python 自定义类型_2. 自定义扩展类型：教程

2.2.Adding data and methods to the Basic example¶

Let's extend the basic example to add some data and methods. Let's also make

the type usable as a base class. We'll create a new module, custom2 that

adds these capabilities:

#define PY_SSIZE_T_CLEAN

#include

#include "structmember.h"

typedef struct {

PyObject_HEAD

PyObject *first; /* first name */

PyObject *last; /* last name */

int number;

} CustomObject;

static void

Custom_dealloc(CustomObject *self)

{

Py_XDECREF(self->first);

Py_XDECREF(self->last);

Py_TYPE(self)->tp_free((PyObject *) self);

}

static PyObject *

Custom_new(PyTypeObject *type, PyObject *args, PyObject *kwds)

{

CustomObject *self;

self = (CustomObject *) type->tp_alloc(type, 0);

if (self != NULL) {

self->first = PyUnicode_FromString("");

if (self->first == NULL) {

Py_DECREF(self);

return NULL;

}

self->last = PyUnicode_FromString("");

if (self->last == NULL) {

Py_DECREF(self);

return NULL;

}

self->number = 0;

}

return (PyObject *) self;

}

static int

Custom_init(CustomObject *self, PyObject *args, PyObject *kwds)

{

static char *kwlist[] = {"first", "last", "number", NULL};

PyObject *first = NULL, *last = NULL, *tmp;

if (!PyArg_ParseTupleAndKeywords(args, kwds, "|OOi", kwlist,

&first, &last,

&self->number))

return -1;

if (first) {

tmp = self->first;

Py_INCREF(first);

self->first = first;

Py_XDECREF(tmp);

}

if (last) {

tmp = self->last;

Py_INCREF(last);

self->last = last;

Py_XDECREF(tmp);

}

return 0;

}

static PyMemberDef Custom_members[] = {

{"first", T_OBJECT_EX, offsetof(CustomObject, first), 0,

"first name"},

{"last", T_OBJECT_EX, offsetof(CustomObject, last), 0,

"last name"},

{"number", T_INT, offsetof(CustomObject, number), 0,

"custom number"},

{NULL} /* Sentinel */

};

static PyObject *

Custom_name(CustomObject *self, PyObject *Py_UNUSED(ignored))

{

if (self->first == NULL) {

PyErr_SetString(PyExc_AttributeError, "first");

return NULL;

}

if (self->last == NULL) {

PyErr_SetString(PyExc_AttributeError, "last");

return NULL;

}

return PyUnicode_FromFormat("%S %S", self->first, self->last);

}

static PyMethodDef Custom_methods[] = {

{"name", (PyCFunction) Custom_name, METH_NOARGS,

"Return the name, combining the first and last name"

},

{NULL} /* Sentinel */

};

static PyTypeObject CustomType = {

PyVarObject_HEAD_INIT(NULL, 0)

.tp_name = "custom2.Custom",

.tp_doc = "Custom objects",

.tp_basicsize = sizeof(CustomObject),

.tp_itemsize = 0,

.tp_flags = Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE,

.tp_new = Custom_new,

.tp_init = (initproc) Custom_init,

.tp_dealloc = (destructor) Custom_dealloc,

.tp_members = Custom_members,

.tp_methods = Custom_methods,

};

static PyModuleDef custommodule = {

PyModuleDef_HEAD_INIT,

.m_name = "custom2",

.m_doc = "Example module that creates an extension type.",

.m_size = -1,

};

PyMODINIT_FUNC

PyInit_custom2(void)

{

PyObject *m;

if (PyType_Ready(&CustomType) < 0)

return NULL;

m = PyModule_Create(&custommodule);

if (m == NULL)

return NULL;

Py_INCREF(&CustomType);

if (PyModule_AddObject(m, "Custom", (PyObject *) &CustomType) < 0) {

Py_DECREF(&CustomType);

Py_DECREF(m);

return NULL;

}

return m;

}

This version of the module has a number of changes.

We've added an extra include:

#include

This include provides declarations that we use to handle attributes, as

described a bit later.

The Custom type now has three data attributes in its C struct,

first, last, and number. The first and last variables are Python

strings containing first and last names. The number attribute is a C integer.

The object structure is updated accordingly:

typedef struct {

PyObject_HEAD

PyObject *first; /* first name */

PyObject *last; /* last name */

int number;

} CustomObject;

Because we now have data to manage, we have to be more careful about object

allocation and deallocation. At a minimum, we need a deallocation method:

static void

Custom_dealloc(CustomObject *self)

{

Py_XDECREF(self->first);

Py_XDECREF(self->last);

Py_TYPE(self)->tp_free((PyObject *) self);

}

which is assigned to the tp_dealloc member:

.tp_dealloc = (destructor) Custom_dealloc,

This method first clears the reference counts of the two Python attributes.

Py_XDECREF() correctly handles the case where its argument is

NULL (which might happen here if tp_new failed midway). It then

calls the tp_free member of the object's type

(computed by Py_TYPE(self)) to free the object's memory. Note that

the object's type might not be CustomType, because the object may

be an instance of a subclass.

注解

The explicit cast to destructor above is needed because we defined

Custom_dealloc to take a CustomObject * argument, but the tp_dealloc

function pointer expects to receive a PyObject * argument. Otherwise,

the compiler will emit a warning. This is object-oriented polymorphism,

in C!

We want to make sure that the first and last names are initialized to empty

strings, so we provide a tp_new implementation:

static PyObject *

Custom_new(PyTypeObject *type, PyObject *args, PyObject *kwds)

{

CustomObject *self;

self = (CustomObject *) type->tp_alloc(type, 0);

if (self != NULL) {

self->first = PyUnicode_FromString("");

if (self->first == NULL) {

Py_DECREF(self);

return NULL;

}

self->last = PyUnicode_FromString("");

if (self->last == NULL) {

Py_DECREF(self);

return NULL;

}

self->number = 0;

}

return (PyObject *) self;

}

and install it in the tp_new member:

.tp_new = Custom_new,

The tp_new handler is responsible for creating (as opposed to initializing)

objects of the type. It is exposed in Python as the __new__() method.

It is not required to define a tp_new member, and indeed many extension

types will simply reuse PyType_GenericNew() as done in the first

version of the Custom type above. In this case, we use the tp_new

handler to initialize the first and last attributes to non-NULL

default values.

tp_new is passed the type being instantiated (not necessarily CustomType,

if a subclass is instantiated) and any arguments passed when the type was

called, and is expected to return the instance created. tp_new handlers

always accept positional and keyword arguments, but they often ignore the

arguments, leaving the argument handling to initializer (a.k.a. tp_init

in C or __init__ in Python) methods.

注解

tp_new shouldn't call tp_init explicitly, as the interpreter

will do it itself.

The tp_new implementation calls the tp_alloc

slot to allocate memory:

self = (CustomObject *) type->tp_alloc(type, 0);

Since memory allocation may fail, we must check the tp_alloc

result against NULL before proceeding.

注解

We didn't fill the tp_alloc slot ourselves. Rather

PyType_Ready() fills it for us by inheriting it from our base class,

which is object by default. Most types use the default allocation

strategy.

注解

If you are creating a co-operative tp_new (one

that calls a base type's tp_new or __new__()),

you must not try to determine what method to call using method resolution

order at runtime. Always statically determine what type you are going to

call, and call its tp_new directly, or via

type->tp_base->tp_new. If you do not do this, Python subclasses of your

type that also inherit from other Python-defined classes may not work correctly.

(Specifically, you may not be able to create instances of such subclasses

without getting a TypeError.)

We also define an initialization function which accepts arguments to provide

initial values for our instance:

static int

Custom_init(CustomObject *self, PyObject *args, PyObject *kwds)

{

static char *kwlist[] = {"first", "last", "number", NULL};

PyObject *first = NULL, *last = NULL, *tmp;

if (!PyArg_ParseTupleAndKeywords(args, kwds, "|OOi", kwlist,

&first, &last,

&self->number))

return -1;

if (first) {

tmp = self->first;

Py_INCREF(first);

self->first = first;

Py_XDECREF(tmp);

}

if (last) {

tmp = self->last;

Py_INCREF(last);

self->last = last;

Py_XDECREF(tmp);

}

return 0;

}

by filling the tp_init slot.

.tp_init = (initproc) Custom_init,

The tp_init slot is exposed in Python as the

__init__() method. It is used to initialize an object after it's

created. Initializers always accept positional and keyword arguments,

and they should return either 0 on success or -1 on error.

Unlike the tp_new handler, there is no guarantee that tp_init

is called at all (for example, the pickle module by default

doesn't call __init__() on unpickled instances). It can also be

called multiple times. Anyone can call the __init__() method on

our objects. For this reason, we have to be extra careful when assigning

the new attribute values. We might be tempted, for example to assign the

first member like this:

if (first) {

Py_XDECREF(self->first);

Py_INCREF(first);

self->first = first;

}

But this would be risky. Our type doesn't restrict the type of the

first member, so it could be any kind of object. It could have a

destructor that causes code to be executed that tries to access the

first member; or that destructor could release the

Global interpreter Lock and let arbitrary code run in other

threads that accesses and modifies our object.

To be paranoid and protect ourselves against this possibility, we almost

always reassign members before decrementing their reference counts. When

don't we have to do this?

when we absolutely know that the reference count is greater than 1;

when we know that deallocation of the object 1 will neither release

the GIL nor cause any calls back into our type's code;

when decrementing a reference count in a tp_dealloc

handler on a type which doesn't support cyclic garbage collection 2.

We want to expose our instance variables as attributes. There are a

number of ways to do that. The simplest way is to define member definitions:

static PyMemberDef Custom_members[] = {

{"first", T_OBJECT_EX, offsetof(CustomObject, first), 0,

"first name"},

{"last", T_OBJECT_EX, offsetof(CustomObject, last), 0,

"last name"},

{"number", T_INT, offsetof(CustomObject, number), 0,

"custom number"},

{NULL} /* Sentinel */

};

and put the definitions in the tp_members slot:

.tp_members = Custom_members,

Each member definition has a member name, type, offset, access flags and

documentation string. See the 泛型属性管理 section

below for details.

A disadvantage of this approach is that it doesn't provide a way to restrict the

types of objects that can be assigned to the Python attributes. We expect the

first and last names to be strings, but any Python objects can be assigned.

Further, the attributes can be deleted, setting the C pointers to NULL. Even

though we can make sure the members are initialized to non-NULL values, the

members can be set to NULL if the attributes are deleted.

We define a single method, Custom.name(), that outputs the objects name as the

concatenation of the first and last names.

static PyObject *

Custom_name(CustomObject *self, PyObject *Py_UNUSED(ignored))

{

if (self->first == NULL) {

PyErr_SetString(PyExc_AttributeError, "first");

return NULL;

}

if (self->last == NULL) {

PyErr_SetString(PyExc_AttributeError, "last");

return NULL;

}

return PyUnicode_FromFormat("%S %S", self->first, self->last);

}

The method is implemented as a C function that takes a Custom (or

Custom subclass) instance as the first argument. Methods always take an

instance as the first argument. Methods often take positional and keyword

arguments as well, but in this case we don't take any and don't need to accept

a positional argument tuple or keyword argument dictionary. This method is

equivalent to the Python method:

def name(self):

return "%s%s" % (self.first, self.last)

Note that we have to check for the possibility that our first and

last members are NULL. This is because they can be deleted, in which

case they are set to NULL. It would be better to prevent deletion of these

attributes and to restrict the attribute values to be strings. We'll see how to

do that in the next section.

Now that we've defined the method, we need to create an array of method

definitions:

static PyMethodDef Custom_methods[] = {

{"name", (PyCFunction) Custom_name, METH_NOARGS,

"Return the name, combining the first and last name"

},

{NULL} /* Sentinel */

};

(note that we used the METH_NOARGS flag to indicate that the method

is expecting no arguments other than self)

and assign it to the tp_methods slot:

.tp_methods = Custom_methods,

Finally, we'll make our type usable as a base class for subclassing. We've

written our methods carefully so far so that they don't make any assumptions

about the type of the object being created or used, so all we need to do is

to add the Py_TPFLAGS_BASETYPE to our class flag definition:

.tp_flags = Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE,

We rename PyInit_custom() to PyInit_custom2(), update the

module name in the PyModuleDef struct, and update the full class

name in the PyTypeObject struct.

Finally, we update our setup.py file to build the new module:

from distutils.core import setup, Extension

setup(name="custom", version="1.0",

ext_modules=[

Extension("custom", ["custom.c"]),

Extension("custom2", ["custom2.c"]),

])