definition ::= 'def' prototype expression
- static FunctionAST *ParseDefinition() {
- getNextToken(); // eat def.
- PrototypeAST *Proto = ParsePrototype();
- if (Proto == 0) return 0;
-
- if (ExprAST *E = ParseExpression())
- return new FunctionAST(Proto, E);
- return 0;
- }
-
- /// toplevelexpr ::= expression
- static FunctionAST *ParseTopLevelExpr() {
- if (ExprAST *E = ParseExpression()) {
- // Make an anonymous proto.
- PrototypeAST *Proto = new PrototypeAST("", std::vector<std::string>());
- return new FunctionAST(Proto, E);
- }
- return 0;
- }
-
- /// external ::= 'extern' prototype
- static PrototypeAST *ParseExtern() {
- getNextToken(); // eat extern.
- return ParsePrototype();
- }
-
- //===----------------------------------------------------------------------===//
- // Top-Level parsing
- //===----------------------------------------------------------------------===//
-
- static void HandleDefinition() {
- if (ParseDefinition()) {
- fprintf(stderr, "Parsed a function definition.\n");
- } else {
- // Skip token for error recovery.
- getNextToken();
- }
- }
-
- static void HandleExtern() {
- if (ParseExtern()) {
- fprintf(stderr, "Parsed an extern\n");
- } else {
- // Skip token for error recovery.
- getNextToken();
- }
- }
-
- static void HandleTopLevelExpression() {
- // Evaluate a top-level expression into an anonymous function.
- if (ParseTopLevelExpr()) {
- fprintf(stderr, "Parsed a top-level expr\n");
- } 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 ';': getNextToken(); break; // ignore top-level semicolons.
- 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();
-
- return 0;
- }
+.. literalinclude:: ../../examples/Kaleidoscope/Chapter2/toy.cpp
+ :language: c++
`Next: Implementing Code Generation to LLVM IR <LangImpl3.html>`_
projects / oota-llvm.git / blobdiff