#include #include #include #include #include #include //===----------------------------------------------------------------------===// // 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 { public: NumberExprAST(double 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 { public: BinaryExprAST(char op, ExprAST *lhs, ExprAST *rhs) {} }; /// CallExprAST - Expression class for function calls. class CallExprAST : public ExprAST { std::string Callee; std::vector Args; public: CallExprAST(const std::string &callee, std::vector &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 Args; public: PrototypeAST(const std::string &name, const std::vector &args) : Name(name), Args(args) {} }; /// FunctionAST - This class represents a function definition itself. class FunctionAST { public: FunctionAST(PrototypeAST *proto, ExprAST *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 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 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 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()); 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; }