方程(表达式)解析器具有优先权？

http://www.engr.mun.ca/~theo/Misc/exp_parsing.htm

对不同方法的非常好的解释:

递归下降识别

调车场算法

经典的解决方案

优先攀登

用简单的语言和伪代码编写.

我喜欢'优先攀登'之一.

这里有一篇很好的文章,关于将简单的递归下降解析器与运算符优先级解析相结合.如果您最近一直在编写解析器,那么阅读它应该非常有趣和有益.

很久以前,我编写了自己的解析算法,在任何解析书中都找不到(比如Dragon Book).看看Shunting Yard算法的指针,我确实看到了相似之处.

大约2年前,我在http://www.perlmonks.org/?node_id=554516上发了一篇关于Perl源代码的文章..移植到其他语言很容易:我做的第一个实现是在Z80汇编程序中.

它是使用数字直接计算的理想选择,但如果必须,可以使用它来生成解析树.

更新因为更多人可以阅读(或运行)Javascript,所以在重新组织代码之后,我已经在Javascript中重新实现了我的解析器.整个解析器不到5k的Javascript代码(解析器大约100行,包装函数大约15行),包括错误报告和注释.

您可以在http://users.telenet.be/bartl/expressionParser/expressionParser.html上找到现场演示.

// operator table
var ops = {
   '+'  : {op: '+', precedence: 10, assoc: 'L', exec: function(l,r) { return l+r; } },
   '-'  : {op: '-', precedence: 10, assoc: 'L', exec: function(l,r) { return l-r; } },
   '*'  : {op: '*', precedence: 20, assoc: 'L', exec: function(l,r) { return l*r; } },
   '/'  : {op: '/', precedence: 20, assoc: 'L', exec: function(l,r) { return l/r; } },
   '**' : {op: '**', precedence: 30, assoc: 'R', exec: function(l,r) { return Math.pow(l,r); } }
};

// constants or variables
var vars = { e: Math.exp(1), pi: Math.atan2(1,1)*4 };

// input for parsing
// var r = { string: '123.45+33*8', offset: 0 };
// r is passed by reference: any change in r.offset is returned to the caller
// functions return the parsed/calculated value
function parseVal(r) {
    var startOffset = r.offset;
    var value;
    var m;
    // floating point number
    // example of parsing ("lexing") without aid of regular expressions
    value = 0;
    while("0123456789".indexOf(r.string.substr(r.offset, 1)) >= 0 && r.offset < r.string.length) r.offset++;
    if(r.string.substr(r.offset, 1) == ".") {
        r.offset++;
        while("0123456789".indexOf(r.string.substr(r.offset, 1)) >= 0 && r.offset < r.string.length) r.offset++;
    }
    if(r.offset > startOffset) {  // did that work?
        // OK, so I'm lazy...
        return parseFloat(r.string.substr(startOffset, r.offset-startOffset));
    } else if(r.string.substr(r.offset, 1) == "+") {  // unary plus
        r.offset++;
        return parseVal(r);
    } else if(r.string.substr(r.offset, 1) == "-") {  // unary minus
        r.offset++;
        return negate(parseVal(r));
    } else if(r.string.substr(r.offset, 1) == "(") {  // expression in parens
        r.offset++;   // eat "("
        value = parseExpr(r);
        if(r.string.substr(r.offset, 1) == ")") {
            r.offset++;
            return value;
        }
        r.error = "Parsing error: ')' expected";
        throw 'parseError';
    } else if(m = /^[a-z_][a-z0-9_]*/i.exec(r.string.substr(r.offset))) {  // variable/constant name        
        // sorry for the regular expression, but I'm too lazy to manually build a varname lexer
        var name = m[0];  // matched string
        r.offset += name.length;
        if(name in vars) return vars[name];  // I know that thing!
        r.error = "Semantic error: unknown variable '" + name + "'";
        throw 'unknownVar';        
    } else {
        if(r.string.length == r.offset) {
            r.error = 'Parsing error at end of string: value expected';
            throw 'valueMissing';
        } else  {
            r.error = "Parsing error: unrecognized value";
            throw 'valueNotParsed';
        }
    }
}

function negate (value) {
    return -value;
}

function parseOp(r) {
    if(r.string.substr(r.offset,2) == '**') {
        r.offset += 2;
        return ops['**'];
    }
    if("+-*/".indexOf(r.string.substr(r.offset,1)) >= 0)
        return ops[r.string.substr(r.offset++, 1)];
    return null;
}

function parseExpr(r) {
    var stack = [{precedence: 0, assoc: 'L'}];
    var op;
    var value = parseVal(r);  // first value on the left
    for(;;){
        op = parseOp(r) || {precedence: 0, assoc: 'L'}; 
        while(op.precedence < stack[stack.length-1].precedence ||
              (op.precedence == stack[stack.length-1].precedence && op.assoc == 'L')) {  
            // precedence op is too low, calculate with what we've got on the left, first
            var tos = stack.pop();
            if(!tos.exec) return value;  // end  reached
            // do the calculation ("reduce"), producing a new value
            value = tos.exec(tos.value, value);
        }
        // store on stack and continue parsing ("shift")
        stack.push({op: op.op, precedence: op.precedence, assoc: op.assoc, exec: op.exec, value: value});
        value = parseVal(r);  // value on the right
    }
}

function parse (string) {   // wrapper
    var r = {string: string, offset: 0};
    try {
        var value = parseExpr(r);
        if(r.offset < r.string.length){
          r.error = 'Syntax error: junk found at offset ' + r.offset;
            throw 'trailingJunk';
        }
        return value;
    } catch(e) {
        alert(r.error + ' (' + e + '):\n' + r.string.substr(0, r.offset) + '<*>' + r.string.substr(r.offset));
        return;
    }    
}

 ::=  +  |
           -  |
          

 ::=  *  |
            /  |
           

 ::= x | y | ... |
             (  ) |
             -  |
             

  ::  |   

   :: + | - | * | /

 ::  | ()

group       = '(' >> expression >> ')';
factor      = integer | group;
term        = factor >> *(('*' >> factor) | ('/' >> factor));
expression  = term >> *(('+' >> term) | ('-' >> term));