阅读该dis
模块的源代码,您会发现很容易进行自己的反汇编并生成您喜欢的任何输出格式。下面是一些在代码对象中生成指令序列的代码,以及它们的参数:
from opcode import *
def disassemble(co):
"""
Disassemble a code object and generate its instructions.
"""
code = co.co_code
n = len(code)
extended_arg = 0
i = 0
free = None
while i < n:
c = code[i]
op = ord(c)
i = i+1
if op < HAVE_ARGUMENT:
yield opname[op],
else:
oparg = ord(code[i]) + ord(code[i+1])*256 + extended_arg
extended_arg = 0
i = i+2
if op == EXTENDED_ARG:
extended_arg = oparg*65536L
if op in hasconst:
arg = co.co_consts[oparg]
elif op in hasname:
arg = co.co_names[oparg]
elif op in hasjrel:
arg = repr(i + oparg)
elif op in haslocal:
arg = co.co_varnames[oparg]
elif op in hascompare:
arg = cmp_op[oparg]
elif op in hasfree:
if free is None:
free = co.co_cellvars + co.co_freevars
arg = free[oparg]
else:
arg = oparg
yield opname[op], arg
这是一个反汇编示例。
>>> def f(x):
... return x + 1
...
>>> list(disassemble(f.func_code))
[('LOAD_FAST', 'x'), ('LOAD_CONST', 1), ('BINARY_ADD',), ('RETURN_VALUE',)]
您可以轻松地将其转换为所需的字典集数据结构:
>>> from collections import defaultdict
>>> d = defaultdict(set)
>>> for op in disassemble(f.func_code):
... if len(op) == 2:
... d[op[0]].add(op[1])
...
>>> d
defaultdict(<type 'set'>, {'LOAD_FAST': set(['x']), 'LOAD_CONST': set([1])})
(或者您可以直接生成字典集数据结构。)
请注意,在您的应用程序中,您实际上可能不需要查找每个操作码的名称。相反,您可以在opcode.opmap
字典中查找所需的操作码并创建命名常量,可能像这样:
LOAD_FAST = opmap['LOAD_FAST'] # actual value is 124
...
for var in disassembly[LOAD_FAST]:
...
更新:在 Python 3.4 中,您可以使用新的dis.get_instructions
:
>>> def f(x):
... return x + 1
>>> import dis
>>> list(dis.get_instructions(f))
[Instruction(opname='LOAD_FAST', opcode=124, arg=0, argval='x',
argrepr='x', offset=0, starts_line=1, is_jump_target=False),
Instruction(opname='LOAD_CONST', opcode=100, arg=1, argval=1,
argrepr='1', offset=3, starts_line=None, is_jump_target=False),
Instruction(opname='BINARY_ADD', opcode=23, arg=None, argval=None,
argrepr='', offset=6, starts_line=None, is_jump_target=False),
Instruction(opname='RETURN_VALUE', opcode=83, arg=None, argval=None,
argrepr='', offset=7, starts_line=None, is_jump_target=False)]