计算字符串中的数学表达式

Question

stringExp = "2^4"
intVal = int(stringExp)      # Expected value: 16

这将返回以下错误：

Traceback (most recent call last):  
File "<stdin>", line 1, in <module>
ValueError: invalid literal for int()
with base 10: '2^4'

我知道eval可以解决这个问题，但难道没有一种更好、更重要、更安全的方法来计算存储在字符串中的数学表达式吗？

Answer 1

Pyparsing可用于解析数学表达式。尤其是fourFn.py 演示如何解析基本算术表达式。下面，我将fourFn重写为一个数值解析器类，以便于重用。

from __future__ import division
from pyparsing import (Literal, CaselessLiteral, Word, Combine, Group, Optional,
                       ZeroOrMore, Forward, nums, alphas, oneOf)
import math
import operator

__author__ = 'Paul McGuire'
__version__ = '$Revision: 0.0 $'
__date__ = '$Date: 2009-03-20 $'
__source__ = '''http://pyparsing.wikispaces.com/file/view/fourFn.py
http://pyparsing.wikispaces.com/message/view/home/15549426
'''
__note__ = '''
All I've done is rewrap Paul McGuire's fourFn.py as a class, so I can use it
more easily in other places.
'''


class NumericStringParser(object):
    '''
    Most of this code comes from the fourFn.py pyparsing example

    '''

    def pushFirst(self, strg, loc, toks):
        self.exprStack.append(toks[0])

    def pushUMinus(self, strg, loc, toks):
        if toks and toks[0] == '-':
            self.exprStack.append('unary -')

    def __init__(self):
        """
        expop   :: '^'
        multop  :: '*' | '/'
        addop   :: '+' | '-'
        integer :: ['+' | '-'] '0'..'9'+
        atom    :: PI | E | real | fn '(' expr ')' | '(' expr ')'
        factor  :: atom [ expop factor ]*
        term    :: factor [ multop factor ]*
        expr    :: term [ addop term ]*
        """
        point = Literal(".")
        e = CaselessLiteral("E")
        fnumber = Combine(Word("+-" + nums, nums) +
                          Optional(point + Optional(Word(nums))) +
                          Optional(e + Word("+-" + nums, nums)))
        ident = Word(alphas, alphas + nums + "_$")
        plus = Literal("+")
        minus = Literal("-")
        mult = Literal("*")
        div = Literal("/")
        lpar = Literal("(").suppress()
        rpar = Literal(")").suppress()
        addop = plus | minus
        multop = mult | div
        expop = Literal("^")
        pi = CaselessLiteral("PI")
        expr = Forward()
        atom = ((Optional(oneOf("- +")) +
                 (ident + lpar + expr + rpar | pi | e | fnumber).setParseAction(self.pushFirst))
                | Optional(oneOf("- +")) + Group(lpar + expr + rpar)
                ).setParseAction(self.pushUMinus)
        # by defining exponentiation as "atom [ ^ factor ]..." instead of
        # "atom [ ^ atom ]...", we get right-to-left exponents, instead of left-to-right
        # that is, 2^3^2 = 2^(3^2), not (2^3)^2.
        factor = Forward()
        factor << atom + \
            ZeroOrMore((expop + factor).setParseAction(self.pushFirst))
        term = factor + \
            ZeroOrMore((multop + factor).setParseAction(self.pushFirst))
        expr << term + \
            ZeroOrMore((addop + term).setParseAction(self.pushFirst))
        # addop_term = ( addop + term ).setParseAction( self.pushFirst )
        # general_term = term + ZeroOrMore( addop_term ) | OneOrMore( addop_term)
        # expr <<  general_term
        self.bnf = expr
        # map operator symbols to corresponding arithmetic operations
        epsilon = 1e-12
        self.opn = {"+": operator.add,
                    "-": operator.sub,
                    "*": operator.mul,
                    "/": operator.truediv,
                    "^": operator.pow}
        self.fn = {"sin": math.sin,
                   "cos": math.cos,
                   "tan": math.tan,
                   "exp": math.exp,
                   "abs": abs,
                   "trunc": lambda a: int(a),
                   "round": round,
                   "sgn": lambda a: abs(a) > epsilon and cmp(a, 0) or 0}

    def evaluateStack(self, s):
        op = s.pop()
        if op == 'unary -':
            return -self.evaluateStack(s)
        if op in "+-*/^":
            op2 = self.evaluateStack(s)
            op1 = self.evaluateStack(s)
            return self.opn[op](op1, op2)
        elif op == "PI":
            return math.pi  # 3.1415926535
        elif op == "E":
            return math.e  # 2.718281828
        elif op in self.fn:
            return self.fn[op](self.evaluateStack(s))
        elif op[0].isalpha():
            return 0
        else:
            return float(op)

    def eval(self, num_string, parseAll=True):
        self.exprStack = []
        results = self.bnf.parseString(num_string, parseAll)
        val = self.evaluateStack(self.exprStack[:])
        return val

你可以这样用

nsp = NumericStringParser()
result = nsp.eval('2^4')
print(result)
# 16.0

result = nsp.eval('exp(2^4)')
print(result)
# 8886110.520507872

Answer 2

一些比eval()和^{}^*更安全的选择：

• asteval
• numexpr

根据文档中的以下警告，^*SymPy^{}也不安全。

Warning: Note that this function uses eval, and thus shouldn’t be used on unsanitized input.

Answer 3

eval是邪恶的

eval("__import__('os').remove('important file')") # arbitrary commands
eval("9**9**9**9**9**9**9**9", {'__builtins__': None}) # CPU, memory

注意：即使使用set __builtins__到None，仍然可能使用内省来中断：

eval('(1).__class__.__bases__[0].__subclasses__()', {'__builtins__': None})

使用ast评估算术表达式

import ast
import operator as op

# supported operators
operators = {ast.Add: op.add, ast.Sub: op.sub, ast.Mult: op.mul,
             ast.Div: op.truediv, ast.Pow: op.pow, ast.BitXor: op.xor,
             ast.USub: op.neg}

def eval_expr(expr):
    """
    >>> eval_expr('2^6')
    4
    >>> eval_expr('2**6')
    64
    >>> eval_expr('1 + 2*3**(4^5) / (6 + -7)')
    -5.0
    """
    return eval_(ast.parse(expr, mode='eval').body)

def eval_(node):
    if isinstance(node, ast.Num): # <number>
        return node.n
    elif isinstance(node, ast.BinOp): # <left> <operator> <right>
        return operators[type(node.op)](eval_(node.left), eval_(node.right))
    elif isinstance(node, ast.UnaryOp): # <operator> <operand> e.g., -1
        return operators[type(node.op)](eval_(node.operand))
    else:
        raise TypeError(node)

您可以轻松地限制每个操作或任何中间结果的允许范围，例如限制a**b的输入参数：

def power(a, b):
    if any(abs(n) > 100 for n in [a, b]):
        raise ValueError((a,b))
    return op.pow(a, b)
operators[ast.Pow] = power

或限制中间结果的大小：

import functools

def limit(max_=None):
    """Return decorator that limits allowed returned values."""
    def decorator(func):
        @functools.wraps(func)
        def wrapper(*args, **kwargs):
            ret = func(*args, **kwargs)
            try:
                mag = abs(ret)
            except TypeError:
                pass # not applicable
            else:
                if mag > max_:
                    raise ValueError(ret)
            return ret
        return wrapper
    return decorator

eval_ = limit(max_=10**100)(eval_)

示例

>>> evil = "__import__('os').remove('important file')"
>>> eval_expr(evil) #doctest:+IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
TypeError:
>>> eval_expr("9**9")
387420489
>>> eval_expr("9**9**9**9**9**9**9**9") #doctest:+IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
...
ValueError: