LLVM学习日志4——Kaleidoscope：词法分析器和语法分析器

要实现一门语言，第一要务就是要能够处理文本文件，搞明白其中究竟写了些什么。传统上，我们会先利用“词法分析器”（也称为“扫描器”）将输入切成“语元（token）”，然后再做处理。词法分析器返回的每个语元都带有一个语元编号，此外可能还会附带一些元数据（比如某个数值）。

看了词法分析器的教程，第一章大概就是讲了如何用语元（token）来表示每个词，使用函数不断读取每个词，并且判断和分类。

词法分析器先对每个单词进行分类使用enum Token定义了5个种类：代码结束的eof；def；extern;

identifier和number。

主要的作用就是循环读取每个词 ，然后进行分类，当然数字部分比较复杂，因为可能是0.1.1这种，需要建立报错机制。但是例子中没有给出。分类是使用c++中isdigit，isalpha之类的函数。对了，特殊符号是直接返回ascii码，比如“+”返回ascii码，定义ID，以后根据ID来确定是什么运算。

在看读取的例程时有一个问题：在读取字母时，为什么要读取数字？

 

在说语法分析器之前要说一下AST——抽象语法树（abstract syntax code，AST）是源代码的抽象语法结构的树状表示，树上的每个节点都表示源代码中的一种结构，这所以说是抽象的，是因为抽象语法树并不会表示出真实语法出现的每一个细节，比如说，嵌套括号被隐含在树的结构中，并没有以节点的形式呈现。抽象语法树并不依赖于源语言的语法，也就是说语法分析阶段所采用的上下文无文文法，因为在写文法时，经常会对文法进行等价的转换（消除左递归，回溯，二义性等），这样会给文法分析引入一些多余的成分，对后续阶段造成不利影响，甚至会使合个阶段变得混乱。因些，很多编译器经常要独立地构造语法分析树，为前端，后端建立一个清晰的接口。

我的想法是这样的，词法分析器对单词进行分析，然后就要将单词串起来，而这个串就是AST，这个工具就是语法分析器。

举个简单例子：1+3*(4-1)+2

 

这个比词法分析器难多了，首先最基础的构建这个AST，主要是ExprAST，其下有VariableExprAST （变量）、BinaryExprAST （运算）、CallExprAST（函数），和call辅助类型PrototypeAST，FunctionAST 。不同的功能词组有不同的定义。

AST框架建好了就是充填，首先是读取一个词，就是一个Token，，然后需要读取下一个Token，进行循环。

接下来定义生成规则，比如（）啊。

最主要的就是解析二元表达式了，根据算数优先级进行解析。

一个函数使用嵌套进行解析了二元表达式，很强！

static ExprAST *ParseBinOpRHS(int ExprPrec, ExprAST *LHS) {
  // If this is a binop, find its precedence.
  while (1) {
//GetTokPrecedence是判断读取的词是不是运算符，返回的是事先设定好的优先级，如果不是运算符，返回-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.
//若果不是运算符，比如单独一个a，这样就返回本身。
    if (TokPrec < ExprPrec)
      return LHS;

    // Okay, we know this is a binop.
//知道运算种类.
    int BinOp = CurTok;
//读取运算符右边的，会进行循环，因为运算符右边可能是一些组合，a+（a+b）
    getNextToken();  // eat binop
//如果没有，就返回0，会报错的
    // Parse the primary expression after the binary operator.
    ExprAST *RHS = ParsePrimary();
    if (!RHS) return 0;
//开始进行嵌套的地方
    // 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);
  }
}

之后还有函数解析等。

完整源码如下：

#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;
}