Hi,
A while ago I asked a question on the list about a simple eval
function, capable of eval'ing simple python constructs (tuples, dicts,
lists, strings, numbers etc) in a secure manner:
http://groups.google.com/group/comp.lang.python/browse_thread/thread/58a01273441d445f/
>From the answers I got I chose to use simplejson... However, I was
also pointed to a simple eval function by Fredrik Lundh:
http://effbot.org/zone/simple-iterator-parser.htm. His solution, using
module tokenize, was short and elegant. So I used his code as a
starting point for simple evaluation of dicts, tuples, lists, strings,
unicode strings, integers, floats, None, True, and False. I've
included the code below, together with some basic tests, and
profiling... On my computer (winXP, python 2.5), simple eval is about
5 times slower than builtin eval...
Comments, speedups, improvements in general, etc are appreciated. As
this is a contribution to the community I suggest that any
improvements are posted in this thread...
-Tor Erik
Code (tested on 2.5, but should work for versions >= 2.3):
'''
Recursive evaluation of:
tuples, lists, dicts, strings, unicode strings, ints, floats,
True, False, and None
'''
import cStringIO, tokenize, itertools
KEYWORDS = {'None': None, 'False': False, 'True': True}
def atom(next, token):
if token[1] == '(':
out = []
token = next()
while token[1] != ')':
out.append(atom(next, token))
token = next()
if token[1] == ',':
token = next()
return tuple(out)
elif token[1] == '[':
out = []
token = next()
while token[1] != ']':
out.append(atom(next, token))
token = next()
if token[1] == ',':
token = next()
return out
elif token[1] == '{':
out = {}
token = next()
while token[1] != '}':
key = atom(next, token)
next() # Skip key-value delimiter
token = next()
out[key] = atom(next, token)
token = next()
if token[1] == ',':
token = next()
return out
elif token[1].startswith('u'):
return token[1][2:-1].decode('unicode-escape')
elif token[0] is tokenize.STRING:
return token[1][1:-1].decode('string-escape')
elif token[0] is tokenize.NUMBER:
try:
return int(token[1], 0)
except ValueError:
return float(token[1])
elif token[1] in KEYWORDS:
return KEYWORDS[token[1]]
raise SyntaxError('malformed expression (%r)¨' % token[1])
def simple_eval(source):
src = cStringIO.StringIO(source).readline
src = tokenize.generate_tokens(src)
src = itertools.ifilter(lambda x: x[0] is not tokenize.NL, src)
res = atom(src.next, src.next())
if src.next()[0] is not tokenize.ENDMARKER:
raise SyntaxError("bogus data after expression")
return res
if __name__ == '__main__':
expr = (1, 2.3, u'h\xf8h\n', 'h\xc3\xa6', ['a', 1],
{'list': [], 'tuple': (), 'dict': {}}, False, True, None)
rexpr = repr(expr)
a = simple_eval(rexpr)
b = eval(rexpr)
assert a == b
import timeit
print timeit.Timer('eval(rexpr)', 'from __main__ import
rexpr').repeat(number=1000)
print timeit.Timer('simple_eval(rexpr)', 'from __main__ import
rexpr, simple_eval').repeat(number=1000)
--
http://mail.python.org/mailman/listinfo/python-list
