为什么在('x'，)中的'x'比'x'=='x'快？

Question

>>> timeit.timeit("'x' in ('x',)")
0.04869917374131205
>>> timeit.timeit("'x' == 'x'")
0.06144205736110564

>>> 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中使用，而不是==！




Answer 1

正如我向大卫·沃尔弗提到的，这不仅仅是表面上的；分派到的两个方法都是；你可以通过做来证明这一点

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

第一个可以这么快，因为它是通过身份进行检查的。

为了找出为什么一个比另一个要花更长的时间，让我们通过执行来跟踪。

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();
}

PyObject *right = POP();
PyObject *left = TOP();

PyObject *res = cmp_outcome(oparg, left, right);

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;
}

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);
}

static PySequenceMethods tuple_as_sequence = {
    ...
    (objobjproc)tuplecontains,                  /* sq_contains */
};

PyTypeObject PyTuple_Type = {
    ...
    &tuple_as_sequence,                         /* tp_as_sequence */
    ...
};

if (sqm != NULL && sqm->sq_contains != NULL)

将接受*sqm->sq_contains，它是函数(objobjproc)tuplecontains。

这是

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，另一个分支不是拿了pyobject_richcomparebool吗？不，是pyobject_richcompare。

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 *
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;
}

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;
        ...
    }
    ...
}

这将执行一些快速检查以调用v->ob_type->tp_richcompare，其为

PyTypeObject PyUnicode_Type = {
    ...
    PyUnicode_RichCompare,      /* tp_richcompare */
    ...
};

哪个有

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;
}

也就是说，left==right...但只有在做了

    if (!PyUnicode_Check(left) || !PyUnicode_Check(right))

    if (PyUnicode_READY(left) == -1 ||
        PyUnicode_READY(right) == -1)

总之，所有路径看起来如下所示（手动递归地内联、展开和剪枝已知分支）

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()                      #

VS

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，但是很明显，最上面的一个字段是一个更小的代码路径，它有更少的函数调用，只有一个switch语句，而且稍微薄一点。