>>> timeit.timeit("'x' in ('x',)")
0.04869917374131205
>>> timeit.timeit("'x' == 'x'")
0.06144205736110564
也适用于具有多个元素的元组，两个版本似乎都是线性增长的:
>>> timeit.timeit("'x' in ('x', 'y')")
0.04866674801541748
>>> timeit.timeit("'x' == 'x' or 'x' == 'y'")
0.06565782838087131
>>> timeit.timeit("'x' in ('y', 'x')")
0.08975995576448526
>>> timeit.timeit("'x' == 'y' or 'x' == 'y'")
0.12992391047427532
基于此，我认为我应该完全开始在任何地方使用 in 而不是 ==!
最佳答案
正如我向 David Wolever 提到的，这不仅仅是表面上看到的；两种方法都派发到 is;你可以通过这样做来证明这一点
min(Timer("x == x", setup="x = 'a' * 1000000").repeat(10, 10000))
#>>> 0.00045456900261342525
min(Timer("x == y", setup="x = 'a' * 1000000; y = 'a' * 1000000").repeat(10, 10000))
#>>> 0.5256857610074803
第一个只能这么快，因为它通过身份检查。
要找出为什么一个会比另一个花更长的时间，让我们跟踪执行。
它们都从 ceval.c 开始，从 COMPARE_OP 因为这是涉及的字节码
TARGET(COMPARE_OP) {
PyObject *right = POP();
PyObject *left = TOP();
PyObject *res = cmp_outcome(oparg, left, right);
Py_DECREF(left);
Py_DECREF(right);
SET_TOP(res);
if (res == NULL)
goto error;
PREDICT(POP_JUMP_IF_FALSE);
PREDICT(POP_JUMP_IF_TRUE);
DISPATCH();
}
这会从堆栈中弹出值(从技术上讲，它只会弹出一个)
PyObject *right = POP();
PyObject *left = TOP();
并运行比较:
PyObject *res = cmp_outcome(oparg, left, right);
cmp_outcome是这样的:
static PyObject *
cmp_outcome(int op, PyObject *v, PyObject *w)
{
int res = 0;
switch (op) {
case PyCmp_IS: ...
case PyCmp_IS_NOT: ...
case PyCmp_IN:
res = PySequence_Contains(w, v);
if (res < 0)
return NULL;
break;
case PyCmp_NOT_IN: ...
case PyCmp_EXC_MATCH: ...
default:
return PyObject_RichCompare(v, w, op);
}
v = res ? Py_True : Py_False;
Py_INCREF(v);
return v;
}
这是路径 split 的地方。 PyCmp_IN 分支确实
int
PySequence_Contains(PyObject *seq, PyObject *ob)
{
Py_ssize_t result;
PySequenceMethods *sqm = seq->ob_type->tp_as_sequence;
if (sqm != NULL && sqm->sq_contains != NULL)
return (*sqm->sq_contains)(seq, ob);
result = _PySequence_IterSearch(seq, ob, PY_ITERSEARCH_CONTAINS);
return Py_SAFE_DOWNCAST(result, Py_ssize_t, int);
}
注意，元组被定义为
static PySequenceMethods tuple_as_sequence = {
...
(objobjproc)tuplecontains, /* sq_contains */
};
PyTypeObject PyTuple_Type = {
...
&tuple_as_sequence, /* tp_as_sequence */
...
};
所以分支
if (sqm != NULL && sqm->sq_contains != NULL)
将被取走，*sqm->sq_contains，即函数(objobjproc)tuplecontains，将被取走。
这样
static int
tuplecontains(PyTupleObject *a, PyObject *el)
{
Py_ssize_t i;
int cmp;
for (i = 0, cmp = 0 ; cmp == 0 && i < Py_SIZE(a); ++i)
cmp = PyObject_RichCompareBool(el, PyTuple_GET_ITEM(a, i),
Py_EQ);
return cmp;
}
...等等，那 PyObject_RichCompareBool 不是其他分支所采用的吗？不，那是 PyObject_RichCompare。
该代码路径很短，因此很可能归结为这两个的速度。比较一下吧。
int
PyObject_RichCompareBool(PyObject *v, PyObject *w, int op)
{
PyObject *res;
int ok;
/* Quick result when objects are the same.
Guarantees that identity implies equality. */
if (v == w) {
if (op == Py_EQ)
return 1;
else if (op == Py_NE)
return 0;
}
...
}
PyObject_RichCompareBool 中的代码路径几乎立即终止。对于 PyObject_RichCompare，确实如此
PyObject *
PyObject_RichCompare(PyObject *v, PyObject *w, int op)
{
PyObject *res;
assert(Py_LT <= op && op <= Py_GE);
if (v == NULL || w == NULL) { ... }
if (Py_EnterRecursiveCall(" in comparison"))
return NULL;
res = do_richcompare(v, w, op);
Py_LeaveRecursiveCall();
return res;
}
Py_EnterRecursiveCall/Py_LeaveRecursiveCall 组合没有在前面的路径中采用，但这些是相对快速的宏，在递增和递减一些全局变量后会短路。
do_richcompare 做:
static PyObject *
do_richcompare(PyObject *v, PyObject *w, int op)
{
richcmpfunc f;
PyObject *res;
int checked_reverse_op = 0;
if (v->ob_type != w->ob_type && ...) { ... }
if ((f = v->ob_type->tp_richcompare) != NULL) {
res = (*f)(v, w, op);
if (res != Py_NotImplemented)
return res;
...
}
...
}
这会进行一些快速检查以调用 v->ob_type->tp_richcompare 这是
PyTypeObject PyUnicode_Type = {
...
PyUnicode_RichCompare, /* tp_richcompare */
...
};
会的
PyObject *
PyUnicode_RichCompare(PyObject *left, PyObject *right, int op)
{
int result;
PyObject *v;
if (!PyUnicode_Check(left) || !PyUnicode_Check(right))
Py_RETURN_NOTIMPLEMENTED;
if (PyUnicode_READY(left) == -1 ||
PyUnicode_READY(right) == -1)
return NULL;
if (left == right) {
switch (op) {
case Py_EQ:
case Py_LE:
case Py_GE:
/* a string is equal to itself */
v = Py_True;
break;
case Py_NE:
case Py_LT:
case Py_GT:
v = Py_False;
break;
default:
...
}
}
else if (...) { ... }
else { ...}
Py_INCREF(v);
return v;
}
即，left == right 上的此快捷方式...但仅在执行之后
if (!PyUnicode_Check(left) || !PyUnicode_Check(right))
if (PyUnicode_READY(left) == -1 ||
PyUnicode_READY(right) == -1)
所有路径看起来都像这样(手动递归内联、展开和修剪已知分支)
POP() # Stack stuff
TOP() #
#
case PyCmp_IN: # Dispatch on operation
#
sqm != NULL # Dispatch to builtin op
sqm->sq_contains != NULL #
*sqm->sq_contains #
#
cmp == 0 # Do comparison in loop
i < Py_SIZE(a) #
v == w #
op == Py_EQ #
++i #
cmp == 0 #
#
res < 0 # Convert to Python-space
res ? Py_True : Py_False #
Py_INCREF(v) #
#
Py_DECREF(left) # Stack stuff
Py_DECREF(right) #
SET_TOP(res) #
res == NULL #
DISPATCH() #
对
POP() # Stack stuff
TOP() #
#
default: # Dispatch on operation
#
Py_LT <= op # Checking operation
op <= Py_GE #
v == NULL #
w == NULL #
Py_EnterRecursiveCall(...) # Recursive check
#
v->ob_type != w->ob_type # More operation checks
f = v->ob_type->tp_richcompare # Dispatch to builtin op
f != NULL #
#
!PyUnicode_Check(left) # ...More checks
!PyUnicode_Check(right)) #
PyUnicode_READY(left) == -1 #
PyUnicode_READY(right) == -1 #
left == right # Finally, doing comparison
case Py_EQ: # Immediately short circuit
Py_INCREF(v); #
#
res != Py_NotImplemented #
#
Py_LeaveRecursiveCall() # Recursive check
#
Py_DECREF(left) # Stack stuff
Py_DECREF(right) #
SET_TOP(res) #
res == NULL #
DISPATCH() #
现在，PyUnicode_Check 和 PyUnicode_READY 非常便宜，因为它们只检查几个字段，但很明显，最上面的一个是较小的代码路径，它函数调用更少，只有一个开关
声明，只是有点薄。
TL;DR:
两者都调度到 if (left_pointer == right_pointer);不同之处在于他们为到达那里做了多少工作。 in 只是做的更少。
关于python - 为什么 'x' 中的 ('x' 比 'x' == 'x' 快？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/28885132/