odoo/bin/tools/safe_eval.py

# -*- coding: utf-8 -*-
##############################################################################
#    
#    Copyright (C) 2004-2010 OpenERP s.a. (<http://www.openerp.com>).
#
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU Affero General Public License as
#    published by the Free Software Foundation, either version 3 of the
#    License, or (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU Affero General Public License for more details.
#
#    You should have received a copy of the GNU Affero General Public License
#    along with this program.  If not, see <http://www.gnu.org/licenses/>.     
#
##############################################################################

"""
safe_eval module - methods intended to provide more restricted alternatives to
                   evaluate simple and/or untrusted code.
                   
Methods in this module are typically used as alternatives to eval() to parse 
OpenERP domain strings, conditions and expressions, mostly based on locals
condition/math builtins.
"""

# Module partially ripped from/inspired by several different sources:
#  - http://code.activestate.com/recipes/286134/
#  - safe_eval in lp:~xrg/openobject-server/optimize-5.0
#  - safe_eval in tryton http://hg.tryton.org/hgwebdir.cgi/trytond/rev/bbb5f73319ad  
#  - python 2.6's ast.literal_eval

from opcode import HAVE_ARGUMENT, opmap, opname

_CONST_CODES = set(opmap[x] for x in [
    'POP_TOP', 'ROT_TWO', 'ROT_THREE', 'ROT_FOUR', 'DUP_TOP',
    'BUILD_LIST', 'BUILD_MAP', 'BUILD_TUPLE',
    'LOAD_CONST', 'RETURN_VALUE', 'STORE_SUBSCR'] if x in opmap)

_EXPR_CODES = _CONST_CODES.union(set(opmap[x] for x in [
    'UNARY_POSITIVE', 'UNARY_NEGATIVE', 'UNARY_NOT',
    'UNARY_INVERT', 'BINARY_POWER', 'BINARY_MULTIPLY',
    'BINARY_DIVIDE', 'BINARY_FLOOR_DIVIDE', 'BINARY_TRUE_DIVIDE',
    'BINARY_MODULO', 'BINARY_ADD', 'BINARY_SUBTRACT', 'BINARY_SUBSCR',
    'BINARY_LSHIFT', 'BINARY_RSHIFT', 'BINARY_AND', 'BINARY_XOR',
    'BINARY_OR'] if x in opmap))

_SAFE_CODES = _EXPR_CODES.union(set(opmap[x] for x in [
    'STORE_MAP', 'LOAD_NAME', 'CALL_FUNCTION', 'COMPARE_OP', 'LOAD_ATTR',
    'STORE_NAME', 'GET_ITER', 'FOR_ITER', 'LIST_APPEND', 'JUMP_ABSOLUTE',
    'DELETE_NAME', 'JUMP_IF_TRUE', 'JUMP_IF_FALSE', 
    ] if x in opmap))


def _get_opcodes(codeobj):
    """_get_opcodes(codeobj) -> [opcodes]

    Extract the actual opcodes as a list from a code object

    >>> c = compile("[1 + 2, (1,2)]", "", "eval")
    >>> _get_opcodes(c)
    [100, 100, 23, 100, 100, 102, 103, 83]
    """
    i = 0
    opcodes = []
    s = codeobj.co_code
    while i < len(s):
        code = ord(s[i])
        opcodes.append(code)
        if code >= HAVE_ARGUMENT:
            i += 3
        else:
            i += 1
    return opcodes        

def test_expr(expr, allowed_codes):
    """test_expr(expression) -> code_object

    Test that the expression contains only the allowed opcodes.
    If the expression is valid and contains only allowed codes,
    return the compiled code object. Otherwise raise a ValueError.
    """
    try:
        code_obj = compile(expr, "", "eval")
    except:
        raise ValueError("%s is not a valid expression" % expr)
    for code in _get_opcodes(code_obj):
        if code not in allowed_codes:
            raise ValueError("opcode %s not allowed (%r)" % (opname[code], expr))
    return code_obj


def const_eval(expr):
    """const_eval(expression) -> value

    Safe Python constant evaluation

    Evaluates a string that contains an expression describing
    a Python constant. Strings that are not valid Python expressions
    or that contain other code besides the constant raise ValueError.

    >>> const_eval("10")
    10
    >>> const_eval("[1,2, (3,4), {'foo':'bar'}]")
    [1, 2, (3, 4), {'foo': 'bar'}]
    >>> const_eval("1+2")
    Traceback (most recent call last):
    ...
    ValueError: opcode BINARY_ADD not allowed
    """
    c = test_expr(expr, _CONST_CODES)
    return eval(c)

def expr_eval(expr):
    """expr_eval(expression) -> value

    Restricted Python expression evaluation

    Evaluates a string that contains an expression that only
    uses Python constants. This can be used to e.g. evaluate 
    a numerical expression from an untrusted source.

    >>> expr_eval("1+2")
    3
    >>> expr_eval("[1,2]*2")
    [1, 2, 1, 2]
    >>> expr_eval("__import__('sys').modules")
    Traceback (most recent call last):
    ...
    ValueError: opcode LOAD_NAME not allowed
    """
    c = test_expr(expr, _EXPR_CODES)
    return eval(c)


# Port of Python 2.6's ast.literal_eval for use under Python 2.5
SAFE_CONSTANTS = {'None': None, 'True': True, 'False': False}

try:
    # first, try importing directly
    from ast import literal_eval
except ImportError:
    from _ast import *
    
    def _convert(node):
        if isinstance(node, Str):
            return node.s
        elif isinstance(node, Num):
            return node.n
        elif isinstance(node, Tuple):
            return tuple(map(_convert, node.elts))
        elif isinstance(node, List):
            return list(map(_convert, node.elts))
        elif isinstance(node, Dict):
            return dict((_convert(k), _convert(v)) for k, v
                        in zip(node.keys, node.values))
        elif isinstance(node, Name):
            if node.id in SAFE_CONSTANTS:
                return SAFE_CONSTANTS[node.id]
        raise ValueError('malformed or disallowed expression')
    
    def parse(expr, filename='<unknown>', mode='eval'):
        """parse(source[, filename], mode]] -> code object
        Parse an expression into an AST node.
        Equivalent to compile(expr, filename, mode, PyCF_ONLY_AST).
        """
        return compile(expr, filename, mode, PyCF_ONLY_AST)

    def literal_eval(node_or_string):
        """literal_eval(expression) -> value
        Safely evaluate an expression node or a string containing a Python
        expression.  The string or node provided may only consist of the
        following Python literal structures: strings, numbers, tuples,
        lists, dicts, booleans, and None.
        
        >>> literal_eval('[1,True,"spam"]')
        [1, True, 'spam']
        
        >>> literal_eval('1+3')
        Traceback (most recent call last):
        ...
        ValueError: malformed or disallowed expression
        """
        if isinstance(node_or_string, basestring):
            node_or_string = parse(node_or_string)
        if isinstance(node_or_string, Expression):
            node_or_string = node_or_string.body
        return _convert(node_or_string)



def safe_eval(expr, context = None):
    """safe_eval(expression, context) -> value

    System-restricted Python expression evaluation

    Evaluates a string that contains an expression that mostly
    uses Python constants, arithmetic expressions and the
    use of the objects provided in context.
     
    This can be used to e.g. evaluate 
    an OpenERP domain expression from an untrusted expr.

    >>> safe_eval("__import__('sys').modules")
    Traceback (most recent call last):
    ...
    ValueError: opcode LOAD_NAME not allowed

    """
    if '__subclasses__' in expr:
       raise ValueError('expression not allowed (__subclasses__)')
    code_obj = compile(expr, '', 'eval')
    byte_codes = code_obj.co_code
    i = 0
    while i < len(byte_codes):
        op_code = ord(byte_codes[i])
        if op_code not in _SAFE_CODES:
            raise ValueError('opcode %byte_codes not allowed' % dis.opname[op_code])
        if op_code >= HAVE_ARGUMENT:
            i += 3
        else:
            i += 1
    return eval(code_obj, {'__builtins__': {
                                'True': True,
                                'False': False,
                                'None': None,
                                'str': str,
                                'globals': locals,
                                'locals': locals,
                                'bool': bool,
                                'dict': dict,
                                'list': list,
                                'tuple': tuple,
                           }
                          }, context)